Try to catch "data lost during self-heal"

2024-02-21 19:24:36 +03:00
320 changed files with 4300 additions and 21905 deletions
--- a/.gitea/workflows/buildenv.Dockerfile
+++ b/.gitea/workflows/buildenv.Dockerfile
@ -22,7 +22,7 @@ RUN apt-get update
 RUN apt-get -y install etcd qemu-system-x86 qemu-block-extra qemu-utils fio libasan5 \
    liburing1 liburing-dev libgoogle-perftools-dev devscripts libjerasure-dev cmake libibverbs-dev libisal-dev
 RUN apt-get -y build-dep fio qemu=`dpkg -s qemu-system-x86|grep ^Version:|awk '{print $2}'`
-RUN apt-get -y install jq lp-solve sudo nfs-common
+RUN apt-get -y install jq lp-solve sudo
 RUN apt-get --download-only source fio qemu=`dpkg -s qemu-system-x86|grep ^Version:|awk '{print $2}'`
 RUN set -ex; \
--- a/.gitea/workflows/test.yml
+++ b/.gitea/workflows/test.yml
@ -64,571 +64,6 @@ jobs:
    # leak sanitizer sometimes crashes
    - run: cd /root/vitastor/build && ASAN_OPTIONS=detect_leaks=0 make -j16 test
  npm_lint:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - run: cd /root/vitastor/mon && npm run lint
  test_add_osd:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 10
      run: /root/vitastor/tests/test_add_osd.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_cas:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_cas.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_change_pg_count:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_change_pg_count.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_change_pg_count_ec:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: SCHEME=ec /root/vitastor/tests/test_change_pg_count.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_change_pg_size:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_change_pg_size.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_create_nomaxid:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_create_nomaxid.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_etcd_fail:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 10
      run: /root/vitastor/tests/test_etcd_fail.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_interrupted_rebalance:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 10
      run: /root/vitastor/tests/test_interrupted_rebalance.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_interrupted_rebalance_imm:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 10
      run: IMMEDIATE_COMMIT=1 /root/vitastor/tests/test_interrupted_rebalance.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_interrupted_rebalance_ec:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 10
      run: SCHEME=ec /root/vitastor/tests/test_interrupted_rebalance.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_interrupted_rebalance_ec_imm:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 10
      run: SCHEME=ec IMMEDIATE_COMMIT=1 /root/vitastor/tests/test_interrupted_rebalance.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_failure_domain:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_failure_domain.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_snapshot:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_snapshot.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_snapshot_ec:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: SCHEME=ec /root/vitastor/tests/test_snapshot.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_minsize_1:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_minsize_1.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_move_reappear:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_move_reappear.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_rm:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_rm.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_snapshot_chain:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_snapshot_chain.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_snapshot_chain_ec:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 6
      run: SCHEME=ec /root/vitastor/tests/test_snapshot_chain.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_snapshot_down:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_snapshot_down.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_snapshot_down_ec:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: SCHEME=ec /root/vitastor/tests/test_snapshot_down.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_splitbrain:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_splitbrain.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_rebalance_verify:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 10
      run: /root/vitastor/tests/test_rebalance_verify.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_rebalance_verify_imm:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 10
      run: IMMEDIATE_COMMIT=1 /root/vitastor/tests/test_rebalance_verify.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_rebalance_verify_ec:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 10
      run: SCHEME=ec /root/vitastor/tests/test_rebalance_verify.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_rebalance_verify_ec_imm:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 10
      run: SCHEME=ec IMMEDIATE_COMMIT=1 /root/vitastor/tests/test_rebalance_verify.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_root_node:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_root_node.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_switch_primary:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_switch_primary.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_write:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_write.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_write_xor:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: SCHEME=xor /root/vitastor/tests/test_write.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_write_no_same:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_write_no_same.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_heal_pg_size_2:
    runs-on: ubuntu-latest
    needs: build
@ -636,7 +71,7 @@ jobs:
    steps:
    - name: Run test
      id: test
-      timeout-minutes: 10
+      timeout-minutes: 1000
      run: PG_SIZE=2 /root/vitastor/tests/test_heal.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
@ -654,7 +89,7 @@ jobs:
    steps:
    - name: Run test
      id: test
-      timeout-minutes: 10
+      timeout-minutes: 1000
      run: SCHEME=ec /root/vitastor/tests/test_heal.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
@ -672,7 +107,7 @@ jobs:
    steps:
    - name: Run test
      id: test
-      timeout-minutes: 10
+      timeout-minutes: 1000
      run: TEST_NAME=csum_32k_dmj OSD_ARGS="--data_csum_type crc32c --csum_block_size 32k --inmemory_metadata false --inmemory_journal false" OFFSET_ARGS=$OSD_ARGS /root/vitastor/tests/test_heal.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
@ -690,7 +125,7 @@ jobs:
    steps:
    - name: Run test
      id: test
-      timeout-minutes: 10
+      timeout-minutes: 1000
      run: TEST_NAME=csum_32k_dj  OSD_ARGS="--data_csum_type crc32c --csum_block_size 32k --inmemory_journal false" OFFSET_ARGS=$OSD_ARGS /root/vitastor/tests/test_heal.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
@ -708,7 +143,7 @@ jobs:
    steps:
    - name: Run test
      id: test
-      timeout-minutes: 10
+      timeout-minutes: 1000
      run: TEST_NAME=csum_32k     OSD_ARGS="--data_csum_type crc32c --csum_block_size 32k" OFFSET_ARGS=$OSD_ARGS /root/vitastor/tests/test_heal.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
@ -726,7 +161,7 @@ jobs:
    steps:
    - name: Run test
      id: test
-      timeout-minutes: 10
+      timeout-minutes: 1000
      run: TEST_NAME=csum_4k_dmj  OSD_ARGS="--data_csum_type crc32c --inmemory_metadata false --inmemory_journal false" OFFSET_ARGS=$OSD_ARGS /root/vitastor/tests/test_heal.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
@ -744,7 +179,7 @@ jobs:
    steps:
    - name: Run test
      id: test
-      timeout-minutes: 10
+      timeout-minutes: 1000
      run: TEST_NAME=csum_4k_dj   OSD_ARGS="--data_csum_type crc32c --inmemory_journal false" OFFSET_ARGS=$OSD_ARGS /root/vitastor/tests/test_heal.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
@ -762,7 +197,7 @@ jobs:
    steps:
    - name: Run test
      id: test
-      timeout-minutes: 10
+      timeout-minutes: 1000
      run: TEST_NAME=csum_4k      OSD_ARGS="--data_csum_type crc32c" OFFSET_ARGS=$OSD_ARGS /root/vitastor/tests/test_heal.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
@ -772,220 +207,3 @@ jobs:
          cat $i
          echo ""
        done
  test_osd_tags:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_osd_tags.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_enospc:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_enospc.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_enospc_xor:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: SCHEME=xor /root/vitastor/tests/test_enospc.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_enospc_imm:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: IMMEDIATE_COMMIT=1 /root/vitastor/tests/test_enospc.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_enospc_imm_xor:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: IMMEDIATE_COMMIT=1 SCHEME=xor /root/vitastor/tests/test_enospc.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_scrub:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_scrub.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_scrub_zero_osd_2:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: ZERO_OSD=2 /root/vitastor/tests/test_scrub.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_scrub_xor:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: SCHEME=xor /root/vitastor/tests/test_scrub.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_scrub_pg_size_3:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: PG_SIZE=3 /root/vitastor/tests/test_scrub.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_scrub_pg_size_6_pg_minsize_4_osd_count_6_ec:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: PG_SIZE=6 PG_MINSIZE=4 OSD_COUNT=6 SCHEME=ec /root/vitastor/tests/test_scrub.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_scrub_ec:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: SCHEME=ec /root/vitastor/tests/test_scrub.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
  test_nfs:
    runs-on: ubuntu-latest
    needs: build
    container: ${{env.TEST_IMAGE}}:${{github.sha}}
    steps:
    - name: Run test
      id: test
      timeout-minutes: 3
      run: /root/vitastor/tests/test_nfs.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
      run: |
        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
          echo "-------- $i --------"
          cat $i
          echo ""
        done
--- a/.gitignore
+++ b/.gitignore
@ -3,3 +3,16 @@
 package-lock.json
 fio
 qemu
 osd
 stub_osd
 stub_uring_osd
 stub_bench
 osd_test
 osd_peering_pg_test
 dump_journal
 nbd_proxy
 rm_inode
 test_allocator
 test_blockstore
 test_shit
 osd_rmw_test
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8.12)
 project(vitastor)
-set(VERSION "1.6.1")
+set(VERSION "1.4.6")
 add_subdirectory(src)
--- a/README-ru.md
+++ b/README-ru.md
@ -6,8 +6,8 @@
 Вернём былую скорость кластерному блочному хранилищу!
-Vitastor - распределённая блочная и файловая SDS (программная СХД), прямой аналог Ceph RBD и CephFS,
+Vitastor - распределённая блочная SDS (программная СХД), прямой аналог Ceph RBD и
-а также внутренних СХД популярных облачных провайдеров. Однако, в отличие от них, Vitastor
+внутренних СХД популярных облачных провайдеров. Однако, в отличие от них, Vitastor
 быстрый и при этом простой. Только пока маленький :-).
 Vitastor архитектурно похож на Ceph, что означает атомарность и строгую консистентность,
@ -63,13 +63,11 @@ Vitastor поддерживает QEMU-драйвер, протоколы NBD и
  - [fio](docs/usage/fio.ru.md) для тестов производительности
  - [NBD](docs/usage/nbd.ru.md) для монтирования ядром
  - [QEMU и qemu-img](docs/usage/qemu.ru.md)
-  - [NFS](docs/usage/nfs.ru.md) кластерная файловая система и псевдо-ФС прокси
+  - [NFS](docs/usage/nfs.ru.md)-прокси для VMWare и подобных
  - [Администрирование](docs/usage/admin.ru.md)
 - Производительность
  - [Понимание сути производительности](docs/performance/understanding.ru.md)
  - [Теоретический максимум](docs/performance/theoretical.ru.md)
  - [Пример сравнения с Ceph](docs/performance/comparison1.ru.md)
  - [Более новый тест Vitastor 1.3.1](docs/performance/bench2.ru.md)
 ## Автор и лицензия
--- a/README.md
+++ b/README.md
@ -6,9 +6,9 @@
 Make Clustered Block Storage Fast Again.
-Vitastor is a distributed block and file SDS, direct replacement of Ceph RBD and CephFS,
+Vitastor is a distributed block SDS, direct replacement of Ceph RBD and internal SDS's
-and also internal SDS's of public clouds. However, in contrast to them, Vitastor is fast
+of public clouds. However, in contrast to them, Vitastor is fast and simple at the same time.
-and simple at the same time. The only thing is it's slightly young :-).
+The only thing is it's slightly young :-).
 Vitastor is architecturally similar to Ceph which means strong consistency,
 primary-replication, symmetric clustering and automatic data distribution over any
@ -63,13 +63,11 @@ Read more details below in the documentation.
  - [fio](docs/usage/fio.en.md) for benchmarks
  - [NBD](docs/usage/nbd.en.md) for kernel mounts
  - [QEMU and qemu-img](docs/usage/qemu.en.md)
-  - [NFS](docs/usage/nfs.en.md) clustered file system and pseudo-FS proxy
+  - [NFS](docs/usage/nfs.en.md) emulator for VMWare and similar
  - [Administration](docs/usage/admin.en.md)
 - Performance
  - [Understanding storage performance](docs/performance/understanding.en.md)
  - [Theoretical performance](docs/performance/theoretical.en.md)
  - [Example comparison with Ceph](docs/performance/comparison1.en.md)
  - [Newer benchmark of Vitastor 1.3.1](docs/performance/bench2.en.md)
 ## Author and License
--- a/copy-fio-includes.sh
+++ b/copy-fio-includes.sh
@ -1,6 +1,6 @@
 #!/bin/bash
-gcc -I. -E -o fio_headers.i src/util/fio_headers.h
+gcc -I. -E -o fio_headers.i src/fio_headers.h
 rm -rf fio-copy
 for i in `grep -Po 'fio/[^"]+' fio_headers.i | sort | uniq`; do
--- a/copy-qemu-includes.sh
+++ b/copy-qemu-includes.sh
@ -5,7 +5,7 @@
 #cd b/qemu; make qapi
 gcc -I qemu/b/qemu `pkg-config glib-2.0 --cflags` \
-    -I qemu/include -E -o qemu_driver.i src/client/qemu_driver.c
+    -I qemu/include -E -o qemu_driver.i src/qemu_driver.c
 rm -rf qemu-copy
 for i in `grep -Po 'qemu/[^"]+' qemu_driver.i | sort | uniq`; do
--- a/csi/Makefile
+++ b/csi/Makefile
@ -1,4 +1,4 @@
-VERSION ?= v1.6.1
+VERSION ?= v1.4.6
 all: build push
--- a/csi/deploy/004-csi-nodeplugin.yaml
+++ b/csi/deploy/004-csi-nodeplugin.yaml
@ -49,7 +49,7 @@ spec:
            capabilities:
              add: ["SYS_ADMIN"]
            allowPrivilegeEscalation: true
-          image: vitalif/vitastor-csi:v1.6.1
+          image: vitalif/vitastor-csi:v1.4.6
          args:
            - "--node=$(NODE_ID)"
            - "--endpoint=$(CSI_ENDPOINT)"
--- a/csi/deploy/007-csi-provisioner.yaml
+++ b/csi/deploy/007-csi-provisioner.yaml
@ -121,7 +121,7 @@ spec:
            privileged: true
            capabilities:
              add: ["SYS_ADMIN"]
-          image: vitalif/vitastor-csi:v1.6.1
+          image: vitalif/vitastor-csi:v1.4.6
          args:
            - "--node=$(NODE_ID)"
            - "--endpoint=$(CSI_ENDPOINT)"
--- a/csi/src/config.go
+++ b/csi/src/config.go
@ -5,7 +5,7 @@ package vitastor
 const (
    vitastorCSIDriverName    = "csi.vitastor.io"
-    vitastorCSIDriverVersion = "1.6.1"
+    vitastorCSIDriverVersion = "1.4.6"
 )
 // Config struct fills the parameters of request or user input
--- a/csi/src/nodeserver.go
+++ b/csi/src/nodeserver.go
@ -5,13 +5,14 @@ package vitastor
 import (
    "context"
    "errors"
    "encoding/json"
    "fmt"
    "os"
    "os/exec"
    "path/filepath"
    "strconv"
    "strings"
    "sync"
    "syscall"
    "time"
@ -33,9 +34,6 @@ type NodeServer struct
    stateDir string
    mounter mount.Interface
    restartInterval time.Duration
    mu sync.Mutex
    cond *sync.Cond
    volumeLocks map[string]bool
 }
 type DeviceState struct
@ -65,9 +63,7 @@ func NewNodeServer(driver *Driver) *NodeServer
        useVduse: checkVduseSupport(),
        stateDir: stateDir,
        mounter: mount.New(""),
        volumeLocks: make(map[string]bool),
    }
    ns.cond = sync.NewCond(&ns.mu)
    if (ns.useVduse)
    {
        ns.restoreVduseDaemons()
@ -85,24 +81,299 @@ func NewNodeServer(driver *Driver) *NodeServer
    return ns
 }
-func (ns *NodeServer) lockVolume(lockId string)
+func checkVduseSupport() bool
 {
-    ns.mu.Lock()
+    // Check VDUSE support (vdpa, vduse, virtio-vdpa kernel modules)
-    defer ns.mu.Unlock()
+    vduse := true
-    for (ns.volumeLocks[lockId])
+    for _, mod := range []string{"vdpa", "vduse", "virtio-vdpa"}
    {
-        ns.cond.Wait()
+        _, err := os.Stat("/sys/module/"+mod)
        if (err != nil)
        {
            if (!errors.Is(err, os.ErrNotExist))
            {
                klog.Errorf("failed to check /sys/module/%s: %v", mod, err)
            }
-    ns.volumeLocks[lockId] = true
+            c := exec.Command("/sbin/modprobe", mod)
-    ns.cond.Broadcast()
+            c.Stdout = os.Stderr
            c.Stderr = os.Stderr
            err := c.Run()
            if (err != nil)
            {
                klog.Errorf("/sbin/modprobe %s failed: %v", mod, err)
                vduse = false
                break
            }
        }
    }
    // Check that vdpa tool functions
    if (vduse)
    {
        c := exec.Command("/sbin/vdpa", "-j", "dev")
        c.Stderr = os.Stderr
        err := c.Run()
        if (err != nil)
        {
            klog.Errorf("/sbin/vdpa -j dev failed: %v", err)
            vduse = false
        }
    }
    if (!vduse)
    {
        klog.Errorf(
            "Your host apparently has no VDUSE support. VDUSE support disabled, NBD will be used to map devices."+
            " For VDUSE you need at least Linux 5.15 and the following kernel modules: vdpa, virtio-vdpa, vduse.",
        )
    }
    return vduse
 }
-func (ns *NodeServer) unlockVolume(lockId string)
+// NodeStageVolume mounts the volume to a staging path on the node.
 func (ns *NodeServer) NodeStageVolume(ctx context.Context, req *csi.NodeStageVolumeRequest) (*csi.NodeStageVolumeResponse, error)
 {
-    ns.mu.Lock()
+    return &csi.NodeStageVolumeResponse{}, nil
-    defer ns.mu.Unlock()
+}
-    delete(ns.volumeLocks, lockId)
+
-    ns.cond.Broadcast()
+// NodeUnstageVolume unstages the volume from the staging path
 func (ns *NodeServer) NodeUnstageVolume(ctx context.Context, req *csi.NodeUnstageVolumeRequest) (*csi.NodeUnstageVolumeResponse, error)
 {
    return &csi.NodeUnstageVolumeResponse{}, nil
 }
 func Contains(list []string, s string) bool
 {
    for i := 0; i < len(list); i++
    {
        if (list[i] == s)
        {
            return true
        }
    }
    return false
 }
 func (ns *NodeServer) mapNbd(volName string, ctxVars map[string]string, readonly bool) (string, error)
 {
    // Map NBD device
    // FIXME: Check if already mapped
    args := []string{
        "map", "--image", volName,
    }
    if (ctxVars["configPath"] != "")
    {
        args = append(args, "--config_path", ctxVars["configPath"])
    }
    if (readonly)
    {
        args = append(args, "--readonly", "1")
    }
    stdout, stderr, err := system("/usr/bin/vitastor-nbd", args...)
    dev := strings.TrimSpace(string(stdout))
    if (dev == "")
    {
        return "", fmt.Errorf("vitastor-nbd did not return the name of NBD device. output: %s", stderr)
    }
    return dev, err
 }
 func (ns *NodeServer) unmapNbd(devicePath string)
 {
    // unmap NBD device
    unmapOut, unmapErr := exec.Command("/usr/bin/vitastor-nbd", "unmap", devicePath).CombinedOutput()
    if (unmapErr != nil)
    {
        klog.Errorf("failed to unmap NBD device %s: %s, error: %v", devicePath, unmapOut, unmapErr)
    }
 }
 func findByPidFile(pidFile string) (*os.Process, error)
 {
    pidBuf, err := os.ReadFile(pidFile)
    if (err != nil)
    {
        return nil, err
    }
    pid, err := strconv.ParseInt(strings.TrimSpace(string(pidBuf)), 0, 64)
    if (err != nil)
    {
        return nil, err
    }
    proc, err := os.FindProcess(int(pid))
    if (err != nil)
    {
        return nil, err
    }
    return proc, nil
 }
 func killByPidFile(pidFile string) error
 {
    klog.Infof("killing process with PID from file %s", pidFile)
    proc, err := findByPidFile(pidFile)
    if (err != nil)
    {
        return err
    }
    return proc.Signal(syscall.SIGTERM)
 }
 func startStorageDaemon(vdpaId, volName, pidFile, configPath string, readonly bool) error
 {
    // Start qemu-storage-daemon
    blockSpec := map[string]interface{}{
        "node-name": "disk1",
        "driver": "vitastor",
        "image": volName,
        "cache": map[string]bool{
            "direct": true,
            "no-flush": false,
        },
        "discard": "unmap",
    }
    if (configPath != "")
    {
        blockSpec["config-path"] = configPath
    }
    blockSpecJson, _ := json.Marshal(blockSpec)
    writable := "true"
    if (readonly)
    {
        writable = "false"
    }
    _, _, err := system(
        "/usr/bin/qemu-storage-daemon", "--daemonize", "--pidfile", pidFile, "--blockdev", string(blockSpecJson),
        "--export", "vduse-blk,id="+vdpaId+",node-name=disk1,name="+vdpaId+",num-queues=16,queue-size=128,writable="+writable,
    )
    return err
 }
 func (ns *NodeServer) mapVduse(volName string, ctxVars map[string]string, readonly bool) (string, string, error)
 {
    // Generate state file
    stateFd, err := os.CreateTemp(ns.stateDir, "vitastor-vduse-*.json")
    if (err != nil)
    {
        return "", "", err
    }
    stateFile := stateFd.Name()
    stateFd.Close()
    vdpaId := filepath.Base(stateFile)
    vdpaId = vdpaId[0:len(vdpaId)-5] // remove ".json"
    pidFile := ns.stateDir + vdpaId + ".pid"
    // Map VDUSE device via qemu-storage-daemon
    err = startStorageDaemon(vdpaId, volName, pidFile, ctxVars["configPath"], readonly)
    if (err == nil)
    {
        // Add device to VDPA bus
        _, _, err = system("/sbin/vdpa", "-j", "dev", "add", "name", vdpaId, "mgmtdev", "vduse")
        if (err == nil)
        {
            // Find block device name
            var matches []string
            matches, err = filepath.Glob("/sys/bus/vdpa/devices/"+vdpaId+"/virtio*/block/*")
            if (err == nil && len(matches) == 0)
            {
                err = errors.New("/sys/bus/vdpa/devices/"+vdpaId+"/virtio*/block/* is not found")
            }
            if (err == nil)
            {
                blockdev := "/dev/"+filepath.Base(matches[0])
                _, err = os.Stat(blockdev)
                if (err == nil)
                {
                    // Generate state file
                    stateJSON, _ := json.Marshal(&DeviceState{
                        ConfigPath: ctxVars["configPath"],
                        VdpaId:     vdpaId,
                        Image:      volName,
                        Blockdev:   blockdev,
                        Readonly:   readonly,
                        PidFile:    pidFile,
                    })
                    err = os.WriteFile(stateFile, stateJSON, 0600)
                    if (err == nil)
                    {
                        return blockdev, vdpaId, nil
                    }
                }
            }
        }
        killErr := killByPidFile(pidFile)
        if (killErr != nil)
        {
            klog.Errorf("Failed to kill started qemu-storage-daemon: %v", killErr)
        }
        os.Remove(stateFile)
        os.Remove(pidFile)
    }
    return "", "", err
 }
 func (ns *NodeServer) unmapVduse(devicePath string)
 {
    if (len(devicePath) < 6 || devicePath[0:6] != "/dev/v")
    {
        klog.Errorf("%s does not start with /dev/v", devicePath)
        return
    }
    vduseDev, err := os.Readlink("/sys/block/"+devicePath[5:])
    if (err != nil)
    {
        klog.Errorf("%s is not a symbolic link to VDUSE device (../devices/virtual/vduse/xxx): %v", devicePath, err)
        return
    }
    vdpaId := ""
    p := strings.Index(vduseDev, "/vduse/")
    if (p >= 0)
    {
        vduseDev = vduseDev[p+7:]
        p = strings.Index(vduseDev, "/")
        if (p >= 0)
        {
            vdpaId = vduseDev[0:p]
        }
    }
    if (vdpaId == "")
    {
        klog.Errorf("%s is not a symbolic link to VDUSE device (../devices/virtual/vduse/xxx), but is %v", devicePath, vduseDev)
        return
    }
    ns.unmapVduseById(vdpaId)
 }
 func (ns *NodeServer) unmapVduseById(vdpaId string)
 {
    _, err := os.Stat("/sys/bus/vdpa/devices/"+vdpaId)
    if (err != nil)
    {
        klog.Errorf("failed to stat /sys/bus/vdpa/devices/"+vdpaId+": %v", err)
    }
    else
    {
        _, _, _ = system("/sbin/vdpa", "-j", "dev", "del", vdpaId)
    }
    stateFile := ns.stateDir + vdpaId + ".json"
    os.Remove(stateFile)
    pidFile := ns.stateDir + vdpaId + ".pid"
    _, err = os.Stat(pidFile)
    if (os.IsNotExist(err))
    {
        // ok, already killed
    }
    else if (err != nil)
    {
        klog.Errorf("Failed to stat %v: %v", pidFile, err)
        return
    }
    else
    {
        err = killByPidFile(pidFile)
        if (err != nil)
        {
            klog.Errorf("Failed to kill started qemu-storage-daemon: %v", err)
        }
        os.Remove(pidFile)
    }
 }
 func (ns *NodeServer) restarter()
@ -151,38 +422,8 @@ func (ns *NodeServer) restoreVduseDaemons()
        vdpaId := filepath.Base(stateFile)
        vdpaId = vdpaId[0:len(vdpaId)-5]
        // Check if VDPA device is still added to the bus
-        if (devs[vdpaId] == nil)
+        if (devs[vdpaId] != nil)
        {
            // Unused, clean it up
            unmapVduseById(ns.stateDir, vdpaId)
            continue
        }
        stateJSON, err := os.ReadFile(stateFile)
        if (err != nil)
        {
            klog.Warningf("error reading state file %v: %v", stateFile, err)
            continue
        }
        var state DeviceState
        err = json.Unmarshal(stateJSON, &state)
        if (err != nil)
        {
            klog.Warningf("state file %v contains invalid JSON (error %v): %v", stateFile, err, string(stateJSON))
            continue
        }
        ns.lockVolume(state.ConfigPath+":"+state.Image)
        // Recheck state file after locking
        _, err = os.ReadFile(stateFile)
        if (err != nil)
        {
            klog.Warningf("state file %v disappeared, skipping volume", stateFile)
            ns.unlockVolume(state.ConfigPath+":"+state.Image)
            continue
        }
            // Check if the storage daemon is still active
            pidFile := ns.stateDir + vdpaId + ".pid"
            exists := false
@ -194,40 +435,45 @@ func (ns *NodeServer) restoreVduseDaemons()
            if (!exists)
            {
                // Restart daemon
                stateJSON, err := os.ReadFile(stateFile)
                if (err != nil)
                {
                    klog.Warningf("error reading state file %v: %v", stateFile, err)
                }
                else
                {
                    var state DeviceState
                    err := json.Unmarshal(stateJSON, &state)
                    if (err != nil)
                    {
                        klog.Warningf("state file %v contains invalid JSON (error %v): %v", stateFile, err, string(stateJSON))
                    }
                    else
                    {
                        klog.Warningf("restarting storage daemon for volume %v (VDPA ID %v)", state.Image, vdpaId)
                        _ = startStorageDaemon(vdpaId, state.Image, pidFile, state.ConfigPath, state.Readonly)
                    }
        ns.unlockVolume(state.ConfigPath+":"+state.Image)
                }
            }
-
+        }
-// NodeStageVolume mounts the volume to a staging path on the node.
+        else
 func (ns *NodeServer) NodeStageVolume(ctx context.Context, req *csi.NodeStageVolumeRequest) (*csi.NodeStageVolumeResponse, error)
        {
-    klog.Infof("received node stage volume request %+v", protosanitizer.StripSecrets(req))
+            // Unused, clean it up
-
+            ns.unmapVduseById(vdpaId)
-    ctxVars := make(map[string]string)
+        }
    err := json.Unmarshal([]byte(req.VolumeId), &ctxVars)
    if (err != nil)
    {
        return nil, status.Error(codes.Internal, "volume ID not in JSON format")
    }
    _, err = GetConnectionParams(ctxVars)
    if (err != nil)
    {
        return nil, err
 }
    volName := ctxVars["name"]
-    ns.lockVolume(ctxVars["configPath"]+":"+volName)
+// NodePublishVolume mounts the volume mounted to the staging path to the target path
-    defer ns.unlockVolume(ctxVars["configPath"]+":"+volName)
+func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublishVolumeRequest) (*csi.NodePublishVolumeResponse, error)
 {
    klog.Infof("received node publish volume request %+v", protosanitizer.StripSecrets(req))
-    targetPath := req.GetStagingTargetPath()
+    targetPath := req.GetTargetPath()
    isBlock := req.GetVolumeCapability().GetBlock() != nil
    // Check that it's not already mounted
-    _, err = mount.IsNotMountPoint(ns.mounter, targetPath)
+    _, err := mount.IsNotMountPoint(ns.mounter, targetPath)
    if (err != nil)
    {
        if (os.IsNotExist(err))
@ -263,14 +509,28 @@ func (ns *NodeServer) NodeStageVolume(ctx context.Context, req *csi.NodeStageVol
        }
    }
    ctxVars := make(map[string]string)
    err = json.Unmarshal([]byte(req.VolumeId), &ctxVars)
    if (err != nil)
    {
        return nil, status.Error(codes.Internal, "volume ID not in JSON format")
    }
    volName := ctxVars["name"]
    _, err = GetConnectionParams(ctxVars)
    if (err != nil)
    {
        return nil, err
    }
    var devicePath, vdpaId string
    if (!ns.useVduse)
    {
-        devicePath, err = mapNbd(volName, ctxVars, false)
+        devicePath, err = ns.mapNbd(volName, ctxVars, req.GetReadonly())
    }
    else
    {
-        devicePath, vdpaId, err = mapVduse(ns.stateDir, volName, ctxVars, false)
+        devicePath, vdpaId, err = ns.mapVduse(volName, ctxVars, req.GetReadonly())
    }
    if (err != nil)
    {
@ -354,182 +614,26 @@ func (ns *NodeServer) NodeStageVolume(ctx context.Context, req *csi.NodeStageVol
        )
        goto unmap
    }
-    return &csi.NodeStageVolumeResponse{}, nil
+    return &csi.NodePublishVolumeResponse{}, nil
 unmap:
    if (!ns.useVduse || len(devicePath) >= 8 && devicePath[0:8] == "/dev/nbd")
    {
-        unmapNbd(devicePath)
+        ns.unmapNbd(devicePath)
    }
    else
    {
-        unmapVduseById(ns.stateDir, vdpaId)
+        ns.unmapVduseById(vdpaId)
    }
    return nil, err
 }
 // NodeUnstageVolume unstages the volume from the staging path
 func (ns *NodeServer) NodeUnstageVolume(ctx context.Context, req *csi.NodeUnstageVolumeRequest) (*csi.NodeUnstageVolumeResponse, error)
 {
    klog.Infof("received node unstage volume request %+v", protosanitizer.StripSecrets(req))
    ctxVars := make(map[string]string)
    err := json.Unmarshal([]byte(req.VolumeId), &ctxVars)
    if (err != nil)
    {
        return nil, status.Error(codes.Internal, "volume ID not in JSON format")
    }
    volName := ctxVars["name"]
    ns.lockVolume(ctxVars["configPath"]+":"+volName)
    defer ns.unlockVolume(ctxVars["configPath"]+":"+volName)
    targetPath := req.GetStagingTargetPath()
    devicePath, refCount, err := mount.GetDeviceNameFromMount(ns.mounter, targetPath)
    if (err != nil)
    {
        if (os.IsNotExist(err))
        {
            return nil, status.Error(codes.NotFound, "Target path not found")
        }
        return nil, err
    }
    if (devicePath == "")
    {
        // volume not mounted
        klog.Warningf("%s is not a mountpoint, deleting", targetPath)
        os.Remove(targetPath)
        return &csi.NodeUnstageVolumeResponse{}, nil
    }
    // unmount
    err = mount.CleanupMountPoint(targetPath, ns.mounter, false)
    if (err != nil)
    {
        return nil, err
    }
    // unmap device
    if (refCount == 1)
    {
        if (!ns.useVduse)
        {
            unmapNbd(devicePath)
        }
        else
        {
            unmapVduse(ns.stateDir, devicePath)
        }
    }
    return &csi.NodeUnstageVolumeResponse{}, nil
 }
 // NodePublishVolume mounts the volume mounted to the staging path to the target path
 func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublishVolumeRequest) (*csi.NodePublishVolumeResponse, error)
 {
    klog.Infof("received node publish volume request %+v", protosanitizer.StripSecrets(req))
    ctxVars := make(map[string]string)
    err := json.Unmarshal([]byte(req.VolumeId), &ctxVars)
    if (err != nil)
    {
        return nil, status.Error(codes.Internal, "volume ID not in JSON format")
    }
    _, err = GetConnectionParams(ctxVars)
    if (err != nil)
    {
        return nil, err
    }
    volName := ctxVars["name"]
    ns.lockVolume(ctxVars["configPath"]+":"+volName)
    defer ns.unlockVolume(ctxVars["configPath"]+":"+volName)
    stagingTargetPath := req.GetStagingTargetPath()
    targetPath := req.GetTargetPath()
    isBlock := req.GetVolumeCapability().GetBlock() != nil
    // Check that stagingTargetPath is mounted
    _, err = mount.IsNotMountPoint(ns.mounter, stagingTargetPath)
    if (err != nil)
    {
        klog.Errorf("staging path %v is not mounted: %v", stagingTargetPath, err)
        return nil, fmt.Errorf("staging path %v is not mounted: %v", stagingTargetPath, err)
    }
    // Check that targetPath is not already mounted
    _, err = mount.IsNotMountPoint(ns.mounter, targetPath)
    if (err != nil)
    {
        if (os.IsNotExist(err))
        {
            if (isBlock)
            {
                pathFile, err := os.OpenFile(targetPath, os.O_CREATE|os.O_RDWR, 0o600)
                if (err != nil)
                {
                    klog.Errorf("failed to create block device mount target %s with error: %v", targetPath, err)
                    return nil, err
                }
                err = pathFile.Close()
                if (err != nil)
                {
                    klog.Errorf("failed to close %s with error: %v", targetPath, err)
                    return nil, err
                }
            }
            else
            {
                err := os.MkdirAll(targetPath, 0777)
                if (err != nil)
                {
                    klog.Errorf("failed to create fs mount target %s with error: %v", targetPath, err)
                    return nil, err
                }
            }
        }
        else
        {
            return nil, err
        }
    }
    execArgs := []string{"--bind", stagingTargetPath, targetPath}
    if (req.GetReadonly())
    {
        execArgs = append(execArgs, "-o", "ro")
    }
    cmd := exec.Command("mount", execArgs...)
    cmd.Stderr = os.Stderr
    klog.Infof("binding volume %v (%v) from %v to %v", volName, ctxVars["configPath"], stagingTargetPath, targetPath)
    out, err := cmd.Output()
    if (err != nil)
    {
        return nil, fmt.Errorf("Error running mount %v: %s", strings.Join(execArgs, " "), out)
    }
    return &csi.NodePublishVolumeResponse{}, nil
 }
 // NodeUnpublishVolume unmounts the volume from the target path
 func (ns *NodeServer) NodeUnpublishVolume(ctx context.Context, req *csi.NodeUnpublishVolumeRequest) (*csi.NodeUnpublishVolumeResponse, error)
 {
    klog.Infof("received node unpublish volume request %+v", protosanitizer.StripSecrets(req))
    ctxVars := make(map[string]string)
    err := json.Unmarshal([]byte(req.VolumeId), &ctxVars)
    if (err != nil)
    {
        return nil, status.Error(codes.Internal, "volume ID not in JSON format")
    }
    volName := ctxVars["name"]
    ns.lockVolume(ctxVars["configPath"]+":"+volName)
    defer ns.unlockVolume(ctxVars["configPath"]+":"+volName)
    targetPath := req.GetTargetPath()
-    devicePath, _, err := mount.GetDeviceNameFromMount(ns.mounter, targetPath)
+    devicePath, refCount, err := mount.GetDeviceNameFromMount(ns.mounter, targetPath)
    if (err != nil)
    {
        if (os.IsNotExist(err))
@ -545,14 +649,24 @@ func (ns *NodeServer) NodeUnpublishVolume(ctx context.Context, req *csi.NodeUnpu
        os.Remove(targetPath)
        return &csi.NodeUnpublishVolumeResponse{}, nil
    }
    // unmount
    err = mount.CleanupMountPoint(targetPath, ns.mounter, false)
    if (err != nil)
    {
        return nil, err
    }
-
+    // unmap NBD device
    if (refCount == 1)
    {
        if (!ns.useVduse)
        {
            ns.unmapNbd(devicePath)
        }
        else
        {
            ns.unmapVduse(devicePath)
        }
    }
    return &csi.NodeUnpublishVolumeResponse{}, nil
 }
@ -571,17 +685,7 @@ func (ns *NodeServer) NodeExpandVolume(ctx context.Context, req *csi.NodeExpandV
 // NodeGetCapabilities returns the supported capabilities of the node server
 func (ns *NodeServer) NodeGetCapabilities(ctx context.Context, req *csi.NodeGetCapabilitiesRequest) (*csi.NodeGetCapabilitiesResponse, error)
 {
-    return &csi.NodeGetCapabilitiesResponse{
+    return &csi.NodeGetCapabilitiesResponse{}, nil
        Capabilities: []*csi.NodeServiceCapability{
            &csi.NodeServiceCapability{
                Type: &csi.NodeServiceCapability_Rpc{
                    Rpc: &csi.NodeServiceCapability_RPC{
                        Type: csi.NodeServiceCapability_RPC_STAGE_UNSTAGE_VOLUME,
                    },
                },
            },
        },
    }, nil
 }
 // NodeGetInfo returns NodeGetInfoResponse for CO.
--- a/csi/src/utils.go
+++ b/csi/src/utils.go
@ -1,301 +0,0 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 or GNU GPL-2.0+ (see README.md for details)
 package vitastor
 import (
    "errors"
    "encoding/json"
    "fmt"
    "os"
    "os/exec"
    "path/filepath"
    "strconv"
    "strings"
    "syscall"
    "k8s.io/klog"
 )
 func Contains(list []string, s string) bool
 {
    for i := 0; i < len(list); i++
    {
        if (list[i] == s)
        {
            return true
        }
    }
    return false
 }
 func checkVduseSupport() bool
 {
    // Check VDUSE support (vdpa, vduse, virtio-vdpa kernel modules)
    vduse := true
    for _, mod := range []string{"vdpa", "vduse", "virtio-vdpa"}
    {
        _, err := os.Stat("/sys/module/"+mod)
        if (err != nil)
        {
            if (!errors.Is(err, os.ErrNotExist))
            {
                klog.Errorf("failed to check /sys/module/%s: %v", mod, err)
            }
            c := exec.Command("/sbin/modprobe", mod)
            c.Stdout = os.Stderr
            c.Stderr = os.Stderr
            err := c.Run()
            if (err != nil)
            {
                klog.Errorf("/sbin/modprobe %s failed: %v", mod, err)
                vduse = false
                break
            }
        }
    }
    // Check that vdpa tool functions
    if (vduse)
    {
        c := exec.Command("/sbin/vdpa", "-j", "dev")
        c.Stderr = os.Stderr
        err := c.Run()
        if (err != nil)
        {
            klog.Errorf("/sbin/vdpa -j dev failed: %v", err)
            vduse = false
        }
    }
    if (!vduse)
    {
        klog.Errorf(
            "Your host apparently has no VDUSE support. VDUSE support disabled, NBD will be used to map devices."+
            " For VDUSE you need at least Linux 5.15 and the following kernel modules: vdpa, virtio-vdpa, vduse.",
        )
    }
    return vduse
 }
 func mapNbd(volName string, ctxVars map[string]string, readonly bool) (string, error)
 {
    // Map NBD device
    // FIXME: Check if already mapped
    args := []string{
        "map", "--image", volName,
    }
    if (ctxVars["configPath"] != "")
    {
        args = append(args, "--config_path", ctxVars["configPath"])
    }
    if (readonly)
    {
        args = append(args, "--readonly", "1")
    }
    stdout, stderr, err := system("/usr/bin/vitastor-nbd", args...)
    dev := strings.TrimSpace(string(stdout))
    if (dev == "")
    {
        return "", fmt.Errorf("vitastor-nbd did not return the name of NBD device. output: %s", stderr)
    }
    return dev, err
 }
 func unmapNbd(devicePath string)
 {
    // unmap NBD device
    unmapOut, unmapErr := exec.Command("/usr/bin/vitastor-nbd", "unmap", devicePath).CombinedOutput()
    if (unmapErr != nil)
    {
        klog.Errorf("failed to unmap NBD device %s: %s, error: %v", devicePath, unmapOut, unmapErr)
    }
 }
 func findByPidFile(pidFile string) (*os.Process, error)
 {
    pidBuf, err := os.ReadFile(pidFile)
    if (err != nil)
    {
        return nil, err
    }
    pid, err := strconv.ParseInt(strings.TrimSpace(string(pidBuf)), 0, 64)
    if (err != nil)
    {
        return nil, err
    }
    proc, err := os.FindProcess(int(pid))
    if (err != nil)
    {
        return nil, err
    }
    return proc, nil
 }
 func killByPidFile(pidFile string) error
 {
    klog.Infof("killing process with PID from file %s", pidFile)
    proc, err := findByPidFile(pidFile)
    if (err != nil)
    {
        return err
    }
    return proc.Signal(syscall.SIGTERM)
 }
 func startStorageDaemon(vdpaId, volName, pidFile, configPath string, readonly bool) error
 {
    // Start qemu-storage-daemon
    blockSpec := map[string]interface{}{
        "node-name": "disk1",
        "driver": "vitastor",
        "image": volName,
        "cache": map[string]bool{
            "direct": true,
            "no-flush": false,
        },
        "discard": "unmap",
    }
    if (configPath != "")
    {
        blockSpec["config-path"] = configPath
    }
    blockSpecJson, _ := json.Marshal(blockSpec)
    writable := "true"
    if (readonly)
    {
        writable = "false"
    }
    _, _, err := system(
        "/usr/bin/qemu-storage-daemon", "--daemonize", "--pidfile", pidFile, "--blockdev", string(blockSpecJson),
        "--export", "vduse-blk,id="+vdpaId+",node-name=disk1,name="+vdpaId+",num-queues=16,queue-size=128,writable="+writable,
    )
    return err
 }
 func mapVduse(stateDir string, volName string, ctxVars map[string]string, readonly bool) (string, string, error)
 {
    // Generate state file
    stateFd, err := os.CreateTemp(stateDir, "vitastor-vduse-*.json")
    if (err != nil)
    {
        return "", "", err
    }
    stateFile := stateFd.Name()
    stateFd.Close()
    vdpaId := filepath.Base(stateFile)
    vdpaId = vdpaId[0:len(vdpaId)-5] // remove ".json"
    pidFile := stateDir + vdpaId + ".pid"
    // Map VDUSE device via qemu-storage-daemon
    err = startStorageDaemon(vdpaId, volName, pidFile, ctxVars["configPath"], readonly)
    if (err == nil)
    {
        // Add device to VDPA bus
        _, _, err = system("/sbin/vdpa", "-j", "dev", "add", "name", vdpaId, "mgmtdev", "vduse")
        if (err == nil)
        {
            // Find block device name
            var matches []string
            matches, err = filepath.Glob("/sys/bus/vdpa/devices/"+vdpaId+"/virtio*/block/*")
            if (err == nil && len(matches) == 0)
            {
                err = errors.New("/sys/bus/vdpa/devices/"+vdpaId+"/virtio*/block/* is not found")
            }
            if (err == nil)
            {
                blockdev := "/dev/"+filepath.Base(matches[0])
                _, err = os.Stat(blockdev)
                if (err == nil)
                {
                    // Generate state file
                    stateJSON, _ := json.Marshal(&DeviceState{
                        ConfigPath: ctxVars["configPath"],
                        VdpaId:     vdpaId,
                        Image:      volName,
                        Blockdev:   blockdev,
                        Readonly:   readonly,
                        PidFile:    pidFile,
                    })
                    err = os.WriteFile(stateFile, stateJSON, 0600)
                    if (err == nil)
                    {
                        return blockdev, vdpaId, nil
                    }
                }
            }
        }
        killErr := killByPidFile(pidFile)
        if (killErr != nil)
        {
            klog.Errorf("Failed to kill started qemu-storage-daemon: %v", killErr)
        }
        os.Remove(stateFile)
        os.Remove(pidFile)
    }
    return "", "", err
 }
 func unmapVduse(stateDir, devicePath string)
 {
    if (len(devicePath) < 6 || devicePath[0:6] != "/dev/v")
    {
        klog.Errorf("%s does not start with /dev/v", devicePath)
        return
    }
    vduseDev, err := os.Readlink("/sys/block/"+devicePath[5:])
    if (err != nil)
    {
        klog.Errorf("%s is not a symbolic link to VDUSE device (../devices/virtual/vduse/xxx): %v", devicePath, err)
        return
    }
    vdpaId := ""
    p := strings.Index(vduseDev, "/vduse/")
    if (p >= 0)
    {
        vduseDev = vduseDev[p+7:]
        p = strings.Index(vduseDev, "/")
        if (p >= 0)
        {
            vdpaId = vduseDev[0:p]
        }
    }
    if (vdpaId == "")
    {
        klog.Errorf("%s is not a symbolic link to VDUSE device (../devices/virtual/vduse/xxx), but is %v", devicePath, vduseDev)
        return
    }
    unmapVduseById(stateDir, vdpaId)
 }
 func unmapVduseById(stateDir, vdpaId string)
 {
    _, err := os.Stat("/sys/bus/vdpa/devices/"+vdpaId)
    if (err != nil)
    {
        klog.Errorf("failed to stat /sys/bus/vdpa/devices/"+vdpaId+": %v", err)
    }
    else
    {
        _, _, _ = system("/sbin/vdpa", "-j", "dev", "del", vdpaId)
    }
    stateFile := stateDir + vdpaId + ".json"
    os.Remove(stateFile)
    pidFile := stateDir + vdpaId + ".pid"
    _, err = os.Stat(pidFile)
    if (os.IsNotExist(err))
    {
        // ok, already killed
    }
    else if (err != nil)
    {
        klog.Errorf("Failed to stat %v: %v", pidFile, err)
        return
    }
    else
    {
        err = killByPidFile(pidFile)
        if (err != nil)
        {
            klog.Errorf("Failed to kill started qemu-storage-daemon: %v", err)
        }
        os.Remove(pidFile)
    }
 }
--- a/debian/build-vitastor-bookworm.sh
+++ b/debian/build-vitastor-bookworm.sh
@ -3,5 +3,5 @@
 cat < vitastor.Dockerfile > ../Dockerfile
 cd ..
 mkdir -p packages
-sudo podman build --build-arg DISTRO=debian --build-arg REL=bookworm -v `pwd`/packages:/root/packages -f Dockerfile .
+sudo podman build --build-arg REL=bookworm -v `pwd`/packages:/root/packages -f Dockerfile .
 rm Dockerfile
--- a/debian/build-vitastor-bullseye.sh
+++ b/debian/build-vitastor-bullseye.sh
@ -3,5 +3,5 @@
 cat < vitastor.Dockerfile > ../Dockerfile
 cd ..
 mkdir -p packages
-sudo podman build --build-arg DISTRO=debian --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f Dockerfile .
+sudo podman build --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f Dockerfile .
 rm Dockerfile
--- a/debian/build-vitastor-buster.sh
+++ b/debian/build-vitastor-buster.sh
@ -3,5 +3,5 @@
 cat < vitastor.Dockerfile > ../Dockerfile
 cd ..
 mkdir -p packages
-sudo podman build --build-arg DISTRO=debian --build-arg REL=buster -v `pwd`/packages:/root/packages -f Dockerfile .
+sudo podman build --build-arg REL=buster -v `pwd`/packages:/root/packages -f Dockerfile .
 rm Dockerfile
--- a/debian/build-vitastor-ubuntu-jammy.sh
+++ b/debian/build-vitastor-ubuntu-jammy.sh
@ -1,7 +0,0 @@
 #!/bin/bash
 cat < vitastor.Dockerfile > ../Dockerfile
 cd ..
 mkdir -p packages
 sudo podman build --build-arg DISTRO=ubuntu --build-arg REL=jammy -v `pwd`/packages:/root/packages -f Dockerfile .
 rm Dockerfile
--- a/debian/changelog
+++ b/debian/changelog
@ -1,4 +1,4 @@
-vitastor (1.6.1-1) unstable; urgency=medium
+vitastor (1.4.6-1) unstable; urgency=medium
  * Bugfixes
--- a/debian/control
+++ b/debian/control
@ -2,7 +2,7 @@ Source: vitastor
 Section: admin
 Priority: optional
 Maintainer: Vitaliy Filippov <vitalif@yourcmc.ru>
-Build-Depends: debhelper, liburing-dev (>= 0.6), g++ (>= 8), libstdc++6 (>= 8), linux-libc-dev, libgoogle-perftools-dev, libjerasure-dev, libgf-complete-dev, libibverbs-dev, libisal-dev, cmake, pkg-config, libnl-3-dev, libnl-genl-3-dev
+Build-Depends: debhelper, liburing-dev (>= 0.6), g++ (>= 8), libstdc++6 (>= 8), linux-libc-dev, libgoogle-perftools-dev, libjerasure-dev, libgf-complete-dev, libibverbs-dev, libisal-dev, cmake, pkg-config
 Standards-Version: 4.5.0
 Homepage: https://vitastor.io/
 Rules-Requires-Root: no
--- a/debian/libvirt.Dockerfile
+++ b/debian/libvirt.Dockerfile
@ -1,14 +1,13 @@
 # Build patched libvirt for Debian Buster or Bullseye/Sid inside a container
-# cd ..; podman build --build-arg DISTRO=debian --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/libvirt.Dockerfile .
+# cd ..; podman build --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/libvirt.Dockerfile .
 ARG DISTRO=
 ARG REL=
-FROM $DISTRO:$REL
+FROM debian:$REL
 ARG REL=
 WORKDIR /root
-RUN if ([ "${DISTRO}" = "debian" ]) && ( [ "${REL}" = "buster" -o "${REL}" = "bullseye" ] ); then \
+RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" ]; then \
        echo "deb http://deb.debian.org/debian $REL-backports main" >> /etc/apt/sources.list; \
        echo >> /etc/apt/preferences; \
        echo 'Package: *' >> /etc/apt/preferences; \
@ -24,7 +23,7 @@ RUN apt-get -y build-dep libvirt0
 RUN apt-get -y install libglusterfs-dev
 RUN apt-get --download-only source libvirt
-ADD patches/libvirt-5.0-vitastor.diff patches/libvirt-7.0-vitastor.diff patches/libvirt-7.5-vitastor.diff patches/libvirt-7.6-vitastor.diff patches/libvirt-8.0-vitastor.diff /root
+ADD patches/libvirt-5.0-vitastor.diff patches/libvirt-7.0-vitastor.diff patches/libvirt-7.5-vitastor.diff patches/libvirt-7.6-vitastor.diff /root
 RUN set -e; \
    mkdir -p /root/packages/libvirt-$REL; \
    rm -rf /root/packages/libvirt-$REL/*; \
--- a/debian/patched-qemu.Dockerfile
+++ b/debian/patched-qemu.Dockerfile
@ -27,7 +27,7 @@ RUN apt-get -y build-dep qemu
 RUN apt-get --download-only source qemu
 ADD patches /root/vitastor/patches
-ADD src/client/qemu_driver.c /root/qemu_driver.c
+ADD src/qemu_driver.c /root/vitastor/src/qemu_driver.c
 #RUN set -e; \
 #    apt-get install -y wget; \
@ -52,7 +52,7 @@ RUN set -e; \
    cd /root/packages/qemu-$REL/qemu-*/; \
    quilt push -a; \
    quilt add block/vitastor.c; \
-    cp /root/qemu_driver.c block/vitastor.c; \
+    cp /root/vitastor/src/qemu_driver.c block/vitastor.c; \
    quilt refresh; \
    V=$(head -n1 debian/changelog | perl -pe 's/5\.2\+dfsg-9/5.2+dfsg-11/; s/^.*\((.*?)(~bpo[\d\+]*)?\).*$/$1/')+vitastor4; \
    if [ "$REL" = bullseye ]; then V=${V}bullseye; fi; \
--- a/debian/vitastor-client.install
+++ b/debian/vitastor-client.install
@ -3,6 +3,4 @@ usr/bin/vitastor-cli
 usr/bin/vitastor-rm
 usr/bin/vitastor-nbd
 usr/bin/vitastor-nfs
 usr/bin/vitastor-kv
 usr/bin/vitastor-kv-stress
 usr/lib/*/libvitastor*.so*
--- a/debian/vitastor-mon.install
+++ b/debian/vitastor-mon.install
@ -1,3 +1,2 @@
-mon usr/lib/vitastor/mon
+mon usr/lib/vitastor
-mon/scripts/make-etcd usr/lib/vitastor/mon
+mon/vitastor-mon.service /lib/systemd/system
 mon/scripts/vitastor-mon.service /lib/systemd/system
--- a/debian/vitastor-osd.install
+++ b/debian/vitastor-osd.install
@ -1,6 +1,6 @@
 usr/bin/vitastor-osd
 usr/bin/vitastor-disk
 usr/bin/vitastor-dump-journal
-mon/scripts/vitastor-osd@.service /lib/systemd/system
+mon/vitastor-osd@.service /lib/systemd/system
-mon/scripts/vitastor.target /lib/systemd/system
+mon/vitastor.target /lib/systemd/system
-mon/scripts/90-vitastor.rules /lib/udev/rules.d
+mon/90-vitastor.rules /lib/udev/rules.d
--- a/debian/vitastor.Dockerfile
+++ b/debian/vitastor.Dockerfile
@ -1,10 +1,8 @@
 # Build Vitastor packages for Debian inside a container
-# cd ..; podman build --build-arg DISTRO=debian --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/vitastor.Dockerfile .
