Save cached_read_* in superblock

Instead of it, just do not verify checksums of currently mutated objects.
When clean data modification during flush runs in parallel to a read request,
that request may read a mix of old and new data. It may even read a mix of
multiple flushed versions if it lasts too long... And attempts to verify it
using temporary copies of metadata make the algorithm too complex and creepy.

.gitea/workflows/buildenv.Dockerfile

@@ -0,0 +1,36 @@
+FROM node:16-bullseye
+
+WORKDIR /root
+
+ADD ./docker/vitastor.gpg /etc/apt/trusted.gpg.d
+
+RUN echo 'deb http://deb.debian.org/debian bullseye-backports main' >> /etc/apt/sources.list; \
+    echo 'deb http://vitastor.io/debian bullseye main' >> /etc/apt/sources.list; \
+    echo >> /etc/apt/preferences; \
+    echo 'Package: *' >> /etc/apt/preferences; \
+    echo 'Pin: release a=bullseye-backports' >> /etc/apt/preferences; \
+    echo 'Pin-Priority: 500' >> /etc/apt/preferences; \
+    echo >> /etc/apt/preferences; \
+    echo 'Package: *' >> /etc/apt/preferences; \
+    echo 'Pin: origin "vitastor.io"' >> /etc/apt/preferences; \
+    echo 'Pin-Priority: 1000' >> /etc/apt/preferences; \
+    grep '^deb ' /etc/apt/sources.list | perl -pe 's/^deb/deb-src/' >> /etc/apt/sources.list; \
+    echo 'APT::Install-Recommends false;' >> /etc/apt/apt.conf; \
+    echo 'APT::Install-Suggests false;' >> /etc/apt/apt.conf
+
+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
+RUN apt-get --download-only source fio qemu=`dpkg -s qemu-system-x86|grep ^Version:|awk '{print $2}'`
+
+RUN set -ex; \
+    mkdir qemu-build; \
+    cd qemu-build; \
+    dpkg-source -x /root/qemu*.dsc; \
+    cd qemu*/; \
+    debian/rules configure-qemu || debian/rules b/configure-stamp; \
+    cd b/qemu; \
+    make -j8 config-poison.h || true; \
+    make -j8 qapi/qapi-builtin-types.h

.gitea/workflows/test.Dockerfile

@@ -0,0 +1,19 @@
+FROM git.yourcmc.ru/vitalif/vitastor/buildenv
+
+ADD . /root/vitastor
+
+RUN set -e -x; \
+    mkdir -p /root/fio-build/; \
+    cd /root/fio-build/; \
+    dpkg-source -x /root/fio*.dsc; \
+    cd /root/vitastor; \
+    ln -s /root/fio-build/fio-*/ ./fio; \
+    ln -s /root/qemu-build/qemu-*/ ./qemu; \
+    ls /usr/include/linux/raw.h || cp ./debian/raw.h /usr/include/linux/raw.h; \
+    cd mon; \
+    npm install; \
+    cd ..; \
+    mkdir build; \
+    cd build; \
+    cmake .. -DWITH_ASAN=yes -DWITH_QEMU=yes; \
+    make -j16

.gitea/workflows/test.yml

@@ -0,0 +1,840 @@
+name: Test
+
+on:
+  push:
+    branches:
+    - '*'
+    paths:
+    - '.gitea/**'
+    - 'src/**'
+    - 'mon/**'
+    - 'json11'
+    - 'cpp-btree'
+    - 'tests/**'
+
+env:
+  BUILDENV_IMAGE: git.yourcmc.ru/vitalif/vitastor/buildenv
+  TEST_IMAGE: git.yourcmc.ru/vitalif/vitastor/test
+  OSD_ARGS: '--etcd_quick_timeout 2000'
+
+concurrency:
+  group: ci-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+
+  buildenv:
+    runs-on: ubuntu-latest
+    container: git.yourcmc.ru/vitalif/gitea-ci-dind
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Build and push
+      run: |
+        set -ex
+        if ! docker manifest inspect $BUILDENV_IMAGE >/dev/null; then
+          docker build -t $BUILDENV_IMAGE -f .gitea/workflows/buildenv.Dockerfile .
+          docker login git.yourcmc.ru -u vitalif -p "${{secrets.TOKEN}}"
+          docker push $BUILDENV_IMAGE
+        fi
+
+  build:
+    runs-on: ubuntu-latest
+    needs: buildenv
+    container: git.yourcmc.ru/vitalif/gitea-ci-dind
+    steps:
+    - uses: actions/checkout@v3
+      with:
+        submodules: true
+
+    - name: Build and push
+      run: |
+        set -ex
+        if ! docker manifest inspect $TEST_IMAGE:$GITHUB_SHA >/dev/null; then
+          docker build -t $TEST_IMAGE:$GITHUB_SHA -f .gitea/workflows/test.Dockerfile .
+          docker login git.yourcmc.ru -u vitalif -p "${{secrets.TOKEN}}"
+          docker push $TEST_IMAGE:$GITHUB_SHA
+        fi
+
+  make_test:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    # leak sanitizer sometimes crashes
+    - run: cd /root/vitastor/build && ASAN_OPTIONS=detect_leaks=0 make -j16 test
+
+  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: 3
+      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_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
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 10
+      run: PG_SIZE=2 /root/vitastor/tests/test_heal.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_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_heal.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_csum_32k_dmj:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 10
+      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'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
+  test_heal_csum_32k_dj:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 10
+      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'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
+  test_heal_csum_32k:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 10
+      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'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
+  test_heal_csum_4k_dmj:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 10
+      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'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
+  test_heal_csum_4k_dj:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 10
+      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'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
+  test_heal_csum_4k:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 10
+      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'
+      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
+

.gitea/workflows/tests-to-yaml.pl

@@ -0,0 +1,75 @@
+#!/usr/bin/perl
+
+use strict;
+
+for my $line (<>)
+{
+    if ($line =~ /\.\/(test_[^\.]+)/s)
+    {
+        chomp $line;
+        my $base_name = $1;
+        my $test_name = $base_name;
+        my $timeout = 3;
+        if ($test_name eq 'test_etcd_fail' || $test_name eq 'test_heal' || $test_name eq 'test_add_osd' ||
+            $test_name eq 'test_interrupted_rebalance' || $test_name eq 'test_rebalance_verify')
+        {
+            $timeout = 10;
+        }
+        while ($line =~ /([^\s=]+)=(\S+)/gs)
+        {
+            if ($1 eq 'TEST_NAME')
+            {
+                $test_name = $base_name.'_'.$2;
+                last;
+            }
+            elsif ($1 eq 'SCHEME' && $2 eq 'ec')
+            {
+                $test_name .= '_ec';
+            }
+            elsif ($1 eq 'SCHEME' && $2 eq 'xor')
+            {
+                $test_name .= '_xor';
+            }
+            elsif ($1 eq 'IMMEDIATE_COMMIT')
+            {
+                $test_name .= '_imm';
+            }
+            else
+            {
+                $test_name .= '_'.lc($1).'_'.$2;
+            }
+        }
+        $line =~ s!\./test_!/root/vitastor/tests/test_!;
+        # Gitea CI doesn't support artifacts yet, lol
+        #- name: Upload results
+        #  uses: actions/upload-artifact\@v3
+        #  if: always()
+        #  with:
+        #    name: ${test_name}_result
+        #    path: |
+        #      /root/vitastor/testdata
+        #      !/root/vitastor/testdata/*.bin
+        #    retention-days: 5
+        print <<"EOF"
+  $test_name:
+    runs-on: ubuntu-latest
+    needs: build
+    container: \${{env.TEST_IMAGE}}:\${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: $timeout
+      run: $line
+    - 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
+
+EOF
+;
+    }
+}

CMakeLists.txt

@@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8.12)
 
 project(vitastor)
 
-set(VERSION "0.8.8")
+set(VERSION "0.9.3")
 
 add_subdirectory(src)

README-ru.md

@@ -15,7 +15,7 @@ Vitastor архитектурно похож на Ceph, что означает
 и автоматическое распределение данных по любому числу дисков любого размера с настраиваемыми схемами
 избыточности - репликацией или с произвольными кодами коррекции ошибок.
 
-Vitastor нацелен на SSD и SSD+HDD кластеры с как минимум 10 Гбит/с сетью, поддерживает
+Vitastor нацелен в первую очередь на SSD и SSD+HDD кластеры с как минимум 10 Гбит/с сетью, поддерживает
 TCP и RDMA и на хорошем железе может достигать задержки 4 КБ чтения и записи на уровне ~0.1 мс,
 что примерно в 10 раз быстрее, чем Ceph и другие популярные программные СХД.
 

README.md

@@ -14,8 +14,8 @@ Vitastor is architecturally similar to Ceph which means strong consistency,
 primary-replication, symmetric clustering and automatic data distribution over any
 number of drives of any size with configurable redundancy (replication or erasure codes/XOR).
 
-Vitastor targets SSD and SSD+HDD clusters with at least 10 Gbit/s network, supports
-TCP and RDMA and may achieve 4 KB read and write latency as low as ~0.1 ms
+Vitastor targets primarily SSD and SSD+HDD clusters with at least 10 Gbit/s network,
+supports TCP and RDMA and may achieve 4 KB read and write latency as low as ~0.1 ms
 with proper hardware which is ~10 times faster than other popular SDS's like Ceph
 or internal systems of public clouds.
 

csi/Makefile

@@ -1,4 +1,4 @@
-VERSION ?= v0.8.8
+VERSION ?= v0.9.3
 
 all: build push
 

csi/deploy/004-csi-nodeplugin.yaml

@@ -49,7 +49,7 @@ spec:
             capabilities:
               add: ["SYS_ADMIN"]
             allowPrivilegeEscalation: true
-          image: vitalif/vitastor-csi:v0.8.8
+          image: vitalif/vitastor-csi:v0.9.3
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/deploy/007-csi-provisioner.yaml

@@ -116,7 +116,7 @@ spec:
             privileged: true
             capabilities:
               add: ["SYS_ADMIN"]
-          image: vitalif/vitastor-csi:v0.8.8
+          image: vitalif/vitastor-csi:v0.9.3
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/go.mod

@@ -4,25 +4,10 @@ go 1.15
 
 require (
 	github.com/container-storage-interface/spec v1.4.0
-	github.com/coreos/bbolt v0.0.0-00010101000000-000000000000 // indirect
-	github.com/coreos/etcd v3.3.25+incompatible // indirect
-	github.com/coreos/go-semver v0.3.0 // indirect
-	github.com/coreos/go-systemd v0.0.0-20191104093116-d3cd4ed1dbcf // indirect
-	github.com/coreos/pkg v0.0.0-20180928190104-399ea9e2e55f // indirect
-	github.com/dustin/go-humanize v1.0.0 // indirect
 	github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b
-	github.com/gorilla/websocket v1.4.2 // indirect
-	github.com/grpc-ecosystem/go-grpc-middleware v1.3.0 // indirect
-	github.com/grpc-ecosystem/go-grpc-prometheus v1.2.0 // indirect
-	github.com/grpc-ecosystem/grpc-gateway v1.16.0 // indirect
-	github.com/jonboulle/clockwork v0.2.2 // indirect
 	github.com/kubernetes-csi/csi-lib-utils v0.9.1
-	github.com/soheilhy/cmux v0.1.5 // indirect
-	github.com/tmc/grpc-websocket-proxy v0.0.0-20201229170055-e5319fda7802 // indirect
-	github.com/xiang90/probing v0.0.0-20190116061207-43a291ad63a2 // indirect
-	go.etcd.io/bbolt v0.0.0-00010101000000-000000000000 // indirect
-	go.etcd.io/etcd v3.3.25+incompatible
 	golang.org/x/net v0.0.0-20201202161906-c7110b5ffcbb
+	golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1 // indirect
 	google.golang.org/grpc v1.33.1
 	k8s.io/klog v1.0.0
 	k8s.io/utils v0.0.0-20210305010621-2afb4311ab10

csi/go.sum

@@ -31,14 +31,11 @@ github.com/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuy
 github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
 github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
 github.com/alecthomas/units v0.0.0-20190717042225-c3de453c63f4/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
-github.com/antihax/optional v1.0.0/go.mod h1:uupD/76wgC+ih3iEmQUL+0Ugr19nfwCT1kdvxnR2qWY=
 github.com/beorn7/perks v0.0.0-20180321164747-3a771d992973/go.mod h1:Dwedo/Wpr24TaqPxmxbtue+5NUziq4I4S80YR8gNf3Q=
 github.com/beorn7/perks v1.0.0/go.mod h1:KWe93zE9D1o94FZ5RNwFwVgaQK1VOXiVxmqh+CedLV8=
-github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
 github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
 github.com/blang/semver v3.5.0+incompatible/go.mod h1:kRBLl5iJ+tD4TcOOxsy/0fnwebNt5EWlYSAyrTnjyyk=
 github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
-github.com/cespare/xxhash/v2 v2.1.1 h1:6MnRN8NT7+YBpUIWxHtefFZOKTAPgGjpQSxqLNn0+qY=
 github.com/cespare/xxhash/v2 v2.1.1/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
 github.com/chzyer/logex v1.1.10/go.mod h1:+Ywpsq7O8HXn0nuIou7OrIPyXbp3wmkHB+jjWRnGsAI=
 github.com/chzyer/readline v0.0.0-20180603132655-2972be24d48e/go.mod h1:nSuG5e5PlCu98SY8svDHJxuZscDgtXS6KTTbou5AhLI=
@@ -46,25 +43,12 @@ github.com/chzyer/test v0.0.0-20180213035817-a1ea475d72b1/go.mod h1:Q3SI9o4m/ZMn
 github.com/container-storage-interface/spec v1.2.0/go.mod h1:6URME8mwIBbpVyZV93Ce5St17xBiQJQY67NDsuohiy4=
 github.com/container-storage-interface/spec v1.4.0 h1:ozAshSKxpJnYUfmkpZCTYyF/4MYeYlhdXbAvPvfGmkg=
 github.com/container-storage-interface/spec v1.4.0/go.mod h1:6URME8mwIBbpVyZV93Ce5St17xBiQJQY67NDsuohiy4=
-github.com/coreos/bbolt v1.3.5 h1:XFv7xaq7701j8ZSEzR28VohFYSlyakMyqNMU5FQH6Ac=
-github.com/coreos/bbolt v1.3.5/go.mod h1:G5EMThwa9y8QZGBClrRx5EY+Yw9kAhnjy3bSjsnlVTQ=
-github.com/coreos/etcd v3.3.25+incompatible h1:0GQEw6h3YnuOVdtwygkIfJ+Omx0tZ8/QkVyXI4LkbeY=
-github.com/coreos/etcd v3.3.25+incompatible/go.mod h1:uF7uidLiAD3TWHmW31ZFd/JWoc32PjwdhPthX9715RE=
-github.com/coreos/go-semver v0.3.0 h1:wkHLiw0WNATZnSG7epLsujiMCgPAc9xhjJ4tgnAxmfM=
-github.com/coreos/go-semver v0.3.0/go.mod h1:nnelYz7RCh+5ahJtPPxZlU+153eP4D4r3EedlOD2RNk=
-github.com/coreos/go-systemd v0.0.0-20191104093116-d3cd4ed1dbcf h1:iW4rZ826su+pqaw19uhpSCzhj44qo35pNgKFGqzDKkU=
-github.com/coreos/go-systemd v0.0.0-20191104093116-d3cd4ed1dbcf/go.mod h1:F5haX7vjVVG0kc13fIWeqUViNPyEJxv/OmvnBo0Yme4=
-github.com/coreos/pkg v0.0.0-20180928190104-399ea9e2e55f h1:lBNOc5arjvs8E5mO2tbpBpLoyyu8B6e44T7hJy6potg=
-github.com/coreos/pkg v0.0.0-20180928190104-399ea9e2e55f/go.mod h1:E3G3o1h8I7cfcXa63jLwjI0eiQQMgzzUDFVpN/nH/eA=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
-github.com/dgrijalva/jwt-go v3.2.0+incompatible h1:7qlOGliEKZXTDg6OTjfoBKDXWrumCAMpl/TFQ4/5kLM=
 github.com/dgrijalva/jwt-go v3.2.0+incompatible/go.mod h1:E3ru+11k8xSBh+hMPgOLZmtrrCbhqsmaPHjLKYnJCaQ=
 github.com/docker/spdystream v0.0.0-20160310174837-449fdfce4d96/go.mod h1:Qh8CwZgvJUkLughtfhJv5dyTYa91l1fOUCrgjqmcifM=
 github.com/docopt/docopt-go v0.0.0-20180111231733-ee0de3bc6815/go.mod h1:WwZ+bS3ebgob9U8Nd0kOddGdZWjyMGR8Wziv+TBNwSE=
-github.com/dustin/go-humanize v1.0.0 h1:VSnTsYCnlFHaM2/igO1h6X3HA71jcobQuxemgkq4zYo=
-github.com/dustin/go-humanize v1.0.0/go.mod h1:HtrtbFcZ19U5GC7JDqmcUSB87Iq5E25KnS6fMYU6eOk=
 github.com/elazarl/goproxy v0.0.0-20180725130230-947c36da3153/go.mod h1:/Zj4wYkgs4iZTTu3o/KG3Itv/qCCa8VVMlb3i9OVuzc=
 github.com/emicklei/go-restful v0.0.0-20170410110728-ff4f55a20633/go.mod h1:otzb+WCGbkyDHkqmQmT5YD2WR4BBwUdeQoFo8l/7tVs=
 github.com/envoyproxy/go-control-plane v0.9.0/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
@@ -73,7 +57,6 @@ github.com/evanphx/json-patch v4.9.0+incompatible/go.mod h1:50XU6AFN0ol/bzJsmQLi
 github.com/fsnotify/fsnotify v1.4.7/go.mod h1:jwhsz4b93w/PPRr/qN1Yymfu8t87LnFCMoQvtojpjFo=
 github.com/fsnotify/fsnotify v1.4.9/go.mod h1:znqG4EE+3YCdAaPaxE2ZRY/06pZUdp0tY4IgpuI1SZQ=
 github.com/ghodss/yaml v0.0.0-20150909031657-73d445a93680/go.mod h1:4dBDuWmgqj2HViK6kFavaiC9ZROes6MMH2rRYeMEF04=
-github.com/ghodss/yaml v1.0.0/go.mod h1:4dBDuWmgqj2HViK6kFavaiC9ZROes6MMH2rRYeMEF04=
 github.com/go-gl/glfw/v3.3/glfw v0.0.0-20191125211704-12ad95a8df72/go.mod h1:tQ2UAYgL5IevRw8kRxooKSPJfGvJ9fJQFa0TUsXzTg8=
 github.com/go-kit/kit v0.8.0/go.mod h1:xBxKIO96dXMWWy0MnWVtmwkA9/13aqxPnvrjFYMA2as=
 github.com/go-kit/kit v0.9.0/go.mod h1:xBxKIO96dXMWWy0MnWVtmwkA9/13aqxPnvrjFYMA2as=
@@ -88,14 +71,10 @@ github.com/go-openapi/spec v0.0.0-20160808142527-6aced65f8501/go.mod h1:J8+jY1nA
 github.com/go-openapi/swag v0.0.0-20160704191624-1d0bd113de87/go.mod h1:DXUve3Dpr1UfpPtxFw+EFuQ41HhCWZfha5jSVRG7C7I=
 github.com/go-stack/stack v1.8.0/go.mod h1:v0f6uXyyMGvRgIKkXu+yp6POWl0qKG85gN/melR3HDY=
 github.com/gogo/protobuf v1.1.1/go.mod h1:r8qH/GZQm5c6nD/R0oafs1akxWv10x8SbQlK7atdtwQ=
-github.com/gogo/protobuf v1.3.1 h1:DqDEcV5aeaTmdFBePNpYsp3FlcVH/2ISVVM9Qf8PSls=
 github.com/gogo/protobuf v1.3.1/go.mod h1:SlYgWuQ5SjCEi6WLHjHCa1yvBfUnHcTbrrZtXPKa29o=
-github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q=
-github.com/gogo/protobuf v1.3.2/go.mod h1:P1XiOD3dCwIKUDQYPy72D8LYyHL2YPYrpS2s69NZV8Q=
 github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b h1:VKtxabqXZkF25pY9ekfRL6a582T4P37/31XEstQ5p58=
 github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfUlaOkMMuAQtPIUF8ecWP5IEl/CR7VP2Q=
 github.com/golang/groupcache v0.0.0-20190702054246-869f871628b6/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
-github.com/golang/groupcache v0.0.0-20191227052852-215e87163ea7 h1:5ZkaAPbicIKTF2I64qf5Fh8Aa83Q/dnOafMYV0OMwjA=
 github.com/golang/groupcache v0.0.0-20191227052852-215e87163ea7/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
 github.com/golang/mock v1.1.1/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
 github.com/golang/mock v1.2.0/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
@@ -113,7 +92,6 @@ github.com/golang/protobuf v1.4.1/go.mod h1:U8fpvMrcmy5pZrNK1lt4xCsGvpyWQ/VVv6QD
 github.com/golang/protobuf v1.4.2 h1:+Z5KGCizgyZCbGh1KZqA0fcLLkwbsjIzS4aV2v7wJX0=
 github.com/golang/protobuf v1.4.2/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI=
 github.com/google/btree v0.0.0-20180813153112-4030bb1f1f0c/go.mod h1:lNA+9X1NB3Zf8V7Ke586lFgjr2dZNuvo3lPJSGZ5JPQ=
-github.com/google/btree v1.0.0 h1:0udJVsspx3VBr5FwtLhQQtuAsVc79tTq0ocGIPAU6qo=
 github.com/google/btree v1.0.0/go.mod h1:lNA+9X1NB3Zf8V7Ke586lFgjr2dZNuvo3lPJSGZ5JPQ=
 github.com/google/go-cmp v0.2.0/go.mod h1:oXzfMopK8JAjlY9xF4vHSVASa0yLyX7SntLO5aqRK0M=
 github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
@@ -127,38 +105,24 @@ github.com/google/pprof v0.0.0-20181206194817-3ea8567a2e57/go.mod h1:zfwlbNMJ+OI
 github.com/google/pprof v0.0.0-20190515194954-54271f7e092f/go.mod h1:zfwlbNMJ+OItoe0UupaVj+oy1omPYYDuagoSzA8v9mc=
 github.com/google/pprof v0.0.0-20191218002539-d4f498aebedc/go.mod h1:ZgVRPoUq/hfqzAqh7sHMqb3I9Rq5C59dIz2SbBwJ4eM=
 github.com/google/renameio v0.1.0/go.mod h1:KWCgfxg9yswjAJkECMjeO8J8rahYeXnNhOm40UhjYkI=
-github.com/google/uuid v1.1.1 h1:Gkbcsh/GbpXz7lPftLA3P6TYMwjCLYm83jiFQZF/3gY=
 github.com/google/uuid v1.1.1/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/googleapis/gax-go/v2 v2.0.4/go.mod h1:0Wqv26UfaUD9n4G6kQubkQ+KchISgw+vpHVxEJEs9eg=
 github.com/googleapis/gax-go/v2 v2.0.5/go.mod h1:DWXyrwAJ9X0FpwwEdw+IPEYBICEFu5mhpdKc/us6bOk=
 github.com/googleapis/gnostic v0.4.1/go.mod h1:LRhVm6pbyptWbWbuZ38d1eyptfvIytN3ir6b65WBswg=
-github.com/gorilla/websocket v1.4.2 h1:+/TMaTYc4QFitKJxsQ7Yye35DkWvkdLcvGKqM+x0Ufc=
-github.com/gorilla/websocket v1.4.2/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=
 github.com/gregjones/httpcache v0.0.0-20180305231024-9cad4c3443a7/go.mod h1:FecbI9+v66THATjSRHfNgh1IVFe/9kFxbXtjV0ctIMA=
-github.com/grpc-ecosystem/go-grpc-middleware v1.3.0 h1:+9834+KizmvFV7pXQGSXQTsaWhq2GjuNUt0aUU0YBYw=
-github.com/grpc-ecosystem/go-grpc-middleware v1.3.0/go.mod h1:z0ButlSOZa5vEBq9m2m2hlwIgKw+rp3sdCBRoJY+30Y=
-github.com/grpc-ecosystem/go-grpc-prometheus v1.2.0 h1:Ovs26xHkKqVztRpIrF/92BcuyuQ/YW4NSIpoGtfXNho=
-github.com/grpc-ecosystem/go-grpc-prometheus v1.2.0/go.mod h1:8NvIoxWQoOIhqOTXgfV/d3M/q6VIi02HzZEHgUlZvzk=
-github.com/grpc-ecosystem/grpc-gateway v1.16.0 h1:gmcG1KaJ57LophUzW0Hy8NmPhnMZb4M0+kPpLofRdBo=
-github.com/grpc-ecosystem/grpc-gateway v1.16.0/go.mod h1:BDjrQk3hbvj6Nolgz8mAMFbcEtjT1g+wF4CSlocrBnw=
 github.com/hashicorp/golang-lru v0.5.0/go.mod h1:/m3WP610KZHVQ1SGc6re/UDhFvYD7pJ4Ao+sR/qLZy8=
 github.com/hashicorp/golang-lru v0.5.1/go.mod h1:/m3WP610KZHVQ1SGc6re/UDhFvYD7pJ4Ao+sR/qLZy8=
 github.com/hpcloud/tail v1.0.0/go.mod h1:ab1qPbhIpdTxEkNHXyeSf5vhxWSCs/tWer42PpOxQnU=
 github.com/ianlancetaylor/demangle v0.0.0-20181102032728-5e5cf60278f6/go.mod h1:aSSvb/t6k1mPoxDqO4vJh6VOCGPwU4O0C2/Eqndh1Sc=
 github.com/imdario/mergo v0.3.5/go.mod h1:2EnlNZ0deacrJVfApfmtdGgDfMuh/nq6Ok1EcJh5FfA=
-github.com/jonboulle/clockwork v0.2.2 h1:UOGuzwb1PwsrDAObMuhUnj0p5ULPj8V/xJ7Kx9qUBdQ=
-github.com/jonboulle/clockwork v0.2.2/go.mod h1:Pkfl5aHPm1nk2H9h0bjmnJD/BcgbGXUBGnn1kMkgxc8=
 github.com/json-iterator/go v1.1.6/go.mod h1:+SdeFBvtyEkXs7REEP0seUULqWtbJapLOCVDaaPEHmU=
-github.com/json-iterator/go v1.1.10 h1:Kz6Cvnvv2wGdaG/V8yMvfkmNiXq9Ya2KUv4rouJJr68=
 github.com/json-iterator/go v1.1.10/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
 github.com/jstemmer/go-junit-report v0.0.0-20190106144839-af01ea7f8024/go.mod h1:6v2b51hI/fHJwM22ozAgKL4VKDeJcHhJFhtBdhmNjmU=
 github.com/jstemmer/go-junit-report v0.9.1/go.mod h1:Brl9GWCQeLvo8nXZwPNNblvFj/XSXhF0NWZEnDohbsk=
 github.com/julienschmidt/httprouter v1.2.0/go.mod h1:SYymIcj16QtmaHHD7aYtjjsJG7VTCxuUUipMqKk8s4w=
 github.com/kisielk/errcheck v1.2.0/go.mod h1:/BMXB+zMLi60iA8Vv6Ksmxu/1UDYcXs4uQLJ+jE2L00=
-github.com/kisielk/errcheck v1.5.0/go.mod h1:pFxgyoBC7bSaBwPgfKdkLd5X25qrDl4LWUI2bnpBCr8=
 github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
 github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
-github.com/konsorten/go-windows-terminal-sequences v1.0.3 h1:CE8S1cTafDpPvMhIxNJKvHsGVBgn1xWYf1NbHQhywc8=
 github.com/konsorten/go-windows-terminal-sequences v1.0.3/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
 github.com/kr/logfmt v0.0.0-20140226030751-b84e30acd515/go.mod h1:+0opPa2QZZtGFBFZlji/RkVcI2GknAs/DXo4wKdlNEc=
 github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
@@ -171,14 +135,11 @@ github.com/kubernetes-csi/csi-lib-utils v0.9.1 h1:sGq6ifVujfMSkfTsMZip44Ttv8SDXv
 github.com/kubernetes-csi/csi-lib-utils v0.9.1/go.mod h1:8E2jVUX9j3QgspwHXa6LwyN7IHQDjW9jX3kwoWnSC+M=
 github.com/mailru/easyjson v0.0.0-20160728113105-d5b7844b561a/go.mod h1:C1wdFJiN94OJF2b5HbByQZoLdCWB1Yqtg26g4irojpc=
 github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0=
-github.com/matttproud/golang_protobuf_extensions v1.0.2-0.20181231171920-c182affec369 h1:I0XW9+e1XWDxdcEniV4rQAIOPUGDq67JSCiRCgGCZLI=
 github.com/matttproud/golang_protobuf_extensions v1.0.2-0.20181231171920-c182affec369/go.mod h1:BSXmuO+STAnVfrANrmjBb36TMTDstsz7MSK+HVaYKv4=
 github.com/moby/term v0.0.0-20200312100748-672ec06f55cd/go.mod h1:DdlQx2hp0Ss5/fLikoLlEeIYiATotOjgB//nb973jeo=
 github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
-github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg=
 github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
 github.com/modern-go/reflect2 v0.0.0-20180701023420-4b7aa43c6742/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
-github.com/modern-go/reflect2 v1.0.1 h1:9f412s+6RmYXLWZSEzVVgPGK7C2PphHj5RJrvfx9AWI=
 github.com/modern-go/reflect2 v1.0.1/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
 github.com/munnerz/goautoneg v0.0.0-20120707110453-a547fc61f48d/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
 github.com/mwitkow/go-conntrack v0.0.0-20161129095857-cc309e4a2223/go.mod h1:qRWi+5nqEBWmkhHvq77mSJWrCKwh8bxhgT7d/eI7P4U=
@@ -188,38 +149,28 @@ github.com/onsi/ginkgo v1.6.0/go.mod h1:lLunBs/Ym6LB5Z9jYTR76FiuTmxDTDusOGeTQH+W
 github.com/onsi/ginkgo v1.11.0/go.mod h1:lLunBs/Ym6LB5Z9jYTR76FiuTmxDTDusOGeTQH+WWjE=
 github.com/onsi/gomega v0.0.0-20170829124025-dcabb60a477c/go.mod h1:C1qb7wdrVGGVU+Z6iS04AVkA3Q65CEZX59MT0QO5uiA=
 github.com/onsi/gomega v1.7.0/go.mod h1:ex+gbHU/CVuBBDIJjb2X0qEXbFg53c61hWP/1CpauHY=
-github.com/opentracing/opentracing-go v1.1.0/go.mod h1:UkNAQd3GIcIGf0SeVgPpRdFStlNbqXla1AfSYxPUl2o=
 github.com/peterbourgon/diskv v2.0.1+incompatible/go.mod h1:uqqh8zWWbv1HBMNONnaR/tNboyR3/BZd58JJSHlUSCU=
 github.com/pkg/errors v0.8.0/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
-github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
 github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/prometheus/client_golang v0.9.1/go.mod h1:7SWBe2y4D6OKWSNQJUaRYU/AaXPKyh/dDVn+NZz0KFw=
 github.com/prometheus/client_golang v1.0.0/go.mod h1:db9x61etRT2tGnBNRi70OPL5FsnadC4Ky3P0J6CfImo=
-github.com/prometheus/client_golang v1.7.1 h1:NTGy1Ja9pByO+xAeH/qiWnLrKtr3hJPNjaVUwnjpdpA=
 github.com/prometheus/client_golang v1.7.1/go.mod h1:PY5Wy2awLA44sXw4AOSfFBetzPP4j5+D6mVACh+pe2M=
 github.com/prometheus/client_model v0.0.0-20180712105110-5c3871d89910/go.mod h1:MbSGuTsp3dbXC40dX6PRTWyKYBIrTGTE9sqQNg2J8bo=
 github.com/prometheus/client_model v0.0.0-20190129233127-fd36f4220a90/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
 github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
-github.com/prometheus/client_model v0.2.0 h1:uq5h0d+GuxiXLJLNABMgp2qUWDPiLvgCzz2dUR+/W/M=
 github.com/prometheus/client_model v0.2.0/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
 github.com/prometheus/common v0.4.1/go.mod h1:TNfzLD0ON7rHzMJeJkieUDPYmFC7Snx/y86RQel1bk4=
-github.com/prometheus/common v0.10.0 h1:RyRA7RzGXQZiW+tGMr7sxa85G1z0yOpM1qq5c8lNawc=
 github.com/prometheus/common v0.10.0/go.mod h1:Tlit/dnDKsSWFlCLTWaA1cyBgKHSMdTB80sz/V91rCo=
 github.com/prometheus/procfs v0.0.0-20181005140218-185b4288413d/go.mod h1:c3At6R/oaqEKCNdg8wHV1ftS6bRYblBhIjjI8uT2IGk=
 github.com/prometheus/procfs v0.0.2/go.mod h1:TjEm7ze935MbeOT/UhFTIMYKhuLP4wbCsTZCD3I8kEA=
-github.com/prometheus/procfs v0.1.3 h1:F0+tqvhOksq22sc6iCHF5WGlWjdwj92p0udFh1VFBS8=
 github.com/prometheus/procfs v0.1.3/go.mod h1:lV6e/gmhEcM9IjHGsFOCxxuZ+z1YqCvr4OA4YeYWdaU=
-github.com/rogpeppe/fastuuid v1.2.0/go.mod h1:jVj6XXZzXRy/MSR5jhDC/2q6DgLz+nrA6LYCDYWNEvQ=
 github.com/rogpeppe/go-internal v1.3.0/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFRclV5y23lUDJ4=
 github.com/sirupsen/logrus v1.2.0/go.mod h1:LxeOpSwHxABJmUn/MG1IvRgCAasNZTLOkJPxbbu5VWo=
 github.com/sirupsen/logrus v1.4.2/go.mod h1:tLMulIdttU9McNUspp0xgXVQah82FyeX6MwdIuYE2rE=
-github.com/sirupsen/logrus v1.6.0 h1:UBcNElsrwanuuMsnGSlYmtmgbb23qDR5dG+6X6Oo89I=
 github.com/sirupsen/logrus v1.6.0/go.mod h1:7uNnSEd1DgxDLC74fIahvMZmmYsHGZGEOFrfsX/uA88=
-github.com/soheilhy/cmux v0.1.5 h1:jjzc5WVemNEDTLwv9tlmemhC73tI08BNOIGwBOo10Js=
-github.com/soheilhy/cmux v0.1.5/go.mod h1:T7TcVDs9LWfQgPlPsdngu6I6QIoyIFZDDC6sNE1GqG0=
 github.com/spf13/afero v1.2.2/go.mod h1:9ZxEEn6pIJ8Rxe320qSDBk6AsU0r9pR7Q4OcevTdifk=
 github.com/spf13/pflag v0.0.0-20170130214245-9ff6c6923cff/go.mod h1:DYY7MBk1bdzusC3SYhjObp+wFpr4gzcvqqNjLnInEg4=
 github.com/spf13/pflag v1.0.3/go.mod h1:DYY7MBk1bdzusC3SYhjObp+wFpr4gzcvqqNjLnInEg4=
@@ -231,24 +182,11 @@ github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UV
 github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
 github.com/stretchr/testify v1.5.1 h1:nOGnQDM7FYENwehXlg/kFVnos3rEvtKTjRvOWSzb6H4=
 github.com/stretchr/testify v1.5.1/go.mod h1:5W2xD1RspED5o8YsWQXVCued0rvSQ+mT+I5cxcmMvtA=
-github.com/tmc/grpc-websocket-proxy v0.0.0-20201229170055-e5319fda7802 h1:uruHq4dN7GR16kFc5fp3d1RIYzJW5onx8Ybykw2YQFA=
-github.com/tmc/grpc-websocket-proxy v0.0.0-20201229170055-e5319fda7802/go.mod h1:ncp9v5uamzpCO7NfCPTXjqaC+bZgJeR0sMTm6dMHP7U=
-github.com/xiang90/probing v0.0.0-20190116061207-43a291ad63a2 h1:eY9dn8+vbi4tKz5Qo6v2eYzo7kUS51QINcR5jNpbZS8=
-github.com/xiang90/probing v0.0.0-20190116061207-43a291ad63a2/go.mod h1:UETIi67q53MR2AWcXfiuqkDkRtnGDLqkBTpCHuJHxtU=
-github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
-github.com/yuin/goldmark v1.2.1/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
-go.etcd.io/bbolt v1.3.5 h1:XAzx9gjCb0Rxj7EoqcClPD1d5ZBxZJk0jbuoPHenBt0=
-go.etcd.io/bbolt v1.3.5/go.mod h1:G5EMThwa9y8QZGBClrRx5EY+Yw9kAhnjy3bSjsnlVTQ=
-go.etcd.io/etcd v3.3.25+incompatible h1:V1RzkZJj9LqsJRy+TUBgpWSbZXITLB819lstuTFoZOY=
-go.etcd.io/etcd v3.3.25+incompatible/go.mod h1:yaeTdrJi5lOmYerz05bd8+V7KubZs8YSFZfzsF9A6aI=
 go.opencensus.io v0.21.0/go.mod h1:mSImk1erAIZhrmZN+AvHh14ztQfjbGwt4TtuofqLduU=
 go.opencensus.io v0.22.0/go.mod h1:+kGneAE2xo2IficOXnaByMWTGM9T73dGwxeWcUqIpI8=
 go.opencensus.io v0.22.2/go.mod h1:yxeiOL68Rb0Xd1ddK5vPZ/oVn4vY4Ynel7k9FzqtOIw=
-go.uber.org/atomic v1.4.0 h1:cxzIVoETapQEqDhQu3QfnvXAV4AlzcvUCxkVUFw3+EU=
 go.uber.org/atomic v1.4.0/go.mod h1:gD2HeocX3+yG+ygLZcrzQJaqmWj9AIm7n08wl/qW/PE=
-go.uber.org/multierr v1.1.0 h1:HoEmRHQPVSqub6w2z2d2EOVs2fjyFRGyofhKuyDq0QI=
 go.uber.org/multierr v1.1.0/go.mod h1:wR5kodmAFQ0UK8QlbwjlSNy0Z68gJhDJUG5sjR94q/0=
-go.uber.org/zap v1.10.0 h1:ORx85nbTijNz8ljznvCMR1ZBIPKFn3jQrag10X2AsuM=
 go.uber.org/zap v1.10.0/go.mod h1:vwi/ZaCAaUcBkycHslxD9B2zi4UTXhF60s6SWpuDF0Q=
 golang.org/x/crypto v0.0.0-20180904163835-0709b304e793/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
@@ -256,7 +194,6 @@ golang.org/x/crypto v0.0.0-20190510104115-cbcb75029529/go.mod h1:yigFU9vqHzYiE8U
 golang.org/x/crypto v0.0.0-20190605123033-f99c8df09eb5/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/crypto v0.0.0-20191206172530-e9b2fee46413/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
-golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9 h1:psW17arqaxU48Z5kZ0CQnkZWQJsqcURM6tKiBApRjXI=
 golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
 golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20190306152737-a1d7652674e8/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
@@ -276,8 +213,6 @@ golang.org/x/mobile v0.0.0-20190719004257-d2bd2a29d028/go.mod h1:E/iHnbuqvinMTCc
 golang.org/x/mod v0.0.0-20190513183733-4bf6d317e70e/go.mod h1:mXi4GBBbnImb6dmsKGUJ2LatrhH/nqhxcFungHvyanc=
 golang.org/x/mod v0.1.0/go.mod h1:0QHyrYULN0/3qlju5TqG8bIK38QM8yzMo5ekMj3DlcY=
 golang.org/x/mod v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg=
-golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
-golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20180906233101-161cd47e91fd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
@@ -291,26 +226,20 @@ golang.org/x/net v0.0.0-20190603091049-60506f45cf65/go.mod h1:HSz+uSET+XFnRR8LxR
 golang.org/x/net v0.0.0-20190613194153-d28f0bde5980/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20191209160850-c0dbc17a3553/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
-golang.org/x/net v0.0.0-20200226121028-0de0cce0169b/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20200324143707-d3edc9973b7e/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
-golang.org/x/net v0.0.0-20200707034311-ab3426394381 h1:VXak5I6aEWmAXeQjA+QSZzlgNrpq9mjcfDemuexIKsU=
 golang.org/x/net v0.0.0-20200707034311-ab3426394381/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
-golang.org/x/net v0.0.0-20200822124328-c89045814202/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
-golang.org/x/net v0.0.0-20201021035429-f5854403a974/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
 golang.org/x/net v0.0.0-20201202161906-c7110b5ffcbb h1:eBmm0M9fYhWpKZLjQUUKka/LtIxf46G4fxeEz5KJr9U=
 golang.org/x/net v0.0.0-20201202161906-c7110b5ffcbb/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20190226205417-e64efc72b421/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
 golang.org/x/oauth2 v0.0.0-20190604053449-0f29369cfe45/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
 golang.org/x/oauth2 v0.0.0-20191202225959-858c2ad4c8b6/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
-golang.org/x/oauth2 v0.0.0-20200107190931-bf48bf16ab8d/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
 golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20190227155943-e225da77a7e6/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20180909124046-d0be0721c37e/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20181116152217-5ac8a444bdc5/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
@@ -326,11 +255,9 @@ golang.org/x/sys v0.0.0-20191005200804-aed5e4c7ecf9/go.mod h1:h1NjWce9XRLGQEsW7w
 golang.org/x/sys v0.0.0-20191204072324-ce4227a45e2e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20191228213918-04cbcbbfeed8/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200106162015-b016eb3dc98e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20200202164722-d101bd2416d5/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200302150141-5c8b2ff67527/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200615200032-f1bc736245b1/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20200622214017-ed371f2e16b4 h1:5/PjkGUjvEU5Gl6BxmvKRPpqo2uNMv4rcHBMwzk/st8=
 golang.org/x/sys v0.0.0-20200622214017-ed371f2e16b4/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f h1:+Nyd8tzPX9R7BWHguqsrbFdRx3WQ/1ib8I44HXV5yTA=
 golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -341,7 +268,6 @@ golang.org/x/text v0.3.3 h1:cokOdA+Jmi5PJGXLlLllQSgYigAEfHXJAERHVMaCc2k=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
-golang.org/x/time v0.0.0-20191024005414-555d28b269f0 h1:/5xXl8Y5W96D+TtHSlonuFqGHIWVuyCkGJLwGh9JJFs=
 golang.org/x/time v0.0.0-20191024005414-555d28b269f0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20181011042414-1f849cf54d09/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
@@ -360,14 +286,10 @@ golang.org/x/tools v0.0.0-20190628153133-6cdbf07be9d0/go.mod h1:/rFqwRUd4F7ZHNgw
 golang.org/x/tools v0.0.0-20190816200558-6889da9d5479/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.0.0-20190911174233-4f2ddba30aff/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.0.0-20191012152004-8de300cfc20a/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
-golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.0.0-20191125144606-a911d9008d1f/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.0.0-20191227053925-7b8e75db28f4/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
-golang.org/x/tools v0.0.0-20200619180055-7c47624df98f/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
-golang.org/x/tools v0.0.0-20210106214847-113979e3529a/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
-golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543 h1:E7g+9GITq07hpfrRu66IVDexMakfv52eLZ2CXBWiKr4=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1 h1:go1bK/D/BFZV2I8cIQd1NKEZ+0owSTG1fDTci4IqFcE=
 golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
@@ -388,8 +310,6 @@ google.golang.org/genproto v0.0.0-20190801165951-fa694d86fc64/go.mod h1:DMBHOl98
 google.golang.org/genproto v0.0.0-20190819201941-24fa4b261c55/go.mod h1:DMBHOl98Agz4BDEuKkezgsaosCRResVns1a3J2ZsMNc=
 google.golang.org/genproto v0.0.0-20190911173649-1774047e7e51/go.mod h1:IbNlFCBrqXvoKpeg0TB2l7cyZUmoaFKYIwrEpbDKLA8=
 google.golang.org/genproto v0.0.0-20191230161307-f3c370f40bfb/go.mod h1:n3cpQtvxv34hfy77yVDNjmbRyujviMdxYliBSkLhpCc=
-google.golang.org/genproto v0.0.0-20200423170343-7949de9c1215/go.mod h1:55QSHmfGQM9UVYDPBsyGGes0y52j32PQ3BqQfXhyH3c=
-google.golang.org/genproto v0.0.0-20200513103714-09dca8ec2884/go.mod h1:55QSHmfGQM9UVYDPBsyGGes0y52j32PQ3BqQfXhyH3c=
 google.golang.org/genproto v0.0.0-20200526211855-cb27e3aa2013 h1:+kGHl1aib/qcwaRi1CbqBZ1rk19r85MNUf8HaBghugY=
 google.golang.org/genproto v0.0.0-20200526211855-cb27e3aa2013/go.mod h1:NbSheEEYHJ7i3ixzK3sjbqSGDJWnxyFXZblF3eUsNvo=
 google.golang.org/grpc v1.25.1 h1:wdKvqQk7IttEw92GoRyKG2IDrUIpgpj6H6m81yfeMW0=
@@ -415,7 +335,6 @@ gopkg.in/inf.v0 v0.9.1/go.mod h1:cWUDdTG/fYaXco+Dcufb5Vnc6Gp2YChqWtbxRZE0mXw=
 gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7/go.mod h1:dt/ZhP58zS4L8KSrWDmTeBkI65Dw0HsyUHuEVlX15mw=
 gopkg.in/yaml.v2 v2.2.1/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
-gopkg.in/yaml.v2 v2.2.3/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.2.4/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.2.5/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.2.8 h1:obN1ZagJSUGI0Ek/LBmuj4SNLPfIny3KsKFopxRdj10=
@@ -444,5 +363,4 @@ k8s.io/utils v0.0.0-20210305010621-2afb4311ab10/go.mod h1:jPW/WVKK9YHAvNhRxK0md/
 rsc.io/binaryregexp v0.2.0/go.mod h1:qTv7/COck+e2FymRvadv62gMdZztPaShugOCi3I+8D8=
 sigs.k8s.io/structured-merge-diff/v4 v4.0.1/go.mod h1:bJZC9H9iH24zzfZ/41RGcq60oK1F7G282QMXDPYydCw=
 sigs.k8s.io/yaml v1.1.0/go.mod h1:UJmg0vDUVViEyp3mgSv9WPwZCDxu4rQW1olrI1uml+o=
-sigs.k8s.io/yaml v1.2.0 h1:kr/MCeFWJWTwyaHoR9c8EjH9OumOmoF9YGiZd7lFm/Q=
 sigs.k8s.io/yaml v1.2.0/go.mod h1:yfXDCHCao9+ENCvLSE62v9VSji2MKu5jeNfTrofGhJc=

