Add postponed send loop to QEMU driver

- Measure and report scrub I/O statistics in vitastor-cli status
- Make aggregated statistics in vitastor-cli status much smoother
  (first derive, then sum instead of first summing and then deriving)
- Fix an old rare bug leading to journal corruption
  (try to use scrub if you think you're affected...)
- Do not start EC PGs without at least <data chunks> OSDs in each old set
  (prevents spurious read errors with EC during reconnections/restarts)
- Fix failed assert(!scrub_list_op) on OSD restart with pending scrubs
- Fix future planned scrubs not starting because of incorrect time comparison
- Build packages for Debian 12 (Bookworm)

.gitea/workflows/test.Dockerfile

@@ -10,6 +10,9 @@ RUN set -e -x; \
     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; \

.gitea/workflows/test.yml

@@ -71,7 +71,7 @@ jobs:
     steps:
     - name: Run test
       id: test
-      timeout-minutes: 3
+      timeout-minutes: 10
       run: /root/vitastor/tests/test_add_osd.sh
     - name: Print logs
       if: always() && steps.test.outcome == 'failure'
@@ -190,24 +190,6 @@ jobs:
           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_interrupted_rebalance:
     runs-on: ubuntu-latest
     needs: build
@@ -280,7 +262,7 @@ jobs:
           echo ""
         done
 
-  test_minsize_1:
+  test_failure_domain:
     runs-on: ubuntu-latest
     needs: build
     container: ${{env.TEST_IMAGE}}:${{github.sha}}
@@ -288,115 +270,7 @@ jobs:
     - 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_rebalance_verify:
-    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_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: 3
-      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: 3
-      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: 3
-      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_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
+      run: /root/vitastor/tests/test_failure_domain.sh
     - name: Print logs
       if: always() && steps.test.outcome == 'failure'
       run: |
@@ -442,6 +316,132 @@ jobs:
           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
@@ -460,6 +460,78 @@ jobs:
           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

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

@@ -9,7 +9,8 @@ for my $line (<>)
         chomp $line;
         my $test_name = $1;
         my $timeout = 3;
-        if ($test_name eq 'test_etcd_fail' || $test_name eq 'test_heal' || $test_name eq 'test_interrupted_rebalance')
+        if ($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;
         }

CMakeLists.txt

@@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8.12)
 
 project(vitastor)
 
-set(VERSION "0.9.1")
+set(VERSION "0.9.2")
 
 add_subdirectory(src)

csi/Makefile

@@ -1,4 +1,4 @@
-VERSION ?= v0.9.1
+VERSION ?= v0.9.2
 
 all: build push
 

csi/deploy/004-csi-nodeplugin.yaml

@@ -49,7 +49,7 @@ spec:
             capabilities:
               add: ["SYS_ADMIN"]
             allowPrivilegeEscalation: true
-          image: vitalif/vitastor-csi:v0.9.1
+          image: vitalif/vitastor-csi:v0.9.2
           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:v0.9.1
+          image: vitalif/vitastor-csi:v0.9.2
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/src/config.go

@@ -5,7 +5,7 @@ package vitastor
 
 const (
     vitastorCSIDriverName    = "csi.vitastor.io"
-    vitastorCSIDriverVersion = "0.9.1"
+    vitastorCSIDriverVersion = "0.9.2"
 )
 
 // 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 (0.9.1-1) unstable; urgency=medium
+vitastor (0.9.2-1) unstable; urgency=medium
 
   * Bugfixes
 
  -- Vitaliy Filippov <vitalif@yourcmc.ru>  Fri, 03 Jun 2022 02:09:44 +0300
 
-vitastor (0.9.1-1) unstable; urgency=medium
+vitastor (0.9.2-1) 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; \
@@ -37,23 +39,14 @@ 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; \
     DEBEMAIL="Vitaliy Filippov <vitalif@yourcmc.ru>" dch -D $REL -v $V 'Plug Vitastor block driver'; \

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-$REL; \
-    cp -r /root/vitastor vitastor-0.9.1; \
-    cd vitastor-0.9.1; \
+    cp -r /root/vitastor vitastor-0.9.2; \
+    cd vitastor-0.9.2; \
     ln -s /root/fio-build/fio-*/ ./fio; \
     FIO=$(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-$REL; \
-    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_0.9.1.orig.tar.xz vitastor-0.9.1; \
-    cd vitastor-0.9.1; \
+    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_0.9.2.orig.tar.xz vitastor-0.9.2; \
+    cd vitastor-0.9.2; \
     V=$(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/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/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`

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`

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

@@ -4,12 +4,12 @@
 
 [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

@@ -35,7 +35,7 @@
 
 - [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)

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
@@ -37,7 +37,7 @@
 
 - [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)