+# cd ..; podman build --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/vitastor.Dockerfile .
 ARG DISTRO=debian
 ARG REL=
-FROM $DISTRO:$REL
+FROM debian:$REL
 ARG DISTRO=debian
 ARG REL=
 WORKDIR /root
@ -25,7 +23,7 @@ RUN apt-get update
 RUN apt-get -y install fio liburing-dev libgoogle-perftools-dev devscripts
 RUN apt-get -y build-dep fio
 RUN apt-get --download-only source fio
-RUN apt-get update && apt-get -y install libjerasure-dev cmake libibverbs-dev libisal-dev libnl-3-dev libnl-genl-3-dev
+RUN apt-get update && apt-get -y install libjerasure-dev cmake libibverbs-dev libisal-dev
 ADD . /root/vitastor
 RUN set -e -x; \
@ -37,8 +35,8 @@ RUN set -e -x; \
    mkdir -p /root/packages/vitastor-$REL; \
    rm -rf /root/packages/vitastor-$REL/*; \
    cd /root/packages/vitastor-$REL; \
-    cp -r /root/vitastor vitastor-1.6.1; \
+    cp -r /root/vitastor vitastor-1.4.6; \
-    cd vitastor-1.6.1; \
+    cd vitastor-1.4.6; \
    ln -s /root/fio-build/fio-*/ ./fio; \
    FIO=$(head -n1 fio/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
    ls /usr/include/linux/raw.h || cp ./debian/raw.h /usr/include/linux/raw.h; \
@ -51,8 +49,8 @@ RUN set -e -x; \
    rm -rf a b; \
    echo "dep:fio=$FIO" > debian/fio_version; \
    cd /root/packages/vitastor-$REL; \
-    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_1.6.1.orig.tar.xz vitastor-1.6.1; \
+    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_1.4.6.orig.tar.xz vitastor-1.4.6; \
-    cd vitastor-1.6.1; \
+    cd vitastor-1.4.6; \
    V=$(head -n1 debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
    DEBFULLNAME="Vitaliy Filippov <vitalif@yourcmc.ru>" dch -D $REL -v "$V""$REL" "Rebuild for $REL"; \
    DEB_BUILD_OPTIONS=nocheck dpkg-buildpackage --jobs=auto -sa; \
--- a/docs/config/client.en.md
+++ b/docs/config/client.en.md
@ -9,9 +9,6 @@
 These parameters apply only to Vitastor clients (QEMU, fio, NBD and so on) and
 affect their interaction with the cluster.
 - [client_retry_interval](#client_retry_interval)
 - [client_eio_retry_interval](#client_eio_retry_interval)
 - [client_retry_enospc](#client_retry_enospc)
 - [client_max_dirty_bytes](#client_max_dirty_bytes)
 - [client_max_dirty_ops](#client_max_dirty_ops)
 - [client_enable_writeback](#client_enable_writeback)
@ -21,36 +18,6 @@ affect their interaction with the cluster.
 - [nbd_timeout](#nbd_timeout)
 - [nbd_max_devices](#nbd_max_devices)
 - [nbd_max_part](#nbd_max_part)
 - [osd_nearfull_ratio](#osd_nearfull_ratio)
 ## client_retry_interval
 - Type: milliseconds
 - Default: 50
 - Minimum: 10
 - Can be changed online: yes
 Retry time for I/O requests failed due to inactive PGs or network
 connectivity errors.
 ## client_eio_retry_interval
 - Type: milliseconds
 - Default: 1000
 - Can be changed online: yes
 Retry time for I/O requests failed due to data corruption or unfinished
 EC object deletions (has_incomplete PG state). 0 disables such retries
 and clients are not blocked and just get EIO error code instead.
 ## client_retry_enospc
 - Type: boolean
 - Default: true
 - Can be changed online: yes
 Retry writes on out of space errors to wait until some space is freed on
 OSDs.
 ## client_max_dirty_bytes
@ -168,18 +135,3 @@ Maximum number of NBD devices in the system. This value is passed as
 Maximum number of partitions per NBD device. This value is passed as
 `max_part` parameter for the nbd kernel module when vitastor-nbd autoloads it.
 Note that (nbds_max)*(1+max_part) usually can't exceed 256.
 ## osd_nearfull_ratio
 - Type: number
 - Default: 0.95
 - Can be changed online: yes
 Ratio of used space on OSD to treat it as "almost full" in vitastor-cli status output.
 Remember that some client writes may hang or complete with an error if even
 just one OSD becomes 100 % full!
 However, unlike in Ceph, 100 % full Vitastor OSDs don't crash (in Ceph they're
 unable to start at all), so you'll be able to recover from "out of space" errors
 without destroying and recreating OSDs.
--- a/docs/config/client.ru.md
+++ b/docs/config/client.ru.md
@ -9,9 +9,6 @@
 Данные параметры применяются только к клиентам Vitastor (QEMU, fio, NBD и т.п.) и
 затрагивают логику их работы с кластером.
 - [client_retry_interval](#client_retry_interval)
 - [client_eio_retry_interval](#client_eio_retry_interval)
 - [client_retry_enospc](#client_retry_enospc)
 - [client_max_dirty_bytes](#client_max_dirty_bytes)
 - [client_max_dirty_ops](#client_max_dirty_ops)
 - [client_enable_writeback](#client_enable_writeback)
@ -21,37 +18,6 @@
 - [nbd_timeout](#nbd_timeout)
 - [nbd_max_devices](#nbd_max_devices)
 - [nbd_max_part](#nbd_max_part)
 - [osd_nearfull_ratio](#osd_nearfull_ratio)
 ## client_retry_interval
 - Тип: миллисекунды
 - Значение по умолчанию: 50
 - Минимальное значение: 10
 - Можно менять на лету: да
 Время повтора запросов ввода-вывода, неудачных из-за неактивных PG или
 ошибок сети.
 ## client_eio_retry_interval
 - Тип: миллисекунды
 - Значение по умолчанию: 1000
 - Можно менять на лету: да
 Время повтора запросов ввода-вывода, неудачных из-за повреждения данных
 или незавершённых удалений EC-объектов (состояния PG has_incomplete).
 0 отключает повторы таких запросов и клиенты не блокируются, а вместо
 этого просто получают код ошибки EIO.
 ## client_retry_enospc
 - Тип: булево (да/нет)
 - Значение по умолчанию: true
 - Можно менять на лету: да
 Повторять запросы записи, завершившиеся с ошибками нехватки места, т.е.
 ожидать, пока на OSD не освободится место.
 ## client_max_dirty_bytes
@ -169,20 +135,3 @@
 Максимальное число разделов на одном NBD-устройстве. Данное значение передаётся
 модулю ядра nbd как параметр `max_part`, когда его загружает vitastor-nbd.
 Имейте в виду, что (nbds_max)*(1+max_part) обычно не может превышать 256.
 ## osd_nearfull_ratio
 - Тип: число
 - Значение по умолчанию: 0.95
 - Можно менять на лету: да
 Доля занятого места на OSD, начиная с которой он считается "почти заполненным" в
 выводе vitastor-cli status.
 Помните, что часть клиентских запросов может зависнуть или завершиться с ошибкой,
 если на 100 % заполнится хотя бы 1 OSD!
 Однако, в отличие от Ceph, заполненные на 100 % OSD Vitastor не падают (в Ceph
 заполненные на 100% OSD вообще не могут стартовать), так что вы сможете
 восстановить работу кластера после ошибок отсутствия свободного места
 без уничтожения и пересоздания OSD.
--- a/docs/config/monitor.en.md
+++ b/docs/config/monitor.en.md
@ -15,7 +15,6 @@ These parameters only apply to Monitors.
 - [mon_stats_timeout](#mon_stats_timeout)
 - [osd_out_time](#osd_out_time)
 - [placement_levels](#placement_levels)
 - [use_old_pg_combinator](#use_old_pg_combinator)
 ## etcd_mon_ttl
@ -78,11 +77,3 @@ values.  Smaller priority means higher level in tree. For example,
 levels are always predefined and can't be removed. If one of them is not
 present in the configuration, then it is defined with the default priority
 (100 for "host", 101 for "osd").
 ## use_old_pg_combinator
 - Type: boolean
 - Default: false
 Use the old PG combination generator which doesn't support [level_placement](pool.en.md#level_placement)
 and [raw_placement](pool.en.md#raw_placement) for pools which don't use this features.
--- a/docs/config/monitor.ru.md
+++ b/docs/config/monitor.ru.md
@ -15,7 +15,6 @@
 - [mon_stats_timeout](#mon_stats_timeout)
 - [osd_out_time](#osd_out_time)
 - [placement_levels](#placement_levels)
 - [use_old_pg_combinator](#use_old_pg_combinator)
 ## etcd_mon_ttl
@ -79,11 +78,3 @@ OSD перед обновлением агрегированной статис
 "host" и "osd" являются предопределёнными и не могут быть удалены. Если
 один из них отсутствует в конфигурации, он доопределяется с приоритетом по
 умолчанию (100 для уровня "host", 101 для "osd").
 ## use_old_pg_combinator
 - Тип: булево (да/нет)
 - Значение по умолчанию: false
 Использовать старый генератор комбинаций PG, не поддерживающий [level_placement](pool.ru.md#level_placement)
 и [raw_placement](pool.ru.md#raw_placement) для пулов, которые не используют данные функции.
--- a/docs/config/network.en.md
+++ b/docs/config/network.en.md
@ -25,11 +25,12 @@ between clients, OSDs and etcd.
 - [peer_connect_timeout](#peer_connect_timeout)
 - [osd_idle_timeout](#osd_idle_timeout)
 - [osd_ping_timeout](#osd_ping_timeout)
 - [up_wait_retry_interval](#up_wait_retry_interval)
 - [max_etcd_attempts](#max_etcd_attempts)
 - [etcd_quick_timeout](#etcd_quick_timeout)
 - [etcd_slow_timeout](#etcd_slow_timeout)
 - [etcd_keepalive_timeout](#etcd_keepalive_timeout)
- [etcd_ws_keepalive_interval](#etcd_ws_keepalive_interval)
+- [etcd_ws_keepalive_timeout](#etcd_ws_keepalive_timeout)
 ## tcp_header_buffer_size
@ -211,6 +212,17 @@ Maximum time to wait for OSD keepalive responses. If an OSD doesn't respond
 within this time, the connection to it is dropped and a reconnection attempt
 is scheduled.
 ## up_wait_retry_interval
 - Type: milliseconds
 - Default: 50
 - Minimum: 10
 - Can be changed online: yes
 OSDs respond to clients with a special error code when they receive I/O
 requests for a PG that's not synchronized and started. This parameter sets
 the time for the clients to wait before re-attempting such I/O requests.
 ## max_etcd_attempts
 - Type: integer
@ -245,10 +257,10 @@ Timeout for etcd requests which are allowed to wait for some time.
 Timeout for etcd connection HTTP Keep-Alive. Should be higher than
 etcd_report_interval to guarantee that keepalive actually works.
-## etcd_ws_keepalive_interval
+## etcd_ws_keepalive_timeout
 - Type: seconds
- Default: 5
+- Default: 30
 - Can be changed online: yes
 etcd websocket ping interval required to keep the connection alive and
--- a/docs/config/network.ru.md
+++ b/docs/config/network.ru.md
@ -25,11 +25,12 @@
 - [peer_connect_timeout](#peer_connect_timeout)
 - [osd_idle_timeout](#osd_idle_timeout)
 - [osd_ping_timeout](#osd_ping_timeout)
 - [up_wait_retry_interval](#up_wait_retry_interval)
 - [max_etcd_attempts](#max_etcd_attempts)
 - [etcd_quick_timeout](#etcd_quick_timeout)
 - [etcd_slow_timeout](#etcd_slow_timeout)
 - [etcd_keepalive_timeout](#etcd_keepalive_timeout)
- [etcd_ws_keepalive_interval](#etcd_ws_keepalive_interval)
+- [etcd_ws_keepalive_timeout](#etcd_ws_keepalive_timeout)
 ## tcp_header_buffer_size
@ -220,6 +221,19 @@ OSD в любом случае согласовывают реальное зн
 Если OSD не отвечает за это время, соединение отключается и производится
 повторная попытка соединения.
 ## up_wait_retry_interval
 - Тип: миллисекунды
 - Значение по умолчанию: 50
 - Минимальное значение: 10
 - Можно менять на лету: да
 Когда OSD получают от клиентов запросы ввода-вывода, относящиеся к не
 поднятым на данный момент на них PG, либо к PG в процессе синхронизации,
 они отвечают клиентам специальным кодом ошибки, означающим, что клиент
 должен некоторое время подождать перед повторением запроса. Именно это время
 ожидания задаёт данный параметр.
 ## max_etcd_attempts
 - Тип: целое число
@ -256,10 +270,10 @@ OSD в любом случае согласовывают реальное зн
 Таймаут для HTTP Keep-Alive в соединениях к etcd. Должен быть больше, чем
 etcd_report_interval, чтобы keepalive гарантированно работал.
-## etcd_ws_keepalive_interval
+## etcd_ws_keepalive_timeout
 - Тип: секунды
- Значение по умолчанию: 5
+- Значение по умолчанию: 30
 - Можно менять на лету: да
 Интервал проверки живости вебсокет-подключений к etcd.
--- a/docs/config/pool.en.md
+++ b/docs/config/pool.en.md
@ -32,8 +32,6 @@ Parameters:
 - [pg_minsize](#pg_minsize)
 - [pg_count](#pg_count)
 - [failure_domain](#failure_domain)
 - [level_placement](#level_placement)
 - [raw_placement](#raw_placement)
 - [max_osd_combinations](#max_osd_combinations)
 - [block_size](#block_size)
 - [bitmap_granularity](#bitmap_granularity)
@ -43,7 +41,6 @@ Parameters:
 - [osd_tags](#osd_tags)
 - [primary_affinity_tags](#primary_affinity_tags)
 - [scrub_interval](#scrub_interval)
 - [used_for_fs](#used_for_fs)
 Examples:
@ -86,11 +83,7 @@ Parent node reference is required for intermediate tree nodes.
 Separate OSD settings are set in etc keys `/vitastor/config/osd/<number>`
 in JSON format `{"<key>":<value>}`.
-As of now, the following settings are supported:
+As of now, two settings are supported:
 - [reweight](#reweight)
 - [tags](#tags)
 - [noout](#noout)
 ## reweight
@ -113,14 +106,6 @@ subsets and then use a specific subset for pool instead of all OSDs.
 For example you can mark SSD OSDs with tag "ssd" and HDD OSDs with "hdd" and
 such tags will work as device classes.
 ## noout
 - Type: boolean
 - Default: false
 If set to true, [osd_out_time](monitor.en.md#osd_out_time) is ignored for this
 OSD and it's never removed from data distribution by the monitor.
 # Pool parameters
 ## name
@ -169,25 +154,8 @@ That is, if it becomes impossible to place PG data on at least (pg_minsize)
 OSDs, PG is deactivated for both read and write. So you know that a fresh
 write always goes to at least (pg_minsize) OSDs (disks).
-For example, the difference between pg_minsize 2 and 1 in a 3-way replicated
+That is, pg_size minus pg_minsize sets the number of disk failures to tolerate
-pool (pg_size=3) is:
+without temporary downtime (for [osd_out_time](monitor.en.md#osd_out_time)).
 - If 2 hosts go down with pg_minsize=2, the pool becomes inactive and remains
  inactive for [osd_out_time](monitor.en.md#osd_out_time) (10 minutes). After
  this timeout, the monitor selects replacement hosts/OSDs and the pool comes
  up and starts to heal. Therefore, if you don't have replacement OSDs, i.e.
  if you only have 3 hosts with OSDs and 2 of them are down, the pool remains
  inactive until you add or return at least 1 host (or change failure_domain
  to "osd").
 - If 2 hosts go down with pg_minsize=1, the pool only experiences a short
  I/O pause until the monitor notices that OSDs are down (5-10 seconds with
  the default [etcd_report_interval](osd.en.md#etcd_report_interval)). After
  this pause, I/O resumes, but new data is temporarily written in only 1 copy.
  Then, after osd_out_time, the monitor also selects replacement OSDs and the
  pool starts to heal.
 So, pg_minsize regulates the number of failures that a pool can tolerate
 without temporary downtime for [osd_out_time](monitor.en.md#osd_out_time),
 but at a cost of slightly reduced storage reliability.
 FIXME: pg_minsize behaviour may be changed in the future to only make PGs
 read-only instead of deactivating them.
@ -200,8 +168,8 @@ read-only instead of deactivating them.
 Number of PGs for this pool. The value should be big enough for the monitor /
 LP solver to be able to optimize data placement.
-"Enough" is usually around 10-100 PGs per OSD, i.e. you set pg_count for pool
+"Enough" is usually around 64-128 PGs per OSD, i.e. you set pg_count for pool
-to (total OSD count * 10 / pg_size). You can round it to the closest power of 2,
+to (total OSD count * 100 / pg_size). You can round it to the closest power of 2,
 because it makes it easier to reduce or increase PG count later by dividing or
 multiplying it by 2.
@ -223,69 +191,6 @@ never put on OSDs in the same failure domain (for example, on the same host).
 So failure domain specifies the unit which failure you are protecting yourself
 from.
 ## level_placement
 - Type: string
 Additional failure domain rules, applied in conjuction with failure_domain.
 Must be specified in the following form:
 `<placement level>=<sequence of characters>, <level2>=<sequence2>, ...`
 Sequence should be exactly [pg_size](#pg_size) character long. Each character
 corresponds to an OSD in the PG of this pool. Equal characters mean that
 corresponding items of the PG should be placed into the same placement tree
 item at this level. Different characters mean that items should be placed into
 different items.
 For example, if you want a EC 4+2 pool and you want every 2 chunks to be stored
 in its own datacenter and you also want each chunk to be stored on a different
 host, you should set `level_placement` to `dc=112233 host=123456`.
 Or you can set `level_placement` to `dc=112233` and leave `failure_domain` empty,
 because `host` is the default `failure_domain` and it will be applied anyway.
 Without this rule, it may happen that 3 chunks will be stored on OSDs in the
 same datacenter, and the data will become inaccessibly if that datacenter goes
 down in this case.
 Of course, you should group your hosts into datacenters before applying the rule
 by setting [placement_levels](monitor.en.md#placement_levels) to something like
 `{"dc":90,"host":100,"osd":110}` and add DCs to [node_placement](#placement-tree),
 like `{"dc1":{"level":"dc"},"host1":{"parent":"dc1"},...}`.
 ## raw_placement
 - Type: string
 Raw PG placement rules, specified in the form of a DSL (domain-specific language).
 Use only if you really know what you're doing :)
 DSL specification:
 ```
 dsl := item | item ("\n" | ",") items
 item := "any" | rules
 rules := rule | rule rules
 rule := level operator arg
 level := /\w+/
 operator := "!=" | "=" | ">" | "?="
 arg := value | "(" values ")"
 values := value | value "," values
 value := item_ref | constant_id
 item_ref := /\d+/
 constant_id := /"([^"]+)"/
 ```
 "?=" operator means "preferred". I.e. `dc ?= "meow"` means "prefer datacenter meow
 for this chunk, but put into another dc if it's unavailable".
 Examples:
 - Simple 3 replicas with failure_domain=host: `any, host!=1, host!=(1,2)`
 - EC 4+2 in 3 DC: `any, dc=1 host!=1, dc!=1, dc=3 host!=3, dc!=(1,3), dc=5 host!=5`
 - 1 replica in fixed DC + 2 in random DCs: `dc?=meow, dc!=1, dc!=(1,2)`
 ## max_osd_combinations
 - Type: integer
@ -377,25 +282,6 @@ of the OSDs containing a data chunk for a PG.
 Automatic scrubbing interval for this pool. Overrides
 [global scrub_interval setting](osd.en.md#scrub_interval).
 ## used_for_fs
 - Type: string
 If non-empty, the pool is marked as used for VitastorFS with metadata stored
 in block image (regular Vitastor volume) named as the value of this pool parameter.
 When a pool is marked as used for VitastorFS, regular block volume creation in it
 is disabled (vitastor-cli refuses to create images without --force) to protect
 the user from block volume and FS file ID collisions and data loss.
 [vitastor-nfs](../usage/nfs.ru.md), in its turn, refuses to use pools not marked
 for the corresponding FS when starting. This also implies that you can use one
 pool only for one VitastorFS.
 The second thing that is disabled for VitastorFS pools is reporting per-inode space
 usage statistics in etcd because a FS pool may store a very large number of files
 and statistics for them all would take a lot of space in etcd.
 # Examples
 ## Replicated pool
--- a/docs/config/pool.ru.md
+++ b/docs/config/pool.ru.md
@ -31,8 +31,6 @@
 - [pg_minsize](#pg_minsize)
 - [pg_count](#pg_count)
 - [failure_domain](#failure_domain)
 - [level_placement](#level_placement)
 - [raw_placement](#raw_placement)
 - [max_osd_combinations](#max_osd_combinations)
 - [block_size](#block_size)
 - [bitmap_granularity](#bitmap_granularity)
@ -42,7 +40,6 @@
 - [osd_tags](#osd_tags)
 - [primary_affinity_tags](#primary_affinity_tags)
 - [scrub_interval](#scrub_interval)
 - [used_for_fs](#used_for_fs)
 Примеры:
@ -85,11 +82,10 @@
 Настройки отдельных OSD задаются в ключах etcd `/vitastor/config/osd/<number>`
 в JSON-формате `{"<key>":<value>}`.
-На данный момент поддерживаются следующие настройки:
+На данный момент поддерживаются две настройки:
 - [reweight](#reweight)
 - [tags](#tags)
 - [noout](#noout)
 ## reweight
@ -113,14 +109,6 @@
 всех. Можно, например, пометить SSD OSD тегом "ssd", а HDD тегом "hdd", в
 этом смысле теги работают аналогично классам устройств.
 ## noout
 - Тип: булево (да/нет)
 - Значение по умолчанию: false
 Если установлено в true, то [osd_out_time](monitor.ru.md#osd_out_time) для этого
 OSD игнорируется и OSD не удаляется из распределения данных монитором.
 # Параметры
 ## name
@ -169,25 +157,9 @@ OSD игнорируется и OSD не удаляется из распред
 OSD, PG деактивируется на чтение и запись. Иными словами, всегда известно,
 что новые блоки данных всегда записываются как минимум на pg_minsize дисков.
-Для примера, разница между pg_minsize 2 и 1 в реплицированном пуле с 3 копиями
+По сути, разница pg_size и pg_minsize задаёт число отказов дисков, которые пул
-данных (pg_size=3), проявляется следующим образом:
+может пережить без временной (на [osd_out_time](monitor.ru.md#osd_out_time))
- Если 2 сервера отключаются при pg_minsize=2, пул становится неактивным и
+остановки обслуживания.
  остаётся неактивным в течение [osd_out_time](monitor.ru.md#osd_out_time)
  (10 минут), после чего монитор назначает другие OSD/серверы на замену, пул
  поднимается и начинает восстанавливать недостающие копии данных. Соответственно,
  если OSD на замену нет - то есть, если у вас всего 3 сервера с OSD и 2 из них
  недоступны - пул так и остаётся недоступным до тех пор, пока вы не вернёте
  или не добавите хотя бы 1 сервер (или не переключите failure_domain на "osd").
 - Если 2 сервера отключаются при pg_minsize=1, ввод-вывод лишь приостанавливается
  на короткое время, до тех пор, пока монитор не поймёт, что OSD отключены
  (что занимает 5-10 секунд при стандартном [etcd_report_interval](osd.ru.md#etcd_report_interval)).
  После этого ввод-вывод восстанавливается, но новые данные временно пишутся
  всего в 1 копии. Когда же проходит osd_out_time, монитор точно так же назначает
  другие OSD на замену выбывшим и пул начинает восстанавливать копии данных.
 То есть, pg_minsize регулирует число отказов, которые пул может пережить без
 временной остановки обслуживания на [osd_out_time](monitor.ru.md#osd_out_time),
 но ценой немного пониженных гарантий надёжности.
 FIXME: Поведение pg_minsize может быть изменено в будущем с полной деактивации
 PG на перевод их в режим только для чтения.
@ -200,8 +172,8 @@ PG на перевод их в режим только для чтения.
 Число PG для данного пула. Число должно быть достаточно большим, чтобы монитор
 мог равномерно распределить по ним данные.
-Обычно это означает примерно 10-100 PG на 1 OSD, т.е. pg_count можно устанавливать
+Обычно это означает примерно 64-128 PG на 1 OSD, т.е. pg_count можно устанавливать
-равным (общему числу OSD * 10 / pg_size). Значение можно округлить до ближайшей
+равным (общему числу OSD * 100 / pg_size). Значение можно округлить до ближайшей
 степени 2, чтобы потом было легче уменьшать или увеличивать число PG, умножая
 или деля его на 2.
@ -222,71 +194,6 @@ PG в Vitastor эферемерны, то есть вы можете менят
 Иными словами, домен отказа - это то, от отказа чего вы защищаете себя избыточным
 хранением.
 ## level_placement
 - Тип: строка
 Правила дополнительных доменов отказа, применяемые вместе с failure_domain.
 Должны задаваться в следующем виде:
 `<уровень>=<последовательность символов>, <уровень2>=<последовательность2>, ...`
 Каждая `<последовательность>` должна состоять ровно из [pg_size](#pg_size) символов.
 Каждый символ соответствует одному OSD (размещению одной части PG) этого пула.
 Одинаковые символы означают, что соответствующие части размещаются в один и тот же
 узел дерева OSD на заданном `<уровне>`. Разные символы означают, что части
 размещаются в разные узлы.
 Например, если вы хотите сделать пул EC 4+2 и хотите поместить каждые 2 части
 данных в свой датацентр, и также вы хотите, чтобы каждая часть размещалась на
 другом хосте, то вы должны задать `level_placement` равным `dc=112233 host=123456`.
 Либо вы просто можете задать `level_placement` равным `dc=112233` и оставить
 `failure_domain` пустым, т.к. `host` это его значение по умолчанию и оно также
 применится автоматически.
 Без этого правила может получиться так, что в одном из датацентров окажется
 3 части данных одной PG и данные окажутся недоступными при временном отключении
 этого датацентра.
 Естественно, перед установкой правила вам нужно сгруппировать ваши хосты в
 датацентры, установив [placement_levels](monitor.ru.md#placement_levels) во что-то
 типа `{"dc":90,"host":100,"osd":110}` и добавив датацентры в [node_placement](#дерево-размещения),
 примерно так: `{"dc1":{"level":"dc"},"host1":{"parent":"dc1"},...}`.
 ## raw_placement
 - Type: string
 Низкоуровневые правила генерации PG в форме DSL (доменно-специфичного языка).
 Используйте, только если действительно знаете, зачем вам это надо :)
 Спецификация DSL:
 ```
 dsl := item | item ("\n" | ",") items
 item := "any" | rules
 rules := rule | rule rules
 rule := level operator arg
 level := /\w+/
 operator := "!=" | "=" | ">" | "?="
 arg := value | "(" values ")"
 values := value | value "," values
 value := item_ref | constant_id
 item_ref := /\d+/
 constant_id := /"([^"]+)"/
 ```
 Оператор "?=" означает "предпочитаемый". Т.е. `dc ?= "meow"` означает "предпочитать
 датацентр meow для этой части данных, но разместить её в другом датацентре, если
 meow недоступен".
 Примеры:
 - Простые 3 реплики с failure_domain=host: `any, host!=1, host!=(1,2)`
 - EC 4+2 в 3 датацентрах: `any, dc=1 host!=1, dc!=1, dc=3 host!=3, dc!=(1,3), dc=5 host!=5`
 - 1 копия в фиксированном ДЦ + 2 в других ДЦ: `dc?=meow, dc!=1, dc!=(1,2)`
 ## max_osd_combinations
 - Тип: целое число
@ -383,27 +290,6 @@ OSD с "all".
 Интервал скраба, то есть, автоматической фоновой проверки данных для данного пула.
 Переопределяет [глобальную настройку scrub_interval](osd.ru.md#scrub_interval).
 ## used_for_fs
 - Type: string
 Если непусто, пул помечается как используемый для файловой системы VitastorFS с
 метаданными, хранимыми в блочном образе Vitastor с именем, равным значению
 этого параметра.
 Когда пул помечается как используемый для VitastorFS, создание обычных блочных
 образов в нём отключается (vitastor-cli отказывается создавать образы без --force),
 чтобы защитить пользователя от коллизий ID файлов и блочных образов и, таким
 образом, от потери данных.
 [vitastor-nfs](../usage/nfs.ru.md), в свою очередь, при запуске отказывается
 использовать для ФС пулы, не выделенные для неё. Это также означает, что один
 пул может использоваться только для одной VitastorFS.
 Также для ФС-пулов отключается передача статистики в etcd по отдельным инодам,
 так как ФС-пул может содержать очень много файлов и статистика по ним всем
 заняла бы очень много места в etcd.
 # Примеры
 ## Реплицированный пул
--- a/docs/config/src/client.yml
+++ b/docs/config/src/client.yml
@ -1,37 +1,3 @@
 - name: client_retry_interval
  type: ms
  min: 10
  default: 50
  online: true
  info: |
    Retry time for I/O requests failed due to inactive PGs or network
    connectivity errors.
  info_ru: |
    Время повтора запросов ввода-вывода, неудачных из-за неактивных PG или
    ошибок сети.
 - name: client_eio_retry_interval
  type: ms
  default: 1000
  online: true
  info: |
    Retry time for I/O requests failed due to data corruption or unfinished
    EC object deletions (has_incomplete PG state). 0 disables such retries
    and clients are not blocked and just get EIO error code instead.
  info_ru: |
    Время повтора запросов ввода-вывода, неудачных из-за повреждения данных
    или незавершённых удалений EC-объектов (состояния PG has_incomplete).
    0 отключает повторы таких запросов и клиенты не блокируются, а вместо
    этого просто получают код ошибки EIO.
 - name: client_retry_enospc
  type: bool
  default: true
  online: true
  info: |
    Retry writes on out of space errors to wait until some space is freed on
    OSDs.
  info_ru: |
    Повторять запросы записи, завершившиеся с ошибками нехватки места, т.е.
    ожидать, пока на OSD не освободится место.
 - name: client_max_dirty_bytes
  type: int
  default: 33554432
@ -200,27 +166,3 @@
    Максимальное число разделов на одном NBD-устройстве. Данное значение передаётся
    модулю ядра nbd как параметр `max_part`, когда его загружает vitastor-nbd.
    Имейте в виду, что (nbds_max)*(1+max_part) обычно не может превышать 256.
 - name: osd_nearfull_ratio
  type: float
  default: 0.95
  online: true
  info: |
    Ratio of used space on OSD to treat it as "almost full" in vitastor-cli status output.
    Remember that some client writes may hang or complete with an error if even
    just one OSD becomes 100 % full!
    However, unlike in Ceph, 100 % full Vitastor OSDs don't crash (in Ceph they're
    unable to start at all), so you'll be able to recover from "out of space" errors
    without destroying and recreating OSDs.
  info_ru: |
    Доля занятого места на OSD, начиная с которой он считается "почти заполненным" в
    выводе vitastor-cli status.
    Помните, что часть клиентских запросов может зависнуть или завершиться с ошибкой,
    если на 100 % заполнится хотя бы 1 OSD!
    Однако, в отличие от Ceph, заполненные на 100 % OSD Vitastor не падают (в Ceph
    заполненные на 100% OSD вообще не могут стартовать), так что вы сможете
    восстановить работу кластера после ошибок отсутствия свободного места
    без уничтожения и пересоздания OSD.
--- a/docs/config/src/included.en.md
+++ b/docs/config/src/included.en.md
@ -56,8 +56,6 @@
 {{../../usage/nfs.en.md}}
 {{../../usage/admin.en.md}}
 ## Performance
 {{../../performance/understanding.en.md}}
@ -66,6 +64,4 @@
 {{../../performance/comparison1.en.md}}
 {{../../performance/bench2.en.md}}
 {{../../intro/author.en.md|indent=1}}
--- a/docs/config/src/included.ru.md
+++ b/docs/config/src/included.ru.md
@ -56,8 +56,6 @@
 {{../../usage/nfs.ru.md}}
 {{../../usage/admin.ru.md}}
 ## Производительность
 {{../../performance/understanding.ru.md}}
@ -66,6 +64,4 @@
 {{../../performance/comparison1.ru.md}}
 {{../../performance/bench2.ru.md}}
 {{../../intro/author.ru.md|indent=1}}
--- a/docs/config/src/monitor.yml
+++ b/docs/config/src/monitor.yml
@ -63,12 +63,3 @@
    "host" и "osd" являются предопределёнными и не могут быть удалены. Если
    один из них отсутствует в конфигурации, он доопределяется с приоритетом по
    умолчанию (100 для уровня "host", 101 для "osd").
 - name: use_old_pg_combinator
  type: bool
  default: false
  info: |
    Use the old PG combination generator which doesn't support [level_placement](pool.en.md#level_placement)
    and [raw_placement](pool.en.md#raw_placement) for pools which don't use this features.
  info_ru: |
    Использовать старый генератор комбинаций PG, не поддерживающий [level_placement](pool.ru.md#level_placement)
    и [raw_placement](pool.ru.md#raw_placement) для пулов, которые не используют данные функции.
--- a/docs/config/src/network.yml
+++ b/docs/config/src/network.yml
@ -243,6 +243,21 @@
    Максимальное время ожидания ответа на запрос проверки состояния соединения.
    Если OSD не отвечает за это время, соединение отключается и производится
    повторная попытка соединения.
 - name: up_wait_retry_interval
  type: ms
  min: 10
  default: 50
  online: true
  info: |
    OSDs respond to clients with a special error code when they receive I/O
    requests for a PG that's not synchronized and started. This parameter sets
    the time for the clients to wait before re-attempting such I/O requests.
  info_ru: |
    Когда OSD получают от клиентов запросы ввода-вывода, относящиеся к не
    поднятым на данный момент на них PG, либо к PG в процессе синхронизации,
    они отвечают клиентам специальным кодом ошибки, означающим, что клиент
    должен некоторое время подождать перед повторением запроса. Именно это время
    ожидания задаёт данный параметр.
 - name: max_etcd_attempts
  type: int
  default: 5
@ -280,9 +295,9 @@
  info_ru: |
    Таймаут для HTTP Keep-Alive в соединениях к etcd. Должен быть больше, чем
    etcd_report_interval, чтобы keepalive гарантированно работал.
- name: etcd_ws_keepalive_interval
+- name: etcd_ws_keepalive_timeout
  type: sec
-  default: 5
+  default: 30
  online: true
  info: |
    etcd websocket ping interval required to keep the connection alive and
--- a/docs/installation/openstack.en.md
+++ b/docs/installation/openstack.en.md
@ -11,8 +11,7 @@ To enable Vitastor support in an OpenStack installation:
 - Install vitastor-client, patched QEMU and libvirt packages from Vitastor DEB or RPM repository
 - Use `patches/nova-21.diff` or `patches/nova-23.diff` to patch your Nova installation.
  Patch 21 fits Nova 21-22, patch 23 fits Nova 23-24.
- Install `patches/cinder-vitastor-21.py` or `pathces/cinder-vitastor-22.py` as `..../cinder/volume/drivers/vitastor.py`
+- Install `patches/cinder-vitastor.py` as `..../cinder/volume/drivers/vitastor.py`
  Patch 21 fits Cinder up 21 (zed), Patch 22 fits Cinder after 22 (2023.1)
 - Define a volume type in cinder.conf (see below)
 - Block network access from VMs to Vitastor network (to OSDs and etcd),
  because Vitastor doesn't support authentication
--- a/docs/installation/openstack.ru.md
+++ b/docs/installation/openstack.ru.md
@ -11,8 +11,7 @@
 - Установите пакеты vitastor-client, libvirt и QEMU из DEB или RPM репозитория Vitastor
 - Примените патч `patches/nova-21.diff` или `patches/nova-23.diff` к вашей инсталляции Nova.
  nova-21.diff подходит для Nova 21-22, nova-23.diff подходит для Nova 23-24.
- Скопируйте `patches/cinder-vitastor-21.py` или `pathces/cinder-vitastor-22.py` в инсталляцию Cinder как `cinder/volume/drivers/vitastor.py`.
+- Скопируйте `patches/cinder-vitastor.py` в инсталляцию Cinder как `cinder/volume/drivers/vitastor.py`
  `cinder-vitastor-21.py` подходит для Cinder 21 (zed) и младше, `cinder-vitastor-22.py` подходит для Cinder 22 (2023.1) и старше.
 - Создайте тип томов в cinder.conf (см. ниже)
 - Обязательно заблокируйте доступ от виртуальных машин к сети Vitastor (OSD и etcd), т.к. Vitastor (пока) не поддерживает аутентификацию
 - Перезапустите Cinder и Nova
--- a/docs/installation/source.en.md
+++ b/docs/installation/source.en.md
@ -41,7 +41,7 @@ It's recommended to build the QEMU driver (qemu_driver.c) in-tree, as a part of
 QEMU build process. To do that:
 - Install vitastor client library headers (from source or from vitastor-client-dev package)
 - Take a corresponding patch from `patches/qemu-*-vitastor.patch` and apply it to QEMU source
- Copy `src/client/qemu_driver.c` to QEMU source directory as `block/vitastor.c`
+- Copy `src/qemu_driver.c` to QEMU source directory as `block/vitastor.c`
 - Build QEMU as usual
 But it is also possible to build it out-of-tree. To do that:
--- a/docs/installation/source.ru.md
+++ b/docs/installation/source.ru.md
@ -41,7 +41,7 @@ cmake .. && make -j8 install
 Драйвер QEMU (qemu_driver.c) рекомендуется собирать вместе с самим QEMU. Для этого:
 - Установите заголовки клиентской библиотеки Vitastor (из исходников или из пакета vitastor-client-dev)
 - Возьмите соответствующий патч из `patches/qemu-*-vitastor.patch` и примените его к исходникам QEMU
- Скопируйте [src/client/qemu_driver.c](../../src/client/qemu_driver.c) в директорию исходников QEMU как `block/vitastor.c`
+- Скопируйте [src/qemu_driver.c](../../src/qemu_driver.c) в директорию исходников QEMU как `block/vitastor.c`
 - Соберите QEMU как обычно
 Однако в целях отладки драйвер также можно собирать отдельно от QEMU. Для этого:
--- a/docs/intro/features.en.md
+++ b/docs/intro/features.en.md
@ -13,7 +13,7 @@
 ## Server-side features
 - Basic part: highly-available block storage with symmetric clustering and no SPOF
- [Performance](../performance/bench2.en.md) ;-D
+- [Performance](../performance/comparison1.en.md) ;-D
 - [Multiple redundancy schemes](../config/pool.en.md#scheme): Replication, XOR n+1, Reed-Solomon erasure codes
  based on jerasure and ISA-L libraries with any number of data and parity drives in a group
 - Configuration via simple JSON data structures in etcd (parameters, pools and images)
@ -33,7 +33,6 @@
 - [Checksums](../config/layout-osd.en.md#data_csum_type)
 - [Client write-back cache](../config/client.en.md#client_enable_writeback)
 - [Intelligent recovery auto-tuning](../config/osd.en.md#recovery_tune_interval)
 - [Clustered file system](../usage/nfs.en.md#vitastorfs)
 ## Plugins and tools
@ -47,12 +46,13 @@
 - [CSI plugin for Kubernetes](../installation/kubernetes.en.md)
 - [OpenStack support: Cinder driver, Nova and libvirt patches](../installation/openstack.en.md)
 - [Proxmox storage plugin and packages](../installation/proxmox.en.md)
- [Simplified NFS proxy for file-based image access emulation (suitable for VMWare)](../usage/nfs.en.md#pseudo-fs)
+- [Simplified NFS proxy for file-based image access emulation (suitable for VMWare)](../usage/nfs.en.md)
 ## Roadmap
 The following features are planned for the future:
 - File system
 - Control plane optimisation
 - Other administrative tools
 - Web GUI
--- a/docs/intro/features.ru.md
+++ b/docs/intro/features.ru.md
@ -13,7 +13,7 @@
 ## Серверные функции
 - Базовая часть - надёжное кластерное блочное хранилище без единой точки отказа
- [Производительность](../performance/bench2.ru.md) ;-D
+- [Производительность](../performance/comparison1.ru.md) ;-D
 - [Несколько схем отказоустойчивости](../config/pool.ru.md#scheme): репликация, XOR n+1 (1 диск чётности), коды коррекции ошибок
  Рида-Соломона на основе библиотек jerasure и ISA-L с любым числом дисков данных и чётности в группе
 - Конфигурация через простые человекочитаемые JSON-структуры в etcd
@ -35,7 +35,6 @@
 - [Контрольные суммы](../config/layout-osd.ru.md#data_csum_type)
 - [Буферизация записи на стороне клиента](../config/client.ru.md#client_enable_writeback)
 - [Интеллектуальная автоподстройка скорости восстановления](../config/osd.ru.md#recovery_tune_interval)
 - [Кластерная файловая система](../usage/nfs.ru.md#vitastorfs)
 ## Драйверы и инструменты
@ -49,10 +48,11 @@
 - [CSI-плагин для Kubernetes](../installation/kubernetes.ru.md)
 - [Базовая поддержка OpenStack: драйвер Cinder, патчи для Nova и libvirt](../installation/openstack.ru.md)
 - [Плагин для Proxmox](../installation/proxmox.ru.md)
- [Упрощённая NFS-прокси для эмуляции файлового доступа к образам (подходит для VMWare)](../usage/nfs.ru.md#псевдо-фс)
+- [Упрощённая NFS-прокси для эмуляции файлового доступа к образам (подходит для VMWare)](../usage/nfs.ru.md)
 ## Планы развития
 - Файловая система
 - Оптимизация слоя управления
 - Другие инструменты администрирования
 - Web-интерфейс
--- a/docs/intro/quickstart.en.md
+++ b/docs/intro/quickstart.en.md
@ -14,7 +14,6 @@
 - [Check cluster status](#check-cluster-status)
 - [Create an image](#create-an-image)
 - [Install plugins](#install-plugins)
 - [Create VitastorFS](#create-vitastorfs)
 ## Preparation
@ -22,7 +21,7 @@
  with lazy fsync, but prepare for inferior single-thread latency. Read more about capacitors
  [here](../config/layout-cluster.en.md#immediate_commit).
 - If you want to use HDDs, get modern HDDs with Media Cache or SSD Cache: HGST Ultrastar,
-  Toshiba MG, Seagate EXOS or something similar. If your drives don't have such cache then
+  Toshiba MG08, Seagate EXOS or something similar. If your drives don't have such cache then
  you also need small SSDs for journal and metadata (even 2 GB per 1 TB of HDD space is enough).
 - Get a fast network (at least 10 Gbit/s). Something like Mellanox ConnectX-4 with RoCEv2 is ideal.
 - Disable CPU powersaving: `cpupower idle-set -D 0 && cpupower frequency-set -g performance`.
@ -33,7 +32,7 @@
 - SATA SSD: Micron 5100/5200/5300/5400, Samsung PM863/PM883/PM893, Intel D3-S4510/4520/4610/4620, Kingston DC500M
 - NVMe: Micron 9100/9200/9300/9400, Micron 7300/7450, Samsung PM983/PM9A3, Samsung PM1723/1735/1743,
  Intel DC-P3700/P4500/P4600, Intel D7-P5500/P5600, Intel Optane, Kingston DC1000B/DC1500M
- HDD: HGST Ultrastar, Toshiba MG, Seagate EXOS
+- HDD: HGST Ultrastar, Toshiba MG06/MG07/MG08, Seagate EXOS
 ## Configure monitors
@ -76,16 +75,18 @@ On the monitor hosts:
 ## Create a pool
-Create a pool using vitastor-cli:
+Create pool configuration in etcd:
 ```
-vitastor-cli create-pool testpool --pg_size 2 --pg_count 256
+etcdctl --endpoints=... put /vitastor/config/pools '{"1":{"name":"testpool",
  "scheme":"replicated","pg_size":2,"pg_minsize":1,"pg_count":256,"failure_domain":"host"}}'
 ```
 For EC pools the configuration should look like the following:
 ```
-vitastor-cli create-pool testpool --ec 2+2 --pg_count 256
+etcdctl --endpoints=... put /vitastor/config/pools '{"2":{"name":"ecpool",
  "scheme":"ec","pg_size":4,"parity_chunks":2,"pg_minsize":2,"pg_count":256,"failure_domain":"host"}}'
 ```
 After you do this, one of the monitors will configure PGs and OSDs will start them.
@ -115,9 +116,3 @@ After that, you can [run benchmarks](../usage/fio.en.md) or [start QEMU manually
 - [Proxmox](../installation/proxmox.en.md)
 - [OpenStack](../installation/openstack.en.md)
 - [Kubernetes CSI](../installation/kubernetes.en.md)
 ## Create VitastorFS
 If you want to use clustered file system in addition to VM or container images:
 - [Follow the instructions here](../usage/nfs.en.md#vitastorfs)
--- a/docs/intro/quickstart.ru.md
+++ b/docs/intro/quickstart.ru.md
@ -14,7 +14,6 @@
 - [Проверьте состояние кластера](#проверьте-состояние-кластера)
 - [Создайте образ](#создайте-образ)
 - [Установите плагины](#установите-плагины)
 - [Создайте VitastorFS](#создайте-vitastorfs)
 ## Подготовка
@ -78,16 +77,18 @@
 ## Создайте пул
-Создайте пул с помощью vitastor-cli:
+Создайте конфигурацию пула с помощью etcdctl:
 ```
-vitastor-cli create-pool testpool --pg_size 2 --pg_count 256
+etcdctl --endpoints=... put /vitastor/config/pools '{"1":{"name":"testpool",
  "scheme":"replicated","pg_size":2,"pg_minsize":1,"pg_count":256,"failure_domain":"host"}}'
 ```
 Для пулов с кодами коррекции ошибок конфигурация должна выглядеть примерно так:
 ```
-vitastor-cli create-pool testpool --ec 2+2 --pg_count 256
+etcdctl --endpoints=... put /vitastor/config/pools '{"2":{"name":"ecpool",
  "scheme":"ec","pg_size":4,"parity_chunks":2,"pg_minsize":2,"pg_count":256,"failure_domain":"host"}}'
 ```
 После этого один из мониторов должен сконфигурировать PG, а OSD должны запустить их.
@ -117,10 +118,3 @@ vitastor-cli create -s 10G testimg
 - [Proxmox](../installation/proxmox.ru.md)
 - [OpenStack](../installation/openstack.ru.md)
 - [Kubernetes CSI](../installation/kubernetes.ru.md)
 ## Создайте VitastorFS
 Если вы хотите использовать не только блочные образы виртуальных машин или контейнеров,
 а также кластерную файловую систему, то:
 - [Следуйте инструкциям](../usage/nfs.ru.md#vitastorfs)
--- a/docs/performance/bench2.en.md
+++ b/docs/performance/bench2.en.md
@ -1,154 +0,0 @@
 [Documentation](../../README.md#documentation) → Performance → Newer benchmark of Vitastor 1.3.1
 -----
 [Читать на русском](bench2.ru.md)
 # Newer benchmark of Vitastor 1.3.1
 - [Test environment](#test-environment)
 - [Notes](#notes)
 - [Raw drive performance](#raw-drive-performance)
 - [2 replicas](#2-replicas)
 - [3 replicas](#3-replicas)
 - [EC 2+1](#ec-2-1)
 ## Test environment
 Hardware configuration: 3 nodes, each with:
 - 8x NVMe Samsung PM9A3 1.92 TB
 - 2x Xeon Gold 6342 (24 cores @ 2.8 GHz)
 - 256 GB RAM
 - Dual-port 25 GbE Mellanox ConnectX-4 LX network card with RoCEv2
 - Connected to 2 Mellanox SN2010 switches with MLAG
 ## Notes
 Vitastor version was 1.3.1.
 Tests were ran from the storage nodes - 4 fio clients per each of 3 nodes.
 The same large 3 TB image was tested from all hosts because Vitastor has no
 performance penalties related to running multiple clients over a single inode.
 CPU power saving was disabled. 4 OSDs were created per each NVMe.
 Checksums were not enabled. Tests with checksums will be conducted later,
 along with the newer version of Vitastor, and results will be updated.
 CPU configuration was not optimal because of NUMA. It's better to avoid 2-socket
 platforms. It was especially noticeable in RDMA tests - in the form of ksoftirqd
 processes (usually 1 per server) eating 100 % of one CPU core and actual bandwidth
 of one network port reduced to 3-5 Gbit/s instead of 25 Gbit/s - probably because
 of RFS (Receive Flow Steering) misses. Many network configurations were tried during
 tests, but nothing helped to solve this problem, so final tests were conducted with
 the default settings.
 # Raw drive performance
 - Linear write ~1000-2000 MB/s, depending on current state of the drive's garbage collector
 - Linear read ~3300 MB/s
 - T1Q1 random write ~60000 iops (latency ~0.015ms)
 - T1Q1 random read ~14700 iops (latency ~0.066ms)
 - T1Q16 random write ~180000 iops
 - T1Q16 random read ~120000 iops
 - T1Q32 random write ~180000 iops
 - T1Q32 random read ~195000 iops
 - T1Q128 random write ~180000 iops
 - T1Q128 random read ~195000 iops
 - T4Q128 random write ~525000 iops
 - T4Q128 random read ~750000 iops
 These numbers make obvious that results could be much better if a faster network
 was available, because NVMe drives obviously weren't a bottleneck. For example,
 theoretical maximum linear read performance for 24 drives could be 79.2 GByte/s,
 which is 633 Gbit/s. Real Vitastor read speed (both linear and random) was around
 16 Gbyte/s, which is 130 Gbit/s. It's important to note that it was still much
 larger than the network bandwidth of one server (50 Gbit/s). This is also correct
 because tests were conducted from all 3 nodes.