csi/src/config.go

@@ -5,7 +5,7 @@ package vitastor
 
 const (
     vitastorCSIDriverName    = "csi.vitastor.io"
-    vitastorCSIDriverVersion = "0.8.8"
+    vitastorCSIDriverVersion = "0.9.3"
 )
 
 // Config struct fills the parameters of request or user input

debian/build-pve-qemu.sh

@@ -0,0 +1,58 @@
+exit
+
+git clone https://git.yourcmc.ru/vitalif/pve-qemu .
+
+# bookworm
+
+docker run -it -v `pwd`/pve-qemu:/root/pve-qemu --name pve-qemu-bullseye debian:bullseye bash
+
+perl -i -pe 's/Types: deb$/Types: deb deb-src/' /etc/apt/sources.list.d/debian.sources
+echo 'deb [arch=amd64] http://download.proxmox.com/debian/pve bookworm pve-no-subscription' >> /etc/apt/sources.list
+echo 'deb https://vitastor.io/debian bookworm main' >> /etc/apt/sources.list
+echo 'APT::Install-Recommends false;' >> /etc/apt/apt.conf
+echo 'ru_RU UTF-8' >> /etc/locale.gen
+echo 'en_US UTF-8' >> /etc/locale.gen
+apt-get update
+apt-get install wget ca-certificates
+wget https://enterprise.proxmox.com/debian/proxmox-release-bookworm.gpg -O /etc/apt/trusted.gpg.d/proxmox-release-bookworm.gpg
+wget https://vitastor.io/debian/pubkey.gpg -O /etc/apt/trusted.gpg.d/vitastor.gpg
+apt-get update
+apt-get install git devscripts equivs wget mc libjemalloc-dev vitastor-client-dev lintian locales
+mk-build-deps --install ./control
+
+# bullseye
+
+docker run -it -v `pwd`/pve-qemu:/root/pve-qemu --name pve-qemu-bullseye debian:bullseye bash
+
+grep '^deb ' /etc/apt/sources.list | perl -pe 's/^deb /deb-src /' >> /etc/apt/sources.list
+echo 'deb [arch=amd64] http://download.proxmox.com/debian/pve bullseye pve-no-subscription' >> /etc/apt/sources.list
+echo 'deb https://vitastor.io/debian bullseye main' >> /etc/apt/sources.list
+echo 'APT::Install-Recommends false;' >> /etc/apt/apt.conf
+echo 'ru_RU UTF-8' >> /etc/locale.gen
+echo 'en_US UTF-8' >> /etc/locale.gen
+apt-get update
+apt-get install wget
+wget https://enterprise.proxmox.com/debian/proxmox-release-bullseye.gpg -O /etc/apt/trusted.gpg.d/proxmox-release-bullseye.gpg
+wget https://vitastor.io/debian/pubkey.gpg -O /etc/apt/trusted.gpg.d/vitastor.gpg
+apt-get update
+apt-get install git devscripts equivs wget mc libjemalloc-dev vitastor-client-dev lintian locales
+mk-build-deps --install ./control
+
+# buster
+
+docker run -it -v `pwd`/pve-qemu:/root/pve-qemu --name pve-qemu-buster debian:buster bash
+
+grep '^deb ' /etc/apt/sources.list | perl -pe 's/^deb /deb-src /' >> /etc/apt/sources.list
+echo 'deb [arch=amd64] http://download.proxmox.com/debian/pve buster pve-no-subscription' >> /etc/apt/sources.list
+echo 'deb https://vitastor.io/debian buster main' >> /etc/apt/sources.list
+echo 'deb http://deb.debian.org/debian buster-backports main' >> /etc/apt/sources.list
+echo 'APT::Install-Recommends false;' >> /etc/apt/apt.conf
+echo 'ru_RU UTF-8' >> /etc/locale.gen
+echo 'en_US UTF-8' >> /etc/locale.gen
+apt-get update
+apt-get install wget ca-certificates
+wget http://download.proxmox.com/debian/proxmox-ve-release-6.x.gpg -O /etc/apt/trusted.gpg.d/proxmox-ve-release-6.x.gpg
+wget https://vitastor.io/debian/pubkey.gpg -O /etc/apt/trusted.gpg.d/vitastor.gpg
+apt-get update
+apt-get install git devscripts equivs wget mc libjemalloc-dev vitastor-client-dev lintian locales
+mk-build-deps --install ./control

debian/build-vitastor-bookworm.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+cat < vitastor.Dockerfile > ../Dockerfile
+cd ..
+mkdir -p packages
+sudo podman build --build-arg REL=bookworm -v `pwd`/packages:/root/packages -f Dockerfile .
+rm Dockerfile

debian/changelog

@@ -1,10 +1,10 @@
-vitastor (0.8.8-1) unstable; urgency=medium
+vitastor (0.9.3-1) unstable; urgency=medium
 
   * Bugfixes
 
  -- Vitaliy Filippov <vitalif@yourcmc.ru>  Fri, 03 Jun 2022 02:09:44 +0300
 
-vitastor (0.8.8-1) unstable; urgency=medium
+vitastor (0.9.3-1) unstable; urgency=medium
 
   * Implement NFS proxy
   * Add documentation

debian/patched-qemu.Dockerfile

@@ -1,4 +1,4 @@
-# Build patched QEMU for Debian Buster or Bullseye/Sid inside a container
+# Build patched QEMU for Debian inside a container
 # cd ..; podman build --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/patched-qemu.Dockerfile .
 
 ARG REL=
@@ -15,17 +15,19 @@ RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" ]; then \
         echo 'Pin-Priority: 500' >> /etc/apt/preferences; \
     fi; \
     grep '^deb ' /etc/apt/sources.list | perl -pe 's/^deb/deb-src/' >> /etc/apt/sources.list; \
+    perl -i -pe 's/Types: deb$/Types: deb deb-src/' /etc/apt/sources.list.d/debian.sources || true; \
     echo 'APT::Install-Recommends false;' >> /etc/apt/apt.conf; \
     echo 'APT::Install-Suggests false;' >> /etc/apt/apt.conf
 
 RUN apt-get update
-RUN apt-get -y install qemu fio liburing1 liburing-dev libgoogle-perftools-dev devscripts
+RUN apt-get -y install fio liburing-dev libgoogle-perftools-dev devscripts
 RUN apt-get -y build-dep qemu
 # To build a custom version
 #RUN cp /root/packages/qemu-orig/* /root
 RUN apt-get --download-only source qemu
 
-ADD patches/qemu-5.0-vitastor.patch patches/qemu-5.1-vitastor.patch patches/qemu-6.1-vitastor.patch src/qemu_driver.c /root/vitastor/patches/
+ADD patches /root/vitastor/patches
+ADD src/qemu_driver.c /root/vitastor/src/qemu_driver.c
 RUN set -e; \
     apt-get install -y wget; \
     wget -q -O /etc/apt/trusted.gpg.d/vitastor.gpg https://vitastor.io/debian/pubkey.gpg; \
@@ -37,25 +39,16 @@ RUN set -e; \
     rm -rf /root/packages/qemu-$REL/*; \
     cd /root/packages/qemu-$REL; \
     dpkg-source -x /root/qemu*.dsc; \
-    if ls -d /root/packages/qemu-$REL/qemu-5.0*; then \
-        D=$(ls -d /root/packages/qemu-$REL/qemu-5.0*); \
-        cp /root/vitastor/patches/qemu-5.0-vitastor.patch $D/debian/patches; \
-        echo qemu-5.0-vitastor.patch >> $D/debian/patches/series; \
-    elif ls /root/packages/qemu-$REL/qemu-6.1*; then \
-        D=$(ls -d /root/packages/qemu-$REL/qemu-6.1*); \
-        cp /root/vitastor/patches/qemu-6.1-vitastor.patch $D/debian/patches; \
-        echo qemu-6.1-vitastor.patch >> $D/debian/patches/series; \
-    else \
-        cp /root/vitastor/patches/qemu-5.1-vitastor.patch /root/packages/qemu-$REL/qemu-*/debian/patches; \
-        P=`ls -d /root/packages/qemu-$REL/qemu-*/debian/patches`; \
-        echo qemu-5.1-vitastor.patch >> $P/series; \
-    fi; \
+    QEMU_VER=$(ls -d qemu*/ | perl -pe 's!^.*(\d+\.\d+).*!$1!'); \
+    D=$(ls -d qemu*/); \
+    cp /root/vitastor/patches/qemu-$QEMU_VER-vitastor.patch ./qemu-*/debian/patches; \
+    echo qemu-$QEMU_VER-vitastor.patch >> $D/debian/patches/series; \
     cd /root/packages/qemu-$REL/qemu-*/; \
     quilt push -a; \
     quilt add block/vitastor.c; \
-    cp /root/vitastor/patches/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/^.*\((.*?)(~bpo[\d\+]*)?\).*$/$1/')+vitastor1; \
+    V=$(head -n1 debian/changelog | perl -pe 's/^.*\((.*?)(~bpo[\d\+]*)?\).*$/$1/')+vitastor3; \
     DEBEMAIL="Vitaliy Filippov <vitalif@yourcmc.ru>" dch -D $REL -v $V 'Plug Vitastor block driver'; \
     DEB_BUILD_OPTIONS=nocheck dpkg-buildpackage --jobs=auto -sa; \
     rm -rf /root/packages/qemu-$REL/qemu-*/

debian/vitastor.Dockerfile

@@ -1,4 +1,4 @@
-# Build Vitastor packages for Debian Buster or Bullseye/Sid inside a container
+# Build Vitastor packages for Debian inside a container
 # cd ..; podman build --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/vitastor.Dockerfile .
 
 ARG REL=
@@ -15,11 +15,12 @@ RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" ]; then \
         echo 'Pin-Priority: 500' >> /etc/apt/preferences; \
     fi; \
     grep '^deb ' /etc/apt/sources.list | perl -pe 's/^deb/deb-src/' >> /etc/apt/sources.list; \
+    perl -i -pe 's/Types: deb$/Types: deb deb-src/' /etc/apt/sources.list.d/debian.sources || true; \
     echo 'APT::Install-Recommends false;' >> /etc/apt/apt.conf; \
     echo 'APT::Install-Suggests false;' >> /etc/apt/apt.conf
 
 RUN apt-get update
-RUN apt-get -y install fio liburing1 liburing-dev libgoogle-perftools-dev devscripts
+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
@@ -34,8 +35,8 @@ RUN set -e -x; \
     mkdir -p /root/packages/vitastor-$REL; \
     rm -rf /root/packages/vitastor-$REL/*; \
     cd /root/packages/vitastor-$REL; \
-    cp -r /root/vitastor vitastor-0.8.8; \
-    cd vitastor-0.8.8; \
+    cp -r /root/vitastor vitastor-0.9.3; \
+    cd vitastor-0.9.3; \
     ln -s /root/fio-build/fio-*/ ./fio; \
     FIO=$(head -n1 fio/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
     ls /usr/include/linux/raw.h || cp ./debian/raw.h /usr/include/linux/raw.h; \
@@ -48,8 +49,8 @@ RUN set -e -x; \
     rm -rf a b; \
     echo "dep:fio=$FIO" > debian/fio_version; \
     cd /root/packages/vitastor-$REL; \
-    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_0.8.8.orig.tar.xz vitastor-0.8.8; \
-    cd vitastor-0.8.8; \
+    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_0.9.3.orig.tar.xz vitastor-0.9.3; \
+    cd vitastor-0.9.3; \
     V=$(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; \

docs/config.en.md

@@ -21,7 +21,7 @@ Configuration parameters can be set in 3 places:
   mon, fio and QEMU options, OpenStack/Proxmox/etc configuration. The latter
   doesn't allow to set all variables directly, but it allows to override the
   configuration file and set everything you need inside it.
-- OSD superblocks created by [vitastor-disk](../usage/disk.en.md) contain
+- OSD superblocks created by [vitastor-disk](usage/disk.en.md) contain
   primarily disk layout parameters of specific OSDs. In fact, these parameters
   are automatically passed into the command line of vitastor-osd process, so
   they have the same "status" as command-line parameters.

docs/config.ru.md

@@ -23,7 +23,7 @@
   монитора, опциях fio и QEMU, настроек OpenStack, Proxmox и т.п. Последние,
   как правило, не включают полный набор параметров напрямую, но позволяют
   определить путь к файлу конфигурации и задать любые параметры в нём.
-- В суперблоке OSD, записываемом [vitastor-disk](../usage/disk.ru.md) - параметры,
+- В суперблоке OSD, записываемом [vitastor-disk](usage/disk.ru.md) - параметры,
   связанные с дисковым форматом и с этим конкретным OSD. На самом деле,
   при запуске OSD эти параметры автоматически передаются в командную строку
   процесса vitastor-osd, то есть по "статусу" они эквивалентны параметрам

docs/config/common.en.md

@@ -25,11 +25,16 @@ running if required parameters are specified.
 ## etcd_address
 
 - Type: string or array of strings
+- Can be changed online: yes
 
 etcd connection endpoint(s). Multiple endpoints may be delimited by "," or
 specified in a JSON array `["10.0.115.10:2379/v3","10.0.115.11:2379/v3"]`.
 Note that https is not supported for etcd connections yet.
 
+etcd connection endpoints can be changed online by updating global
+configuration in etcd itself - this allows to switch the cluster to new
+etcd addresses without downtime.
+
 ## etcd_prefix
 
 - Type: string
@@ -42,5 +47,6 @@ example, use a single etcd cluster for multiple Vitastor clusters.
 
 - Type: integer
 - Default: 0
+- Can be changed online: yes
 
 Log level. Raise if you want more verbose output.

docs/config/common.ru.md

@@ -24,10 +24,14 @@
 ## etcd_address
 
 - Тип: строка или массив строк
+- Можно менять на лету: да
 
 Адрес(а) подключения к etcd. Несколько адресов могут разделяться запятой
 или указываться в виде JSON-массива `["10.0.115.10:2379/v3","10.0.115.11:2379/v3"]`.
 
+Адреса подключения к etcd можно поменять на лету, обновив конфигурацию в
+самом etcd - это позволяет переключить кластер на новые etcd без остановки.
+
 ## etcd_prefix
 
 - Тип: строка
@@ -41,5 +45,6 @@
 
 - Тип: целое число
 - Значение по умолчанию: 0
+- Можно менять на лету: да
 
 Уровень логгирования. Повысьте, если хотите более подробный вывод.

docs/config/layout-cluster.en.md

@@ -33,12 +33,13 @@ Size of objects (data blocks) into which all physical and virtual drives
 in Vitastor, affects memory usage, write amplification and I/O load
 distribution effectiveness.
 
-Recommended default block size is 128 KB for SSD and 4 MB for HDD. In fact,
-it's possible to use 4 MB for SSD too - it will lower memory usage, but
+Recommended default block size is 128 KB for SSD and 1 MB for HDD. In fact,
+it's possible to use 1 MB for SSD too - it will lower memory usage, but
 may increase average WA and reduce linear performance.
 
 OSD memory usage is roughly (SIZE / BLOCK * 68 bytes) which is roughly
 544 MB per 1 TB of used disk space with the default 128 KB block size.
+With 1 MB it's 8 times lower.
 
 ## bitmap_granularity
 

docs/config/layout-cluster.ru.md

@@ -33,14 +33,14 @@ OSD) могут сосуществовать в одном кластере Vita
 настроек, влияет на потребление памяти, объём избыточной записи (write
 amplification) и эффективность распределения нагрузки по OSD.
 
-Рекомендуемые по умолчанию размеры блока - 128 килобайт для SSD и 4
-мегабайта для HDD. В принципе, для SSD можно тоже использовать 4 мегабайта,
+Рекомендуемые по умолчанию размеры блока - 128 килобайт для SSD и 1 мегабайт
+для HDD. В принципе, для SSD можно тоже использовать блок размером 1 мегабайт,
 это понизит использование памяти, но ухудшит распределение нагрузки и в
 среднем увеличит WA.
 
 Потребление памяти OSD составляет примерно (РАЗМЕР / БЛОК * 68 байт),
 т.е. примерно 544 МБ памяти на 1 ТБ занятого места на диске при
-стандартном 128 КБ блоке.
+стандартном 128 КБ блоке. При 1 МБ блоке памяти нужно в 8 раз меньше.
 
 ## bitmap_granularity
 

docs/config/layout-osd.en.md

@@ -24,6 +24,8 @@ initialization and can't be changed after it without losing data.
 - [disable_journal_fsync](#disable_journal_fsync)
 - [disable_device_lock](#disable_device_lock)
 - [disk_alignment](#disk_alignment)
+- [data_csum_type](#data_csum_type)
+- [csum_block_size](#csum_block_size)
 
 ## data_device
 
@@ -174,3 +176,42 @@ Intel Optane (probably, not tested yet).
 
 Clients don't need to be aware of disk_alignment, so it's not required to
 put a modified value into etcd key /vitastor/config/global.
+
+## data_csum_type
+
+- Type: string
+- Default: none
+
+Data checksum type to use. May be "crc32c" or "none". Set to "crc32c" to
+enable data checksums.
+
+## csum_block_size
+
+- Type: integer
+- Default: 4096
+
+Checksum calculation block size.
+
+Must be equal or a multiple of [bitmap_granularity](layout-cluster.en.md#bitmap_granularity)
+(which is usually 4 KB).
+
+Checksums increase metadata size by 4 bytes per each csum_block_size of data.
+
+Checksums are always a compromise:
+1. You either sacrifice +1 GB RAM per 1 TB of data
+2. Or you raise csum_block_size, for example, to 32k and sacrifice
+   50% random write iops due to checksum read-modify-write
+3. Or you turn off [inmemory_metadata](osd.en.md#inmemory_metadata) and
+   sacrifice 50% random read iops due to checksum reads
+
+Option 1 (default) is recommended for all-flash setups because these usually
+have enough RAM.
+
+Option 2 is recommended for HDD-only setups. HDD-only setups usually do NOT
+have enough RAM for the default 4 KB csum_block_size.
+
+Option 3 is recommended for SSD+HDD setups (because metadata SSDs will handle
+extra reads without any performance drop) and also *maybe* for NVMe all-flash
+setups when you don't have enough RAM (because NVMe drives have plenty
+of read iops to spare). You may also consider enabling
+[cached_read_meta](osd.en.md#cached_read_meta) in this case.

docs/config/layout-osd.ru.md

@@ -25,6 +25,8 @@
 - [disable_journal_fsync](#disable_journal_fsync)
 - [disable_device_lock](#disable_device_lock)
 - [disk_alignment](#disk_alignment)
+- [data_csum_type](#data_csum_type)
+- [csum_block_size](#csum_block_size)
 
 ## data_device
 
@@ -183,3 +185,52 @@ journal_block_size и meta_block_size. Однако единственные SSD
 
 Клиентам не обязательно знать про disk_alignment, так что помещать значение
 этого параметра в etcd в /vitastor/config/global не нужно.
+
+## data_csum_type
+
+- Тип: строка
+- Значение по умолчанию: none
+
+Тип используемых OSD контрольных сумм данных. Может быть "crc32c" или "none".
+Установите в "crc32c", чтобы включить расчёт и проверку контрольных сумм данных.
+
+Следует понимать, что контрольные суммы в зависимости от размера блока их
+расчёта либо увеличивают потребление памяти, либо снижают производительность.
+Подробнее смотрите в описании параметра [csum_block_size](#csum_block_size).
+
+## csum_block_size
+
+- Тип: целое число
+- Значение по умолчанию: 4096
+
+Размер блока расчёта контрольных сумм.
+
+Должен быть равен или кратен [bitmap_granularity](layout-cluster.ru.md#bitmap_granularity)
+(который обычно равен 4 КБ).
+
+Контрольные суммы увеличивают размер метаданных на 4 байта на каждые
+csum_block_size данных.
+
+Контрольные суммы - это всегда компромисс:
+1. Вы либо жертвуете потреблением +1 ГБ памяти на 1 ТБ дискового пространства
+2. Либо вы повышаете csum_block_size до, скажем, 32k и жертвуете 50%
+   скорости случайной записи из-за цикла чтения-изменения-записи для расчёта
+   новых контрольных сумм
+3. Либо вы отключаете [inmemory_metadata](osd.ru.md#inmemory_metadata) и
+   жертвуете 50% скорости случайного чтения из-за чтения контрольных сумм
+   с диска
+
+Вариант 1 (при настройках по умолчанию) рекомендуется для SSD (All-Flash)
+кластеров, потому что памяти в них обычно хватает.
+
+Вариант 2 рекомендуется для кластеров на одних жёстких дисках (без SSD
+под метаданные). На 4 кб блок контрольной суммы памяти в таких кластерах
+обычно НЕ хватает.
+
+Вариант 3 рекомендуется для гибридных кластеров (SSD+HDD), потому что
+скорости SSD под метаданными хватит, чтобы обработать дополнительные чтения
+без снижения производительности. Также вариант 3 *может* рекомендоваться
+для All-Flash кластеров на основе NVMe-дисков, когда памяти НЕ достаточно,
+потому что NVMe-диски имеют огромный запас производительности по чтению.
+В таких случаях, возможно, также имеет смысл включать параметр
+[cached_read_meta](osd.ru.md#cached_read_meta).

docs/config/network.en.md

@@ -153,6 +153,7 @@ operations.
 - Type: seconds
 - Default: 5
 - Minimum: 1
+- Can be changed online: yes
 
 Interval before attempting to reconnect to an unavailable OSD.
 
@@ -161,6 +162,7 @@ Interval before attempting to reconnect to an unavailable OSD.
 - Type: seconds
 - Default: 5
 - Minimum: 1
+- Can be changed online: yes
 
 Timeout for OSD connection attempts.
 
@@ -169,6 +171,7 @@ Timeout for OSD connection attempts.
 - Type: seconds
 - Default: 5
 - Minimum: 1
+- Can be changed online: yes
 
 OSD connection inactivity time after which clients and other OSDs send
 keepalive requests to check state of the connection.
@@ -178,6 +181,7 @@ keepalive requests to check state of the connection.
 - Type: seconds
 - Default: 5
 - Minimum: 1
+- Can be changed online: yes
 
 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
@@ -188,6 +192,7 @@ is scheduled.
 - Type: milliseconds
 - Default: 500
 - Minimum: 50
+- 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
@@ -197,6 +202,7 @@ the time for the clients to wait before re-attempting such I/O requests.
 
 - Type: integer
 - Default: 5
+- Can be changed online: yes
 
 Maximum number of attempts for etcd requests which can't be retried
 indefinitely.
@@ -205,6 +211,7 @@ indefinitely.
 
 - Type: milliseconds
 - Default: 1000
+- Can be changed online: yes
 
 Timeout for etcd requests which should complete quickly, like lease refresh.
 
@@ -212,6 +219,7 @@ Timeout for etcd requests which should complete quickly, like lease refresh.
 
 - Type: milliseconds
 - Default: 5000
+- Can be changed online: yes
 
 Timeout for etcd requests which are allowed to wait for some time.
 
@@ -219,6 +227,7 @@ Timeout for etcd requests which are allowed to wait for some time.
 
 - Type: seconds
 - Default: max(30, etcd_report_interval*2)
+- Can be changed online: yes
 
 Timeout for etcd connection HTTP Keep-Alive. Should be higher than
 etcd_report_interval to guarantee that keepalive actually works.
@@ -227,6 +236,7 @@ etcd_report_interval to guarantee that keepalive actually works.
 
 - Type: seconds
 - Default: 30
+- Can be changed online: yes
 
 etcd websocket ping interval required to keep the connection alive and
 detect disconnections quickly.
@@ -235,6 +245,7 @@ detect disconnections quickly.
 
 - Type: integer
 - Default: 33554432
+- Can be changed online: yes
 
 Without immediate_commit=all this parameter sets the limit of "dirty"
 (not committed by fsync) data allowed by the client before forcing an

docs/config/network.ru.md

@@ -161,6 +161,7 @@ OSD в любом случае согласовывают реальное зн
 - Тип: секунды
 - Значение по умолчанию: 5
 - Минимальное значение: 1
+- Можно менять на лету: да
 
 Время ожидания перед повторной попыткой соединиться с недоступным OSD.
 
@@ -169,6 +170,7 @@ OSD в любом случае согласовывают реальное зн
 - Тип: секунды
 - Значение по умолчанию: 5
 - Минимальное значение: 1
+- Можно менять на лету: да
 
 Максимальное время ожидания попытки соединения с OSD.
 
@@ -177,6 +179,7 @@ OSD в любом случае согласовывают реальное зн
 - Тип: секунды
 - Значение по умолчанию: 5
 - Минимальное значение: 1
+- Можно менять на лету: да
 
 Время неактивности соединения с OSD, после которого клиенты или другие OSD
 посылают запрос проверки состояния соединения.
@@ -186,6 +189,7 @@ OSD в любом случае согласовывают реальное зн
 - Тип: секунды
 - Значение по умолчанию: 5
 - Минимальное значение: 1
+- Можно менять на лету: да
 
 Максимальное время ожидания ответа на запрос проверки состояния соединения.
 Если OSD не отвечает за это время, соединение отключается и производится
@@ -196,6 +200,7 @@ OSD в любом случае согласовывают реальное зн
 - Тип: миллисекунды
 - Значение по умолчанию: 500
 - Минимальное значение: 50
+- 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,
@@ -207,6 +212,7 @@ OSD в любом случае согласовывают реальное зн
 
 - Тип: целое число
 - Значение по умолчанию: 5
+- Можно менять на лету: да
 
 Максимальное число попыток выполнения запросов к etcd для тех запросов,
 которые нельзя повторять бесконечно.
@@ -215,6 +221,7 @@ OSD в любом случае согласовывают реальное зн
 
 - Тип: миллисекунды
 - Значение по умолчанию: 1000
+- Можно менять на лету: да
 
 Максимальное время выполнения запросов к etcd, которые должны завершаться
 быстро, таких, как обновление резервации (lease).
@@ -223,6 +230,7 @@ OSD в любом случае согласовывают реальное зн
 
 - Тип: миллисекунды
 - Значение по умолчанию: 5000
+- Можно менять на лету: да
 
 Максимальное время выполнения запросов к etcd, для которых не обязательно
 гарантировать быстрое выполнение.
@@ -231,6 +239,7 @@ OSD в любом случае согласовывают реальное зн
 
 - Тип: секунды
 - Значение по умолчанию: max(30, etcd_report_interval*2)
+- Можно менять на лету: да
 
 Таймаут для HTTP Keep-Alive в соединениях к etcd. Должен быть больше, чем
 etcd_report_interval, чтобы keepalive гарантированно работал.
@@ -239,6 +248,7 @@ etcd_report_interval, чтобы keepalive гарантированно рабо
 
 - Тип: секунды
 - Значение по умолчанию: 30
+- Можно менять на лету: да
 
 Интервал проверки живости вебсокет-подключений к etcd.
 
@@ -246,6 +256,7 @@ etcd_report_interval, чтобы keepalive гарантированно рабо
 
 - Тип: целое число
 - Значение по умолчанию: 33554432
+- Можно менять на лету: да
 
 При работе без immediate_commit=all - это лимит объёма "грязных" (не
 зафиксированных fsync-ом) данных, при достижении которого клиент будет

docs/config/osd.en.md

@@ -7,7 +7,8 @@
 # Runtime OSD Parameters
 
 These parameters only apply to OSDs, are not fixed at the moment of OSD drive
-initialization and can be changed with an OSD restart.
+initialization and can be changed - either with an OSD restart or, for some of
+them, even without restarting by updating configuration in etcd.
 
 - [etcd_report_interval](#etcd_report_interval)
 - [run_primary](#run_primary)
@@ -30,6 +31,9 @@ initialization and can be changed with an OSD restart.
 - [max_flusher_count](#max_flusher_count)
 - [inmemory_metadata](#inmemory_metadata)
 - [inmemory_journal](#inmemory_journal)
+- [cached_read_data](#cached_read_data)
+- [cached_read_meta](#cached_read_meta)
+- [cached_read_journal](#cached_read_journal)
 - [journal_sector_buffer_count](#journal_sector_buffer_count)
 - [journal_no_same_sector_overwrites](#journal_no_same_sector_overwrites)
 - [throttle_small_writes](#throttle_small_writes)
@@ -38,6 +42,14 @@ initialization and can be changed with an OSD restart.
 - [throttle_target_parallelism](#throttle_target_parallelism)
 - [throttle_threshold_us](#throttle_threshold_us)
 - [osd_memlock](#osd_memlock)
+- [auto_scrub](#auto_scrub)
+- [no_scrub](#no_scrub)
+- [scrub_interval](#scrub_interval)
+- [scrub_queue_depth](#scrub_queue_depth)
+- [scrub_sleep](#scrub_sleep)
+- [scrub_list_limit](#scrub_list_limit)
+- [scrub_find_best](#scrub_find_best)
+- [scrub_ec_max_bruteforce](#scrub_ec_max_bruteforce)
 
 ## etcd_report_interval
 
@@ -91,6 +103,7 @@ OSD by hand.
 
 - Type: seconds
 - Default: 5
+- Can be changed online: yes
 
 Time interval at which automatic fsyncs/flushes are issued by each OSD when
 the immediate_commit mode if disabled. fsyncs are required because without
@@ -103,6 +116,7 @@ issue fsyncs at all.
 
 - Type: integer
 - Default: 128
+- Can be changed online: yes
 
 Same as autosync_interval, but sets the maximum number of uncommitted write
 operations before issuing an fsync operation internally.
@@ -111,6 +125,7 @@ operations before issuing an fsync operation internally.
 
 - Type: integer
 - Default: 4
+- Can be changed online: yes
 
 Maximum recovery operations per one primary OSD at any given moment of time.
 Currently it's the only parameter available to tune the speed or recovery
@@ -120,6 +135,7 @@ and rebalancing, but it's planned to implement more.
 
 - Type: integer
 - Default: 128
+- Can be changed online: yes
 
 Number of recovery operations before switching to recovery of the next PG.
 The idea is to mix all PGs during recovery for more even space and load
@@ -130,6 +146,7 @@ Degraded PGs are anyway scanned first.
 
 - Type: integer
 - Default: 16
+- Can be changed online: yes
 
 Maximum number of recovery operations before issuing an additional fsync.
 
@@ -145,6 +162,7 @@ the underlying device. This may be useful for recovery purposes.
 
 - Type: boolean
 - Default: false
+- Can be changed online: yes
 
 Disable automatic background recovery of objects. Note that it doesn't
 affect implicit recovery of objects happening during writes - a write is
@@ -154,6 +172,7 @@ always made to a full set of at least pg_minsize OSDs.
 
 - Type: boolean
 - Default: false
+- Can be changed online: yes
 
 Disable background movement of data between different OSDs. Disabling it
 means that PGs in the `has_misplaced` state will be left in it indefinitely.
@@ -162,6 +181,7 @@ means that PGs in the `has_misplaced` state will be left in it indefinitely.
 
 - Type: seconds
 - Default: 3
+- Can be changed online: yes
 
 Time interval at which OSDs print simple human-readable operation
 statistics on stdout.
@@ -170,6 +190,7 @@ statistics on stdout.
 
 - Type: seconds
 - Default: 10
+- Can be changed online: yes
 
 Time interval at which OSDs dump slow or stuck operations on stdout, if
 they're any. Also it's the time after which an operation is considered
@@ -179,6 +200,7 @@ they're any. Also it's the time after which an operation is considered
 
 - Type: seconds
 - Default: 60
+- Can be changed online: yes
 
 Number of seconds after which a deleted inode is removed from OSD statistics.
 
@@ -186,6 +208,7 @@ Number of seconds after which a deleted inode is removed from OSD statistics.
 
 - Type: integer
 - Default: 128
+- Can be changed online: yes
 
 Parallel client write operation limit per one OSD. Operations that exceed
 this limit are pushed to a temporary queue instead of being executed
@@ -195,6 +218,7 @@ immediately.
 
 - Type: integer
 - Default: 1
+- Can be changed online: yes
 
 Flusher is a micro-thread that moves data from the journal to the data
 area of the device. Their number is auto-tuned between minimum and maximum.
@@ -204,6 +228,7 @@ Minimum number is set by this parameter.
 
 - Type: integer
 - Default: 256
+- Can be changed online: yes
 
 Maximum number of journal flushers (see above min_flusher_count).
 
@@ -233,6 +258,46 @@ is typically very small because it's sufficient to have 16-32 MB journal
 for SSD OSDs. However, in theory it's possible that you'll want to turn it
 off for hybrid (HDD+SSD) OSDs with large journals on quick devices.
 
+## cached_read_data
+
+- Type: boolean
+- Default: false
+
+Read data through Linux page cache, i.e. use a file descriptor opened without
+O_DIRECT for data reads. May improve read performance for frequently accessed
+data if it fits in RAM. Memory in page cache is shared by all processes and
+not accounted in OSD memory consumption.
+
+## cached_read_meta
+
+- Type: boolean
+- Default: false
+
+Read metadata through Linux page cache. May be beneficial when checksums
+are enabled and [inmemory_metadata](#inmemory_metadata) is disabled, because
+in this case metadata blocks are read from disk to verify checksums on every
+read request and caching them may reduce this extra read load.
+
+Absolutely pointless to enable with enabled inmemory_metadata because all
+metadata is kept in memory anyway, and likely pointless without checksums,
+because in that case, metadata blocks are read from disk only during journal
+flushing.
+
+If the same device is used for data and metadata, enabling [cached_read_data](#cached_read_data)
+also enables this parameter, given that it isn't turned off explicitly.
+
+## cached_read_journal
+
+- Type: boolean
+- Default: false
+
+Read buffered data from journal through Linux page cache. Does not have sense
+without disabling [inmemory_journal](#inmemory_journal), which, again, is
+enabled by default.
+
+If the same device is used for metadata and journal, enabling [cached_read_meta](#cached_read_meta)
+also enables this parameter, given that it isn't turned off explicitly.
+
 ## journal_sector_buffer_count
 
 - Type: integer
@@ -260,6 +325,7 @@ Most (99%) other SSDs don't need this option.
 
 - Type: boolean
 - Default: false
+- Can be changed online: yes
 
 Enable soft throttling of small journaled writes. Useful for hybrid OSDs
 with fast journal/metadata devices and slow data devices. The idea is that
@@ -277,6 +343,7 @@ fills up.
 
 - Type: integer
 - Default: 100
+- Can be changed online: yes
 
 Target maximum number of throttled operations per second under the condition
 of full journal. Set it to approximate random write iops of your data devices
@@ -286,6 +353,7 @@ of full journal. Set it to approximate random write iops of your data devices
 
 - Type: integer
 - Default: 100
+- Can be changed online: yes
 
 Target maximum bandwidth in MB/s of throttled operations per second under
 the condition of full journal. Set it to approximate linear write
@@ -295,6 +363,7 @@ performance of your data devices (HDDs).
 
 - Type: integer
 - Default: 1
+- Can be changed online: yes
 
 Target maximum parallelism of throttled operations under the condition of
 full journal. Set it to approximate internal parallelism of your data
@@ -304,6 +373,7 @@ devices (1 for HDDs, 4-8 for SSDs).
 
 - Type: microseconds
 - Default: 50
+- Can be changed online: yes
 
 Minimal computed delay to be applied to throttled operations. Usually
 doesn't need to be changed.
@@ -313,4 +383,103 @@ doesn't need to be changed.
 - Type: boolean
 - Default: false
 
-Lock all OSD memory to prevent it from being unloaded into swap with mlockall(). Requires sufficient ulimit -l (max locked memory).
+Lock all OSD memory to prevent it from being unloaded into swap with
+mlockall(). Requires sufficient ulimit -l (max locked memory).
+
+## auto_scrub
+
+- Type: boolean
+- Default: false
+- Can be changed online: yes
+
+Data scrubbing is the process of background verification of copies to find
+and repair corrupted blocks. It's not run automatically by default since
+it's a new feature. Set this parameter to true to enable automatic scrubs.
+
+This parameter makes OSDs automatically schedule data scrubbing of clean PGs
+every `scrub_interval` (see below). You can also start/schedule scrubbing
+manually by setting `next_scrub` JSON key to the desired UNIX time of the
+next scrub in `/pg/history/...` values in etcd.
+
+## no_scrub
+
+- Type: boolean
+- Default: false
+- Can be changed online: yes
+
+Temporarily disable scrubbing and stop running scrubs.
+
+## scrub_interval
+
+- Type: string
+- Default: 30d
+- Can be changed online: yes
+
+Default automatic scrubbing interval for all pools. Numbers without suffix
+are treated as seconds, possible unit suffixes include 's' (seconds),
+'m' (minutes), 'h' (hours), 'd' (days), 'M' (months) and 'y' (years).
+
+## scrub_queue_depth
+
+- Type: integer
+- Default: 1
+- Can be changed online: yes
+
+Number of parallel scrubbing operations per one OSD.
+
+## scrub_sleep
+
+- Type: milliseconds
+- Default: 0
+- Can be changed online: yes
+
+Additional interval between two consecutive scrubbing operations on one OSD.
+Can be used to slow down scrubbing if it affects user load too much.
+
+## scrub_list_limit
+
+- Type: integer
+- Default: 1000
+- Can be changed online: yes
+
+Number of objects to list in one listing operation during scrub.
+
+## scrub_find_best
+
+- Type: boolean
+- Default: true
+- Can be changed online: yes
+
+Find and automatically restore best versions of objects with unmatched
+copies. In replicated setups, the best version is the version with most
+matching replicas. In EC setups, the best version is the subset of data
+and parity chunks without mismatches.
+
+The hypothetical situation where you might want to disable it is when
+you have 3 replicas and you are paranoid that 2 HDDs out of 3 may silently
+corrupt an object in the same way (for example, zero it out) and only
+1 HDD will remain good. In this case disabling scrub_find_best may help
+you to recover the data! See also scrub_ec_max_bruteforce below.
+
+## scrub_ec_max_bruteforce
+
+- Type: integer
+- Default: 100
+- Can be changed online: yes
+
+Vitastor can locate corrupted chunks in EC setups with more than 1 parity
+chunk by brute-forcing all possible error locations. This configuration
+value limits the maximum number of checked combinations. You can try to
+increase it if you have EC N+K setup with N and K large enough for
+combination count `C(N+K-1, K-1) = (N+K-1)! / (K-1)! / N!` to be greater
+than the default 100.
+
+If there are too many possible combinations or if multiple combinations give
+correct results then objects are marked inconsistent and aren't recovered
+automatically.
+
+In replicated setups bruteforcing isn't needed, Vitastor just assumes that
+the variant with most available equal copies is correct. For example, if
+you have 3 replicas and 1 of them differs, this one is considered to be
+corrupted. But if there is no "best" version with more copies than all
+others have then the object is also marked as inconsistent.

docs/config/osd.ru.md

@@ -8,7 +8,8 @@
 
 Данные параметры используются только OSD, но, в отличие от дисковых параметров,
 не фиксируются в момент инициализации дисков OSD и могут быть изменены в любой
-момент с перезапуском OSD.
+момент с помощью перезапуска OSD, а некоторые и без перезапуска, с помощью
+изменения конфигурации в etcd.
 
 - [etcd_report_interval](#etcd_report_interval)
 - [run_primary](#run_primary)
@@ -31,6 +32,9 @@
 - [max_flusher_count](#max_flusher_count)
 - [inmemory_metadata](#inmemory_metadata)
 - [inmemory_journal](#inmemory_journal)
+- [cached_read_data](#cached_read_data)
+- [cached_read_meta](#cached_read_meta)
+- [cached_read_journal](#cached_read_journal)
 - [journal_sector_buffer_count](#journal_sector_buffer_count)
 - [journal_no_same_sector_overwrites](#journal_no_same_sector_overwrites)
 - [throttle_small_writes](#throttle_small_writes)
@@ -39,6 +43,14 @@
 - [throttle_target_parallelism](#throttle_target_parallelism)
 - [throttle_threshold_us](#throttle_threshold_us)
 - [osd_memlock](#osd_memlock)
+- [auto_scrub](#auto_scrub)
+- [no_scrub](#no_scrub)
+- [scrub_interval](#scrub_interval)
+- [scrub_queue_depth](#scrub_queue_depth)
+- [scrub_sleep](#scrub_sleep)
+- [scrub_list_limit](#scrub_list_limit)
+- [scrub_find_best](#scrub_find_best)
+- [scrub_ec_max_bruteforce](#scrub_ec_max_bruteforce)
 
 ## etcd_report_interval
 
@@ -93,6 +105,7 @@ RUNNING), подходящий под заданную маску. Также н
 
 - Тип: секунды
 - Значение по умолчанию: 5
+- Можно менять на лету: да
 
 Временной интервал отправки автоматических fsync-ов (операций очистки кэша)
 каждым OSD для случая, когда режим immediate_commit отключён. fsync-и нужны
@@ -105,6 +118,7 @@ OSD, чтобы успевать очищать журнал - без них OSD
 
 - Тип: целое число
 - Значение по умолчанию: 128
+- Можно менять на лету: да
 
 Аналогично autosync_interval, но задаёт не временной интервал, а
 максимальное количество незафиксированных операций записи перед
@@ -114,6 +128,7 @@ OSD, чтобы успевать очищать журнал - без них OSD
 
 - Тип: целое число
 - Значение по умолчанию: 4
+- Можно менять на лету: да
 
 Максимальное число операций восстановления на одном первичном OSD в любой
 момент времени. На данный момент единственный параметр, который можно менять
@@ -124,6 +139,7 @@ OSD, чтобы успевать очищать журнал - без них OSD
 
 - Тип: целое число
 - Значение по умолчанию: 128
+- Можно менять на лету: да
 
 Число операций восстановления перед переключением на восстановление другой PG.
 Идея заключается в том, чтобы восстанавливать все PG одновременно для более
@@ -135,6 +151,7 @@ OSD, чтобы успевать очищать журнал - без них OSD
 
 - Тип: целое число
 - Значение по умолчанию: 16
+- Можно менять на лету: да
 
 Максимальное число операций восстановления перед дополнительным fsync.
 
@@ -150,6 +167,7 @@ OSD, чтобы успевать очищать журнал - без них OSD
 
 - Тип: булево (да/нет)
 - Значение по умолчанию: false
+- Можно менять на лету: да
 
 Отключить автоматическое фоновое восстановление объектов. Обратите внимание,
 что эта опция не отключает восстановление объектов, происходящее при
@@ -160,6 +178,7 @@ OSD.
 
 - Тип: булево (да/нет)
 - Значение по умолчанию: false
+- Можно менять на лету: да
 
 Отключить фоновое перемещение объектов между разными OSD. Отключение
 означает, что PG, находящиеся в состоянии `has_misplaced`, будут оставлены
@@ -169,6 +188,7 @@ OSD.
 
 - Тип: секунды
 - Значение по умолчанию: 3
+- Можно менять на лету: да
 
 Временной интервал, с которым OSD печатают простую человекочитаемую
 статистику выполнения операций в стандартный вывод.
@@ -177,6 +197,7 @@ OSD.
 
 - Тип: секунды
 - Значение по умолчанию: 10
+- Можно менять на лету: да
 
 Временной интервал, с которым OSD выводят в стандартный вывод список
 медленных или зависших операций, если таковые имеются. Также время, при
@@ -186,6 +207,7 @@ OSD.
 
 - Тип: секунды
 - Значение по умолчанию: 60
+- Можно менять на лету: да
 
 Число секунд, через которое удалённые инод удаляется и из статистики OSD.
 
@@ -193,6 +215,7 @@ OSD.
 
 - Тип: целое число
 - Значение по умолчанию: 128
+- Можно менять на лету: да
 
 Максимальное число одновременных клиентских операций записи на один OSD.
 Операции, превышающие этот лимит, не исполняются сразу, а сохраняются во
@@ -202,6 +225,7 @@ OSD.
 
 - Тип: целое число
 - Значение по умолчанию: 1
+- Можно менять на лету: да
 
 Flusher - это микро-поток (корутина), которая копирует данные из журнала в
 основную область устройства данных. Их число настраивается динамически между
@@ -211,6 +235,7 @@ Flusher - это микро-поток (корутина), которая коп
 
 - Тип: целое число
 - Значение по умолчанию: 256
+- Можно менять на лету: да
 
 Максимальное число микро-потоков очистки журнала (см. выше min_flusher_count).
 
@@ -241,6 +266,51 @@ Flusher - это микро-поток (корутина), которая коп
 параметра может оказаться полезным для гибридных OSD (HDD+SSD) с большими
 журналами, расположенными на быстром по сравнению с HDD устройстве.
 
+## cached_read_data
+
+- Тип: булево (да/нет)
+- Значение по умолчанию: false
+
+Читать данные через системный кэш Linux (page cache), то есть, использовать
+для чтения данных файловый дескриптор, открытый без флага O_DIRECT. Может
+улучшить производительность чтения для часто используемых данных, если они
+помещаются в память. Память кэша разделяется между всеми процессами в
+системе и не учитывается в потреблении памяти процессом OSD.
+
+## cached_read_meta
+
+- Тип: булево (да/нет)
+- Значение по умолчанию: false
+
+Читать метаданные через системный кэш Linux. Может быть полезно, когда
+включены контрольные суммы, а параметр [inmemory_metadata](#inmemory_metadata)
+отключён, так как в этом случае блоки метаданных читаются с диска при каждом
+запросе чтения для проверки контрольных сумм и их кэширование может снизить
+дополнительную нагрузку на диск.
+
+Абсолютно бессмысленно включать данный параметр, если параметр
+inmemory_metadata включён (по умолчанию это так), и также вероятно
+бессмысленно включать его, если не включены контрольные суммы, так как в
+этом случае блоки метаданных читаются с диска только во время сброса
+журнала.
+
+Если одно и то же устройство используется для данных и метаданных, включение
+[cached_read_data](#cached_read_data) также включает данный параметр, при
+условии, что он не отключён явным образом.
+
+## cached_read_journal
+
+- Тип: булево (да/нет)
+- Значение по умолчанию: false
+
+Читать буферизованные в журнале данные через системный кэш Linux. Не имеет
+смысла без отключения параметра [inmemory_journal](#inmemory_journal),
+который, опять же, по умолчанию включён.
+
+Если одно и то же устройство используется для метаданных и журнала,
+включение [cached_read_meta](#cached_read_meta) также включает данный
+параметр, при условии, что он не отключён явным образом.
+
 ## journal_sector_buffer_count
 
 - Тип: целое число
@@ -270,6 +340,7 @@ Flusher - это микро-поток (корутина), которая коп
 
 - Тип: булево (да/нет)
 - Значение по умолчанию: false
+- Можно менять на лету: да
 
 Разрешить мягкое ограничение скорости журналируемой записи. Полезно для
 гибридных OSD с быстрыми устройствами метаданных и медленными устройствами
@@ -288,6 +359,7 @@ Flusher - это микро-поток (корутина), которая коп
 
 - Тип: целое число
 - Значение по умолчанию: 100
+- Можно менять на лету: да
 
 Расчётное максимальное число ограничиваемых операций в секунду при условии
 отсутствия свободного места в журнале. Устанавливайте приблизительно равным
@@ -298,6 +370,7 @@ Flusher - это микро-поток (корутина), которая коп
 
 - Тип: целое число
 - Значение по умолчанию: 100
+- Можно менять на лету: да
 
 Расчётный максимальный размер в МБ/с ограничиваемых операций в секунду при
 условии отсутствия свободного места в журнале. Устанавливайте приблизительно
@@ -308,6 +381,7 @@ Flusher - это микро-поток (корутина), которая коп
 
 - Тип: целое число
 - Значение по умолчанию: 1
+- Можно менять на лету: да
 
 Расчётный максимальный параллелизм ограничиваемых операций в секунду при
 условии отсутствия свободного места в журнале. Устанавливайте приблизительно
@@ -318,6 +392,7 @@ Flusher - это микро-поток (корутина), которая коп
 
 - Тип: микросекунды
 - Значение по умолчанию: 50
+- Можно менять на лету: да
 
 Минимальная применимая к ограничиваемым операциям задержка. Обычно не
 требует изменений.
@@ -327,4 +402,113 @@ Flusher - это микро-поток (корутина), которая коп
 - Тип: булево (да/нет)
 - Значение по умолчанию: false
 
-Блокировать всю память OSD с помощью mlockall, чтобы запретить её выгрузку в пространство подкачки. Требует достаточного значения ulimit -l (лимита заблокированной памяти).
+Блокировать всю память OSD с помощью mlockall, чтобы запретить её выгрузку
+в пространство подкачки. Требует достаточного значения ulimit -l (лимита
+заблокированной памяти).
+
+## auto_scrub
+
+- Тип: булево (да/нет)
+- Значение по умолчанию: false
+- Можно менять на лету: да
+
+Скраб - процесс фоновой проверки копий данных, предназначенный, чтобы
+находить и исправлять повреждённые блоки. По умолчанию эти проверки ещё не
+запускаются автоматически, так как являются новой функцией. Чтобы включить
+автоматическое планирование скрабов, установите данный параметр в true.
+
+Включённый параметр заставляет OSD автоматически планировать фоновую
+проверку чистых PG раз в `scrub_interval` (см. ниже). Вы также можете
+запустить или запланировать проверку вручную, установив значение ключа JSON
+`next_scrub` внутри ключей etcd `/pg/history/...` в UNIX-время следующей
+желаемой проверки.
+
+## no_scrub
+
+- Тип: булево (да/нет)
+- Значение по умолчанию: false
+- Можно менять на лету: да
+
+Временно отключить и остановить запущенные скрабы.
+
+## scrub_interval
+
+- Тип: строка
+- Значение по умолчанию: 30d
+- Можно менять на лету: да
+
+Интервал автоматической фоновой проверки по умолчанию для всех пулов.
+Значения без указанной единицы измерения считаются в секундах, допустимые
+символы единиц измерения в конце: 's' (секунды),
+'m' (минуты), 'h' (часы), 'd' (дни), 'M' (месяца) или 'y' (годы).
+
+## scrub_queue_depth
+
+- Тип: целое число
+- Значение по умолчанию: 1
+- Можно менять на лету: да
+
+Число параллельных операций фоновой проверки на один OSD.
+
+## scrub_sleep
+
+- Тип: миллисекунды
+- Значение по умолчанию: 0
+- Можно менять на лету: да
+
+Дополнительный интервал ожидания после фоновой проверки каждого объекта на
+одном OSD. Может использоваться для замедления скраба, если он слишком
+сильно влияет на пользовательскую нагрузку.
+
+## scrub_list_limit
+
+- Тип: целое число
+- Значение по умолчанию: 1000
+- Можно менять на лету: да
+
+Размер загружаемых за одну операцию списков объектов в процессе фоновой
+проверки.
+
+## scrub_find_best
+
+- Тип: булево (да/нет)
+- Значение по умолчанию: true
+- Можно менять на лету: да
+
+Находить и автоматически восстанавливать "лучшие версии" объектов с
+несовпадающими копиями/частями. При использовании репликации "лучшая"
+версия - версия, доступная в большем числе экземпляров, чем другие. При
+использовании кодов коррекции ошибок "лучшая" версия - это подмножество
+частей данных и чётности, полностью соответствующих друг другу.
+
+Гипотетическая ситуация, в которой вы можете захотеть отключить этот
+поиск - это если у вас 3 реплики и вы боитесь, что 2 диска из 3 могут
+незаметно и одинаково повредить данные одного и того же объекта, например,
+занулив его, и только 1 диск останется неповреждённым. В этой ситуации
+отключение этого параметра поможет вам восстановить данные! Смотрите также
+описание следующего параметра - scrub_ec_max_bruteforce.
+
+## scrub_ec_max_bruteforce
+
+- Тип: целое число
+- Значение по умолчанию: 100
+- Можно менять на лету: да
+
+Vitastor старается определить повреждённые части объектов при использовании
+EC (кодов коррекции ошибок) с более, чем 1 диском чётности, путём перебора
+всех возможных комбинаций ошибочных частей. Данное значение конфигурации
+ограничивает число перебираемых комбинаций. Вы можете попробовать поднять
+его, если используете схему кодирования EC N+K с N и K, достаточно большими
+для того, чтобы число сочетаний `C(N+K-1, K-1) = (N+K-1)! / (K-1)! / N!`
+было больше, чем стандартное значение 100.
+
+Если возможных комбинаций слишком много или если корректная комбинаций не
+определяется однозначно, объекты помечаются неконсистентными (inconsistent)
+и не восстанавливаются автоматически.
+
+При использовании репликации перебор не нужен, Vitastor просто предполагает,
+что вариант объекта с наибольшим количеством одинаковых копий корректен.
+Например, если вы используете 3 реплики и 1 из них отличается, эта 1 копия
+считается некорректной. Однако, если "лучшую" версию с числом доступных
+копий большим, чем у всех других версий, найти невозможно, то объект тоже
+маркируется неконсистентным.

docs/config/pool.en.md

@@ -40,6 +40,7 @@ Parameters:
 - [root_node](#root_node)
 - [osd_tags](#osd_tags)
 - [primary_affinity_tags](#primary_affinity_tags)
+- [scrub_interval](#scrub_interval)
 
 Examples:
 
@@ -272,6 +273,13 @@ Specifies OSD tags to prefer putting primary OSDs in this pool to.
 Note that for EC/XOR pools Vitastor always prefers to put primary OSD on one
 of the OSDs containing a data chunk for a PG.
 
+## scrub_interval
+
+- Type: time interval (number + unit s/m/h/d/M/y)
+
+Automatic scrubbing interval for this pool. Overrides
+[global scrub_interval setting](osd.en.md#scrub_interval).
+
 # Examples
 
 ## Replicated pool

docs/config/pool.ru.md

@@ -39,6 +39,7 @@
 - [root_node](#root_node)
 - [osd_tags](#osd_tags)
 - [primary_affinity_tags](#primary_affinity_tags)
+- [scrub_interval](#scrub_interval)
 
 Примеры:
 
@@ -276,6 +277,13 @@ PG в Vitastor эферемерны, то есть вы можете менят
 для PG этого пула. Имейте в виду, что для EC-пулов Vitastor также всегда
 предпочитает помещать первичный OSD на один из OSD с данными, а не с чётностью.
 
+## scrub_interval
+
+- Тип: временной интервал (число + единица измерения s/m/h/d/M/y)
+
+Интервал скраба, то есть, автоматической фоновой проверки данных для данного пула.
+Переопределяет [глобальную настройку scrub_interval](osd.ru.md#scrub_interval).
+
 # Примеры
 
 ## Реплицированный пул

docs/config/src/common.yml

@@ -11,13 +11,21 @@
 - name: etcd_address
   type: string or array of strings
   type_ru: строка или массив строк
+  online: true
   info: |
     etcd connection endpoint(s). Multiple endpoints may be delimited by "," or
     specified in a JSON array `["10.0.115.10:2379/v3","10.0.115.11:2379/v3"]`.
     Note that https is not supported for etcd connections yet.
+
+    etcd connection endpoints can be changed online by updating global
+    configuration in etcd itself - this allows to switch the cluster to new
+    etcd addresses without downtime.
   info_ru: |
     Адрес(а) подключения к etcd. Несколько адресов могут разделяться запятой
     или указываться в виде JSON-массива `["10.0.115.10:2379/v3","10.0.115.11:2379/v3"]`.
+
+    Адреса подключения к etcd можно поменять на лету, обновив конфигурацию в
+    самом etcd - это позволяет переключить кластер на новые etcd без остановки.
 - name: etcd_prefix
   type: string
   default: "/vitastor"
@@ -31,5 +39,6 @@
 - name: log_level
   type: int
   default: 0
+  online: true
   info: Log level. Raise if you want more verbose output.
   info_ru: Уровень логгирования. Повысьте, если хотите более подробный вывод.

docs/config/src/include.js

@@ -0,0 +1,145 @@
+#!/usr/bin/nodejs
+
+const fsp = require('fs').promises;
+
+run(process.argv).catch(console.error);
+
+async function run(argv)
+{
+    if (argv.length < 3)
+    {
+        console.log('Markdown preprocessor\nUSAGE: ./include.js file.md');
+        return;
+    }
+    const index_file = await fsp.realpath(argv[2]);
+    const re = /(\{\{[\s\S]*?\}\}|\[[^\]]+\]\([^\)]+\)|(?:^|\n)#[^\n]+)/;
+    let text = await fsp.readFile(index_file, { encoding: 'utf-8' });
+    text = text.split(re);
+    let included = {};
+    let heading = 0, heading_name = '', m;
+    for (let i = 0; i < text.length; i++)
+    {
+        if (text[i].substr(0, 2) == '{{')
+        {
+            // Inclusion
+            let incfile = text[i].substr(2, text[i].length-4);
+            let section = null;
+            let indent = heading;
+            incfile = incfile.replace(/\s*\|\s*indent\s*=\s*(-?\d+)\s*$/, (m, m1) => { indent = parseInt(m1); return ''; });
+            incfile = incfile.replace(/\s*#\s*([^#]+)$/, (m, m1) => { section = m1; return ''; });
+            let inc_heading = section;
+            incfile = rel2abs(index_file, incfile);
+            let inc = await fsp.readFile(incfile, { encoding: 'utf-8' });
+            inc = inc.trim().replace(/^[\s\S]+?\n#/, '#'); // remove until the first header
+            inc = inc.split(re);
+            const indent_str = new Array(indent+1).join('#');
+            let section_start = -1, section_end = -1;
+            for (let j = 0; j < inc.length; j++)
+            {
+                if ((m = /^(\n?)(#+\s*)([\s\S]+)$/.exec(inc[j])))
+                {
+                    if (!inc_heading)
+                    {
+                        inc_heading = m[3].trim();
+                    }
+                    if (section)
+                    {
+                        if (m[3].trim() == section)
+                            section_start = j;
+                        else if (section_start >= 0)
+                        {
+                            section_end = j;
+                            break;
+                        }
+                    }
+                    inc[j] = m[1] + indent_str + m[2] + m[3];
+                }
+                else if ((m = /^(\[[^\]]+\]\()([^\)]+)(\))$/.exec(inc[j])) && !/^https?:(\/\/)|^#/.exec(m[2]))
+                {
+                    const abs_m2 = rel2abs(incfile, m[2]);
+                    const rel_m = abs2rel(__filename, abs_m2);
+                    if (rel_m.substr(0, 9) == '../../../') // outside docs
+                        inc[j] = m[1] + 'https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/'+rel2abs('docs/config/src/include.js', rel_m) + m[3];
+                    else
+                        inc[j] = m[1] + abs_m2 + m[3];
+                }
+            }
+            if (section)
+            {
+                inc = section_start >= 0 ? inc.slice(section_start, section_end < 0 ? inc.length : section_end) : [];
+            }
+            if (inc.length)
+            {
+                if (!inc_heading)
+                    inc_heading = heading_name||'';
+                included[incfile+(section ? '#'+section : '')] = '#'+inc_heading.toLowerCase().replace(/\P{L}+/ug, '-').replace(/^-|-$/g, '');
+                inc[0] = inc[0].replace(/^\s+/, '');
+                inc[inc.length-1] = inc[inc.length-1].replace(/\s+$/, '');
+            }
+            text.splice(i, 1, ...inc);
+            i = i + inc.length - 1;
+        }
+        else if ((m = /^\n?(#+)\s*([\s\S]+)$/.exec(text[i])))
+        {
+            // Heading
+            heading = m[1].length;
+            heading_name = m[2].trim();
+        }
+    }
+    for (let i = 0; i < text.length; i++)
+    {
+        if ((m = /^(\[[^\]]+\]\()([^\)]+)(\))$/.exec(text[i])) && !/^https?:(\/\/)|^#/.exec(m[2]))
+        {
+            const p = m[2].indexOf('#');
+            if (included[m[2]])
+            {
+                text[i] = m[1]+included[m[2]]+m[3];
+            }
+            else if (p >= 0 && included[m[2].substr(0, p)])
+            {
+                text[i] = m[1]+m[2].substr(p)+m[3];
+            }
+        }
+    }
+    console.log(text.join(''));
+}
+
+function rel2abs(ref, rel)
+{
+    rel = [ ...ref.replace(/^(.*)\/[^\/]+$/, '$1').split(/\/+/), ...rel.split(/\/+/) ];
+    return killdots(rel).join('/');
+}
+
+function abs2rel(ref, abs)
+{
+    ref = ref.split(/\/+/);
+    abs = abs.split(/\/+/);
+    while (ref.length > 1 && ref[0] == abs[0])
+    {
+        ref.shift();
+        abs.shift();
+    }
+    for (let i = 1; i < ref.length; i++)
+    {
+        abs.unshift('..');
+    }
+    return killdots(abs).join('/');
+}
+
+function killdots(rel)
+{
+    for (let i = 0; i < rel.length; i++)
+    {
+        if (rel[i] == '.')
+        {
+            rel.splice(i, 1);
+            i--;
+        }
+        else if (i >= 1 && rel[i] == '..' && rel[i-1] != '..')
+        {
+            rel.splice(i-1, 2);
+            i -= 2;
+        }
+    }
+    return rel;
+}

docs/config/src/included.en.md

@@ -0,0 +1,65 @@
+# Vitastor
+
+{{../../../README.md#The Idea}}
+
+{{../../../README.md#Talks and presentations}}
+
+{{../../intro/features.en.md}}
+
+{{../../intro/quickstart.en.md}}
+
+{{../../intro/architecture.en.md}}
+
+## Installation
+
+{{../../installation/packages.en.md}}
+
+{{../../installation/proxmox.en.md}}
+
+{{../../installation/openstack.en.md}}
+
+{{../../installation/kubernetes.en.md}}
+
+{{../../installation/source.en.md}}
+
+{{../../config.en.md|indent=1}}
+
+{{../../config/common.en.md|indent=2}}
+
+{{../../config/network.en.md|indent=2}}
+
+{{../../config/layout-cluster.en.md|indent=2}}
+
+{{../../config/layout-osd.en.md|indent=2}}
+
+{{../../config/osd.en.md|indent=2}}
+
+{{../../config/monitor.en.md|indent=2}}
+
+{{../../config/pool.en.md|indent=2}}
+
+{{../../config/inode.en.md|indent=2}}
+
+## Usage
+
+{{../../usage/cli.en.md}}
+
+{{../../usage/disk.en.md}}
+
+{{../../usage/fio.en.md}}
+
+{{../../usage/nbd.en.md}}
+
+{{../../usage/qemu.en.md}}
+
+{{../../usage/nfs.en.md}}
+
+## Performance
+
+{{../../performance/understanding.en.md}}
+
+{{../../performance/theoretical.en.md}}
+
+{{../../performance/comparison1.en.md}}
+
+{{../../intro/author.en.md|indent=1}}

docs/config/src/included.ru.md

@@ -0,0 +1,65 @@
+# Vitastor
+
+{{../../../README-ru.md#Идея|indent=0}}
+
+{{../../../README-ru.md#Презентации и записи докладов|indent=0}}
+
+{{../../intro/features.ru.md}}
+
+{{../../intro/quickstart.ru.md}}
+
+{{../../intro/architecture.ru.md}}
+
+## Установка
+
+{{../../installation/packages.ru.md}}
+
+{{../../installation/proxmox.ru.md}}
+
+{{../../installation/openstack.ru.md}}
+
+{{../../installation/kubernetes.ru.md}}
+
+{{../../installation/source.ru.md}}
+
+{{../../config.ru.md|indent=1}}
+
+{{../../config/common.ru.md|indent=2}}
+
+{{../../config/network.ru.md|indent=2}}
+
+{{../../config/layout-cluster.ru.md|indent=2}}
+
+{{../../config/layout-osd.ru.md|indent=2}}
+
+{{../../config/osd.ru.md|indent=2}}
+
+{{../../config/monitor.ru.md|indent=2}}
+
+{{../../config/pool.ru.md|indent=2}}
+
+{{../../config/inode.ru.md|indent=2}}
+
+## Использование
+
+{{../../usage/cli.ru.md}}
+
+{{../../usage/disk.ru.md}}
+
+{{../../usage/fio.ru.md}}
+
+{{../../usage/nbd.ru.md}}
+
+{{../../usage/qemu.ru.md}}
+
+{{../../usage/nfs.ru.md}}
+
+## Производительность
+
+{{../../performance/understanding.ru.md}}
+
+{{../../performance/theoretical.ru.md}}
+
+{{../../performance/comparison1.ru.md}}
+
+{{../../intro/author.ru.md|indent=1}}

docs/config/src/layout-cluster.yml

@@ -7,26 +7,27 @@
     in Vitastor, affects memory usage, write amplification and I/O load
     distribution effectiveness.
 