 ## 2 replicas
 |                              | TCP          | RDMA         |
 |------------------------------|--------------|--------------|
 | Linear read (4M T6 Q16)      | 13.13 GB/s   | 16.25 GB/s   |
 | Linear write (4M T6 Q16)     | 8.16 GB/s    | 7.88 GB/s    |
 | Read 4k T1 Q1                | 8745 iops    | 10252 iops   |
 | Write 4k T1 Q1               | 8097 iops    | 11488 iops   |
 | Read 4k T12 Q128             | 1305936 iops | 4265861 iops |
 | Write 4k T12 Q128            | 660490 iops  | 1384033 iops |
 CPU consumption OSD per 1 disk:
 |                              | TCP     | RDMA    |
 |------------------------------|---------|---------|
 | Linear read (4M T6 Q16)      | 29.7 %  | 29.8 %  |
 | Linear write (4M T6 Q16)     | 84.4 %  | 33.2 %  |
 | Read 4k T12 Q128             | 98.4 %  | 119.1 % |
 | Write 4k T12 Q128            | 173.4 % | 175.9 % |
 CPU consumption per 1 client (fio):
 |                              | TCP    | RDMA   |
 |------------------------------|--------|--------|
 | Linear read (4M T6 Q16)      | 100 %  | 85.2 % |
 | Linear write (4M T6 Q16)     | 55.8 % | 48.8 % |
 | Read 4k T12 Q128             | 99.9 % | 96 %   |
 | Write 4k T12 Q128            | 71.6 % | 48.5 % |
 ## 3 replicas
 |                              | TCP          | RDMA         |
 |------------------------------|--------------|--------------|
 | Linear read (4M T6 Q16)      | 13.98 GB/s   | 16.54 GB/s   |
 | Linear write (4M T6 Q16)     | 5.38 GB/s    | 5.7 GB/s     |
 | Read 4k T1 Q1                | 8969 iops    | 9980 iops    |
 | Write 4k T1 Q1               | 8126 iops    | 11672 iops   |
 | Read 4k T12 Q128             | 1358818 iops | 4279088 iops |
 | Write 4k T12 Q128            | 433890 iops  | 993506 iops  |
 CPU consumption OSD per 1 disk:
 |                              | TCP    | RDMA    |
 |------------------------------|--------|---------|
 | Linear read (4M T6 Q16)      | 24.9 % | 25.4 %  |
 | Linear write (4M T6 Q16)     | 99.3 % | 38.4 %  |
 | Read 4k T12 Q128             | 95.3 % | 111.7 % |
 | Write 4k T12 Q128            | 173 %  | 194 %   |
 CPU consumption per 1 client (fio):
 |                              | TCP    | RDMA   |
 |------------------------------|--------|--------|
 | Linear read (4M T6 Q16)      | 99.9 % | 85.8 % |
 | Linear write (4M T6 Q16)     | 38.9 % | 38.1 % |
 | Read 4k T12 Q128             | 100 %  | 96.1 % |
 | Write 4k T12 Q128            | 51.6 % | 41.9 % |
 ## EC 2+1
 |                              | TCP          | RDMA         |
 |------------------------------|--------------|--------------|
 | Linear read (4M T6 Q16)      | 10.07 GB/s   | 11.43 GB/s   |
 | Linear write (4M T6 Q16)     | 7.74 GB/s    | 8.32 GB/s    |
 | Read 4k T1 Q1                | 7408 iops    | 8891 iops    |
 | Write 4k T1 Q1               | 3525 iops    | 4903 iops    |
 | Read 4k T12 Q128             | 1216496 iops | 2552765 iops |
 | Write 4k T12 Q128            | 278110 iops  | 821261 iops  |
 CPU consumption OSD per 1 disk:
 |                              | TCP     | RDMA    |
 |------------------------------|---------|---------|
 | Linear read (4M T6 Q16)      | 68.6 %  | 33.6 %  |
 | Linear write (4M T6 Q16)     | 108.3 % | 50.2 %  |
 | Read 4k T12 Q128             | 138.1 % | 97.9 %  |
 | Write 4k T12 Q128            | 168.7 % | 188.5 % |
 CPU consumption per 1 client (fio):
 |                              | TCP    | RDMA   |
 |------------------------------|--------|--------|
 | Linear read (4M T6 Q16)      | 88.2 % | 52.4 % |
 | Linear write (4M T6 Q16)     | 51.8 % | 46.8 % |
 | Read 4k T12 Q128             | 99.7 % | 61.3 % |
 | Write 4k T12 Q128            | 35.1 % | 31.3 % |
--- a/docs/performance/bench2.ru.md
+++ b/docs/performance/bench2.ru.md
@ -1,157 +0,0 @@
 [Документация](../../README-ru.md#документация) → Производительность → Более новый тест Vitastor 1.3.1
 -----
 [Read in English](bench2.en.md)
 # Более новый тест Vitastor 1.3.1
 - [Описание стенда](#описание-стенда)
 - [Примечания](#примечания)
 - [Производительность голых дисков](#производительность-голых-дисков)
 - [2 реплики](#2-реплики)
 - [3 реплики](#3-реплики)
 - [EC 2+1](#ec-2-1)
 ## Описание стенда
 Железо: 3 сервера, в каждом:
 - 8x NVMe Samsung PM9A3 1.92 TB
 - 2x Xeon Gold 6342 (24 ядра @ 2.8 GHz)
 - 256 GB RAM
 - Двухпортовая 25 GbE сетевая карта Mellanox ConnectX-4 LX с поддержкой RoCEv2
 - Подключение к 2 коммутаторам Mellanox SN2010 в MLAG
 ## Примечания
 Версия Vitastor 1.3.1.
 Тесты проводились с самих серверов хранения - по 4 клиента fio с каждого из 3 серверов.
 Тестировался один большой образ размером 3 ТБ со всех хостов - создавать отдельные образы
 для тестов в Vitastor необязательно, т.к. в Vitastor нет замедления при записи в один
 узел несколькими клиентами.
 Экономия энергии CPU отключена. На каждый NVMe создавалось 4 OSD.
 Контрольные суммы не включались. Тесты с контрольными суммами будут проведены
 позднее. Тогда же будет протестирована более новая версия Vitastor, и результаты
 будут обновлены.
 Конфигурация CPU стенда неоптимальна из-за NUMA - двухпроцессорных серверов лучше
 избегать. Особенно это проявлялось во время тестов с RDMA - выражалось это в потреблении
 100% одного ядра CPU одним процессом ksoftirqd и работой одного из двух сетевых портов
 на скорости 3-5 ГБит/с вместо 25 ГБит/с - предположительно, из-за "непопаданий" RFS
 (Receive Flow Steering) на нужные ядра. Решить эту проблему во время проведения тестов
 не получилось. Было перепробовано множество различных настроек, но в итоге тесты проведены
 с настройками по умолчанию, т.к. улучшения добиться не удалось.
 # Производительность голых дисков
 - Линейная запись ~1000-2000 МБ/с, в зависимости от состояния сборщика мусора диска
 - Линейное чтение ~3300 МБ/с
 - T1Q1 запись ~60000 iops (задержка ~0.015ms)
 - T1Q1 чтение ~14700 iops (задержка ~0.066ms)
 - T1Q16 запись ~180000 iops
 - T1Q16 чтение ~120000 iops
 - T1Q32 запись ~180000 iops
 - T1Q32 чтение ~195000 iops
 - T1Q128 запись ~180000 iops
 - T1Q128 чтение ~195000 iops
 - T4Q128 запись ~525000 iops
 - T4Q128 чтение ~750000 iops
 Из данных цифр очевидно, что при наличии более быстрой сети результаты были бы
 значительно лучше, так как в диски тест, очевидно, не упирался. Например, теоретический предел по
 линейному чтению для 24 таких дисков был бы около 79.2 ГБайт/с, то есть,
 633 гигабита в секунду. Реальная скорость чтения (и случайного, и линейного)
 Vitastor составила примерно 16 ГБайт/с, то есть 130 гигабит в секунду. При этом
 следует заметить, что этот результат всё равно значительно лучше пропускной способности
 сети отдельно взятого узла - что тоже вполне логично, так как тест выполнялся со
 всех трёх узлов.
 ## 2 реплики
 |                              | TCP          | RDMA         |
 |------------------------------|--------------|--------------|
 | Линейное чтение (4M T6 Q16)  | 13.13 ГБ/с   | 16.25 ГБ/с   |
 | Линейная запись (4M T6 Q16)  | 8.16 ГБ/с    | 7.88 ГБ/с    |
 | Чтение 4k T1 Q1              | 8745 iops    | 10252 iops   |
 | Запись 4k T1 Q1              | 8097 iops    | 11488 iops   |
 | Чтение 4k T12 Q128           | 1305936 iops | 4265861 iops |
 | Запись 4k T12 Q128           | 660490 iops  | 1384033 iops |
 Потребление CPU OSD на 1 диск:
 |                              | TCP     | RDMA    |
 |------------------------------|---------|---------|
 | Линейное чтение (4M T6 Q16)  | 29.7 %  | 29.8 %  |
 | Линейная запись (4M T6 Q16)  | 84.4 %  | 33.2 %  |
 | Чтение 4k T12 Q128           | 98.4 %  | 119.1 % |
 | Запись 4k T12 Q128           | 173.4 % | 175.9 % |
 Потребление CPU на 1 клиента (fio):
 |                              | TCP    | RDMA   |
 |------------------------------|--------|--------|
 | Линейное чтение (4M T6 Q16)  | 100 %  | 85.2 % |
 | Линейная запись (4M T6 Q16)  | 55.8 % | 48.8 % |
 | Чтение 4k T12 Q128           | 99.9 % | 96 %   |
 | Запись 4k T12 Q128           | 71.6 % | 48.5 % |
 ## 3 реплики
 |                              | TCP          | RDMA         |
 |------------------------------|--------------|--------------|
 | Линейное чтение (4M T6 Q16)  | 13.98 ГБ/с   | 16.54 ГБ/с   |
 | Линейная запись (4M T6 Q16)  | 5.38 ГБ/с    | 5.7 ГБ/с     |
 | Чтение 4k T1 Q1              | 8969 iops    | 9980 iops    |
 | Запись 4k T1 Q1              | 8126 iops    | 11672 iops   |
 | Чтение 4k T12 Q128           | 1358818 iops | 4279088 iops |
 | Запись 4k T12 Q128           | 433890 iops  | 993506 iops  |
 Потребление CPU OSD на 1 диск:
 |                              | TCP    | RDMA    |
 |------------------------------|--------|---------|
 | Линейное чтение (4M T6 Q16)  | 24.9 % | 25.4 %  |
 | Линейная запись (4M T6 Q16)  | 99.3 % | 38.4 %  |
 | Чтение 4k T12 Q128           | 95.3 % | 111.7 % |
 | Запись 4k T12 Q128           | 173 %  | 194 %   |
 Потребление CPU на 1 клиента (fio):
 |                              | TCP    | RDMA   |
 |------------------------------|--------|--------|
 | Линейное чтение (4M T6 Q16)  | 99.9 % | 85.8 % |
 | Линейная запись (4M T6 Q16)  | 38.9 % | 38.1 % |
 | Чтение 4k T12 Q128           | 100 %  | 96.1 % |
 | Запись 4k T12 Q128           | 51.6 % | 41.9 % |
 ## EC 2+1
 |                              | TCP          | RDMA         |
 |------------------------------|--------------|--------------|
 | Линейное чтение (4M T6 Q16)  | 10.07 ГБ/с   | 11.43 ГБ/с   |
 | Линейная запись (4M T6 Q16)  | 7.74 ГБ/с    | 8.32 ГБ/с    |
 | Чтение 4k T1 Q1              | 7408 iops    | 8891 iops    |
 | Запись 4k T1 Q1              | 3525 iops    | 4903 iops    |
 | Чтение 4k T12 Q128           | 1216496 iops | 2552765 iops |
 | Запись 4k T12 Q128           | 278110 iops  | 821261 iops  |
 Потребление CPU OSD на 1 диск:
 |                              | TCP     | RDMA    |
 |------------------------------|---------|---------|
 | Линейное чтение (4M T6 Q16)  | 68.6 %  | 33.6 %  |
 | Линейная запись (4M T6 Q16)  | 108.3 % | 50.2 %  |
 | Чтение 4k T12 Q128           | 138.1 % | 97.9 %  |
 | Запись 4k T12 Q128           | 168.7 % | 188.5 % |
 Потребление CPU на 1 клиента (fio):
 |                              | TCP    | RDMA   |
 |------------------------------|--------|--------|
 | Линейное чтение (4M T6 Q16)  | 88.2 % | 52.4 % |
 | Линейная запись (4M T6 Q16)  | 51.8 % | 46.8 % |
 | Чтение 4k T12 Q128           | 99.7 % | 61.3 % |
 | Запись 4k T12 Q128           | 35.1 % | 31.3 % |
--- a/docs/usage/admin.en.md
+++ b/docs/usage/admin.en.md
@ -1,215 +0,0 @@
 [Documentation](../../README.md#documentation) → Usage → Administration
 -----
 [Читать на русском](admin.ru.md)
 # Administration
 - [Pool states](#pool-states)
 - [PG states](#pg-states)
  - [Base PG states](#base-pg-states)
  - [Additional PG states](#additional-pg-states)
 - [Removing a healthy disk](#removing-a-healthy-disk)
 - [Removing a failed disk](#removing-a-failed-disk)
 - [Adding a disk](#adding-a-disk)
 - [Restoring from lost pool configuration](#restoring-from-lost-pool-configuration)
 - [Upgrading Vitastor](#upgrading-vitastor)
 - [OSD memory usage](#osd-memory-usage)
 ## Pool states
 Pool is active — that is, fully available for client input/output — when all its PGs are
 'active' (maybe with some additional state flags).
 If at least 1 PG is inactive, pool is also inactive and all clients suspend their I/O and
 wait until you fix the cluster. :-)
 ## PG states
 PG states may be seen in [vitastor-cli status](cli.en.md#status) output.
 PG state consists of exactly 1 base state and an arbitrary number of additional states.
 ### Base PG states
 PG state always includes exactly 1 of the following base states:
 - **active** — PG is active and handles user I/O.
 - **incomplete** — Not enough OSDs are available to activate this PG. That is, more disks
  are lost than it's allowed by the pool's redundancy scheme. For example, if the pool has
  pg_size=3 and pg_minsize=1, part of the data may be written only to 1 OSD. If that exact
  OSD is lost, PG will become **incomplete**.
 - **offline** — PG isn't activated by any OSD at all. Either primary OSD isn't set for
  this PG at all (if the pool is just created), or an unavailable OSD is set as primary,
  or the primary OSD refuses to start this PG (for example, because of wrong block_size),
  or the PG is stopped by the monitor using `pause: true` flag in `/vitastor/config/pgs` in etcd.
 - **starting** — primary OSD has acquired PG lock in etcd, PG is starting.
 - **peering** — primary OSD requests PG object listings from secondary OSDs and calculates
  the PG state.
 - **repeering** — PG is waiting for current I/O operations to complete and will
  then transition to **peering**.
 - **stopping** — PG is waiting for current I/O operations to complete and will
  then transition to **offline** or be activated by another OSD.
 All states except **active** mean that PG is inactive and client I/O is suspended.
 **peering** state is normally visible only for a short period of time during OSD restarts
 and during switching primary OSD of PGs.
 **starting**, **repeering**, **stopping** states normally almost aren't visible at all.
 If you notice them for any noticeable time — chances are some operations on some OSDs hung.
 Search for "slow op" in OSD logs to find them — operations hung for more than
 [slow_log_interval](../config/osd.en.md#slow_log_interval) are logged as "slow ops".
 State transition diagram:
 ![PG state transitions](pg_states.svg "PG state transitions")
 ### Additional PG states
 If a PG is active it can also have any number of the following additional states:
 - **degraded** — PG is running on reduced number of drives (OSDs), redundancy of all
  objects in this PG is reduced.
 - **has_incomplete** — some objects in this PG are incomplete (unrecoverable), that is,
  they have too many lost EC parts (more than pool's [parity_chunks](../config/pool.en.md#parity_chunks)).
 - **has_degraded** — some objects in this PG have reduced redundancy
  compared to the rest of the PG (so PG can be degraded+has_degraded at the same time).
  These objects should be healed automatically by recovery process, unless
  it's disabled by [no_recovery](../config/osd.en.md#no_recovery).
 - **has_misplaced** — some objects in this PG are stored on an OSD set different from
  the target set of the PG. These objects should be moved automatically, unless
  rebalance is disabled by [no_rebalance](../config/osd.en.md#no_rebalance). Objects
  that are degraded and misplaced at the same time are treated as just degraded.
 - **has_unclean** — one more state normally noticeable only for very short time during
  PG activation. It's used only with EC pools and means that some objects of this PG
  have started but not finished modifications. All such objects are either quickly
  committed or rolled back by the primary OSD when starting the PG, that is why the
  state shouldn't be noticeable. If you notice it, it probably means that commit or
  rollback operations are hung.
 - **has_invalid** — PG contains objects with incorrect part ID. Never occurs normally.
  It can only occur if you delete a non-empty EC pool and then recreate it as a replica
  pool or with smaller data part count.
 - **has_corrupted** — PG has corrupted objects, discovered by checking checksums during
  read or during scrub. When possible, such objects should be recovered automatically.
  If objects remain corrupted, use [vitastor-cli describe](cli.en.md#describe) to find
  out details and/or look into the log of the primary OSD of the PG.
 - **has_inconsistent** — PG has objects with non-matching parts or copies on different OSDs,
  and it's impossible to determine which copy is correct automatically. It may happen
  if you use a pool with 2 replica and you don't enable checksums, and if data on one
  of replicas becomes corrupted. You should also use vitastor-cli [describe](cli.en.md#describe)
  and [fix](cli.en.md#fix) commands to remove the incorrect version in this case.
 - **left_on_dead** — part of the data of this PG is left on unavailable OSD that isn't
  fully removed from the cluster. You should either start the corresponding OSD back and
  let it remove the unneeded data or remove it from cluster using vitastor-cli
  [rm-osd](cli.en.md#rm-osd) if you know that it's gone forever (for example, if the disk died).
 - **scrubbing** — data [scrub](../config/osd.en.md#auto_scrub) is running for this PG.
 ## Removing a healthy disk
 Befor removing a healthy disk from the cluster set its OSD weight(s) to 0 to
 move data away. To do that, add `"reweight":0` to etcd key `/vitastor/config/osd/<OSD_NUMBER>`.
 For example:
 ```
 etcdctl --endpoints=http://1.1.1.1:2379/v3 put /vitastor/config/osd/1 '{"reweight":0}'
 ```
 Then wait until rebalance finishes and remove OSD by running `vitastor-disk purge /dev/vitastor/osdN-data`.
 ## Removing a failed disk
 If a disk is already dead, its OSD(s) are likely already stopped.
 In this case just remove OSD(s) from the cluster by running `vitastor-cli rm-osd OSD_NUMBER`.
 ## Adding a disk
 If you're adding a server, first install Vitastor packages and copy the
 `/etc/vitastor/vitastor.conf` configuration file to it.
 After that you can just run `vitastor-disk prepare /dev/nvmeXXX`, of course with
 the same parameters which you used for other OSDs in your cluster before.
 ## Restoring from lost pool configuration
 If you remove or corrupt `/vitastor/config/pools` key in etcd all pools will
 be deleted. Don't worry, the data won't be lost, but you'll need to perform
 a specific recovery procedure.
 First you need to restore previous configuration of the pool with the same ID
 and EC/replica parameters and wait until pool PGs appear in `vitastor-cli status`.
 Then add all OSDs into the history records of all PGs. You can do it by running
 the following script (just don't forget to use your own PG_COUNT and POOL_ID):
 ```
 PG_COUNT=32
 POOL_ID=1
 ALL_OSDS=$(etcdctl --endpoints=your_etcd_address:2379 get --keys-only --prefix /vitastor/osd/stats/ | \
    perl -e '$/ = undef; $a = <>; $a =~ s/\s*$//; $a =~ s!/vitastor/osd/stats/!!g; $a =~ s/\s+/,/g; print $a')
 for i in $(seq 1 $PG_COUNT); do
    etcdctl --endpoints=your_etcd_address:2379 put /vitastor/pg/history/$POOL_ID/$i '{"all_peers":['$ALL_OSDS']}'; done
 done
 ```
 After that all PGs should peer and find all previous data.
 ## Upgrading Vitastor
 Every upcoming Vitastor version is usually compatible with previous both forward
 and backward regarding the network protocol and etcd data structures.
 So, by default, if this page doesn't contain explicit different instructions, you
 can upgrade your Vitastor cluster by simply upgrading packages and restarting all
 OSDs and monitors in any order.
 Upgrading is performed without stopping clients (VMs/containers), you just need to
 upgrade and restart servers one by one. However, ideally you should restart VMs too
 to make them use the new version of the client library.
 Exceptions (specific upgrade instructions):
 - Upgrading <= 1.1.x to 1.2.0 or later, if you use EC n+k with k>=2, is recommended
  to be performed with full downtime: first you should stop all clients, then all OSDs,
  then upgrade and start everything back — because versions before 1.2.0 have several
  bugs leading to invalid data being read in EC n+k, k>=2 configurations in degraded pools.
 - Versions <= 0.8.7 are incompatible with versions >= 0.9.0, so you should first
  upgrade from <= 0.8.7 to 0.8.8 or 0.8.9, and only then to >= 0.9.x. If you upgrade
  without this intermediate step, client I/O will hang until the end of upgrade process.
 - Upgrading from <= 0.5.x to >= 0.6.x is not supported.
 Rollback:
 - Version 1.0.0 has a new disk format, so OSDs initiaziled on 1.0.0 can't be rolled
  back to 0.9.x or previous versions.
 - Versions before 0.8.0 don't have vitastor-disk, so OSDs, initialized by it, won't
  start with 0.7.x or 0.6.x. :-)
 ## OSD memory usage
 OSD uses RAM mainly for:
 - Metadata index: `data_size`/[`block_size`](../config/layout-cluster.en.md#block_size) * `approximately 1.1` * `32` bytes.
  Consumed always.
 - Copy of the on-disk metadata area: `data_size`/[`block_size`](../config/layout-cluster.en.md#block_size) * `28` bytes.
  Consumed if [inmemory_metadata](../config/osd.en.md#inmemory_metadata) isn't disabled.
 - Bitmaps: `data_size`/[`bitmap_granularity`](../config/layout-cluster.en.md#bitmap_granularity)/`8` * `2` bytes.
  Consumed always.
 - Journal index: between 0 and, approximately, journal size. Consumed always.
 - Copy of the on-disk journal area: exactly journal size. Consumed if
  [inmemory_journal](../config/osd.en.md#inmemory_journal) isn't disabled.
 - Checksums: `data_size`/[`csum_block_size`](../config/osd.en.md#csum_block_size) * 4 bytes.
  Consumed if checksums are enabled and [inmemory_metadata](../config/osd.en.md#inmemory_metadata) isn't disabled.
 bitmap_granularity is almost always 4 KB.
 So with default SSD settings (block_size=128k, journal_size=32M, csum_block_size=4k) memory usage is:
 - Metadata and bitmaps: ~600 MB per 1 TB of data.
 - Journal: up to 64 MB per 1 OSD.
 - Checksums: 1 GB per 1 TB of data.
 With default HDD settings (block_size=1M, journal_size=128M, csum_block_size=32k):
 - Metadata and bitmaps: ~128 MB per 1 TB of data.
 - Journal: up to 256 MB per 1 OSD.
 - Checksums: 128 MB per 1 TB of data.
--- a/docs/usage/admin.ru.md
+++ b/docs/usage/admin.ru.md
@ -1,211 +0,0 @@
 [Документация](../../README-ru.md#документация) → Использование → Администрирование
 -----
 [Read in English](admin.en.md)
 # Администрирование
 - [Состояния пулов](#состояния-пулов)
 - [Состояния PG](#состояния-pg)
  - [Базовые состояния PG](#базовые-состояния-pg)
  - [Дополнительные состояния PG](#дополнительные-состояния-pg)
 - [Удаление исправного диска](#удаление-исправного-диска)
 - [Удаление неисправного диска](#удаление-неисправного-диска)
 - [Добавление диска](#добавление-диска)
 - [Восстановление потерянной конфигурации пулов](#восстановление-потерянной-конфигурации-пулов)
 - [Обновление Vitastor](#обновление-vitastor)
 - [Потребление памяти OSD](#потребление-памяти-osd)
 ## Состояния пулов
 Пул активен — то есть, полностью доступен для клиентского ввода-вывода — когда все его PG
 активны, то есть, имеют статус active, возможно, с любым набором дополнительных флагов.
 Если хотя бы 1 PG неактивна, пул неактивен и все клиенты зависают и ждут, пока вы почините
 кластер. :-)
 ## Состояния PG
 Вы можете видеть состояния PG в выводе команды [vitastor-cli status](cli.ru.md#status).
 Состояние PG состоит из ровно 1 базового флага состояния, плюс любого числа дополнительных.
 ### Базовые состояния PG
 Состояние PG включает в себя ровно 1 флаг из следующих:
 - **active** — PG активна и обрабатывает запросы ввода-вывода от пользователей.
 - **incomplete** — Недостаточно живых OSD, чтобы включить эту PG.
  То есть, дисков потеряно больше, чем разрешено схемой отказоустойчивости пула и pg_minsize.
  Например, если у пула pg_size=3 и pg_minsize=1, то часть данных может записаться всего на 1 OSD.
  Если потом конкретно этот OSD упадёт, PG окажется **incomplete**.
 - **offline** — PG вообще не активирована ни одним OSD. Либо первичный OSD не назначен вообще
  (если пул только создан), либо в качестве первичного назначен недоступный OSD, либо
  назначенный OSD отказывается запускать эту PG (например, из-за несовпадения block_size),
  либо PG остановлена монитором через флаг `pause: true` в `/vitastor/config/pgs` в etcd.
 - **starting** — первичный OSD захватил блокировку PG в etcd, PG запускается.
 - **peering** — первичный OSD опрашивает вторичные OSD на предмет списков объектов данной PG и рассчитывает её состояние.
 - **repeering** — PG ожидает завершения текущих операций ввода-вывода, после чего перейдёт в состояние **peering**.
 - **stopping** — PG ожидает завершения текущих операций ввода-вывода, после чего перейдёт в состояние **offline** или поднимется на другом OSD.
 Все состояния, кроме **active**, означают, что PG неактивна и ввод-вывод приостановлен.
 Состояние **peering** в норме заметно только при перезапуске OSD или переключении первичных
 OSD, на протяжении небольшого периода времени.
 Состояния **starting**, **repeering**, **stopping** в норме практически не заметны вообще,
 PG должны очень быстро переходить из них в другие. Если эти состояния заметны
 хоть сколько-то значительное время — вероятно, какие-то операции на каких-то OSD зависли.
 Чтобы найти их, ищите "slow op" в журналах OSD — операции, зависшие дольше,
 чем на [slow_log_interval](../config/osd.ru.md#slow_log_interval), записываются в
 журналы OSD как "slow op".
 Диаграмма переходов:
 ![Диаграмма переходов](pg_states.svg "Диаграмма переходов")
 ### Дополнительные состояния PG
 Если PG активна, она также может иметь любое число дополнительных флагов состояний:
 - **degraded** — PG поднята на неполном числе дисков (OSD), избыточность хранения всех объектов снижена.
 - **has_incomplete** — часть объектов в PG неполные (невосстановимые), то есть, у них потеряно
  слишком много EC-частей (больше, чем [parity_chunks](../config/pool.ru.md#parity_chunks) пула).
 - **has_degraded** — часть объектов в PG деградированы, избыточность их хранения снижена по сравнению
  с остальным содержимым данной PG (то есть, PG может одновременно быть degraded+has_degraded).
  Данные объекты должны восстановиться автоматически, если только восстановление не отключено
  через [no_recovery](../config/osd.ru.md#no_recovery).
 - **has_misplaced** — часть объектов в PG сейчас расположена не на целевом наборе OSD этой PG.
  Данные объекты должны переместиться автоматически, если только перебалансировка не отключена
  через [no_rebalance](../config/osd.ru.md#no_rebalance). Объекты, являющиеся одновременно
  degraded и misplaced, считаются просто degraded.
 - **has_unclean** — ещё одно состояние, в норме заметное только очень короткое время при поднятии PG.
  Применяется только к EC и означает, что на каких-то OSD этой PG есть EC-части объектов, для которых
  был начат, но не завершён процесс записи. Все такие объекты первичный OSD либо завершает, либо
  откатывает при поднятии PG первым делом, поэтому состояние и не должно быть заметно. Опять-таки,
  если оно заметно — значит, скорее всего, операции отката или завершения записи на каких-то OSD зависли.
 - **has_invalid** — в PG найдены объекты с некорректными ID части. В норме не проявляется вообще
  никогда, проявляется только если, не удалив данные, создать на месте EC-пула либо реплика-пул,
  либо EC-пул с меньшим числом частей данных.
 - **has_corrupted** — в PG есть повреждённые объекты, обнаруженные с помощью контрольных сумм или
  скраба (сверки копий). Если объекты можно восстановить, они восстановятся автоматически. Если
  не восстанавливаются, используйте команду [vitastor-cli describe](cli.ru.md#describe) для
  выяснения деталей и/или смотрите в журнал первичного OSD данной PG.
 - **has_inconsistent** — в PG есть объекты, у которых не совпадают копии/части данных на разных OSD,
  и при этом автоматически определить, какая копия верная, а какая нет, невозможно. Такое может
  произойти, если вы используете 2 реплики, не включали контрольные суммы, и на одной из реплик
  данные повредились. В этом случае тоже надо использовать команды vitastor-cli [describe](cli.ru.md#describe)
  и [fix](cli.ru.md#fix) для удаления некорректной версии.
 - **left_on_dead** — часть данных PG осталась на отключённом, но не удалённом из кластера окончательно,
  OSD. Вам нужно либо вернуть соответствующий OSD в строй и дать ему очистить лишние данные, либо
  удалить его из кластера окончательно с помощью vitastor-cli [rm-osd](cli.ru.md#rm-osd), если
  известно, что он уже не вернётся (например, если умер диск).
 - **scrubbing** — идёт фоновая проверка данных PG ([скраб](../config/osd.ru.md#auto_scrub)).
 ## Удаление исправного диска
 Перед удалением исправного диска из кластера установите его OSD вес в 0, чтобы убрать с него данные.
 Для этого добавьте в ключ `/vitastor/config/osd/<НОМЕР_OSD>` в etcd значение `"reweight":0`, например:
 ```
 etcdctl --endpoints=http://1.1.1.1:2379/v3 put /vitastor/config/osd/1 '{"reweight":0}'
 ```
 Дождитесь завершения ребаланса, после чего удалите OSD командой `vitastor-disk purge /dev/vitastor/osdN-data`.
 ## Удаление неисправного диска
 Если диск уже умер, его OSD, скорее всего, уже будет/будут остановлен(ы).
 В этом случае просто удалите OSD из etcd командой `vitastor-cli rm-osd НОМЕР_OSD`.
 ## Добавление диска
 Если сервер новый, установите на него пакеты Vitastor и скопируйте файл конфигурации
 `/etc/vitastor/vitastor.conf`.
 После этого достаточно выполнить команду `vitastor-disk prepare /dev/nvmeXXX`, разумеется,
 с параметрами, аналогичными другим OSD в вашем кластере.
 ## Восстановление потерянной конфигурации пулов
 Если удалить или повредить ключ `/vitastor/config/pools` в etcd, все пулы будут удалены.
 Не волнуйтесь, данные потеряны не будут, но вам нужно будет провести специальную
 процедуру восстановления.
 Сначала нужно будет восстановить конфигурацию пулов, создав пул с таким же ID и
 с такими же параметрами EC/реплик, и подождать, пока PG пула появятся в `vitastor-cli status`.
 Далее нужно будет добавить все OSD в исторические записи всех PG. Примерно так
 (только подставьте свои PG_COUNT и POOL_ID):
 ```
 PG_COUNT=32
 POOL_ID=1
 ALL_OSDS=$(etcdctl --endpoints=your_etcd_address:2379 get --keys-only --prefix /vitastor/osd/stats/ | \
    perl -e '$/ = undef; $a = <>; $a =~ s/\s*$//; $a =~ s!/vitastor/osd/stats/!!g; $a =~ s/\s+/,/g; print $a')
 for i in $(seq 1 $PG_COUNT); do
    etcdctl --endpoints=your_etcd_address:2379 put /vitastor/pg/history/$POOL_ID/$i '{"all_peers":['$ALL_OSDS']}'; done
 done
 ```
 После этого все PG должны пройти peering и найти все предыдущие данные.
 ## Обновление Vitastor
 Обычно каждая следующая версия Vitastor совместима с предыдущими и "вперёд", и "назад"
 с точки зрения сетевого протокола и структур данных в etcd.
 Так что по умолчанию, если на данной странице не указано обратное, считается, что для
 обновления достаточно обновить пакеты и перезапустить все OSD и мониторы Vitastor в
 произвольном порядке.
 Обновление производится без остановки клиентов (виртуальных машин/контейнеров), для этого
 достаточно обновлять серверы по одному. Однако, конечно, чтобы запущенные виртуальные машины
 начали использовать новую версию клиентской библиотеки, их тоже нужно перезапустить.
 Исключения (особые указания при обновлении):
 - Обновляться с версий <= 1.1.x до версий >= 1.2.0, если вы используете EC n+k и k>=2,
  рекомендуется с временной остановкой кластера — сначала нужно остановить всех клиентов,
  потом все OSD, потом обновить и запустить всё обратно — из-за нескольких багов, которые
  могли приводить к некорректному чтению данных в деградированных EC-пулах.
 - Версии <= 0.8.7 несовместимы с версиями >= 0.9.0, поэтому при обновлении с <= 0.8.7
  нужно сначала обновиться до 0.8.8 или 0.8.9, а уже потом до любых версий >= 0.9.x.
  Иначе клиентский ввод-вывод зависнет до завершения обновления.
 - Обновление с версий 0.5.x и более ранних до 0.6.x и более поздних не поддерживается.
 Откат:
 - В версии 1.0.0 поменялся дисковый формат, поэтому OSD, созданные на версии >= 1.0.0,
  нельзя откатить до версии 0.9.x и более ранних.
 - В версиях ранее 0.8.0 нет vitastor-disk, значит, созданные им OSD нельзя откатить
  до 0.7.x или 0.6.x. :-)
 ## Потребление памяти OSD
 Основное потребление памяти складывается из:
 - Индекс метаданных: `размер_данных`/[`block_size`](../config/layout-cluster.ru.md#block_size) * `примерно 1.1` * `32` байт.
  Потребляется всегда.
 - Копия дисковой области метаданных: `размер_данных`/[`block_size`](../config/layout-cluster.ru.md#block_size) * `28` байт.
  Потребляется, если не отключена настройка [inmemory_metadata](../config/osd.ru.md#inmemory_metadata).
 - Битмапы: `размер_данных`/[`bitmap_granularity`](../config/layout-cluster.ru.md#bitmap_granularity)/`8` * `2` байт.
  Потребляется всегда.
 - Индекс журнала: от 0 до, приблизительно, размера журнала. Потребляется всегда.
 - Копия дисковой области журнала: в точности размер журнала. Потребляется,
  если не отключена настройка [inmemory_journal](../config/osd.ru.md#inmemory_journal).
 - Контрольные суммы: `размер_данных`/[`csum_block_size`](../config/osd.ru.md#csum_block_size) * `4` байт.
  Потребляется, если включены контрольные суммы и не отключена настройка [inmemory_metadata](../config/osd.ru.md#inmemory_metadata).
 bitmap_granularity, как правило, никогда не меняется и равен 4 килобайтам.
 Таким образом, при SSD-настройках по умолчанию (block_size=128k, journal_size=32M, csum_block_size=4k) потребляется:
 - Метаданные и битмапы: ~600 МБ на 1 ТБ данных
 - Журнал: до 64 МБ на 1 OSD
 - Контрольные суммы: 1 ГБ на 1 ТБ данных
 При HDD-настройках по умолчанию (block_size=1M, journal_size=128M, csum_block_size=32k):
 - Метаданные и битмапы: ~128 МБ на 1 ТБ данных
 - Журнал: до 256 МБ на 1 OSD
 - Контрольные суммы: 128 МБ на 1 ТБ данных
--- a/docs/usage/cli.en.md
+++ b/docs/usage/cli.en.md
@ -24,10 +24,6 @@ It supports the following commands:
 - [fix](#fix)
 - [alloc-osd](#alloc-osd)
 - [rm-osd](#rm-osd)
 - [create-pool](#create-pool)
 - [modify-pool](#modify-pool)
 - [ls-pools](#ls-pools)
 - [rm-pool](#rm-pool)
 Global options:
@ -135,18 +131,19 @@ See also about [how to export snapshots](qemu.en.md#exporting-snapshots).
 ## modify
-`vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force] [--down-ok]`
+`vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force]`
 Rename, resize image or change its readonly status. Images with children can't be made read-write.
 If the new size is smaller than the old size, extra data will be purged.
 You should resize file system in the image, if present, before shrinking it.
-* `-f|--force` - Proceed with shrinking or setting readwrite flag even if the image has children.
+```
-* `--down-ok` - Proceed with shrinking even if some data will be left on unavailable OSDs.
+-f|--force  Proceed with shrinking or setting readwrite flag even if the image has children.
 ```
 ## rm
-`vitastor-cli rm <from> [<to>] [--writers-stopped] [--down-ok]`
+`vitastor-cli rm <from> [<to>] [--writers-stopped]`
 Remove `<from>` or all layers between `<from>` and `<to>` (`<to>` must be a child of `<from>`),
 rebasing all their children accordingly. --writers-stopped allows merging to be a bit
@ -154,10 +151,6 @@ more effective in case of a single 'slim' read-write child and 'fat' removed par
 the child is merged into parent and parent is renamed to child in that case.
 In other cases parent layers are always merged into children.
 Other options:
 * `--down-ok` - Continue deletion/merging even if some data will be left on unavailable OSDs.
 ## flatten
 `vitastor-cli flatten <layer>`
@ -186,9 +179,11 @@ Merge layer data without changing metadata. Merge `<from>`..`<to>` to `<target>`
 ## describe
-`vitastor-cli describe [OPTIONS]`
+`vitastor-cli describe [--osds <osds>] [--object-state <states>] [--pool <pool>]
    [--inode <ino>] [--min-inode <ino>] [--max-inode <ino>]
    [--min-offset <offset>] [--max-offset <offset>]`
-Describe unclean object locations in the cluster. Options:
+Describe unclean object locations in the cluster.
 ```
 --osds <osds>
@ -198,8 +193,6 @@ Describe unclean object locations in the cluster. Options:
    degraded, misplaced, incomplete, corrupted, inconsistent.
 --pool <pool name or number>
    Only list objects in the given pool.
 --pg <pg number>
    Only list objects in the given PG of the pool.
 --inode, --min-inode, --max-inode
    Restrict listing to specific inode numbers.
 --min-offset, --max-offset
@ -245,93 +238,3 @@ Refuses to remove OSDs with data without `--force` and `--allow-data-loss`.
 With `--dry-run` only checks if deletion is possible without data loss and
 redundancy degradation.
 ## create-pool
 `vitastor-cli create-pool|pool-create <name> (-s <pg_size>|--ec <N>+<K>) -n <pg_count> [OPTIONS]`
 Create a pool. Required parameters:
 | <!-- -->                 | <!-- -->                                                                              |
 |--------------------------|---------------------------------------------------------------------------------------|
 | `-s R` or `--pg_size R`  | Number of replicas for replicated pools                                               |
 | `--ec N+K`               | Number of data (N) and parity (K) chunks for erasure-coded pools                      |
 | `-n N` or `--pg_count N` | PG count for the new pool (start with 10*<OSD count>/pg_size rounded to a power of 2) |
 Optional parameters:
 | <!-- -->                       | <!-- -->                                                                   |
 |--------------------------------|----------------------------------------------------------------------------|
 | `--pg_minsize <number>`        | R or N+K minus number of failures to tolerate without downtime ([details](../config/pool.en.md#pg_minsize)) |
 | `--failure_domain host`        | Failure domain: host, osd or a level from placement_levels. Default: host  |
 | `--root_node <node>`           | Put pool only on child OSDs of this placement tree node                    |
 | `--osd_tags <tag>[,<tag>]...`  | Put pool only on OSDs tagged with all specified tags                       |
 | `--block_size 128k`            | Put pool only on OSDs with this data block size                            |
 | `--bitmap_granularity 4k`      | Put pool only on OSDs with this logical sector size                        |
 | `--immediate_commit none`      | Put pool only on OSDs with this or larger immediate_commit (none < small < all) |
 | `--level_placement <rules>`    | Use additional failure domain rules (example: "dc=112233")                 |
 | `--raw_placement <rules>`      | Specify raw PG generation rules ([details](../config/pool.en.md#raw_placement)) |
 | `--primary_affinity_tags tags` | Prefer to put primary copies on OSDs with all specified tags               |
 | `--scrub_interval <time>`      | Enable regular scrubbing for this pool. Format: number + unit s/m/h/d/M/y  |
 | `--used_for_fs <name>`         | Mark pool as used for VitastorFS with metadata in image <name>             |
 | `--pg_stripe_size <number>`    | Increase object grouping stripe                                            |
 | `--max_osd_combinations 10000` | Maximum number of random combinations for LP solver input                  |
 | `--wait`                       | Wait for the new pool to come online                                       |
 | `-f` or `--force`              | Do not check that cluster has enough OSDs to create the pool               |
 See also [Pool configuration](../config/pool.en.md) for detailed parameter descriptions.
 Examples:
 `vitastor-cli create-pool test_x4 -s 4 -n 32`
 `vitastor-cli create-pool test_ec42 --ec 4+2 -n 32`
 ## modify-pool
 `vitastor-cli modify-pool|pool-modify <id|name> [--name <new_name>] [PARAMETERS...]`
 Modify an existing pool. Modifiable parameters:
 ```
 [-s|--pg_size <number>] [--pg_minsize <number>] [-n|--pg_count <count>]
 [--failure_domain <level>] [--root_node <node>] [--osd_tags <tags>] [--no_inode_stats 0|1]
 [--max_osd_combinations <number>] [--primary_affinity_tags <tags>] [--scrub_interval <time>]
 ```
 Non-modifiable parameters (changing them WILL lead to data loss):
 ```
 [--block_size <size>] [--bitmap_granularity <size>]
 [--immediate_commit <all|small|none>] [--pg_stripe_size <size>]
 ```
 These, however, can still be modified with -f|--force.
 See [create-pool](#create-pool) for parameter descriptions.
 Examples:
 `vitastor-cli modify-pool pool_A --name pool_B`
 `vitastor-cli modify-pool 2 --pg_size 4 -n 128`
 ## rm-pool
 `vitastor-cli rm-pool|pool-rm [--force] <id|name>`
 Remove a pool. Refuses to remove pools with images without `--force`.
 ## ls-pools
 `vitastor-cli ls-pools|pool-ls|ls-pool|pools [-l] [--detail] [--sort FIELD] [-r] [-n N] [--stats] [<glob> ...]`
 List pools (only matching <glob> patterns if passed).
 | <!-- -->             | <!-- -->                                              |
 |----------------------|-------------------------------------------------------|
 | `-l` or `--long`     | Also report I/O statistics                            |
 | `--detail`           | Use list format (not table), show all details         |
 | `--sort FIELD`       | Sort by specified field (see fields in --json output) |
 | `-r` or `--reverse`  | Sort in descending order                              |
 | `-n` or `--count N`  | Only list first N items                               |
--- a/docs/usage/cli.ru.md
+++ b/docs/usage/cli.ru.md
@ -23,10 +23,6 @@ vitastor-cli - интерфейс командной строки для адм
 - [merge-data](#merge-data)
 - [alloc-osd](#alloc-osd)
 - [rm-osd](#rm-osd)
 - [create-pool](#create-pool)
 - [modify-pool](#modify-pool)
 - [ls-pools](#ls-pools)
 - [rm-pool](#rm-pool)
 Глобальные опции:
@ -89,8 +85,8 @@ kaveri    2/1     32   0 B      10 G    0 B        100%    0%
 `vitastor-cli ls [-l] [-p POOL] [--sort FIELD] [-r] [-n N] [<glob> ...]`
-Показать список образов, если передан(ы) шаблон(ы) `<glob>`, то только с именами,
+Показать список образов, если переданы шаблоны `<glob>`, то только с именами,
-соответствующими одному из шаблонов (стандартные ФС-шаблоны с * и ?).
+соответствующими этим шаблонам (стандартные ФС-шаблоны с * и ?).
 Опции:
@ -136,7 +132,7 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
 ## modify
-`vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force] [--down-ok]`
+`vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force]`
 Изменить размер, имя образа или флаг "только для чтения". Снимать флаг "только для чтения"
 и уменьшать размер образов, у которых есть дочерние клоны, без `--force` нельзя.
@ -144,12 +140,13 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
 Если новый размер меньше старого, "лишние" данные будут удалены, поэтому перед уменьшением
 образа сначала уменьшите файловую систему в нём.
-* `-f|--force` - Разрешить уменьшение или перевод в чтение-запись образа, у которого есть клоны.
+```
-* `--down-ok` - Разрешить уменьшение, даже если часть данных останется неудалённой на недоступных OSD.
+-f|--force  Разрешить уменьшение или перевод в чтение-запись образа, у которого есть клоны.
 ```
 ## rm
-`vitastor-cli rm <from> [<to>] [--writers-stopped] [--down-ok]`
+`vitastor-cli rm <from> [<to>] [--writers-stopped]`
 Удалить образ `<from>` или все слои от `<from>` до `<to>` (`<to>` должен быть дочерним
 образом `<from>`), одновременно меняя родительские образы их клонов (если таковые есть).
@ -161,10 +158,6 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
 В других случаях родительские слои вливаются в дочерние.
 Другие опции:
 * `--down-ok` - Продолжать удаление/слияние, даже если часть данных останется неудалённой на недоступных OSD.
 ## flatten
 `vitastor-cli flatten <layer>`
@ -194,10 +187,12 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
 ## describe
-`vitastor-cli describe [ОПЦИИ]`
+`vitastor-cli describe [--osds <osds>] [--object-state <состояния>] [--pool <пул>]
    [--inode <номер>] [--min-inode <номер>] [--max-inode <номер>]
    [--min-offset <смещение>] [--max-offset <смещение>]`
 Описать состояние "грязных" объектов в кластере, то есть таких объектов, копии
-или части которых хранятся на наборе OSD, не равном целевому. Опции:
+или части которых хранятся на наборе OSD, не равном целевому.
 ```
 --osds <osds>
@ -212,8 +207,6 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
    - inconsistent - неконсистентный, с неоднозначным расхождением копий/частей
 --pool <имя или ID пула>
    Перечислять только объекты из заданного пула.
 --pg <номер PG>
    Перечислять только объекты из заданной PG пула.
 --inode, --min-inode, --max-inode
    Перечислять только объекты из указанных номеров инодов (образов).
 --min-offset, --max-offset
@ -262,93 +255,3 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
 С опцией `--dry-run` только проверяет, возможно ли удаление без потери данных и деградации
 избыточности.
 ## create-pool
 `vitastor-cli create-pool|pool-create <name> (-s <pg_size>|--ec <N>+<K>) -n <pg_count> [OPTIONS]`
 Создать пул. Обязательные параметры:
 | <!-- -->                  | <!-- -->                                                                                    |
 |---------------------------|---------------------------------------------------------------------------------------------|
 | `-s R` или `--pg_size R`  | Число копий данных для реплицированных пулов                                                |
 | `--ec N+K`                | Число частей данных (N) и чётности (K) для пулов с кодами коррекции ошибок                  |
 | `-n N` или `--pg_count N` | Число PG для нового пула (начните с 10*<число OSD>/pg_size, округлённого до степени двойки) |
 Необязательные параметры:
 | <!-- -->                       | <!-- -->                                                                   |
 |--------------------------------|----------------------------------------------------------------------------|
 | `--pg_minsize <number>`        | (R или N+K) минус число разрешённых отказов без остановки пула ([подробнее](../config/pool.ru.md#pg_minsize)) |
 | `--failure_domain host`        | Домен отказа: host, osd или другой из placement_levels. По умолчанию: host |
 | `--root_node <node>`           | Использовать для пула только дочерние OSD этого узла дерева размещения     |
 | `--osd_tags <tag>[,<tag>]...`  | ...только OSD со всеми заданными тегами                                    |
 | `--block_size 128k`            | ...только OSD с данным размером блока                                      |
 | `--bitmap_granularity 4k`      | ...только OSD с данным размером логического сектора                        |
 | `--immediate_commit none`      | ...только OSD с этим или большим immediate_commit (none < small < all)     |
 | `--level_placement <rules>`    | Задать правила дополнительных доменов отказа (пример: "dc=112233")         |
 | `--raw_placement <rules>`      | Задать низкоуровневые правила генерации PG ([детали](../config/pool.ru.md#raw_placement)) |
 | `--primary_affinity_tags tags` | Предпочитать OSD со всеми данными тегами для роли первичных                |
 | `--scrub_interval <time>`      | Включить скрабы с заданным интервалом времени (число + единица s/m/h/d/M/y) |
 | `--pg_stripe_size <number>`    | Увеличить блок группировки объектов по PG                                  |
 | `--max_osd_combinations 10000` | Максимальное число случайных комбинаций OSD для ЛП-солвера                 |
 | `--wait`                       | Подождать, пока новый пул будет активирован                                |
 | `-f` или `--force`             | Не проверять, что в кластере достаточно доменов отказа для создания пула   |
 Подробно о параметрах см. [Конфигурация пулов](../config/pool.ru.md).
 Примеры:
 `vitastor-cli create-pool test_x4 -s 4 -n 32`
 `vitastor-cli create-pool test_ec42 --ec 4+2 -n 32`
 ## modify-pool
 `vitastor-cli modify-pool|pool-modify <id|name> [--name <new_name>] [PARAMETERS...]`
 Изменить настройки существующего пула. Изменяемые параметры:
 ```
 [-s|--pg_size <number>] [--pg_minsize <number>] [-n|--pg_count <count>]
 [--failure_domain <level>] [--root_node <node>] [--osd_tags <tags>]
 [--max_osd_combinations <number>] [--primary_affinity_tags <tags>] [--scrub_interval <time>]
 ```
 Неизменяемые параметры (их изменение ПРИВЕДЁТ к потере данных):
 ```
 [--block_size <size>] [--bitmap_granularity <size>]
 [--immediate_commit <all|small|none>] [--pg_stripe_size <size>]
 ```
 Эти параметры можно изменить, только если явно передать опцию -f или --force.
 Описания параметров смотрите в [create-pool](#create-pool).
 Примеры:
 `vitastor-cli modify-pool pool_A --name pool_B`
 `vitastor-cli modify-pool 2 --pg_size 4 -n 128`
 ## rm-pool
 `vitastor-cli rm-pool|pool-rm [--force] <id|name>`
 Удалить пул. Отказывается удалять пул, в котором ещё есть образы, без `--force`.
 ## ls-pools
 `vitastor-cli ls-pools|pool-ls|ls-pool|pools [-l] [--detail] [--sort FIELD] [-r] [-n N] [--stats] [<glob> ...]`
 Показать список пулов. Если передан(ы) шаблон(ы) `<glob>`, то только с именами,
 соответствующими одному из шаблонов (стандартные ФС-шаблоны с * и ?).
 | <!-- -->              | <!-- -->                                                   |
 |-----------------------|------------------------------------------------------------|
 | `-l` или `--long`     | Вывести также статистику ввода-вывода                      |
 | `--detail`            | Максимально подробный вывод в виде списка (а не таблицы)   |
 | `--sort FIELD`        | Сортировать по заданному полю (поля см. в выводе с --json) |
 | `-r` или `--reverse`  | Сортировать в обратном порядке                             |
 | `-n` или `--count N`  | Выводить только первые N записей                           |
--- a/docs/usage/disk.en.md
+++ b/docs/usage/disk.en.md
@ -88,7 +88,7 @@ Options (both modes):
 --block_size 1M/128k       Set blockstore object size
 --bitmap_granularity 4k    Set bitmap granularity
 --data_csum_type none      Set data checksum type (crc32c or none)
--csum_block_size 4k/32k   Set data checksum block size (SSD/HDD default)
+--csum_block_size 4k       Set data checksum block size
 --data_device_block 4k     Override data device block size
 --meta_device_block 4k     Override metadata device block size
 --journal_device_block 4k  Override journal device block size
--- a/docs/usage/disk.ru.md
+++ b/docs/usage/disk.ru.md
@ -89,7 +89,7 @@ vitastor-disk - инструмент командной строки для уп
 --block_size 1M/128k       Задать размер объекта хранилища
 --bitmap_granularity 4k    Задать гранулярность битовых карт
 --data_csum_type none      Задать тип контрольных сумм (crc32c или none)
--csum_block_size 4k/32k   Задать размер блока расчёта контрольных сумм (дефолт SSD/HDD)
+--csum_block_size 4k       Задать размер блока расчёта контрольных сумм
 --data_device_block 4k     Задать размер блока устройства данных
 --meta_device_block 4k     Задать размер блока метаданных
 --journal_device_block 4k  Задать размер блока журнала
--- a/docs/usage/nbd.en.md
+++ b/docs/usage/nbd.en.md
@ -15,21 +15,12 @@ See also [VDUSE](qemu.en.md#vduse) as a better alternative to NBD.
 Vitastor Kubernetes CSI driver uses NBD when VDUSE is unavailable.
-Supports the following commands:
+## Map image
 - [map](#map)
 - [unmap](#unmap)
 - [ls](#ls)
 - [netlink-map](#netlink-map)
 - [netlink-unmap](#netlink-unmap)
 - [netlink-revive](#netlink-revive)
 ## map
 To create a local block device for a Vitastor image run:
 ```
-vitastor-nbd map [/dev/nbdN] --image testimg
+vitastor-nbd map --image testimg
 ```
 It will output a block device name like /dev/nbd0 which you can then use as a normal disk.
@ -38,25 +29,25 @@ You can also use `--pool <POOL> --inode <INODE> --size <SIZE>` instead of `--ima
 vitastor-nbd supports all usual Vitastor configuration options like `--config_file <path_to_config>` plus NBD-specific:
-* `--nbd_timeout 0` \
+* `--nbd_timeout 300` \
-  Timeout for I/O operations in seconds after exceeding which the kernel stops the device.
+  Timeout for I/O operations in seconds after exceeding which the kernel stops
-  Before Linux 5.19, if nbd_timeout is 0, a dead NBD device can't be removed from
+  the device. You can set it to 0 to disable the timeout, but beware that you
-  the system at all without rebooting.
+  won't be able to stop the device at all if vitastor-nbd process dies.
 * `--nbd_max_devices 64 --nbd_max_part 3` \
  Options for the `nbd` kernel module when modprobing it (`nbds_max` and `max_part`).
  note that maximum allowed (nbds_max)*(1+max_part) is 256.
 * `--logfile /path/to/log/file.txt` \
  Write log messages to the specified file instead of dropping them (in background mode)
  or printing them to the standard output (in foreground mode).
 * `--dev_num N` \
-  Use the specified device /dev/nbdN instead of automatic selection (alternative syntax
+  Use the specified device /dev/nbdN instead of automatic selection.
  to /dev/nbdN positional parameter).
 * `--foreground 1` \
  Stay in foreground, do not daemonize.
 Note that `nbd_timeout`, `nbd_max_devices` and `nbd_max_part` options may also be specified
 in `/etc/vitastor/vitastor.conf` or in other configuration file specified with `--config_file`.
-## unmap
+## Unmap image
 To unmap the device run:
@ -64,14 +55,12 @@ To unmap the device run:
 vitastor-nbd unmap /dev/nbd0
 ```
-## ls
+## List mapped images
 ```
 vitastor-nbd ls [--json]
 ```
 List mapped images.
 Example output (normal format):
 ```
@ -89,45 +78,3 @@ Example output (JSON format):
 ```
 {"/dev/nbd0": {"image": "bench", "pid": 584536}, "/dev/nbd1": {"image": "bench1", "pid": 584546}}
 ```
 ## netlink-map
 ```
 vitastor-nbd netlink-map [/dev/nbdN] (--image <image> | --pool <pool> --inode <inode> --size <size in bytes>)
 ```
 On recent kernel versions it's also possinle to map NBD devices using netlink interface.
 This is an experimental feature because it doesn't solve all issues of NBD. Differences from regular ioctl-based 'map':
 1. netlink-map can create new `/dev/nbdN` devices (those not present in /dev/).
 2. netlink-mapped devices can be unmapped only using `netlink-unmap` command.
 3. netlink-mapped devices don't show up `ls` output (yet).
 4. Dead netlink-mapped devices can be 'revived' using `netlink-revive`.
   However, old I/O requests will hang forever if `nbd_timeout` is not specified.
 5. netlink-map supports additional options:
 * `--nbd_conn_timeout 0` \
  Disconnect a dead device automatically after this number of seconds.
 * `--nbd_destroy_on_disconnect 1` \
  Delete the nbd device on disconnect.
 * `--nbd_disconnect_on_close 1` \
  Disconnect the nbd device on close by last opener.
 * `--nbd_ro 1` \
  Set device into read only mode.
 ## netlink-unmap
 ```
 vitastor-nbd netlink-unmap /dev/nbdN
 ```
 Unmap a device using netlink interface. Works with both netlink and ioctl mapped devices.
 ## netlink-revive
 ```
 vitastor-nbd netlink-revive /dev/nbdX (--image <image> | --pool <pool> --inode <inode> --size <size in bytes>)
 ```
 Restart a dead NBD netlink-mapped device without removing it. Supports the same options as `netlink-map`.
--- a/docs/usage/nbd.ru.md
+++ b/docs/usage/nbd.ru.md
@ -18,21 +18,12 @@ NBD немного снижает производительность из-за
 CSI-драйвер Kubernetes Vitastor использует NBD, когда VDUSE недоступен.
-Поддерживаются следующие команды:
+## Подключить устройство
 - [map](#map)
 - [unmap](#unmap)
 - [ls](#ls)
 - [netlink-map](#netlink-map)
 - [netlink-unmap](#netlink-unmap)
 - [netlink-revive](#netlink-revive)
 ## map
 Чтобы создать локальное блочное устройство для образа, выполните команду:
 ```
-vitastor-nbd map [/dev/nbdN] --image testimg
+vitastor-nbd map --image testimg
 ```
 Команда напечатает название блочного устройства вида /dev/nbd0, которое потом можно
@ -44,13 +35,16 @@ vitastor-nbd map [/dev/nbdN] --image testimg
 vitastor-nbd поддерживает все обычные опции Vitastor, например, `--config_file <path_to_config>`,
 плюс специфичные для NBD:
-* `--nbd_timeout 0` \
+* `--nbd_timeout 30` \
  Максимальное время выполнения любой операции чтения/записи в секундах, при
-  превышении которого ядро остановит NBD-устройство. На ядрах Linux старее 5.19,
+  превышении которого ядро остановит NBD-устройство. Вы можете установить опцию
-  если таймаут установлен в 0, NBD-устройство вообще невозможно отключить из системы
+  в 0, чтобы отключить ограничение времени, но имейте в виду, что в этом случае
-  при нештатном завершении процесса.
+  вы вообще не сможете отключить NBD-устройство при нештатном завершении процесса
  vitastor-nbd.
 * `--nbd_max_devices 64 --nbd_max_part 3` \
-  Опции, передаваемые модулю ядра nbd, если его загружает vitastor-nbd (`nbds_max` и `max_part`).
+  Опции, передаваемые модулю ядра nbd, если его загружает vitastor-nbd
  (`nbds_max` и `max_part`). Имейте в виду, что (nbds_max)*(1+max_part)
  обычно не должно превышать 256.
 * `--logfile /path/to/log/file.txt` \
  Писать сообщения о процессе работы в заданный файл, вместо пропуска их
  при фоновом режиме запуска или печати на стандартный вывод при запуске
@ -64,7 +58,7 @@ vitastor-nbd поддерживает все обычные опции Vitastor,
 также задавать в `/etc/vitastor/vitastor.conf` или в другом файле конфигурации,
 заданном опцией `--config_file`.
-## unmap
+## Отключить устройство
 Для отключения устройства выполните:
@ -72,14 +66,12 @@ vitastor-nbd поддерживает все обычные опции Vitastor,
 vitastor-nbd unmap /dev/nbd0
 ```
-## ls
+## Вывести подключённые устройства
 ```
 vitastor-nbd ls [--json]
 ```
 Вывести подключённые устройства.
 Пример вывода в обычном формате:
 ```
@ -97,46 +89,3 @@ pid: 584546
 ```
 {"/dev/nbd0": {"image": "bench", "pid": 584536}, "/dev/nbd1": {"image": "bench1", "pid": 584546}}
 ```
 ## netlink-map
 ```
 vitastor-nbd netlink-map [/dev/nbdN] (--image <image> | --pool <POOL> --inode <INODE> --size <SIZE>)
 ```
 На свежих версиях ядра Linux также возможно подключать NBD-устройства через интерфейс netlink.
 Это экспериментальная функция, так как она не решает всех проблем NBD. Отличия от обычного 'map':
 1. Можно создавать новые `/dev/nbdN` устройства (отсутствующие в /dev/).
 2. Отключать netlink-устройства можно только командой `netlink-unmap`.
 3. netlink-устройства не видно в выводе `ls` (пока что).
 4. Мёртвые netlink-устройства можно "оживить" командой `netlink-revive`. Правда, предыдущие
   запросы ввода-вывода всё равно зависнут навсегда, если `nbd_timeout` не задан.
 5. Поддерживаются дополнительные опции:
 * `--nbd_conn_timeout 0` \
  Отключать мёртвое устройство автоматически через данное число секунд.
 * `--nbd_destroy_on_disconnect 1` \
  Удалять NBD-устройство при отключении.
 * `--nbd_disconnect_on_close 1` \
  Отключать NBD-устройство автоматически, когда его все закроют.
 * `--nbd_ro 1` \
  Установить для NBD-устройства режим "только для чтения".
 ## netlink-unmap
 ```
 vitastor-nbd netlink-unmap /dev/nbdN
 ```
 Отключить устройство через интерфейс netlink. Работает и с обычными, и с netlink-устройствами.
 ## netlink-revive
 ```
 vitastor-nbd netlink-revive /dev/nbdX (--image <image> | --pool <pool> --inode <inode> --size <size in bytes>)
 ```
 Оживить мёртвое NBD-устройство, ранее подключённое через netlink, без удаления. Поддерживает
 те же опции, что и `netlink-map`.
--- a/docs/usage/nfs.en.md
+++ b/docs/usage/nfs.en.md
@ -1,153 +1,45 @@
-[Documentation](../../README.md#documentation) → Usage → VitastorFS and pseudo-FS
+[Documentation](../../README.md#documentation) → Usage → NFS
 -----
 [Читать на русском](nfs.ru.md)
-# VitastorFS and pseudo-FS
+# NFS
-Vitastor has two file system implementations. Both can be used via `vitastor-nfs`.
+Vitastor has a simplified NFS 3.0 proxy for file-based image access emulation. It's not
 suitable as a full-featured file system, at least because all file/image metadata is stored
 in etcd and kept in memory all the time - thus you can't put a lot of files in it.
-Commands:
+However, NFS proxy is totally fine as a method to provide VM image access and allows to
- [mount](#mount)
+plug Vitastor into, for example, VMWare. It's important to note that for VMWare it's a much
- [start](#start)
+better access method than iSCSI, because with iSCSI we'd have to put all VM images into one
 Vitastor image exported as a LUN to VMWare and formatted with VMFS. VMWare doesn't use VMFS
 over NFS.
-## Pseudo-FS
+NFS proxy is stateless if you use immediate_commit=all mode (for SSD with capacitors or
 HDDs with disabled cache), so you can run multiple NFS proxies and use a network load
 balancer or any failover method you want to in that case.
-Simplified pseudo-FS proxy is used for file-based image access emulation. It's not
+vitastor-nfs usage:
 suitable as a full-featured file system: it lacks a lot of FS features, it stores
 all file/image metadata in memory and in etcd. So it's fine for hundreds or thousands
 of large files/images, but not for millions.
 Pseudo-FS proxy is intended for environments where other block volume access methods
 can't be used or impose additional restrictions - for example, VMWare. NFS is better
 for VMWare than, for example, iSCSI, because with iSCSI, VMWare puts all VM images
 into one large shared block image in its own VMFS file system, and with NFS, VMWare
 doesn't use VMFS and puts each VM disk in a regular file which is equal to one
 Vitastor block image, just as originally intended.
 To use Vitastor pseudo-FS locally, run `vitastor-nfs mount --block /mnt/vita`.
 Also you can start the network server:
 ```
-vitastor-nfs start --block --etcd_address 192.168.5.10:2379 --portmap 0 --port 2050 --pool testpool
+vitastor-nfs [STANDARD OPTIONS] [OTHER OPTIONS]
 --subdir <DIR>    export images prefixed <DIR>/ (default empty - export all images)
 --portmap 0       do not listen on port 111 (portmap/rpcbind, requires root)
 --bind <IP>       bind service to <IP> address (default 0.0.0.0)
 --nfspath <PATH>  set NFS export path to <PATH> (default is /)
 --port <PORT>     use port <PORT> for NFS services (default is 2049)
 --pool <POOL>     use <POOL> as default pool for new files (images)
 --foreground 1    stay in foreground, do not daemonize
 ```
-To mount the FS exported by this server, run:
+Example start and mount commands (etcd_address is optional):
 ```
-mount server:/ /mnt/ -o port=2050,mountport=2050,nfsvers=3,soft,nolock,tcp
+vitastor-nfs --etcd_address 192.168.5.10:2379 --portmap 0 --port 2050 --pool testpool
 ```
-## VitastorFS
+```
-
+mount localhost:/ /mnt/ -o port=2050,mountport=2050,nfsvers=3,soft,nolock,tcp
-VitastorFS is a full-featured clustered (Read-Write-Many) file system. It supports most POSIX
+```
 features like hierarchical organization, symbolic links, hard links, quick renames and so on.
 VitastorFS metadata is stored in a Parallel Optimistic B-Tree key-value database,
 implemented over a regular Vitastor block volume. Directory entries and inodes
 are stored in a simple human-readable JSON format in the B-Tree. `vitastor-kv` tool
 can be used to inspect the database.
 To use VitastorFS:
 1. Create a pool or choose an existing empty pool for FS data
 2. Create an image for FS metadata, preferably in a faster (SSD or replica-HDD) pool,
   but you can create it in the data pool too if you want (image size doesn't matter):
   `vitastor-cli create -s 10G -p fastpool testfs`
 3. Mark data pool as an FS pool: `vitastor-cli modify-pool --used-for-fs testfs data-pool`
 4. Either mount the FS: `vitastor-nfs mount --fs testfs --pool data-pool /mnt/vita`
 5. Or start the NFS server: `vitastor-nfs start --fs testfs --pool data-pool`
 ### Supported POSIX features
 - Read-after-write semantics (read returns new data immediately after write)
 - Linear and random read and write
 - Writing outside current file size
 - Hierarchical structure, immediate rename of files and directories
 - File size change support (truncate)
 - Permissions (chmod/chown)
 - Flushing data to stable storage (if required) (fsync)
 - Symbolic links
 - Hard links
 - Special files (devices, sockets, named pipes)
 - File modification and attribute change time tracking (mtime and ctime)
 - Modification time (mtime) and last access time (atime) change support (utimes)
 - Correct handling of directory listing during file creation/deletion
 ### Limitations
 POSIX features currently not implemented in VitastorFS:
 - File locking is not supported
 - Actually used space is not counted, so `du` always reports apparent file sizes
  instead of actually allocated space
 - Access times (`atime`) are not tracked (like `-o noatime`)
 - Modification time (`mtime`) is updated lazily every second (like `-o lazytime`)
 Other notable missing features which should be addressed in the future:
 - Defragmentation of "shared" inodes. Files smaller than pool object size (block_size
  multiplied by data part count if pool is EC) are internally stored in large block
  volumes sequentially, one after another, and leave garbage after deleting or resizing.
  Defragmentator will be implemented to collect this garbage.
 - Inode ID reuse. Currently inode IDs always grow, the limit is 2^48 inodes, so
  in theory you may hit it if you create and delete a very large number of files
 - Compaction of the key-value B-Tree. Current implementation never merges or deletes
  B-Tree blocks, so B-Tree may become bloated over time. Currently you can
  use `vitastor-kv dumpjson` & `loadjson` commands to recreate the index in such
  situations.
 - Filesystem check tool. VitastorFS doesn't have journal because it would impose a
  severe performance hit, optimistic CAS-based transactions are used instead of it.
  So, again, in theory an abnormal shutdown of the FS server may leave some garbage
  in the DB. The FS is implemented is such way that this garbage doesn't affect its
  function, but having a tool to clean it up still seems a right thing to do.
 ## Horizontal scaling
 Linux NFS 3.0 client doesn't support built-in scaling or failover, i.e. you can't
 specify multiple server addresses when mounting the FS.
 However, you can use any regular TCP load balancing over multiple NFS servers.
 It's absolutely safe with `immediate_commit=all` and `client_enable_writeback=false`
 settings, because Vitastor NFS proxy doesn't keep uncommitted data in memory
 with these settings. But it may even work without `immediate_commit=all` because
 the Linux NFS client repeats all uncommitted writes if it loses the connection.
 ## Commands
 ### mount
 `vitastor-nfs (--fs <NAME> | --block) [-o <OPT>] mount <MOUNTPOINT>`
 Start local filesystem server and mount file system to <MOUNTPOINT>.
 Use regular `umount <MOUNTPOINT>` to unmount the FS.
 The server will be automatically stopped when the FS is unmounted.
 - `-o|--options <OPT>` - Pass additional NFS mount options (ex.: -o async).
 ### start
 `vitastor-nfs (--fs <NAME> | --block) start`
 Start network NFS server. Options:
 | <!-- -->        | <!-- -->                                                   |
 |-----------------|------------------------------------------------------------|
 | `--bind <IP>`   | bind service to \<IP> address (default 0.0.0.0)            |
 | `--port <PORT>` | use port \<PORT> for NFS services (default is 2049)        |
 | `--portmap 0`   | do not listen on port 111 (portmap/rpcbind, requires root) |
 ## Common options
 | <!-- -->           | <!-- -->                                                 |
 |--------------------|----------------------------------------------------------|
 | `--fs <NAME>`      | use VitastorFS with metadata in image \<NAME>            |
 | `--block`          | use pseudo-FS presenting images as files                 |
 | `--pool <POOL>`    | use \<POOL> as default pool for new files                |
 | `--subdir <DIR>`   | export \<DIR> instead of root directory (pseudo-FS only) |
 | `--nfspath <PATH>` | set NFS export path to \<PATH> (default is /)            |
 | `--pidfile <FILE>` | write process ID to the specified file                   |
 | `--logfile <FILE>` | log to the specified file                                |
 | `--foreground 1`   | stay in foreground, do not daemonize                     |
--- a/docs/usage/nfs.ru.md
+++ b/docs/usage/nfs.ru.md
@ -1,159 +1,44 @@
-[Документация](../../README-ru.md#документация) → Использование → VitastorFS и псевдо-ФС
+[Документация](../../README-ru.md#документация) → Использование → NFS
 -----
 [Read in English](nfs.en.md)
-# VitastorFS и псевдо-ФС
+# NFS
-В Vitastor есть две реализации файловой системы. Обе используются через `vitastor-nfs`.
+В Vitastor реализована упрощённая NFS 3.0 прокси для эмуляции файлового доступа к образам.
 Это не полноценная файловая система, т.к. метаданные всех файлов (образов) сохраняются
 в etcd и всё время хранятся в оперативной памяти - то есть, положить туда много файлов
 не получится.
-Команды:
+Однако в качестве способа доступа к образам виртуальных машин NFS прокси прекрасно подходит
- [mount](#mount)
+и позволяет подключить Vitastor, например, к VMWare.
 - [start](#start)
-## Псевдо-ФС
+При этом, если вы используете режим immediate_commit=all (для SSD с конденсаторами или HDD
 с отключённым кэшем), то NFS-сервер не имеет состояния и вы можете свободно поднять
 его в нескольких экземплярах и использовать поверх них сетевой балансировщик нагрузки или
 схему с отказоустойчивостью.
-Упрощённая реализация псевдо-ФС используется для эмуляции файлового доступа к блочным
+Использование vitastor-nfs:
 образам Vitastor. Это не полноценная файловая система - в ней отсутствуют многие функции
 POSIX ФС, а метаданные всех файлов (образов) сохраняются в etcd и всё время хранятся в
 оперативной памяти - то есть, псевдо-ФС подходит для сотен или тысяч файлов, но не миллионов.
 Псевдо-ФС предназначена для доступа к образам виртуальных машин в средах, где другие
 способы невозможны или неудобны - например, в VMWare. Для VMWare это лучшая опция, чем
 iSCSI, так как при использовании iSCSI VMWare размещает все виртуальные машины в одном
 большом блочном образе внутри собственной ФС VMFS, а с NFS VMFS не используется и каждый
 диск ВМ представляется в виде одного файла, то есть, соответствует одному блочному образу
 Vitastor, как это и задумано изначально.
 Чтобы подключить псевдо-ФС Vitastor, выполните команду `vitastor-nfs mount --block /mnt/vita`.
 Либо же запустите сетевой вариант сервера:
 ```
-vitastor-nfs start --block --etcd_address 192.168.5.10:2379 --portmap 0 --port 2050 --pool testpool
+vitastor-nfs [СТАНДАРТНЫЕ ОПЦИИ] [ДРУГИЕ ОПЦИИ]
 --subdir <DIR>    экспортировать "поддиректорию" - образы с префиксом имени <DIR>/ (по умолчанию пусто - экспортировать все образы)
 --portmap 0       отключить сервис portmap/rpcbind на порту 111 (по умолчанию включён и требует root привилегий)
 --bind <IP>       принимать соединения по адресу <IP> (по умолчанию 0.0.0.0 - на всех)
 --nfspath <PATH>  установить путь NFS-экспорта в <PATH> (по умолчанию /)
 --port <PORT>     использовать порт <PORT> для NFS-сервисов (по умолчанию 2049)
 --pool <POOL>     использовать пул <POOL> для новых образов (обязательно, если пул в кластере не один)
 --foreground 1    не уходить в фон после запуска
 ```
-Примонтировать ФС, запущенную с такими опциями, можно следующей командой:
+Пример монтирования Vitastor через NFS (etcd_address необязателен):
 ```
-mount server:/ /mnt/ -o port=2050,mountport=2050,nfsvers=3,soft,nolock,tcp
+vitastor-nfs --etcd_address 192.168.5.10:2379 --portmap 0 --port 2050 --pool testpool
 ```
-## VitastorFS
+```
-
+mount localhost:/ /mnt/ -o port=2050,mountport=2050,nfsvers=3,soft,nolock,tcp
-VitastorFS - полноценная кластерная (Read-Write-Many) файловая система. Она поддерживает
+```
 большую часть функций POSIX - иерархическую организацию, символические ссылки, жёсткие
 ссылки, быстрые переименования и так далее.
 Метаданные VitastorFS хранятся в собственной реализации БД формата ключ-значения,
 основанной на Параллельном Оптимистичном Б-дереве поверх обычного блочного образа Vitastor.
 И записи каталогов, и иноды, как обычно в Vitastor, хранятся в простом человекочитаемом
 JSON-формате :-). Для инспекции содержимого БД можно использовать инструмент `vitastor-kv`.
 Чтобы использовать VitastorFS:
 1. Создайте пул для данных ФС или выберите существующий пустой пул
 2. Создайте блочный образ для метаданных ФС, желательно, в более быстром пуле (на SSD
   или по крайней мере на HDD, но без EC), но можно и в том же пуле, что данные
   (размер образа значения не имеет):
   `vitastor-cli create -s 10G -p fastpool testfs`
 3. Пометьте пул данных как ФС-пул: `vitastor-cli modify-pool --used-for-fs testfs data-pool`
 4. Либо примонтируйте ФС: `vitastor-nfs mount --fs testfs --pool data-pool /mnt/vita`
 5. Либо запустите сетевой NFS-сервер: `vitastor-nfs start --fs testfs --pool data-pool`
 ### Поддерживаемые функции POSIX
 - Чтение актуальной версии данных сразу после записи
 - Последовательное и произвольное чтение и запись
 - Запись за пределами текущего размера файла
 - Иерархическая организация, мгновенное переименование файлов и каталогов
 - Изменение размера файла (truncate)
 - Права на файлы (chmod/chown)
 - Фиксация данных на диски (когда необходимо) (fsync)
 - Символические ссылки
 - Жёсткие ссылки
 - Специальные файлы (устройства, сокеты, каналы)
 - Отслеживание времён модификации (mtime), изменения атрибутов (ctime)
 - Ручное изменение времён модификации (mtime), последнего доступа (atime)
 - Корректная обработка изменений списка файлов во время листинга
 ### Ограничения
 Отсутствующие на данный момент в VitastorFS функции POSIX:
 - Блокировки файлов не поддерживаются
 - Фактически занятое файлами место не подсчитывается и не возвращается вызовами
  stat(2), так что `du` всегда показывает сумму размеров файлов, а не фактически занятое место
 - Времена доступа (`atime`) не отслеживаются (как будто ФС смонтирована с `-o noatime`)
 - Времена модификации (`mtime`) отслеживаются асинхронно (как будто ФС смонтирована с `-o lazytime`)
 Другие недостающие функции, которые нужно добавить в будущем:
 - Дефрагментация "общих инодов". На уровне реализации ФС файлы, меньшие, чем размер
  объекта пула (block_size умножить на число частей данных, если пул EC),
  упаковываются друг за другом в большие "общие" иноды/тома. Если такие файлы удалять
  или увеличивать, они перемещаются и оставляют за собой "мусор", вот тут-то и нужен
  дефрагментатор.
 - Переиспользование номеров инодов. В текущей реализации номера инодов всё время
  увеличиваются, так что в теории вы можете упереться в лимит, если насоздаёте
  и наудаляете больше, чем 2^48 файлов.
 - Очистка места в Б-дереве метаданных. Текущая реализация никогда не сливает и не
  удаляет блоки Б-дерева, так что в теории дерево может разростись и стать неоптимальным.
  Если вы столкнётесь с такой ситуацией сейчас, вы можете решить её с помощью
  команд `vitastor-kv dumpjson` и `loadjson` (т.е. пересоздав и загрузив обратно все метаданные ФС).
 - Инструмент проверки метаданных файловой системы. У VitastorFS нет журнала, так как
  журнал бы сильно замедлил реализацию, вместо него используются оптимистичные
  транзакции на основе CAS (сравнить-и-записать), и теоретически при нештатном
  завершении сервера ФС в БД также могут оставаться неконсистентные "мусорные"
  записи. ФС устроена так, что на работу они не влияют, но для порядка и их стоит
  уметь подчищать.
 ## Горизонтальное масштабирование
 Клиент Linux NFS 3.0 не поддерживает встроенное масштабирование или отказоустойчивость.
 То есть, вы не можете задать несколько адресов серверов при монтировании ФС.
 Однако вы можете использовать любые стандартные сетевые балансировщики нагрузки
 или схемы с отказоустойчивостью. Это точно безопасно при настройках `immediate_commit=all` и
 `client_enable_writeback=false`, так как с ними NFS-сервер Vitastor вообще не хранит
 в памяти ещё не зафиксированные на дисках данные; и вполне вероятно безопасно
 даже без `immediate_commit=all`, потому что NFS-клиент ядра Linux повторяет все
 незафиксированные запросы при потере соединения.
 ## Команды
 ### mount
 `vitastor-nfs (--fs <NAME> | --block) mount [-o <OPT>] <MOUNTPOINT>`
 Запустить локальный сервер и примонтировать ФС в директорию <MOUNTPOINT>.
 Чтобы отмонтировать ФС, используйте обычную команду `umount <MOUNTPOINT>`.
 Сервер автоматически останавливается при отмонтировании ФС.
 - `-o|--options <OPT>` - Передать дополнительные опции монтирования NFS (пример: -o async).
 ### start
 `vitastor-nfs (--fs <NAME> | --block) start`
 Запустить сетевой NFS-сервер. Опции:
 | <!-- -->        | <!-- -->                                                              |
 |-----------------|-----------------------------------------------------------------------|
 | `--bind <IP>`   | принимать соединения по адресу \<IP> (по умолчанию 0.0.0.0 - на всех) |
 | `--port <PORT>` | использовать порт \<PORT> для NFS-сервисов (по умолчанию 2049)        |
 | `--portmap 0`   | отключить сервис portmap/rpcbind на порту 111 (по умолчанию включён и требует root привилегий) |
 ## Общие опции
 | <!-- -->           | <!-- -->                                                |
 |--------------------|---------------------------------------------------------|
 | `--fs <NAME>`      | использовать VitastorFS с метаданными в образе \<NAME>  |
 | `--block`          | использовать псевдо-ФС для доступа к блочным образам    |
 | `--pool <POOL>`    | использовать пул \<POOL> для новых файлов (обязательно, если пул в кластере не один) |
 | `--subdir <DIR>`   | экспортировать подкаталог \<DIR>, а не корень (только для псевдо-ФС) |
 | `--nfspath <PATH>` | установить путь NFS-экспорта в \<PATH> (по умолчанию /) |
 | `--pidfile <FILE>` | записать ID процесса в заданный файл                    |
 | `--logfile <FILE>` | записывать логи в заданный файл                         |
 | `--foreground 1`   | не уходить в фон после запуска                          |
--- a/docs/usage/pg_states.dot
+++ b/docs/usage/pg_states.dot
@ -1,13 +0,0 @@
 digraph G {
    rankdir=LR;
    bgcolor=transparent;
    edge [color="#00A000"];
    node [shape=hexagon, fillcolor="#A0A000", fontcolor=white, fontname="sans-serif", fontsize=12, style=filled, penwidth=0];
    offline -> starting -> peering -> offline;
    stopping -> offline;
    starting -> incomplete -> offline;
    active -> repeering -> peering -> active -> stopping;
    offline [fillcolor="#A00000"];
    incomplete [fillcolor="#A00000"];
    active [fillcolor="#00A000"];
 }
--- a/docs/usage/pg_states.svg
+++ b/docs/usage/pg_states.svg
@ -1,114 +0,0 @@
 <?xml version="1.0" encoding="UTF-8" standalone="no"?>
 <!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN"
 "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
 <!-- Generated by graphviz version 2.43.0 (0)
 -->
 <!-- Title: G Pages: 1 -->
 <svg width="603pt" height="123pt"
 viewBox="0.00 0.00 602.66 122.55" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
 <g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 118.55)">
 <title>G</title>
 <!-- offline -->
 <g id="node1" class="node">
 <title>offline</title>
 <polygon fill="#a00000" stroke="black" stroke-width="0" points="75.52,-56 56.6,-74 18.75,-74 -0.17,-56 18.75,-38 56.6,-38 75.52,-56"/>
 <text text-anchor="middle" x="37.67" y="-52.9" font-family="sans-serif" font-size="12.00" fill="white">offline</text>
 </g>
 <!-- starting -->
 <g id="node2" class="node">
 <title>starting</title>
 <polygon fill="#a0a000" stroke="black" stroke-width="0" points="199.56,-79 177.49,-97 133.35,-97 111.28,-79 133.35,-61 177.49,-61 199.56,-79"/>
 <text text-anchor="middle" x="155.42" y="-75.9" font-family="sans-serif" font-size="12.00" fill="white">starting</text>
 </g>
 <!-- offline&#45;&gt;starting -->
 <g id="edge1" class="edge">
 <title>offline&#45;&gt;starting</title>
 <path fill="none" stroke="#00a000" d="M69.39,-62.1C81.66,-64.54 96.04,-67.4 109.45,-70.06"/>
 <polygon fill="#00a000" stroke="#00a000" points="108.98,-73.54 119.47,-72.05 110.34,-66.67 108.98,-73.54"/>
 </g>
 <!-- peering -->
 <g id="node3" class="node">
 <title>peering</title>
 <polygon fill="#a0a000" stroke="black" stroke-width="0" points="335.57,-95 313.96,-113 270.74,-113 249.13,-95 270.74,-77 313.96,-77 335.57,-95"/>
 <text text-anchor="middle" x="292.35" y="-91.9" font-family="sans-serif" font-size="12.00" fill="white">peering</text>
 </g>
 <!-- starting&#45;&gt;peering -->
 <g id="edge2" class="edge">
 <title>starting&#45;&gt;peering</title>
 <path fill="none" stroke="#00a000" d="M194.36,-83.5C209.71,-85.32 227.6,-87.44 243.8,-89.36"/>
 <polygon fill="#00a000" stroke="#00a000" points="243.82,-92.89 254.16,-90.59 244.64,-85.94 243.82,-92.89"/>
 </g>
 <!-- incomplete -->
 <g id="node5" class="node">
 <title>incomplete</title>
 <polygon fill="#a00000" stroke="black" stroke-width="0" points="349.09,-41 320.72,-59 263.99,-59 235.62,-41 263.99,-23 320.72,-23 349.09,-41"/>
 <text text-anchor="middle" x="292.35" y="-37.9" font-family="sans-serif" font-size="12.00" fill="white">incomplete</text>
 </g>
 <!-- starting&#45;&gt;incomplete -->
 <g id="edge5" class="edge">
 <title>starting&#45;&gt;incomplete</title>
 <path fill="none" stroke="#00a000" d="M188.74,-69.9C204.92,-65.34 224.85,-59.73 242.82,-54.67"/>
 <polygon fill="#00a000" stroke="#00a000" points="243.9,-58 252.57,-51.92 242,-51.26 243.9,-58"/>
 </g>
 <!-- peering&#45;&gt;offline -->
 <g id="edge3" class="edge">
 <title>peering&#45;&gt;offline</title>
 <path fill="none" stroke="#00a000" d="M259.32,-103.69C222.67,-112.11 161.28,-121.52 111.35,-106 94.55,-100.78 78.2,-90.18 65.27,-80.08"/>
 <polygon fill="#00a000" stroke="#00a000" points="67.26,-77.19 57.3,-73.58 62.84,-82.61 67.26,-77.19"/>
 </g>
 <!-- active -->
 <g id="node6" class="node">
 <title>active</title>
 <polygon fill="#00a000" stroke="black" stroke-width="0" points="456.34,-49 438.55,-67 402.97,-67 385.18,-49 402.97,-31 438.55,-31 456.34,-49"/>
 <text text-anchor="middle" x="420.76" y="-45.9" font-family="sans-serif" font-size="12.00" fill="white">active</text>
 </g>
 <!-- peering&#45;&gt;active -->
 <g id="edge9" class="edge">
 <title>peering&#45;&gt;active</title>
 <path fill="none" stroke="#00a000" d="M322.99,-84.22C341.47,-77.49 365.34,-68.8 384.75,-61.74"/>
 <polygon fill="#00a000" stroke="#00a000" points="385.96,-65.03 394.16,-58.32 383.56,-58.45 385.96,-65.03"/>
 </g>
 <!-- stopping -->
 <g id="node4" class="node">
 <title>stopping</title>
 <polygon fill="#a0a000" stroke="black" stroke-width="0" points="591.65,-18 567.57,-36 519.39,-36 495.31,-18 519.39,0 567.57,0 591.65,-18"/>
 <text text-anchor="middle" x="543.48" y="-14.9" font-family="sans-serif" font-size="12.00" fill="white">stopping</text>
 </g>
 <!-- stopping&#45;&gt;offline -->
 <g id="edge4" class="edge">
 <title>stopping&#45;&gt;offline</title>
 <path fill="none" stroke="#00a000" d="M500.13,-14.3C440.78,-9.83 329.58,-4.07 235.49,-14 179.71,-19.89 116.5,-34.9 77.11,-45.29"/>
 <polygon fill="#00a000" stroke="#00a000" points="76.14,-41.92 67.38,-47.89 77.94,-48.69 76.14,-41.92"/>
 </g>
 <!-- incomplete&#45;&gt;offline -->
 <g id="edge6" class="edge">
 <title>incomplete&#45;&gt;offline</title>
 <path fill="none" stroke="#00a000" d="M240.25,-44.03C194.33,-46.76 127.57,-50.72 83.64,-53.33"/>
 <polygon fill="#00a000" stroke="#00a000" points="83.32,-49.84 73.54,-53.93 83.73,-56.83 83.32,-49.84"/>
 </g>
 <!-- active&#45;&gt;stopping -->
 <g id="edge10" class="edge">
 <title>active&#45;&gt;stopping</title>
 <path fill="none" stroke="#00a000" d="M449.46,-41.89C463.64,-38.25 481.26,-33.72 497.34,-29.59"/>
 <polygon fill="#00a000" stroke="#00a000" points="498.29,-32.96 507.11,-27.08 496.55,-26.18 498.29,-32.96"/>
 </g>
 <!-- repeering -->
 <g id="node7" class="node">
 <title>repeering</title>
 <polygon fill="#a0a000" stroke="black" stroke-width="0" points="594.84,-83 569.16,-101 517.8,-101 492.12,-83 517.8,-65 569.16,-65 594.84,-83"/>
 <text text-anchor="middle" x="543.48" y="-79.9" font-family="sans-serif" font-size="12.00" fill="white">repeering</text>
 </g>
 <!-- active&#45;&gt;repeering -->
 <g id="edge7" class="edge">
 <title>active&#45;&gt;repeering</title>
 <path fill="none" stroke="#00a000" d="M448.85,-56.63C462.9,-60.59 480.44,-65.53 496.53,-70.06"/>
 <polygon fill="#00a000" stroke="#00a000" points="495.74,-73.47 506.32,-72.82 497.64,-66.74 495.74,-73.47"/>
 </g>
 <!-- repeering&#45;&gt;peering -->
 <g id="edge8" class="edge">
 <title>repeering&#45;&gt;peering</title>
 <path fill="none" stroke="#00a000" d="M495.33,-85.27C451.99,-87.36 387.93,-90.44 343.63,-92.58"/>
 <polygon fill="#00a000" stroke="#00a000" points="343.2,-89.09 333.38,-93.07 343.54,-96.09 343.2,-89.09"/>
 </g>
 </g>
 </svg>
--- a/mon/.eslintrc.js
+++ b/mon/.eslintrc.js
@ -1,54 +0,0 @@
 module.exports = {
    "env": {
        "es6": true,
        "node": true
    },
    "extends": [
        "eslint:recommended",
        "plugin:node/recommended"
    ],
    "parserOptions": {
        "ecmaVersion": 2020
    },
    "plugins": [
        "import"
    ],
    "rules": {
        "indent": [
            "error",
            4
        ],
        "brace-style": [
            "error",
            "allman",
            { "allowSingleLine": true }
        ],
        "linebreak-style": [
            "error",
            "unix"
        ],
        "semi": [
            "error",
            "always"
        ],
        "no-useless-escape": [
            "off"
        ],
        "no-control-regex": [
            "off"
        ],
        "no-empty": [
            "off"
        ],
        "no-process-exit": [
            "off"
        ],
        "node/shebang": [
            "off"
        ],
        "import/no-unresolved": [
            2,
            { "commonjs": true }
        ]
    }
 };
--- a/mon/scripts/90-vitastor.rules
+++ b/mon/scripts/90-vitastor.rules
--- a/mon/pg_utils.js
+++ b/mon/pg_utils.js
@ -97,6 +97,7 @@ function scale_pg_history(prev_pg_history, prev_pgs, new_pgs)
 function scale_pg_count(prev_pgs, new_pg_count)
 {
    const old_pg_count = prev_pgs.length;
    // Just for the lp_solve optimizer - pick a "previous" PG for each "new" one
    if (prev_pgs.length < new_pg_count)
    {
--- a/mon/scripts/afr.js
+++ b/mon/scripts/afr.js
--- a/mon/scripts/afr_test.js
+++ b/mon/scripts/afr_test.js
--- a/mon/etcd_adapter.js
+++ b/mon/etcd_adapter.js
@ -1,356 +0,0 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 (see README.md for details)
 const http = require('http');
 const WebSocket = require('ws');
 const MON_STOPPED = 'Monitor instance is stopped';
 class EtcdAdapter
 {
    constructor(mon)
    {
        this.mon = mon;
        this.ws = null;
        this.ws_alive = false;
        this.ws_keepalive_timer = null;
    }
    parse_config(config)
    {
        this.parse_etcd_addresses(config.etcd_address||config.etcd_url);
    }
    parse_etcd_addresses(addrs)
    {
        const is_local_ip = this.mon.local_ips(true).reduce((a, c) => { a[c] = true; return a; }, {});
        this.etcd_local = [];
        this.etcd_urls = [];
        this.selected_etcd_url = null;
        this.etcd_urls_to_try = [];
        if (!(addrs instanceof Array))
            addrs = addrs ? (''+(addrs||'')).split(/,/) : [];
        if (!addrs.length)
        {
            console.error('Vitastor etcd address(es) not specified. Please set on the command line or in the config file');
            process.exit(1);
        }
        for (let url of addrs)
        {
            let scheme = 'http';
            url = url.trim().replace(/^(https?):\/\//, (m, m1) => { scheme = m1; return ''; });
            const slash = url.indexOf('/');
            const colon = url.indexOf(':');
            const is_local = is_local_ip[colon >= 0 ? url.substr(0, colon) : (slash >= 0 ? url.substr(0, slash) : url)];
            url = scheme+'://'+(slash >= 0 ? url : url+'/v3');
            if (is_local)
                this.etcd_local.push(url);
            else
                this.etcd_urls.push(url);
        }
    }
    pick_next_etcd()
    {
        if (this.selected_etcd_url)
            return this.selected_etcd_url;
        if (!this.etcd_urls_to_try || !this.etcd_urls_to_try.length)
        {
            this.etcd_urls_to_try = [ ...this.etcd_local ];
            const others = [ ...this.etcd_urls ];
            while (others.length)
            {
                const url = others.splice(0|(others.length*Math.random()), 1);
                this.etcd_urls_to_try.push(url[0]);
            }
        }
        this.selected_etcd_url = this.etcd_urls_to_try.shift();
        return this.selected_etcd_url;
    }
    stop_watcher(cur_addr)
    {
        cur_addr = cur_addr || this.selected_etcd_url;
        if (this.ws)
        {
            console.log('Disconnected from etcd at '+this.ws_used_url);
            this.ws.close();
            this.ws = null;
        }
        if (this.ws_keepalive_timer)
        {
            clearInterval(this.ws_keepalive_timer);
            this.ws_keepalive_timer = null;
        }
        if (this.selected_etcd_url == cur_addr)
        {
            this.selected_etcd_url = null;
        }
    }
    restart_watcher(cur_addr)
    {
        this.stop_watcher(cur_addr);
        this.start_watcher(this.mon.config.etcd_mon_retries).catch(this.mon.die);
    }
    async start_watcher(retries)
    {
        let retry = 0;
        if (!retries || retries < 1)
        {
            retries = 1;
        }
        const tried = {};
        while (retries < 0 || retry < retries)
        {
            const cur_addr = this.pick_next_etcd();
            const base = 'ws'+cur_addr.substr(4);
            let now = Date.now();
            if (tried[base] && now-tried[base] < this.mon.config.etcd_start_timeout)
            {
                await new Promise(ok => setTimeout(ok, this.mon.config.etcd_start_timeout-(now-tried[base])));
                now = Date.now();
            }
            tried[base] = now;
            if (this.mon.stopped)
            {
                return;
            }
            const ok = await new Promise(ok =>
            {
                const timer_id = setTimeout(() =>
                {
                    if (this.ws)
                    {
                        console.log('Disconnected from etcd at '+this.ws_used_url);
                        this.ws.close();
                        this.ws = null;
                    }
                    ok(false);
                }, this.mon.config.etcd_mon_timeout);
                this.ws = new WebSocket(base+'/watch');
                this.ws_used_url = cur_addr;
                const fail = () =>
                {
                    ok(false);
                };
                this.ws.on('error', fail);
                this.ws.on('open', () =>
                {
                    this.ws.removeListener('error', fail);
                    if (timer_id)
                        clearTimeout(timer_id);
                    ok(true);
                });
            });
            if (ok)
                break;
            if (this.selected_etcd_url == cur_addr)
                this.selected_etcd_url = null;
            this.ws = null;
            retry++;
        }
        if (!this.ws)
        {
            this.mon.die('Failed to open etcd watch websocket');
            return;
        }
        if (this.mon.stopped)
        {
            this.stop_watcher();
            return;
        }
        const cur_addr = this.selected_etcd_url;
        this.ws_alive = true;
        this.ws_keepalive_timer = setInterval(() =>
        {
            if (this.ws_alive && this.ws)
            {
                this.ws_alive = false;
                this.ws.send(JSON.stringify({ progress_request: {} }));
            }
            else
            {
                console.log('etcd websocket timed out, restarting it');
                this.restart_watcher(cur_addr);
            }
        }, (Number(this.mon.config.etcd_ws_keepalive_interval) || 5)*1000);
        this.ws.on('error', () => this.restart_watcher(cur_addr));
        this.ws.send(JSON.stringify({
            create_request: {
                key: b64(this.mon.config.etcd_prefix+'/'),
                range_end: b64(this.mon.config.etcd_prefix+'0'),
                start_revision: ''+this.mon.etcd_watch_revision,
                watch_id: 1,
                progress_notify: true,
            },
        }));
        this.ws.on('message', (msg) =>
        {
            if (this.mon.stopped)
            {
                this.stop_watcher();
                return;
            }
            this.ws_alive = true;
            let data;
            try
            {
                data = JSON.parse(msg);
            }
            catch (e)
            {
            }
            if (!data || !data.result)
            {
                console.error('Unknown message received from watch websocket: '+msg);
            }
            else if (data.result.canceled)
            {
                // etcd watch canceled
                if (data.result.compact_revision)
                {
                    // we may miss events if we proceed
                    this.mon.die('Revisions before '+data.result.compact_revision+' were compacted by etcd, exiting');
                }
                this.mon.die('Watch canceled by etcd, reason: '+data.result.cancel_reason+', exiting');
            }
            else if (data.result.created)
            {
                // etcd watch created
                console.log('Successfully subscribed to etcd at '+this.selected_etcd_url+', revision '+data.result.header.revision);
            }
            else
            {
                this.mon.on_message(data.result);
            }
        });
    }
    async become_master()
    {
        const state = { ...this.mon.get_mon_state(), id: ''+this.mon.etcd_lease_id };
        // eslint-disable-next-line no-constant-condition
        while (1)
        {
            const res = await this.etcd_call('/kv/txn', {
                compare: [ { target: 'CREATE', create_revision: 0, key: b64(this.mon.config.etcd_prefix+'/mon/master') } ],
                success: [ { requestPut: { key: b64(this.mon.config.etcd_prefix+'/mon/master'), value: b64(JSON.stringify(state)), lease: ''+this.mon.etcd_lease_id } } ],
            }, this.mon.config.etcd_start_timeout, 0);
            if (res.succeeded)
            {
                break;
            }
            console.log('Waiting to become master');
            await new Promise(ok => setTimeout(ok, this.mon.config.etcd_start_timeout));
        }
        console.log('Became master');
    }
    async etcd_call(path, body, timeout, retries)
    {
        let retry = 0;
        if (retries >= 0 && retries < 1)
        {
            retries = 1;
        }
        const tried = {};
        while (retries < 0 || retry < retries)
        {
            retry++;
            const base = this.pick_next_etcd();
            let now = Date.now();
            if (tried[base] && now-tried[base] < timeout)
            {
                await new Promise(ok => setTimeout(ok, timeout-(now-tried[base])));
                now = Date.now();
            }
            tried[base] = now;
            if (this.mon.stopped)
            {
                throw new Error(MON_STOPPED);
            }
            const res = await POST(base+path, body, timeout);
            if (this.mon.stopped)
            {
                throw new Error(MON_STOPPED);
            }
            if (res.error)
            {
                if (this.selected_etcd_url == base)
                    this.selected_etcd_url = null;
                console.error('Failed to query etcd '+path+' (retry '+retry+'/'+retries+'): '+res.error);
                continue;
            }
            if (res.json)
            {
                if (res.json.error)
                {
                    console.error(path+': etcd returned error: '+res.json.error);
                    break;
                }
                return res.json;
            }
        }
        throw new Error('Failed to query etcd ('+retries+' retries)');
    }
 }
 function POST(url, body, timeout)
 {
    return new Promise(ok =>
    {
        const body_text = Buffer.from(JSON.stringify(body));
        let timer_id = timeout > 0 ? setTimeout(() =>
        {
            if (req)
                req.abort();
            req = null;
            ok({ error: 'timeout' });
        }, timeout) : null;
        let req = http.request(url, { method: 'POST', headers: {
            'Content-Type': 'application/json',
            'Content-Length': body_text.length,
        } }, (res) =>
        {
            if (!req)
            {
                return;
            }
            clearTimeout(timer_id);
            let res_body = '';
            res.setEncoding('utf8');
            res.on('error', (error) => ok({ error }));
            res.on('data', chunk => { res_body += chunk; });
            res.on('end', () =>
            {
                if (res.statusCode != 200)
                {
                    ok({ error: res_body, code: res.statusCode });
                    return;
                }
                try
                {
                    res_body = JSON.parse(res_body);
                    ok({ response: res, json: res_body });
                }
                catch (e)
                {
                    ok({ error: e, response: res, body: res_body });
                }
            });
        });
        req.on('error', (error) => ok({ error }));
        req.on('close', () => ok({ error: new Error('Connection closed prematurely') }));
        req.write(body_text);
        req.end();
    });
 }
 function b64(str)
 {
    return Buffer.from(str).toString('base64');
 }
 module.exports = EtcdAdapter;
--- a/mon/etcd_schema.js
+++ b/mon/etcd_schema.js
@ -1,391 +0,0 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 (see README.md for details)
 // FIXME document all etcd keys and config variables in the form of JSON schema or similar
 const etcd_nonempty_keys = {
    'config/global': 1,
    'config/node_placement': 1,
    'config/pools': 1,
    'config/pgs': 1,
    'history/last_clean_pgs': 1,
    'stats': 1,
 };
 const etcd_allow = new RegExp('^'+[
    'config/global',
    'config/node_placement',
    'config/pools',
    'config/osd/[1-9]\\d*',
    'config/pgs',
    'config/inode/[1-9]\\d*/[1-9]\\d*',
    'osd/state/[1-9]\\d*',
    'osd/stats/[1-9]\\d*',
    'osd/inodestats/[1-9]\\d*',
    'osd/space/[1-9]\\d*',
    'mon/master',
    'mon/member/[a-f0-9]+',
    'pg/state/[1-9]\\d*/[1-9]\\d*',
    'pg/stats/[1-9]\\d*/[1-9]\\d*',
    'pg/history/[1-9]\\d*/[1-9]\\d*',
    'history/last_clean_pgs',
    'inode/stats/[1-9]\\d*/\\d+',
    'pool/stats/[1-9]\\d*',
    'stats',
    'index/image/.*',
    'index/maxid/[1-9]\\d*',
 ].join('$|^')+'$');
 const etcd_tree = {
    config: {
        /* global: {
            // WARNING: NOT ALL OF THESE ARE ACTUALLY CONFIGURABLE HERE
            // THIS IS JUST A POOR MAN'S CONFIG DOCUMENTATION
            // etcd connection
            config_path: "/etc/vitastor/vitastor.conf",
            etcd_prefix: "/vitastor",
            // etcd connection - configurable online
            etcd_address: "10.0.115.10:2379/v3",
            // mon
            etcd_mon_ttl: 5, // min: 1
            etcd_mon_timeout: 1000, // ms. min: 0
            etcd_mon_retries: 5, // min: 0
            mon_change_timeout: 1000, // ms. min: 100
            mon_retry_change_timeout: 50, // ms. min: 10
            mon_stats_timeout: 1000, // ms. min: 100
            osd_out_time: 600, // seconds. min: 0
            placement_levels: { datacenter: 1, rack: 2, host: 3, osd: 4, ... },
            use_old_pg_combinator: false,
            // client and osd
            tcp_header_buffer_size: 65536,
            use_sync_send_recv: false,
            use_rdma: true,
            rdma_device: null, // for example, "rocep5s0f0"
            rdma_port_num: 1,
            rdma_gid_index: 0,
            rdma_mtu: 4096,
            rdma_max_sge: 128,
            rdma_max_send: 8,
            rdma_max_recv: 16,
            rdma_max_msg: 132096,
            block_size: 131072,
            disk_alignment: 4096,
            bitmap_granularity: 4096,
            immediate_commit: false, // 'all' or 'small'
            // client - configurable online
            client_max_dirty_bytes: 33554432,
            client_max_dirty_ops: 1024,
            client_enable_writeback: false,
            client_max_buffered_bytes: 33554432,
            client_max_buffered_ops: 1024,
            client_max_writeback_iodepth: 256,
            client_retry_interval: 50, // ms. min: 10
            client_eio_retry_interval: 1000, // ms
            client_retry_enospc: true,
            osd_nearfull_ratio: 0.95,
            // client and osd - configurable online
            log_level: 0,
            peer_connect_interval: 5, // seconds. min: 1
            peer_connect_timeout: 5, // seconds. min: 1
            osd_idle_timeout: 5, // seconds. min: 1
            osd_ping_timeout: 5, // seconds. min: 1
            max_etcd_attempts: 5,
            etcd_quick_timeout: 1000, // ms
            etcd_slow_timeout: 5000, // ms
            etcd_keepalive_timeout: 30, // seconds, default is max(30, etcd_report_interval*2)
            etcd_ws_keepalive_interval: 5, // seconds
            // osd
            etcd_report_interval: 5, // seconds
            etcd_stats_interval: 30, // seconds
            run_primary: true,
            osd_network: null, // "192.168.7.0/24" or an array of masks
            bind_address: "0.0.0.0",
            bind_port: 0,
            readonly: false,
            osd_memlock: false,
            // osd - configurable online
            autosync_interval: 5,
            autosync_writes: 128,
            client_queue_depth: 128, // unused
            recovery_queue_depth: 1,
            recovery_sleep_us: 0,
            recovery_tune_util_low: 0.1,
            recovery_tune_client_util_low: 0,
            recovery_tune_util_high: 1.0,
            recovery_tune_client_util_high: 0.5,
            recovery_tune_interval: 1,
            recovery_tune_agg_interval: 10, // 10 times recovery_tune_interval
            recovery_tune_sleep_min_us: 10, // 10 microseconds
            recovery_pg_switch: 128,
            recovery_sync_batch: 16,
            no_recovery: false,
            no_rebalance: false,
            print_stats_interval: 3,
            slow_log_interval: 10,
            inode_vanish_time: 60,
            auto_scrub: false,
            no_scrub: false,
            scrub_interval: '30d', // 1s/1m/1h/1d
            scrub_queue_depth: 1,
            scrub_sleep: 0, // milliseconds
            scrub_list_limit: 1000, // objects to list on one scrub iteration
            scrub_find_best: true,
            scrub_ec_max_bruteforce: 100, // maximum EC error locator brute-force iterators
            // blockstore - fixed in superblock
            block_size,
            disk_alignment,
            journal_block_size,
            meta_block_size,
            bitmap_granularity,
            journal_device,
            journal_offset,
            journal_size,
            disable_journal_fsync,
            data_device,
            data_offset,
            data_size,
            disable_data_fsync,
            meta_device,
            meta_offset,
            disable_meta_fsync,
            disable_device_lock,
            // blockstore - configurable offline
            inmemory_metadata,
            inmemory_journal,
            journal_sector_buffer_count,
            journal_no_same_sector_overwrites,
            // blockstore - configurable online
            max_write_iodepth,
            min_flusher_count: 1,
            max_flusher_count: 256,
            throttle_small_writes: false,
            throttle_target_iops: 100,
            throttle_target_mbs: 100,
            throttle_target_parallelism: 1,
            throttle_threshold_us: 50,
        }, */
        global: {},
        /* node_placement: {
            host1: { level: 'host', parent: 'rack1' },
            ...