-    Recommended default block size is 128 KB for SSD and 4 MB for HDD. In fact,
-    it's possible to use 4 MB for SSD too - it will lower memory usage, but
+    Recommended default block size is 128 KB for SSD and 1 MB for HDD. In fact,
+    it's possible to use 1 MB for SSD too - it will lower memory usage, but
     may increase average WA and reduce linear performance.
 
     OSD memory usage is roughly (SIZE / BLOCK * 68 bytes) which is roughly
     544 MB per 1 TB of used disk space with the default 128 KB block size.
+    With 1 MB it's 8 times lower.
   info_ru: |
     Размер объектов (блоков данных), на которые делятся физические и виртуальные
     диски в Vitastor (в рамках каждого пула). Одна из ключевых на данный момент
     настроек, влияет на потребление памяти, объём избыточной записи (write
     amplification) и эффективность распределения нагрузки по OSD.
 
-    Рекомендуемые по умолчанию размеры блока - 128 килобайт для SSD и 4
-    мегабайта для HDD. В принципе, для SSD можно тоже использовать 4 мегабайта,
+    Рекомендуемые по умолчанию размеры блока - 128 килобайт для SSD и 1 мегабайт
+    для HDD. В принципе, для SSD можно тоже использовать блок размером 1 мегабайт,
     это понизит использование памяти, но ухудшит распределение нагрузки и в
     среднем увеличит WA.
 
     Потребление памяти OSD составляет примерно (РАЗМЕР / БЛОК * 68 байт),
     т.е. примерно 544 МБ памяти на 1 ТБ занятого места на диске при
-    стандартном 128 КБ блоке.
+    стандартном 128 КБ блоке. При 1 МБ блоке памяти нужно в 8 раз меньше.
 - name: bitmap_granularity
   type: int
   default: 4096

docs/config/src/layout-osd.yml

@@ -204,3 +204,77 @@
 
     Клиентам не обязательно знать про disk_alignment, так что помещать значение
     этого параметра в etcd в /vitastor/config/global не нужно.
+- name: data_csum_type
+  type: string
+  default: none
+  info: |
+    Data checksum type to use. May be "crc32c" or "none". Set to "crc32c" to
+    enable data checksums.
+  info_ru: |
+    Тип используемых OSD контрольных сумм данных. Может быть "crc32c" или "none".
+    Установите в "crc32c", чтобы включить расчёт и проверку контрольных сумм данных.
+
+    Следует понимать, что контрольные суммы в зависимости от размера блока их
+    расчёта либо увеличивают потребление памяти, либо снижают производительность.
+    Подробнее смотрите в описании параметра [csum_block_size](#csum_block_size).
+- name: csum_block_size
+  type: int
+  default: 4096
+  info: |
+    Checksum calculation block size.
+
+    Must be equal or a multiple of [bitmap_granularity](layout-cluster.en.md#bitmap_granularity)
+    (which is usually 4 KB).
+
+    Checksums increase metadata size by 4 bytes per each csum_block_size of data.
+
+    Checksums are always a compromise:
+    1. You either sacrifice +1 GB RAM per 1 TB of data
+    2. Or you raise csum_block_size, for example, to 32k and sacrifice
+       50% random write iops due to checksum read-modify-write
+    3. Or you turn off [inmemory_metadata](osd.en.md#inmemory_metadata) and
+       sacrifice 50% random read iops due to checksum reads
+
+    Option 1 (default) is recommended for all-flash setups because these usually
+    have enough RAM.
+
+    Option 2 is recommended for HDD-only setups. HDD-only setups usually do NOT
+    have enough RAM for the default 4 KB csum_block_size.
+
+    Option 3 is recommended for SSD+HDD setups (because metadata SSDs will handle
+    extra reads without any performance drop) and also *maybe* for NVMe all-flash
+    setups when you don't have enough RAM (because NVMe drives have plenty
+    of read iops to spare). You may also consider enabling
+    [cached_read_meta](osd.en.md#cached_read_meta) in this case.
+  info_ru: |
+    Размер блока расчёта контрольных сумм.
+
+    Должен быть равен или кратен [bitmap_granularity](layout-cluster.ru.md#bitmap_granularity)
+    (который обычно равен 4 КБ).
+
+    Контрольные суммы увеличивают размер метаданных на 4 байта на каждые
+    csum_block_size данных.
+
+    Контрольные суммы - это всегда компромисс:
+    1. Вы либо жертвуете потреблением +1 ГБ памяти на 1 ТБ дискового пространства
+    2. Либо вы повышаете csum_block_size до, скажем, 32k и жертвуете 50%
+       скорости случайной записи из-за цикла чтения-изменения-записи для расчёта
+       новых контрольных сумм
+    3. Либо вы отключаете [inmemory_metadata](osd.ru.md#inmemory_metadata) и
+       жертвуете 50% скорости случайного чтения из-за чтения контрольных сумм
+       с диска
+
+    Вариант 1 (при настройках по умолчанию) рекомендуется для SSD (All-Flash)
+    кластеров, потому что памяти в них обычно хватает.
+
+    Вариант 2 рекомендуется для кластеров на одних жёстких дисках (без SSD
+    под метаданные). На 4 кб блок контрольной суммы памяти в таких кластерах
+    обычно НЕ хватает.
+
+    Вариант 3 рекомендуется для гибридных кластеров (SSD+HDD), потому что
+    скорости SSD под метаданными хватит, чтобы обработать дополнительные чтения
+    без снижения производительности. Также вариант 3 *может* рекомендоваться
+    для All-Flash кластеров на основе NVMe-дисков, когда памяти НЕ достаточно,
+    потому что NVMe-диски имеют огромный запас производительности по чтению.
+    В таких случаях, возможно, также имеет смысл включать параметр
+    [cached_read_meta](osd.ru.md#cached_read_meta).

docs/config/src/make.js

@@ -14,6 +14,7 @@ const L = {
         toc_config: '[Configuration](../config.en.md)',
         toc_usage: 'Usage',
         toc_performance: 'Performance',
+        online: 'Can be changed online: yes',
     },
     ru: {
         Documentation: 'Документация',
@@ -28,6 +29,7 @@ const L = {
         toc_config: '[Конфигурация](../config.ru.md)',
         toc_usage: 'Использование',
         toc_performance: 'Производительность',
+        online: 'Можно менять на лету: да',
     },
 };
 const types = {
@@ -70,6 +72,8 @@ for (const file of params_files)
                 out += `- ${L[lang]['Default'] || 'Default'}: ${c.default}\n`;
             if (c.min !== undefined)
                 out += `- ${L[lang]['Minimum'] || 'Minimum'}: ${c.min}\n`;
+            if (c.online)
+                out += `- ${L[lang]['online'] || 'Can be changed online: yes'}\n`;
             out += `\n`+(c["info_"+lang] || c["info"]).replace(/\s+$/, '');
         }
         const head = fs.readFileSync(__dirname+'/'+file+'.'+lang+'.md', { encoding: 'utf-8' });

docs/config/src/network.yml

@@ -164,18 +164,21 @@
   type: sec
   min: 1
   default: 5
+  online: true
   info: Interval before attempting to reconnect to an unavailable OSD.
   info_ru: Время ожидания перед повторной попыткой соединиться с недоступным OSD.
 - name: peer_connect_timeout
   type: sec
   min: 1
   default: 5
+  online: true
   info: Timeout for OSD connection attempts.
   info_ru: Максимальное время ожидания попытки соединения с OSD.
 - name: osd_idle_timeout
   type: sec
   min: 1
   default: 5
+  online: true
   info: |
     OSD connection inactivity time after which clients and other OSDs send
     keepalive requests to check state of the connection.
@@ -186,6 +189,7 @@
   type: sec
   min: 1
   default: 5
+  online: true
   info: |
     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
@@ -198,6 +202,7 @@
   type: ms
   min: 50
   default: 500
+  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
@@ -211,6 +216,7 @@
 - name: max_etcd_attempts
   type: int
   default: 5
+  online: true
   info: |
     Maximum number of attempts for etcd requests which can't be retried
     indefinitely.
@@ -220,6 +226,7 @@
 - name: etcd_quick_timeout
   type: ms
   default: 1000
+  online: true
   info: |
     Timeout for etcd requests which should complete quickly, like lease refresh.
   info_ru: |
@@ -228,6 +235,7 @@
 - name: etcd_slow_timeout
   type: ms
   default: 5000
+  online: true
   info: Timeout for etcd requests which are allowed to wait for some time.
   info_ru: |
     Максимальное время выполнения запросов к etcd, для которых не обязательно
@@ -235,6 +243,7 @@
 - name: etcd_keepalive_timeout
   type: sec
   default: max(30, etcd_report_interval*2)
+  online: true
   info: |
     Timeout for etcd connection HTTP Keep-Alive. Should be higher than
     etcd_report_interval to guarantee that keepalive actually works.
@@ -244,6 +253,7 @@
 - name: etcd_ws_keepalive_timeout
   type: sec
   default: 30
+  online: true
   info: |
     etcd websocket ping interval required to keep the connection alive and
     detect disconnections quickly.
@@ -252,6 +262,7 @@
 - name: client_dirty_limit
   type: int
   default: 33554432
+  online: true
   info: |
     Without immediate_commit=all this parameter sets the limit of "dirty"
     (not committed by fsync) data allowed by the client before forcing an

docs/config/src/osd.en.md

@@ -1,4 +1,5 @@
 # Runtime OSD Parameters
 
 These parameters only apply to OSDs, are not fixed at the moment of OSD drive
-initialization and can be changed with an OSD restart.
+initialization and can be changed - either with an OSD restart or, for some of
+them, even without restarting by updating configuration in etcd.

docs/config/src/osd.ru.md

@@ -2,4 +2,5 @@
 
 Данные параметры используются только OSD, но, в отличие от дисковых параметров,
 не фиксируются в момент инициализации дисков OSD и могут быть изменены в любой
-момент с перезапуском OSD.
+момент с помощью перезапуска OSD, а некоторые и без перезапуска, с помощью
+изменения конфигурации в etcd.

docs/config/src/osd.yml

@@ -66,6 +66,7 @@
 - name: autosync_interval
   type: sec
   default: 5
+  online: true
   info: |
     Time interval at which automatic fsyncs/flushes are issued by each OSD when
     the immediate_commit mode if disabled. fsyncs are required because without
@@ -83,6 +84,7 @@
 - name: autosync_writes
   type: int
   default: 128
+  online: true
   info: |
     Same as autosync_interval, but sets the maximum number of uncommitted write
     operations before issuing an fsync operation internally.
@@ -93,6 +95,7 @@
 - name: recovery_queue_depth
   type: int
   default: 4
+  online: true
   info: |
     Maximum recovery operations per one primary OSD at any given moment of time.
     Currently it's the only parameter available to tune the speed or recovery
@@ -105,6 +108,7 @@
 - name: recovery_pg_switch
   type: int
   default: 128
+  online: true
   info: |
     Number of recovery operations before switching to recovery of the next PG.
     The idea is to mix all PGs during recovery for more even space and load
@@ -119,6 +123,7 @@
 - name: recovery_sync_batch
   type: int
   default: 16
+  online: true
   info: Maximum number of recovery operations before issuing an additional fsync.
   info_ru: Максимальное число операций восстановления перед дополнительным fsync.
 - name: readonly
@@ -133,6 +138,7 @@
 - name: no_recovery
   type: bool
   default: false
+  online: true
   info: |
     Disable automatic background recovery of objects. Note that it doesn't
     affect implicit recovery of objects happening during writes - a write is
@@ -145,6 +151,7 @@
 - name: no_rebalance
   type: bool
   default: false
+  online: true
   info: |
     Disable background movement of data between different OSDs. Disabling it
     means that PGs in the `has_misplaced` state will be left in it indefinitely.
@@ -155,6 +162,7 @@
 - name: print_stats_interval
   type: sec
   default: 3
+  online: true
   info: |
     Time interval at which OSDs print simple human-readable operation
     statistics on stdout.
@@ -164,6 +172,7 @@
 - name: slow_log_interval
   type: sec
   default: 10
+  online: true
   info: |
     Time interval at which OSDs dump slow or stuck operations on stdout, if
     they're any. Also it's the time after which an operation is considered
@@ -175,6 +184,7 @@
 - name: inode_vanish_time
   type: sec
   default: 60
+  online: true
   info: |
     Number of seconds after which a deleted inode is removed from OSD statistics.
   info_ru: |
@@ -182,6 +192,7 @@
 - name: max_write_iodepth
   type: int
   default: 128
+  online: true
   info: |
     Parallel client write operation limit per one OSD. Operations that exceed
     this limit are pushed to a temporary queue instead of being executed
@@ -193,6 +204,7 @@
 - name: min_flusher_count
   type: int
   default: 1
+  online: true
   info: |
     Flusher is a micro-thread that moves data from the journal to the data
     area of the device. Their number is auto-tuned between minimum and maximum.
@@ -204,6 +216,7 @@
 - name: max_flusher_count
   type: int
   default: 256
+  online: true
   info: |
     Maximum number of journal flushers (see above min_flusher_count).
   info_ru: |
@@ -247,6 +260,70 @@
     достаточно 16- или 32-мегабайтного журнала. Однако в теории отключение
     параметра может оказаться полезным для гибридных OSD (HDD+SSD) с большими
     журналами, расположенными на быстром по сравнению с HDD устройстве.
+- name: cached_read_data
+  type: bool
+  default: false
+  info: |
+    Read data through Linux page cache, i.e. use a file descriptor opened without
+    O_DIRECT for data reads. May improve read performance for frequently accessed
+    data if it fits in RAM. Memory in page cache is shared by all processes and
+    not accounted in OSD memory consumption.
+  info_ru: |
+    Читать данные через системный кэш Linux (page cache), то есть, использовать
+    для чтения данных файловый дескриптор, открытый без флага O_DIRECT. Может
+    улучшить производительность чтения для часто используемых данных, если они
+    помещаются в память. Память кэша разделяется между всеми процессами в
+    системе и не учитывается в потреблении памяти процессом OSD.
+- name: cached_read_meta
+  type: bool
+  default: false
+  info: |
+    Read metadata through Linux page cache. May be beneficial when checksums
+    are enabled and [inmemory_metadata](#inmemory_metadata) is disabled, because
+    in this case metadata blocks are read from disk to verify checksums on every
+    read request and caching them may reduce this extra read load.
+
+    Absolutely pointless to enable with enabled inmemory_metadata because all
+    metadata is kept in memory anyway, and likely pointless without checksums,
+    because in that case, metadata blocks are read from disk only during journal
+    flushing.
+
+    If the same device is used for data and metadata, enabling [cached_read_data](#cached_read_data)
+    also enables this parameter, given that it isn't turned off explicitly.
+  info_ru: |
+    Читать метаданные через системный кэш Linux. Может быть полезно, когда
+    включены контрольные суммы, а параметр [inmemory_metadata](#inmemory_metadata)
+    отключён, так как в этом случае блоки метаданных читаются с диска при каждом
+    запросе чтения для проверки контрольных сумм и их кэширование может снизить
+    дополнительную нагрузку на диск.
+
+    Абсолютно бессмысленно включать данный параметр, если параметр
+    inmemory_metadata включён (по умолчанию это так), и также вероятно
+    бессмысленно включать его, если не включены контрольные суммы, так как в
+    этом случае блоки метаданных читаются с диска только во время сброса
+    журнала.
+
+    Если одно и то же устройство используется для данных и метаданных, включение
+    [cached_read_data](#cached_read_data) также включает данный параметр, при
+    условии, что он не отключён явным образом.
+- name: cached_read_journal
+  type: bool
+  default: false
+  info: |
+    Read buffered data from journal through Linux page cache. Does not have sense
+    without disabling [inmemory_journal](#inmemory_journal), which, again, is
+    enabled by default.
+
+    If the same device is used for metadata and journal, enabling [cached_read_meta](#cached_read_meta)
+    also enables this parameter, given that it isn't turned off explicitly.
+  info_ru: |
+    Читать буферизованные в журнале данные через системный кэш Linux. Не имеет
+    смысла без отключения параметра [inmemory_journal](#inmemory_journal),
+    который, опять же, по умолчанию включён.
+
+    Если одно и то же устройство используется для метаданных и журнала,
+    включение [cached_read_meta](#cached_read_meta) также включает данный
+    параметр, при условии, что он не отключён явным образом.
 - name: journal_sector_buffer_count
   type: int
   default: 32
@@ -284,6 +361,7 @@
 - name: throttle_small_writes
   type: bool
   default: false
+  online: true
   info: |
     Enable soft throttling of small journaled writes. Useful for hybrid OSDs
     with fast journal/metadata devices and slow data devices. The idea is that
@@ -312,6 +390,7 @@
 - name: throttle_target_iops
   type: int
   default: 100
+  online: true
   info: |
     Target maximum number of throttled operations per second under the condition
     of full journal. Set it to approximate random write iops of your data devices
@@ -324,6 +403,7 @@
 - name: throttle_target_mbs
   type: int
   default: 100
+  online: true
   info: |
     Target maximum bandwidth in MB/s of throttled operations per second under
     the condition of full journal. Set it to approximate linear write
@@ -336,6 +416,7 @@
 - name: throttle_target_parallelism
   type: int
   default: 1
+  online: true
   info: |
     Target maximum parallelism of throttled operations under the condition of
     full journal. Set it to approximate internal parallelism of your data
@@ -348,6 +429,7 @@
 - name: throttle_threshold_us
   type: us
   default: 50
+  online: true
   info: |
     Minimal computed delay to be applied to throttled operations. Usually
     doesn't need to be changed.
@@ -357,10 +439,151 @@
 - name: osd_memlock
   type: bool
   default: false
-  info: >
+  info: |
     Lock all OSD memory to prevent it from being unloaded into swap with
     mlockall(). Requires sufficient ulimit -l (max locked memory).
-  info_ru: >
+  info_ru: |
     Блокировать всю память OSD с помощью mlockall, чтобы запретить её выгрузку
     в пространство подкачки. Требует достаточного значения ulimit -l (лимита
     заблокированной памяти).
+- name: auto_scrub
+  type: bool
+  default: false
+  online: true
+  info: |
+    Data scrubbing is the process of background verification of copies to find
+    and repair corrupted blocks. It's not run automatically by default since
+    it's a new feature. Set this parameter to true to enable automatic scrubs.
+
+    This parameter makes OSDs automatically schedule data scrubbing of clean PGs
+    every `scrub_interval` (see below). You can also start/schedule scrubbing
+    manually by setting `next_scrub` JSON key to the desired UNIX time of the
+    next scrub in `/pg/history/...` values in etcd.
+  info_ru: |
+    Скраб - процесс фоновой проверки копий данных, предназначенный, чтобы
+    находить и исправлять повреждённые блоки. По умолчанию эти проверки ещё не
+    запускаются автоматически, так как являются новой функцией. Чтобы включить
+    автоматическое планирование скрабов, установите данный параметр в true.
+
+    Включённый параметр заставляет OSD автоматически планировать фоновую
+    проверку чистых PG раз в `scrub_interval` (см. ниже). Вы также можете
+    запустить или запланировать проверку вручную, установив значение ключа JSON
+    `next_scrub` внутри ключей etcd `/pg/history/...` в UNIX-время следующей
+    желаемой проверки.
+- name: no_scrub
+  type: bool
+  default: false
+  online: true
+  info: |
+    Temporarily disable scrubbing and stop running scrubs.
+  info_ru: |
+    Временно отключить и остановить запущенные скрабы.
+- name: scrub_interval
+  type: string
+  default: 30d
+  online: true
+  info: |
+    Default automatic scrubbing interval for all pools. Numbers without suffix
+    are treated as seconds, possible unit suffixes include 's' (seconds),
+    'm' (minutes), 'h' (hours), 'd' (days), 'M' (months) and 'y' (years).
+  info_ru: |
+    Интервал автоматической фоновой проверки по умолчанию для всех пулов.
+    Значения без указанной единицы измерения считаются в секундах, допустимые
+    символы единиц измерения в конце: 's' (секунды),
+    'm' (минуты), 'h' (часы), 'd' (дни), 'M' (месяца) или 'y' (годы).
+- name: scrub_queue_depth
+  type: int
+  default: 1
+  online: true
+  info: |
+    Number of parallel scrubbing operations per one OSD.
+  info_ru: |
+    Число параллельных операций фоновой проверки на один OSD.
+- name: scrub_sleep
+  type: ms
+  default: 0
+  online: true
+  info: |
+    Additional interval between two consecutive scrubbing operations on one OSD.
+    Can be used to slow down scrubbing if it affects user load too much.
+  info_ru: |
+    Дополнительный интервал ожидания после фоновой проверки каждого объекта на
+    одном OSD. Может использоваться для замедления скраба, если он слишком
+    сильно влияет на пользовательскую нагрузку.
+- name: scrub_list_limit
+  type: int
+  default: 1000
+  online: true
+  info: |
+    Number of objects to list in one listing operation during scrub.
+  info_ru: |
+    Размер загружаемых за одну операцию списков объектов в процессе фоновой
+    проверки.
+- name: scrub_find_best
+  type: bool
+  default: true
+  online: true
+  info: |
+    Find and automatically restore best versions of objects with unmatched
+    copies. In replicated setups, the best version is the version with most
+    matching replicas. In EC setups, the best version is the subset of data
+    and parity chunks without mismatches.
+
+    The hypothetical situation where you might want to disable it is when
+    you have 3 replicas and you are paranoid that 2 HDDs out of 3 may silently
+    corrupt an object in the same way (for example, zero it out) and only
+    1 HDD will remain good. In this case disabling scrub_find_best may help
+    you to recover the data! See also scrub_ec_max_bruteforce below.
+  info_ru: |
+    Находить и автоматически восстанавливать "лучшие версии" объектов с
+    несовпадающими копиями/частями. При использовании репликации "лучшая"
+    версия - версия, доступная в большем числе экземпляров, чем другие. При
+    использовании кодов коррекции ошибок "лучшая" версия - это подмножество
+    частей данных и чётности, полностью соответствующих друг другу.
+
+    Гипотетическая ситуация, в которой вы можете захотеть отключить этот
+    поиск - это если у вас 3 реплики и вы боитесь, что 2 диска из 3 могут
+    незаметно и одинаково повредить данные одного и того же объекта, например,
+    занулив его, и только 1 диск останется неповреждённым. В этой ситуации
+    отключение этого параметра поможет вам восстановить данные! Смотрите также
+    описание следующего параметра - scrub_ec_max_bruteforce.
+- name: scrub_ec_max_bruteforce
+  type: int
+  default: 100
+  online: true
+  info: |
+    Vitastor can locate corrupted chunks in EC setups with more than 1 parity
+    chunk by brute-forcing all possible error locations. This configuration
+    value limits the maximum number of checked combinations. You can try to
+    increase it if you have EC N+K setup with N and K large enough for
+    combination count `C(N+K-1, K-1) = (N+K-1)! / (K-1)! / N!` to be greater
+    than the default 100.
+
+    If there are too many possible combinations or if multiple combinations give
+    correct results then objects are marked inconsistent and aren't recovered
+    automatically.
+
+    In replicated setups bruteforcing isn't needed, Vitastor just assumes that
+    the variant with most available equal copies is correct. For example, if
+    you have 3 replicas and 1 of them differs, this one is considered to be
+    corrupted. But if there is no "best" version with more copies than all
+    others have then the object is also marked as inconsistent.
+  info_ru: |
+    Vitastor старается определить повреждённые части объектов при использовании
+    EC (кодов коррекции ошибок) с более, чем 1 диском чётности, путём перебора
+    всех возможных комбинаций ошибочных частей. Данное значение конфигурации
+    ограничивает число перебираемых комбинаций. Вы можете попробовать поднять
+    его, если используете схему кодирования EC N+K с N и K, достаточно большими
+    для того, чтобы число сочетаний `C(N+K-1, K-1) = (N+K-1)! / (K-1)! / N!`
+    было больше, чем стандартное значение 100.
+
+    Если возможных комбинаций слишком много или если корректная комбинаций не
+    определяется однозначно, объекты помечаются неконсистентными (inconsistent)
+    и не восстанавливаются автоматически.
+
+    При использовании репликации перебор не нужен, Vitastor просто предполагает,
+    что вариант объекта с наибольшим количеством одинаковых копий корректен.
+    Например, если вы используете 3 реплики и 1 из них отличается, эта 1 копия
+    считается некорректной. Однако, если "лучшую" версию с числом доступных
+    копий большим, чем у всех других версий, найти невозможно, то объект тоже
+    маркируется неконсистентным.

docs/installation/kubernetes.ru.md

@@ -8,13 +8,13 @@
 
 У Vitastor есть CSI-плагин для Kubernetes, поддерживающий RWO, а также блочные RWX, тома.
 
-Для установки возьмите манифесты из директории [csi/deploy/](../csi/deploy/), поместите
-вашу конфигурацию подключения к Vitastor в [csi/deploy/001-csi-config-map.yaml](../csi/deploy/001-csi-config-map.yaml),
-настройте StorageClass в [csi/deploy/009-storage-class.yaml](../csi/deploy/009-storage-class.yaml)
+Для установки возьмите манифесты из директории [csi/deploy/](../../csi/deploy/), поместите
+вашу конфигурацию подключения к Vitastor в [csi/deploy/001-csi-config-map.yaml](../../csi/deploy/001-csi-config-map.yaml),
+настройте StorageClass в [csi/deploy/009-storage-class.yaml](../../csi/deploy/009-storage-class.yaml)
 и примените все `NNN-*.yaml` к вашей инсталляции Kubernetes.
 
 ```
 for i in ./???-*.yaml; do kubectl apply -f $i; done
 ```
 
-После этого вы сможете создавать PersistentVolume. Пример смотрите в файле [csi/deploy/example-pvc.yaml](../csi/deploy/example-pvc.yaml).
+После этого вы сможете создавать PersistentVolume. Пример смотрите в файле [csi/deploy/example-pvc.yaml](../../csi/deploy/example-pvc.yaml).

docs/installation/openstack.en.md

@@ -36,5 +36,5 @@ vitastor_pool_id = 1
 image_upload_use_cinder_backend = True
 ```
 
-To put Glance images in Vitastor, use [https://docs.openstack.org/cinder/pike/admin/blockstorage-volume-backed-image.html](volume-backed images),
+To put Glance images in Vitastor, use [volume-backed images](https://docs.openstack.org/cinder/pike/admin/blockstorage-volume-backed-image.html),
 although the support has not been verified yet.

docs/installation/openstack.ru.md

@@ -36,5 +36,5 @@ image_upload_use_cinder_backend = True
 ```
 
 Чтобы помещать в Vitastor Glance-образы, нужно использовать
-[https://docs.openstack.org/cinder/pike/admin/blockstorage-volume-backed-image.html](образы на основе томов Cinder),
+[образы на основе томов Cinder](https://docs.openstack.org/cinder/pike/admin/blockstorage-volume-backed-image.html),
 однако, поддержка этой функции ещё не проверялась.

docs/installation/packages.en.md

@@ -11,7 +11,8 @@
 - Trust Vitastor package signing key:
   `wget https://vitastor.io/debian/pubkey.gpg -O /etc/apt/trusted.gpg.d/vitastor.gpg`
 - Add Vitastor package repository to your /etc/apt/sources.list:
-  - Debian 11 (Bullseye/Sid): `deb https://vitastor.io/debian bullseye main`
+  - Debian 12 (Bookworm/Sid): `deb https://vitastor.io/debian bookworm main`
+  - Debian 11 (Bullseye): `deb https://vitastor.io/debian bullseye main`
   - Debian 10 (Buster): `deb https://vitastor.io/debian buster main`
 - For Debian 10 (Buster) also enable backports repository:
   `deb http://deb.debian.org/debian buster-backports main`
@@ -31,8 +32,8 @@
 - Enable elrepo-kernel:
   - CentOS 7: `yum install https://www.elrepo.org/elrepo-release-7.el7.elrepo.noarch.rpm`
   - CentOS 8: `dnf install https://www.elrepo.org/elrepo-release-8.el8.elrepo.noarch.rpm`
-  - RHEL 9 clones: optional, not required: `dnf install https://www.elrepo.org/elrepo-release-9.el9.elrepo.noarch.rpm`
-- Install packages: `yum/dnf install vitastor lpsolve etcd qemu-kvm` and optionally `kernel-ml` if you use elrepo-kernel
+  - RHEL 9 clones: `dnf install https://www.elrepo.org/elrepo-release-9.el9.elrepo.noarch.rpm`
+- Install packages: `yum/dnf install vitastor lpsolve etcd kernel-ml qemu-kvm`
 
 ## Installation requirements
 
@@ -45,3 +46,10 @@
 - etcd 3.4.15 or newer. Earlier versions won't work because of various bugs,
   for example [#12402](https://github.com/etcd-io/etcd/pull/12402).
 - node.js 10 or newer
+
+## Version archive
+
+All previous Vitastor and other components (QEMU, etcd...) package builds
+can be found here:
+
+https://vitastor.io/archive/

docs/installation/packages.ru.md

@@ -11,7 +11,8 @@
 - Добавьте ключ репозитория Vitastor:
   `wget https://vitastor.io/debian/pubkey.gpg -O /etc/apt/trusted.gpg.d/vitastor.gpg`
 - Добавьте репозиторий Vitastor в /etc/apt/sources.list:
-  - Debian 11 (Bullseye/Sid): `deb https://vitastor.io/debian bullseye main`
+  - Debian 12 (Bookworm/Sid): `deb https://vitastor.io/debian bookworm main`
+  - Debian 11 (Bullseye): `deb https://vitastor.io/debian bullseye main`
   - Debian 10 (Buster): `deb https://vitastor.io/debian buster main`
 - Для Debian 10 (Buster) также включите репозиторий backports:
   `deb http://deb.debian.org/debian buster-backports main`
@@ -22,13 +23,16 @@
 - Добавьте в систему репозиторий Vitastor:
   - CentOS 7: `yum install https://vitastor.io/rpms/centos/7/vitastor-release.rpm`
   - CentOS 8: `dnf install https://vitastor.io/rpms/centos/8/vitastor-release.rpm`
+  - AlmaLinux 9 и другие клоны RHEL 9 (Rocky, Oracle...): `dnf install https://vitastor.io/rpms/centos/9/vitastor-release.rpm`
 - Включите EPEL: `yum/dnf install epel-release`
 - Включите дополнительные репозитории CentOS:
   - CentOS 7: `yum install centos-release-scl`
   - CentOS 8: `dnf install centos-release-advanced-virtualization`
+  - Клоны RHEL 9: не нужно
 - Включите elrepo-kernel:
   - CentOS 7: `yum install https://www.elrepo.org/elrepo-release-7.el7.elrepo.noarch.rpm`
   - CentOS 8: `dnf install https://www.elrepo.org/elrepo-release-8.el8.elrepo.noarch.rpm`
+  - Клоны RHEL 9: `dnf install https://www.elrepo.org/elrepo-release-9.el9.elrepo.noarch.rpm`
 - Установите пакеты: `yum/dnf install vitastor lpsolve etcd kernel-ml qemu-kvm`
 
 ## Установочные требования
@@ -41,3 +45,10 @@
 - etcd 3.4.15 или новее. Более старые версии не будут работать из-за разных багов,
   например, [#12402](https://github.com/etcd-io/etcd/pull/12402).
 - node.js 10 или новее
+
+## Архив предыдущих версий
+
+Все предыдущие сборки пакетов Vitastor и других компонентов, таких, как QEMU
+и etcd, можно скачать по следующей ссылке:
+
+https://vitastor.io/archive/

docs/installation/proxmox.en.md

@@ -6,10 +6,10 @@
 
 # Proxmox VE
 
-To enable Vitastor support in Proxmox Virtual Environment (6.4-7.4 are supported):
+To enable Vitastor support in Proxmox Virtual Environment (6.4-8.0 are supported):
 
 - Add the corresponding Vitastor Debian repository into sources.list on Proxmox hosts:
-  buster for 6.4, bullseye for 7.4, pve7.1 for 7.1, pve7.2 for 7.2, pve7.3 for 7.3
+  bookworm for 8.0, bullseye for 7.4, pve7.3 for 7.3, pve7.2 for 7.2, pve7.1 for 7.1, buster for 6.4
 - Install vitastor-client, pve-qemu-kvm, pve-storage-vitastor (* or see note) packages from Vitastor repository
 - Define storage in `/etc/pve/storage.cfg` (see below)
 - Block network access from VMs to Vitastor network (to OSDs and etcd),
@@ -35,5 +35,5 @@ vitastor: vitastor
     vitastor_nbd 0
 ```
 
-\* Note: you can also manually copy [patches/VitastorPlugin.pm](patches/VitastorPlugin.pm) to Proxmox hosts
+\* Note: you can also manually copy [patches/VitastorPlugin.pm](../../patches/VitastorPlugin.pm) to Proxmox hosts
 as `/usr/share/perl5/PVE/Storage/Custom/VitastorPlugin.pm` instead of installing pve-storage-vitastor.

docs/installation/proxmox.ru.md

@@ -1,15 +1,15 @@
-[Документация](../../README-ru.md#документация) → Установка → Proxmox
+[Документация](../../README-ru.md#документация) → Установка → Proxmox VE
 
 -----
 
 [Read in English](proxmox.en.md)
 
-# Proxmox
+# Proxmox VE
 
-Чтобы подключить Vitastor к Proxmox Virtual Environment (поддерживаются версии 6.4-7.4):
+Чтобы подключить Vitastor к Proxmox Virtual Environment (поддерживаются версии 6.4-8.0):
 
 - Добавьте соответствующий Debian-репозиторий Vitastor в sources.list на хостах Proxmox:
-  buster для 6.4, bullseye для 7.4, pve7.1 для 7.1, pve7.2 для 7.2, pve7.3 для 7.3
+  bookworm для 8.0, bullseye для 7.4, pve7.3 для 7.3, pve7.2 для 7.2, pve7.1 для 7.1, buster для 6.4
 - Установите пакеты vitastor-client, pve-qemu-kvm, pve-storage-vitastor (* или см. сноску) из репозитория Vitastor
 - Определите тип хранилища в `/etc/pve/storage.cfg` (см. ниже)
 - Обязательно заблокируйте доступ от виртуальных машин к сети Vitastor (OSD и etcd), т.к. Vitastor (пока) не поддерживает аутентификацию
@@ -35,5 +35,5 @@ vitastor: vitastor
 ```
 
 \* Примечание: вместо установки пакета pve-storage-vitastor вы можете вручную скопировать файл
-[patches/VitastorPlugin.pm](patches/VitastorPlugin.pm) на хосты Proxmox как
+[patches/VitastorPlugin.pm](../../patches/VitastorPlugin.pm) на хосты Proxmox как
 `/usr/share/perl5/PVE/Storage/Custom/VitastorPlugin.pm`.

docs/intro/architecture.en.md

@@ -44,7 +44,7 @@
   depends linearly on drive capacity and data store block size which is 128 KB by default.
   With 128 KB blocks metadata takes around 512 MB per 1 TB (which is still less than Ceph wants).
   Journal is also kept in memory by default, but in SSD-only clusters it's only 32 MB, and in SSD+HDD
-  clusters, where it's beneficial to increase it, [inmemory_journal](docs/config/osd.en.md#inmemory_journal) can be disabled.
+  clusters, where it's beneficial to increase it, [inmemory_journal](../config/osd.en.md#inmemory_journal) can be disabled.
 - Vitastor storage layer doesn't have internal copy-on-write or redirect-write. I know that maybe
   it's possible to create a good copy-on-write storage, but it's much harder and makes performance
   less deterministic, so CoW isn't used in Vitastor.

docs/intro/architecture.ru.md

@@ -156,7 +156,7 @@
   блока хранилища (block_size, по умолчанию 128 КБ). С 128 КБ блоком потребление памяти
   составляет примерно 512 МБ на 1 ТБ данных. Журналы по умолчанию тоже хранятся в памяти,
   но в SSD-кластерах нужный размер журнала составляет всего 32 МБ, а в гибридных (SSD+HDD)
-  кластерах, в которых есть смысл делать журналы больше, можно отключить [inmemory_journal](../docs/config/osd.ru.md#inmemory_journal).
+  кластерах, в которых есть смысл делать журналы больше, можно отключить [inmemory_journal](../config/osd.ru.md#inmemory_journal).
 - В Vitastor нет внутреннего copy-on-write. Я считаю, что реализация CoW-хранилища гораздо сложнее,
   поэтому сложнее добиться устойчиво хороших результатов. Возможно, в один прекрасный день
   я придумаю красивый алгоритм для CoW-хранилища, но пока нет — внутреннего CoW в Vitastor не будет.

docs/intro/features.en.md

@@ -29,12 +29,14 @@
 - Snapshots and copy-on-write image clones
 - [Write throttling to smooth random write workloads in SSD+HDD configurations](../config/osd.en.md#throttle_small_writes)
 - [RDMA/RoCEv2 support via libibverbs](../config/network.en.md#rdma_device)
+- [Scrubbing without checksums](../config/osd.en.md#auto_scrub) (verification of copies)
+- [Checksums](../config/layout-osd.en.md#data_csum_type)
 
 ## Plugins and tools
 
 - [Debian and CentOS packages](../installation/packages.en.md)
 - [Image management CLI (vitastor-cli)](../usage/cli.en.md)
-- [Disk management CLI (vitastor-disk)](docs/usage/disk.en.md)
+- [Disk management CLI (vitastor-disk)](../usage/disk.en.md)
 - Generic user-space client library
 - [Native QEMU driver](../usage/qemu.en.md)
 - [Loadable fio engine for benchmarks](../usage/fio.en.md)
@@ -54,8 +56,6 @@ The following features are planned for the future:
 - iSCSI proxy
 - Multi-threaded client
 - Faster failover
-- Scrubbing without checksums (verification of replicas)
-- Checksums
 - Tiered storage (SSD caching)
 - NVDIMM support
 - Compression (possibly)

docs/intro/features.ru.md

@@ -13,7 +13,7 @@
 ## Серверные функции
 
 - Базовая часть - надёжное кластерное блочное хранилище без единой точки отказа
-- [Производительность](../comparison1.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
@@ -31,12 +31,14 @@
 - Снапшоты и copy-on-write клоны
 - [Сглаживание производительности случайной записи в SSD+HDD конфигурациях](../config/osd.ru.md#throttle_small_writes)
 - [Поддержка RDMA/RoCEv2 через libibverbs](../config/network.ru.md#rdma_device)
+- [Фоновая проверка целостности без контрольных сумм](../config/osd.ru.md#auto_scrub) (сверка копий)
+- [Контрольные суммы](../config/layout-osd.ru.md#data_csum_type)
 
 ## Драйверы и инструменты
 
 - [Пакеты для Debian и CentOS](../installation/packages.ru.md)
 - [Консольный интерфейс управления образами (vitastor-cli)](../usage/cli.ru.md)
-- [Инструмент управления дисками (vitastor-disk)](docs/usage/disk.ru.md)
+- [Инструмент управления дисками (vitastor-disk)](../usage/disk.ru.md)
 - Общая пользовательская клиентская библиотека для работы с кластером
 - [Драйвер диска для QEMU](../usage/qemu.ru.md)
 - [Драйвер диска для утилиты тестирования производительности fio](../usage/fio.ru.md)
@@ -54,8 +56,6 @@
 - iSCSI-прокси
 - Многопоточный клиент
 - Более быстрое переключение при отказах
-- Фоновая проверка целостности без контрольных сумм (сверка реплик)
-- Контрольные суммы
 - Поддержка SSD-кэширования (tiered storage)
 - Поддержка NVDIMM
 - Возможно, сжатие

docs/intro/quickstart.en.md

@@ -7,6 +7,7 @@
 # Quick Start
 
 - [Preparation](#preparation)
+- [Recommended drives](#recommended-drives)
 - [Configure monitors](#configure-monitors)
 - [Configure OSDs](#configure-osds)
 - [Create a pool](#create-a-pool)
@@ -19,10 +20,20 @@
 - Get some SATA or NVMe SSDs with capacitors (server-grade drives). You can use desktop SSDs
   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 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`.
 - [Install Vitastor packages](../installation/packages.en.md).
 