        }, */
        node_placement: {},
        /* pools: {
            <id>: {
                name: 'testpool',
                // 'ec' uses Reed-Solomon-Vandermonde codes, 'jerasure' is an alias for 'ec'
                scheme: 'replicated' | 'xor' | 'ec' | 'jerasure',
                pg_size: 3,
                pg_minsize: 2,
                // number of parity chunks, required for EC
                parity_chunks?: 1,
                pg_count: 100,
                // default is failure_domain=host
                failure_domain?: 'host',
                // additional failure domain rules; failure_domain=x is equivalent to x=123..N
                level_placement?: 'dc=112233 host=123456',
                raw_placement?: 'any, dc=1 host!=1, dc=1 host!=(1,2)',
                old_combinator: false,
                max_osd_combinations: 10000,
                // block_size, bitmap_granularity, immediate_commit must match all OSDs used in that pool
                block_size: 131072,
                bitmap_granularity: 4096,
                // 'all'/'small'/'none', same as in OSD options
                immediate_commit: 'none',
                pg_stripe_size: 0,
                root_node?: 'rack1',
                // restrict pool to OSDs having all of these tags
                osd_tags?: 'nvme' | [ 'nvme', ... ],
                // prefer to put primary on OSD with these tags
                primary_affinity_tags?: 'nvme' | [ 'nvme', ... ],
                // scrub interval
                scrub_interval?: '30d',
            },
            ...
        }, */
        pools: {},
        osd: {
            /* <id>: { reweight?: 1, tags?: [ 'nvme', ... ], noout?: true }, ... */
        },
        /* pgs: {
            hash: string,
            items: {
                <pool_id>: {
                    <pg_id>: {
                        osd_set: [ 1, 2, 3 ],
                        primary: 1,
                        pause: false,
                    }
                }
            }
        }, */
        pgs: {},
        /* inode: {
            <pool_id>: {
                <inode_t>: {
                    name: string,
                    size?: uint64_t, // bytes
                    parent_pool?: <pool_id>,
                    parent_id?: <inode_t>,
                    readonly?: boolean,
                }
            }
        }, */
        inode: {},
    },
    osd: {
        state: {
            /* <osd_num_t>: {
                state: "up",
                addresses: string[],
                host: string,
                port: uint16_t,
                primary_enabled: boolean,
                blockstore_enabled: boolean,
            }, */
        },
        stats: {
            /* <osd_num_t>: {
                time: number, // unix time
                blockstore_ready: boolean,
                size: uint64_t, // bytes
                free: uint64_t, // bytes
                host: string,
                op_stats: {
                    <string>: { count: uint64_t, usec: uint64_t, bytes: uint64_t },
                },
                subop_stats: {
                    <string>: { count: uint64_t, usec: uint64_t },
                },
                recovery_stats: {
                    degraded: { count: uint64_t, bytes: uint64_t },
                    misplaced: { count: uint64_t, bytes: uint64_t },
                },
            }, */
        },
        inodestats: {
            /* <pool_id>: {
                <inode_t>: {
                    read: { count: uint64_t, usec: uint64_t, bytes: uint64_t },
                    write: { count: uint64_t, usec: uint64_t, bytes: uint64_t },
                    delete: { count: uint64_t, usec: uint64_t, bytes: uint64_t },
                },
            }, */
        },
        space: {
            /* <osd_num_t>: {
                <pool_id>: {
                    <inode_t>: uint64_t, // bytes
                },
            }, */
        },
    },
    mon: {
        master: {
            /* ip: [ string ], id: uint64_t */
        },
        standby: {
            /* <uint64_t>: { ip: [ string ] }, */
        },
    },
    pg: {
        state: {
            /* <pool_id>: {
                <pg_id>: {
                    primary: osd_num_t,
                    state: ("starting"|"peering"|"incomplete"|"active"|"repeering"|"stopping"|"offline"|
                        "degraded"|"has_incomplete"|"has_degraded"|"has_misplaced"|"has_unclean"|
                        "has_invalid"|"has_inconsistent"|"has_corrupted"|"left_on_dead"|"scrubbing")[],
                }
            }, */
        },
        stats: {
            /* <pool_id>: {
                <pg_id>: {
                    object_count: uint64_t,
                    clean_count: uint64_t,
                    misplaced_count: uint64_t,
                    degraded_count: uint64_t,
                    incomplete_count: uint64_t,
                    write_osd_set: osd_num_t[],
                },
            }, */
        },
        history: {
            /* <pool_id>: {
                <pg_id>: {
                    osd_sets: osd_num_t[][],
                    all_peers: osd_num_t[],
                    epoch: uint64_t,
                    next_scrub: uint64_t,
                },
            }, */
        },
    },
    inode: {
        stats: {
            /* <pool_id>: {
                <inode_t>: {
                    raw_used: uint64_t, // raw used bytes on OSDs
                    read: { count: uint64_t, usec: uint64_t, bytes: uint64_t, bps: uint64_t, iops: uint64_t, lat: uint64_t },
                    write: { count: uint64_t, usec: uint64_t, bytes: uint64_t, bps: uint64_t, iops: uint64_t, lat: uint64_t },
                    delete: { count: uint64_t, usec: uint64_t, bytes: uint64_t, bps: uint64_t, iops: uint64_t, lat: uint64_t },
                },
            }, */
        },
    },
    pool: {
        stats: {
            /* <pool_id>: {
                used_raw_tb: float, // used raw space in the pool
                total_raw_tb: float, // maximum amount of space in the pool
                raw_to_usable: float, // raw to usable ratio
                space_efficiency: float, // 0..1
            } */
        },
    },
    stats: {
        /* op_stats: {
            <string>: { count: uint64_t, usec: uint64_t, bytes: uint64_t, bps: uint64_t, iops: uint64_t, lat: uint64_t },
        },
        subop_stats: {
            <string>: { count: uint64_t, usec: uint64_t, iops: uint64_t, lat: uint64_t },
        },
        recovery_stats: {
            degraded: { count: uint64_t, bytes: uint64_t, bps: uint64_t, iops: uint64_t },
            misplaced: { count: uint64_t, bytes: uint64_t, bps: uint64_t, iops: uint64_t },
        },
        object_counts: {
            object: uint64_t,
            clean: uint64_t,
            misplaced: uint64_t,
            degraded: uint64_t,
            incomplete: uint64_t,
        },
        object_bytes: {
            total: uint64_t,
            clean: uint64_t,
            misplaced: uint64_t,
            degraded: uint64_t,
            incomplete: uint64_t,
        }, */
    },
    history: {
        last_clean_pgs: {},
    },
    index: {
        image: {
            /* <name>: {
                id: uint64_t,
                pool_id: uint64_t,
            }, */
        },
        maxid: {
            /* <pool_id>: uint64_t, */
        },
    },
 };
 module.exports = {
    etcd_nonempty_keys,
    etcd_allow,
    etcd_tree,
 };
--- a/mon/lp_optimizer/lp_optimizer.js
+++ b/mon/lp_optimizer/lp_optimizer.js
@ -50,15 +50,15 @@ async function lp_solve(text)
    return { score, vars };
 }
-// osd_weights = { [id]: weight }
+async function optimize_initial({ osd_tree, pg_count, pg_size = 3, pg_minsize = 2, max_combinations = 10000, parity_space = 1, ordered = false })
 async function optimize_initial({ osd_weights, combinator, pg_count, pg_size = 3, pg_minsize = 2, parity_space = 1, ordered = false })
 {
-    if (!pg_count || !osd_weights)
+    if (!pg_count || !osd_tree)
    {
        return null;
    }
-    const total_weight = Object.values(osd_weights).reduce((a, c) => Number(a) + Number(c), 0);
+    const all_weights = Object.assign({}, ...Object.values(osd_tree));
-    const all_pgs = Object.values(make_cyclic(combinator.random_combinations(), parity_space));
+    const total_weight = Object.values(all_weights).reduce((a, c) => Number(a) + Number(c), 0);
    const all_pgs = Object.values(random_combinations(osd_tree, pg_size, max_combinations, parity_space > 1));
    const pg_per_osd = {};
    for (const pg of all_pgs)
    {
@ -69,15 +69,15 @@ async function optimize_initial({ osd_weights, combinator, pg_count, pg_size = 3
            pg_per_osd[osd].push((i >= pg_minsize ? parity_space+'*' : '')+"pg_"+pg.join("_"));
        }
    }
-    let pg_effsize = all_pgs.reduce((a, c) => Math.max(a, c.filter(e => e != NO_OSD).length), 0);
+    const pg_effsize = Math.min(pg_minsize, Object.keys(osd_tree).length)
-    pg_effsize = Math.min(pg_minsize, pg_effsize) + Math.max(0, Math.min(pg_size, pg_effsize) - pg_minsize) * parity_space;
+        + Math.max(0, Math.min(pg_size, Object.keys(osd_tree).length) - pg_minsize) * parity_space;
    let lp = '';
    lp += "max: "+all_pgs.map(pg => 'pg_'+pg.join('_')).join(' + ')+";\n";
    for (const osd in pg_per_osd)
    {
        if (osd !== NO_OSD)
        {
-            let osd_pg_count = osd_weights[osd]/total_weight*pg_effsize*pg_count;
+            let osd_pg_count = all_weights[osd]/total_weight*pg_effsize*pg_count;
            lp += pg_per_osd[osd].join(' + ')+' <= '+osd_pg_count+';\n';
        }
    }
@ -93,7 +93,7 @@ async function optimize_initial({ osd_weights, combinator, pg_count, pg_size = 3
        throw new Error('Problem is infeasible or unbounded - is it a bug?');
    }
    const int_pgs = make_int_pgs(lp_result.vars, pg_count, ordered);
-    const eff = pg_list_space_efficiency(int_pgs, osd_weights, pg_minsize, parity_space);
+    const eff = pg_list_space_efficiency(int_pgs, all_weights, pg_minsize, parity_space);
    const res = {
        score: lp_result.score,
        weights: lp_result.vars,
@ -104,22 +104,6 @@ async function optimize_initial({ osd_weights, combinator, pg_count, pg_size = 3
    return res;
 }
 function make_cyclic(pgs, parity_space)
 {
    if (parity_space > 1)
    {
        for (const pg in pgs)
        {
            for (let i = 1; i < pg.size; i++)
            {
                const cyclic = [ ...pg.slice(i), ...pg.slice(0, i) ];
                pgs['pg_'+cyclic.join('_')] = cyclic;
            }
        }
    }
    return pgs;
 }
 function shuffle(array)
 {
    for (let i = array.length - 1, j, x; i > 0; i--)
@ -215,7 +199,7 @@ function calc_intersect_weights(old_pg_size, pg_size, pg_count, prev_weights, al
                {
                    const intersect_count = ordered
                        ? pg.reduce((a, osd, i) => a + (prev_hash[osd] == 1+i ? 1 : 0), 0)
-                        : pg.reduce((a, osd) => a + (prev_hash[osd] ? 1 : 0), 0);
+                        : pg.reduce((a, osd, i) => a + (prev_hash[osd] ? 1 : 0), 0);
                    if (max_int < intersect_count)
                    {
                        max_int = intersect_count;
@ -232,17 +216,47 @@ function calc_intersect_weights(old_pg_size, pg_size, pg_count, prev_weights, al
    return move_weights;
 }
-// Try to minimize data movement
+function add_valid_previous(osd_tree, prev_weights, all_pgs)
 async function optimize_change({ prev_pgs: prev_int_pgs, osd_weights, combinator, pg_size = 3, pg_minsize = 2, parity_space = 1, ordered = false })
 {
-    if (!osd_weights)
+    // Add previous combinations that are still valid
    const hosts = Object.keys(osd_tree).sort();
    const host_per_osd = {};
    for (const host in osd_tree)
    {
        for (const osd in osd_tree[host])
        {
            host_per_osd[osd] = host;
        }
    }
    skip_pg: for (const pg_name in prev_weights)
    {
        const seen_hosts = {};
        const pg = pg_name.substr(3).split(/_/);
        for (const osd of pg)
        {
            if (!host_per_osd[osd] || seen_hosts[host_per_osd[osd]])
            {
                continue skip_pg;
            }
            seen_hosts[host_per_osd[osd]] = true;
        }
        if (!all_pgs[pg_name])
        {
            all_pgs[pg_name] = pg;
        }
    }
 }
 // Try to minimize data movement
 async function optimize_change({ prev_pgs: prev_int_pgs, osd_tree, pg_size = 3, pg_minsize = 2, max_combinations = 10000, parity_space = 1, ordered = false })
 {
    if (!osd_tree)
    {
        return null;
    }
    // FIXME: use parity_chunks with parity_space instead of pg_minsize
-    let all_pgs = make_cyclic(combinator.random_combinations(), parity_space);
+    const pg_effsize = Math.min(pg_minsize, Object.keys(osd_tree).length)
-    let pg_effsize = Object.values(all_pgs).reduce((a, c) => Math.max(a, c.filter(e => e != NO_OSD).length), 0);
+        + Math.max(0, Math.min(pg_size, Object.keys(osd_tree).length) - pg_minsize) * parity_space;
    pg_effsize = Math.min(pg_minsize, pg_effsize) + Math.max(0, Math.min(pg_size, pg_effsize) - pg_minsize) * parity_space;
    const pg_count = prev_int_pgs.length;
    const prev_weights = {};
    const prev_pg_per_osd = {};
@ -259,13 +273,10 @@ async function optimize_change({ prev_pgs: prev_int_pgs, osd_weights, combinator
    }
    const old_pg_size = prev_int_pgs[0].length;
    // Get all combinations
    let all_pgs = random_combinations(osd_tree, pg_size, max_combinations, parity_space > 1);
    if (old_pg_size == pg_size)
    {
-        const still_valid = combinator.check_combinations(Object.keys(prev_weights).map(pg_name => pg_name.substr(3).split('_')));
+        add_valid_previous(osd_tree, prev_weights, all_pgs);
        for (const pg of still_valid)
        {
            all_pgs['pg_'+pg.join('_')] = pg;
        }
    }
    all_pgs = Object.values(all_pgs);
    const pg_per_osd = {};
@ -284,7 +295,8 @@ async function optimize_change({ prev_pgs: prev_int_pgs, osd_weights, combinator
    // Calculate total weight - old PG weights
    const all_pg_names = all_pgs.map(pg => 'pg_'+pg.join('_'));
    const all_pgs_hash = all_pg_names.reduce((a, c) => { a[c] = true; return a; }, {});
-    const total_weight = Object.values(osd_weights).reduce((a, c) => Number(a) + Number(c), 0);
+    const all_weights = Object.assign({}, ...Object.values(osd_tree));
    const total_weight = Object.values(all_weights).reduce((a, c) => Number(a) + Number(c), 0);
    // Generate the LP problem
    let lp = '';
    lp += 'max: '+all_pg_names.map(pg_name => (
@ -299,7 +311,7 @@ async function optimize_change({ prev_pgs: prev_int_pgs, osd_weights, combinator
            )).join(' + ');
            const rm_osd_pg_count = (prev_pg_per_osd[osd]||[])
                .reduce((a, [ old_pg_name, space ]) => (a + (all_pgs_hash[old_pg_name] ? space : 0)), 0);
-            const osd_pg_count = osd_weights[osd]*pg_effsize/total_weight*pg_count - rm_osd_pg_count;
+            const osd_pg_count = all_weights[osd]*pg_effsize/total_weight*pg_count - rm_osd_pg_count;
            lp += osd_sum + ' <= ' + osd_pg_count + ';\n';
        }
    }
@ -409,7 +421,7 @@ async function optimize_change({ prev_pgs: prev_int_pgs, osd_weights, combinator
        int_pgs: new_pgs,
        differs,
        osd_differs,
-        space: pg_effsize * pg_list_space_efficiency(new_pgs, osd_weights, pg_minsize, parity_space),
+        space: pg_effsize * pg_list_space_efficiency(new_pgs, all_weights, pg_minsize, parity_space),
        total_space: total_weight,
    };
 }
@ -490,6 +502,198 @@ function put_aligned_pgs(aligned_pgs, int_pgs, prev_int_pgs, keygen)
    }
 }
 // Convert multi-level osd_tree = { level: number|string, id?: string, size?: number, children?: osd_tree }[]
 // levels = { string: number }
 // to a two-level osd_tree suitable for all_combinations()
 function flatten_tree(osd_tree, levels, failure_domain_level, osd_level, domains = {}, i = { i: 1 })
 {
    osd_level = levels[osd_level] || osd_level;
    failure_domain_level = levels[failure_domain_level] || failure_domain_level;
    for (const node of osd_tree)
    {
        if ((levels[node.level] || node.level) < failure_domain_level)
        {
            flatten_tree(node.children||[], levels, failure_domain_level, osd_level, domains, i);
        }
        else
        {
            domains['dom'+(i.i++)] = extract_osds([ node ], levels, osd_level);
        }
    }
    return domains;
 }
 function extract_osds(osd_tree, levels, osd_level, osds = {})
 {
    for (const node of osd_tree)
    {
        if ((levels[node.level] || node.level) >= osd_level)
        {
            osds[node.id] = node.size;
        }
        else
        {
            extract_osds(node.children||[], levels, osd_level, osds);
        }
    }
    return osds;
 }
 // ordered = don't treat (x,y) and (y,x) as equal
 function random_combinations(osd_tree, pg_size, count, ordered)
 {
    let seed = 0x5f020e43;
    let rng = () =>
    {
        seed ^= seed << 13;
        seed ^= seed >> 17;
        seed ^= seed << 5;
        return seed + 2147483648;
    };
    const osds = Object.keys(osd_tree).reduce((a, c) => { a[c] = Object.keys(osd_tree[c]).sort(); return a; }, {});
    const hosts = Object.keys(osd_tree).sort().filter(h => osds[h].length > 0);
    const r = {};
    // Generate random combinations including each OSD at least once
    for (let h = 0; h < hosts.length; h++)
    {
        for (let o = 0; o < osds[hosts[h]].length; o++)
        {
            const pg = [ osds[hosts[h]][o] ];
            const cur_hosts = [ ...hosts ];
            cur_hosts.splice(h, 1);
            for (let i = 1; i < pg_size && i < hosts.length; i++)
            {
                const next_host = rng() % cur_hosts.length;
                const next_osd = rng() % osds[cur_hosts[next_host]].length;
                pg.push(osds[cur_hosts[next_host]][next_osd]);
                cur_hosts.splice(next_host, 1);
            }
            const cyclic_pgs = [ pg ];
            if (ordered)
            {
                for (let i = 1; i < pg.size; i++)
                {
                    cyclic_pgs.push([ ...pg.slice(i), ...pg.slice(0, i) ]);
                }
            }
            for (const pg of cyclic_pgs)
            {
                while (pg.length < pg_size)
                {
                    pg.push(NO_OSD);
                }
                r['pg_'+pg.join('_')] = pg;
            }
        }
    }
    // Generate purely random combinations
    while (count > 0)
    {
        let host_idx = [];
        const cur_hosts = [ ...hosts.map((h, i) => i) ];
        const max_hosts = pg_size < hosts.length ? pg_size : hosts.length;
        if (ordered)
        {
            for (let i = 0; i < max_hosts; i++)
            {
                const r = rng() % cur_hosts.length;
                host_idx[i] = cur_hosts[r];
                cur_hosts.splice(r, 1);
            }
        }
        else
        {
            for (let i = 0; i < max_hosts; i++)
            {
                const r = rng() % (cur_hosts.length - (max_hosts - i - 1));
                host_idx[i] = cur_hosts[r];
                cur_hosts.splice(0, r+1);
            }
        }
        let pg = host_idx.map(h => osds[hosts[h]][rng() % osds[hosts[h]].length]);
        while (pg.length < pg_size)
        {
            pg.push(NO_OSD);
        }
        r['pg_'+pg.join('_')] = pg;
        count--;
    }
    return r;
 }
 // Super-stupid algorithm. Given the current OSD tree, generate all possible OSD combinations
 // osd_tree = { failure_domain1: { osd1: size1, ... }, ... }
 // ordered = return combinations without duplicates having different order
 function all_combinations(osd_tree, pg_size, ordered, count)
 {
    const hosts = Object.keys(osd_tree).sort();
    const osds = Object.keys(osd_tree).reduce((a, c) => { a[c] = Object.keys(osd_tree[c]).sort(); return a; }, {});
    while (hosts.length < pg_size)
    {
        osds[NO_OSD] = [ NO_OSD ];
        hosts.push(NO_OSD);
    }
    let host_idx = [];
    let osd_idx = [];
    for (let i = 0; i < pg_size; i++)
    {
        host_idx.push(i);
        osd_idx.push(0);
    }
    const r = [];
    while (!count || count < 0 || r.length < count)
    {
        r.push(host_idx.map((hi, i) => osds[hosts[hi]][osd_idx[i]]));
        let inc = pg_size-1;
        while (inc >= 0)
        {
            osd_idx[inc]++;
            if (osd_idx[inc] >= osds[hosts[host_idx[inc]]].length)
            {
                osd_idx[inc] = 0;
                inc--;
            }
            else
            {
                break;
            }
        }
        if (inc < 0)
        {
            // no osds left in the current host combination, select the next one
            inc = pg_size-1;
            same_again: while (inc >= 0)
            {
                host_idx[inc]++;
                for (let prev_host = 0; prev_host < inc; prev_host++)
                {
                    if (host_idx[prev_host] == host_idx[inc])
                    {
                        continue same_again;
                    }
                }
                if (host_idx[inc] < (ordered ? hosts.length-(pg_size-1-inc) : hosts.length))
                {
                    while ((++inc) < pg_size)
                    {
                        host_idx[inc] = (ordered ? host_idx[inc-1]+1 : 0);
                    }
                    break;
                }
                else
                {
                    inc--;
                }
            }
            if (inc < 0)
            {
                break;
            }
        }
    }
    return r;
 }
 function pg_weights_space_efficiency(weights, pg_count, osd_sizes)
 {
    const per_osd = {};
@ -548,8 +752,11 @@ module.exports = {
    pg_weights_space_efficiency,
    pg_list_space_efficiency,
    pg_per_osd_space_efficiency,
    flatten_tree,
    lp_solve,
    make_int_pgs,
    align_pgs,
    random_combinations,
    all_combinations,
 };
--- a/mon/lp_optimizer/dsl_pgs.js
+++ b/mon/lp_optimizer/dsl_pgs.js
@ -1,409 +0,0 @@
 const { select_murmur3 } = require('./murmur3.js');
 const NO_OSD = 'Z';
 class RuleCombinator
 {
    constructor(osd_tree, rules, max_combinations, ordered)
    {
        this.osd_tree = index_tree(Object.values(osd_tree).filter(o => o.id));
        this.rules = rules;
        this.max_combinations = max_combinations;
        this.ordered = ordered;
    }
    random_combinations()
    {
        return random_custom_combinations(this.osd_tree, this.rules, this.max_combinations, this.ordered);
    }
    check_combinations(pgs)
    {
        return check_custom_combinations(this.osd_tree, this.rules, pgs);
    }
 }
 // Convert alternative "level-index" format to rules
 // level_index = { [level: string]: string | string[] }
 // level_sequence = optional, levels from upper to lower, i.e. [ 'dc', 'host' ]
 // Example: level_index = { dc: "112233", host: "ABCDEF" }
 function parse_level_indexes(level_index, level_sequence)
 {
    const rules = [];
    const lvl_first = {};
    for (const level in level_index)
    {
        const idx = level_index[level];
        while (rules.length < idx.length)
        {
            rules.push([]);
        }
        const seen = {};
        for (let i = 0; i < idx.length; i++)
        {
            if (!seen[idx[i]])
            {
                const other = Object.values(seen);
                if (other.length)
                {
                    rules[i].push([ level, '!=', other ]);
                }
                seen[idx[i]] = i+1;
            }
            else
            {
                rules[i].push([ level, '=', seen[idx[i]] ]);
            }
        }
        lvl_first[level] = seen;
    }
    if (level_sequence)
    {
        // Prune useless rules for the sake of prettiness
        // For simplicity, call "upper" level DC and "lower" level host
        const level_prio = Object.keys(level_sequence).reduce((a, c) => { a[level_sequence[c]] = c; return a; }, {});
        for (let upper_i = 0; upper_i < level_sequence.length-1; upper_i++)
        {
            const upper_level = level_sequence[upper_i];
            for (let i = 0; i < rules.length; i++)
            {
                const noteq = {};
                for (let k = 0; k < level_index[upper_level].length; k++)
                {
                    // If upper_level[x] is different from upper_level[y]
                    // then lower_level[x] is also different from lower_level[y]
                    if (level_index[upper_level][k] != level_index[upper_level][i])
                    {
                        noteq[k+1] = true;
                    }
                }
                for (let j = 0; j < rules[i].length; j++)
                {
                    if (level_prio[rules[i][j][0]] != null && level_prio[rules[i][j][0]] > upper_i && rules[i][j][1] == '!=')
                    {
                        rules[i][j][2] = rules[i][j][2].filter(other_host => !noteq[other_host]);
                        if (!rules[i][j][2].length)
                        {
                            rules[i].splice(j--, 1);
                        }
                    }
                }
            }
        }
    }
    return rules;
 }
 // Parse rules in DSL format
 // dsl := item | item ("\n" | ",") items
 // item := "any" | rules
 // rules := rule | rule rules
 // rule := level operator arg
 // level := /\w+/
 // operator := "!=" | "=" | ">" | "?="
 // arg := value | "(" values ")"
 // values := value | value "," values
 // value := item_ref | constant_id
 // item_ref := /\d+/
 // constant_id := /"([^"]+)"/
 //
 // Output: [ level, operator, value ][][]
 function parse_pg_dsl(text)
 {
    const tokens = [ ...text.matchAll(/\w+|!=|\?=|[>=\(\),\n]|"([^\"]+)"/g) ].map(t => [ t[0], t.index ]);
    let positions = [ [] ];
    let rules = positions[0];
    for (let i = 0; i < tokens.length; )
    {
        if (tokens[i][0] === '\n' || tokens[i][0] === ',')
        {
            rules = [];
            positions.push(rules);
            i++;
        }
        else if (!rules.length && tokens[i][0] === 'any' && (i == tokens.length-1 || tokens[i+1][0] === ',' || tokens[i+1][0] === '\n'))
        {
            i++;
        }
        else
        {
            if (!/^\w/.exec(tokens[i][0]))
            {
                throw new Error('Unexpected '+tokens[i][0]+' at '+tokens[i][1]+' (level name expected)');
            }
            if (i > tokens.length-3)
            {
                throw new Error('Unexpected EOF (operator and value expected)');
            }
            if (/^\w/.exec(tokens[i+1][0]) || tokens[i+1][0] === ',' || tokens[i+1][0] === '\n')
            {
                throw new Error('Unexpected '+tokens[i+1][0]+' at '+tokens[i+1][1]+' (operator expected)');
            }
            if (!/^[\w"(]/.exec(tokens[i+2][0])) // "
            {
                throw new Error('Unexpected '+tokens[i+2][0]+' at '+tokens[i+2][1]+' (id, round brace, number or node ID expected)');
            }
            let rule = [ tokens[i][0], tokens[i+1][0], tokens[i+2][0] ];
            i += 3;
            if (rule[2][0] == '"')
            {
                rule[2] = { id: rule[2].substr(1, rule[2].length-2) };
            }
            else if (rule[2] === '(')
            {
                rule[2] = [];
                // eslint-disable-next-line no-constant-condition
                while (true)
                {
                    if (i > tokens.length-1)
                    {
                        throw new Error('Unexpected EOF (expected list and a closing round brace)');
                    }
                    if (tokens[i][0] === ',')
                    {
                        i++;
                    }
                    else if (tokens[i][0] === ')')
                    {
                        i++;
                        break;
                    }
                    else if (tokens[i][0][0] === '"')
                    {
                        rule[2].push({ id: tokens[i][0].substr(1, tokens[i][0].length-2) });
                        i++;
                    }
                    else if (/^\d+$/.exec(tokens[i][0]))
                    {
                        const n = 0|tokens[i][0];
                        if (!n)
                        {
                            throw new Error('Level reference cannot be 0 (refs count from 1) at '+tokens[i][1]);
                        }
                        else if (n > positions.length)
                        {
                            throw new Error('Forward references are forbidden at '+tokens[i][1]);
                        }
                        rule[2].push(n);
                        i++;
                    }
                    else if (!/^\w/.exec(tokens[i][0]))
                    {
                        throw new Error('Unexpected '+tokens[i][0]+' at '+tokens[i][1]+' (number or node ID expected)');
                    }
                    else
                    {
                        rule[2].push({ id: tokens[i][0] });
                        i++;
                    }
                }
            }
            else if (!/^\d+$/.exec(rule[2]))
            {
                rule[2] = { id: rule[2] };
            }
            else
            {
                rule[2] = 0|rule[2];
                if (!rule[2])
                {
                    throw new Error('Level reference cannot be 0 (refs count from 1) at '+tokens[i-1][1]);
                }
                else if (rule[2] > positions.length)
                {
                    throw new Error('Forward references are forbidden at '+tokens[i-1][1]);
                }
            }
            rules.push(rule);
        }
    }
    return positions;
 }
 // osd_tree = index_tree() output
 // levels = { string: number }
 // rules = [ level, operator, value ][][]
 //   level = string
 //   operator = '=' | '!=' | '>' | '?='
 //   value = number|number[] | { id: string|string[] }
 // examples:
 // 1) simple 3 replicas with failure_domain=host:
 //    [ [], [ [ 'host', '!=', 1 ] ], [ [ 'host', '!=', [ 1, 2 ] ] ] ]
 //    in DSL form: any, host!=1, host!=(1,2)
 // 2) EC 4+2 in 3 DC:
 //    [ [], [ [ 'dc', '=', 1 ], [ 'host', '!=', 1 ] ],
 //      [ 'dc', '!=', 1 ], [ [ 'dc', '=', 3 ], [ 'host', '!=', 3 ] ],
 //      [ 'dc', '!=', [ 1, 3 ] ], [ [ 'dc', '=', 5 ], [ 'host', '!=', 5 ] ] ]
 //    in DSL form: any, dc=1 host!=1, dc!=1, dc=3 host!=3, dc!=(1,3), dc=5 host!=5
 // 3) 1 replica in fixed DC + 2 in random DCs:
 //    [ [ [ 'dc', '=', { id: 'meow' } ] ], [ [ 'dc', '!=', 1 ] ], [ [ 'dc', '!=', [ 1, 2 ] ] ] ]
 //    in DSL form: dc=meow, dc!=1, dc!=(1,2)
 // 4) 2 replicas in each DC (almost the same as (2)):
 //    DSL: any, dc=1 host!=1, dc!=1, dc=3 host!=3
 // Alternative simpler way to specify rules would be: [ DC: 112233 HOST: 123456 ]
 function random_custom_combinations(osd_tree, rules, count, ordered)
 {
    const r = {};
    const first = filter_tree_by_rules(osd_tree, rules[0], []);
    let max_size = 0;
    // All combinations for the first item (usually "any") to try to include each OSD at least once
    for (const f of first)
    {
        const selected = [ f ];
        for (let i = 1; i < rules.length; i++)
        {
            const filtered = filter_tree_by_rules(osd_tree, rules[i], selected);
            const idx = select_murmur3(filtered.length, i => 'p:'+f.id+':'+filtered[i].id);
            selected.push(idx == null ? { levels: {}, id: null } : filtered[idx]);
        }
        const size = selected.filter(s => s.id !== null).length;
        max_size = max_size < size ? size : max_size;
        const pg = selected.map(s => s.id === null ? NO_OSD : (0|s.id));
        if (!ordered)
            pg.sort();
        r['pg_'+pg.join('_')] = pg;
    }
    // Pseudo-random selection
    for (let n = 0; n < count; n++)
    {
        const selected = [];
        for (const item_rules of rules)
        {
            const filtered = selected.length ? filter_tree_by_rules(osd_tree, item_rules, selected) : first;
            const idx = select_murmur3(filtered.length, i => n+':'+filtered[i].id);
            selected.push(idx == null ? { levels: {}, id: null } : filtered[idx]);
        }
        const size = selected.filter(s => s.id !== null).length;
        max_size = max_size < size ? size : max_size;
        const pg = selected.map(s => s.id === null ? NO_OSD : (0|s.id));
        if (!ordered)
            pg.sort();
        r['pg_'+pg.join('_')] = pg;
    }
    // Exclude PGs with less successful selections than maximum
    for (const k in r)
    {
        if (r[k].filter(s => s !== NO_OSD).length < max_size)
        {
            delete r[k];
        }
    }
    return r;
 }
 function filter_tree_by_rules(osd_tree, rules, selected)
 {
    let cur = osd_tree[''].children;
    for (const rule of rules)
    {
        const val = (rule[2] instanceof Array ? rule[2] : [ rule[2] ])
            .map(v => v instanceof Object ? v.id : selected[v-1].levels[rule[0]]);
        let preferred = [], other = [];
        for (let i = 0; i < cur.length; i++)
        {
            const item = cur[i];
            const level_id = item.levels[rule[0]];
            if (level_id)
            {
                if (rule[1] == '>' && val.filter(v => level_id <= v).length == 0 ||
                    (rule[1] == '=' || rule[1] == '?=') && val.filter(v => level_id != v).length == 0 ||
                    rule[1] == '!=' && val.filter(v => level_id == v).length == 0)
                {
                    // Include
                    preferred.push(item);
                }
                else if (rule[1] == '?=' && val.filter(v => level_id != v).length > 0)
                {
                    // Non-preferred
                    other.push(item);
                }
            }
            else if (item.children)
            {
                // Descend
                cur.splice(i+1, 0, ...item.children);
            }
        }
        cur = preferred.length ? preferred : other;
    }
    // Get leaf items
    for (let i = 0; i < cur.length; i++)
    {
        if (cur[i].children)
        {
            // Descend
            cur.splice(i, 1, ...cur[i].children);
            i--;
        }
    }
    return cur;
 }
 // Convert from
 // node_list = { id: string|number, level: string, size?: number, parent?: string|number }[]
 // to
 // node_tree = { [node_id]: { id, level, size?, parent?, children?: child_node_id[], levels: { [level]: id, ... } } }
 function index_tree(node_list)
 {
    const tree = { '': { children: [], levels: {} } };
    for (const node of node_list)
    {
        tree[node.id] = { ...node, levels: {} };
        delete tree[node.id].children;
    }
    for (const node of node_list)
    {
        const parent_id = node.parent && tree[node.parent] ? node.parent : '';
        tree[parent_id].children = tree[parent_id].children || [];
        tree[parent_id].children.push(tree[node.id]);
    }
    const cur = tree[''].children;
    for (let i = 0; i < cur.length; i++)
    {
        cur[i].levels[cur[i].level] = cur[i].id;
        if (cur[i].children)
        {
            for (const child of cur[i].children)
            {
                child.levels = { ...cur[i].levels, ...child.levels };
            }
            cur.splice(i, 1, ...cur[i].children);
            i--;
        }
    }
    return tree;
 }
 // selection = id[]
 // osd_tree = index_tree output
 // rules = parse_pg_dsl output
 function check_custom_combinations(osd_tree, rules, pgs)
 {
    const res = [];
    skip_pg: for (const pg of pgs)
    {
        let selected = pg.map(id => osd_tree[id] || null);
        for (let i = 0; i < rules.length; i++)
        {
            const filtered = filter_tree_by_rules(osd_tree, rules[i], selected);
            if (selected[i] === null && filtered.length ||
                !filtered.filter(ok => selected[i].id === ok.id).length)
            {
                continue skip_pg;
            }
        }
        res.push(pg);
    }
    return res;
 }
 module.exports = {
    RuleCombinator,
    NO_OSD,
    index_tree,
    parse_level_indexes,
    parse_pg_dsl,
    random_custom_combinations,
    check_custom_combinations,
 };
--- a/mon/lp_optimizer/murmur3.js
+++ b/mon/lp_optimizer/murmur3.js
@ -1,38 +0,0 @@
 function select_murmur3(count, cb)
 {
    if (!count)
    {
        return null;
    }
    else
    {
        let i = 0, maxh = -1;
        for (let j = 0; j < count; j++)
        {
            const h = murmur3(cb(j));
            if (h > maxh)
            {
                i = j;
                maxh = h;
            }
        }
        return i;
    }
 }
 function murmur3(s)
 {
    let hash = 0x12345678;
    for (let i = 0; i < s.length; i++)
    {
        hash ^= s.charCodeAt(i);
        hash = (hash*0x5bd1e995) & 0xFFFFFFFF;
        hash ^= (hash >> 15);
    }
    return hash;
 }
 module.exports = {
    murmur3,
    select_murmur3,
 };
--- a/mon/lp_optimizer/simple_pgs.js
+++ b/mon/lp_optimizer/simple_pgs.js
@ -1,241 +0,0 @@
 const { select_murmur3 } = require('./murmur3.js');
 const NO_OSD = 'Z';
 class SimpleCombinator
 {
    constructor(flat_tree, pg_size, max_combinations, ordered)
    {
        this.osd_tree = flat_tree;
        this.pg_size = pg_size;
        this.max_combinations = max_combinations;
        this.ordered = ordered;
    }
    random_combinations()
    {
        return random_combinations(this.osd_tree, this.pg_size, this.max_combinations, this.ordered);
    }
    check_combinations(pgs)
    {
        return check_combinations(this.osd_tree, pgs);
    }
 }
 // Convert multi-level osd_tree = { level: number|string, id?: string, size?: number, children?: osd_tree }[]
 // levels = { string: number }
 // to a two-level osd_tree suitable for all_combinations()
 function flatten_tree(osd_tree, levels, failure_domain_level, osd_level, domains = {}, i = { i: 1 })
 {
    osd_level = levels[osd_level] || osd_level;
    failure_domain_level = levels[failure_domain_level] || failure_domain_level;
    for (const node of osd_tree)
    {
        if ((levels[node.level] || node.level) < failure_domain_level)
        {
            flatten_tree(node.children||[], levels, failure_domain_level, osd_level, domains, i);
        }
        else
        {
            domains['dom'+(i.i++)] = extract_osds([ node ], levels, osd_level);
        }
    }
    return domains;
 }
 function extract_osds(osd_tree, levels, osd_level, osds = {})
 {
    for (const node of osd_tree)
    {
        if ((levels[node.level] || node.level) >= osd_level)
        {
            osds[node.id] = node.size;
        }
        else
        {
            extract_osds(node.children||[], levels, osd_level, osds);
        }
    }
    return osds;
 }
 // ordered = don't treat (x,y) and (y,x) as equal
 function random_combinations(osd_tree, pg_size, count, ordered)
 {
    const osds = Object.keys(osd_tree).reduce((a, c) => { a[c] = Object.keys(osd_tree[c]).sort(); return a; }, {});
    const hosts = Object.keys(osd_tree).sort().filter(h => osds[h].length > 0);
    const r = {};
    // Generate random combinations including each OSD at least once
    for (let h = 0; h < hosts.length; h++)
    {
        for (let o = 0; o < osds[hosts[h]].length; o++)
        {
            const pg = [ osds[hosts[h]][o] ];
            const cur_hosts = [ ...hosts ];
            cur_hosts.splice(h, 1);
            for (let i = 1; i < pg_size && i < hosts.length; i++)
            {
                const next_host = select_murmur3(cur_hosts.length, i => pg[0]+':i:'+cur_hosts[i]);
                const next_osd = select_murmur3(osds[cur_hosts[next_host]].length, i => pg[0]+':i:'+osds[cur_hosts[next_host]][i]);
                pg.push(osds[cur_hosts[next_host]][next_osd]);
                cur_hosts.splice(next_host, 1);
            }
            while (pg.length < pg_size)
            {
                pg.push(NO_OSD);
            }
            r['pg_'+pg.join('_')] = pg;
        }
    }
    // Generate purely random combinations
    while (count > 0)
    {
        let host_idx = [];
        const cur_hosts = [ ...hosts.map((h, i) => i) ];
        const max_hosts = pg_size < hosts.length ? pg_size : hosts.length;
        if (ordered)
        {
            for (let i = 0; i < max_hosts; i++)
            {
                const r = select_murmur3(cur_hosts.length, i => count+':h:'+cur_hosts[i]);
                host_idx[i] = cur_hosts[r];
                cur_hosts.splice(r, 1);
            }
        }
        else
        {
            for (let i = 0; i < max_hosts; i++)
            {
                const r = select_murmur3(cur_hosts.length - (max_hosts - i - 1), i => count+':h:'+cur_hosts[i]);
                host_idx[i] = cur_hosts[r];
                cur_hosts.splice(0, r+1);
            }
        }
        let pg = host_idx.map(h => osds[hosts[h]][select_murmur3(osds[hosts[h]].length, i => count+':o:'+osds[hosts[h]][i])]);
        while (pg.length < pg_size)
        {
            pg.push(NO_OSD);
        }
        r['pg_'+pg.join('_')] = pg;
        count--;
    }
    return r;
 }
 // Super-stupid algorithm. Given the current OSD tree, generate all possible OSD combinations
 // osd_tree = { failure_domain1: { osd1: size1, ... }, ... }
 // ordered = return combinations without duplicates having different order
 function all_combinations(osd_tree, pg_size, ordered, count)
 {
    const hosts = Object.keys(osd_tree).sort();
    const osds = Object.keys(osd_tree).reduce((a, c) => { a[c] = Object.keys(osd_tree[c]).sort(); return a; }, {});
    while (hosts.length < pg_size)
    {
        osds[NO_OSD] = [ NO_OSD ];
        hosts.push(NO_OSD);
    }
    let host_idx = [];
    let osd_idx = [];
    for (let i = 0; i < pg_size; i++)
    {
        host_idx.push(i);
        osd_idx.push(0);
    }
    const r = [];
    while (!count || count < 0 || r.length < count)
    {
        r.push(host_idx.map((hi, i) => osds[hosts[hi]][osd_idx[i]]));
        let inc = pg_size-1;
        while (inc >= 0)
        {
            osd_idx[inc]++;
            if (osd_idx[inc] >= osds[hosts[host_idx[inc]]].length)
            {
                osd_idx[inc] = 0;
                inc--;
            }
            else
            {
                break;
            }
        }
        if (inc < 0)
        {
            // no osds left in the current host combination, select the next one
            inc = pg_size-1;
            same_again: while (inc >= 0)
            {
                host_idx[inc]++;
                for (let prev_host = 0; prev_host < inc; prev_host++)
                {
                    if (host_idx[prev_host] == host_idx[inc])
                    {
                        continue same_again;
                    }
                }
                if (host_idx[inc] < (ordered ? hosts.length-(pg_size-1-inc) : hosts.length))
                {
                    while ((++inc) < pg_size)
                    {
                        host_idx[inc] = (ordered ? host_idx[inc-1]+1 : 0);
                    }
                    break;
                }
                else
                {
                    inc--;
                }
            }
            if (inc < 0)
            {
                break;
            }
        }
    }
    return r;
 }
 function check_combinations(osd_tree, pgs)
 {
    const host_per_osd = {};
    for (const host in osd_tree)
    {
        for (const osd in osd_tree[host])
        {
            host_per_osd[osd] = host;
        }
    }
    const res = [];
    skip_pg: for (const pg of pgs)
    {
        const seen_hosts = {};
        for (const osd of pg)
        {
            if (!host_per_osd[osd] || seen_hosts[host_per_osd[osd]])
            {
                continue skip_pg;
            }
            seen_hosts[host_per_osd[osd]] = true;
        }
        res.push(pg);
    }
    return res;
 }
 function compat(params)
 {
    return {
        ...params,
        osd_weights: Object.assign({}, ...Object.values(params.osd_tree)),
        combinator: new SimpleCombinator(params.osd_tree, params.pg_size, params.max_combinations||10000),
    };
 }
 module.exports = {
    flatten_tree,
    all_combinations,
    SimpleCombinator,
    compat,
    NO_OSD,
 };
--- a/mon/lp_optimizer/test-parse-dsl.js
+++ b/mon/lp_optimizer/test-parse-dsl.js
@ -1,118 +0,0 @@
 const { random_custom_combinations, index_tree, parse_level_indexes, parse_pg_dsl } = require('./dsl_pgs.js');
 function check(result, expected)
 {
    console.dir(result, { depth: null });
    if (JSON.stringify(result) !== JSON.stringify(expected))
    {
        process.stderr.write('Unexpected value, expected: ');
        console.dir(expected, { depth: null });
        process.exit(1);
    }
 }
 check(
    parse_pg_dsl("any, dc=1 host!=1, dc!=1, dc=3 host!=3, dc!=(1,3), dc=5 host!=5"),
    [
        [],
        [ [ 'dc', '=', 1 ], [ 'host', '!=', 1 ] ],
        [ [ 'dc', '!=', 1 ] ],
        [ [ 'dc', '=', 3 ], [ 'host', '!=', 3 ] ],
        [ [ 'dc', '!=', [ 1, 3 ] ] ],
        [ [ 'dc', '=', 5 ], [ 'host', '!=', 5 ] ],
    ]
 );
 check(
    parse_pg_dsl("dc=meow, dc!=1, dc>2"),
    [
        [ [ 'dc', '=', { id: 'meow' } ] ],
        [ [ 'dc', '!=', 1 ] ],
        [ [ 'dc', '>', 2 ] ],
    ]
 );
 check(
    parse_level_indexes({ dc: '112233', host: 'ABCDEF' }),
    [
        [],
        [ [ 'dc', '=', 1 ],         [ 'host', '!=', [ 1 ] ] ],
        [ [ 'dc', '!=', [ 1 ] ],    [ 'host', '!=', [ 1, 2 ] ] ],
        [ [ 'dc', '=', 3 ],         [ 'host', '!=', [ 1, 2, 3 ] ] ],
        [ [ 'dc', '!=', [ 1, 3 ] ], [ 'host', '!=', [ 1, 2, 3, 4 ] ] ],
        [ [ 'dc', '=', 5 ],         [ 'host', '!=', [ 1, 2, 3, 4, 5 ] ] ],
    ]
 );
 check(
    parse_level_indexes({ dc: '112233', host: 'ABCDEF' }, [ 'dc', 'host' ]),
    [
        [],
        [ [ 'dc', '=', 1 ],         [ 'host', '!=', [ 1 ] ] ],
        [ [ 'dc', '!=', [ 1 ] ] ],
        [ [ 'dc', '=', 3 ],         [ 'host', '!=', [ 3 ] ] ],
        [ [ 'dc', '!=', [ 1, 3 ] ] ],
        [ [ 'dc', '=', 5 ],         [ 'host', '!=', [ 5 ] ] ],
    ]
 );
 check(
    parse_level_indexes({ dc: '112211223333', host: '123456789ABC' }),
    [
        [],
        [ [ 'dc', '=', 1 ],         [ 'host', '!=', [ 1 ] ] ],
        [ [ 'dc', '!=', [ 1 ] ],    [ 'host', '!=', [ 1, 2 ] ] ],
        [ [ 'dc', '=', 3 ],         [ 'host', '!=', [ 1, 2, 3 ] ] ],
        [ [ 'dc', '=', 1 ],         [ 'host', '!=', [ 1, 2, 3, 4 ] ] ],
        [ [ 'dc', '=', 1 ],         [ 'host', '!=', [ 1, 2, 3, 4, 5 ] ] ],
        [ [ 'dc', '=', 3 ],         [ 'host', '!=', [ 1, 2, 3, 4, 5, 6 ] ] ],
        [ [ 'dc', '=', 3 ],         [ 'host', '!=', [ 1, 2, 3, 4, 5, 6, 7 ] ] ],
        [ [ 'dc', '!=', [ 1, 3 ] ], [ 'host', '!=', [ 1, 2, 3, 4, 5, 6, 7, 8 ] ] ],
        [ [ 'dc', '=', 9 ],         [ 'host', '!=', [ 1, 2, 3, 4, 5, 6, 7, 8, 9 ] ] ],
        [ [ 'dc', '=', 9 ],         [ 'host', '!=', [ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 ] ] ],
        [ [ 'dc', '=', 9 ],         [ 'host', '!=', [ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 ] ] ],
    ]
 );
 check(
    parse_level_indexes({ dc: '112211223333', host: '123456789ABC' }, [ 'dc', 'host' ]),
    [
        [],
        [ [ 'dc', '=', 1 ], [ 'host', '!=', [ 1 ] ] ],
        [ [ 'dc', '!=', [ 1 ] ] ],
        [ [ 'dc', '=', 3 ], [ 'host', '!=', [ 3 ] ] ],
        [ [ 'dc', '=', 1 ], [ 'host', '!=', [ 1, 2 ] ] ],
        [ [ 'dc', '=', 1 ], [ 'host', '!=', [ 1, 2, 5 ] ] ],
        [ [ 'dc', '=', 3 ], [ 'host', '!=', [ 3, 4 ] ] ],
        [ [ 'dc', '=', 3 ], [ 'host', '!=', [ 3, 4, 7 ] ] ],
        [ [ 'dc', '!=', [ 1, 3 ] ] ],
        [ [ 'dc', '=', 9 ], [ 'host', '!=', [ 9 ] ] ],
        [ [ 'dc', '=', 9 ], [ 'host', '!=', [ 9, 10 ] ] ],
        [ [ 'dc', '=', 9 ], [ 'host', '!=', [ 9, 10, 11 ] ] ]
    ]
 );
 check(
    Object.keys(random_custom_combinations(index_tree([
        { id: '1', size: 1, level: 'osd' },
        { id: '2', size: 2, level: 'osd' },
        { id: '3', size: 3, level: 'osd' }
    ]), parse_level_indexes({ osd: '12' }), 10000)).sort(),
    [ 'pg_1_2', 'pg_1_3', 'pg_2_3' ]
 );
 check(
    Object.keys(random_custom_combinations(index_tree([
        { id: 'h1', level: 'host' },
        { id: 'h2', level: 'host' },
        { id: 'h3', level: 'host' },
        { id: '1', size: 1, level: 'osd', parent: 'h1' },
        { id: '2', size: 1, level: 'osd', parent: 'h2' },
        { id: '3', size: 1, level: 'osd', parent: 'h2' },
        { id: '4', size: 1, level: 'osd', parent: 'h3' },
        { id: '5', size: 1, level: 'osd', parent: 'h3' },
    ]), parse_level_indexes({ host: '1122', osd: '1234' }), 10000)).sort(),
    [ 'pg_2_3_4_5' ]
 );
 console.log('OK');
--- a/mon/scripts/make-etcd
+++ b/mon/scripts/make-etcd
--- a/mon/mon-main.js
+++ b/mon/mon-main.js
@ -23,4 +23,4 @@ for (let i = 2; i < process.argv.length; i++)
    }
 }
-Mon.run_forever(options);
+new Mon(options).start().catch(e => { console.error(e); process.exit(1); });
--- a/mon/mon.js
+++ b/mon/mon.js
--- a/mon/osd_tree.js
+++ b/mon/osd_tree.js
@ -1,215 +0,0 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 (see README.md for details)
 function get_osd_tree(global_config, state)
 {
    const levels = global_config.placement_levels||{};
    levels.host = levels.host || 100;
    levels.osd = levels.osd || 101;
    const tree = {};
    let up_osds = {};
    // This requires monitor system time to be in sync with OSD system times (at least to some extent)
    const down_time = Date.now()/1000 - global_config.osd_out_time;
    for (const osd_num of Object.keys(state.osd.stats).sort((a, b) => a - b))
    {
        const stat = state.osd.stats[osd_num];
        const osd_cfg = state.config.osd[osd_num];
        let reweight = osd_cfg == null ? 1 : Number(osd_cfg.reweight);
        if (reweight < 0 || isNaN(reweight))
            reweight = 1;
        if (stat && stat.size && reweight && (state.osd.state[osd_num] || Number(stat.time) >= down_time ||
            osd_cfg && osd_cfg.noout))
        {
            // Numeric IDs are reserved for OSDs
            if (state.osd.state[osd_num] && reweight > 0)
            {
                // React to down OSDs immediately
                up_osds[osd_num] = true;
            }
            tree[osd_num] = tree[osd_num] || {};
            tree[osd_num].id = osd_num;
            tree[osd_num].parent = tree[osd_num].parent || stat.host;
            tree[osd_num].level = 'osd';
            tree[osd_num].size = reweight * stat.size / 1024 / 1024 / 1024 / 1024; // terabytes
            if (osd_cfg && osd_cfg.tags)
            {
                tree[osd_num].tags = (osd_cfg.tags instanceof Array ? [ ...osd_cfg.tags ] : [ osd_cfg.tags ])
                    .reduce((a, c) => { a[c] = true; return a; }, {});
            }
            delete tree[osd_num].children;
            if (!tree[stat.host])
            {
                tree[stat.host] = {
                    id: stat.host,
                    level: 'host',
                    parent: null,
                    children: [],
                };
            }
        }
    }
    for (const node_id in state.config.node_placement||{})
    {
        const node_cfg = state.config.node_placement[node_id];
        if (/^\d+$/.exec(node_id))
        {
            node_cfg.level = 'osd';
        }
        if (!node_id || !node_cfg.level || !levels[node_cfg.level] ||
            node_cfg.level === 'osd' && !tree[node_id])
        {
            // All nodes must have non-empty IDs and valid levels
            // OSDs have to actually exist
            continue;
        }
        tree[node_id] = tree[node_id] || {};
        tree[node_id].id = node_id;
        tree[node_id].level = node_cfg.level;
        tree[node_id].parent = node_cfg.parent;
        if (node_cfg.level !== 'osd')
        {
            tree[node_id].children = [];
        }
    }
    return { up_osds, levels, osd_tree: tree };
 }
 function make_hier_tree(global_config, tree)
 {
    const levels = global_config.placement_levels||{};
    levels.host = levels.host || 100;
    levels.osd = levels.osd || 101;
    tree = { ...tree };
    for (const node_id in tree)
    {
        tree[node_id] = { ...tree[node_id], children: [] };
    }
    tree[''] = { children: [] };
    for (const node_id in tree)
    {
        if (node_id === '' || tree[node_id].level === 'osd' && (!tree[node_id].size || tree[node_id].size <= 0))
        {
            continue;
        }
        const node_cfg = tree[node_id];
        const node_level = levels[node_cfg.level] || node_cfg.level;
        let parent_level = node_cfg.parent && tree[node_cfg.parent] && tree[node_cfg.parent].children
            && tree[node_cfg.parent].level;
        parent_level = parent_level ? (levels[parent_level] || parent_level) : null;
        // Parent's level must be less than child's; OSDs must be leaves
        const parent = parent_level && parent_level < node_level ? node_cfg.parent : '';
        tree[parent].children.push(tree[node_id]);
    }
    // Delete empty nodes
    let deleted = 0;
    do
    {
        deleted = 0;
        for (const node_id in tree)
        {
            if (tree[node_id].level !== 'osd' && (!tree[node_id].children || !tree[node_id].children.length))
            {
                const parent = tree[node_id].parent;
                if (parent)
                {
                    tree[parent].children = tree[parent].children.filter(c => c != tree[node_id]);
                }
                deleted++;
                delete tree[node_id];
            }
        }
    } while (deleted > 0);
    return tree;
 }
 function filter_osds_by_root_node(global_config, pool_tree, root_node)
 {
    if (!root_node)
    {
        return;
    }
    let hier_tree = make_hier_tree(global_config, pool_tree);
    let included = [ ...(hier_tree[root_node] || {}).children||[] ];
    for (let i = 0; i < included.length; i++)
    {
        if (included[i].children)
        {
            included.splice(i+1, 0, ...included[i].children);
        }
    }
    let cur = pool_tree[root_node] || {};
    while (cur && cur.id)
    {
        included.unshift(cur);
        cur = pool_tree[cur.parent||''];
    }
    included = included.reduce((a, c) => { a[c.id||''] = true; return a; }, {});
    for (const item in pool_tree)
    {
        if (!included[item])
        {
            delete pool_tree[item];
        }
    }
 }
 function filter_osds_by_tags(orig_tree, tags)
 {
    if (!tags)
    {
        return;
    }
    for (const tag of (tags instanceof Array ? tags : [ tags ]))
    {
        for (const osd in orig_tree)
        {
            if (orig_tree[osd].level === 'osd' &&
                (!orig_tree[osd].tags || !orig_tree[osd].tags[tag]))
            {
                delete orig_tree[osd];
            }
        }
    }
 }
 function filter_osds_by_block_layout(orig_tree, osd_stats, block_size, bitmap_granularity, immediate_commit)
 {
    for (const osd in orig_tree)
    {
        if (orig_tree[osd].level === 'osd')
        {
            const osd_stat = osd_stats[osd];
            if (osd_stat && (osd_stat.bs_block_size && osd_stat.bs_block_size != block_size ||
                osd_stat.bitmap_granularity && osd_stat.bitmap_granularity != bitmap_granularity ||
                osd_stat.immediate_commit == 'small' && immediate_commit == 'all' ||
                osd_stat.immediate_commit == 'none' && immediate_commit != 'none'))
            {
                delete orig_tree[osd];
            }
        }
    }
 }
 function get_affinity_osds(pool_cfg, up_osds, osd_tree)
 {
    let aff_osds = up_osds;
    if (pool_cfg.primary_affinity_tags)
    {
        aff_osds = Object.keys(up_osds).reduce((a, c) => { a[c] = osd_tree[c]; return a; }, {});
        filter_osds_by_tags(aff_osds, pool_cfg.primary_affinity_tags);
        for (const osd in aff_osds)
        {
            aff_osds[osd] = true;
        }
    }
    return aff_osds;
 }
 module.exports = {
    get_osd_tree,
    make_hier_tree,
    filter_osds_by_root_node,
    filter_osds_by_tags,
    filter_osds_by_block_layout,
    get_affinity_osds,
 };
--- a/mon/package.json
+++ b/mon/package.json
@ -1,23 +1,15 @@
 {
  "name": "vitastor-mon",
-  "version": "1.6.1",
+  "version": "1.4.6",
  "description": "Vitastor SDS monitor service",
  "main": "mon-main.js",
  "scripts": {
-    "lint": "eslint *.js lp_optimizer/*.js scripts/*.js"
+    "test": "echo \"Error: no test specified\" && exit 1"
  },
  "author": "Vitaliy Filippov",
  "license": "UNLICENSED",
  "dependencies": {
    "sprintf-js": "^1.1.2",
    "ws": "^7.2.5"
  },
  "devDependencies": {
    "eslint": "^8.0.0",
    "eslint-plugin-import": "^2.29.1",
    "eslint-plugin-node": "^11.1.0"
  },
  "engines": {
    "node": ">=12.0.0"
  }
 }
--- a/mon/pg_gen.js
+++ b/mon/pg_gen.js
@ -1,267 +0,0 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 (see README.md for details)
 const { RuleCombinator } = require('./lp_optimizer/dsl_pgs.js');
 const { SimpleCombinator, flatten_tree } = require('./lp_optimizer/simple_pgs.js');
 const { validate_pool_cfg, get_pg_rules } = require('./pool_config.js');
 const LPOptimizer = require('./lp_optimizer/lp_optimizer.js');
 const { scale_pg_count } = require('./pg_utils.js');
 const { make_hier_tree, filter_osds_by_root_node,
    filter_osds_by_tags, filter_osds_by_block_layout, get_affinity_osds } = require('./osd_tree.js');
 let seed;
 function reset_rng()
 {
    seed = 0x5f020e43;
 }
 function rng()
 {
    seed ^= seed << 13;
    seed ^= seed >> 17;
    seed ^= seed << 5;
    return seed + 2147483648;
 }
 function pick_primary(pool_config, osd_set, up_osds, aff_osds)
 {
    let alive_set;
    if (pool_config.scheme === 'replicated')
    {
        // Prefer "affinity" OSDs
        alive_set = osd_set.filter(osd_num => osd_num && aff_osds[osd_num]);
        if (!alive_set.length)
            alive_set = osd_set.filter(osd_num => osd_num && up_osds[osd_num]);
    }
    else
    {
        // Prefer data OSDs for EC because they can actually read something without an additional network hop
        const pg_data_size = (pool_config.pg_size||0) - (pool_config.parity_chunks||0);
        alive_set = osd_set.slice(0, pg_data_size).filter(osd_num => osd_num && aff_osds[osd_num]);
        if (!alive_set.length)
            alive_set = osd_set.filter(osd_num => osd_num && aff_osds[osd_num]);
        if (!alive_set.length)
        {
            alive_set = osd_set.slice(0, pg_data_size).filter(osd_num => osd_num && up_osds[osd_num]);
            if (!alive_set.length)
                alive_set = osd_set.filter(osd_num => osd_num && up_osds[osd_num]);
        }
    }
    if (!alive_set.length)
    {
        return 0;
    }
    return alive_set[rng() % alive_set.length];
 }
 function recheck_primary(state, global_config, up_osds, osd_tree)
 {
    let new_config_pgs;
    for (const pool_id in state.config.pools)
    {
        const pool_cfg = state.config.pools[pool_id];
        if (!validate_pool_cfg(pool_id, pool_cfg, global_config.placement_levels, false))
        {
            continue;
        }
        const aff_osds = get_affinity_osds(pool_cfg, up_osds, osd_tree);
        reset_rng();
        for (let pg_num = 1; pg_num <= pool_cfg.pg_count; pg_num++)
        {
            if (!state.config.pgs.items[pool_id])
            {
                continue;
            }
            const pg_cfg = state.config.pgs.items[pool_id][pg_num];
            if (pg_cfg)
            {
                const new_primary = pick_primary(state.config.pools[pool_id], pg_cfg.osd_set, up_osds, aff_osds);
                if (pg_cfg.primary != new_primary)
                {
                    if (!new_config_pgs)
                    {
                        new_config_pgs = JSON.parse(JSON.stringify(state.config.pgs));
                    }
                    console.log(
                        `Moving pool ${pool_id} (${pool_cfg.name || 'unnamed'}) PG ${pg_num}`+
                        ` primary OSD from ${pg_cfg.primary} to ${new_primary}`
                    );
                    new_config_pgs.items[pool_id][pg_num].primary = new_primary;
                }
            }
        }
    }
    return new_config_pgs;
 }
 function save_new_pgs_txn(save_to, request, state, etcd_prefix, etcd_watch_revision, pool_id, up_osds, osd_tree, prev_pgs, new_pgs, pg_history)
 {
    const aff_osds = get_affinity_osds(state.config.pools[pool_id] || {}, up_osds, osd_tree);
    const pg_items = {};
    reset_rng();
    new_pgs.map((osd_set, i) =>
    {
        osd_set = osd_set.map(osd_num => osd_num === LPOptimizer.NO_OSD ? 0 : osd_num);
        pg_items[i+1] = {
            osd_set,
            primary: pick_primary(state.config.pools[pool_id], osd_set, up_osds, aff_osds),
        };
        if (prev_pgs[i] && prev_pgs[i].join(' ') != osd_set.join(' ') &&
            prev_pgs[i].filter(osd_num => osd_num).length > 0)
        {
            pg_history[i] = pg_history[i] || {};
            pg_history[i].osd_sets = pg_history[i].osd_sets || [];
            pg_history[i].osd_sets.push(prev_pgs[i]);
        }
        if (pg_history[i] && pg_history[i].osd_sets)
        {
            pg_history[i].osd_sets = Object.values(pg_history[i].osd_sets
                .reduce((a, c) => { a[c.join(' ')] = c; return a; }, {}));
        }
    });
    for (let i = 0; i < new_pgs.length || i < prev_pgs.length; i++)
    {
        // FIXME: etcd has max_txn_ops limit, and it's 128 by default
        // Sooo we probably want to change our storage scheme for PG histories...