+## Recommended drives
+
+- 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 MG06/MG07/MG08, Seagate EXOS
+
 ## Configure monitors
 
 On the monitor hosts:
@@ -45,9 +56,10 @@ On the monitor hosts:
   }
   ```
 - Initialize OSDs:
-  - SSD-only: `vitastor-disk prepare /dev/sdXXX [/dev/sdYYY ...]`. You can add
-    `--disable_data_fsync off` to leave disk cache enabled if you use desktop
-    SSDs without capacitors.
+  - SSD-only or HDD-only: `vitastor-disk prepare /dev/sdXXX [/dev/sdYYY ...]`.
+    Add `--disable_data_fsync off` to leave disk write cache enabled if you use
+    desktop SSDs without capacitors. Do NOT add `--disable_data_fsync off` if you
+    use HDDs or SSD+HDD.
   - Hybrid, SSD+HDD: `vitastor-disk prepare --hybrid /dev/sdXXX [/dev/sdYYY ...]`.
     Pass all your devices (HDD and SSD) to this script — it will partition disks and initialize journals on its own.
     This script skips HDDs which are already partitioned so if you want to use non-empty disks for

docs/intro/quickstart.ru.md

@@ -7,6 +7,7 @@
 # Быстрый старт
 
 - [Подготовка](#подготовка)
+- [Рекомендуемые диски](#рекомендуемые-диски)
 - [Настройте мониторы](#настройте-мониторы)
 - [Настройте OSD](#настройте-osd)
 - [Создайте пул](#создайте-пул)
@@ -19,10 +20,20 @@
 - Возьмите серверы с SSD (SATA или NVMe), желательно с конденсаторами (серверные SSD). Можно
   использовать и десктопные SSD, включив режим отложенного fsync, но производительность будет хуже.
   О конденсаторах читайте [здесь](../config/layout-cluster.ru.md#immediate_commit).
+- Если хотите использовать HDD, берите современные модели с Media или SSD кэшем - HGST Ultrastar,
+  Toshiba MG08, Seagate EXOS или что-то похожее. Если такого кэша у ваших дисков нет,
+  обязательно возьмите SSD под метаданные и журнал (маленькие, буквально 2 ГБ на 1 ТБ HDD-места).
 - Возьмите быструю сеть, минимум 10 гбит/с. Идеал - что-то вроде Mellanox ConnectX-4 с RoCEv2.
 - Для лучшей производительности отключите энергосбережение CPU: `cpupower idle-set -D 0 && cpupower frequency-set -g performance`.
 - [Установите пакеты Vitastor](../installation/packages.ru.md).
 
+## Рекомендуемые диски
+
+- 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 MG06/MG07/MG08, Seagate EXOS
+
 ## Настройте мониторы
 
 На хостах, выделенных под мониторы:
@@ -45,9 +56,10 @@
   }
   ```
 - Инициализуйте OSD:
-  - SSD: `vitastor-disk prepare /dev/sdXXX [/dev/sdYYY ...]`. Если вы используете
-    десктопные SSD без конденсаторов, можете оставить кэш включённым, добавив
-    опцию `--disable_data_fsync off`.
+  - Только SSD или только HDD: `vitastor-disk prepare /dev/sdXXX [/dev/sdYYY ...]`.
+    Если вы используете десктопные SSD без конденсаторов, добавьте опцию `--disable_data_fsync off`,
+    чтобы оставить кэш записи диска включённым. НЕ добавляйте эту опцию, если используете
+    жёсткие диски (HDD).
   - Гибридные, SSD+HDD: `vitastor-disk prepare --hybrid /dev/sdXXX [/dev/sdYYY ...]`.
     Передайте все ваши SSD и HDD скрипту в командной строке подряд, скрипт автоматически выделит
     разделы под журналы на SSD и данные на HDD. Скрипт пропускает HDD, на которых уже есть разделы

docs/usage/cli.en.md

@@ -20,6 +20,8 @@ It supports the following commands:
 - [flatten](#flatten)
 - [rm-data](#rm-data)
 - [merge-data](#merge-data)
+- [describe](#describe)
+- [fix](#fix)
 - [alloc-osd](#alloc-osd)
 - [rm-osd](#rm-osd)
 
@@ -174,6 +176,51 @@ Merge layer data without changing metadata. Merge `<from>`..`<to>` to `<target>`
 `<to>` must be a child of `<from>` and `<target>` may be one of the layers between
 `<from>` and `<to>`, including `<from>` and `<to>`.
 
+## describe
+
+`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.
+
+```
+--osds <osds>
+    Only list objects from primary OSD(s) <osds>.
+--object-state <states>
+    Only list objects in given state(s). State(s) may include:
+    degraded, misplaced, incomplete, corrupted, inconsistent.
+--pool <pool name or number>
+    Only list objects in the given pool.
+--inode, --min-inode, --max-inode
+    Restrict listing to specific inode numbers.
+--min-offset, --max-offset
+    Restrict listing to specific offsets inside inodes.
+```
+
+## fix
+
+`vitastor-cli fix [--objects <objects>] [--bad-osds <osds>] [--part <part>] [--check no]`
+
+Fix inconsistent objects in the cluster by deleting some copies.
+
+```
+--objects <objects>
+    Objects to fix, either in plain text or JSON format. If not specified,
+    object list will be read from STDIN in one of the same formats.
+    Plain text format: 0x<inode>:0x<stripe> <any delimiter> 0x<inode>:0x<stripe> ...
+    JSON format: [{"inode":"0x...","stripe":"0x..."},...]
+--bad-osds <osds>
+    Remove inconsistent copies/parts of objects from these OSDs, effectively
+    marking them bad and allowing Vitastor to recover objects from other copies.
+--part <number>
+    Only remove EC part <number> (from 0 to pg_size-1), required for extreme
+    edge cases where one OSD has multiple parts of a EC object.
+--check no
+    Do not recheck that requested objects are actually inconsistent,
+    delete requested copies/parts anyway.
+```
+
 ## alloc-osd
 
 `vitastor-cli alloc-osd`

docs/usage/cli.ru.md

@@ -184,6 +184,59 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
 в целевой образ `<target>`. `<to>` должен быть дочерним образом `<from>`, а `<target>`
 должен быть одним из слоёв между `<from>` и `<to>`, включая сами `<from>` и `<to>`.
 
+## describe
+
+`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.
+
+```
+--osds <osds>
+    Перечислять только объекты с первичных OSD из списка <osds>.
+--object-state <состояния>
+    Перечислять только объекты в указанных состояниях. Возможные состояния
+    объектов:
+    - degraded - деградированная избыточность
+    - misplaced - перемещённый
+    - incomplete - нечитаемый из-за потери большего числа частей, чем допустимо
+    - corrupted - с одной или более повреждённой частью
+    - inconsistent - неконсистентный, с неоднозначным расхождением копий/частей
+--pool <имя или ID пула>
+    Перечислять только объекты из заданного пула.
+--inode, --min-inode, --max-inode
+    Перечислять только объекты из указанных номеров инодов (образов).
+--min-offset, --max-offset
+    Перечислять только объекты с заданных смещений внутри образов.
+```
+
+## fix
+
+`vitastor-cli fix [--objects <объекты>] [--bad-osds <osds>] [--part <номер>] [--check no]`
+
+Исправить неконсистентные (неоднозначные) объекты путём удаления части копий.
+
+```
+--objects <объекты>
+    Объекты для исправления - в простом текстовом или JSON формате. Если опция
+    не указана, список объектов читается со стандартного ввода в тех же форматах.
+    Простой формат: 0x<инод>:0x<смещение> <любой разделитель> 0x<инод>:0x<смещение> ...
+    Формат JSON: [{"inode":"0x<инод>","stripe":"0x<смещение>"},...]
+--bad-osds <osds>
+    Удалить неконсистентные копии/части объектов с данных OSD, таким образом
+    признавая потерю этих копий и позволяя Vitastor-у восстановить объекты из
+    других копий.
+--part <номер>
+    Удалить только части EC с заданным номером (от 0 до pg_size-1). Нужно только
+    в редких граничных случаях, когда один и тот же OSD содержит несколько частей
+    одного EC-объекта.
+--check no
+    Не перепроверять, что заданные объекты действительно в неконсистентном
+    состоянии и просто удалять заданные части.
+```
+
 ## alloc-osd
 
 `vitastor-cli alloc-osd`

docs/usage/disk.en.md

@@ -86,6 +86,8 @@ Options (both modes):
 --journal_size 1G/32M      Set journal size (area or partition size)
 --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       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
@@ -100,8 +102,9 @@ checks the device cache status on start and tries to disable cache for SATA/SAS
 If it doesn't succeed it issues a warning in the system log.
 
 You can also pass other OSD options here as arguments and they'll be persisted
-to the superblock: max_write_iodepth, max_write_iodepth, min_flusher_count,
-max_flusher_count, inmemory_metadata, inmemory_journal, journal_sector_buffer_count,
+in the superblock: cached_read_data, cached_read_meta, cached_read_journal,
+inmemory_metadata, inmemory_journal, max_write_iodepth,
+min_flusher_count, max_flusher_count, journal_sector_buffer_count,
 journal_no_same_sector_overwrites, throttle_small_writes, throttle_target_iops,
 throttle_target_mbs, throttle_target_parallelism, throttle_threshold_us.
 See [Runtime OSD Parameters](../config/osd.en.md) for details.
@@ -249,7 +252,9 @@ Options (see also [Cluster-Wide Disk Layout Parameters](../config/layout-cluster
 ```
 --object_size 128k       Set blockstore block size
 --bitmap_granularity 4k  Set bitmap granularity
---journal_size 32M       Set journal size
+--journal_size 16M       Set journal size
+--data_csum_type none    Set data checksum type (crc32c or none)
+--csum_block_size 4k     Set data checksum block size
 --device_block_size 4k   Set device block size
 --journal_offset 0       Set journal offset
 --device_size 0          Set device size

docs/usage/disk.ru.md

@@ -87,6 +87,8 @@ vitastor-disk - инструмент командной строки для уп
 --journal_size 1G/32M      Задать размер журнала (области или раздела журнала)
 --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       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
@@ -101,8 +103,9 @@ vitastor-disk - инструмент командной строки для уп
 это не удаётся, в системный журнал выводится предупреждение.
 
 Вы можете передать данной команде и некоторые другие опции OSD в качестве аргументов
-и они тоже будут сохранены в суперблок: max_write_iodepth, max_write_iodepth, min_flusher_count,
-max_flusher_count, inmemory_metadata, inmemory_journal, journal_sector_buffer_count,
+и они тоже будут сохранены в суперблок: cached_read_data, cached_read_meta,
+cached_read_journal, inmemory_metadata, inmemory_journal, max_write_iodepth,
+min_flusher_count, max_flusher_count, journal_sector_buffer_count,
 journal_no_same_sector_overwrites, throttle_small_writes, throttle_target_iops,
 throttle_target_mbs, throttle_target_parallelism, throttle_threshold_us.
 Читайте об этих параметрах подробнее в разделе [Изменяемые параметры OSD](../config/osd.ru.md).
@@ -254,7 +257,9 @@ OSD отключены fsync-и.
 ```
 --object_size 128k       Размер блока хранилища
 --bitmap_granularity 4k  Гранулярность битовых карт
---journal_size 32M       Размер журнала
+--journal_size 16M       Размер журнала
+--data_csum_type none    Задать тип контрольных сумм (crc32c или none)
+--csum_block_size 4k     Задать размер блока расчёта контрольных сумм
 --device_block_size 4k   Размер блока устройства
 --journal_offset 0       Смещение журнала
 --device_size 0          Размер устройства

docs/usage/nbd.en.md

@@ -13,6 +13,8 @@ remains decent (see an example [here](../performance/comparison1.en.md#vitastor-
 
 Vitastor Kubernetes CSI driver is based on NBD.
 
+See also [VDUSE](qemu.en.md#vduse).
+
 ## Map image
 
 To create a local block device for a Vitastor image run:
@@ -25,6 +27,23 @@ It will output a block device name like /dev/nbd0 which you can then use as a no
 
 You can also use `--pool <POOL> --inode <INODE> --size <SIZE>` instead of `--image <IMAGE>` if you want.
 
+Additional options for map command:
+
+* `--nbd_timeout 30` \
+  Timeout for I/O operations in seconds after exceeding which the kernel stops
+  the device. You can set it to 0 to disable the timeout, but beware that you
+  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.
+* `--foreground 1` \
+  Stay in foreground, do not daemonize.
+
 ## Unmap image
 
 To unmap the device run:
@@ -32,3 +51,27 @@ To unmap the device run:
 ```
 vitastor-nbd unmap /dev/nbd0
 ```
+
+## List mapped images
+
+```
+vitastor-nbd ls [--json]
+```
+
+Example output (normal format):
+
+```
+/dev/nbd0
+image: bench
+pid: 584536
+
+/dev/nbd1
+image: bench1
+pid: 584546
+```
+
+Example output (JSON format):
+
+```
+{"/dev/nbd0": {"image": "bench", "pid": 584536}, "/dev/nbd1": {"image": "bench1", "pid": 584546}}
+```

docs/usage/nbd.ru.md

@@ -16,6 +16,8 @@ NBD немного снижает производительность из-за
 
 CSI-драйвер Kubernetes Vitastor основан на NBD.
 
+Смотрите также [VDUSE](qemu.ru.md#vduse).
+
 ## Подключить устройство
 
 Чтобы создать локальное блочное устройство для образа, выполните команду:
@@ -30,6 +32,27 @@ vitastor-nbd map --etcd_address 10.115.0.10:2379/v3 --image testimg
 Для обращения по номеру инода, аналогично другим командам, можно использовать опции
 `--pool <POOL> --inode <INODE> --size <SIZE>` вместо `--image testimg`.
 
+Дополнительные опции для команды подключения NBD-устройства:
+
+* `--nbd_timeout 30` \
+  Максимальное время выполнения любой операции чтения/записи в секундах, при
+  превышении которого ядро остановит NBD-устройство. Вы можете установить опцию
+  в 0, чтобы отключить ограничение времени, но имейте в виду, что в этом случае
+  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`). 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
+  в консоли с `--foreground 1`.
+* `--dev_num N` \
+  Использовать заданное устройство `/dev/nbdN` вместо автоматического подбора.
+* `--foreground 1` \
+  Не уводить процесс в фоновый режим.
+
 ## Отключить устройство
 
 Для отключения устройства выполните:
@@ -37,3 +60,27 @@ vitastor-nbd map --etcd_address 10.115.0.10:2379/v3 --image testimg
 ```
 vitastor-nbd unmap /dev/nbd0
 ```
+
+## Вывести подключённые устройства
+
+```
+vitastor-nbd ls [--json]
+```
+
+Пример вывода в обычном формате:
+
+```
+/dev/nbd0
+image: bench
+pid: 584536
+
+/dev/nbd1
+image: bench1
+pid: 584546
+```
+
+Пример вывода в JSON-формате:
+
+```
+{"/dev/nbd0": {"image": "bench", "pid": 584536}, "/dev/nbd1": {"image": "bench1", "pid": 584546}}
+```

docs/usage/nfs.ru.md

@@ -29,7 +29,7 @@ vitastor-nfs [--etcd_address ADDR] [ДРУГИЕ ОПЦИИ]
 --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>     исползовать пул <POOL> для новых образов (обязательно, если пул в кластере не один)
+--pool <POOL>     использовать пул <POOL> для новых образов (обязательно, если пул в кластере не один)
 --foreground 1    не уходить в фон после запуска
 ```
 

docs/usage/qemu.en.md

@@ -83,3 +83,43 @@ qemu-img rebase -u -b '' testimg.qcow2
 This can be used for backups. Just note that exporting an image that is currently being written to
 is of course unsafe and doesn't produce a consistent result, so only export snapshots if you do this
 on a live VM.
+
+## VDUSE
+
+Linux kernel, starting with version 5.15, supports a new interface for attaching virtual disks
+to the host - VDUSE (vDPA Device in Userspace). QEMU, starting with 7.2, has support for
+exporting QEMU block devices over this protocol using qemu-storage-daemon.
+
+VDUSE has the same problem as other FUSE-like interfaces in Linux: if a userspace process hangs,
+for example, if it loses connectivity with Vitastor cluster - active processes doing I/O may
+hang in the D state (uninterruptible sleep) and you won't be able to kill them even with kill -9.
+In this case reboot will be the only way to remove VDUSE devices from system.
+
+On the other hand, VDUSE is faster than [NBD](nbd.en.md), so you may prefer to use it if
+performance is important for you. Approximate performance numbers:
+direct fio benchmark - 115000 iops, NBD - 60000 iops, VDUSE - 90000 iops.
+
+To try VDUSE you need at least Linux 5.15, built with VDUSE support
+(CONFIG_VIRTIO_VDPA=m and CONFIG_VDPA_USER=m). Debian Linux kernels have these options
+disabled by now, so if you want to try it on Debian, use a kernel from Ubuntu
+[kernel-ppa/mainline](https://kernel.ubuntu.com/~kernel-ppa/mainline/) or Proxmox.
+
+Commands to attach Vitastor image as a VDUSE device:
+
+```
+modprobe vduse virtio-vdpa
+qemu-storage-daemon --daemonize --blockdev '{"node-name":"test1","driver":"vitastor",\
+  "etcd-host":"192.168.7.2:2379/v3","image":"testosd1","cache":{"direct":true,"no-flush":false},"discard":"unmap"}' \
+  --export vduse-blk,id=test1,node-name=test1,name=test1,num-queues=16,queue-size=128,writable=true
+vdpa dev add name test1 mgmtdev vduse
+```
+
+After running these commands /dev/vda device will appear in the system and you'll be able to
+use it as a normal disk.
+
+To remove the device:
+
+```
+vdpa dev del test1
+kill <qemu-storage-daemon_process_PID>
+```

docs/usage/qemu.ru.md

@@ -87,3 +87,43 @@ qemu-img rebase -u -b '' testimg.qcow2
 Это можно использовать для резервного копирования. Только помните, что экспортировать образ, в который
 в то же время идёт запись, небезопасно - результат чтения не будет целостным. Так что если вы работаете
 с активными виртуальными машинами, экспортируйте только их снимки, но не сам образ.
+
+## VDUSE
+
+В Linux, начиная с версии ядра 5.15, доступен новый интерфейс для подключения виртуальных дисков
+к системе - VDUSE (vDPA Device in Userspace), а в QEMU, начиная с версии 7.2, есть поддержка
+экспорта блочных устройств QEMU по этому протоколу через qemu-storage-daemon.
+
+VDUSE страдает общей проблемой FUSE-подобных интерфейсов в Linux: если пользовательский процесс
+подвиснет, например, если будет потеряна связь с кластером Vitastor - читающие/пишущие в кластер
+процессы могут "залипнуть" в состоянии D (непрерываемый сон) и их будет невозможно убить даже
+через kill -9. В этом случае удалить из системы устройство можно только перезагрузившись.
+
+С другой стороны, VDUSE быстрее по сравнению с [NBD](nbd.ru.md), поэтому его может
+быть предпочтительно использовать там, где производительность важнее. Порядок показателей:
+прямое тестирование через fio - 115000 iops, NBD - 60000 iops, VDUSE - 90000 iops.
+
+Чтобы использовать VDUSE, вам нужно ядро Linux версии хотя бы 5.15, собранное с поддержкой
+VDUSE (CONFIG_VIRTIO_VDPA=m и CONFIG_VDPA_USER=m). В ядрах в Debian Linux поддержка пока
+отключена - если хотите попробовать эту функцию на Debian, поставьте ядро из Ubuntu
+[kernel-ppa/mainline](https://kernel.ubuntu.com/~kernel-ppa/mainline/) или из Proxmox.
+
+Команды для подключения виртуального диска через VDUSE:
+
+```
+modprobe vduse virtio-vdpa
+qemu-storage-daemon --daemonize --blockdev '{"node-name":"test1","driver":"vitastor",\
+  "etcd-host":"192.168.7.2:2379/v3","image":"testosd1","cache":{"direct":true,"no-flush":false},"discard":"unmap"}' \
+  --export vduse-blk,id=test1,node-name=test1,name=test1,num-queues=16,queue-size=128,writable=true
+vdpa dev add name test1 mgmtdev vduse
+```
+
+После этого в системе появится устройство /dev/vda, которое можно будет использовать как
+обычный диск.
+
+Для удаления устройства из системы:
+
+```
+vdpa dev del test1
+kill <PID_процесса_qemu-storage-daemon>
+```

mon/make-etcd

@@ -63,8 +63,9 @@ Wants=network-online.target local-fs.target time-sync.target
 
 [Service]
 Restart=always
-ExecStart=/usr/local/bin/etcd -name etcd${num} --data-dir /var/lib/etcd${num}.etcd \\
-    --advertise-client-urls http://${etcds[num]}:2379 --listen-client-urls http://${etcds[num]}:2379 \\
+Environment=GOGC=50
+ExecStart=etcd -name etcd${num} --data-dir /var/lib/etcd${num}.etcd \\
+    --snapshot-count 10000 --advertise-client-urls http://${etcds[num]}:2379 --listen-client-urls http://${etcds[num]}:2379 \\
     --initial-advertise-peer-urls http://${etcds[num]}:2380 --listen-peer-urls http://${etcds[num]}:2380 \\
     --initial-cluster-token vitastor-etcd-1 --initial-cluster ${etcd_cluster} \\
     --initial-cluster-state new --max-txn-ops=100000 --max-request-bytes=104857600 \\

mon/mon.js

@@ -104,12 +104,21 @@ const etcd_tree = {
             autosync_writes: 128,
             client_queue_depth: 128, // unused
             recovery_queue_depth: 4,
+            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,
@@ -172,6 +181,8 @@ const etcd_tree = {
                 osd_tags?: 'nvme' | [ 'nvme', ... ],
                 // prefer to put primary on OSD with these tags
                 primary_affinity_tags?: 'nvme' | [ 'nvme', ... ],
+                // scrub interval
+                scrub_interval?: '30d',
             },
             ...
         }, */
@@ -267,7 +278,7 @@ const etcd_tree = {
                     primary: osd_num_t,
                     state: ("starting"|"peering"|"incomplete"|"active"|"repeering"|"stopping"|"offline"|
                         "degraded"|"has_incomplete"|"has_degraded"|"has_misplaced"|"has_unclean"|
-                        "has_invalid"|"left_on_dead")[],
+                        "has_invalid"|"has_inconsistent"|"has_corrupted"|"left_on_dead"|"scrubbing")[],
                 }
             }, */
         },
@@ -289,6 +300,7 @@ const etcd_tree = {
                     osd_sets: osd_num_t[][],
                     all_peers: osd_num_t[],
                     epoch: uint64_t,
+                    next_scrub: uint64_t,
                 },
             }, */
         },
@@ -379,6 +391,7 @@ class Mon
         this.etcd_start_timeout = (config.etcd_start_timeout || 5) * 1000;
         this.state = JSON.parse(JSON.stringify(this.constructor.etcd_tree));
         this.signals_set = false;
+        this.stat_time = Date.now();
         this.ws = null;
         this.ws_alive = false;
         this.ws_keepalive_timer = null;
@@ -848,7 +861,7 @@ class Mon
         }
         for (const node_id in tree)
         {
-            if (node_id === '')
+            if (node_id === '' || tree[node_id].level === 'osd' && (!tree[node_id].size || tree[node_id].size <= 0))
             {
                 continue;
             }
@@ -958,7 +971,7 @@ class Mon
 
     save_new_pgs_txn(save_to, request, pool_id, up_osds, osd_tree, prev_pgs, new_pgs, pg_history)
     {
-        const aff_osds = this.get_affinity_osds(this.state.config.pools[pool_id], up_osds, osd_tree);
+        const aff_osds = this.get_affinity_osds(this.state.config.pools[pool_id] || {}, up_osds, osd_tree);
         const pg_items = {};
         this.reset_rng();
         new_pgs.map((osd_set, i) =>
@@ -1398,65 +1411,75 @@ class Mon
         }
     }
 
+    derive_osd_stats(st, prev)
+    {
+        const zero_stats = { op: { bps: 0n, iops: 0n, lat: 0n }, subop: { iops: 0n, lat: 0n }, recovery: { bps: 0n, iops: 0n } };
+        const diff = { op_stats: {}, subop_stats: {}, recovery_stats: {} };
+        if (!st || !st.time || prev && (prev.time || this.stat_time/1000) >= st.time)
+        {
+            return diff;
+        }
+        const timediff = BigInt(st.time*1000 - (prev && prev.time*1000 || this.stat_time));
+        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 };
+        }
+        return diff;
+    }
+
     sum_op_stats(timestamp, prev_stats)
     {
-        const op_stats = {}, subop_stats = {}, recovery_stats = {};
+        const sum_diff = { op_stats: {}, subop_stats: {}, recovery_stats: {} };
+        if (!prev_stats || prev_stats.timestamp >= timestamp)
+        {
+            return sum_diff;
+        }
+        const tm = BigInt(timestamp - (prev_stats.timestamp || 0));
+        // Sum derived values instead of deriving summed
         for (const osd in this.state.osd.stats)
         {
-            const st = this.state.osd.stats[osd]||{};
-            for (const op in st.op_stats||{})
+            const derived = this.derive_osd_stats(this.state.osd.stats[osd],
+                this.prev_stats && this.prev_stats.osd_stats && this.prev_stats.osd_stats[osd]);
+            for (const type in derived)
             {
-                op_stats[op] = op_stats[op] || { count: 0n, usec: 0n, bytes: 0n };
-                op_stats[op].count += BigInt(st.op_stats[op].count||0);
-                op_stats[op].usec += BigInt(st.op_stats[op].usec||0);
-                op_stats[op].bytes += BigInt(st.op_stats[op].bytes||0);
-            }
-            for (const op in st.subop_stats||{})
-            {
-                subop_stats[op] = subop_stats[op] || { count: 0n, usec: 0n };
-                subop_stats[op].count += BigInt(st.subop_stats[op].count||0);
-                subop_stats[op].usec += BigInt(st.subop_stats[op].usec||0);
-            }
-            for (const op in st.recovery_stats||{})
-            {
-                recovery_stats[op] = recovery_stats[op] || { count: 0n, bytes: 0n };
-                recovery_stats[op].count += BigInt(st.recovery_stats[op].count||0);
-                recovery_stats[op].bytes += BigInt(st.recovery_stats[op].bytes||0);
+                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];
+                    }
+                }
             }
         }
-        if (prev_stats && prev_stats.timestamp >= timestamp)
-        {
-            prev_stats = null;
-        }
-        const tm = prev_stats ? BigInt(timestamp - prev_stats.timestamp) : 0;
-        for (const op in op_stats)
-        {
-            if (prev_stats && prev_stats.op_stats && prev_stats.op_stats[op])
-            {
-                op_stats[op].bps = (op_stats[op].bytes - prev_stats.op_stats[op].bytes) * 1000n / tm;
-                op_stats[op].iops = (op_stats[op].count - prev_stats.op_stats[op].count) * 1000n / tm;
-                op_stats[op].lat = (op_stats[op].usec - prev_stats.op_stats[op].usec)
-                    / ((op_stats[op].count - prev_stats.op_stats[op].count) || 1n);
-            }
-        }
-        for (const op in subop_stats)
-        {
-            if (prev_stats && prev_stats.subop_stats && prev_stats.subop_stats[op])
-            {
-                subop_stats[op].iops = (subop_stats[op].count - prev_stats.subop_stats[op].count) * 1000n / tm;
-                subop_stats[op].lat = (subop_stats[op].usec - prev_stats.subop_stats[op].usec)
-                    / ((subop_stats[op].count - prev_stats.subop_stats[op].count) || 1n);
-            }
-        }
-        for (const op in recovery_stats)
-        {
-            if (prev_stats && prev_stats.recovery_stats && prev_stats.recovery_stats[op])
-            {
-                recovery_stats[op].bps = (recovery_stats[op].bytes - prev_stats.recovery_stats[op].bytes) * 1000n / tm;
-                recovery_stats[op].iops = (recovery_stats[op].count - prev_stats.recovery_stats[op].count) * 1000n / tm;
-            }
-        }
-        return { op_stats, subop_stats, recovery_stats };
+        return sum_diff;
     }
 
     sum_object_counts()
@@ -1585,7 +1608,7 @@ class Mon
                 }
             }
         }
-        return inode_stats;
+        return { inode_stats, seen_pools };
     }
 
     serialize_bigints(obj)
@@ -1611,11 +1634,12 @@ class Mon
         const timestamp = Date.now();
         const { object_counts, object_bytes } = this.sum_object_counts();
         let stats = this.sum_op_stats(timestamp, this.prev_stats);
-        let inode_stats = this.sum_inode_stats(
+        let { inode_stats, seen_pools } = this.sum_inode_stats(
             this.prev_stats ? this.prev_stats.inode_stats : null,
             timestamp, this.prev_stats ? this.prev_stats.timestamp : null
         );
-        this.prev_stats = { timestamp, ...stats, inode_stats };
+        this.prev_stats = { timestamp, inode_stats, osd_stats: { ...this.state.osd.stats } };
+        this.stat_time = Date.now();
         stats.object_counts = object_counts;
         stats.object_bytes = object_bytes;
         stats = this.serialize_bigints(stats);
@@ -1645,12 +1669,22 @@ class Mon
         }
         for (const pool_id in this.state.pool.stats)
         {
-            const pool_stats = { ...this.state.pool.stats[pool_id] };
-            this.serialize_bigints(pool_stats);
-            txn.push({ requestPut: {
-                key: b64(this.etcd_prefix+'/pool/stats/'+pool_id),
-                value: b64(JSON.stringify(pool_stats)),
-            } });
+            if (!seen_pools[pool_id])
+            {
+                txn.push({ requestDeleteRange: {
+                    key: b64(this.etcd_prefix+'/pool/stats/'+pool_id),
+                } });
+                delete this.state.pool.stats[pool_id];
+            }
+            else
+            {
+                const pool_stats = { ...this.state.pool.stats[pool_id] };
+                this.serialize_bigints(pool_stats);
+                txn.push({ requestPut: {
+                    key: b64(this.etcd_prefix+'/pool/stats/'+pool_id),
+                    value: b64(JSON.stringify(pool_stats)),
+                } });
+            }
         }
         if (txn.length)
         {
@@ -1731,13 +1765,14 @@ class Mon
         else if (key_parts[0] === 'osd' && key_parts[1] === 'stats')
         {
             // Recheck OSD tree on OSD addition/deletion
+            const osd_num = key_parts[2];
             if ((!old) != (!kv.value) || old && kv.value && old.size != kv.value.size)
             {
                 this.schedule_recheck();
             }
             // Recheck PGs <osd_out_time> after last OSD statistics report
             this.schedule_next_recheck_at(
-                !this.state.osd.stats[key[2]] ? 0 : this.state.osd.stats[key[2]].time+this.config.osd_out_time
+                !this.state.osd.stats[osd_num] ? 0 : this.state.osd.stats[osd_num].time+this.config.osd_out_time
             );
         }
     }
@@ -1823,6 +1858,7 @@ function POST(url, body, timeout)
             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', () =>
             {
@@ -1842,6 +1878,8 @@ function POST(url, body, timeout)
                 }
             });
         });
+        req.on('error', (error) => ok({ error }));
+        req.on('close', () => ok({ error: new Error('Connection closed prematurely') }));
         req.write(body_text);
         req.end();
     });

patches/VitastorPlugin.pm

@@ -388,8 +388,6 @@ sub unmap_volume
     my ($class, $storeid, $scfg, $volname, $snapname) = @_;
     my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
 
-    return 1 if !$scfg->{vitastor_nbd};
-
     my ($vtype, $name, $vmid) = $class->parse_volname($volname);
     $name .= '@'.$snapname if $snapname;
 
@@ -413,7 +411,7 @@ sub activate_volume
 sub deactivate_volume
 {
     my ($class, $storeid, $scfg, $volname, $snapname, $cache) = @_;
-    $class->unmap_volume($storeid, $scfg, $volname, $snapname);
+    $class->unmap_volume($storeid, $scfg, $volname, $snapname) if $scfg->{vitastor_nbd};
     return 1;
 }
 

patches/cinder-vitastor.py

@@ -50,7 +50,7 @@ from cinder.volume import configuration
 from cinder.volume import driver
 from cinder.volume import volume_utils
 
-VERSION = '0.8.8'
+VERSION = '0.9.3'
 
 LOG = logging.getLogger(__name__)
 

patches/libvirt-9.0-vitastor.diff

@@ -0,0 +1,644 @@
+commit e6f935157944279c2c0634915c3c00feeec748c9
+Author: Vitaliy Filippov <vitalif@yourcmc.ru>
+Date:   Mon Jun 19 00:58:19 2023 +0300
+
+    Add Vitastor support
+
+diff --git a/include/libvirt/libvirt-storage.h b/include/libvirt/libvirt-storage.h
+index aaad4a3..5f5daa8 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 45965fa..b7c23d3 100644
+--- a/src/conf/domain_conf.c
++++ b/src/conf/domain_conf.c
+@@ -7103,7 +7103,8 @@ 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)
+@@ -30121,6 +30122,7 @@ 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 5a9bf20..05058b8 100644
+--- a/src/conf/domain_validate.c
++++ b/src/conf/domain_validate.c
+@@ -494,6 +494,7 @@ 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) {
+@@ -550,11 +551,15 @@ 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/schemas/domaincommon.rng b/src/conf/schemas/domaincommon.rng
+index 6cb0a20..8bf7de9 100644
+--- a/src/conf/schemas/domaincommon.rng
++++ b/src/conf/schemas/domaincommon.rng
+@@ -1972,6 +1972,35 @@
+     </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">
+@@ -2264,6 +2293,7 @@
+       <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 f5a9636..8339bc4 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 |
+@@ -542,6 +554,11 @@ 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;
+@@ -1132,6 +1149,7 @@ 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 fc67957..720c07e 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 cecd7e8..d7b79a4 100644
+--- a/src/conf/storage_source_conf.c
++++ b/src/conf/storage_source_conf.c
+@@ -87,6 +87,7 @@ VIR_ENUM_IMPL(virStorageNetProtocol,
+               "ssh",
+               "vxhs",
+               "nfs",
++              "vitastor",
+ );
+ 
+ 
+@@ -1286,6 +1287,7 @@ 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 14a6825..eb4acac 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 e6c187e..035b423 100644
+--- a/src/conf/virstorageobj.c
++++ b/src/conf/virstorageobj.c
+@@ -1433,6 +1433,7 @@ 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:
+@@ -1918,6 +1919,8 @@ 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 8490034..ab2cdaa 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 17ac880..59711b5 100644
+--- a/src/libxl/libxl_conf.c
++++ b/src/libxl/libxl_conf.c
+@@ -970,6 +970,7 @@ 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 6919325..55ffc32 100644
+--- a/src/libxl/xen_xl.c
++++ b/src/libxl/xen_xl.c
+@@ -1445,6 +1445,7 @@ 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 e865aa1..40162af 100644
+--- a/src/qemu/qemu_block.c
++++ b/src/qemu/qemu_block.c
+@@ -604,6 +604,38 @@ 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)
+ {
+@@ -917,6 +949,12 @@ 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)))
+@@ -1860,6 +1898,7 @@ 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:
+@@ -2242,6 +2281,12 @@ 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 2eb5653..60ee82d 100644
+--- a/src/qemu/qemu_domain.c
++++ b/src/qemu/qemu_domain.c
+@@ -4958,7 +4958,8 @@ 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;
+@@ -10129,6 +10130,7 @@ 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 b841680..a6be771 100644
+--- a/src/qemu/qemu_snapshot.c
++++ b/src/qemu/qemu_snapshot.c
+@@ -373,6 +373,7 @@ 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:
+@@ -578,6 +579,7 @@ 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 d90c1c9..e853457 100644
+--- a/src/storage/storage_driver.c
++++ b/src/storage/storage_driver.c
+@@ -1627,6 +1627,7 @@ 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 e48ae72..2017ccc 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 bd6f063..cce34e1 100644
+--- a/src/test/test_driver.c
++++ b/src/test/test_driver.c
+@@ -7338,6 +7338,7 @@ 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 eee75af..8bd0a57 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 805950a..852df0d 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 e8e40d6..db55fe5 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 8a98c6a..4b1bbd4 100644
+--- a/tools/virsh-pool.c
++++ b/tools/virsh-pool.c
+@@ -1221,6 +1221,9 @@ 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;
+             }

patches/pve-qemu-8.0-vitastor.patch

@@ -0,0 +1,190 @@
+diff --git a/block/meson.build b/block/meson.build
+index 382bec0e7d..af6207dbce 100644
+--- a/block/meson.build
++++ b/block/meson.build
+@@ -114,6 +114,7 @@ foreach m : [
+   [libnfs, 'nfs', files('nfs.c')],
+   [libssh, 'ssh', files('ssh.c')],
+   [rbd, 'rbd', files('rbd.c')],
++  [vitastor, 'vitastor', files('vitastor.c')],
+ ]
+   if m[0].found()
+     module_ss = ss.source_set()
+diff --git a/meson.build b/meson.build
+index c44d05a13f..ebedb42843 100644
+--- a/meson.build
++++ b/meson.build
+@@ -1028,6 +1028,26 @@ if not get_option('rbd').auto() or have_block
+   endif
+ endif
+ 
++vitastor = not_found
++if not get_option('vitastor').auto() or have_block
++  libvitastor_client = cc.find_library('vitastor_client', has_headers: ['vitastor_c.h'],
++    required: get_option('vitastor'), kwargs: static_kwargs)
++  if libvitastor_client.found()
++    if cc.links('''
++      #include <vitastor_c.h>
++      int main(void) {
++        vitastor_c_create_qemu(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
++        return 0;
++      }''', dependencies: libvitastor_client)
++      vitastor = declare_dependency(dependencies: libvitastor_client)
++    elif get_option('vitastor').enabled()
++      error('could not link libvitastor_client')
++    else
++      warning('could not link libvitastor_client, disabling')
++    endif
++  endif
++endif
++
+ glusterfs = not_found
+ glusterfs_ftruncate_has_stat = false
+ glusterfs_iocb_has_stat = false
+@@ -1882,6 +1902,7 @@ endif
+ config_host_data.set('CONFIG_OPENGL', opengl.found())
+ config_host_data.set('CONFIG_PROFILER', get_option('profiler'))
+ config_host_data.set('CONFIG_RBD', rbd.found())
++config_host_data.set('CONFIG_VITASTOR', vitastor.found())
+ config_host_data.set('CONFIG_RDMA', rdma.found())
+ config_host_data.set('CONFIG_SDL', sdl.found())
+ config_host_data.set('CONFIG_SDL_IMAGE', sdl_image.found())
+@@ -4020,6 +4041,7 @@ if spice_protocol.found()
+   summary_info += {'  spice server support': spice}
+ endif
+ summary_info += {'rbd support':       rbd}
++summary_info += {'vitastor support':  vitastor}
+ summary_info += {'smartcard support': cacard}
+ summary_info += {'U2F support':       u2f}
+ summary_info += {'libusb':            libusb}
+diff --git a/meson_options.txt b/meson_options.txt
+index fc9447d267..c4ac55c283 100644
+--- a/meson_options.txt
++++ b/meson_options.txt
+@@ -173,6 +173,8 @@ option('lzo', type : 'feature', value : 'auto',
+        description: 'lzo compression support')
+ option('rbd', type : 'feature', value : 'auto',
+        description: 'Ceph block device driver')
++option('vitastor', type : 'feature', value : 'auto',
++       description: 'Vitastor block device driver')
+ option('opengl', type : 'feature', value : 'auto',
+        description: 'OpenGL support')
+ option('rdma', type : 'feature', value : 'auto',
+diff --git a/qapi/block-core.json b/qapi/block-core.json
+index c05ad0c07e..f5eb701604 100644
+--- a/qapi/block-core.json
++++ b/qapi/block-core.json
+@@ -3308,7 +3308,7 @@
+             'raw', 'rbd',
+             { 'name': 'replication', 'if': 'CONFIG_REPLICATION' },
+             'pbs',
+-            'ssh', 'throttle', 'vdi', 'vhdx',
++            'ssh', 'throttle', 'vdi', 'vhdx', 'vitastor',
+             { 'name': 'virtio-blk-vfio-pci', 'if': 'CONFIG_BLKIO' },
+             { 'name': 'virtio-blk-vhost-user', 'if': 'CONFIG_BLKIO' },
+             { 'name': 'virtio-blk-vhost-vdpa', 'if': 'CONFIG_BLKIO' },
+@@ -4338,6 +4338,28 @@
+             '*key-secret': 'str',
+             '*server': ['InetSocketAddressBase'] } }
+ 
++##
++# @BlockdevOptionsVitastor:
++#
++# Driver specific block device options for vitastor
++#
++# @image:       Image name
++# @inode:       Inode number
++# @pool:        Pool ID
++# @size:        Desired image size in bytes
++# @config-path: Path to Vitastor configuration
++# @etcd-host:   etcd connection address(es)
++# @etcd-prefix: etcd key/value prefix
++##
++{ 'struct': 'BlockdevOptionsVitastor',
++  'data': { '*inode': 'uint64',
++            '*pool': 'uint64',
++            '*size': 'uint64',
++            '*image': 'str',
++            '*config-path': 'str',
++            '*etcd-host': 'str',
++            '*etcd-prefix': 'str' } }
++
+ ##
+ # @ReplicationMode:
+ #
+@@ -4787,6 +4809,7 @@
+       'throttle':   'BlockdevOptionsThrottle',
+       'vdi':        'BlockdevOptionsGenericFormat',
+       'vhdx':       'BlockdevOptionsGenericFormat',
++      'vitastor':   'BlockdevOptionsVitastor',
+       'virtio-blk-vfio-pci':
+                     { 'type': 'BlockdevOptionsVirtioBlkVfioPci',
+                       'if': 'CONFIG_BLKIO' },
+@@ -5187,6 +5210,17 @@
+             '*cluster-size' :   'size',
+             '*encrypt' :        'RbdEncryptionCreateOptions' } }
+ 
++##
++# @BlockdevCreateOptionsVitastor:
++#
++# Driver specific image creation options for Vitastor.
++#
++# @size: Size of the virtual disk in bytes
++##
++{ 'struct': 'BlockdevCreateOptionsVitastor',
++  'data': { 'location':         'BlockdevOptionsVitastor',
++            'size':             'size' } }
++
+ ##
+ # @BlockdevVmdkSubformat:
+ #
+@@ -5385,6 +5419,7 @@
+       'ssh':            'BlockdevCreateOptionsSsh',
+       'vdi':            'BlockdevCreateOptionsVdi',
+       'vhdx':           'BlockdevCreateOptionsVhdx',
++      'vitastor':       'BlockdevCreateOptionsVitastor',
+       'vmdk':           'BlockdevCreateOptionsVmdk',
+       'vpc':            'BlockdevCreateOptionsVpc'
+   } }
+diff --git a/scripts/ci/org.centos/stream/8/x86_64/configure b/scripts/ci/org.centos/stream/8/x86_64/configure
+index 6e8983f39c..1b0b9fcf3e 100755
+--- a/scripts/ci/org.centos/stream/8/x86_64/configure
++++ b/scripts/ci/org.centos/stream/8/x86_64/configure
+@@ -32,7 +32,7 @@
+ --with-git=meson \
+ --with-git-submodules=update \
+ --target-list="x86_64-softmmu" \
+---block-drv-rw-whitelist="qcow2,raw,file,host_device,nbd,iscsi,rbd,blkdebug,luks,null-co,nvme,copy-on-read,throttle,gluster" \
++--block-drv-rw-whitelist="qcow2,raw,file,host_device,nbd,iscsi,rbd,vitastor,blkdebug,luks,null-co,nvme,copy-on-read,throttle,gluster" \
+ --audio-drv-list="" \
+ --block-drv-ro-whitelist="vmdk,vhdx,vpc,https,ssh" \
+ --with-coroutine=ucontext \
+@@ -179,6 +179,7 @@
+ --enable-opengl \
+ --enable-pie \
+ --enable-rbd \
++--enable-vitastor \
+ --enable-rdma \
+ --enable-seccomp \
+ --enable-snappy \
+diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh
+index 009fab1515..95914e6ebc 100644
+--- a/scripts/meson-buildoptions.sh
++++ b/scripts/meson-buildoptions.sh
+@@ -144,6 +144,7 @@ meson_options_help() {
+   printf "%s\n" '  qed             qed image format support'
+   printf "%s\n" '  qga-vss         build QGA VSS support (broken with MinGW)'
+   printf "%s\n" '  rbd             Ceph block device driver'
++  printf "%s\n" '  vitastor        Vitastor block device driver'
+   printf "%s\n" '  rdma            Enable RDMA-based migration'
+   printf "%s\n" '  replication     replication support'
+   printf "%s\n" '  sdl             SDL user interface'
+@@ -392,6 +393,8 @@ _meson_option_parse() {
+     --disable-qom-cast-debug) printf "%s" -Dqom_cast_debug=false ;;
+     --enable-rbd) printf "%s" -Drbd=enabled ;;
+     --disable-rbd) printf "%s" -Drbd=disabled ;;
++    --enable-vitastor) printf "%s" -Dvitastor=enabled ;;
++    --disable-vitastor) printf "%s" -Dvitastor=disabled ;;
+     --enable-rdma) printf "%s" -Drdma=enabled ;;
+     --disable-rdma) printf "%s" -Drdma=disabled ;;
+     --enable-replication) printf "%s" -Dreplication=enabled ;;

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-0.8.8/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-0.8.8$(rpm --eval '%dist').tar.gz *
+tar --transform 's#^#vitastor-0.9.3/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-0.9.3$(rpm --eval '%dist').tar.gz *

rpm/vitastor-el7.Dockerfile

@@ -35,7 +35,7 @@ ADD . /root/vitastor
 RUN set -e; \
     cd /root/vitastor/rpm; \
     sh build-tarball.sh; \
-    cp /root/vitastor-0.8.8.el7.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-0.9.3.el7.tar.gz ~/rpmbuild/SOURCES; \
     cp vitastor-el7.spec ~/rpmbuild/SPECS/vitastor.spec; \
     cd ~/rpmbuild/SPECS/; \
     rpmbuild -ba vitastor.spec; \

rpm/vitastor-el7.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        0.8.8
+Version:        0.9.3
 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-0.8.8.el7.tar.gz
+Source0:        vitastor-0.9.3.el7.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

rpm/vitastor-el8.Dockerfile

@@ -35,7 +35,7 @@ ADD . /root/vitastor
 RUN set -e; \
     cd /root/vitastor/rpm; \
     sh build-tarball.sh; \
-    cp /root/vitastor-0.8.8.el8.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-0.9.3.el8.tar.gz ~/rpmbuild/SOURCES; \
     cp vitastor-el8.spec ~/rpmbuild/SPECS/vitastor.spec; \
     cd ~/rpmbuild/SPECS/; \
     rpmbuild -ba vitastor.spec; \

rpm/vitastor-el8.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        0.8.8
+Version:        0.9.3
 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-0.8.8.el8.tar.gz
+Source0:        vitastor-0.9.3.el8.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

rpm/vitastor-el9.Dockerfile

@@ -18,7 +18,7 @@ ADD . /root/vitastor
 RUN set -e; \
     cd /root/vitastor/rpm; \
     sh build-tarball.sh; \
-    cp /root/vitastor-0.8.8.el9.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-0.9.3.el9.tar.gz ~/rpmbuild/SOURCES; \
     cp vitastor-el9.spec ~/rpmbuild/SPECS/vitastor.spec; \
     cd ~/rpmbuild/SPECS/; \
     rpmbuild -ba vitastor.spec; \

rpm/vitastor-el9.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        0.8.8
+Version:        0.9.3
 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-0.8.8.el9.tar.gz
+Source0:        vitastor-0.9.3.el9.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel
@@ -73,7 +73,7 @@ Vitastor library headers for development.
 Summary:        Vitastor - fio drivers
 Group:          Development/Libraries
 Requires:       vitastor-client = %{version}-%{release}
-Requires:       fio = 3.27-7.el9
+Requires:       fio = 3.27-8.el9
 
 
 %description -n vitastor-fio

src/CMakeLists.txt

@@ -16,7 +16,7 @@ if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
 	set(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
 endif()
 
-add_definitions(-DVERSION="0.8.8")
+add_definitions(-DVERSION="0.9.3")
 add_definitions(-Wall -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith -fdiagnostics-color=always -I ${CMAKE_SOURCE_DIR}/src)
 if (${WITH_ASAN})
 	add_definitions(-fsanitize=address -fno-omit-frame-pointer)
@@ -111,7 +111,7 @@ target_compile_options(vitastor_common PUBLIC -fPIC)
 add_executable(vitastor-osd
 	osd_main.cpp osd.cpp osd_secondary.cpp osd_peering.cpp osd_flush.cpp osd_peering_pg.cpp
 	osd_primary.cpp osd_primary_chain.cpp osd_primary_sync.cpp osd_primary_write.cpp osd_primary_subops.cpp
-	osd_cluster.cpp osd_rmw.cpp
+	osd_cluster.cpp osd_rmw.cpp osd_scrub.cpp osd_primary_describe.cpp
 )
 target_link_libraries(vitastor-osd
 	vitastor_common
@@ -141,6 +141,8 @@ add_library(vitastor_client SHARED
 	cli_common.cpp
 	cli_alloc_osd.cpp
 	cli_status.cpp
+	cli_describe.cpp
+	cli_fix.cpp
 	cli_df.cpp
 	cli_ls.cpp
 	cli_create.cpp
@@ -299,7 +301,7 @@ add_executable(test_cluster_client
 	EXCLUDE_FROM_ALL
 	test_cluster_client.cpp
 	pg_states.cpp osd_ops.cpp cluster_client.cpp cluster_client_list.cpp msgr_op.cpp mock/messenger.cpp msgr_stop.cpp
-	etcd_state_client.cpp timerfd_manager.cpp ../json11/json11.cpp
+	etcd_state_client.cpp timerfd_manager.cpp str_util.cpp ../json11/json11.cpp
 )
 target_compile_definitions(test_cluster_client PUBLIC -D__MOCK__)
 target_include_directories(test_cluster_client PUBLIC ${CMAKE_SOURCE_DIR}/src/mock)

src/allocator.cpp

@@ -143,34 +143,83 @@ uint64_t allocator::get_free_count()
     return free;
 }
 
+// FIXME: Move to utils?
 void bitmap_set(void *bitmap, uint64_t start, uint64_t len, uint64_t bitmap_granularity)
 {
-    if (start == 0)
+    if (start == 0 && len == 32*bitmap_granularity)
+        *((uint32_t*)bitmap) = UINT32_MAX;
+    else if (start == 0 && len == 64*bitmap_granularity)
+        *((uint64_t*)bitmap) = UINT64_MAX;
+    else
     {
-        if (len == 32*bitmap_granularity)
+        unsigned bit_start = start / bitmap_granularity;
+        unsigned bit_end = ((start + len) + bitmap_granularity - 1) / bitmap_granularity;
+        while (bit_start < bit_end)
         {
-            *((uint32_t*)bitmap) = UINT32_MAX;
-            return;
-        }
-        else if (len == 64*bitmap_granularity)
-        {
-            *((uint64_t*)bitmap) = UINT64_MAX;
-            return;
-        }
-    }
-    unsigned bit_start = start / bitmap_granularity;
-    unsigned bit_end = ((start + len) + bitmap_granularity - 1) / bitmap_granularity;
-    while (bit_start < bit_end)
-    {
-        if (!(bit_start & 7) && bit_end >= bit_start+8)
-        {
-            ((uint8_t*)bitmap)[bit_start / 8] = UINT8_MAX;
-            bit_start += 8;
-        }
-        else
-        {
-            ((uint8_t*)bitmap)[bit_start / 8] |= 1 << (bit_start % 8);
-            bit_start++;
+            if (!(bit_start & 7) && bit_end >= bit_start+8)
+            {
+                ((uint8_t*)bitmap)[bit_start / 8] = UINT8_MAX;
+                bit_start += 8;
+            }
+            else
+            {
+                ((uint8_t*)bitmap)[bit_start / 8] |= 1 << (bit_start % 8);
+                bit_start++;
+            }
         }
     }
 }
+
+void bitmap_clear(void *bitmap, uint64_t start, uint64_t len, uint64_t bitmap_granularity)
+{
+    if (start == 0 && len == 32*bitmap_granularity)
+        *((uint32_t*)bitmap) = 0;
+    else if (start == 0 && len == 64*bitmap_granularity)
+        *((uint64_t*)bitmap) = 0;
+    else
+    {
+        unsigned bit_start = start / bitmap_granularity;
+        unsigned bit_end = ((start + len) + bitmap_granularity - 1) / bitmap_granularity;
+        while (bit_start < bit_end)
+        {
+            if (!(bit_start & 7) && bit_end >= bit_start+8)
+            {
+                ((uint8_t*)bitmap)[bit_start / 8] = 0;
+                bit_start += 8;
+            }
+            else
+            {
+                ((uint8_t*)bitmap)[bit_start / 8] &= (0xFF ^ (1 << (bit_start % 8)));
+                bit_start++;
+            }
+        }
+    }
+}
+
+bool bitmap_check(void *bitmap, uint64_t start, uint64_t len, uint64_t bitmap_granularity)
+{
+    bool r = false;
+    if (start == 0 && len == 32*bitmap_granularity)
+        r = !!*((uint32_t*)bitmap);
+    else if (start == 0 && len == 64*bitmap_granularity)
+        r = !!*((uint64_t*)bitmap);
+    else
+    {
+        unsigned bit_start = start / bitmap_granularity;
+        unsigned bit_end = ((start + len) + bitmap_granularity - 1) / bitmap_granularity;
+        while (bit_start < bit_end)
+        {
+            if (!(bit_start & 7) && bit_end >= bit_start+8)
+            {
+                r = r || !!((uint8_t*)bitmap)[bit_start / 8];
+                bit_start += 8;
+            }
+            else
+            {
+                r = r || (((uint8_t*)bitmap)[bit_start / 8] & (1 << (bit_start % 8)));
+                bit_start++;
+            }
+        }
+    }
+    return r;
+}

src/allocator.h

@@ -23,3 +23,5 @@ public:
 };
 
 void bitmap_set(void *bitmap, uint64_t start, uint64_t len, uint64_t bitmap_granularity);
+void bitmap_clear(void *bitmap, uint64_t start, uint64_t len, uint64_t bitmap_granularity);
+bool bitmap_check(void *bitmap, uint64_t start, uint64_t len, uint64_t bitmap_granularity);

src/blockstore.h

@@ -73,7 +73,11 @@ Input:
   write request is copied into the metadata area bitwise and stored there.
 
 Output:
-- retval = number of bytes actually read/written or negative error number (-EINVAL or -ENOSPC)
+- retval = number of bytes actually read/written or negative error number
+  -EINVAL = invalid input parameters
+  -ENOENT = requested object/version does not exist for reads
+  -ENOSPC = no space left in the store for writes
+  -EDOM = checksum error.
 - version = the version actually read or written
 
 ## BS_OP_DELETE
@@ -122,11 +126,14 @@ Output:
 Get a list of all objects in this Blockstore.
 
 Input:
-- oid.stripe = PG alignment
-- len = PG count or 0 to list all objects
-- offset = PG number
-- oid.inode = min inode number or 0 to list all inodes
-- version = max inode number or 0 to list all inodes
+- pg_alignment = PG alignment
+- pg_count = PG count or 0 to list all objects
+- pg_number = PG number
+- list_stable_limit = max number of clean objects in the reply
+  it's guaranteed that dirty objects are returned from the same interval,
+  i.e. from (min_oid .. min(max_oid, max(returned stable OIDs)))
+- min_oid = min inode/stripe or 0 to list all objects
+- max_oid = max inode/stripe or 0 to list all objects
 
 Output:
 - retval = total obj_ver_id count
@@ -143,10 +150,27 @@ struct blockstore_op_t
     uint64_t opcode;
     // finish callback
     std::function<void (blockstore_op_t*)> callback;
-    object_id oid;
-    uint64_t version;
-    uint32_t offset;
-    uint32_t len;
+    union __attribute__((__packed__))
+    {
+        // R/W
+        struct __attribute__((__packed__))
+        {
+            object_id oid;
+            uint64_t version;
+            uint32_t offset;
+            uint32_t len;
+        };
+        // List
+        struct __attribute__((__packed__))
+        {
+            object_id min_oid;
+            object_id max_oid;
+            uint32_t pg_alignment;
+            uint32_t pg_count;
+            uint32_t pg_number;
+            uint32_t list_stable_limit;
+        };
+    };
     void *buf;
     void *bitmap;
     int retval;

src/blockstore_disk.cpp

@@ -40,10 +40,31 @@ void blockstore_disk_t::parse_config(std::map<std::string, std::string> & config
     data_block_size = parse_size(config["block_size"]);
     journal_device = config["journal_device"];
     journal_offset = parse_size(config["journal_offset"]);
-    disk_alignment = strtoull(config["disk_alignment"].c_str(), NULL, 10);
-    journal_block_size = strtoull(config["journal_block_size"].c_str(), NULL, 10);
-    meta_block_size = strtoull(config["meta_block_size"].c_str(), NULL, 10);
-    bitmap_granularity = strtoull(config["bitmap_granularity"].c_str(), NULL, 10);
+    disk_alignment = parse_size(config["disk_alignment"]);
+    journal_block_size = parse_size(config["journal_block_size"]);
+    meta_block_size = parse_size(config["meta_block_size"]);
+    bitmap_granularity = parse_size(config["bitmap_granularity"]);
+    meta_format = stoull_full(config["meta_format"]);
+    cached_read_data = config["cached_read_data"] == "true" || config["cached_read_data"] == "yes" || config["cached_read_data"] == "1";
+    cached_read_meta = cached_read_data && (meta_device == data_device || meta_device == "") &&
+        config.find("cached_read_meta") == config.end() ||
+        config["cached_read_meta"] == "true" || config["cached_read_meta"] == "yes" || config["cached_read_meta"] == "1";
+    cached_read_journal = cached_read_meta && (journal_device == meta_device || journal_device == "") &&
+        config.find("cached_read_journal") == config.end() ||
+        config["cached_read_journal"] == "true" || config["cached_read_journal"] == "yes" || config["cached_read_journal"] == "1";
+    if (config["data_csum_type"] == "crc32c")
+    {
+        data_csum_type = BLOCKSTORE_CSUM_CRC32C;
+    }
+    else if (config["data_csum_type"] == "" || config["data_csum_type"] == "none")
+    {
+        data_csum_type = BLOCKSTORE_CSUM_NONE;
+    }
+    else
+    {
+        throw std::runtime_error("data_csum_type="+config["data_csum_type"]+" is unsupported, only \"crc32c\" and \"none\" are supported");
+    }
+    csum_block_size = parse_size(config["csum_block_size"]);
     // Validate
     if (!data_block_size)
     {
@@ -91,7 +112,23 @@ void blockstore_disk_t::parse_config(std::map<std::string, std::string> & config
     }
     if (data_block_size % bitmap_granularity)
     {
-        throw std::runtime_error("Block size must be a multiple of sparse write tracking granularity");
+        throw std::runtime_error("Data block size must be a multiple of sparse write tracking granularity");
+    }
+    if (!data_csum_type)
+    {
+        csum_block_size = 0;
+    }
+    else if (!csum_block_size)
+    {
+        csum_block_size = bitmap_granularity;
+    }
+    if (csum_block_size && (csum_block_size % bitmap_granularity))
+    {
+        throw std::runtime_error("Checksum block size must be a multiple of sparse write tracking granularity");
+    }
+    if (csum_block_size && (data_block_size % csum_block_size))
+    {
+        throw std::runtime_error("Checksum block size must be a divisor of data block size");
     }
     if (meta_device == "")