        request.compare.push({
            key: b64(etcd_prefix+'/pg/history/'+pool_id+'/'+(i+1)),
            target: 'MOD',
            mod_revision: ''+etcd_watch_revision,
            result: 'LESS',
        });
        if (pg_history[i])
        {
            request.success.push({
                requestPut: {
                    key: b64(etcd_prefix+'/pg/history/'+pool_id+'/'+(i+1)),
                    value: b64(JSON.stringify(pg_history[i])),
                },
            });
        }
        else
        {
            request.success.push({
                requestDeleteRange: {
                    key: b64(etcd_prefix+'/pg/history/'+pool_id+'/'+(i+1)),
                },
            });
        }
    }
    save_to.items = save_to.items || {};
    if (!new_pgs.length)
    {
        delete save_to.items[pool_id];
    }
    else
    {
        save_to.items[pool_id] = pg_items;
    }
 }
 async function generate_pool_pgs(state, global_config, pool_id, osd_tree, levels)
 {
    const pool_cfg = state.config.pools[pool_id];
    if (!validate_pool_cfg(pool_id, pool_cfg, global_config.placement_levels, false))
    {
        return null;
    }
    let pool_tree = { ...osd_tree };
    filter_osds_by_root_node(global_config, pool_tree, pool_cfg.root_node);
    filter_osds_by_tags(pool_tree, pool_cfg.osd_tags);
    filter_osds_by_block_layout(
        pool_tree,
        state.osd.stats,
        pool_cfg.block_size || global_config.block_size || 131072,
        pool_cfg.bitmap_granularity || global_config.bitmap_granularity || 4096,
        pool_cfg.immediate_commit || global_config.immediate_commit || 'none'
    );
    pool_tree = make_hier_tree(global_config, pool_tree);
    // First try last_clean_pgs to minimize data movement
    let prev_pgs = [];
    for (const pg in ((state.history.last_clean_pgs.items||{})[pool_id]||{}))
    {
        prev_pgs[pg-1] = [ ...state.history.last_clean_pgs.items[pool_id][pg].osd_set ];
    }
    if (!prev_pgs.length)
    {
        // Fall back to config/pgs if it's empty
        for (const pg in ((state.config.pgs.items||{})[pool_id]||{}))
        {
            prev_pgs[pg-1] = [ ...state.config.pgs.items[pool_id][pg].osd_set ];
        }
    }
    const old_pg_count = prev_pgs.length;
    const optimize_cfg = {
        osd_weights: Object.values(pool_tree).filter(item => item.level === 'osd').reduce((a, c) => { a[c.id] = c.size; return a; }, {}),
        combinator: !global_config.use_old_pg_combinator || pool_cfg.level_placement || pool_cfg.raw_placement
            // new algorithm:
            ? new RuleCombinator(pool_tree, get_pg_rules(pool_id, pool_cfg, global_config.placement_levels), pool_cfg.max_osd_combinations)
            // old algorithm:
            : new SimpleCombinator(flatten_tree(pool_tree[''].children, levels, pool_cfg.failure_domain, 'osd'), pool_cfg.pg_size, pool_cfg.max_osd_combinations),
        pg_count: pool_cfg.pg_count,
        pg_size: pool_cfg.pg_size,
        pg_minsize: pool_cfg.pg_minsize,
        ordered: pool_cfg.scheme != 'replicated',
    };
    let optimize_result;
    // Re-shuffle PGs if config/pgs.hash is empty
    if (old_pg_count > 0 && state.config.pgs.hash)
    {
        if (prev_pgs.length != pool_cfg.pg_count)
        {
            // Scale PG count
            // Do it even if old_pg_count is already equal to pool_cfg.pg_count,
            // because last_clean_pgs may still contain the old number of PGs
            scale_pg_count(prev_pgs, pool_cfg.pg_count);
        }
        for (const pg of prev_pgs)
        {
            while (pg.length < pool_cfg.pg_size)
            {
                pg.push(0);
            }
        }
        optimize_result = await LPOptimizer.optimize_change({
            prev_pgs,
            ...optimize_cfg,
        });
    }
    else
    {
        optimize_result = await LPOptimizer.optimize_initial(optimize_cfg);
    }
    console.log(`Pool ${pool_id} (${pool_cfg.name || 'unnamed'}):`);
    LPOptimizer.print_change_stats(optimize_result);
    let pg_effsize = pool_cfg.pg_size;
    for (const pg of optimize_result.int_pgs)
    {
        const this_pg_size = pg.filter(osd => osd != LPOptimizer.NO_OSD).length;
        if (this_pg_size && this_pg_size < pg_effsize)
        {
            pg_effsize = this_pg_size;
        }
    }
    return {
        pool_id,
        pgs: optimize_result.int_pgs,
        stats: {
            total_raw_tb: optimize_result.space,
            pg_real_size: pg_effsize || pool_cfg.pg_size,
            raw_to_usable: (pg_effsize || pool_cfg.pg_size) / (pool_cfg.scheme === 'replicated'
                ? 1 : (pool_cfg.pg_size - (pool_cfg.parity_chunks||0))),
            space_efficiency: optimize_result.space/(optimize_result.total_space||1),
        },
    };
 }
 function b64(str)
 {
    return Buffer.from(str).toString('base64');
 }
 module.exports = {
    recheck_primary,
    save_new_pgs_txn,
    generate_pool_pgs,
 };
--- a/mon/pool_config.js
+++ b/mon/pool_config.js
@ -1,169 +0,0 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 (see README.md for details)
 const { parse_level_indexes, parse_pg_dsl } = require('./lp_optimizer/dsl_pgs.js');
 function validate_pool_cfg(pool_id, pool_cfg, placement_levels, warn)
 {
    pool_cfg.pg_size = Math.floor(pool_cfg.pg_size);
    pool_cfg.pg_minsize = Math.floor(pool_cfg.pg_minsize);
    pool_cfg.parity_chunks = Math.floor(pool_cfg.parity_chunks) || undefined;
    pool_cfg.pg_count = Math.floor(pool_cfg.pg_count);
    pool_cfg.max_osd_combinations = Math.floor(pool_cfg.max_osd_combinations) || 10000;
    if (!/^[1-9]\d*$/.exec(''+pool_id))
    {
        if (warn)
            console.log('Pool ID '+pool_id+' is invalid');
        return false;
    }
    if (pool_cfg.scheme !== 'xor' && pool_cfg.scheme !== 'replicated' &&
        pool_cfg.scheme !== 'ec' && pool_cfg.scheme !== 'jerasure')
    {
        if (warn)
            console.log('Pool '+pool_id+' has invalid coding scheme (one of "xor", "replicated", "ec" and "jerasure" required)');
        return false;
    }
    if (!pool_cfg.pg_size || pool_cfg.pg_size < 1 || pool_cfg.pg_size > 256 ||
        pool_cfg.scheme !== 'replicated' && pool_cfg.pg_size < 3)
    {
        if (warn)
            console.log('Pool '+pool_id+' has invalid pg_size');
        return false;
    }
    if (!pool_cfg.pg_minsize || pool_cfg.pg_minsize < 1 || pool_cfg.pg_minsize > pool_cfg.pg_size ||
        pool_cfg.scheme === 'xor' && pool_cfg.pg_minsize < (pool_cfg.pg_size - 1))
    {
        if (warn)
            console.log('Pool '+pool_id+' has invalid pg_minsize');
        return false;
    }
    if (pool_cfg.scheme === 'xor' && pool_cfg.parity_chunks != 0 && pool_cfg.parity_chunks != 1)
    {
        if (warn)
            console.log('Pool '+pool_id+' has invalid parity_chunks (must be 1)');
        return false;
    }
    if ((pool_cfg.scheme === 'ec' || pool_cfg.scheme === 'jerasure') &&
        (pool_cfg.parity_chunks < 1 || pool_cfg.parity_chunks > pool_cfg.pg_size-2))
    {
        if (warn)
            console.log('Pool '+pool_id+' has invalid parity_chunks (must be between 1 and pg_size-2)');
        return false;
    }
    if (!pool_cfg.pg_count || pool_cfg.pg_count < 1)
    {
        if (warn)
            console.log('Pool '+pool_id+' has invalid pg_count');
        return false;
    }
    if (!pool_cfg.name)
    {
        if (warn)
            console.log('Pool '+pool_id+' has empty name');
        return false;
    }
    if (pool_cfg.max_osd_combinations < 100)
    {
        if (warn)
            console.log('Pool '+pool_id+' has invalid max_osd_combinations (must be at least 100)');
        return false;
    }
    if (pool_cfg.root_node && typeof(pool_cfg.root_node) != 'string')
    {
        if (warn)
            console.log('Pool '+pool_id+' has invalid root_node (must be a string)');
        return false;
    }
    if (pool_cfg.osd_tags && typeof(pool_cfg.osd_tags) != 'string' &&
        (!(pool_cfg.osd_tags instanceof Array) || pool_cfg.osd_tags.filter(t => typeof t != 'string').length > 0))
    {
        if (warn)
            console.log('Pool '+pool_id+' has invalid osd_tags (must be a string or array of strings)');
        return false;
    }
    if (pool_cfg.primary_affinity_tags && typeof(pool_cfg.primary_affinity_tags) != 'string' &&
        (!(pool_cfg.primary_affinity_tags instanceof Array) || pool_cfg.primary_affinity_tags.filter(t => typeof t != 'string').length > 0))
    {
        if (warn)
            console.log('Pool '+pool_id+' has invalid primary_affinity_tags (must be a string or array of strings)');
        return false;
    }
    if (!get_pg_rules(pool_id, pool_cfg, placement_levels, true))
    {
        return false;
    }
    return true;
 }
 function get_pg_rules(pool_id, pool_cfg, placement_levels, warn)
 {
    if (pool_cfg.level_placement)
    {
        const pg_size = (0|pool_cfg.pg_size);
        let rules = pool_cfg.level_placement;
        if (typeof rules === 'string')
        {
            rules = rules.split(/\s+/).map(s => s.split(/=/, 2)).reduce((a, c) => { a[c[0]] = c[1]; return a; }, {});
        }
        else
        {
            rules = { ...rules };
        }
        // Always add failure_domain to prevent rules from being totally incorrect
        const all_diff = [];
        for (let i = 1; i <= pg_size; i++)
        {
            all_diff.push(i);
        }
        rules[pool_cfg.failure_domain || 'host'] = all_diff;
        placement_levels = placement_levels||{};
        placement_levels.host = placement_levels.host || 100;
        placement_levels.osd = placement_levels.osd || 101;
        for (const k in rules)
        {
            if (!placement_levels[k] || typeof rules[k] !== 'string' &&
                (!(rules[k] instanceof Array) ||
                rules[k].filter(s => typeof s !== 'string' && typeof s !== 'number').length > 0))
            {
                if (warn)
                    console.log('Pool '+pool_id+' configuration is invalid: level_placement should be { [level]: string | (string|number)[] }');
                return null;
            }
            else if (rules[k].length != pg_size)
            {
                if (warn)
                    console.log('Pool '+pool_id+' configuration is invalid: values in level_placement should contain exactly pg_size ('+pg_size+') items');
                return null;
            }
        }
        return parse_level_indexes(rules);
    }
    else if (typeof pool_cfg.raw_placement === 'string')
    {
        try
        {
            return parse_pg_dsl(pool_cfg.raw_placement);
        }
        catch (e)
        {
            if (warn)
                console.log('Pool '+pool_id+' configuration is invalid: invalid raw_placement: '+e.message);
        }
    }
    else
    {
        let rules = [ [] ];
        let prev = [ 1 ];
        for (let i = 1; i < pool_cfg.pg_size; i++)
        {
            rules.push([ [ pool_cfg.failure_domain||'host', '!=', prev ] ]);
            prev = [ ...prev, i+1 ];
        }
        return rules;
    }
 }
 module.exports = {
    validate_pool_cfg,
    get_pg_rules,
 };
--- a/mon/scripts/simple-offsets.js
+++ b/mon/scripts/simple-offsets.js
@ -38,7 +38,7 @@ async function run()
        const st = await fs.stat(options.device);
        options.device_block_size = st.blksize;
        if (st.isBlockDevice())
-            device_size = Number(await system("/sbin/blockdev --getsize64 "+options.device));
+            device_size = Number(await system("/sbin/blockdev --getsize64 "+options.device))
        else
            device_size = st.size;
    }
@ -91,7 +91,7 @@ async function run()
 function system(cmd)
 {
-    return new Promise((ok, no) => child_process.exec(cmd, { maxBuffer: 64*1024*1024 }, (err, stdout/*, stderr*/) => (err ? no(err.message) : ok(stdout))));
+    return new Promise((ok, no) => child_process.exec(cmd, { maxBuffer: 64*1024*1024 }, (err, stdout, stderr) => (err ? no(err.message) : ok(stdout))));
 }
 run().catch(err => { console.error(err); process.exit(1); });
--- a/mon/stats.js
+++ b/mon/stats.js
@ -1,286 +0,0 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 (see README.md for details)
 function derive_osd_stats(st, prev, prev_diff)
 {
    const diff = { op_stats: {}, subop_stats: {}, recovery_stats: {}, inode_stats: {} };
    if (!st || !st.time || !prev || !prev.time || prev.time >= st.time)
    {
        return prev_diff || diff;
    }
    const timediff = BigInt(st.time*1000 - prev.time*1000);
    for (const op in st.op_stats||{})
    {
        const pr = prev && prev.op_stats && prev.op_stats[op];
        let c = st.op_stats[op];
        c = { bytes: BigInt(c.bytes||0), usec: BigInt(c.usec||0), count: BigInt(c.count||0) };
        const b = c.bytes - BigInt(pr && pr.bytes||0);
        const us = c.usec - BigInt(pr && pr.usec||0);
        const n = c.count - BigInt(pr && pr.count||0);
        if (n > 0)
            diff.op_stats[op] = { ...c, bps: b*1000n/timediff, iops: n*1000n/timediff, lat: us/n };
    }
    for (const op in st.subop_stats||{})
    {
        const pr = prev && prev.subop_stats && prev.subop_stats[op];
        let c = st.subop_stats[op];
        c = { usec: BigInt(c.usec||0), count: BigInt(c.count||0) };
        const us = c.usec - BigInt(pr && pr.usec||0);
        const n = c.count - BigInt(pr && pr.count||0);
        if (n > 0)
            diff.subop_stats[op] = { ...c, iops: n*1000n/timediff, lat: us/n };
    }
    for (const op in st.recovery_stats||{})
    {
        const pr = prev && prev.recovery_stats && prev.recovery_stats[op];
        let c = st.recovery_stats[op];
        c = { bytes: BigInt(c.bytes||0), count: BigInt(c.count||0) };
        const b = c.bytes - BigInt(pr && pr.bytes||0);
        const n = c.count - BigInt(pr && pr.count||0);
        if (n > 0)
            diff.recovery_stats[op] = { ...c, bps: b*1000n/timediff, iops: n*1000n/timediff };
    }
    for (const pool_id in st.inode_stats||{})
    {
        diff.inode_stats[pool_id] = {};
        for (const inode_num in st.inode_stats[pool_id])
        {
            const inode_diff = diff.inode_stats[pool_id][inode_num] = {};
            for (const op of [ 'read', 'write', 'delete' ])
            {
                const c = st.inode_stats[pool_id][inode_num][op];
                const pr = prev && prev.inode_stats && prev.inode_stats[pool_id] &&
                    prev.inode_stats[pool_id][inode_num] && prev.inode_stats[pool_id][inode_num][op];
                const n = BigInt(c.count||0) - BigInt(pr && pr.count||0);
                inode_diff[op] = {
                    bps: (BigInt(c.bytes||0) - BigInt(pr && pr.bytes||0))*1000n/timediff,
                    iops: n*1000n/timediff,
                    lat: (BigInt(c.usec||0) - BigInt(pr && pr.usec||0))/(n || 1n),
                };
            }
        }
    }
    return diff;
 }
 // sum_op_stats(this.state.osd, this.prev_stats)
 function sum_op_stats(all_osd, prev_stats)
 {
    for (const osd in all_osd.stats)
    {
        const cur = { ...all_osd.stats[osd], inode_stats: all_osd.inodestats[osd]||{} };
        prev_stats.osd_diff[osd] = derive_osd_stats(
            cur, prev_stats.osd_stats[osd], prev_stats.osd_diff[osd]
        );
        prev_stats.osd_stats[osd] = cur;
    }
    const sum_diff = { op_stats: {}, subop_stats: {}, recovery_stats: {} };
    // Sum derived values instead of deriving summed
    for (const osd in all_osd.state)
    {
        const derived = prev_stats.osd_diff[osd];
        if (!all_osd.state[osd] || !derived)
        {
            continue;
        }
        for (const type in sum_diff)
        {
            for (const op in derived[type]||{})
            {
                for (const k in derived[type][op])
                {
                    sum_diff[type][op] = sum_diff[type][op] || {};
                    sum_diff[type][op][k] = (sum_diff[type][op][k] || 0n) + derived[type][op][k];
                }
            }
        }
    }
    return sum_diff;
 }
 // sum_object_counts(this.state, this.config)
 function sum_object_counts(state, global_config)
 {
    const object_counts = { object: 0n, clean: 0n, misplaced: 0n, degraded: 0n, incomplete: 0n };
    const object_bytes = { object: 0n, clean: 0n, misplaced: 0n, degraded: 0n, incomplete: 0n };
    for (const pool_id in state.pg.stats)
    {
        let object_size = 0;
        for (const osd_num of state.pg.stats[pool_id].write_osd_set||[])
        {
            if (osd_num && state.osd.stats[osd_num] && state.osd.stats[osd_num].block_size)
            {
                object_size = state.osd.stats[osd_num].block_size;
                break;
            }
        }
        const pool_cfg = (state.config.pools[pool_id]||{});
        if (!object_size)
        {
            object_size = pool_cfg.block_size || global_config.block_size || 131072;
        }
        if (pool_cfg.scheme !== 'replicated')
        {
            object_size *= ((pool_cfg.pg_size||0) - (pool_cfg.parity_chunks||0));
        }
        object_size = BigInt(object_size);
        for (const pg_num in state.pg.stats[pool_id])
        {
            const st = state.pg.stats[pool_id][pg_num];
            if (st)
            {
                for (const k in object_counts)
                {
                    if (st[k+'_count'])
                    {
                        object_counts[k] += BigInt(st[k+'_count']);
                        object_bytes[k] += BigInt(st[k+'_count']) * object_size;
                    }
                }
            }
        }
    }
    return { object_counts, object_bytes };
 }
 // sum_inode_stats(this.state, this.prev_stats)
 function sum_inode_stats(state, prev_stats)
 {
    const inode_stats = {};
    const inode_stub = () => ({
        raw_used: 0n,
        read: { count: 0n, usec: 0n, bytes: 0n, bps: 0n, iops: 0n, lat: 0n },
        write: { count: 0n, usec: 0n, bytes: 0n, bps: 0n, iops: 0n, lat: 0n },
        delete: { count: 0n, usec: 0n, bytes: 0n, bps: 0n, iops: 0n, lat: 0n },
    });
    const seen_pools = {};
    for (const pool_id in state.config.pools)
    {
        seen_pools[pool_id] = true;
        state.pool.stats[pool_id] = state.pool.stats[pool_id] || {};
        state.pool.stats[pool_id].used_raw_tb = 0n;
    }
    for (const osd_num in state.osd.space)
    {
        for (const pool_id in state.osd.space[osd_num])
        {
            state.pool.stats[pool_id] = state.pool.stats[pool_id] || {};
            if (!seen_pools[pool_id])
            {
                state.pool.stats[pool_id].used_raw_tb = 0n;
                seen_pools[pool_id] = true;
            }
            inode_stats[pool_id] = inode_stats[pool_id] || {};
            for (const inode_num in state.osd.space[osd_num][pool_id])
            {
                const u = BigInt(state.osd.space[osd_num][pool_id][inode_num]||0);
                if (inode_num)
                {
                    inode_stats[pool_id][inode_num] = inode_stats[pool_id][inode_num] || inode_stub();
                    inode_stats[pool_id][inode_num].raw_used += u;
                }
                state.pool.stats[pool_id].used_raw_tb += u;
            }
        }
    }
    for (const pool_id in seen_pools)
    {
        const used = state.pool.stats[pool_id].used_raw_tb;
        state.pool.stats[pool_id].used_raw_tb = Number(used)/1024/1024/1024/1024;
    }
    for (const osd_num in state.osd.state)
    {
        const ist = state.osd.inodestats[osd_num];
        if (!ist || !state.osd.state[osd_num])
        {
            continue;
        }
        for (const pool_id in ist)
        {
            inode_stats[pool_id] = inode_stats[pool_id] || {};
            for (const inode_num in ist[pool_id])
            {
                inode_stats[pool_id][inode_num] = inode_stats[pool_id][inode_num] || inode_stub();
                for (const op of [ 'read', 'write', 'delete' ])
                {
                    inode_stats[pool_id][inode_num][op].count += BigInt(ist[pool_id][inode_num][op].count||0);
                    inode_stats[pool_id][inode_num][op].usec += BigInt(ist[pool_id][inode_num][op].usec||0);
                    inode_stats[pool_id][inode_num][op].bytes += BigInt(ist[pool_id][inode_num][op].bytes||0);
                }
            }
        }
    }
    for (const osd in state.osd.state)
    {
        const osd_diff = prev_stats.osd_diff[osd];
        if (!osd_diff || !state.osd.state[osd])
        {
            continue;
        }
        for (const pool_id in osd_diff.inode_stats)
        {
            for (const inode_num in prev_stats.osd_diff[osd].inode_stats[pool_id])
            {
                inode_stats[pool_id][inode_num] = inode_stats[pool_id][inode_num] || inode_stub();
                for (const op of [ 'read', 'write', 'delete' ])
                {
                    const op_diff = prev_stats.osd_diff[osd].inode_stats[pool_id][inode_num][op] || {};
                    const op_st = inode_stats[pool_id][inode_num][op];
                    op_st.bps += op_diff.bps;
                    op_st.iops += op_diff.iops;
                    op_st.lat += op_diff.lat;
                    op_st.n_osd = (op_st.n_osd || 0) + 1;
                }
            }
        }
    }
    for (const pool_id in inode_stats)
    {
        for (const inode_num in inode_stats[pool_id])
        {
            let nonzero = inode_stats[pool_id][inode_num].raw_used > 0;
            for (const op of [ 'read', 'write', 'delete' ])
            {
                const op_st = inode_stats[pool_id][inode_num][op];
                if (op_st.n_osd)
                {
                    op_st.lat /= BigInt(op_st.n_osd);
                    delete op_st.n_osd;
                }
                if (op_st.bps > 0 || op_st.iops > 0)
                    nonzero = true;
            }
            if (!nonzero && (!state.config.inode[pool_id] || !state.config.inode[pool_id][inode_num]))
            {
                // Deleted inode (no data, no I/O, no config)
                delete inode_stats[pool_id][inode_num];
            }
        }
    }
    return { inode_stats, seen_pools };
 }
 function serialize_bigints(obj)
 {
    obj = { ...obj };
    for (const k in obj)
    {
        if (typeof obj[k] == 'bigint')
        {
            obj[k] = ''+obj[k];
        }
        else if (typeof obj[k] == 'object')
        {
            obj[k] = serialize_bigints(obj[k]);
        }
    }
    return obj;
 }
 module.exports = {
    derive_osd_stats,
    sum_op_stats,
    sum_object_counts,
    sum_inode_stats,
    serialize_bigints,
 };
--- a/mon/lp_optimizer/test-nonuniform.js
+++ b/mon/lp_optimizer/test-nonuniform.js
@ -7,8 +7,7 @@
 // This leads to really uneven OSD fill ratio in Ceph even when PGs are perfectly balanced.
 // But we support this case with the "parity_space" parameter in optimize_initial()/optimize_change().
-const { SimpleCombinator } = require('./simple_pgs.js');
+const LPOptimizer = require('./lp-optimizer.js');
 const LPOptimizer = require('./lp_optimizer.js');
 const osd_tree = {
    ripper5: {
@ -115,17 +114,16 @@ Fine, let's try to optimize for it.
 async function run()
 {
-    const osd_weights = Object.assign({}, ...Object.values(osd_tree));
+    const all_weights = Object.assign({}, ...Object.values(osd_tree));
-    const total_weight = Object.values(osd_weights).reduce((a, c) => Number(a) + Number(c), 0);
+    const total_weight = Object.values(all_weights).reduce((a, c) => Number(a) + Number(c), 0);
-    const eff = LPOptimizer.pg_list_space_efficiency(prev_pgs, osd_weights, 2, 2.26);
+    const eff = LPOptimizer.pg_list_space_efficiency(prev_pgs, all_weights, 2, 2.26);
    const orig = eff*4.26 / total_weight;
    console.log('Original efficiency was: '+Math.round(orig*10000)/100+' %');
-    const combinator = new SimpleCombinator(osd_tree, 3, 10000);
+    let prev = await LPOptimizer.optimize_initial({ osd_tree, pg_size: 3, pg_count: 256, parity_space: 2.26 });
    let prev = await LPOptimizer.optimize_initial({ osd_weights, combinator, pg_size: 3, pg_count: 256, parity_space: 2.26 });
    LPOptimizer.print_change_stats(prev);
-    let next = await LPOptimizer.optimize_change({ prev_pgs, osd_weights, combinator, pg_size: 3, parity_space: 2.26 });
+    let next = await LPOptimizer.optimize_change({ prev_pgs, osd_tree, pg_size: 3, max_combinations: 10000, parity_space: 2.26 });
    LPOptimizer.print_change_stats(next);
 }
--- a/mon/lp_optimizer/test-optimize-simple.js
+++ b/mon/lp_optimizer/test-optimize-simple.js
@ -1,8 +1,7 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 (see README.md for details)
-const { compat } = require('./simple_pgs.js');
+const LPOptimizer = require('./lp-optimizer.js');
 const LPOptimizer = require('./lp_optimizer.js');
 async function run()
 {
@ -15,26 +14,26 @@ async function run()
    let res;
    console.log('16 PGs, size=3');
-    res = await LPOptimizer.optimize_initial(compat({ osd_tree, pg_size: 3, pg_count: 16, ordered: false }));
+    res = await LPOptimizer.optimize_initial({ osd_tree, pg_size: 3, pg_count: 16, ordered: false });
    LPOptimizer.print_change_stats(res, false);
    assert(res.space == 3, 'Initial distribution');
    console.log('\nChange size to 2');
-    res = await LPOptimizer.optimize_change(compat({ prev_pgs: res.int_pgs, osd_tree, pg_size: 2, ordered: false }));
+    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree, pg_size: 2, ordered: false });
    LPOptimizer.print_change_stats(res, false);
    assert(res.space >= 3*14/16 && res.osd_differs == 0, 'Redistribution');
    console.log('\nRemove OSD 3');
    const no3_tree = { ...osd_tree };
    delete no3_tree['300'];
-    res = await LPOptimizer.optimize_change(compat({ prev_pgs: res.int_pgs, osd_tree: no3_tree, pg_size: 2, ordered: false }));
+    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree: no3_tree, pg_size: 2, ordered: false });
    LPOptimizer.print_change_stats(res, false);
    assert(res.space == 2, 'Redistribution after OSD removal');
    console.log('\n16 PGs, size=3, ordered');
-    res = await LPOptimizer.optimize_initial(compat({ osd_tree, pg_size: 3, pg_count: 16, ordered: true }));
+    res = await LPOptimizer.optimize_initial({ osd_tree, pg_size: 3, pg_count: 16, ordered: true });
    LPOptimizer.print_change_stats(res, false);
    assert(res.space == 3, 'Initial distribution');
    console.log('\nChange size to 2, ordered');
-    res = await LPOptimizer.optimize_change(compat({ prev_pgs: res.int_pgs, osd_tree, pg_size: 2, ordered: true }));
+    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree, pg_size: 2, ordered: true });
    LPOptimizer.print_change_stats(res, false);
    assert(res.space >= 3*14/16 && res.osd_differs < 8, 'Redistribution');
 }
--- a/mon/lp_optimizer/test-optimize-undersized.js
+++ b/mon/lp_optimizer/test-optimize-undersized.js
@ -1,8 +1,7 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 (see README.md for details)
-const { compat, flatten_tree } = require('./simple_pgs.js');
+const LPOptimizer = require('./lp-optimizer.js');
 const LPOptimizer = require('./lp_optimizer.js');
 const crush_tree = [
    { level: 1, children: [
@ -37,44 +36,44 @@ const crush_tree = [
    ] },
 ];
-const osd_tree = flatten_tree(crush_tree, {}, 1, 3);
+const osd_tree = LPOptimizer.flatten_tree(crush_tree, {}, 1, 3);
 console.log(osd_tree);
 async function run()
 {
    const cur_tree = {};
    console.log('Empty tree:');
-    let res = await LPOptimizer.optimize_initial(compat({ osd_tree: cur_tree, pg_size: 3, pg_count: 256 }));
+    let res = await LPOptimizer.optimize_initial({ osd_tree: cur_tree, pg_size: 3, pg_count: 256 });
    LPOptimizer.print_change_stats(res, false);
    assert(res.space == 0);
    console.log('\nAdding 1st failure domain:');
    cur_tree['dom1'] = osd_tree['dom1'];
-    res = await LPOptimizer.optimize_change(compat({ prev_pgs: res.int_pgs, osd_tree: cur_tree, pg_size: 3 }));
+    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree: cur_tree, pg_size: 3 });
    LPOptimizer.print_change_stats(res, false);
    assert(res.space == 12 && res.total_space == 12);
    console.log('\nAdding 2nd failure domain:');
    cur_tree['dom2'] = osd_tree['dom2'];
-    res = await LPOptimizer.optimize_change(compat({ prev_pgs: res.int_pgs, osd_tree: cur_tree, pg_size: 3 }));
+    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree: cur_tree, pg_size: 3 });
    LPOptimizer.print_change_stats(res, false);
    assert(res.space == 24 && res.total_space == 24);
    console.log('\nAdding 3rd failure domain:');
    cur_tree['dom3'] = osd_tree['dom3'];
-    res = await LPOptimizer.optimize_change(compat({ prev_pgs: res.int_pgs, osd_tree: cur_tree, pg_size: 3 }));
+    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree: cur_tree, pg_size: 3 });
    LPOptimizer.print_change_stats(res, false);
    assert(res.space == 36 && res.total_space == 36);
    console.log('\nRemoving 3rd failure domain:');
    delete cur_tree['dom3'];
-    res = await LPOptimizer.optimize_change(compat({ prev_pgs: res.int_pgs, osd_tree: cur_tree, pg_size: 3 }));
+    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree: cur_tree, pg_size: 3 });
    LPOptimizer.print_change_stats(res, false);
    assert(res.space == 24 && res.total_space == 24);
    console.log('\nRemoving 2nd failure domain:');
    delete cur_tree['dom2'];
-    res = await LPOptimizer.optimize_change(compat({ prev_pgs: res.int_pgs, osd_tree: cur_tree, pg_size: 3 }));
+    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree: cur_tree, pg_size: 3 });
    LPOptimizer.print_change_stats(res, false);
    assert(res.space == 12 && res.total_space == 12);
    console.log('\nRemoving 1st failure domain:');
    delete cur_tree['dom1'];
-    res = await LPOptimizer.optimize_change(compat({ prev_pgs: res.int_pgs, osd_tree: cur_tree, pg_size: 3 }));
+    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree: cur_tree, pg_size: 3 });
    LPOptimizer.print_change_stats(res, false);
    assert(res.space == 0);
 }
--- a/mon/lp_optimizer/test-optimize-unfeasible.js
+++ b/mon/lp_optimizer/test-optimize-unfeasible.js
@ -1,8 +1,7 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 (see README.md for details)
-const { compat } = require('./simple_pgs.js');
+const LPOptimizer = require('./lp-optimizer.js');
 const LPOptimizer = require('./lp_optimizer.js');
 const osd_tree = {
    100: {
@ -21,13 +20,13 @@ async function run()
 {
    let res;
    console.log('256 PGs, 3+3 OSDs, size=2');
-    res = await LPOptimizer.optimize_initial(compat({ osd_tree, pg_size: 2, pg_count: 256 }));
+    res = await LPOptimizer.optimize_initial({ osd_tree, pg_size: 2, pg_count: 256 });
    LPOptimizer.print_change_stats(res, false);
    // Should NOT fail with the "unfeasible or unbounded" exception
    console.log('\nRemoving osd.2');
    delete osd_tree[100][2];
-    res = await LPOptimizer.optimize_change(compat({ prev_pgs: res.int_pgs, osd_tree, pg_size: 2 }));
+    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree, pg_size: 2 });
    LPOptimizer.print_change_stats(res, false);
 }
--- a/mon/lp_optimizer/test-optimize.js
+++ b/mon/lp_optimizer/test-optimize.js
@ -1,8 +1,7 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 (see README.md for details)
-const { compat, flatten_tree } = require('./simple_pgs.js');
+const LPOptimizer = require('./lp-optimizer.js');
 const LPOptimizer = require('./lp_optimizer.js');
 const osd_tree = {
    100: {
@ -20,7 +19,7 @@ const osd_tree = {
    },
    500: {
        4: 3.58498,
-        /*8: 3.58589,*/
+//        8: 3.58589,
        9: 3.63869,
    },
    600: {
@ -85,31 +84,31 @@ async function run()
    // Space efficiency is ~99% in all cases.
    console.log('256 PGs, size=2');
-    res = await LPOptimizer.optimize_initial(compat({ osd_tree, pg_size: 2, pg_count: 256 }));
+    res = await LPOptimizer.optimize_initial({ osd_tree, pg_size: 2, pg_count: 256 });
    LPOptimizer.print_change_stats(res, false);
    console.log('\nAdding osd.8');
    osd_tree[500][8] = 3.58589;
-    res = await LPOptimizer.optimize_change(compat({ prev_pgs: res.int_pgs, osd_tree, pg_size: 2 }));
+    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree, pg_size: 2 });
    LPOptimizer.print_change_stats(res, false);
    console.log('\nRemoving osd.8');
    delete osd_tree[500][8];
-    res = await LPOptimizer.optimize_change(compat({ prev_pgs: res.int_pgs, osd_tree, pg_size: 2 }));
+    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree, pg_size: 2 });
    LPOptimizer.print_change_stats(res, false);
    console.log('\n256 PGs, size=3');
-    res = await LPOptimizer.optimize_initial(compat({ osd_tree, pg_size: 3, pg_count: 256 }));
+    res = await LPOptimizer.optimize_initial({ osd_tree, pg_size: 3, pg_count: 256 });
    LPOptimizer.print_change_stats(res, false);
    console.log('\nAdding osd.8');
    osd_tree[500][8] = 3.58589;
-    res = await LPOptimizer.optimize_change(compat({ prev_pgs: res.int_pgs, osd_tree, pg_size: 3 }));
+    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree, pg_size: 3 });
    LPOptimizer.print_change_stats(res, false);
    console.log('\nRemoving osd.8');
    delete osd_tree[500][8];
-    res = await LPOptimizer.optimize_change(compat({ prev_pgs: res.int_pgs, osd_tree, pg_size: 3 }));
+    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree, pg_size: 3 });
    LPOptimizer.print_change_stats(res, false);
    console.log('\n256 PGs, size=3, failure domain=rack');
-    res = await LPOptimizer.optimize_initial(compat({ osd_tree: flatten_tree(crush_tree, {}, 1, 3), pg_size: 3, pg_count: 256 }));
+    res = await LPOptimizer.optimize_initial({ osd_tree: LPOptimizer.flatten_tree(crush_tree, {}, 1, 3), pg_size: 3, pg_count: 256 });
    LPOptimizer.print_change_stats(res, false);
 }
--- a/mon/scripts/vitastor-mon.service
+++ b/mon/scripts/vitastor-mon.service
--- a/mon/scripts/vitastor-osd@.service
+++ b/mon/scripts/vitastor-osd@.service
--- a/mon/scripts/vitastor.target
+++ b/mon/scripts/vitastor.target
--- a/patches/cinder-vitastor-22.py
+++ b/patches/cinder-vitastor-22.py
@ -1,966 +0,0 @@
 # Vitastor Driver for OpenStack Cinder
 #
 # --------------------------------------------
 # Install as cinder/volume/drivers/vitastor.py
 # --------------------------------------------
 #
 # Copyright 2020 Vitaliy Filippov
 #
 # Licensed under the Apache License, Version 2.0 (the "License"); you may
 # not use this file except in compliance with the License. You may obtain
 # a copy of the License at
 #
 # http://www.apache.org/licenses/LICENSE-2.0
 #
 # Unless required by applicable law or agreed to in writing, software
 # distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
 # WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
 # License for the specific language governing permissions and limitations
 # under the License.
 """Cinder Vitastor Driver"""
 import binascii
 import base64
 import errno
 import json
 import math
 import os
 import tempfile
 from castellan import key_manager
 from oslo_config import cfg
 from oslo_log import log as logging
 from oslo_service import loopingcall
 from oslo_concurrency import processutils
 from oslo_utils import encodeutils
 from oslo_utils import excutils
 from oslo_utils import fileutils
 from oslo_utils import units
 import six
 from six.moves.urllib import request
 from cinder import exception
 from cinder.i18n import _
 from cinder.image import image_utils
 from cinder import interface
 from cinder import objects
 from cinder.objects import fields
 from cinder import utils
 from cinder.volume import configuration
 from cinder.volume import driver
 from cinder.volume import volume_utils
 VERSION = '1.4.1'
 LOG = logging.getLogger(__name__)
 VITASTOR_OPTS = [
    cfg.StrOpt(
        'vitastor_config_path',
        default='/etc/vitastor/vitastor.conf',
        help='Vitastor configuration file path'
    ),
    cfg.StrOpt(
        'vitastor_etcd_address',
        default='',
        help='Vitastor etcd address(es)'),
    cfg.StrOpt(
        'vitastor_etcd_prefix',
        default='/vitastor',
        help='Vitastor etcd prefix'
    ),
    cfg.StrOpt(
        'vitastor_pool_id',
        default='',
        help='Vitastor pool ID to use for volumes'
    ),
    # FIXME exclusive_cinder_pool ?
 ]
 CONF = cfg.CONF
 CONF.register_opts(VITASTOR_OPTS, group = configuration.SHARED_CONF_GROUP)
 class VitastorDriverException(exception.VolumeDriverException):
    message = _("Vitastor Cinder driver failure: %(reason)s")
@interface.volumedriver
 class VitastorDriver(driver.CloneableImageVD,
    driver.ManageableVD, driver.ManageableSnapshotsVD,
    driver.BaseVD):
    """Implements Vitastor volume commands."""
    cfg = {}
    _etcd_urls = []
    def __init__(self, active_backend_id = None, *args, **kwargs):
        super(VitastorDriver, self).__init__(*args, **kwargs)
        self.configuration.append_config_values(VITASTOR_OPTS)
    @classmethod
    def get_driver_options(cls):
        additional_opts = cls._get_oslo_driver_opts(
            'reserved_percentage',
            'max_over_subscription_ratio',
            'volume_dd_blocksize'
        )
        return VITASTOR_OPTS + additional_opts
    def do_setup(self, context):
        """Performs initialization steps that could raise exceptions."""
        super(VitastorDriver, self).do_setup(context)
        # Make sure configuration is in UTF-8
        for attr in [ 'config_path', 'etcd_address', 'etcd_prefix', 'pool_id' ]:
            val = self.configuration.safe_get('vitastor_'+attr)
            if val is not None:
                self.cfg[attr] = utils.convert_str(val)
        self.cfg = self._load_config(self.cfg)
    def _load_config(self, cfg):
        # Try to load configuration file
        try:
            f = open(cfg['config_path'] or '/etc/vitastor/vitastor.conf')
            conf = json.loads(f.read())
            f.close()
            for k in conf:
                cfg[k] = cfg.get(k, conf[k])
        except:
            pass
        if isinstance(cfg['etcd_address'], str):
            cfg['etcd_address'] = cfg['etcd_address'].split(',')
        # Sanitize etcd URLs
        for i, etcd_url in enumerate(cfg['etcd_address']):
            ssl = False
            if etcd_url.lower().startswith('http://'):
                etcd_url = etcd_url[7:]
            elif etcd_url.lower().startswith('https://'):
                etcd_url = etcd_url[8:]
                ssl = True
            if etcd_url.find('/') < 0:
                etcd_url += '/v3'
            if ssl:
                etcd_url = 'https://'+etcd_url
            else:
                etcd_url = 'http://'+etcd_url
            cfg['etcd_address'][i] = etcd_url
        return cfg
    def check_for_setup_error(self):
        """Returns an error if prerequisites aren't met."""
    def _encode_etcd_key(self, key):
        if not isinstance(key, bytes):
            key = str(key).encode('utf-8')
        return base64.b64encode(self.cfg['etcd_prefix'].encode('utf-8')+b'/'+key).decode('utf-8')
    def _encode_etcd_value(self, value):
        if not isinstance(value, bytes):
            value = str(value).encode('utf-8')
        return base64.b64encode(value).decode('utf-8')
    def _encode_etcd_requests(self, obj):
        for v in obj:
            for rt in v:
                if 'key' in v[rt]:
                    v[rt]['key'] = self._encode_etcd_key(v[rt]['key'])
                if 'range_end' in v[rt]:
                    v[rt]['range_end'] = self._encode_etcd_key(v[rt]['range_end'])
                if 'value' in v[rt]:
                    v[rt]['value'] = self._encode_etcd_value(v[rt]['value'])
    def _etcd_txn(self, params):
        if 'compare' in params:
            for v in params['compare']:
                if 'key' in v:
                    v['key'] = self._encode_etcd_key(v['key'])
        if 'failure' in params:
            self._encode_etcd_requests(params['failure'])
        if 'success' in params:
            self._encode_etcd_requests(params['success'])
        body = json.dumps(params).encode('utf-8')
        headers = {
            'Content-Type': 'application/json'
        }
        err = None
        for etcd_url in self.cfg['etcd_address']:
            try:
                resp = request.urlopen(request.Request(etcd_url+'/kv/txn', body, headers), timeout = 5)
                data = json.loads(resp.read())
                if 'responses' not in data:
                    data['responses'] = []
                for i, resp in enumerate(data['responses']):
                    if 'response_range' in resp:
                        if 'kvs' not in resp['response_range']:
                            resp['response_range']['kvs'] = []
                        for kv in resp['response_range']['kvs']:
                            kv['key'] = base64.b64decode(kv['key'].encode('utf-8')).decode('utf-8')
                            if kv['key'].startswith(self.cfg['etcd_prefix']+'/'):
                                kv['key'] = kv['key'][len(self.cfg['etcd_prefix'])+1 : ]
                            kv['value'] = json.loads(base64.b64decode(kv['value'].encode('utf-8')))
                    if len(resp.keys()) != 1:
                        LOG.exception('unknown responses['+str(i)+'] format: '+json.dumps(resp))
                    else:
                        resp = data['responses'][i] = resp[list(resp.keys())[0]]
                return data
            except Exception as e:
                LOG.exception('error calling etcd transaction: '+body.decode('utf-8')+'\nerror: '+str(e))
                err = e
        raise err
    def _etcd_foreach(self, prefix, add_fn):
        total = 0
        batch = 1000
        begin = prefix+'/'
        while True:
            resp = self._etcd_txn({ 'success': [
                { 'request_range': {
                    'key': begin,
                    'range_end': prefix+'0',
                    'limit': batch+1,
                } },
            ] })
            i = 0
            while i < batch and i < len(resp['responses'][0]['kvs']):
                kv = resp['responses'][0]['kvs'][i]
                add_fn(kv)
                i += 1
            if len(resp['responses'][0]['kvs']) <= batch:
                break
            begin = resp['responses'][0]['kvs'][batch]['key']
        return total
    def _update_volume_stats(self):
        location_info = json.dumps({
            'config': self.configuration.vitastor_config_path,
            'etcd_address': self.configuration.vitastor_etcd_address,
            'etcd_prefix': self.configuration.vitastor_etcd_prefix,
            'pool_id': self.configuration.vitastor_pool_id,
        })
        stats = {
            'vendor_name': 'Vitastor',
            'driver_version': self.VERSION,
            'storage_protocol': 'vitastor',
            'total_capacity_gb': 'unknown',
            'free_capacity_gb': 'unknown',
            # FIXME check if safe_get is required
            'reserved_percentage': self.configuration.safe_get('reserved_percentage'),
            'multiattach': True,
            'thin_provisioning_support': True,
            'max_over_subscription_ratio': self.configuration.safe_get('max_over_subscription_ratio'),
            'location_info': location_info,
            'backend_state': 'down',
            'volume_backend_name': self.configuration.safe_get('volume_backend_name') or 'vitastor',
            'replication_enabled': False,
        }
        try:
            pool_stats = self._etcd_txn({ 'success': [
                { 'request_range': { 'key': 'pool/stats/'+str(self.cfg['pool_id']) } }
            ] })
            total_provisioned = 0
            def add_total(kv):
                nonlocal total_provisioned
                if kv['key'].find('@') >= 0:
                    total_provisioned += kv['value']['size']
            self._etcd_foreach('config/inode/'+str(self.cfg['pool_id']), lambda kv: add_total(kv))
            stats['provisioned_capacity_gb'] = round(total_provisioned/1024.0/1024.0/1024.0, 2)
            pool_stats = pool_stats['responses'][0]['kvs']
            if len(pool_stats):
                pool_stats = pool_stats[0]['value']
                stats['free_capacity_gb'] = round(1024.0*(pool_stats['total_raw_tb']-pool_stats['used_raw_tb'])/pool_stats['raw_to_usable'], 2)
                stats['total_capacity_gb'] = round(1024.0*pool_stats['total_raw_tb'], 2)
            stats['backend_state'] = 'up'
        except Exception as e:
            # just log and return unknown capacities
            LOG.exception('error getting vitastor pool stats: '+str(e))
        self._stats = stats
    def get_volume_stats(self, refresh=False):
        """Get volume stats.