     {
@@ -110,7 +147,9 @@ void blockstore_disk_t::parse_config(std::map<std::string, std::string> & config
         throw std::runtime_error("journal_offset must be a multiple of journal_block_size = "+std::to_string(journal_block_size));
     }
     clean_entry_bitmap_size = data_block_size / bitmap_granularity / 8;
-    clean_entry_size = sizeof(clean_disk_entry) + 2*clean_entry_bitmap_size;
+    clean_dyn_size = clean_entry_bitmap_size*2 + (csum_block_size
+        ? data_block_size/csum_block_size*(data_csum_type & 0xFF) : 0);
+    clean_entry_size = sizeof(clean_disk_entry) + clean_dyn_size + 4 /*entry_csum*/;
 }
 
 void blockstore_disk_t::calc_lengths(bool skip_meta_check)
@@ -160,6 +199,25 @@ void blockstore_disk_t::calc_lengths(bool skip_meta_check)
     // required metadata size
     block_count = data_len / data_block_size;
     meta_len = (1 + (block_count - 1 + meta_block_size / clean_entry_size) / (meta_block_size / clean_entry_size)) * meta_block_size;
+    if (meta_format == BLOCKSTORE_META_FORMAT_V1 ||
+        !meta_format && !skip_meta_check && meta_area_size < meta_len && !data_csum_type)
+    {
+        uint64_t clean_entry_v0_size = sizeof(clean_disk_entry) + 2*clean_entry_bitmap_size;
+        uint64_t meta_v0_len = (1 + (block_count - 1 + meta_block_size / clean_entry_v0_size)
+            / (meta_block_size / clean_entry_v0_size)) * meta_block_size;
+        if (meta_format == BLOCKSTORE_META_FORMAT_V1 || meta_area_size >= meta_v0_len)
+        {
+            // Old metadata fits.
+            printf("Warning: Using old metadata format without checksums because the new format doesn't fit into provided area\n");
+            clean_entry_size = clean_entry_v0_size;
+            meta_len = meta_v0_len;
+            meta_format = BLOCKSTORE_META_FORMAT_V1;
+        }
+        else
+            meta_format = BLOCKSTORE_META_FORMAT_V2;
+    }
+    else
+        meta_format = BLOCKSTORE_META_FORMAT_V2;
     if (!skip_meta_check && meta_area_size < meta_len)
     {
         throw std::runtime_error("Metadata area is too small, need at least "+std::to_string(meta_len)+" bytes");
@@ -237,6 +295,18 @@ void blockstore_disk_t::open_data()
     {
         throw std::runtime_error(std::string("Failed to lock data device: ") + strerror(errno));
     }
+    if (cached_read_data)
+    {
+        read_data_fd = open(data_device.c_str(), O_RDWR);
+        if (read_data_fd == -1)
+        {
+            throw std::runtime_error("Failed to open data device "+data_device+": "+std::string(strerror(errno)));
+        }
+    }
+    else
+    {
+        read_data_fd = data_fd;
+    }
 }
 
 void blockstore_disk_t::open_meta()
@@ -257,6 +327,18 @@ void blockstore_disk_t::open_meta()
         {
             throw std::runtime_error(std::string("Failed to lock metadata device: ") + strerror(errno));
         }
+        if (cached_read_meta)
+        {
+            read_meta_fd = open(meta_device.c_str(), O_RDWR);
+            if (read_meta_fd == -1)
+            {
+                throw std::runtime_error("Failed to open metadata device "+meta_device+": "+std::string(strerror(errno)));
+            }
+        }
+        else
+        {
+            read_meta_fd = meta_fd;
+        }
     }
     else
     {
@@ -275,6 +357,22 @@ void blockstore_disk_t::open_meta()
             ") is not a multiple of data device sector size ("+std::to_string(meta_device_sect)+")"
         );
     }
+    if (!cached_read_meta)
+    {
+        read_meta_fd = meta_fd;
+    }
+    else if (meta_device == data_device && cached_read_data)
+    {
+        read_meta_fd = read_data_fd;
+    }
+    else
+    {
+        read_meta_fd = open(meta_device.c_str(), O_RDWR);
+        if (read_meta_fd == -1)
+        {
+            throw std::runtime_error("Failed to open metadata device "+meta_device+": "+std::string(strerror(errno)));
+        }
+    }
 }
 
 void blockstore_disk_t::open_journal()
@@ -309,6 +407,26 @@ void blockstore_disk_t::open_journal()
             ") is not a multiple of journal device sector size ("+std::to_string(journal_device_sect)+")"
         );
     }
+    if (!cached_read_journal)
+    {
+        read_journal_fd = journal_fd;
+    }
+    else if (journal_device == meta_device && cached_read_meta)
+    {
+        read_journal_fd = read_meta_fd;
+    }
+    else if (journal_device == data_device && cached_read_data)
+    {
+        read_journal_fd = read_data_fd;
+    }
+    else
+    {
+        read_journal_fd = open(journal_device.c_str(), O_RDWR);
+        if (read_journal_fd == -1)
+        {
+            throw std::runtime_error("Failed to open journal device "+journal_device+": "+std::string(strerror(errno)));
+        }
+    }
 }
 
 void blockstore_disk_t::close_all()
@@ -319,5 +437,12 @@ void blockstore_disk_t::close_all()
         close(meta_fd);
     if (journal_fd >= 0 && journal_fd != meta_fd)
         close(journal_fd);
+    if (read_data_fd >= 0 && read_data_fd != data_fd)
+        close(read_data_fd);
+    if (read_meta_fd >= 0 && read_meta_fd != meta_fd)
+        close(read_meta_fd);
+    if (read_journal_fd >= 0 && read_journal_fd != journal_fd)
+        close(read_journal_fd);
     data_fd = meta_fd = journal_fd = -1;
+    read_data_fd = read_meta_fd = read_journal_fd = -1;
 }

src/blockstore_disk.h

@@ -8,6 +8,10 @@
 #include <string>
 #include <map>
 
+#define BLOCKSTORE_CSUM_NONE 0
+// Lower byte of checksum type is its length
+#define BLOCKSTORE_CSUM_CRC32C 0x104
+
 struct blockstore_disk_t
 {
     std::string data_device, meta_device, journal_device;
@@ -21,17 +25,24 @@ struct blockstore_disk_t
     uint64_t meta_block_size = 4096;
     // Sparse write tracking granularity. 4 KB is a good choice. Must be a multiple of disk_alignment
     uint64_t bitmap_granularity = 4096;
+    // Data checksum type, BLOCKSTORE_CSUM_NONE or BLOCKSTORE_CSUM_CRC32C
+    uint32_t data_csum_type = BLOCKSTORE_CSUM_NONE;
+    // Checksum block size, must be a multiple of bitmap_granularity
+    uint32_t csum_block_size = 4096;
     // By default, Blockstore locks all opened devices exclusively. This option can be used to disable locking
     bool disable_flock = false;
+    // Use linux page cache for reads. If enabled, separate buffered FDs will be opened for reading
+    bool cached_read_data = false, cached_read_meta = false, cached_read_journal = false;
 
     int meta_fd = -1, data_fd = -1, journal_fd = -1;
-    uint64_t meta_offset, meta_device_sect, meta_device_size, meta_len;
+    int read_meta_fd = -1, read_data_fd = -1, read_journal_fd = -1;
+    uint64_t meta_offset, meta_device_sect, meta_device_size, meta_len, meta_format = 0;
     uint64_t data_offset, data_device_sect, data_device_size, data_len;
     uint64_t journal_offset, journal_device_sect, journal_device_size, journal_len;
 
     uint32_t block_order;
     uint64_t block_count;
-    uint32_t clean_entry_bitmap_size = 0, clean_entry_size = 0;
+    uint32_t clean_entry_bitmap_size = 0, clean_entry_size = 0, clean_dyn_size = 0;
 
     void parse_config(std::map<std::string, std::string> & config);
     void open_data();
@@ -39,4 +50,13 @@ struct blockstore_disk_t
     void open_journal();
     void calc_lengths(bool skip_meta_check = false);
     void close_all();
+
+    inline uint64_t dirty_dyn_size(uint64_t offset, uint64_t len)
+    {
+        // Checksums may be partial if write is not aligned with csum_block_size
+        return clean_entry_bitmap_size + (csum_block_size && len > 0
+            ? ((offset+len+csum_block_size-1)/csum_block_size - offset/csum_block_size)
+                * (data_csum_type & 0xFF)
+            : 0);
+    }
 };

src/blockstore_flush.h

@@ -1,10 +1,22 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 (see README.md for details)
 
+#define COPY_BUF_JOURNAL 1
+#define COPY_BUF_DATA 2
+#define COPY_BUF_ZERO 4
+#define COPY_BUF_CSUM_FILL 8
+#define COPY_BUF_COALESCED 16
+#define COPY_BUF_META_BLOCK 32
+#define COPY_BUF_JOURNALED_BIG 64
+
 struct copy_buffer_t
 {
-    uint64_t offset, len;
+    int copy_flags;
+    uint64_t offset, len, disk_offset;
+    uint64_t journal_sector; // only for reads: sector+1 if used and !journal.inmemory, otherwise 0
     void *buf;
+    uint8_t *csum_buf;
+    int *dyn_data;
 };
 
 struct meta_sector_t
@@ -37,7 +49,7 @@ class journal_flusher_co
 {
     blockstore_impl_t *bs;
     journal_flusher_t *flusher;
-    int wait_state, wait_count;
+    int wait_state, wait_count, wait_journal_count;
     struct io_uring_sqe *sqe;
     struct ring_data_t *data;
 
@@ -46,28 +58,39 @@ class journal_flusher_co
     obj_ver_id cur;
     std::map<obj_ver_id, dirty_entry>::iterator dirty_it, dirty_start, dirty_end;
     std::map<object_id, uint64_t>::iterator repeat_it;
-    std::function<void(ring_data_t*)> simple_callback_r, simple_callback_w;
+    std::function<void(ring_data_t*)> simple_callback_r, simple_callback_rj, simple_callback_w;
 
     bool skip_copy, has_delete, has_writes;
     std::vector<copy_buffer_t> v;
     std::vector<copy_buffer_t>::iterator it;
+    int i;
+    bool fill_incomplete, cleared_incomplete;
+    int read_to_fill_incomplete;
     int copy_count;
-    uint64_t clean_loc, old_clean_loc;
+    uint64_t clean_loc, clean_ver, old_clean_loc, old_clean_ver;
     flusher_meta_write_t meta_old, meta_new;
     bool clean_init_bitmap;
     uint64_t clean_bitmap_offset, clean_bitmap_len;
-    void *new_clean_bitmap;
+    uint8_t *clean_init_dyn_ptr;
+    uint8_t *new_clean_bitmap;
 
     uint64_t new_trim_pos;
 
-    // local: scan_dirty()
-    uint64_t offset, end_offset, submit_offset, submit_len;
-
     friend class journal_flusher_t;
-    bool scan_dirty(int wait_base);
+    void scan_dirty();
+    bool read_dirty(int wait_base);
+    bool modify_meta_do_reads(int wait_base);
+    bool wait_meta_reads(int wait_base);
     bool modify_meta_read(uint64_t meta_loc, flusher_meta_write_t &wr, int wait_base);
+    bool clear_incomplete_csum_block_bits(int wait_base);
+    void calc_block_checksums(uint32_t *new_data_csums, bool skip_overwrites);
+    void update_metadata_entry();
+    bool write_meta_block(flusher_meta_write_t & meta_block, int wait_base);
     void update_clean_db();
+    void free_data_blocks();
     bool fsync_batch(bool fsync_meta, int wait_base);
+    bool trim_journal(int wait_base);
+    void free_buffers();
 public:
     journal_flusher_co();
     bool loop();
@@ -95,14 +118,16 @@ class journal_flusher_t
 
     std::map<uint64_t, meta_sector_t> meta_sectors;
     std::deque<object_id> flush_queue;
-    std::map<object_id, uint64_t> flush_versions;
+    std::map<object_id, uint64_t> flush_versions; // FIXME: consider unordered_map?
 
     bool try_find_older(std::map<obj_ver_id, dirty_entry>::iterator & dirty_end, obj_ver_id & cur);
+    bool try_find_other(std::map<obj_ver_id, dirty_entry>::iterator & dirty_end, obj_ver_id & cur);
 
 public:
     journal_flusher_t(blockstore_impl_t *bs);
     ~journal_flusher_t();
     void loop();
+    bool is_trim_wanted() { return trim_wanted; }
     bool is_active();
     void mark_trim_possible();
     void request_trim();
@@ -111,4 +136,5 @@ public:
     void unshift_flush(obj_ver_id oid, bool force);
     void remove_flush(object_id oid);
     void dump_diagnostics();
+    bool is_mutated(uint64_t clean_loc);
 };

src/blockstore_impl.cpp

@@ -13,6 +13,7 @@ blockstore_impl_t::blockstore_impl_t(blockstore_config_t & config, ring_loop_t *
     initialized = 0;
     parse_config(config, true);
     zero_object = (uint8_t*)memalign_or_die(MEM_ALIGNMENT, dsk.data_block_size);
+    alloc_dyn_data = dsk.clean_dyn_size > sizeof(void*) || dsk.csum_block_size > 0;
     try
     {
         dsk.open_data();
@@ -38,8 +39,8 @@ blockstore_impl_t::~blockstore_impl_t()
     dsk.close_all();
     if (metadata_buffer)
         free(metadata_buffer);
-    if (clean_bitmap)
-        free(clean_bitmap);
+    if (clean_bitmaps)
+        free(clean_bitmaps);
 }
 
 bool blockstore_impl_t::is_started()
@@ -462,11 +463,11 @@ void blockstore_impl_t::reshard_clean_db(pool_id_t pool, uint32_t pg_count, uint
 
 void blockstore_impl_t::process_list(blockstore_op_t *op)
 {
-    uint32_t list_pg = op->offset+1;
-    uint32_t pg_count = op->len;
-    uint64_t pg_stripe_size = op->oid.stripe;
-    uint64_t min_inode = op->oid.inode;
-    uint64_t max_inode = op->version;
+    uint32_t list_pg = op->pg_number+1;
+    uint32_t pg_count = op->pg_count;
+    uint64_t pg_stripe_size = op->pg_alignment;
+    uint64_t min_inode = op->min_oid.inode;
+    uint64_t max_inode = op->max_oid.inode;
     // Check PG
     if (pg_count != 0 && (pg_stripe_size < MIN_DATA_BLOCK_SIZE || list_pg > pg_count))
     {
@@ -513,7 +514,13 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
             stable_alloc += clean_db.size();
         }
     }
-    else
+    if (op->list_stable_limit > 0)
+    {
+        stable_alloc = op->list_stable_limit;
+        if (stable_alloc > 1024*1024)
+            stable_alloc = 1024*1024;
+    }
+    if (stable_alloc < 32768)
     {
         stable_alloc = 32768;
     }
@@ -524,22 +531,22 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
         FINISH_OP(op);
         return;
     }
+    auto max_oid = op->max_oid;
+    bool limited = false;
+    pool_pg_id_t last_shard_id = 0;
     for (auto shard_it = clean_db_shards.lower_bound(first_shard);
         shard_it != clean_db_shards.end() && shard_it->first <= last_shard;
         shard_it++)
     {
         auto & clean_db = shard_it->second;
         auto clean_it = clean_db.begin(), clean_end = clean_db.end();
-        if ((min_inode != 0 || max_inode != 0) && min_inode <= max_inode)
+        if (op->min_oid.inode != 0 || op->min_oid.stripe != 0)
         {
-            clean_it = clean_db.lower_bound({
-                .inode = min_inode,
-                .stripe = 0,
-            });
-            clean_end = clean_db.upper_bound({
-                .inode = max_inode,
-                .stripe = UINT64_MAX,
-            });
+            clean_it = clean_db.lower_bound(op->min_oid);
+        }
+        if ((max_oid.inode != 0 || max_oid.stripe != 0) && !(max_oid < op->min_oid))
+        {
+            clean_end = clean_db.upper_bound(max_oid);
         }
         for (; clean_it != clean_end; clean_it++)
         {
@@ -558,11 +565,29 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
                 .oid = clean_it->first,
                 .version = clean_it->second.version,
             };
+            if (op->list_stable_limit > 0 && stable_count >= op->list_stable_limit)
+            {
+                if (!limited)
+                {
+                    limited = true;
+                    max_oid = stable[stable_count-1].oid;
+                }
+                break;
+            }
         }
+        if (op->list_stable_limit > 0)
+        {
+            // To maintain the order, we have to include objects in the same range from other shards
+            if (last_shard_id != 0 && last_shard_id != shard_it->first)
+                std::sort(stable, stable+stable_count);
+            if (stable_count > op->list_stable_limit)
+                stable_count = op->list_stable_limit;
+        }
+        last_shard_id = shard_it->first;
     }
-    if (first_shard != last_shard)
+    if (op->list_stable_limit == 0 && first_shard != last_shard)
     {
-        // If that's not a per-PG listing, sort clean entries
+        // If that's not a per-PG listing, sort clean entries (already sorted if list_stable_limit != 0)
         std::sort(stable, stable+stable_count);
     }
     int clean_stable_count = stable_count;
@@ -571,20 +596,17 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
     obj_ver_id *unstable = NULL;
     {
         auto dirty_it = dirty_db.begin(), dirty_end = dirty_db.end();
-        if ((min_inode != 0 || max_inode != 0) && min_inode <= max_inode)
+        if (op->min_oid.inode != 0 || op->min_oid.stripe != 0)
         {
             dirty_it = dirty_db.lower_bound({
-                .oid = {
-                    .inode = min_inode,
-                    .stripe = 0,
-                },
+                .oid = op->min_oid,
                 .version = 0,
             });
+        }
+        if ((max_oid.inode != 0 || max_oid.stripe != 0) && !(max_oid < op->min_oid))
+        {
             dirty_end = dirty_db.upper_bound({
-                .oid = {
-                    .inode = max_inode,
-                    .stripe = UINT64_MAX,
-                },
+                .oid = max_oid,
                 .version = UINT64_MAX,
             });
         }
@@ -628,6 +650,11 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
                             stable[stable_count++] = dirty_it->first;
                         }
                     }
+                    if (op->list_stable_limit > 0 && stable_count >= op->list_stable_limit)
+                    {
+                        // Stop here
+                        break;
+                    }
                 }
                 else
                 {

src/blockstore_impl.h

@@ -93,11 +93,10 @@
 
 // "VITAstor"
 #define BLOCKSTORE_META_MAGIC_V1 0x726F747341544956l
-#define BLOCKSTORE_META_VERSION_V1 1
+#define BLOCKSTORE_META_FORMAT_V1 1
+#define BLOCKSTORE_META_FORMAT_V2 2
 
 // metadata header (superblock)
-// FIXME: After adding the OSD superblock, add a key to metadata
-// and journal headers to check if they belong to the same OSD
 struct __attribute__((__packed__)) blockstore_meta_header_v1_t
 {
     uint64_t zero;
@@ -108,14 +107,29 @@ struct __attribute__((__packed__)) blockstore_meta_header_v1_t
     uint32_t bitmap_granularity;
 };
 
+struct __attribute__((__packed__)) blockstore_meta_header_v2_t
+{
+    uint64_t zero;
+    uint64_t magic;
+    uint64_t version;
+    uint32_t meta_block_size;
+    uint32_t data_block_size;
+    uint32_t bitmap_granularity;
+    uint32_t data_csum_type;
+    uint32_t csum_block_size;
+    uint32_t header_csum;
+};
+
 // 32 bytes = 24 bytes + block bitmap (4 bytes by default) + external attributes (also bitmap, 4 bytes by default)
 // per "clean" entry on disk with fixed metadata tables
-// FIXME: maybe add crc32's to metadata
 struct __attribute__((__packed__)) clean_disk_entry
 {
     object_id oid;
     uint64_t version;
     uint8_t bitmap[];
+    // Two more fields come after bitmap in metadata version 2:
+    // uint32_t data_csum[];
+    // uint32_t entry_csum;
 };
 
 // 32 = 16 + 16 bytes per "clean" entry in memory (object_id => clean_entry)
@@ -125,7 +139,7 @@ struct __attribute__((__packed__)) clean_entry
     uint64_t location;
 };
 
-// 64 = 24 + 40 bytes per dirty entry in memory (obj_ver_id => dirty_entry)
+// 64 = 24 + 40 bytes per dirty entry in memory (obj_ver_id => dirty_entry). Plus checksums
 struct __attribute__((__packed__)) dirty_entry
 {
     uint32_t state;
@@ -134,7 +148,7 @@ struct __attribute__((__packed__)) dirty_entry
     uint32_t offset;   // data offset within object (stripe)
     uint32_t len;      // data length
     uint64_t journal_sector; // journal sector used for this entry
-    void* bitmap;   // either external bitmap itself when it fits, or a pointer to it when it doesn't
+    void* dyn_data;    // dynamic data: external bitmap and data block checksums. may be a pointer to the in-memory journal
 };
 
 // - Sync must be submitted after previous writes/deletes (not before!)
@@ -163,12 +177,23 @@ struct __attribute__((__packed__)) dirty_entry
 // Suspend operation until there is some free space on the data device
 #define WAIT_FREE 5
 
-struct fulfill_read_t
+struct used_clean_obj_t
 {
-    uint64_t offset, len;
-    uint64_t journal_sector; // sector+1 if used and !journal.inmemory, otherwise 0
+    int refs;
+    bool was_freed; // was freed by a parallel flush?
+    bool was_changed; // was changed by a parallel flush?
 };
 
+// https://github.com/algorithm-ninja/cpp-btree
+// https://github.com/greg7mdp/sparsepp/ was used previously, but it was TERRIBLY slow after resizing
+// with sparsepp, random reads dropped to ~700 iops very fast with just as much as ~32k objects in the DB
+typedef btree::btree_map<object_id, clean_entry> blockstore_clean_db_t;
+typedef std::map<obj_ver_id, dirty_entry> blockstore_dirty_db_t;
+
+#include "blockstore_init.h"
+
+#include "blockstore_flush.h"
+
 #define PRIV(op) ((blockstore_op_private_t*)(op)->private_data)
 #define FINISH_OP(op) PRIV(op)->~blockstore_op_private_t(); std::function<void (blockstore_op_t*)>(op->callback)(op)
 
@@ -181,7 +206,8 @@ struct blockstore_op_private_t
     int op_state;
 
     // Read
-    std::vector<fulfill_read_t> read_vec;
+    uint64_t clean_block_used;
+    std::vector<copy_buffer_t> read_vec;
 
     // Sync, write
     int min_flushed_journal_sector, max_flushed_journal_sector;
@@ -197,16 +223,6 @@ struct blockstore_op_private_t
     int sync_small_checked, sync_big_checked;
 };
 
-// https://github.com/algorithm-ninja/cpp-btree
-// https://github.com/greg7mdp/sparsepp/ was used previously, but it was TERRIBLY slow after resizing
-// with sparsepp, random reads dropped to ~700 iops very fast with just as much as ~32k objects in the DB
-typedef btree::btree_map<object_id, clean_entry> blockstore_clean_db_t;
-typedef std::map<obj_ver_id, dirty_entry> blockstore_dirty_db_t;
-
-#include "blockstore_init.h"
-
-#include "blockstore_flush.h"
-
 typedef uint32_t pool_id_t;
 typedef uint64_t pool_pg_id_t;
 
@@ -253,7 +269,7 @@ class blockstore_impl_t
 
     std::map<pool_id_t, pool_shard_settings_t> clean_db_settings;
     std::map<pool_pg_id_t, blockstore_clean_db_t> clean_db_shards;
-    uint8_t *clean_bitmap = NULL;
+    uint8_t *clean_bitmaps = NULL;
     blockstore_dirty_db_t dirty_db;
     std::vector<blockstore_op_t*> submit_queue;
     std::vector<obj_ver_id> unsynced_big_writes, unsynced_small_writes;
@@ -267,6 +283,10 @@ class blockstore_impl_t
     journal_flusher_t *flusher;
     int big_to_flush = 0;
     int write_iodepth = 0;
+    bool alloc_dyn_data = false;
+
+    // clean data blocks referenced by read operations
+    std::map<uint64_t, used_clean_obj_t> used_clean_objects;
 
     bool live = false, queue_stall = false;
     ring_loop_t *ringloop;
@@ -310,8 +330,30 @@ class blockstore_impl_t
 
     // Read
     int dequeue_read(blockstore_op_t *read_op);
-    int fulfill_read(blockstore_op_t *read_op, uint64_t &fulfilled, uint32_t item_start, uint32_t item_end,
-        uint32_t item_state, uint64_t item_version, uint64_t item_location, uint64_t journal_sector);
+    void find_holes(std::vector<copy_buffer_t> & read_vec, uint32_t item_start, uint32_t item_end,
+        std::function<int(int, bool, uint32_t, uint32_t)> callback);
+    int fulfill_read(blockstore_op_t *read_op,
+        uint64_t &fulfilled, uint32_t item_start, uint32_t item_end,
+        uint32_t item_state, uint64_t item_version, uint64_t item_location,
+        uint64_t journal_sector, uint8_t *csum, int *dyn_data);
+    bool fulfill_clean_read(blockstore_op_t *read_op, uint64_t & fulfilled,
+        uint8_t *clean_entry_bitmap, int *dyn_data,
+        uint32_t item_start, uint32_t item_end, uint64_t clean_loc, uint64_t clean_ver);
+    int fill_partial_checksum_blocks(std::vector<copy_buffer_t> & rv, uint64_t & fulfilled,
+        uint8_t *clean_entry_bitmap, int *dyn_data, bool from_journal, uint8_t *read_buf, uint64_t read_offset, uint64_t read_end);
+    int pad_journal_read(std::vector<copy_buffer_t> & rv, copy_buffer_t & cp,
+        uint64_t dirty_offset, uint64_t dirty_end, uint64_t dirty_loc, uint8_t *csum_ptr, int *dyn_data,
+        uint64_t offset, uint64_t submit_len, uint64_t & blk_begin, uint64_t & blk_end, uint8_t* & blk_buf);
+    bool read_range_fulfilled(std::vector<copy_buffer_t> & rv, uint64_t & fulfilled, uint8_t *read_buf,
+        uint8_t *clean_entry_bitmap, uint32_t item_start, uint32_t item_end);
+    bool read_checksum_block(blockstore_op_t *op, int rv_pos, uint64_t &fulfilled, uint64_t clean_loc);
+    uint8_t* read_clean_meta_block(blockstore_op_t *read_op, uint64_t clean_loc, int rv_pos);
+    bool verify_padded_checksums(uint8_t *clean_entry_bitmap, uint8_t *csum_buf, uint32_t offset,
+        iovec *iov, int n_iov, std::function<void(uint32_t, uint32_t, uint32_t)> bad_block_cb);
+    bool verify_journal_checksums(uint8_t *csums, uint32_t offset,
+        iovec *iov, int n_iov, std::function<void(uint32_t, uint32_t, uint32_t)> bad_block_cb);
+    bool verify_clean_padded_checksums(blockstore_op_t *op, uint64_t clean_loc, uint8_t *dyn_data, bool from_journal,
+        iovec *iov, int n_iov, std::function<void(uint32_t, uint32_t, uint32_t)> bad_block_cb);
     int fulfill_read_push(blockstore_op_t *op, void *buf, uint64_t offset, uint64_t len,
         uint32_t item_state, uint64_t item_version);
     void handle_read_event(ring_data_t *data, blockstore_op_t *op);
@@ -342,6 +384,7 @@ class blockstore_impl_t
     int continue_rollback(blockstore_op_t *op);
     void mark_rolled_back(const obj_ver_id & ov);
     void erase_dirty(blockstore_dirty_db_t::iterator dirty_start, blockstore_dirty_db_t::iterator dirty_end, uint64_t clean_loc);
+    void free_dirty_dyn_data(dirty_entry & e);
 
     // List
     void process_list(blockstore_op_t *op);

src/blockstore_init.cpp

@@ -65,7 +65,7 @@ int blockstore_init_meta::loop()
     GET_SQE();
     data->iov = { metadata_buffer, bs->dsk.meta_block_size };
     data->callback = [this](ring_data_t *data) { handle_event(data, -1); };
-    my_uring_prep_readv(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset);
+    my_uring_prep_readv(sqe, bs->dsk.read_meta_fd, &data->iov, 1, bs->dsk.meta_offset);
     bs->ringloop->submit();
     submitted++;
 resume_1:
@@ -77,13 +77,20 @@ resume_1:
     if (iszero((uint64_t*)metadata_buffer, bs->dsk.meta_block_size / sizeof(uint64_t)))
     {
         {
-            blockstore_meta_header_v1_t *hdr = (blockstore_meta_header_v1_t *)metadata_buffer;
+            blockstore_meta_header_v2_t *hdr = (blockstore_meta_header_v2_t *)metadata_buffer;
             hdr->zero = 0;
             hdr->magic = BLOCKSTORE_META_MAGIC_V1;
-            hdr->version = BLOCKSTORE_META_VERSION_V1;
+            hdr->version = bs->dsk.meta_format;
             hdr->meta_block_size = bs->dsk.meta_block_size;
             hdr->data_block_size = bs->dsk.data_block_size;
             hdr->bitmap_granularity = bs->dsk.bitmap_granularity;
+            if (bs->dsk.meta_format >= BLOCKSTORE_META_FORMAT_V2)
+            {
+                hdr->data_csum_type = bs->dsk.data_csum_type;
+                hdr->csum_block_size = bs->dsk.csum_block_size;
+                hdr->header_csum = 0;
+                hdr->header_csum = crc32c(0, hdr, sizeof(*hdr));
+            }
         }
         if (bs->readonly)
         {
@@ -109,28 +116,62 @@ resume_1:
     }
     else
     {
-        blockstore_meta_header_v1_t *hdr = (blockstore_meta_header_v1_t *)metadata_buffer;
-        if (hdr->zero != 0 ||
-            hdr->magic != BLOCKSTORE_META_MAGIC_V1 ||
-            hdr->version != BLOCKSTORE_META_VERSION_V1)
+        blockstore_meta_header_v2_t *hdr = (blockstore_meta_header_v2_t *)metadata_buffer;
+        if (hdr->zero != 0 || hdr->magic != BLOCKSTORE_META_MAGIC_V1 || hdr->version < BLOCKSTORE_META_FORMAT_V1)
         {
             printf(
-                "Metadata is corrupt or old version.\n"
-                " If this is a new OSD please zero out the metadata area before starting it.\n"
-                " If you need to upgrade from 0.5.x please request it via the issue tracker.\n"
+                "Metadata is corrupt or too old (pre-0.6.x).\n"
+                " If this is a new OSD, please zero out the metadata area before starting it.\n"
+                " If you need to upgrade from 0.5.x, convert metadata with vitastor-disk.\n"
+            );
+            exit(1);
+        }
+        if (hdr->version == BLOCKSTORE_META_FORMAT_V2)
+        {
+            uint32_t csum = hdr->header_csum;
+            hdr->header_csum = 0;
+            if (crc32c(0, hdr, sizeof(*hdr)) != csum)
+            {
+                printf("Metadata header is corrupt (checksum mismatch).\n");
+                exit(1);
+            }
+            hdr->header_csum = csum;
+            bs->dsk.meta_format = BLOCKSTORE_META_FORMAT_V2;
+        }
+        else if (hdr->version == BLOCKSTORE_META_FORMAT_V1)
+        {
+            hdr->data_csum_type = 0;
+            hdr->csum_block_size = 0;
+            hdr->header_csum = 0;
+            // Enable compatibility mode - entries without checksums
+            bs->dsk.clean_entry_size = sizeof(clean_disk_entry) + bs->dsk.clean_entry_bitmap_size*2;
+            bs->dsk.meta_len = (1 + (bs->dsk.block_count - 1 + bs->dsk.meta_block_size / bs->dsk.clean_entry_size)
+                / (bs->dsk.meta_block_size / bs->dsk.clean_entry_size)) * bs->dsk.meta_block_size;
+            bs->dsk.meta_format = BLOCKSTORE_META_FORMAT_V1;
+            printf("Warning: Starting with metadata in the old format without checksums, as stored on disk\n");
+        }
+        else if (hdr->version > BLOCKSTORE_META_FORMAT_V2)
+        {
+            printf(
+                "Metadata format is too new for me (stored version is %lu, max supported %u).\n",
+                hdr->version, BLOCKSTORE_META_FORMAT_V2
             );
             exit(1);
         }
         if (hdr->meta_block_size != bs->dsk.meta_block_size ||
             hdr->data_block_size != bs->dsk.data_block_size ||
-            hdr->bitmap_granularity != bs->dsk.bitmap_granularity)
+            hdr->bitmap_granularity != bs->dsk.bitmap_granularity ||
+            hdr->data_csum_type != bs->dsk.data_csum_type ||
+            hdr->csum_block_size != bs->dsk.csum_block_size)
         {
             printf(
                 "Configuration stored in metadata superblock"
-                " (meta_block_size=%u, data_block_size=%u, bitmap_granularity=%u)"
-                " differs from OSD configuration (%lu/%u/%lu).\n",
+                " (meta_block_size=%u, data_block_size=%u, bitmap_granularity=%u, data_csum_type=%u, csum_block_size=%u)"
+                " differs from OSD configuration (%lu/%u/%lu, %u/%u).\n",
                 hdr->meta_block_size, hdr->data_block_size, hdr->bitmap_granularity,
-                bs->dsk.meta_block_size, bs->dsk.data_block_size, bs->dsk.bitmap_granularity
+                hdr->data_csum_type, hdr->csum_block_size,
+                bs->dsk.meta_block_size, bs->dsk.data_block_size, bs->dsk.bitmap_granularity,
+                bs->dsk.data_csum_type, bs->dsk.csum_block_size
             );
             exit(1);
         }
@@ -161,7 +202,7 @@ resume_2:
                 data->iov = { bufs[i].buf, bufs[i].size };
                 data->callback = [this, i](ring_data_t *data) { handle_event(data, i); };
                 if (!zero_on_init)
-                    my_uring_prep_readv(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + bufs[i].offset);
+                    my_uring_prep_readv(sqe, bs->dsk.read_meta_fd, &data->iov, 1, bs->dsk.meta_offset + bufs[i].offset);
                 else
                 {
                     // Fill metadata with zeroes
@@ -218,7 +259,7 @@ resume_2:
             GET_SQE();
             data->iov = { metadata_buffer, bs->dsk.meta_block_size };
             data->callback = [this](ring_data_t *data) { handle_event(data, -1); };
-            my_uring_prep_readv(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + (1+next_offset)*bs->dsk.meta_block_size);
+            my_uring_prep_readv(sqe, bs->dsk.read_meta_fd, &data->iov, 1, bs->dsk.meta_offset + (1+next_offset)*bs->dsk.meta_block_size);
             submitted++;
 resume_5:
             if (submitted > 0)
@@ -279,12 +320,22 @@ bool blockstore_init_meta::handle_meta_block(uint8_t *buf, uint64_t entries_per_
     for (uint64_t i = 0; i < max_i; i++)
     {
         clean_disk_entry *entry = (clean_disk_entry*)(buf + i*bs->dsk.clean_entry_size);
-        if (!bs->inmemory_meta && bs->dsk.clean_entry_bitmap_size)
-        {
-            memcpy(bs->clean_bitmap + (done_cnt+i)*2*bs->dsk.clean_entry_bitmap_size, &entry->bitmap, 2*bs->dsk.clean_entry_bitmap_size);
-        }
         if (entry->oid.inode > 0)
         {
+            if (bs->dsk.meta_format >= BLOCKSTORE_META_FORMAT_V2)
+            {
+                // Check entry crc32
+                uint32_t *entry_csum = (uint32_t*)((uint8_t*)entry + bs->dsk.clean_entry_size - 4);
+                if (*entry_csum != crc32c(0, entry, bs->dsk.clean_entry_size - 4))
+                {
+                    printf("Metadata entry %lu is corrupt (checksum mismatch), skipping\n", done_cnt+i);
+                    continue;
+                }
+            }
+            if (!bs->inmemory_meta && bs->dsk.clean_entry_bitmap_size)
+            {
+                memcpy(bs->clean_bitmaps + (done_cnt+i) * 2 * bs->dsk.clean_entry_bitmap_size, &entry->bitmap, 2 * bs->dsk.clean_entry_bitmap_size);
+            }
             auto & clean_db = bs->clean_db_shard(entry->oid);
             auto clean_it = clean_db.find(entry->oid);
             if (clean_it == clean_db.end() || clean_it->second.version < entry->version)
@@ -416,7 +467,7 @@ int blockstore_init_journal::loop()
     data = ((ring_data_t*)sqe->user_data);
     data->iov = { submitted_buf, bs->journal.block_size };
     data->callback = simple_callback;
-    my_uring_prep_readv(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset);
+    my_uring_prep_readv(sqe, bs->dsk.read_journal_fd, &data->iov, 1, bs->journal.offset);
     bs->ringloop->submit();
     wait_count = 1;
 resume_1:
@@ -440,7 +491,9 @@ resume_1:
             .size = sizeof(journal_entry_start),
             .reserved = 0,
             .journal_start = bs->journal.block_size,
-            .version = JOURNAL_VERSION,
+            .version = JOURNAL_VERSION_V2,
+            .data_csum_type = bs->dsk.data_csum_type,
+            .csum_block_size = bs->dsk.csum_block_size,
         };
         ((journal_entry_start*)submitted_buf)->crc32 = je_crc32((journal_entry*)submitted_buf);
         if (bs->readonly)
@@ -492,18 +545,36 @@ resume_1:
         if (je_start->magic != JOURNAL_MAGIC ||
             je_start->type != JE_START ||
             je_crc32((journal_entry*)je_start) != je_start->crc32 ||
-            je_start->size != sizeof(journal_entry_start) && je_start->size != JE_START_LEGACY_SIZE)
+            je_start->size != JE_START_V0_SIZE && je_start->size != JE_START_V1_SIZE && je_start->size != JE_START_V2_SIZE)
         {
             // Entry is corrupt
-            fprintf(stderr, "First entry of the journal is corrupt\n");
+            fprintf(stderr, "First entry of the journal is corrupt or unsupported\n");
             exit(1);
         }
-        if (je_start->size == JE_START_LEGACY_SIZE || je_start->version != JOURNAL_VERSION)
+        if (je_start->size == JE_START_V0_SIZE ||
+            (je_start->version != JOURNAL_VERSION_V1 || je_start->size != JE_START_V1_SIZE) &&
+            (je_start->version != JOURNAL_VERSION_V2 || je_start->size != JE_START_V2_SIZE))
         {
             fprintf(
-                stderr, "The code only supports journal version %d, but it is %lu on disk."
-                    " Please use the previous version to flush the journal before upgrading OSD\n",
-                JOURNAL_VERSION, je_start->size == JE_START_LEGACY_SIZE ? 0 : je_start->version
+                stderr, "The code only supports journal versions 2 and 1, but it is %lu on disk."
+                    " Please use vitastor-disk to rewrite the journal\n",
+                je_start->size == JE_START_V0_SIZE ? 0 : je_start->version
+            );
+            exit(1);
+        }
+        if (je_start->version == JOURNAL_VERSION_V1)
+        {
+            je_start->data_csum_type = 0;
+            je_start->csum_block_size = 0;
+        }
+        if (je_start->data_csum_type != bs->dsk.data_csum_type ||
+            je_start->csum_block_size != bs->dsk.csum_block_size)
+        {
+            printf(
+                "Configuration stored in journal superblock (data_csum_type=%u, csum_block_size=%u)"
+                " differs from OSD configuration (%u/%u).\n",
+                je_start->data_csum_type, je_start->csum_block_size,
+                bs->dsk.data_csum_type, bs->dsk.csum_block_size
             );
             exit(1);
         }
@@ -536,7 +607,7 @@ resume_1:
                     end - journal_pos < JOURNAL_BUFFER_SIZE ? end - journal_pos : JOURNAL_BUFFER_SIZE,
                 };
                 data->callback = [this](ring_data_t *data1) { handle_event(data1); };
-                my_uring_prep_readv(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset + journal_pos);
+                my_uring_prep_readv(sqe, bs->dsk.read_journal_fd, &data->iov, 1, bs->journal.offset + journal_pos);
                 bs->ringloop->submit();
             }
             while (done.size() > 0)
@@ -705,11 +776,14 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                     snprintf(err, 1024, "BUG: calculated journal data offset (%08lx) != stored journal data offset (%08lx)", location, je->small_write.data_offset);
                     throw std::runtime_error(err);
                 }
-                uint32_t data_crc32 = 0;
+                small_write_data.clear();
                 if (location >= done_pos && location+je->small_write.len <= done_pos+len)
                 {
                     // data is within this buffer
-                    data_crc32 = crc32c(0, (uint8_t*)buf + location - done_pos, je->small_write.len);
+                    small_write_data.push_back((iovec){
+                        .iov_base = (uint8_t*)buf + location - done_pos,
+                        .iov_len = je->small_write.len,
+                    });
                 }
                 else
                 {
@@ -724,7 +798,10 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                                 ? location+je->small_write.len : done[i].pos+done[i].len);
                             uint64_t part_begin = (location < done[i].pos ? done[i].pos : location);
                             covered += part_end - part_begin;
-                            data_crc32 = crc32c(data_crc32, (uint8_t*)done[i].buf + part_begin - done[i].pos, part_end - part_begin);
+                            small_write_data.push_back((iovec){
+                                .iov_base = (uint8_t*)done[i].buf + part_begin - done[i].pos,
+                                .iov_len = part_end - part_begin,
+                            });
                         }
                     }
                     if (covered < je->small_write.len)
@@ -734,12 +811,102 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                         return 2;
                     }
                 }
-                if (data_crc32 != je->small_write.crc32_data)
+                bool data_csum_valid = true;
+                if (!bs->dsk.csum_block_size)
+                {
+                    uint32_t data_crc32 = 0;
+                    for (auto & sd: small_write_data)
+                    {
+                        data_crc32 = crc32c(data_crc32, sd.iov_base, sd.iov_len);
+                    }
+                    data_csum_valid = data_crc32 == je->small_write.crc32_data;
+                    if (!data_csum_valid)
+                    {
+                        printf(
+                            "Journal entry data is corrupt for small_write%s oid=%lx:%lx ver=%lu offset=%u len=%u - data crc32 %x != %x\n",
+                            je->type == JE_SMALL_WRITE_INSTANT ? "_instant" : "",
+                            je->small_write.oid.inode, je->small_write.oid.stripe, je->small_write.version,
+                            je->small_write.offset, je->small_write.len,
+                            data_crc32, je->small_write.crc32_data
+                        );
+                    }
+                }
+                else if (je->small_write.len > 0)
+                {
+                    // FIXME: deduplicate with disk_tool_journal.cpp
+                    // like in enqueue_write()
+                    uint32_t start = je->small_write.offset / bs->dsk.csum_block_size;
+                    uint32_t end = (je->small_write.offset+je->small_write.len-1) / bs->dsk.csum_block_size;
+                    uint32_t data_csum_size = (end-start+1) * (bs->dsk.data_csum_type & 0xFF);
+                    uint32_t required_size = sizeof(journal_entry_small_write) + bs->dsk.clean_entry_bitmap_size + data_csum_size;
+                    if (je->size != required_size)
+                    {
+                        printf(
+                            "Journal entry data has invalid size for small_write%s oid=%lx:%lx ver=%lu offset=%u len=%u - should be %u bytes but is %u bytes\n",
+                            je->type == JE_SMALL_WRITE_INSTANT ? "_instant" : "",
+                            je->small_write.oid.inode, je->small_write.oid.stripe, je->small_write.version,
+                            je->small_write.offset, je->small_write.len,
+                            required_size, je->size
+                        );
+                        data_csum_valid = false;
+                    }
+                    else
+                    {
+                        int sd_num = 0;
+                        size_t sd_pos = 0;
+                        uint32_t *block_csums = (uint32_t*)((uint8_t*)je + sizeof(journal_entry_small_write) + bs->dsk.clean_entry_bitmap_size);
+                        for (uint32_t pos = start; pos <= end; pos++, block_csums++)
+                        {