        If 'refresh' is True, run update the stats first.
        """
        if not self._stats or refresh:
            self._update_volume_stats()
        return self._stats
    def _next_id(self, resp):
        if len(resp['kvs']) == 0:
            return (1, 0)
        else:
            return (1 + resp['kvs'][0]['value'], resp['kvs'][0]['mod_revision'])
    def create_volume(self, volume):
        """Creates a logical volume."""
        size = int(volume.size) * units.Gi
        # FIXME: Check if convert_str is really required
        vol_name = utils.convert_str(volume.name)
        if vol_name.find('@') >= 0 or vol_name.find('/') >= 0:
            raise exception.VolumeBackendAPIException(data = '@ and / are forbidden in volume and snapshot names')
        LOG.debug("creating volume '%s'", vol_name)
        self._create_image(vol_name, { 'size': size })
        if volume.encryption_key_id:
            self._create_encrypted_volume(volume, volume.obj_context)
        volume_update = {}
        return volume_update
    def _create_encrypted_volume(self, volume, context):
        """Create a new LUKS encrypted image directly in Vitastor."""
        vol_name = utils.convert_str(volume.name)
        f, opts = self._encrypt_opts(volume, context)
        # FIXME: Check if it works at all :-)
        self._execute(
            'qemu-img', 'convert', '-f', 'luks', *opts,
            'vitastor:image='+vol_name.replace(':', '\\:')+self._qemu_args(),
            '%sM' % (volume.size * 1024)
        )
        f.close()
    def _encrypt_opts(self, volume, context):
        encryption = volume_utils.check_encryption_provider(self.db, volume, context)
        # Fetch the key associated with the volume and decode the passphrase
        keymgr = key_manager.API(CONF)
        key = keymgr.get(context, encryption['encryption_key_id'])
        passphrase = binascii.hexlify(key.get_encoded()).decode('utf-8')
        # Decode the dm-crypt style cipher spec into something qemu-img can use
        cipher_spec = image_utils.decode_cipher(encryption['cipher'], encryption['key_size'])
        tmp_dir = volume_utils.image_conversion_dir()
        f = tempfile.NamedTemporaryFile(prefix = 'luks_', dir = tmp_dir)
        f.write(passphrase)
        f.flush()
        return (f, [
            '--object', 'secret,id=luks_sec,format=raw,file=%(passfile)s' % {'passfile': f.name},
            '-o', 'key-secret=luks_sec,cipher-alg=%(cipher_alg)s,cipher-mode=%(cipher_mode)s,ivgen-alg=%(ivgen_alg)s' % cipher_spec,
        ])
    def create_snapshot(self, snapshot):
        """Creates a volume snapshot."""
        vol_name = utils.convert_str(snapshot.volume_name)
        snap_name = utils.convert_str(snapshot.name)
        if snap_name.find('@') >= 0 or snap_name.find('/') >= 0:
            raise exception.VolumeBackendAPIException(data = '@ and / are forbidden in volume and snapshot names')
        self._create_snapshot(vol_name, vol_name+'@'+snap_name)
    def snapshot_revert_use_temp_snapshot(self):
        """Disable the use of a temporary snapshot on revert."""
        return False
    def revert_to_snapshot(self, context, volume, snapshot):
        """Revert a volume to a given snapshot."""
        vol_name = utils.convert_str(snapshot.volume_name)
        snap_name = utils.convert_str(snapshot.name)
        # Delete the image and recreate it from the snapshot
        args = [ 'vitastor-cli', 'rm', vol_name, *(self._vitastor_args()) ]
        try:
            self._execute(*args)
        except processutils.ProcessExecutionError as exc:
            LOG.error("Failed to delete image "+vol_name+": "+exc)
            raise exception.VolumeBackendAPIException(data = exc.stderr)
        args = [
            'vitastor-cli', 'create', '--parent', vol_name+'@'+snap_name,
            vol_name, *(self._vitastor_args())
        ]
        try:
            self._execute(*args)
        except processutils.ProcessExecutionError as exc:
            LOG.error("Failed to recreate image "+vol_name+" from "+vol_name+"@"+snap_name+": "+exc)
            raise exception.VolumeBackendAPIException(data = exc.stderr)
    def delete_snapshot(self, snapshot):
        """Deletes a snapshot."""
        vol_name = utils.convert_str(snapshot.volume_name)
        snap_name = utils.convert_str(snapshot.name)
        args = [
            'vitastor-cli', 'rm', vol_name+'@'+snap_name,
            *(self._vitastor_args())
        ]
        try:
            self._execute(*args)
        except processutils.ProcessExecutionError as exc:
            LOG.error("Failed to remove snapshot "+vol_name+'@'+snap_name+": "+exc)
            raise exception.VolumeBackendAPIException(data = exc.stderr)
    def _child_count(self, parents):
        children = 0
        def add_child(kv):
            nonlocal children
            children += self._check_parent(kv, parents)
        self._etcd_foreach('config/inode', lambda kv: add_child(kv))
        return children
    def _check_parent(self, kv, parents):
        if 'parent_id' not in kv['value']:
            return 0
        parent_id = kv['value']['parent_id']
        _, _, pool_id, inode_id = kv['key'].split('/')
        parent_pool_id = pool_id
        if 'parent_pool_id' in kv['value'] and kv['value']['parent_pool_id']:
            parent_pool_id = kv['value']['parent_pool_id']
        inode = (int(pool_id) << 48) | (int(inode_id) & 0xffffffffffff)
        parent = (int(parent_pool_id) << 48) | (int(parent_id) & 0xffffffffffff)
        if parent in parents and inode not in parents:
            return 1
        return 0
    def create_cloned_volume(self, volume, src_vref):
        """Create a cloned volume from another volume."""
        size = int(volume.size) * units.Gi
        src_name = utils.convert_str(src_vref.name)
        dest_name = utils.convert_str(volume.name)
        if dest_name.find('@') >= 0 or dest_name.find('/') >= 0:
            raise exception.VolumeBackendAPIException(data = '@ and / are forbidden in volume and snapshot names')
        # FIXME Do full copy if requested (cfg.disable_clone)
        if src_vref.admin_metadata.get('readonly') == 'True':
            # source volume is a volume-image cache entry or other readonly volume
            # clone without intermediate snapshot
            src = self._get_image(src_name)
            LOG.debug("creating image '%s' from '%s'", dest_name, src_name)
            new_cfg = self._create_image(dest_name, {
                'size': size,
                'parent_id': src['idx']['id'],
                'parent_pool_id': src['idx']['pool_id'],
            })
            return {}
        clone_snap = "%s@%s.clone_snap" % (src_name, dest_name)
        make_img = True
        if (volume.display_name and
            volume.display_name.startswith('image-') and
            src_vref.project_id != volume.project_id):
            # idiotic openstack creates image-volume cache entries
            # as clones of normal VM volumes... :-X prevent it :-D
            clone_snap = dest_name
            make_img = False
        LOG.debug("creating layer '%s' under '%s'", clone_snap, src_name)
        new_cfg = self._create_snapshot(src_name, clone_snap, True)
        if make_img:
            # Then create a clone from it
            new_cfg = self._create_image(dest_name, {
                'size': size,
                'parent_id': new_cfg['parent_id'],
                'parent_pool_id': new_cfg['parent_pool_id'],
            })
        return {}
    def create_volume_from_snapshot(self, volume, snapshot):
        """Creates a cloned volume from an existing snapshot."""
        vol_name = utils.convert_str(volume.name)
        snap_name = utils.convert_str(snapshot.name)
        snap = self._get_image('volume-'+snapshot.volume_id+'@'+snap_name)
        if not snap:
            raise exception.SnapshotNotFound(snapshot_id = snap_name)
        snap_inode_id = int(resp['responses'][0]['kvs'][0]['value']['id'])
        snap_pool_id = int(resp['responses'][0]['kvs'][0]['value']['pool_id'])
        size = snap['cfg']['size']
        if int(volume.size):
            size = int(volume.size) * units.Gi
        new_cfg = self._create_image(vol_name, {
            'size': size,
            'parent_id': snap['idx']['id'],
            'parent_pool_id': snap['idx']['pool_id'],
        })
        return {}
    def _vitastor_args(self):
        args = []
        for k in [ 'config_path', 'etcd_address', 'etcd_prefix' ]:
            v = self.configuration.safe_get('vitastor_'+k)
            if v:
                args.extend(['--'+k, v])
        return args
    def _qemu_args(self):
        args = ''
        for k in [ 'config_path', 'etcd_address', 'etcd_prefix' ]:
            v = self.configuration.safe_get('vitastor_'+k)
            kk = k
            if kk == 'etcd_address':
                # FIXME use etcd_address in qemu driver
                kk = 'etcd_host'
            if v:
                args += ':'+kk.replace('_', '-')+'='+v.replace(':', '\\:')
        return args
    def delete_volume(self, volume):
        """Deletes a logical volume."""
        vol_name = utils.convert_str(volume.name)
        # Find the volume and all its snapshots
        range_end = b'index/image/' + vol_name.encode('utf-8')
        range_end = range_end[0 : len(range_end)-1] + six.int2byte(range_end[len(range_end)-1] + 1)
        resp = self._etcd_txn({ 'success': [
            { 'request_range': { 'key': 'index/image/'+vol_name, 'range_end': range_end } },
        ] })
        if len(resp['responses'][0]['kvs']) == 0:
            # already deleted
            LOG.info("volume %s no longer exists in backend", vol_name)
            return
        layers = resp['responses'][0]['kvs']
        layer_ids = {}
        for kv in layers:
            inode_id = int(kv['value']['id'])
            pool_id = int(kv['value']['pool_id'])
            inode_pool_id = (pool_id << 48) | (inode_id & 0xffffffffffff)
            layer_ids[inode_pool_id] = True
        # Check if the volume has clones and raise 'busy' if so
        children = self._child_count(layer_ids)
        if children > 0:
            raise exception.VolumeIsBusy(volume_name = vol_name)
        # Clear data
        for kv in layers:
            args = [
                'vitastor-cli', 'rm-data', '--pool', str(kv['value']['pool_id']),
                '--inode', str(kv['value']['id']), '--progress', '0',
                *(self._vitastor_args())
            ]
            try:
                self._execute(*args)
            except processutils.ProcessExecutionError as exc:
                LOG.error("Failed to remove layer "+kv['key']+": "+exc)
                raise exception.VolumeBackendAPIException(data = exc.stderr)
        # Delete all layers from etcd
        requests = []
        for kv in layers:
            requests.append({ 'request_delete_range': { 'key': kv['key'] } })
            requests.append({ 'request_delete_range': { 'key': 'config/inode/'+str(kv['value']['pool_id'])+'/'+str(kv['value']['id']) } })
        self._etcd_txn({ 'success': requests })
    def retype(self, context, volume, new_type, diff, host):
        """Change extra type specifications for a volume."""
        # FIXME Maybe (in the future) support multiple pools as different types
        return True, {}
    def ensure_export(self, context, volume):
        """Synchronously recreates an export for a logical volume."""
        pass
    def create_export(self, context, volume, connector):
        """Exports the volume."""
        pass
    def remove_export(self, context, volume):
        """Removes an export for a logical volume."""
        pass
    def _create_image(self, vol_name, cfg):
        pool_s = str(self.cfg['pool_id'])
        image_id = 0
        while image_id == 0:
            # check if the image already exists and find a free ID
            resp = self._etcd_txn({ 'success': [
                { 'request_range': { 'key': 'index/image/'+vol_name } },
                { 'request_range': { 'key': 'index/maxid/'+pool_s } },
            ] })
            if len(resp['responses'][0]['kvs']) > 0:
                # already exists
                raise exception.VolumeBackendAPIException(data = 'Volume '+vol_name+' already exists')
            image_id, id_mod = self._next_id(resp['responses'][1])
            # try to create the image
            resp = self._etcd_txn({ 'compare': [
                { 'target': 'MOD', 'mod_revision': id_mod, 'key': 'index/maxid/'+pool_s },
                { 'target': 'VERSION', 'version': 0, 'key': 'index/image/'+vol_name },
                { 'target': 'VERSION', 'version': 0, 'key': 'config/inode/'+pool_s+'/'+str(image_id) },
            ], 'success': [
                { 'request_put': { 'key': 'index/maxid/'+pool_s, 'value': image_id } },
                { 'request_put': { 'key': 'index/image/'+vol_name, 'value': json.dumps({
                    'id': image_id, 'pool_id': self.cfg['pool_id']
                }) } },
                { 'request_put': { 'key': 'config/inode/'+pool_s+'/'+str(image_id), 'value': json.dumps({
                    **cfg, 'name': vol_name,
                }) } },
            ] })
            if not resp.get('succeeded'):
                # repeat
                image_id = 0
    def _create_snapshot(self, vol_name, snap_vol_name, allow_existing = False):
        while True:
            # check if the image already exists and snapshot doesn't
            resp = self._etcd_txn({ 'success': [
                { 'request_range': { 'key': 'index/image/'+vol_name } },
                { 'request_range': { 'key': 'index/image/'+snap_vol_name } },
            ] })
            if len(resp['responses'][0]['kvs']) == 0:
                raise exception.VolumeBackendAPIException(data = 'Volume '+vol_name+' does not exist')
            if len(resp['responses'][1]['kvs']) > 0:
                if allow_existing:
                    snap_idx = resp['responses'][1]['kvs'][0]['value']
                    resp = self._etcd_txn({ 'success': [
                        { 'request_range': { 'key': 'config/inode/'+str(snap_idx['pool_id'])+'/'+str(snap_idx['id']) } },
                    ] })
                    if len(resp['responses'][0]['kvs']) == 0:
                        raise exception.VolumeBackendAPIException(data =
                            'Volume '+snap_vol_name+' is already indexed, but does not exist'
                        )
                    return resp['responses'][0]['kvs'][0]['value']
                raise exception.VolumeBackendAPIException(
                    data = 'Volume '+snap_vol_name+' already exists'
                )
            vol_idx = resp['responses'][0]['kvs'][0]['value']
            vol_idx_mod = resp['responses'][0]['kvs'][0]['mod_revision']
            # get image inode config and find a new ID
            resp = self._etcd_txn({ 'success': [
                { 'request_range': { 'key': 'config/inode/'+str(vol_idx['pool_id'])+'/'+str(vol_idx['id']) } },
                { 'request_range': { 'key': 'index/maxid/'+str(self.cfg['pool_id']) } },
            ] })
            if len(resp['responses'][0]['kvs']) == 0:
                raise exception.VolumeBackendAPIException(data = 'Volume '+vol_name+' does not exist')
            vol_cfg = resp['responses'][0]['kvs'][0]['value']
            vol_mod = resp['responses'][0]['kvs'][0]['mod_revision']
            new_id, id_mod = self._next_id(resp['responses'][1])
            # try to redirect image to the new inode
            new_cfg = {
                **vol_cfg, 'name': vol_name, 'parent_id': vol_idx['id'], 'parent_pool_id': vol_idx['pool_id']
            }
            resp = self._etcd_txn({ 'compare': [
                { 'target': 'MOD', 'mod_revision': vol_idx_mod, 'key': 'index/image/'+vol_name },
                { 'target': 'MOD', 'mod_revision': vol_mod, 'key': 'config/inode/'+str(vol_idx['pool_id'])+'/'+str(vol_idx['id']) },
                { 'target': 'MOD', 'mod_revision': id_mod, 'key': 'index/maxid/'+str(self.cfg['pool_id']) },
                { 'target': 'VERSION', 'version': 0, 'key': 'index/image/'+snap_vol_name },
                { 'target': 'VERSION', 'version': 0, 'key': 'config/inode/'+str(self.cfg['pool_id'])+'/'+str(new_id) },
            ], 'success': [
                { 'request_put': { 'key': 'index/maxid/'+str(self.cfg['pool_id']), 'value': new_id } },
                { 'request_put': { 'key': 'index/image/'+vol_name, 'value': json.dumps({
                    'id': new_id, 'pool_id': self.cfg['pool_id']
                }) } },
                { 'request_put': { 'key': 'config/inode/'+str(self.cfg['pool_id'])+'/'+str(new_id), 'value': json.dumps(new_cfg) } },
                { 'request_put': { 'key': 'index/image/'+snap_vol_name, 'value': json.dumps({
                    'id': vol_idx['id'], 'pool_id': vol_idx['pool_id']
                }) } },
                { 'request_put': { 'key': 'config/inode/'+str(vol_idx['pool_id'])+'/'+str(vol_idx['id']), 'value': json.dumps({
                    **vol_cfg, 'name': snap_vol_name, 'readonly': True
                }) } }
            ] })
            if resp.get('succeeded'):
                return new_cfg
    def initialize_connection(self, volume, connector):
        data = {
            'driver_volume_type': 'vitastor',
            'data': {
                'config_path': self.configuration.vitastor_config_path,
                'etcd_address': self.configuration.vitastor_etcd_address,
                'etcd_prefix': self.configuration.vitastor_etcd_prefix,
                'name': volume.name,
                'logical_block_size': '512',
                'physical_block_size': '4096',
            }
        }
        LOG.debug('connection data: %s', data)
        return data
    def terminate_connection(self, volume, connector, **kwargs):
        pass
    def clone_image(self, context, volume, image_location, image_meta, image_service):
        if image_location:
            # Note: image_location[0] is glance image direct_url.
            # image_location[1] contains the list of all locations (including
            # direct_url) or None if show_multiple_locations is False in
            # glance configuration.
            if image_location[1]:
                url_locations = [location['url'] for location in image_location[1]]
            else:
                url_locations = [image_location[0]]
            # iterate all locations to look for a cloneable one.
            for url_location in url_locations:
                if url_location and url_location.startswith('cinder://'):
                    # The idea is to use cinder://<volume-id> Glance volumes as base images
                    base_vol = self.db.volume_get(context, url_location[len('cinder://') : ])
                    if not base_vol or base_vol.volume_type_id != volume.volume_type_id:
                        continue
                    size = int(volume.size) * units.Gi
                    dest_name = utils.convert_str(volume.name)
                    # Find or create the base snapshot
                    snap_cfg = self._create_snapshot(base_vol.name, base_vol.name+'@.clone_snap', True)
                    # Then create a clone from it
                    new_cfg = self._create_image(dest_name, {
                        'size': size,
                        'parent_id': snap_cfg['parent_id'],
                        'parent_pool_id': snap_cfg['parent_pool_id'],
                    })
                    return ({}, True)
        return ({}, False)
    def copy_image_to_encrypted_volume(self, context, volume, image_service, image_id):
        self.copy_image_to_volume(context, volume, image_service, image_id, encrypted = True)
    def copy_image_to_volume(self, context, volume, image_service, image_id, encrypted = False, disable_sparse = False):
        tmp_dir = volume_utils.image_conversion_dir()
        with tempfile.NamedTemporaryFile(dir = tmp_dir) as tmp:
            image_utils.fetch_to_raw(
                context, image_service, image_id, tmp.name,
                self.configuration.volume_dd_blocksize, size = volume.size
            )
            out_format = [ '-O', 'raw' ]
            if encrypted:
                key_file, opts = self._encrypt_opts(volume, context)
                out_format = [ '-O', 'luks', *opts ]
            dest_name = utils.convert_str(volume.name)
            self._try_execute(
                'qemu-img', 'convert', '-f', 'raw', tmp.name, *out_format,
                'vitastor:image='+dest_name.replace(':', '\\:')+self._qemu_args()
            )
            if encrypted:
                key_file.close()
    def copy_volume_to_image(self, context, volume, image_service, image_meta):
        tmp_dir = volume_utils.image_conversion_dir()
        tmp_file = os.path.join(tmp_dir, volume.name + '-' + image_meta['id'])
        with fileutils.remove_path_on_error(tmp_file):
            vol_name = utils.convert_str(volume.name)
            self._try_execute(
                'qemu-img', 'convert', '-f', 'raw',
                'vitastor:image='+vol_name.replace(':', '\\:')+self._qemu_args(),
                '-O', 'raw', tmp_file
            )
            # FIXME: Copy directly if the destination image is also in Vitastor
            volume_utils.upload_volume(context, image_service, image_meta, tmp_file, volume)
        os.unlink(tmp_file)
    def _get_image(self, vol_name):
        # find the image
        resp = self._etcd_txn({ 'success': [
            { 'request_range': { 'key': 'index/image/'+vol_name } },
        ] })
        if len(resp['responses'][0]['kvs']) == 0:
            return None
        vol_idx = resp['responses'][0]['kvs'][0]['value']
        vol_idx_mod = resp['responses'][0]['kvs'][0]['mod_revision']
        # get image inode config
        resp = self._etcd_txn({ 'success': [
            { 'request_range': { 'key': 'config/inode/'+str(vol_idx['pool_id'])+'/'+str(vol_idx['id']) } },
        ] })
        if len(resp['responses'][0]['kvs']) == 0:
            return None
        vol_cfg = resp['responses'][0]['kvs'][0]['value']
        vol_cfg_mod = resp['responses'][0]['kvs'][0]['mod_revision']
        return {
            'cfg': vol_cfg,
            'cfg_mod': vol_cfg_mod,
            'idx': vol_idx,
            'idx_mod': vol_idx_mod,
        }
    def extend_volume(self, volume, new_size):
        """Extend an existing volume."""
        vol_name = utils.convert_str(volume.name)
        while True:
            vol = self._get_image(vol_name)
            if not vol:
                raise exception.VolumeBackendAPIException(data = 'Volume '+vol_name+' does not exist')
            # change size
            size = int(new_size) * units.Gi
            if size == vol['cfg']['size']:
                break
            resp = self._etcd_txn({ 'compare': [ {
                'target': 'MOD',
                'mod_revision': vol['cfg_mod'],
                'key': 'config/inode/'+str(vol['idx']['pool_id'])+'/'+str(vol['idx']['id']),
            } ], 'success': [
                { 'request_put': {
                    'key': 'config/inode/'+str(vol['idx']['pool_id'])+'/'+str(vol['idx']['id']),
                    'value': json.dumps({ **vol['cfg'], 'size': size }),
                } },
            ] })
            if resp.get('succeeded'):
                break
        LOG.debug(
            "Extend volume from %(old_size)s GB to %(new_size)s GB.",
            {'old_size': volume.size, 'new_size': new_size}
        )
    def _add_manageable_volume(self, kv, manageable_volumes, cinder_ids):
        cfg = kv['value']
        if kv['key'].find('@') >= 0:
            # snapshot
            return
        image_id = volume_utils.extract_id_from_volume_name(cfg['name'])
        image_info = {
            'reference': {'source-name': image_name},
            'size': int(math.ceil(float(cfg['size']) / units.Gi)),
            'cinder_id': None,
            'extra_info': None,
        }
        if image_id in cinder_ids:
            image_info['cinder_id'] = image_id
            image_info['safe_to_manage'] = False
            image_info['reason_not_safe'] = 'already managed'
        else:
            image_info['safe_to_manage'] = True
            image_info['reason_not_safe'] = None
        manageable_volumes.append(image_info)
    def get_manageable_volumes(self, cinder_volumes, marker, limit, offset, sort_keys, sort_dirs):
        manageable_volumes = []
        cinder_ids = [resource['id'] for resource in cinder_volumes]
        # List all volumes
        # FIXME: It's possible to use pagination in our case, but.. do we want it?
        self._etcd_foreach('config/inode/'+str(self.cfg['pool_id']),
            lambda kv: self._add_manageable_volume(kv, manageable_volumes, cinder_ids))
        return volume_utils.paginate_entries_list(
            manageable_volumes, marker, limit, offset, sort_keys, sort_dirs)
    def _get_existing_name(existing_ref):
        if not isinstance(existing_ref, dict):
            existing_ref = {"source-name": existing_ref}
        if 'source-name' not in existing_ref:
            reason = _('Reference must contain source-name element.')
            raise exception.ManageExistingInvalidReference(existing_ref=existing_ref, reason=reason)
        src_name = utils.convert_str(existing_ref['source-name'])
        if not src_name:
            reason = _('Reference must contain source-name element.')
            raise exception.ManageExistingInvalidReference(existing_ref=existing_ref, reason=reason)
        return src_name
    def manage_existing_get_size(self, volume, existing_ref):
        """Return size of an existing image for manage_existing.
        :param volume: volume ref info to be set
        :param existing_ref: {'source-name': <image name>}
        """
        src_name = self._get_existing_name(existing_ref)
        vol = self._get_image(src_name)
        if not vol:
            raise exception.VolumeBackendAPIException(data = 'Volume '+src_name+' does not exist')
        return int(math.ceil(float(vol['cfg']['size']) / units.Gi))
    def manage_existing(self, volume, existing_ref):
        """Manages an existing image.
        Renames the image name to match the expected name for the volume.
        :param volume: volume ref info to be set
        :param existing_ref: {'source-name': <image name>}
        """
        from_name = self._get_existing_name(existing_ref)
        to_name = utils.convert_str(volume.name)
        self._rename(from_name, to_name)
    def _rename(self, from_name, to_name):
        while True:
            vol = self._get_image(from_name)
            if not vol:
                raise exception.VolumeBackendAPIException(data = 'Volume '+from_name+' does not exist')
            to = self._get_image(to_name)
            if to:
                raise exception.VolumeBackendAPIException(data = 'Volume '+to_name+' already exists')
            resp = self._etcd_txn({ 'compare': [
                { 'target': 'MOD', 'mod_revision': vol['idx_mod'], 'key': 'index/image/'+vol['cfg']['name'] },
                { 'target': 'MOD', 'mod_revision': vol['cfg_mod'], 'key': 'config/inode/'+str(vol['idx']['pool_id'])+'/'+str(vol['idx']['id']) },
                { 'target': 'VERSION', 'version': 0, 'key': 'index/image/'+to_name },
            ], 'success': [
                { 'request_delete_range': { 'key': 'index/image/'+vol['cfg']['name'] } },
                { 'request_put': { 'key': 'index/image/'+to_name, 'value': json.dumps(vol['idx']) } },
                { 'request_put': { 'key': 'config/inode/'+str(vol['idx']['pool_id'])+'/'+str(vol['idx']['id']),
                    'value': json.dumps({ **vol['cfg'], 'name': to_name }) } },
            ] })
            if resp.get('succeeded'):
                break
    def unmanage(self, volume):
        pass
    def _add_manageable_snapshot(self, kv, manageable_snapshots, cinder_ids):
        cfg = kv['value']
        dog = kv['key'].find('@')
        if dog < 0:
            # snapshot
            return
        image_name = kv['key'][0 : dog]
        snap_name = kv['key'][dog+1 : ]
        snapshot_id = volume_utils.extract_id_from_snapshot_name(snap_name)
        snapshot_info = {
            'reference': {'source-name': snap_name},
            'size': int(math.ceil(float(cfg['size']) / units.Gi)),
            'cinder_id': None,
            'extra_info': None,
            'safe_to_manage': False,
            'reason_not_safe': None,
            'source_reference': {'source-name': image_name}
        }
        if snapshot_id in cinder_ids:
            # Exclude snapshots already managed.
            snapshot_info['reason_not_safe'] = ('already managed')
            snapshot_info['cinder_id'] = snapshot_id
        elif snap_name.endswith('.clone_snap'):
            # Exclude clone snapshot.
            snapshot_info['reason_not_safe'] = ('used for clone snap')
        else:
            snapshot_info['safe_to_manage'] = True
        manageable_snapshots.append(snapshot_info)
    def get_manageable_snapshots(self, cinder_snapshots, marker, limit, offset, sort_keys, sort_dirs):
        """List manageable snapshots in Vitastor."""
        manageable_snapshots = []
        cinder_snapshot_ids = [resource['id'] for resource in cinder_snapshots]
        # List all volumes
        # FIXME: It's possible to use pagination in our case, but.. do we want it?
        self._etcd_foreach('config/inode/'+str(self.cfg['pool_id']),
            lambda kv: self._add_manageable_volume(kv, manageable_snapshots, cinder_snapshot_ids))
        return volume_utils.paginate_entries_list(
            manageable_snapshots, marker, limit, offset, sort_keys, sort_dirs)
    def manage_existing_snapshot_get_size(self, snapshot, existing_ref):
        """Return size of an existing image for manage_existing.
        :param snapshot: snapshot ref info to be set
        :param existing_ref: {'source-name': <name of snapshot>}
        """
        vol_name = utils.convert_str(snapshot.volume_name)
        snap_name = self._get_existing_name(existing_ref)
        vol = self._get_image(vol_name+'@'+snap_name)
        if not vol:
            raise exception.ManageExistingInvalidReference(
                existing_ref=snapshot_name, reason='Specified snapshot does not exist.'
            )
        return int(math.ceil(float(vol['cfg']['size']) / units.Gi))
    def manage_existing_snapshot(self, snapshot, existing_ref):
        """Manages an existing snapshot.
        Renames the snapshot name to match the expected name for the snapshot.
        Error checking done by manage_existing_get_size is not repeated.
        :param snapshot: snapshot ref info to be set
        :param existing_ref: {'source-name': <name of snapshot>}
        """
        vol_name = utils.convert_str(snapshot.volume_name)
        snap_name = self._get_existing_name(existing_ref)
        from_name = vol_name+'@'+snap_name
        to_name = vol_name+'@'+utils.convert_str(snapshot.name)
        self._rename(from_name, to_name)
    def unmanage_snapshot(self, snapshot):
        """Removes the specified snapshot from Cinder management."""
        pass
    def _dumps(self, obj):
        return json.dumps(obj, separators=(',', ':'), sort_keys=True)
--- a/patches/cinder-vitastor-21.py
+++ b/patches/cinder-vitastor-21.py
@ -50,7 +50,7 @@ from cinder.volume import configuration
 from cinder.volume import driver
 from cinder.volume import volume_utils
-VERSION = '1.6.1'
+VERSION = '1.4.6'
 LOG = logging.getLogger(__name__)
--- a/patches/libvirt-10.4-vitastor.diff
+++ b/patches/libvirt-10.4-vitastor.diff
@ -1,643 +0,0 @@
 commit 1f7e90e36b2afca0312392979b96d31951a8d66b
 Author: Vitaliy Filippov <vitalif@yourcmc.ru>
 Date:   Thu Jun 27 01:34:54 2024 +0300
    Add Vitastor support
 diff --git a/include/libvirt/libvirt-storage.h b/include/libvirt/libvirt-storage.h
 index aaad4a3da1..5f5daa8341 100644
 --- a/include/libvirt/libvirt-storage.h
 +++ b/include/libvirt/libvirt-storage.h
@@ -326,6 +326,7 @@ typedef enum {
     VIR_CONNECT_LIST_STORAGE_POOLS_ZFS           = 1 << 17, /* (Since: 1.2.8) */
     VIR_CONNECT_LIST_STORAGE_POOLS_VSTORAGE      = 1 << 18, /* (Since: 3.1.0) */
     VIR_CONNECT_LIST_STORAGE_POOLS_ISCSI_DIRECT  = 1 << 19, /* (Since: 5.6.0) */
 +    VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR      = 1 << 20, /* (Since: 5.0.0) */
 } virConnectListAllStoragePoolsFlags;
 int                     virConnectListAllStoragePools(virConnectPtr conn,
 diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c
 index fde594f811..66537db3e3 100644
 --- a/src/conf/domain_conf.c
 +++ b/src/conf/domain_conf.c
@@ -7220,7 +7220,8 @@ virDomainDiskSourceNetworkParse(xmlNodePtr node,
     src->configFile = virXPathString("string(./config/@file)", ctxt);
     if (src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTP ||
 -        src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTPS)
 +        src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTPS ||
 +        src->protocol == VIR_STORAGE_NET_PROTOCOL_VITASTOR)
         src->query = virXMLPropString(node, "query");
     if (virDomainStorageNetworkParseHosts(node, ctxt, &src->hosts, &src->nhosts) < 0)
@@ -30734,6 +30735,7 @@ virDomainStorageSourceTranslateSourcePool(virStorageSource *src,
     case VIR_STORAGE_POOL_MPATH:
     case VIR_STORAGE_POOL_RBD:
 +    case VIR_STORAGE_POOL_VITASTOR:
     case VIR_STORAGE_POOL_SHEEPDOG:
     case VIR_STORAGE_POOL_GLUSTER:
     case VIR_STORAGE_POOL_LAST:
 diff --git a/src/conf/domain_validate.c b/src/conf/domain_validate.c
 index 395e036e8f..8a0190f85b 100644
 --- a/src/conf/domain_validate.c
 +++ b/src/conf/domain_validate.c
@@ -495,6 +495,7 @@ virDomainDiskDefValidateSourceChainOne(const virStorageSource *src)
         case VIR_STORAGE_NET_PROTOCOL_RBD:
             break;
 +        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
         case VIR_STORAGE_NET_PROTOCOL_NBD:
         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
         case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
@@ -541,7 +542,7 @@ virDomainDiskDefValidateSourceChainOne(const virStorageSource *src)
         }
     }
 -    /* internal snapshots and config files are currently supported only with rbd: */
 +    /* internal snapshots are currently supported only with rbd: */
     if (virStorageSourceGetActualType(src) != VIR_STORAGE_TYPE_NETWORK &&
         src->protocol != VIR_STORAGE_NET_PROTOCOL_RBD) {
         if (src->snapshot) {
@@ -549,10 +550,15 @@ virDomainDiskDefValidateSourceChainOne(const virStorageSource *src)
                            _("<snapshot> element is currently supported only with 'rbd' disks"));
             return -1;
         }
 +    }
 +    /* config files are currently supported only with rbd and vitastor: */
 +    if (virStorageSourceGetActualType(src) != VIR_STORAGE_TYPE_NETWORK &&
 +        src->protocol != VIR_STORAGE_NET_PROTOCOL_RBD &&
 +        src->protocol != VIR_STORAGE_NET_PROTOCOL_VITASTOR) {
         if (src->configFile) {
             virReportError(VIR_ERR_XML_ERROR, "%s",
 -                           _("<config> element is currently supported only with 'rbd' disks"));
 +                           _("<config> element is currently supported only with 'rbd' and 'vitastor' disks"));
             return -1;
         }
     }
 diff --git a/src/conf/schemas/domaincommon.rng b/src/conf/schemas/domaincommon.rng
 index a46a824f88..4c5b720643 100644
 --- a/src/conf/schemas/domaincommon.rng
 +++ b/src/conf/schemas/domaincommon.rng
@@ -1997,6 +1997,35 @@
     </element>
   </define>
 +  <define name="diskSourceNetworkProtocolVitastor">
 +    <element name="source">
 +      <interleave>
 +        <attribute name="protocol">
 +          <value>vitastor</value>
 +        </attribute>
 +        <ref name="diskSourceCommon"/>
 +        <optional>
 +          <attribute name="name"/>
 +        </optional>
 +        <optional>
 +          <attribute name="query"/>
 +        </optional>
 +        <zeroOrMore>
 +          <ref name="diskSourceNetworkHost"/>
 +        </zeroOrMore>
 +        <optional>
 +          <element name="config">
 +            <attribute name="file">
 +              <ref name="absFilePath"/>
 +            </attribute>
 +            <empty/>
 +          </element>
 +        </optional>
 +        <empty/>
 +      </interleave>
 +    </element>
 +  </define>
 +
   <define name="diskSourceNetworkProtocolISCSI">
     <element name="source">
       <attribute name="protocol">
@@ -2347,6 +2376,7 @@
       <ref name="diskSourceNetworkProtocolSimple"/>
       <ref name="diskSourceNetworkProtocolVxHS"/>
       <ref name="diskSourceNetworkProtocolNFS"/>
 +      <ref name="diskSourceNetworkProtocolVitastor"/>
     </choice>
   </define>
 diff --git a/src/conf/storage_conf.c b/src/conf/storage_conf.c
 index 68842004b7..1d69a788b6 100644
 --- a/src/conf/storage_conf.c
 +++ b/src/conf/storage_conf.c
@@ -56,7 +56,7 @@ VIR_ENUM_IMPL(virStoragePool,
               "logical", "disk", "iscsi",
               "iscsi-direct", "scsi", "mpath",
               "rbd", "sheepdog", "gluster",
 -              "zfs", "vstorage",
 +              "zfs", "vstorage", "vitastor",
 );
 VIR_ENUM_IMPL(virStoragePoolFormatFileSystem,
@@ -242,6 +242,18 @@ static virStoragePoolTypeInfo poolTypeInfo[] = {
           .formatToString = virStorageFileFormatTypeToString,
       }
     },
 +    {.poolType = VIR_STORAGE_POOL_VITASTOR,
 +     .poolOptions = {
 +         .flags = (VIR_STORAGE_POOL_SOURCE_HOST |
 +                   VIR_STORAGE_POOL_SOURCE_NETWORK |
 +                   VIR_STORAGE_POOL_SOURCE_NAME),
 +      },
 +      .volOptions = {
 +          .defaultFormat = VIR_STORAGE_FILE_RAW,
 +          .formatFromString = virStorageVolumeFormatFromString,
 +          .formatToString = virStorageFileFormatTypeToString,
 +      }
 +    },
     {.poolType = VIR_STORAGE_POOL_SHEEPDOG,
      .poolOptions = {
          .flags = (VIR_STORAGE_POOL_SOURCE_HOST |
@@ -538,6 +550,11 @@ virStoragePoolDefParseSource(xmlXPathContextPtr ctxt,
                        _("element 'name' is mandatory for RBD pool"));
         return -1;
     }
 +    if (pool_type == VIR_STORAGE_POOL_VITASTOR && source->name == NULL) {
 +        virReportError(VIR_ERR_XML_ERROR, "%s",
 +                       _("element 'name' is mandatory for Vitastor pool"));
 +        return -1;
 +    }
     if (options->formatFromString) {
         g_autofree char *format = NULL;
@@ -1127,6 +1144,7 @@ virStoragePoolDefFormatBuf(virBuffer *buf,
     /* RBD, Sheepdog, Gluster and Iscsi-direct devices are not local block devs nor
      * files, so they don't have a target */
     if (def->type != VIR_STORAGE_POOL_RBD &&
 +        def->type != VIR_STORAGE_POOL_VITASTOR &&
         def->type != VIR_STORAGE_POOL_SHEEPDOG &&
         def->type != VIR_STORAGE_POOL_GLUSTER &&
         def->type != VIR_STORAGE_POOL_ISCSI_DIRECT) {
 diff --git a/src/conf/storage_conf.h b/src/conf/storage_conf.h
 index fc67957cfe..720c07ef74 100644
 --- a/src/conf/storage_conf.h
 +++ b/src/conf/storage_conf.h
@@ -103,6 +103,7 @@ typedef enum {
     VIR_STORAGE_POOL_GLUSTER,  /* Gluster device */
     VIR_STORAGE_POOL_ZFS,      /* ZFS */
     VIR_STORAGE_POOL_VSTORAGE, /* Virtuozzo Storage */
 +    VIR_STORAGE_POOL_VITASTOR, /* Vitastor */
     VIR_STORAGE_POOL_LAST,
 } virStoragePoolType;
@@ -454,6 +455,7 @@ VIR_ENUM_DECL(virStoragePartedFs);
                  VIR_CONNECT_LIST_STORAGE_POOLS_SCSI     | \
                  VIR_CONNECT_LIST_STORAGE_POOLS_MPATH    | \
                  VIR_CONNECT_LIST_STORAGE_POOLS_RBD      | \
 +                 VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR | \
                  VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG | \
                  VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER  | \
                  VIR_CONNECT_LIST_STORAGE_POOLS_ZFS      | \
 diff --git a/src/conf/storage_source_conf.c b/src/conf/storage_source_conf.c
 index 959ec5ed40..e751dd4d6a 100644
 --- a/src/conf/storage_source_conf.c
 +++ b/src/conf/storage_source_conf.c
@@ -88,6 +88,7 @@ VIR_ENUM_IMPL(virStorageNetProtocol,
               "ssh",
               "vxhs",
               "nfs",
 +              "vitastor",
 );
@@ -1301,6 +1302,7 @@ virStorageSourceNetworkDefaultPort(virStorageNetProtocol protocol)
         case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
             return 24007;
 +        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
         case VIR_STORAGE_NET_PROTOCOL_RBD:
             /* we don't provide a default for RBD */
             return 0;
 diff --git a/src/conf/storage_source_conf.h b/src/conf/storage_source_conf.h
 index 05b4bda16c..b5ed143c39 100644
 --- a/src/conf/storage_source_conf.h
 +++ b/src/conf/storage_source_conf.h
@@ -129,6 +129,7 @@ typedef enum {
     VIR_STORAGE_NET_PROTOCOL_SSH,
     VIR_STORAGE_NET_PROTOCOL_VXHS,
     VIR_STORAGE_NET_PROTOCOL_NFS,
 +    VIR_STORAGE_NET_PROTOCOL_VITASTOR,
     VIR_STORAGE_NET_PROTOCOL_LAST
 } virStorageNetProtocol;
 diff --git a/src/conf/virstorageobj.c b/src/conf/virstorageobj.c
 index 59fa5da372..4739167f5f 100644
 --- a/src/conf/virstorageobj.c
 +++ b/src/conf/virstorageobj.c
@@ -1438,6 +1438,7 @@ virStoragePoolObjSourceFindDuplicateCb(const void *payload,
             return 1;
         break;
 +    case VIR_STORAGE_POOL_VITASTOR:
     case VIR_STORAGE_POOL_ISCSI_DIRECT:
     case VIR_STORAGE_POOL_RBD:
     case VIR_STORAGE_POOL_LAST:
@@ -1921,6 +1922,8 @@ virStoragePoolObjMatch(virStoragePoolObj *obj,
                (obj->def->type == VIR_STORAGE_POOL_MPATH))   ||
               (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_RBD) &&
                (obj->def->type == VIR_STORAGE_POOL_RBD))     ||
 +              (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR) &&
 +               (obj->def->type == VIR_STORAGE_POOL_VITASTOR)) ||
               (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG) &&
                (obj->def->type == VIR_STORAGE_POOL_SHEEPDOG)) ||
               (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER) &&
 diff --git a/src/libvirt-storage.c b/src/libvirt-storage.c
 index db7660aac4..561df34709 100644
 --- a/src/libvirt-storage.c
 +++ b/src/libvirt-storage.c
@@ -94,6 +94,7 @@ virStoragePoolGetConnect(virStoragePoolPtr pool)
  * VIR_CONNECT_LIST_STORAGE_POOLS_SCSI
  * VIR_CONNECT_LIST_STORAGE_POOLS_MPATH
  * VIR_CONNECT_LIST_STORAGE_POOLS_RBD
 + * VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR
  * VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG
  * VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER
  * VIR_CONNECT_LIST_STORAGE_POOLS_ZFS
 diff --git a/src/libxl/libxl_conf.c b/src/libxl/libxl_conf.c
 index 62e1be6672..71a1d42896 100644
 --- a/src/libxl/libxl_conf.c
 +++ b/src/libxl/libxl_conf.c
@@ -979,6 +979,7 @@ libxlMakeNetworkDiskSrcStr(virStorageSource *src,
     case VIR_STORAGE_NET_PROTOCOL_SSH:
     case VIR_STORAGE_NET_PROTOCOL_VXHS:
     case VIR_STORAGE_NET_PROTOCOL_NFS:
 +    case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
     case VIR_STORAGE_NET_PROTOCOL_LAST:
     case VIR_STORAGE_NET_PROTOCOL_NONE:
         virReportError(VIR_ERR_NO_SUPPORT,
 diff --git a/src/libxl/xen_xl.c b/src/libxl/xen_xl.c
 index 53f6871efc..c34b8cee1a 100644
 --- a/src/libxl/xen_xl.c
 +++ b/src/libxl/xen_xl.c
@@ -1456,6 +1456,7 @@ xenFormatXLDiskSrcNet(virStorageSource *src)
     case VIR_STORAGE_NET_PROTOCOL_SSH:
     case VIR_STORAGE_NET_PROTOCOL_VXHS:
     case VIR_STORAGE_NET_PROTOCOL_NFS:
 +    case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
     case VIR_STORAGE_NET_PROTOCOL_LAST:
     case VIR_STORAGE_NET_PROTOCOL_NONE:
         virReportError(VIR_ERR_NO_SUPPORT,
 diff --git a/src/qemu/qemu_block.c b/src/qemu/qemu_block.c
 index 738b72d7ea..5dd082fc89 100644
 --- a/src/qemu/qemu_block.c
 +++ b/src/qemu/qemu_block.c
@@ -758,6 +758,38 @@ qemuBlockStorageSourceGetRBDProps(virStorageSource *src,
 }
 +static virJSONValue *
 +qemuBlockStorageSourceGetVitastorProps(virStorageSource *src)
 +{
 +    virJSONValue *ret = NULL;
 +    virStorageNetHostDef *host;
 +    size_t i;
 +    g_auto(virBuffer) buf = VIR_BUFFER_INITIALIZER;
 +    g_autofree char *etcd = NULL;
 +
 +    for (i = 0; i < src->nhosts; i++) {
 +        host = src->hosts + i;
 +        if ((virStorageNetHostTransport)host->transport != VIR_STORAGE_NET_HOST_TRANS_TCP) {
 +            return NULL;
 +        }
 +        virBufferAsprintf(&buf, i > 0 ? ",%s:%u" : "%s:%u", host->name, host->port);
 +    }
 +    if (src->nhosts > 0) {
 +        etcd = virBufferContentAndReset(&buf);
 +    }
 +
 +    if (virJSONValueObjectAdd(&ret,
 +                              "S:etcd-host", etcd,
 +                              "S:etcd-prefix", src->query,
 +                              "S:config-path", src->configFile,
 +                              "s:image", src->path,
 +                              NULL) < 0)
 +        return NULL;
 +
 +    return ret;
 +}
 +
 +
 static virJSONValue *
 qemuBlockStorageSourceGetSheepdogProps(virStorageSource *src)
 {
@@ -1140,6 +1172,12 @@ qemuBlockStorageSourceGetBackendProps(virStorageSource *src,
                 return NULL;
             break;
 +        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
 +            driver = "vitastor";
 +            if (!(fileprops = qemuBlockStorageSourceGetVitastorProps(src)))
 +                return NULL;
 +            break;
 +
         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
             driver = "sheepdog";