+                            size_t block_left = (pos == start
+                                ? (start == end
+                                    ? je->small_write.len
+                                    : bs->dsk.csum_block_size - je->small_write.offset%bs->dsk.csum_block_size)
+                                : (pos < end
+                                    ? bs->dsk.csum_block_size
+                                    : (je->small_write.offset + je->small_write.len)%bs->dsk.csum_block_size));
+                            if (pos > start && pos == end && block_left == 0)
+                            {
+                                // full last block
+                                block_left = bs->dsk.csum_block_size;
+                            }
+                            uint32_t block_crc32 = 0;
+                            while (block_left > 0)
+                            {
+                                assert(sd_num < small_write_data.size());
+                                if (small_write_data[sd_num].iov_len >= sd_pos+block_left)
+                                {
+                                    block_crc32 = crc32c(block_crc32, (uint8_t*)small_write_data[sd_num].iov_base+sd_pos, block_left);
+                                    sd_pos += block_left;
+                                    break;
+                                }
+                                else
+                                {
+                                    block_crc32 = crc32c(block_crc32, (uint8_t*)small_write_data[sd_num].iov_base+sd_pos, small_write_data[sd_num].iov_len-sd_pos);
+                                    block_left -= (small_write_data[sd_num].iov_len-sd_pos);
+                                    sd_pos = 0;
+                                    sd_num++;
+                                }
+                            }
+                            if (block_crc32 != *block_csums)
+                            {
+                                printf(
+                                    "Journal entry data is corrupt for small_write%s oid=%lx:%lx ver=%lu offset=%u len=%u - block %u crc32 %x != %x\n",
+                                    je->type == JE_SMALL_WRITE_INSTANT ? "_instant" : "",
+                                    je->small_write.oid.inode, je->small_write.oid.stripe, je->small_write.version,
+                                    je->small_write.offset, je->small_write.len,
+                                    pos, block_crc32, *block_csums
+                                );
+                                data_csum_valid = false;
+                                break;
+                            }
+                        }
+                    }
+                }
+                if (!data_csum_valid)
                 {
                     // journal entry is corrupt, stop here
                     // interesting thing is that we must clear the corrupt entry if we're not readonly,
                     // because we don't write next entries in the same journal block
-                    printf("Journal entry data is corrupt (data crc32 %x != %x)\n", data_crc32, je->small_write.crc32_data);
                     memset((uint8_t*)buf + proc_pos - done_pos + pos, 0, bs->journal.block_size - pos);
                     bs->journal.next_free = prev_free;
                     init_write_buf = (uint8_t*)buf + proc_pos - done_pos;
@@ -755,11 +922,14 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                         .oid = je->small_write.oid,
                         .version = je->small_write.version,
                     };
-                    void *bmp = NULL;
-                    void *bmp_from = (uint8_t*)je + sizeof(journal_entry_small_write);
-                    if (bs->dsk.clean_entry_bitmap_size <= sizeof(void*))
+                    uint64_t dyn_size = bs->dsk.dirty_dyn_size(je->small_write.offset, je->small_write.len);
+                    void *dyn = NULL;
+                    void *dyn_from = (uint8_t*)je + sizeof(journal_entry_small_write);
+                    if (!bs->alloc_dyn_data)
                     {
-                        memcpy(&bmp, bmp_from, bs->dsk.clean_entry_bitmap_size);
+                        // Bitmap without checksum is only 4 bytes for 128k objects, save it inline
+                        // It can even contain 4 byte bitmap + 4 byte CRC32 for 4 kb writes :)
+                        memcpy(&dyn, dyn_from, dyn_size);
                     }
                     else
                     {
@@ -767,8 +937,9 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                         // allocations for entry bitmaps. This can only be fixed by using
                         // a patched map with dynamic entry size, but not the btree_map,
                         // because it doesn't keep iterators valid all the time.
-                        bmp = malloc_or_die(bs->dsk.clean_entry_bitmap_size);
-                        memcpy(bmp, bmp_from, bs->dsk.clean_entry_bitmap_size);
+                        dyn = malloc_or_die(dyn_size+sizeof(int));
+                        *((int*)dyn) = 1;
+                        memcpy((uint8_t*)dyn+sizeof(int), dyn_from, dyn_size);
                     }
                     bs->dirty_db.emplace(ov, (dirty_entry){
                         .state = (BS_ST_SMALL_WRITE | BS_ST_SYNCED),
@@ -777,7 +948,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                         .offset = je->small_write.offset,
                         .len = je->small_write.len,
                         .journal_sector = proc_pos,
-                        .bitmap = bmp,
+                        .dyn_data = dyn,
                     });
                     bs->journal.used_sectors[proc_pos]++;
 #ifdef BLOCKSTORE_DEBUG
@@ -836,11 +1007,13 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                         .oid = je->big_write.oid,
                         .version = je->big_write.version,
                     };
-                    void *bmp = NULL;
-                    void *bmp_from = (uint8_t*)je + sizeof(journal_entry_big_write);
-                    if (bs->dsk.clean_entry_bitmap_size <= sizeof(void*))
+                    uint64_t dyn_size = bs->dsk.dirty_dyn_size(je->big_write.offset, je->big_write.len);
+                    void *dyn = NULL;
+                    void *dyn_from = (uint8_t*)je + sizeof(journal_entry_big_write);
+                    if (!bs->alloc_dyn_data)
                     {
-                        memcpy(&bmp, bmp_from, bs->dsk.clean_entry_bitmap_size);
+                        // Bitmap without checksum is only 4 bytes for 128k objects, save it inline
+                        memcpy(&dyn, dyn_from, dyn_size);
                     }
                     else
                     {
@@ -848,8 +1021,9 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                         // allocations for entry bitmaps. This can only be fixed by using
                         // a patched map with dynamic entry size, but not the btree_map,
                         // because it doesn't keep iterators valid all the time.
-                        bmp = malloc_or_die(bs->dsk.clean_entry_bitmap_size);
-                        memcpy(bmp, bmp_from, bs->dsk.clean_entry_bitmap_size);
+                        dyn = malloc_or_die(dyn_size+sizeof(int));
+                        *((int*)dyn) = 1;
+                        memcpy((uint8_t*)dyn+sizeof(int), dyn_from, dyn_size);
                     }
                     auto dirty_it = bs->dirty_db.emplace(ov, (dirty_entry){
                         .state = (BS_ST_BIG_WRITE | BS_ST_SYNCED),
@@ -858,7 +1032,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                         .offset = je->big_write.offset,
                         .len = je->big_write.len,
                         .journal_sector = proc_pos,
-                        .bitmap = bmp,
+                        .dyn_data = dyn,
                     }).first;
                     if (bs->data_alloc->get(je->big_write.location >> bs->dsk.block_order))
                     {

src/blockstore_init.h

@@ -50,6 +50,7 @@ class blockstore_init_journal
     uint64_t next_free;
     std::vector<bs_init_journal_done> done;
     std::vector<obj_ver_id> double_allocs;
+    std::vector<iovec> small_write_data;
     uint64_t journal_pos = 0;
     uint64_t continue_pos = 0;
     void *init_write_buf = NULL;

src/blockstore_journal.cpp

@@ -17,6 +17,7 @@ blockstore_journal_check_t::blockstore_journal_check_t(blockstore_impl_t *bs)
 // Check if we can write <required> entries of <size> bytes and <data_after> data bytes after them to the journal
 int blockstore_journal_check_t::check_available(blockstore_op_t *op, int entries_required, int size, int data_after)
 {
+    uint64_t prev_next = next_sector;
     int required = entries_required;
     while (1)
     {
@@ -35,11 +36,19 @@ int blockstore_journal_check_t::check_available(blockstore_op_t *op, int entries
             }
             required -= fits;
             next_in_pos += fits * size;
-            sectors_to_write++;
+            if (next_sector != prev_next || !sectors_to_write)
+            {
+                // Except the previous call to this function
+                sectors_to_write++;
+            }
         }
         else if (bs->journal.sector_info[next_sector].dirty)
         {
-            sectors_to_write++;
+            if (next_sector != prev_next || !sectors_to_write)
+            {
+                // Except the previous call to this function
+                sectors_to_write++;
+            }
         }
         if (required <= 0)
         {
@@ -236,14 +245,6 @@ journal_t::~journal_t()
 uint64_t journal_t::get_trim_pos()
 {
     auto journal_used_it = used_sectors.lower_bound(used_start);
-#ifdef BLOCKSTORE_DEBUG
-    printf(
-        "Trimming journal (used_start=%08lx, next_free=%08lx, dirty_start=%08lx, new_start=%08lx, new_refcount=%ld)\n",
-        used_start, next_free, dirty_start,
-        journal_used_it == used_sectors.end() ? 0 : journal_used_it->first,
-        journal_used_it == used_sectors.end() ? 0 : journal_used_it->second
-    );
-#endif
     if (journal_used_it == used_sectors.end())
     {
         // Journal is cleared to its end, restart from the beginning
@@ -256,12 +257,26 @@ uint64_t journal_t::get_trim_pos()
         else
         {
             // next_free does not need updating during trim
+#ifdef BLOCKSTORE_DEBUG
+            printf(
+                "Trimming journal (used_start=%08lx, next_free=%08lx, dirty_start=%08lx, new_start=%08lx, new_refcount=%ld)\n",
+                used_start, next_free, dirty_start,
+                journal_used_it->first, journal_used_it->second
+            );
+#endif
             return journal_used_it->first;
         }
     }
     else if (journal_used_it->first > used_start)
     {
         // Journal is cleared up to <journal_used_it>
+#ifdef BLOCKSTORE_DEBUG
+        printf(
+            "Trimming journal (used_start=%08lx, next_free=%08lx, dirty_start=%08lx, new_start=%08lx, new_refcount=%ld)\n",
+            used_start, next_free, dirty_start,
+            journal_used_it->first, journal_used_it->second
+        );
+#endif
         return journal_used_it->first;
     }
     // Can't trim journal
@@ -283,3 +298,31 @@ void journal_t::dump_diagnostics()
         journal_used_it == used_sectors.end() ? 0 : journal_used_it->second
     );
 }
+
+static uint64_t zero_page[4096];
+
+uint32_t crc32c_pad(uint32_t prev_crc, const void *buf, size_t len, size_t left_pad, size_t right_pad)
+{
+    uint32_t r = prev_crc;
+    while (left_pad >= 4096)
+    {
+        r = crc32c(r, zero_page, 4096);
+        left_pad -= 4096;
+    }
+    if (left_pad > 0)
+        r = crc32c(r, zero_page, left_pad);
+    r = crc32c(r, buf, len);
+    while (right_pad >= 4096)
+    {
+        r = crc32c(r, zero_page, 4096);
+        right_pad -= 4096;
+    }
+    if (left_pad > 0)
+        r = crc32c(r, zero_page, right_pad);
+    return r;
+}
+
+uint32_t crc32c_nopad(uint32_t prev_crc, const void *buf, size_t len, size_t left_pad, size_t right_pad)
+{
+    return crc32c(0, buf, len);
+}

src/blockstore_journal.h

@@ -8,7 +8,8 @@
 
 #define MIN_JOURNAL_SIZE 4*1024*1024
 #define JOURNAL_MAGIC 0x4A33
-#define JOURNAL_VERSION 1
+#define JOURNAL_VERSION_V1 1
+#define JOURNAL_VERSION_V2 2
 #define JOURNAL_BUFFER_SIZE 4*1024*1024
 #define JOURNAL_ENTRY_HEADER_SIZE 16
 
@@ -32,7 +33,7 @@
 #define JE_BIG_WRITE_INSTANT   0x08
 #define JE_MAX         0x08
 
-// crc32c comes first to ease calculation and is equal to crc32()
+// crc32c comes first to ease calculation
 struct __attribute__((__packed__)) journal_entry_start
 {
     uint32_t crc32;
@@ -42,8 +43,12 @@ struct __attribute__((__packed__)) journal_entry_start
     uint32_t reserved;
     uint64_t journal_start;
     uint64_t version;
+    uint32_t data_csum_type;
+    uint32_t csum_block_size;
 };
-#define JE_START_LEGACY_SIZE 24
+#define JE_START_V0_SIZE 24
+#define JE_START_V1_SIZE 32
+#define JE_START_V2_SIZE 40
 
 struct __attribute__((__packed__)) journal_entry_small_write
 {
@@ -59,10 +64,12 @@ struct __attribute__((__packed__)) journal_entry_small_write
     // small_write entries contain <len> bytes of data which is stored in next sectors
     // data_offset is its offset within journal
     uint64_t data_offset;
-    uint32_t crc32_data;
+    uint32_t crc32_data; // zero when data_csum_type != 0
     // small_write and big_write entries are followed by the "external" bitmap
     // its size is dynamic and included in journal entry's <size> field
     uint8_t bitmap[];
+    // and then data checksums if data_csum_type != 0
+    // uint32_t data_crc32c[];
 };
 
 struct __attribute__((__packed__)) journal_entry_big_write
@@ -80,6 +87,8 @@ struct __attribute__((__packed__)) journal_entry_big_write
     // small_write and big_write entries are followed by the "external" bitmap
     // its size is dynamic and included in journal entry's <size> field
     uint8_t bitmap[];
+    // and then data checksums if data_csum_type != 0
+    // uint32_t data_crc32c[];
 };
 
 struct __attribute__((__packed__)) journal_entry_stable
@@ -218,3 +227,6 @@ struct blockstore_journal_check_t
 };
 
 journal_entry* prefill_single_journal_entry(journal_t & journal, uint16_t type, uint32_t size);
+
+uint32_t crc32c_pad(uint32_t prev_crc, const void *buf, size_t len, size_t left_pad, size_t right_pad);
+uint32_t crc32c_nopad(uint32_t prev_crc, const void *buf, size_t len, size_t left_pad, size_t right_pad);

src/blockstore_open.cpp

@@ -133,19 +133,24 @@ void blockstore_impl_t::calc_lengths()
     {
         metadata_buffer = memalign(MEM_ALIGNMENT, dsk.meta_len);
         if (!metadata_buffer)
-            throw std::runtime_error("Failed to allocate memory for the metadata");
+            throw std::runtime_error("Failed to allocate memory for the metadata ("+std::to_string(dsk.meta_len/1024/1024)+" MB)");
     }
-    else if (dsk.clean_entry_bitmap_size)
+    else if (dsk.clean_entry_bitmap_size || dsk.data_csum_type)
     {
-        clean_bitmap = (uint8_t*)malloc(dsk.block_count * 2*dsk.clean_entry_bitmap_size);
-        if (!clean_bitmap)
-            throw std::runtime_error("Failed to allocate memory for the metadata sparse write bitmap");
+        clean_bitmaps = (uint8_t*)malloc(dsk.block_count * 2 * dsk.clean_entry_bitmap_size);
+        if (!clean_bitmaps)
+        {
+            throw std::runtime_error(
+                "Failed to allocate memory for the metadata sparse write bitmap ("+
+                std::to_string(dsk.block_count * 2 * dsk.clean_entry_bitmap_size / 1024 / 1024)+" MB)"
+            );
+        }
     }
     if (journal.inmemory)
     {
         journal.buffer = memalign(MEM_ALIGNMENT, journal.len);
         if (!journal.buffer)
-            throw std::runtime_error("Failed to allocate memory for journal");
+            throw std::runtime_error("Failed to allocate memory for journal ("+std::to_string(journal.len/1024/1024)+" MB)");
     }
     else
     {

src/blockstore_rollback.cpp

@@ -179,7 +179,7 @@ void blockstore_impl_t::erase_dirty(blockstore_dirty_db_t::iterator dirty_start,
     {
         object_id oid = dirty_it->first.oid;
 #ifdef BLOCKSTORE_DEBUG
-        printf("Unblock writes-after-delete %lx:%lx v%lx\n", oid.inode, oid.stripe, dirty_it->first.version);
+        printf("Unblock writes-after-delete %lx:%lx v%lu\n", oid.inode, oid.stripe, dirty_it->first.version);
 #endif
         dirty_it = dirty_end;
         // Unblock operations blocked by delete flushing
@@ -218,7 +218,7 @@ void blockstore_impl_t::erase_dirty(blockstore_dirty_db_t::iterator dirty_start,
         auto used = --journal.used_sectors[dirty_it->second.journal_sector];
 #ifdef BLOCKSTORE_DEBUG
         printf(
-            "remove usage of journal offset %08lx by %lx:%lx v%lu (%d refs)\n", dirty_it->second.journal_sector,
+            "remove usage of journal offset %08lx by %lx:%lx v%lu (%lu refs)\n", dirty_it->second.journal_sector,
             dirty_it->first.oid.inode, dirty_it->first.oid.stripe, dirty_it->first.version, used
         );
 #endif
@@ -227,11 +227,7 @@ void blockstore_impl_t::erase_dirty(blockstore_dirty_db_t::iterator dirty_start,
             journal.used_sectors.erase(dirty_it->second.journal_sector);
             flusher->mark_trim_possible();
         }
-        if (dsk.clean_entry_bitmap_size > sizeof(void*))
-        {
-            free(dirty_it->second.bitmap);
-            dirty_it->second.bitmap = NULL;
-        }
+        free_dirty_dyn_data(dirty_it->second);
         if (dirty_it == dirty_start)
         {
             break;
@@ -240,3 +236,18 @@ void blockstore_impl_t::erase_dirty(blockstore_dirty_db_t::iterator dirty_start,
     }
     dirty_db.erase(dirty_start, dirty_end);
 }
+
+void blockstore_impl_t::free_dirty_dyn_data(dirty_entry & e)
+{
+    if (e.dyn_data)
+    {
+        if (alloc_dyn_data &&
+            --*((int*)e.dyn_data) == 0) // refcount
+        {
+            // dyn_data contains the bitmap and checksums
+            // free it if it doesn't refer to the in-memory journal
+            free(e.dyn_data);
+        }
+        e.dyn_data = NULL;
+    }
+}

src/blockstore_stable.cpp

@@ -103,7 +103,7 @@ blockstore_op_t* blockstore_impl_t::selective_sync(blockstore_op_t *op)
     blockstore_op_t *sync_op = new blockstore_op_t;
     sync_op->opcode = BS_OP_SYNC;
     sync_op->buf = NULL;
-    sync_op->callback = [this](blockstore_op_t *sync_op)
+    sync_op->callback = [](blockstore_op_t *sync_op)
     {
         delete sync_op;
     };
@@ -244,7 +244,7 @@ int blockstore_impl_t::split_stab_op(blockstore_op_t *op, std::function<int(obj_
         // Make a wrapped callback
         int *split_op_counter = (int*)malloc_or_die(sizeof(int));
         *split_op_counter = (sync_op ? 1 : 0) + (split_stab_op ? 1 : 0) + (todo ? 1 : 0);
-        auto cb = [this, op, good_items = good_vers.items,
+        auto cb = [op, good_items = good_vers.items,
             bad_items = bad_vers.items, split_op_counter,
             orig_buf, real_cb = op->callback](blockstore_op_t *split_op)
         {
@@ -458,6 +458,16 @@ void blockstore_impl_t::mark_stable(const obj_ver_id & v, bool forget_dirty)
                     big_to_flush++;
                 }
             }
+            else if (IS_IN_FLIGHT(dirty_it->second.state))
+            {
+                // mark_stable should never be called for in-flight or submitted writes
+                printf(
+                    "BUG: Attempt to mark_stable object %lx:%lx v%lu state of which is %x\n",
+                    dirty_it->first.oid.inode, dirty_it->first.oid.stripe, dirty_it->first.version,
+                    dirty_it->second.state
+                );
+                exit(1);
+            }
             if (forget_dirty && (IS_BIG_WRITE(dirty_it->second.state) ||
                 IS_DELETE(dirty_it->second.state)))
             {

src/blockstore_sync.cpp

@@ -78,7 +78,23 @@ int blockstore_impl_t::continue_sync(blockstore_op_t *op)
         // 2nd step: Data device is synced, prepare & write journal entries
         // Check space in the journal and journal memory buffers
         blockstore_journal_check_t space_check(this);
-        if (!space_check.check_available(op, PRIV(op)->sync_big_writes.size(),
+        if (dsk.csum_block_size)
+        {
+            // More complex check because all journal entries have different lengths
+            int left = PRIV(op)->sync_big_writes.size();
+            for (auto & sbw: PRIV(op)->sync_big_writes)
+            {
+                left--;
+                auto & dirty_entry = dirty_db.at(sbw);
+                uint64_t dyn_size = dsk.dirty_dyn_size(dirty_entry.offset, dirty_entry.len);
+                if (!space_check.check_available(op, 1, sizeof(journal_entry_big_write) + dyn_size,
+                    left == 0 ? JOURNAL_STABILIZE_RESERVATION : 0))
+                {
+                    return 0;
+                }
+            }
+        }
+        else if (!space_check.check_available(op, PRIV(op)->sync_big_writes.size(),
             sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size, JOURNAL_STABILIZE_RESERVATION))
         {
             return 0;
@@ -90,16 +106,17 @@ int blockstore_impl_t::continue_sync(blockstore_op_t *op)
         int s = 0;
         while (it != PRIV(op)->sync_big_writes.end())
         {
-            if (!journal.entry_fits(sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size) &&
+            auto & dirty_entry = dirty_db.at(*it);
+            uint64_t dyn_size = dsk.dirty_dyn_size(dirty_entry.offset, dirty_entry.len);
+            if (!journal.entry_fits(sizeof(journal_entry_big_write) + dyn_size) &&
                 journal.sector_info[journal.cur_sector].dirty)
             {
                 prepare_journal_sector_write(journal.cur_sector, op);
                 s++;
             }
-            auto & dirty_entry = dirty_db.at(*it);
             journal_entry_big_write *je = (journal_entry_big_write*)prefill_single_journal_entry(
                 journal, (dirty_entry.state & BS_ST_INSTANT) ? JE_BIG_WRITE_INSTANT : JE_BIG_WRITE,
-                sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size
+                sizeof(journal_entry_big_write) + dyn_size
             );
             dirty_entry.journal_sector = journal.sector_info[journal.cur_sector].offset;
             journal.used_sectors[journal.sector_info[journal.cur_sector].offset]++;
@@ -115,8 +132,8 @@ int blockstore_impl_t::continue_sync(blockstore_op_t *op)
             je->offset = dirty_entry.offset;
             je->len = dirty_entry.len;
             je->location = dirty_entry.location;
-            memcpy((void*)(je+1), (dsk.clean_entry_bitmap_size > sizeof(void*)
-                ? dirty_entry.bitmap : &dirty_entry.bitmap), dsk.clean_entry_bitmap_size);
+            memcpy((void*)(je+1), (alloc_dyn_data
+                ? (uint8_t*)dirty_entry.dyn_data+sizeof(int) : (uint8_t*)&dirty_entry.dyn_data), dyn_size);
             je->crc32 = je_crc32((journal_entry*)je);
             journal.crc32_last = je->crc32;
             it++;

src/blockstore_write.cpp

@@ -6,14 +6,23 @@
 bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
 {
     // Check or assign version number
-    bool found = false, deleted = false, is_del = (op->opcode == BS_OP_DELETE);
+    bool found = false, deleted = false, unsynced = false, is_del = (op->opcode == BS_OP_DELETE);
     bool wait_big = false, wait_del = false;
-    void *bmp = NULL;
-    uint64_t version = 1;
-    if (!is_del && dsk.clean_entry_bitmap_size > sizeof(void*))
+    void *dyn = NULL;
+    if (is_del)
     {
-        bmp = calloc_or_die(1, dsk.clean_entry_bitmap_size);
+        op->len = 0;
     }
+    size_t dyn_size = dsk.dirty_dyn_size(op->offset, op->len);
+    if (!is_del && alloc_dyn_data)
+    {
+        // FIXME: Working with `dyn_data` has to be refactored somehow but I first have to decide how :)
+        // +sizeof(int) = refcount
+        dyn = calloc_or_die(1, dyn_size+sizeof(int));
+        *((int*)dyn) = 1;
+    }
+    uint8_t *dyn_ptr = (uint8_t*)(alloc_dyn_data ? dyn+sizeof(int) : &dyn);
+    uint64_t version = 1;
     if (dirty_db.size() > 0)
     {
         auto dirty_it = dirty_db.upper_bound((obj_ver_id){
@@ -26,16 +35,16 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
             found = true;
             version = dirty_it->first.version + 1;
             deleted = IS_DELETE(dirty_it->second.state);
+            unsynced = !IS_SYNCED(dirty_it->second.state);
             wait_del = ((dirty_it->second.state & BS_ST_WORKFLOW_MASK) == BS_ST_WAIT_DEL);
             wait_big = (dirty_it->second.state & BS_ST_TYPE_MASK) == BS_ST_BIG_WRITE
                 ? !IS_SYNCED(dirty_it->second.state)
                 : ((dirty_it->second.state & BS_ST_WORKFLOW_MASK) == BS_ST_WAIT_BIG);
             if (!is_del && !deleted)
             {
-                if (dsk.clean_entry_bitmap_size > sizeof(void*))
-                    memcpy(bmp, dirty_it->second.bitmap, dsk.clean_entry_bitmap_size);
-                else
-                    bmp = dirty_it->second.bitmap;
+                void *dyn_from = alloc_dyn_data
+                    ? (uint8_t*)dirty_it->second.dyn_data + sizeof(int) : (uint8_t*)&dirty_it->second.dyn_data;
+                memcpy(dyn_ptr, dyn_from, dsk.clean_entry_bitmap_size);
             }
         }
     }
@@ -49,7 +58,7 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
             if (!is_del)
             {
                 void *bmp_ptr = get_clean_entry_bitmap(clean_it->second.location, dsk.clean_entry_bitmap_size);
-                memcpy((dsk.clean_entry_bitmap_size > sizeof(void*) ? bmp : &bmp), bmp_ptr, dsk.clean_entry_bitmap_size);
+                memcpy(dyn_ptr, bmp_ptr, dsk.clean_entry_bitmap_size);
             }
         }
         else
@@ -81,10 +90,28 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
             wait_del = true;
             PRIV(op)->real_version = op->version;
             op->version = version;
-            flusher->unshift_flush((obj_ver_id){
-                .oid = op->oid,
-                .version = version-1,
-            }, true);
+            if (unsynced)
+            {
+                // Issue an additional sync so the delete reaches the journal
+                blockstore_op_t *sync_op = new blockstore_op_t;
+                sync_op->opcode = BS_OP_SYNC;
+                sync_op->callback = [this, op](blockstore_op_t *sync_op)
+                {
+                    flusher->unshift_flush((obj_ver_id){
+                        .oid = op->oid,
+                        .version = op->version-1,
+                    }, true);
+                    delete sync_op;
+                };
+                enqueue_op(sync_op);
+            }
+            else
+            {
+                flusher->unshift_flush((obj_ver_id){
+                    .oid = op->oid,
+                    .version = version-1,
+                }, true);
+            }
         }
         else
         {
@@ -93,9 +120,9 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
             printf("Write %lx:%lx v%lu requested, but we already have v%lu\n", op->oid.inode, op->oid.stripe, op->version, version);
 #endif
             op->retval = -EEXIST;
-            if (!is_del && dsk.clean_entry_bitmap_size > sizeof(void*))
+            if (!is_del && alloc_dyn_data)
             {
-                free(bmp);
+                free(dyn);
             }
             return false;
         }
@@ -139,26 +166,50 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
         if (op->bitmap)
         {
             // Only allow to overwrite part of the object bitmap respective to the write's offset/len
-            uint8_t *bmp_ptr = (uint8_t*)(dsk.clean_entry_bitmap_size > sizeof(void*) ? bmp : &bmp);
             uint32_t bit = op->offset/dsk.bitmap_granularity;
             uint32_t bits_left = op->len/dsk.bitmap_granularity;
             while (!(bit % 8) && bits_left >= 8)
             {
                 // Copy bytes
-                bmp_ptr[bit/8] = ((uint8_t*)op->bitmap)[bit/8];
+                dyn_ptr[bit/8] = ((uint8_t*)op->bitmap)[bit/8];
                 bit += 8;
                 bits_left -= 8;
             }
             while (bits_left > 0)
             {
                 // Copy bits
-                bmp_ptr[bit/8] = (bmp_ptr[bit/8] & ~(1 << (bit%8)))
+                dyn_ptr[bit/8] = (dyn_ptr[bit/8] & ~(1 << (bit%8)))
                     | (((uint8_t*)op->bitmap)[bit/8] & (1 << bit%8));
                 bit++;
                 bits_left--;
             }
         }
     }
+    // Calculate checksums
+    // FIXME: Allow to receive checksums from outside?
+    if (!is_del && dsk.data_csum_type && op->len > 0)
+    {
+        uint32_t *data_csums = (uint32_t*)(dyn_ptr + dsk.clean_entry_bitmap_size);
+        uint32_t start = op->offset / dsk.csum_block_size;
+        uint32_t end = (op->offset+op->len-1) / dsk.csum_block_size;
+        auto fn = state & BS_ST_BIG_WRITE ? crc32c_pad : crc32c_nopad;
+        if (start == end)
+            data_csums[0] = fn(0, op->buf, op->len, op->offset - start*dsk.csum_block_size, end*dsk.csum_block_size - (op->offset+op->len));
+        else
+        {
+            // First block
+            data_csums[0] = fn(0, op->buf, dsk.csum_block_size*(start+1)-op->offset, op->offset - start*dsk.csum_block_size, 0);
+            // Intermediate blocks
+            for (uint32_t i = start+1; i < end; i++)
+                data_csums[i-start] = crc32c(0, (uint8_t*)op->buf + dsk.csum_block_size*i-op->offset, dsk.csum_block_size);
+            // Last block
+            data_csums[end-start] = fn(
+                0, (uint8_t*)op->buf + end*dsk.csum_block_size - op->offset,
+                op->offset+op->len - end*dsk.csum_block_size,
+                0, (end+1)*dsk.csum_block_size - (op->offset+op->len)
+            );
+        }
+    }
     dirty_db.emplace((obj_ver_id){
         .oid = op->oid,
         .version = op->version,
@@ -169,7 +220,7 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
         .offset = is_del ? 0 : op->offset,
         .len = is_del ? 0 : op->len,
         .journal_sector = 0,
-        .bitmap = bmp,
+        .dyn_data = dyn,
     });
     return true;
 }
@@ -178,8 +229,7 @@ void blockstore_impl_t::cancel_all_writes(blockstore_op_t *op, blockstore_dirty_
 {
     while (dirty_it != dirty_db.end() && dirty_it->first.oid == op->oid)
     {
-        if (dsk.clean_entry_bitmap_size > sizeof(void*))
-            free(dirty_it->second.bitmap);
+        free_dirty_dyn_data(dirty_it->second);
         dirty_db.erase(dirty_it++);
     }
     bool found = false;
@@ -261,7 +311,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
     {
         blockstore_journal_check_t space_check(this);
         if (!space_check.check_available(op, unsynced_big_write_count + 1,
-            sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size,
+            sizeof(journal_entry_big_write) + dsk.clean_dyn_size,
             (dirty_it->second.state & BS_ST_INSTANT) ? JOURNAL_INSTANT_RESERVATION : JOURNAL_STABILIZE_RESERVATION))
         {
             return 0;
@@ -344,12 +394,13 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
     {
         // Small (journaled) write
         // First check if the journal has sufficient space
+        uint64_t dyn_size = dsk.dirty_dyn_size(op->offset, op->len);
         blockstore_journal_check_t space_check(this);
         if (unsynced_big_write_count &&
             !space_check.check_available(op, unsynced_big_write_count,
-                sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size, 0)
+                sizeof(journal_entry_big_write) + dsk.clean_dyn_size, 0)
             || !space_check.check_available(op, 1,
-                sizeof(journal_entry_small_write) + dsk.clean_entry_bitmap_size,
+                sizeof(journal_entry_small_write) + dyn_size,
                 op->len + ((dirty_it->second.state & BS_ST_INSTANT) ? JOURNAL_INSTANT_RESERVATION : JOURNAL_STABILIZE_RESERVATION)))
         {
             return 0;
@@ -358,7 +409,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
         BS_SUBMIT_CHECK_SQES(
             // Write current journal sector only if it's dirty and full, or in the immediate_commit mode
             (immediate_commit != IMMEDIATE_NONE ||
-                !journal.entry_fits(sizeof(journal_entry_small_write) + dsk.clean_entry_bitmap_size) ? 1 : 0) +
+                !journal.entry_fits(sizeof(journal_entry_small_write) + dyn_size) ? 1 : 0) +
             (op->len > 0 ? 1 : 0)
         );
         write_iodepth++;
@@ -366,7 +417,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
         auto cb = [this, op](ring_data_t *data) { handle_write_event(data, op); };
         if (immediate_commit == IMMEDIATE_NONE)
         {
-            if (!journal.entry_fits(sizeof(journal_entry_small_write) + dsk.clean_entry_bitmap_size))
+            if (!journal.entry_fits(sizeof(journal_entry_small_write) + dyn_size))
             {
                 prepare_journal_sector_write(journal.cur_sector, op);
             }
@@ -378,7 +429,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
         // Then pre-fill journal entry
         journal_entry_small_write *je = (journal_entry_small_write*)prefill_single_journal_entry(
             journal, op->opcode == BS_OP_WRITE_STABLE ? JE_SMALL_WRITE_INSTANT : JE_SMALL_WRITE,
-            sizeof(journal_entry_small_write) + dsk.clean_entry_bitmap_size
+            sizeof(journal_entry_small_write) + dyn_size
         );
         dirty_it->second.journal_sector = journal.sector_info[journal.cur_sector].offset;
         journal.used_sectors[journal.sector_info[journal.cur_sector].offset]++;
@@ -390,14 +441,31 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
         );
 #endif
         // Figure out where data will be
-        journal.next_free = (journal.next_free + op->len) <= journal.len ? journal.next_free : dsk.journal_block_size;
+        auto next_next_free = (journal.next_free + op->len) <= journal.len ? journal.next_free : dsk.journal_block_size;
+        if (op->len > 0)
+        {
+            auto journal_used_it = journal.used_sectors.lower_bound(next_next_free);
+            if (journal_used_it != journal.used_sectors.end() &&
+                journal_used_it->first < next_next_free + op->len)
+            {
+                printf(
+                    "BUG: Attempt to overwrite used offset (%lx, %lu refs) of the journal with the object %lx:%lx v%lu: data at %lx, len %x!"
+                    " Journal used_start=%08lx (%lu refs), next_free=%08lx, dirty_start=%08lx\n",
+                    journal_used_it->first, journal_used_it->second, op->oid.inode, op->oid.stripe, op->version, next_next_free, op->len,
+                    journal.used_start, journal.used_sectors[journal.used_start], journal.next_free, journal.dirty_start
+                );
+                exit(1);
+            }
+        }
+        journal.next_free = next_next_free;
         je->oid = op->oid;
         je->version = op->version;
         je->offset = op->offset;
         je->len = op->len;
         je->data_offset = journal.next_free;
-        je->crc32_data = crc32c(0, op->buf, op->len);
-        memcpy((void*)(je+1), (dsk.clean_entry_bitmap_size > sizeof(void*) ? dirty_it->second.bitmap : &dirty_it->second.bitmap), dsk.clean_entry_bitmap_size);
+        je->crc32_data = dsk.csum_block_size ? 0 : crc32c(0, op->buf, op->len);
+        memcpy((void*)(je+1), (alloc_dyn_data
+            ? (uint8_t*)dirty_it->second.dyn_data+sizeof(int) : (uint8_t*)&dirty_it->second.dyn_data), dyn_size);
         je->crc32 = je_crc32((journal_entry*)je);
         journal.crc32_last = je->crc32;
         if (immediate_commit != IMMEDIATE_NONE)
@@ -466,9 +534,9 @@ resume_2:
             .version = op->version,
         });
         assert(dirty_it != dirty_db.end());
+        uint64_t dyn_size = dsk.dirty_dyn_size(op->offset, op->len);
         blockstore_journal_check_t space_check(this);
-        if (!space_check.check_available(op, 1,
-            sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size,
+        if (!space_check.check_available(op, 1, sizeof(journal_entry_big_write) + dyn_size,
             ((dirty_it->second.state & BS_ST_INSTANT) ? JOURNAL_INSTANT_RESERVATION : JOURNAL_STABILIZE_RESERVATION)))
         {
             return 0;
@@ -476,7 +544,7 @@ resume_2:
         BS_SUBMIT_CHECK_SQES(1);
         journal_entry_big_write *je = (journal_entry_big_write*)prefill_single_journal_entry(
             journal, op->opcode == BS_OP_WRITE_STABLE ? JE_BIG_WRITE_INSTANT : JE_BIG_WRITE,
-            sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size
+            sizeof(journal_entry_big_write) + dyn_size
         );
         dirty_it->second.journal_sector = journal.sector_info[journal.cur_sector].offset;
         journal.used_sectors[journal.sector_info[journal.cur_sector].offset]++;
@@ -492,7 +560,8 @@ resume_2:
         je->offset = op->offset;
         je->len = op->len;
         je->location = dirty_it->second.location;
-        memcpy((void*)(je+1), (dsk.clean_entry_bitmap_size > sizeof(void*) ? dirty_it->second.bitmap : &dirty_it->second.bitmap), dsk.clean_entry_bitmap_size);
+        memcpy((void*)(je+1), (alloc_dyn_data
+            ? (uint8_t*)dirty_it->second.dyn_data+sizeof(int) : (uint8_t*)&dirty_it->second.dyn_data), dyn_size);
         je->crc32 = je_crc32((journal_entry*)je);
         journal.crc32_last = je->crc32;
         prepare_journal_sector_write(journal.cur_sector, op);
@@ -626,8 +695,13 @@ void blockstore_impl_t::release_journal_sectors(blockstore_op_t *op)
         uint64_t s = PRIV(op)->min_flushed_journal_sector;
         while (1)
         {
-            if (s != (1+journal.cur_sector) && journal.sector_info[s-1].flush_count == 0)
+            if (!journal.sector_info[s-1].dirty && journal.sector_info[s-1].flush_count == 0)
             {
+                if (s == (1+journal.cur_sector))
+                {
+                    // Forcibly move to the next sector and move dirty position
+                    journal.in_sector_pos = journal.block_size;
+                }
                 // We know for sure that we won't write into this sector anymore
                 uint64_t new_ds = journal.sector_info[s-1].offset + journal.block_size;
                 if (new_ds >= journal.len)

src/cli.cpp

@@ -73,6 +73,37 @@ static const char* help_text =
     "  <to> must be a child of <from> and <target> may be one of the layers between\n"
     "  <from> and <to>, including <from> and <to>.\n"
     "\n"
+    "vitastor-cli describe [--osds <osds>] [--object-state <states>] [--pool <pool>] [--inode <ino>] [--min-inode <ino>] [--max-inode <ino>] [--min-offset <offset>] [--max-offset <offset>]\n"
+    "  Describe unclean object locations in the cluster.\n"
+    "  --osds <osds>\n"
+    "      Only list objects from primary OSD(s) <osds>.\n"
+    "  --object-state <states>\n"
+    "      Only list objects in given state(s). State(s) may include:\n"
+    "      degraded, misplaced, incomplete, corrupted, inconsistent.\n"
+    "  --pool <pool name or number>\n"
+    "      Only list objects in the given pool.\n"
+    "  --inode, --min-inode, --max-inode\n"
+    "      Restrict listing to specific inode numbers.\n"
+    "  --min-offset, --max-offset\n"
+    "      Restrict listing to specific offsets inside inodes.\n"
+    "\n"
+    "vitastor-cli fix [--objects <objects>] [--bad-osds <osds>] [--part <part>] [--check no]\n"
+    "  Fix inconsistent objects in the cluster by deleting some copies.\n"
+    "  --objects <objects>\n"
+    "      Objects to fix, either in plain text or JSON format. If not specified,\n"
+    "      object list will be read from STDIN in one of the same formats.\n"
+    "      Plain text format: 0x<inode>:0x<stripe> <any delimiter> 0x<inode>:0x<stripe> ...\n"
+    "      JSON format: [{\"inode\":\"0x...\",\"stripe\":\"0x...\"},...]\n"
+    "  --bad-osds <osds>\n"
+    "      Remove inconsistent copies/parts of objects from these OSDs, effectively\n"
+    "      marking them bad and allowing Vitastor to recover objects from other copies.\n"
+    "  --part <number>\n"
+    "      Only remove EC part <number> (from 0 to pg_size-1), required for extreme\n"
+    "      edge cases where one OSD has multiple parts of a EC object.\n"
+    "  --check no\n"
+    "      Do not recheck that requested objects are actually inconsistent,\n"
+    "      delete requested copies/parts anyway.\n"
+    "\n"
     "vitastor-cli alloc-osd\n"
     "  Allocate a new OSD number and reserve it by creating empty /osd/stats/<n> key.\n"
     "\n"
@@ -168,6 +199,7 @@ static json11::Json::object parse_args(int narg, const char *args[])
 static int run(cli_tool_t *p, json11::Json::object cfg)
 {
     cli_result_t result = {};
+    p->is_command_line = true;
     p->parse_config(cfg);
     json11::Json::array cmd = cfg["command"].array_items();
     cfg.erase("command");
@@ -276,6 +308,16 @@ static int run(cli_tool_t *p, json11::Json::object cfg)
         }
         action_cb = p->start_rm(cfg);
     }
+    else if (cmd[0] == "describe")
+    {
+        // Describe unclean objects
+        action_cb = p->start_describe(cfg);
+    }
+    else if (cmd[0] == "fix")
+    {
+        // Fix inconsistent objects (by deleting some copies)
+        action_cb = p->start_fix(cfg);
+    }
     else if (cmd[0] == "alloc-osd")
     {
         // Allocate a new OSD number