             if (!(fileprops = qemuBlockStorageSourceGetSheepdogProps(src)))
@@ -2020,6 +2058,7 @@ qemuBlockGetBackingStoreString(virStorageSource *src,
             case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
             case VIR_STORAGE_NET_PROTOCOL_RBD:
 +            case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
             case VIR_STORAGE_NET_PROTOCOL_VXHS:
             case VIR_STORAGE_NET_PROTOCOL_NFS:
             case VIR_STORAGE_NET_PROTOCOL_SSH:
@@ -2400,6 +2439,12 @@ qemuBlockStorageSourceCreateGetStorageProps(virStorageSource *src,
                 return -1;
             break;
 +        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
 +            driver = "vitastor";
 +            if (!(location = qemuBlockStorageSourceGetVitastorProps(src)))
 +                return -1;
 +            break;
 +
         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
             driver = "sheepdog";
             if (!(location = qemuBlockStorageSourceGetSheepdogProps(src)))
 diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c
 index bda62f2e5c..84b4e5f2b8 100644
 --- a/src/qemu/qemu_domain.c
 +++ b/src/qemu/qemu_domain.c
@@ -5260,7 +5260,8 @@ qemuDomainValidateStorageSource(virStorageSource *src,
     if (src->query &&
         (actualType != VIR_STORAGE_TYPE_NETWORK ||
          (src->protocol != VIR_STORAGE_NET_PROTOCOL_HTTPS &&
 -          src->protocol != VIR_STORAGE_NET_PROTOCOL_HTTP))) {
 +          src->protocol != VIR_STORAGE_NET_PROTOCOL_HTTP &&
 +          src->protocol != VIR_STORAGE_NET_PROTOCOL_VITASTOR))) {
         virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
                        _("query is supported only with HTTP(S) protocols"));
         return -1;
@@ -10514,6 +10515,7 @@ qemuDomainPrepareStorageSourceTLS(virStorageSource *src,
         break;
     case VIR_STORAGE_NET_PROTOCOL_RBD:
 +    case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
     case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
     case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
     case VIR_STORAGE_NET_PROTOCOL_ISCSI:
 diff --git a/src/qemu/qemu_snapshot.c b/src/qemu/qemu_snapshot.c
 index f5260c4a22..2f9d8406fe 100644
 --- a/src/qemu/qemu_snapshot.c
 +++ b/src/qemu/qemu_snapshot.c
@@ -423,6 +423,7 @@ qemuSnapshotPrepareDiskExternalInactive(virDomainSnapshotDiskDef *snapdisk,
         case VIR_STORAGE_NET_PROTOCOL_NONE:
         case VIR_STORAGE_NET_PROTOCOL_NBD:
         case VIR_STORAGE_NET_PROTOCOL_RBD:
 +        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
         case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
         case VIR_STORAGE_NET_PROTOCOL_ISCSI:
@@ -648,6 +649,7 @@ qemuSnapshotPrepareDiskInternal(virDomainDiskDef *disk,
         case VIR_STORAGE_NET_PROTOCOL_NONE:
         case VIR_STORAGE_NET_PROTOCOL_NBD:
         case VIR_STORAGE_NET_PROTOCOL_RBD:
 +        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
         case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
         case VIR_STORAGE_NET_PROTOCOL_ISCSI:
 diff --git a/src/storage/storage_driver.c b/src/storage/storage_driver.c
 index 86c03762d2..630c6eff1a 100644
 --- a/src/storage/storage_driver.c
 +++ b/src/storage/storage_driver.c
@@ -1626,6 +1626,7 @@ storageVolLookupByPathCallback(virStoragePoolObj *obj,
         case VIR_STORAGE_POOL_GLUSTER:
         case VIR_STORAGE_POOL_RBD:
 +        case VIR_STORAGE_POOL_VITASTOR:
         case VIR_STORAGE_POOL_SHEEPDOG:
         case VIR_STORAGE_POOL_ZFS:
         case VIR_STORAGE_POOL_LAST:
 diff --git a/src/storage_file/storage_source_backingstore.c b/src/storage_file/storage_source_backingstore.c
 index 80681924ea..8a3ade9ec0 100644
 --- a/src/storage_file/storage_source_backingstore.c
 +++ b/src/storage_file/storage_source_backingstore.c
@@ -287,6 +287,75 @@ virStorageSourceParseRBDColonString(const char *rbdstr,
 }
 +static int
 +virStorageSourceParseVitastorColonString(const char *colonstr,
 +                                         virStorageSource *src)
 +{
 +    char *p, *e, *next;
 +    g_autofree char *options = NULL;
 +
 +    /* optionally skip the "vitastor:" prefix if provided */
 +    if (STRPREFIX(colonstr, "vitastor:"))
 +        colonstr += strlen("vitastor:");
 +
 +    options = g_strdup(colonstr);
 +
 +    p = options;
 +    while (*p) {
 +        /* find : delimiter or end of string */
 +        for (e = p; *e && *e != ':'; ++e) {
 +            if (*e == '\\') {
 +                e++;
 +                if (*e == '\0')
 +                    break;
 +            }
 +        }
 +        if (*e == '\0') {
 +            next = e;    /* last kv pair */
 +        } else {
 +            next = e + 1;
 +            *e = '\0';
 +        }
 +
 +        if (STRPREFIX(p, "image=")) {
 +            src->path = g_strdup(p + strlen("image="));
 +        } else if (STRPREFIX(p, "etcd-prefix=")) {
 +            src->query = g_strdup(p + strlen("etcd-prefix="));
 +        } else if (STRPREFIX(p, "config-path=")) {
 +            src->configFile = g_strdup(p + strlen("config-path="));
 +        } else if (STRPREFIX(p, "etcd-host=")) {
 +            char *h, *sep;
 +
 +            h = p + strlen("etcd-host=");
 +            while (h < e) {
 +                for (sep = h; sep < e; ++sep) {
 +                    if (*sep == '\\' && (sep[1] == ',' ||
 +                                         sep[1] == ';' ||
 +                                         sep[1] == ' ')) {
 +                        *sep = '\0';
 +                        sep += 2;
 +                        break;
 +                    }
 +                }
 +
 +                if (virStorageSourceRBDAddHost(src, h) < 0)
 +                    return -1;
 +
 +                h = sep;
 +            }
 +        }
 +
 +        p = next;
 +    }
 +
 +    if (!src->path) {
 +        return -1;
 +    }
 +
 +    return 0;
 +}
 +
 +
 static int
 virStorageSourceParseNBDColonString(const char *nbdstr,
                                     virStorageSource *src)
@@ -399,6 +468,11 @@ virStorageSourceParseBackingColon(virStorageSource *src,
             return -1;
         break;
 +    case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
 +        if (virStorageSourceParseVitastorColonString(path, src) < 0)
 +            return -1;
 +        break;
 +
     case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
     case VIR_STORAGE_NET_PROTOCOL_LAST:
     case VIR_STORAGE_NET_PROTOCOL_NONE:
@@ -975,6 +1049,54 @@ virStorageSourceParseBackingJSONRBD(virStorageSource *src,
     return 0;
 }
 +static int
 +virStorageSourceParseBackingJSONVitastor(virStorageSource *src,
 +                                         virJSONValue *json,
 +                                         const char *jsonstr G_GNUC_UNUSED,
 +                                         int opaque G_GNUC_UNUSED)
 +{
 +    const char *filename;
 +    const char *image = virJSONValueObjectGetString(json, "image");
 +    const char *conf = virJSONValueObjectGetString(json, "config-path");
 +    const char *etcd_prefix = virJSONValueObjectGetString(json, "etcd-prefix");
 +    virJSONValue *servers = virJSONValueObjectGetArray(json, "server");
 +    size_t nservers;
 +    size_t i;
 +
 +    src->type = VIR_STORAGE_TYPE_NETWORK;
 +    src->protocol = VIR_STORAGE_NET_PROTOCOL_VITASTOR;
 +
 +    /* legacy syntax passed via 'filename' option */
 +    if ((filename = virJSONValueObjectGetString(json, "filename")))
 +        return virStorageSourceParseVitastorColonString(filename, src);
 +
 +    if (!image) {
 +        virReportError(VIR_ERR_INVALID_ARG, "%s",
 +                       _("missing image name in Vitastor backing volume "
 +                         "JSON specification"));
 +        return -1;
 +    }
 +
 +    src->path = g_strdup(image);
 +    src->configFile = g_strdup(conf);
 +    src->query = g_strdup(etcd_prefix);
 +
 +    if (servers) {
 +        nservers = virJSONValueArraySize(servers);
 +
 +        src->hosts = g_new0(virStorageNetHostDef, nservers);
 +        src->nhosts = nservers;
 +
 +        for (i = 0; i < nservers; i++) {
 +            if (virStorageSourceParseBackingJSONInetSocketAddress(src->hosts + i,
 +                                                                  virJSONValueArrayGet(servers, i)) < 0)
 +                return -1;
 +        }
 +    }
 +
 +    return 0;
 +}
 +
 static int
 virStorageSourceParseBackingJSONRaw(virStorageSource *src,
                                     virJSONValue *json,
@@ -1152,6 +1274,7 @@ static const struct virStorageSourceJSONDriverParser jsonParsers[] = {
     {"sheepdog", false, virStorageSourceParseBackingJSONSheepdog, 0},
     {"ssh", false, virStorageSourceParseBackingJSONSSH, 0},
     {"rbd", false, virStorageSourceParseBackingJSONRBD, 0},
 +    {"vitastor", false, virStorageSourceParseBackingJSONVitastor, 0},
     {"raw", true, virStorageSourceParseBackingJSONRaw, 0},
     {"nfs", false, virStorageSourceParseBackingJSONNFS, 0},
     {"vxhs", false, virStorageSourceParseBackingJSONVxHS, 0},
 diff --git a/src/test/test_driver.c b/src/test/test_driver.c
 index d2d1bc43e3..31a92e4a01 100644
 --- a/src/test/test_driver.c
 +++ b/src/test/test_driver.c
@@ -7339,6 +7339,7 @@ testStorageVolumeTypeForPool(int pooltype)
     case VIR_STORAGE_POOL_ISCSI_DIRECT:
     case VIR_STORAGE_POOL_GLUSTER:
     case VIR_STORAGE_POOL_RBD:
 +    case VIR_STORAGE_POOL_VITASTOR:
         return VIR_STORAGE_VOL_NETWORK;
     case VIR_STORAGE_POOL_LOGICAL:
     case VIR_STORAGE_POOL_DISK:
 diff --git a/tests/storagepoolcapsschemadata/poolcaps-fs.xml b/tests/storagepoolcapsschemadata/poolcaps-fs.xml
 index eee75af746..8bd0a57bdd 100644
 --- a/tests/storagepoolcapsschemadata/poolcaps-fs.xml
 +++ b/tests/storagepoolcapsschemadata/poolcaps-fs.xml
@@ -204,4 +204,11 @@
       </enum>
     </volOptions>
   </pool>
 +  <pool type='vitastor' supported='no'>
 +    <volOptions>
 +      <defaultFormat type='raw'/>
 +      <enum name='targetFormatType'>
 +      </enum>
 +    </volOptions>
 +  </pool>
 </storagepoolCapabilities>
 diff --git a/tests/storagepoolcapsschemadata/poolcaps-full.xml b/tests/storagepoolcapsschemadata/poolcaps-full.xml
 index 805950a937..852df0de16 100644
 --- a/tests/storagepoolcapsschemadata/poolcaps-full.xml
 +++ b/tests/storagepoolcapsschemadata/poolcaps-full.xml
@@ -204,4 +204,11 @@
       </enum>
     </volOptions>
   </pool>
 +  <pool type='vitastor' supported='yes'>
 +    <volOptions>
 +      <defaultFormat type='raw'/>
 +      <enum name='targetFormatType'>
 +      </enum>
 +    </volOptions>
 +  </pool>
 </storagepoolCapabilities>
 diff --git a/tests/storagepoolxml2argvtest.c b/tests/storagepoolxml2argvtest.c
 index e8e40d695e..db55fe5f3a 100644
 --- a/tests/storagepoolxml2argvtest.c
 +++ b/tests/storagepoolxml2argvtest.c
@@ -65,6 +65,7 @@ testCompareXMLToArgvFiles(bool shouldFail,
     case VIR_STORAGE_POOL_GLUSTER:
     case VIR_STORAGE_POOL_ZFS:
     case VIR_STORAGE_POOL_VSTORAGE:
 +    case VIR_STORAGE_POOL_VITASTOR:
     case VIR_STORAGE_POOL_LAST:
     default:
         VIR_TEST_DEBUG("pool type '%s' has no xml2argv test", defTypeStr);
 diff --git a/tools/virsh-pool.c b/tools/virsh-pool.c
 index f9aad8ded0..64704b4288 100644
 --- a/tools/virsh-pool.c
 +++ b/tools/virsh-pool.c
@@ -1187,6 +1187,9 @@ cmdPoolList(vshControl *ctl, const vshCmd *cmd G_GNUC_UNUSED)
             case VIR_STORAGE_POOL_VSTORAGE:
                 flags |= VIR_CONNECT_LIST_STORAGE_POOLS_VSTORAGE;
                 break;
 +            case VIR_STORAGE_POOL_VITASTOR:
 +                flags |= VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR;
 +                break;
             case VIR_STORAGE_POOL_LAST:
                 break;
             }
--- a/patches/libvirt-8.0-vitastor.diff
+++ b/patches/libvirt-8.0-vitastor.diff
@ -1,692 +0,0 @@
 commit d85024bd803b3b91f15578ed22de4ce31856626f
 Author: Vitaliy Filippov <vitalif@yourcmc.ru>
 Date:   Wed Jan 24 18:07:43 2024 +0300
    Add Vitastor support
 diff --git a/docs/schemas/domaincommon.rng b/docs/schemas/domaincommon.rng
 index 7fa5c2b8b5..2d77f391e7 100644
 --- a/docs/schemas/domaincommon.rng
 +++ b/docs/schemas/domaincommon.rng
@@ -1898,6 +1898,35 @@
     </element>
   </define>
 +  <define name="diskSourceNetworkProtocolVitastor">
 +    <element name="source">
 +      <interleave>
 +        <attribute name="protocol">
 +          <value>vitastor</value>
 +        </attribute>
 +        <ref name="diskSourceCommon"/>
 +        <optional>
 +          <attribute name="name"/>
 +        </optional>
 +        <optional>
 +          <attribute name="query"/>
 +        </optional>
 +        <zeroOrMore>
 +          <ref name="diskSourceNetworkHost"/>
 +        </zeroOrMore>
 +        <optional>
 +          <element name="config">
 +            <attribute name="file">
 +              <ref name="absFilePath"/>
 +            </attribute>
 +            <empty/>
 +          </element>
 +        </optional>
 +        <empty/>
 +      </interleave>
 +    </element>
 +  </define>
 +
   <define name="diskSourceNetworkProtocolISCSI">
     <element name="source">
       <attribute name="protocol">
@@ -2154,6 +2183,7 @@
       <ref name="diskSourceNetworkProtocolSimple"/>
       <ref name="diskSourceNetworkProtocolVxHS"/>
       <ref name="diskSourceNetworkProtocolNFS"/>
 +      <ref name="diskSourceNetworkProtocolVitastor"/>
     </choice>
   </define>
 diff --git a/include/libvirt/libvirt-storage.h b/include/libvirt/libvirt-storage.h
 index f89856b93e..a8cb9387e2 100644
 --- a/include/libvirt/libvirt-storage.h
 +++ b/include/libvirt/libvirt-storage.h
@@ -246,6 +246,7 @@ typedef enum {
     VIR_CONNECT_LIST_STORAGE_POOLS_ZFS           = 1 << 17,
     VIR_CONNECT_LIST_STORAGE_POOLS_VSTORAGE      = 1 << 18,
     VIR_CONNECT_LIST_STORAGE_POOLS_ISCSI_DIRECT  = 1 << 19,
 +    VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR      = 1 << 20,
 } virConnectListAllStoragePoolsFlags;
 int                     virConnectListAllStoragePools(virConnectPtr conn,
 diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c
 index 5691b8d2d5..6669e8451d 100644
 --- a/src/conf/domain_conf.c
 +++ b/src/conf/domain_conf.c
@@ -8293,7 +8293,8 @@ virDomainDiskSourceNetworkParse(xmlNodePtr node,
     src->configFile = virXPathString("string(./config/@file)", ctxt);
     if (src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTP ||
 -        src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTPS)
 +        src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTPS ||
 +        src->protocol == VIR_STORAGE_NET_PROTOCOL_VITASTOR)
         src->query = virXMLPropString(node, "query");
     if (virDomainStorageNetworkParseHosts(node, ctxt, &src->hosts, &src->nhosts) < 0)
@@ -31267,6 +31268,7 @@ virDomainStorageSourceTranslateSourcePool(virStorageSource *src,
     case VIR_STORAGE_POOL_MPATH:
     case VIR_STORAGE_POOL_RBD:
 +    case VIR_STORAGE_POOL_VITASTOR:
     case VIR_STORAGE_POOL_SHEEPDOG:
     case VIR_STORAGE_POOL_GLUSTER:
     case VIR_STORAGE_POOL_LAST:
 diff --git a/src/conf/domain_validate.c b/src/conf/domain_validate.c
 index a4271f1247..621c1b7b31 100644
 --- a/src/conf/domain_validate.c
 +++ b/src/conf/domain_validate.c
@@ -508,7 +508,7 @@ virDomainDiskDefValidateSourceChainOne(const virStorageSource *src)
         }
     }
 -    /* internal snapshots and config files are currently supported only with rbd: */
 +    /* internal snapshots are currently supported only with rbd: */
     if (virStorageSourceGetActualType(src) != VIR_STORAGE_TYPE_NETWORK &&
         src->protocol != VIR_STORAGE_NET_PROTOCOL_RBD) {
         if (src->snapshot) {
@@ -517,11 +517,15 @@ virDomainDiskDefValidateSourceChainOne(const virStorageSource *src)
                              "only with 'rbd' disks"));
             return -1;
         }
 -
 +    }
 +    /* config files are currently supported only with rbd and vitastor: */
 +    if (virStorageSourceGetActualType(src) != VIR_STORAGE_TYPE_NETWORK &&
 +        src->protocol != VIR_STORAGE_NET_PROTOCOL_RBD &&
 +        src->protocol != VIR_STORAGE_NET_PROTOCOL_VITASTOR) {
         if (src->configFile) {
             virReportError(VIR_ERR_XML_ERROR, "%s",
                            _("<config> element is currently supported "
 -                             "only with 'rbd' disks"));
 +                             "only with 'rbd' and 'vitastor' disks"));
             return -1;
         }
     }
 diff --git a/src/conf/storage_conf.c b/src/conf/storage_conf.c
 index 6690d26ffd..2255df9d28 100644
 --- a/src/conf/storage_conf.c
 +++ b/src/conf/storage_conf.c
@@ -60,7 +60,7 @@ VIR_ENUM_IMPL(virStoragePool,
               "logical", "disk", "iscsi",
               "iscsi-direct", "scsi", "mpath",
               "rbd", "sheepdog", "gluster",
 -              "zfs", "vstorage",
 +              "zfs", "vstorage", "vitastor",
 );
 VIR_ENUM_IMPL(virStoragePoolFormatFileSystem,
@@ -246,6 +246,18 @@ static virStoragePoolTypeInfo poolTypeInfo[] = {
           .formatToString = virStorageFileFormatTypeToString,
       }
     },
 +    {.poolType = VIR_STORAGE_POOL_VITASTOR,
 +     .poolOptions = {
 +         .flags = (VIR_STORAGE_POOL_SOURCE_HOST |
 +                   VIR_STORAGE_POOL_SOURCE_NETWORK |
 +                   VIR_STORAGE_POOL_SOURCE_NAME),
 +      },
 +      .volOptions = {
 +          .defaultFormat = VIR_STORAGE_FILE_RAW,
 +          .formatFromString = virStorageVolumeFormatFromString,
 +          .formatToString = virStorageFileFormatTypeToString,
 +      }
 +    },
     {.poolType = VIR_STORAGE_POOL_SHEEPDOG,
      .poolOptions = {
          .flags = (VIR_STORAGE_POOL_SOURCE_HOST |
@@ -546,6 +558,11 @@ virStoragePoolDefParseSource(xmlXPathContextPtr ctxt,
                        _("element 'name' is mandatory for RBD pool"));
         return -1;
     }
 +    if (pool_type == VIR_STORAGE_POOL_VITASTOR && source->name == NULL) {
 +        virReportError(VIR_ERR_XML_ERROR, "%s",
 +                       _("element 'name' is mandatory for Vitastor pool"));
 +        return -1;
 +    }
     if (options->formatFromString) {
         g_autofree char *format = NULL;
@@ -1176,6 +1193,7 @@ virStoragePoolDefFormatBuf(virBuffer *buf,
     /* RBD, Sheepdog, Gluster and Iscsi-direct devices are not local block devs nor
      * files, so they don't have a target */
     if (def->type != VIR_STORAGE_POOL_RBD &&
 +        def->type != VIR_STORAGE_POOL_VITASTOR &&
         def->type != VIR_STORAGE_POOL_SHEEPDOG &&
         def->type != VIR_STORAGE_POOL_GLUSTER &&
         def->type != VIR_STORAGE_POOL_ISCSI_DIRECT) {
 diff --git a/src/conf/storage_conf.h b/src/conf/storage_conf.h
 index aaecf138d6..97172db38b 100644
 --- a/src/conf/storage_conf.h
 +++ b/src/conf/storage_conf.h
@@ -106,6 +106,7 @@ typedef enum {
     VIR_STORAGE_POOL_GLUSTER,  /* Gluster device */
     VIR_STORAGE_POOL_ZFS,      /* ZFS */
     VIR_STORAGE_POOL_VSTORAGE, /* Virtuozzo Storage */
 +    VIR_STORAGE_POOL_VITASTOR, /* Vitastor */
     VIR_STORAGE_POOL_LAST,
 } virStoragePoolType;
@@ -466,6 +467,7 @@ VIR_ENUM_DECL(virStoragePartedFs);
                  VIR_CONNECT_LIST_STORAGE_POOLS_SCSI     | \
                  VIR_CONNECT_LIST_STORAGE_POOLS_MPATH    | \
                  VIR_CONNECT_LIST_STORAGE_POOLS_RBD      | \
 +                 VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR | \
                  VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG | \
                  VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER  | \
                  VIR_CONNECT_LIST_STORAGE_POOLS_ZFS      | \
 diff --git a/src/conf/storage_source_conf.c b/src/conf/storage_source_conf.c
 index d42f715f26..29d8da3d10 100644
 --- a/src/conf/storage_source_conf.c
 +++ b/src/conf/storage_source_conf.c
@@ -86,6 +86,7 @@ VIR_ENUM_IMPL(virStorageNetProtocol,
               "ssh",
               "vxhs",
               "nfs",
 +              "vitastor",
 );
@@ -1265,6 +1266,7 @@ virStorageSourceNetworkDefaultPort(virStorageNetProtocol protocol)
         case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
             return 24007;
 +        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
         case VIR_STORAGE_NET_PROTOCOL_RBD:
             /* we don't provide a default for RBD */
             return 0;
 diff --git a/src/conf/storage_source_conf.h b/src/conf/storage_source_conf.h
 index c4a026881c..67568e9181 100644
 --- a/src/conf/storage_source_conf.h
 +++ b/src/conf/storage_source_conf.h
@@ -128,6 +128,7 @@ typedef enum {
     VIR_STORAGE_NET_PROTOCOL_SSH,
     VIR_STORAGE_NET_PROTOCOL_VXHS,
     VIR_STORAGE_NET_PROTOCOL_NFS,
 +    VIR_STORAGE_NET_PROTOCOL_VITASTOR,
     VIR_STORAGE_NET_PROTOCOL_LAST
 } virStorageNetProtocol;
 diff --git a/src/conf/virstorageobj.c b/src/conf/virstorageobj.c
 index 02903ac487..504df599fb 100644
 --- a/src/conf/virstorageobj.c
 +++ b/src/conf/virstorageobj.c
@@ -1481,6 +1481,7 @@ virStoragePoolObjSourceFindDuplicateCb(const void *payload,
             return 1;
         break;
 +    case VIR_STORAGE_POOL_VITASTOR:
     case VIR_STORAGE_POOL_RBD:
     case VIR_STORAGE_POOL_LAST:
         break;
@@ -1978,6 +1979,8 @@ virStoragePoolObjMatch(virStoragePoolObj *obj,
                (obj->def->type == VIR_STORAGE_POOL_MPATH))   ||
               (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_RBD) &&
                (obj->def->type == VIR_STORAGE_POOL_RBD))     ||
 +              (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR) &&
 +               (obj->def->type == VIR_STORAGE_POOL_VITASTOR)) ||
               (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG) &&
                (obj->def->type == VIR_STORAGE_POOL_SHEEPDOG)) ||
               (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER) &&
 diff --git a/src/libvirt-storage.c b/src/libvirt-storage.c
 index cbc522b300..b4760fa58d 100644
 --- a/src/libvirt-storage.c
 +++ b/src/libvirt-storage.c
@@ -92,6 +92,7 @@ virStoragePoolGetConnect(virStoragePoolPtr pool)
  * VIR_CONNECT_LIST_STORAGE_POOLS_SCSI
  * VIR_CONNECT_LIST_STORAGE_POOLS_MPATH
  * VIR_CONNECT_LIST_STORAGE_POOLS_RBD
 + * VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR
  * VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG
  * VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER
  * VIR_CONNECT_LIST_STORAGE_POOLS_ZFS
 diff --git a/src/libxl/libxl_conf.c b/src/libxl/libxl_conf.c
 index 1ac6253ad7..abe4587f94 100644
 --- a/src/libxl/libxl_conf.c
 +++ b/src/libxl/libxl_conf.c
@@ -962,6 +962,7 @@ libxlMakeNetworkDiskSrcStr(virStorageSource *src,
     case VIR_STORAGE_NET_PROTOCOL_SSH:
     case VIR_STORAGE_NET_PROTOCOL_VXHS:
     case VIR_STORAGE_NET_PROTOCOL_NFS:
 +    case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
     case VIR_STORAGE_NET_PROTOCOL_LAST:
     case VIR_STORAGE_NET_PROTOCOL_NONE:
         virReportError(VIR_ERR_NO_SUPPORT,
 diff --git a/src/libxl/xen_xl.c b/src/libxl/xen_xl.c
 index 7604e3d534..6453bb9776 100644
 --- a/src/libxl/xen_xl.c
 +++ b/src/libxl/xen_xl.c
@@ -1506,6 +1506,7 @@ xenFormatXLDiskSrcNet(virStorageSource *src)
     case VIR_STORAGE_NET_PROTOCOL_SSH:
     case VIR_STORAGE_NET_PROTOCOL_VXHS:
     case VIR_STORAGE_NET_PROTOCOL_NFS:
 +    case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
     case VIR_STORAGE_NET_PROTOCOL_LAST:
     case VIR_STORAGE_NET_PROTOCOL_NONE:
         virReportError(VIR_ERR_NO_SUPPORT,
 diff --git a/src/qemu/qemu_block.c b/src/qemu/qemu_block.c
 index e5ff653a60..884ecc79ea 100644
 --- a/src/qemu/qemu_block.c
 +++ b/src/qemu/qemu_block.c
@@ -943,6 +943,38 @@ qemuBlockStorageSourceGetRBDProps(virStorageSource *src,
 }
 +static virJSONValue *
 +qemuBlockStorageSourceGetVitastorProps(virStorageSource *src)
 +{
 +    virJSONValue *ret = NULL;
 +    virStorageNetHostDef *host;
 +    size_t i;
 +    g_auto(virBuffer) buf = VIR_BUFFER_INITIALIZER;
 +    g_autofree char *etcd = NULL;
 +
 +    for (i = 0; i < src->nhosts; i++) {
 +        host = src->hosts + i;
 +        if ((virStorageNetHostTransport)host->transport != VIR_STORAGE_NET_HOST_TRANS_TCP) {
 +            return NULL;
 +        }
 +        virBufferAsprintf(&buf, i > 0 ? ",%s:%u" : "%s:%u", host->name, host->port);
 +    }
 +    if (src->nhosts > 0) {
 +        etcd = virBufferContentAndReset(&buf);
 +    }
 +
 +    if (virJSONValueObjectCreate(&ret,
 +                                 "S:etcd-host", etcd,
 +                                 "S:etcd-prefix", src->query,
 +                                 "S:config-path", src->configFile,
 +                                 "s:image", src->path,
 +                                 NULL) < 0)
 +        return NULL;
 +
 +    return ret;
 +}
 +
 +
 static virJSONValue *
 qemuBlockStorageSourceGetSheepdogProps(virStorageSource *src)
 {
@@ -1233,6 +1265,12 @@ qemuBlockStorageSourceGetBackendProps(virStorageSource *src,
                 return NULL;
             break;
 +        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
 +            driver = "vitastor";
 +            if (!(fileprops = qemuBlockStorageSourceGetVitastorProps(src)))
 +                return NULL;
 +            break;
 +
         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
             driver = "sheepdog";
             if (!(fileprops = qemuBlockStorageSourceGetSheepdogProps(src)))
@@ -2244,6 +2282,7 @@ qemuBlockGetBackingStoreString(virStorageSource *src,
             case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
             case VIR_STORAGE_NET_PROTOCOL_RBD:
 +            case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
             case VIR_STORAGE_NET_PROTOCOL_VXHS:
             case VIR_STORAGE_NET_PROTOCOL_NFS:
             case VIR_STORAGE_NET_PROTOCOL_SSH:
@@ -2626,6 +2665,12 @@ qemuBlockStorageSourceCreateGetStorageProps(virStorageSource *src,
                 return -1;
             break;
 +        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
 +            driver = "vitastor";
 +            if (!(location = qemuBlockStorageSourceGetVitastorProps(src)))
 +                return -1;
 +            break;
 +
         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
             driver = "sheepdog";
             if (!(location = qemuBlockStorageSourceGetSheepdogProps(src)))
 diff --git a/src/qemu/qemu_command.c b/src/qemu/qemu_command.c
 index d822533ccb..afe2087303 100644
 --- a/src/qemu/qemu_command.c
 +++ b/src/qemu/qemu_command.c
@@ -1723,6 +1723,43 @@ qemuBuildNetworkDriveStr(virStorageSource *src,
             ret = virBufferContentAndReset(&buf);
             break;
 +        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
 +            if (strchr(src->path, ':')) {
 +                virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
 +                               _("':' not allowed in Vitastor source volume name '%s'"),
 +                               src->path);
 +                return NULL;
 +            }
 +
 +            virBufferStrcat(&buf, "vitastor:image=", src->path, NULL);
 +
 +            if (src->nhosts > 0) {
 +                virBufferAddLit(&buf, ":etcd-host=");
 +                for (i = 0; i < src->nhosts; i++) {
 +                    if (i)
 +                        virBufferAddLit(&buf, ",");
 +
 +                    /* assume host containing : is ipv6 */
 +                    if (strchr(src->hosts[i].name, ':'))
 +                        virBufferEscape(&buf, '\\', ":", "[%s]",
 +                                        src->hosts[i].name);
 +                    else
 +                        virBufferAsprintf(&buf, "%s", src->hosts[i].name);
 +
 +                    if (src->hosts[i].port)
 +                        virBufferAsprintf(&buf, "\\:%u", src->hosts[i].port);
 +                }
 +            }
 +
 +            if (src->configFile)
 +                virBufferEscape(&buf, '\\', ":", ":config-path=%s", src->configFile);
 +
 +            if (src->query)
 +                virBufferEscape(&buf, '\\', ":", ":etcd-prefix=%s", src->query);
 +
 +            ret = virBufferContentAndReset(&buf);
 +            break;
 +
         case VIR_STORAGE_NET_PROTOCOL_VXHS:
             virReportError(VIR_ERR_INTERNAL_ERROR, "%s",
                            _("VxHS protocol does not support URI syntax"));
 diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c
 index a8401bac30..3dc1fe6db0 100644
 --- a/src/qemu/qemu_domain.c
 +++ b/src/qemu/qemu_domain.c
@@ -4731,7 +4731,8 @@ qemuDomainValidateStorageSource(virStorageSource *src,
     if (src->query &&
         (actualType != VIR_STORAGE_TYPE_NETWORK ||
          (src->protocol != VIR_STORAGE_NET_PROTOCOL_HTTPS &&
 -          src->protocol != VIR_STORAGE_NET_PROTOCOL_HTTP))) {
 +          src->protocol != VIR_STORAGE_NET_PROTOCOL_HTTP &&
 +          src->protocol != VIR_STORAGE_NET_PROTOCOL_VITASTOR))) {
         virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
                        _("query is supported only with HTTP(S) protocols"));
         return -1;
@@ -9919,6 +9920,7 @@ qemuDomainPrepareStorageSourceTLS(virStorageSource *src,
         break;
     case VIR_STORAGE_NET_PROTOCOL_RBD:
 +    case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
     case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
     case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
     case VIR_STORAGE_NET_PROTOCOL_ISCSI:
 diff --git a/src/qemu/qemu_snapshot.c b/src/qemu/qemu_snapshot.c
 index f92e00f9c0..854a3fbc90 100644
 --- a/src/qemu/qemu_snapshot.c
 +++ b/src/qemu/qemu_snapshot.c
@@ -393,6 +393,7 @@ qemuSnapshotPrepareDiskExternalInactive(virDomainSnapshotDiskDef *snapdisk,
         case VIR_STORAGE_NET_PROTOCOL_NONE:
         case VIR_STORAGE_NET_PROTOCOL_NBD:
         case VIR_STORAGE_NET_PROTOCOL_RBD:
 +        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
         case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
         case VIR_STORAGE_NET_PROTOCOL_ISCSI:
@@ -485,6 +486,7 @@ qemuSnapshotPrepareDiskExternalActive(virDomainObj *vm,
         case VIR_STORAGE_NET_PROTOCOL_NONE:
         case VIR_STORAGE_NET_PROTOCOL_NBD:
         case VIR_STORAGE_NET_PROTOCOL_RBD:
 +        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
         case VIR_STORAGE_NET_PROTOCOL_ISCSI:
         case VIR_STORAGE_NET_PROTOCOL_HTTP:
@@ -638,6 +640,7 @@ qemuSnapshotPrepareDiskInternal(virDomainDiskDef *disk,
         case VIR_STORAGE_NET_PROTOCOL_NONE:
         case VIR_STORAGE_NET_PROTOCOL_NBD:
         case VIR_STORAGE_NET_PROTOCOL_RBD:
 +        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
         case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
         case VIR_STORAGE_NET_PROTOCOL_ISCSI:
 diff --git a/src/storage/storage_driver.c b/src/storage/storage_driver.c
 index 4df2c75a2b..5a5e48ef71 100644
 --- a/src/storage/storage_driver.c
 +++ b/src/storage/storage_driver.c
@@ -1643,6 +1643,7 @@ storageVolLookupByPathCallback(virStoragePoolObj *obj,
         case VIR_STORAGE_POOL_GLUSTER:
         case VIR_STORAGE_POOL_RBD:
 +        case VIR_STORAGE_POOL_VITASTOR:
         case VIR_STORAGE_POOL_SHEEPDOG:
         case VIR_STORAGE_POOL_ZFS:
         case VIR_STORAGE_POOL_LAST:
 diff --git a/src/storage_file/storage_source_backingstore.c b/src/storage_file/storage_source_backingstore.c
 index e48ae725ab..2017ccc88c 100644
 --- a/src/storage_file/storage_source_backingstore.c
 +++ b/src/storage_file/storage_source_backingstore.c
@@ -284,6 +284,75 @@ virStorageSourceParseRBDColonString(const char *rbdstr,
 }
 +static int
 +virStorageSourceParseVitastorColonString(const char *colonstr,
 +                                         virStorageSource *src)
 +{
 +    char *p, *e, *next;
 +    g_autofree char *options = NULL;
 +
 +    /* optionally skip the "vitastor:" prefix if provided */
 +    if (STRPREFIX(colonstr, "vitastor:"))
 +        colonstr += strlen("vitastor:");
 +
 +    options = g_strdup(colonstr);
 +
 +    p = options;
 +    while (*p) {
 +        /* find : delimiter or end of string */
 +        for (e = p; *e && *e != ':'; ++e) {
 +            if (*e == '\\') {
 +                e++;
 +                if (*e == '\0')
 +                    break;
 +            }
 +        }
 +        if (*e == '\0') {
 +            next = e;    /* last kv pair */
 +        } else {
 +            next = e + 1;
 +            *e = '\0';
 +        }
 +
 +        if (STRPREFIX(p, "image=")) {
 +            src->path = g_strdup(p + strlen("image="));
 +        } else if (STRPREFIX(p, "etcd-prefix=")) {
 +            src->query = g_strdup(p + strlen("etcd-prefix="));
 +        } else if (STRPREFIX(p, "config-path=")) {
 +            src->configFile = g_strdup(p + strlen("config-path="));
 +        } else if (STRPREFIX(p, "etcd-host=")) {
 +            char *h, *sep;
 +
 +            h = p + strlen("etcd-host=");
 +            while (h < e) {
 +                for (sep = h; sep < e; ++sep) {
 +                    if (*sep == '\\' && (sep[1] == ',' ||
 +                                         sep[1] == ';' ||
 +                                         sep[1] == ' ')) {
 +                        *sep = '\0';
 +                        sep += 2;
 +                        break;
 +                    }
 +                }
 +
 +                if (virStorageSourceRBDAddHost(src, h) < 0)
 +                    return -1;
 +
 +                h = sep;
 +            }
 +        }
 +
 +        p = next;
 +    }
 +
 +    if (!src->path) {
 +        return -1;
 +    }
 +
 +    return 0;
 +}
 +
 +
 static int
 virStorageSourceParseNBDColonString(const char *nbdstr,
                                     virStorageSource *src)
@@ -396,6 +465,11 @@ virStorageSourceParseBackingColon(virStorageSource *src,
             return -1;
         break;
 +    case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
 +        if (virStorageSourceParseVitastorColonString(path, src) < 0)
 +            return -1;
 +        break;
 +
     case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
     case VIR_STORAGE_NET_PROTOCOL_LAST:
     case VIR_STORAGE_NET_PROTOCOL_NONE:
@@ -984,6 +1058,54 @@ virStorageSourceParseBackingJSONRBD(virStorageSource *src,
     return 0;
 }
 +static int
 +virStorageSourceParseBackingJSONVitastor(virStorageSource *src,
 +                                         virJSONValue *json,
 +                                         const char *jsonstr G_GNUC_UNUSED,
 +                                         int opaque G_GNUC_UNUSED)
 +{
 +    const char *filename;
 +    const char *image = virJSONValueObjectGetString(json, "image");
 +    const char *conf = virJSONValueObjectGetString(json, "config-path");
 +    const char *etcd_prefix = virJSONValueObjectGetString(json, "etcd-prefix");
 +    virJSONValue *servers = virJSONValueObjectGetArray(json, "server");
 +    size_t nservers;
 +    size_t i;
 +
 +    src->type = VIR_STORAGE_TYPE_NETWORK;
 +    src->protocol = VIR_STORAGE_NET_PROTOCOL_VITASTOR;
 +
 +    /* legacy syntax passed via 'filename' option */
 +    if ((filename = virJSONValueObjectGetString(json, "filename")))
 +        return virStorageSourceParseVitastorColonString(filename, src);
 +
 +    if (!image) {
 +        virReportError(VIR_ERR_INVALID_ARG, "%s",
 +                       _("missing image name in Vitastor backing volume "
 +                         "JSON specification"));
 +        return -1;
 +    }
 +
 +    src->path = g_strdup(image);
 +    src->configFile = g_strdup(conf);
 +    src->query = g_strdup(etcd_prefix);
 +
 +    if (servers) {
 +        nservers = virJSONValueArraySize(servers);
 +
 +        src->hosts = g_new0(virStorageNetHostDef, nservers);
 +        src->nhosts = nservers;
 +
 +        for (i = 0; i < nservers; i++) {
 +            if (virStorageSourceParseBackingJSONInetSocketAddress(src->hosts + i,
 +                                                                  virJSONValueArrayGet(servers, i)) < 0)
 +                return -1;
 +        }
 +    }
 +
 +    return 0;
 +}
 +
 static int
 virStorageSourceParseBackingJSONRaw(virStorageSource *src,
                                     virJSONValue *json,
@@ -1162,6 +1284,7 @@ static const struct virStorageSourceJSONDriverParser jsonParsers[] = {
     {"sheepdog", false, virStorageSourceParseBackingJSONSheepdog, 0},
     {"ssh", false, virStorageSourceParseBackingJSONSSH, 0},
     {"rbd", false, virStorageSourceParseBackingJSONRBD, 0},
 +    {"vitastor", false, virStorageSourceParseBackingJSONVitastor, 0},
     {"raw", true, virStorageSourceParseBackingJSONRaw, 0},
     {"nfs", false, virStorageSourceParseBackingJSONNFS, 0},
     {"vxhs", false, virStorageSourceParseBackingJSONVxHS, 0},
 diff --git a/src/test/test_driver.c b/src/test/test_driver.c
 index 0e93b79922..b4d33f5f56 100644
 --- a/src/test/test_driver.c
 +++ b/src/test/test_driver.c
@@ -7367,6 +7367,7 @@ testStorageVolumeTypeForPool(int pooltype)
     case VIR_STORAGE_POOL_ISCSI_DIRECT:
     case VIR_STORAGE_POOL_GLUSTER:
     case VIR_STORAGE_POOL_RBD:
 +    case VIR_STORAGE_POOL_VITASTOR:
         return VIR_STORAGE_VOL_NETWORK;
     case VIR_STORAGE_POOL_LOGICAL:
     case VIR_STORAGE_POOL_DISK:
 diff --git a/tests/storagepoolcapsschemadata/poolcaps-fs.xml b/tests/storagepoolcapsschemadata/poolcaps-fs.xml
 index eee75af746..8bd0a57bdd 100644
 --- a/tests/storagepoolcapsschemadata/poolcaps-fs.xml
 +++ b/tests/storagepoolcapsschemadata/poolcaps-fs.xml
@@ -204,4 +204,11 @@
       </enum>
     </volOptions>
   </pool>
 +  <pool type='vitastor' supported='no'>
 +    <volOptions>
 +      <defaultFormat type='raw'/>
 +      <enum name='targetFormatType'>
 +      </enum>
 +    </volOptions>
 +  </pool>
 </storagepoolCapabilities>
 diff --git a/tests/storagepoolcapsschemadata/poolcaps-full.xml b/tests/storagepoolcapsschemadata/poolcaps-full.xml
 index 805950a937..852df0de16 100644
 --- a/tests/storagepoolcapsschemadata/poolcaps-full.xml
 +++ b/tests/storagepoolcapsschemadata/poolcaps-full.xml
@@ -204,4 +204,11 @@
       </enum>
     </volOptions>
   </pool>
 +  <pool type='vitastor' supported='yes'>
 +    <volOptions>
 +      <defaultFormat type='raw'/>
 +      <enum name='targetFormatType'>
 +      </enum>
 +    </volOptions>
 +  </pool>
 </storagepoolCapabilities>
 diff --git a/tests/storagepoolxml2argvtest.c b/tests/storagepoolxml2argvtest.c
 index 449b745519..7f95cc8e08 100644
 --- a/tests/storagepoolxml2argvtest.c
 +++ b/tests/storagepoolxml2argvtest.c
@@ -68,6 +68,7 @@ testCompareXMLToArgvFiles(bool shouldFail,
     case VIR_STORAGE_POOL_GLUSTER:
     case VIR_STORAGE_POOL_ZFS:
     case VIR_STORAGE_POOL_VSTORAGE:
 +    case VIR_STORAGE_POOL_VITASTOR:
     case VIR_STORAGE_POOL_LAST:
     default:
         VIR_TEST_DEBUG("pool type '%s' has no xml2argv test", defTypeStr);
 diff --git a/tools/virsh-pool.c b/tools/virsh-pool.c
 index d391257f6e..46799c4a90 100644
 --- a/tools/virsh-pool.c
 +++ b/tools/virsh-pool.c
@@ -1213,6 +1213,9 @@ cmdPoolList(vshControl *ctl, const vshCmd *cmd G_GNUC_UNUSED)
             case VIR_STORAGE_POOL_VSTORAGE:
                 flags |= VIR_CONNECT_LIST_STORAGE_POOLS_VSTORAGE;
                 break;
 +            case VIR_STORAGE_POOL_VITASTOR:
 +                flags |= VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR;
 +                break;
             case VIR_STORAGE_POOL_LAST:
                 break;
             }
--- a/patches/qemu-make-patches.sh
+++ b/patches/qemu-make-patches.sh
@ -9,7 +9,7 @@ for i in "$DIR"/qemu-*-vitastor.patch "$DIR"/pve-qemu-*-vitastor.patch; do
        echo '===================================================================' >> $i
        echo '--- /dev/null' >> $i
        echo '+++ a/block/vitastor.c' >> $i
-        echo '@@ -0,0 +1,'$(wc -l "$DIR"/../src/client/qemu_driver.c | cut -d ' ' -f 1)' @@' >> $i
+        echo '@@ -0,0 +1,'$(wc -l "$DIR"/../src/qemu_driver.c | cut -d ' ' -f 1)' @@' >> $i
-        cat "$DIR"/../src/client/qemu_driver.c | sed 's/^/+/' >> $i
+        cat "$DIR"/../src/qemu_driver.c | sed 's/^/+/' >> $i
    fi
 done
--- a/rpm/build-tarball.sh
+++ b/rpm/build-tarball.sh
@ -24,4 +24,4 @@ rm fio
 mv fio-copy fio
 FIO=`rpm -qi fio | perl -e 'while(<>) { /^Epoch[\s:]+(\S+)/ && print "$1:"; /^Version[\s:]+(\S+)/ && print $1; /^Release[\s:]+(\S+)/ && print "-$1"; }'`
 perl -i -pe 's/(Requires:\s*fio)([^\n]+)?/$1 = '$FIO'/' $VITASTOR/rpm/vitastor-el$EL.spec
-tar --transform 's#^#vitastor-1.6.1/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-1.6.1$(rpm --eval '%dist').tar.gz *
+tar --transform 's#^#vitastor-1.4.6/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-1.4.6$(rpm --eval '%dist').tar.gz *
--- a/rpm/qemu-el8.Dockerfile
+++ b/rpm/qemu-el8.Dockerfile
@ -1,5 +1,5 @@
 # This is an attempt to automatically build patched RPM specs
-# More or less broken, better use *.spec.patch for now (and copy src/client/qemu_driver.c to SOURCES/qemu-vitastor.c)
+# More or less broken, better use *.spec.patch for now (and copy src/qemu_driver.c to SOURCES/qemu-vitastor.c)
 # Build packages for CentOS 8 inside a container
 # cd ..; podman build -t qemu-el8 -v `pwd`/packages:/root/packages -f rpm/qemu-el8.Dockerfile .
--- a/rpm/vitastor-el7.Dockerfile
+++ b/rpm/vitastor-el7.Dockerfile
@ -10,7 +10,7 @@ RUN rm -f /etc/yum.repos.d/CentOS-Media.repo
 RUN yum -y --enablerepo=extras install centos-release-scl epel-release yum-utils rpm-build
 RUN yum -y install https://vitastor.io/rpms/centos/7/vitastor-release-1.0-1.el7.noarch.rpm
 RUN yum -y install devtoolset-9-gcc-c++ devtoolset-9-libatomic-devel gcc make cmake gperftools-devel \
-    fio rh-nodejs12 jerasure-devel libisa-l-devel gf-complete-devel rdma-core-devel libnl3-devel
+    fio rh-nodejs12 jerasure-devel libisa-l-devel gf-complete-devel rdma-core-devel
 RUN yumdownloader --disablerepo=centos-sclo-rh --source fio
 RUN rpm --nomd5 -i fio*.src.rpm
 RUN rm -f /etc/yum.repos.d/CentOS-Media.repo
@ -36,7 +36,7 @@ ADD . /root/vitastor
 RUN set -e; \
    cd /root/vitastor/rpm; \
    sh build-tarball.sh; \
-    cp /root/vitastor-1.6.1.el7.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-1.4.6.el7.tar.gz ~/rpmbuild/SOURCES; \
    cp vitastor-el7.spec ~/rpmbuild/SPECS/vitastor.spec; \
    cd ~/rpmbuild/SPECS/; \
    rpmbuild -ba vitastor.spec; \
--- a/rpm/vitastor-el7.spec
+++ b/rpm/vitastor-el7.spec
@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        1.6.1
+Version:        1.4.6
 Release:        1%{?dist}
 Summary:        Vitastor, a fast software-defined clustered block storage
 License:        Vitastor Network Public License 1.1
 URL:            https://vitastor.io/
-Source0:        vitastor-1.6.1.el7.tar.gz
+Source0:        vitastor-1.4.6.el7.tar.gz
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel
@ -17,7 +17,6 @@ BuildRequires:  libisa-l-devel
 BuildRequires:  gf-complete-devel
 BuildRequires:  libibverbs-devel
 BuildRequires:  cmake3
 BuildRequires:  libnl3-devel
 Requires:       vitastor-osd = %{version}-%{release}
 Requires:       vitastor-mon = %{version}-%{release}
 Requires:       vitastor-client = %{version}-%{release}
@ -104,15 +103,14 @@ rm -rf $RPM_BUILD_ROOT
 %make_install
 . /opt/rh/rh-nodejs12/enable
 cd mon
-npm install --production
+npm install
 cd ..
 mkdir -p %buildroot/usr/lib/vitastor
 cp -r mon %buildroot/usr/lib/vitastor
 mv %buildroot/usr/lib/vitastor/mon/scripts/make-etcd %buildroot/usr/lib/vitastor/mon/
 mkdir -p %buildroot/lib/systemd/system
-cp mon/scripts/vitastor.target mon/scripts/vitastor-mon.service mon/scripts/vitastor-osd@.service %buildroot/lib/systemd/system
+cp mon/vitastor.target mon/vitastor-mon.service mon/vitastor-osd@.service %buildroot/lib/systemd/system
 mkdir -p %buildroot/lib/udev/rules.d
-cp mon/scripts/90-vitastor.rules %buildroot/lib/udev/rules.d
+cp mon/90-vitastor.rules %buildroot/lib/udev/rules.d
 %files
@ -151,12 +149,9 @@ mkdir -p /etc/vitastor
 %_bindir/vitastor-nfs
 %_bindir/vitastor-cli
 %_bindir/vitastor-rm
 %_bindir/vitastor-kv
 %_bindir/vitastor-kv-stress
 %_bindir/vita
 %_libdir/libvitastor_blk.so*
 %_libdir/libvitastor_client.so*
 %_libdir/libvitastor_kv.so*
 %files -n vitastor-client-devel
--- a/rpm/vitastor-el8.Dockerfile
+++ b/rpm/vitastor-el8.Dockerfile
@ -11,7 +11,7 @@ RUN dnf -y install centos-release-advanced-virtualization epel-release dnf-plugi
 RUN sed -i 's/^mirrorlist=/#mirrorlist=/; s!#baseurl=.*!baseurl=http://vault.centos.org/centos/8.4.2105/virt/$basearch/$avdir/!; s!^baseurl=.*Source/.*!baseurl=http://vault.centos.org/centos/8.4.2105/virt/Source/advanced-virtualization/!' /etc/yum.repos.d/CentOS-Advanced-Virtualization.repo
 RUN yum -y install https://vitastor.io/rpms/centos/8/vitastor-release-1.0-1.el8.noarch.rpm
 RUN dnf -y install gcc-toolset-9 gcc-toolset-9-gcc-c++ gperftools-devel \
-    fio nodejs rpm-build jerasure-devel libisa-l-devel gf-complete-devel libibverbs-devel libarchive cmake libnl3-devel
+    fio nodejs rpm-build jerasure-devel libisa-l-devel gf-complete-devel libibverbs-devel libarchive cmake
 RUN dnf download --source fio
 RUN rpm --nomd5 -i fio*.src.rpm
 RUN cd ~/rpmbuild/SPECS && dnf builddep -y --enablerepo=powertools --spec fio.spec
@ -35,7 +35,7 @@ ADD . /root/vitastor
 RUN set -e; \
    cd /root/vitastor/rpm; \
    sh build-tarball.sh; \
-    cp /root/vitastor-1.6.1.el8.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-1.4.6.el8.tar.gz ~/rpmbuild/SOURCES; \
    cp vitastor-el8.spec ~/rpmbuild/SPECS/vitastor.spec; \
    cd ~/rpmbuild/SPECS/; \
    rpmbuild -ba vitastor.spec; \
--- a/Show More
+++ b/Show More
`@ -1,4 +1,4 @@`
	`VERSION ?= v1.6.1`	`VERSION ?= v1.4.6`

	`all: build push`	`all: build push`
`@ -1,4 +1,4 @@`
	`vitastor (1.6.1-1) unstable; urgency=medium`	`vitastor (1.4.6-1) unstable; urgency=medium`

	`* Bugfixes`	`* Bugfixes`