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
 ```
 

mon/make-etcd

@@ -63,7 +63,7 @@ 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 \\
+ExecStart=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 \\
     --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} \\

mon/mon.js

@@ -391,6 +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;
@@ -1410,65 +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()
@@ -1627,7 +1638,8 @@ class Mon
             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);
@@ -1743,13 +1755,14 @@ 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
             );
         }
     }

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 = '0.9.1'
+VERSION = '0.9.2'
 
 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-0.9.1/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-0.9.1$(rpm --eval '%dist').tar.gz *
+tar --transform 's#^#vitastor-0.9.2/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-0.9.2$(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-0.9.1.el7.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-0.9.2.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:        0.9.1
+Version:        0.9.2
 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-0.9.1.el7.tar.gz
+Source0:        vitastor-0.9.2.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-0.9.1.el8.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-0.9.2.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:        0.9.1
+Version:        0.9.2
 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-0.9.1.el8.tar.gz
+Source0:        vitastor-0.9.2.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-0.9.1.el9.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-0.9.2.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:        0.9.1
+Version:        0.9.2
 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-0.9.1.el9.tar.gz
+Source0:        vitastor-0.9.2.el9.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

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="0.9.1")
+add_definitions(-DVERSION="0.9.2")
 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)

src/blockstore_flush.cpp

@@ -675,53 +675,58 @@ resume_1:
                     return false;
                 }
                 flusher->trimming = true;
-                // First update journal "superblock" and only then update <used_start> in memory
-                await_sqe(12);
-                *((journal_entry_start*)flusher->journal_superblock) = {
-                    .crc32 = 0,
-                    .magic = JOURNAL_MAGIC,
-                    .type = JE_START,
-                    .size = sizeof(journal_entry_start),
-                    .reserved = 0,
-                    .journal_start = new_trim_pos,
-                    .version = JOURNAL_VERSION,
-                };
-                ((journal_entry_start*)flusher->journal_superblock)->crc32 = je_crc32((journal_entry*)flusher->journal_superblock);
-                data->iov = (struct iovec){ flusher->journal_superblock, bs->dsk.journal_block_size };
-                data->callback = simple_callback_w;
-                my_uring_prep_writev(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset);
-                wait_count++;
-            resume_13:
-                if (wait_count > 0)
+                // Recheck the position with the "lock" taken
+                new_trim_pos = bs->journal.get_trim_pos();
+                if (new_trim_pos != bs->journal.used_start)
                 {
-                    wait_state = 13;
-                    return false;
-                }
-                if (!bs->disable_journal_fsync)
-                {
-                    await_sqe(20);
-                    my_uring_prep_fsync(sqe, bs->dsk.journal_fd, IORING_FSYNC_DATASYNC);
-                    data->iov = { 0 };
+                    // First update journal "superblock" and only then update <used_start> in memory
+                    await_sqe(12);
+                    *((journal_entry_start*)flusher->journal_superblock) = {
+                        .crc32 = 0,
+                        .magic = JOURNAL_MAGIC,
+                        .type = JE_START,
+                        .size = sizeof(journal_entry_start),
+                        .reserved = 0,
+                        .journal_start = new_trim_pos,
+                        .version = JOURNAL_VERSION,
+                    };
+                    ((journal_entry_start*)flusher->journal_superblock)->crc32 = je_crc32((journal_entry*)flusher->journal_superblock);
+                    data->iov = (struct iovec){ flusher->journal_superblock, bs->dsk.journal_block_size };
                     data->callback = simple_callback_w;
-                resume_21:
+                    my_uring_prep_writev(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset);
+                    wait_count++;
+                resume_13:
                     if (wait_count > 0)
                     {
-                        wait_state = 21;
+                        wait_state = 13;
                         return false;
                     }
-                }
-                bs->journal.used_start = new_trim_pos;
+                    if (!bs->disable_journal_fsync)
+                    {
+                        await_sqe(20);
+                        my_uring_prep_fsync(sqe, bs->dsk.journal_fd, IORING_FSYNC_DATASYNC);
+                        data->iov = { 0 };
+                        data->callback = simple_callback_w;
+                    resume_21:
+                        if (wait_count > 0)
+                        {
+                            wait_state = 21;
+                            return false;
+                        }
+                    }
+                    bs->journal.used_start = new_trim_pos;
 #ifdef BLOCKSTORE_DEBUG
-                printf("Journal trimmed to %08lx (next_free=%08lx)\n", bs->journal.used_start, bs->journal.next_free);
+                    printf("Journal trimmed to %08lx (next_free=%08lx)\n", bs->journal.used_start, bs->journal.next_free);
 #endif
+                    if (bs->journal.flush_journal && !flusher->flush_queue.size())
+                    {
+                        assert(bs->journal.used_start == bs->journal.next_free);
+                        printf("Journal flushed\n");
+                        exit(0);
+                    }
+                }
                 flusher->trimming = false;
             }
-            if (bs->journal.flush_journal && !flusher->flush_queue.size())
-            {
-                assert(bs->journal.used_start == bs->journal.next_free);
-                printf("Journal flushed\n");
-                exit(0);
-            }
         }
         // All done
         flusher->active_flushers--;

src/blockstore_journal.cpp

@@ -236,14 +236,6 @@ 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 +248,26 @@ 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

src/blockstore_stable.cpp

@@ -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_write.cpp

@@ -409,7 +409,23 @@ 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;

src/cli_merge.cpp

@@ -41,7 +41,7 @@ struct snap_merger_t
     int fsync_interval = 128;
 
     // -- STATE --
-    inode_t target;
+    inode_t target, to_num;
     int target_rank;
     bool inside_continue = false;
     int state = 0;
@@ -98,6 +98,7 @@ struct snap_merger_t
             state = 100;
             return;
         }
+        to_num = to_cfg->num;
         // Check that to_cfg is actually a child of from_cfg and target_cfg is somewhere between them
         std::vector<inode_t> chain_list;
         inode_config_t *cur = to_cfg;
@@ -451,7 +452,7 @@ struct snap_merger_t
     {
         cluster_op_t *op = &rwo->op;
         op->opcode = OSD_OP_READ;
-        op->inode = target;
+        op->inode = to_num;
         op->offset = rwo->offset;
         op->len = target_block_size;
         op->iov.push_back(rwo->buf, target_block_size);
@@ -483,7 +484,7 @@ struct snap_merger_t
                 {
                     // write start->end
                     rwo->todo++;
-                    write_subop(rwo, rwo->start*gran, rwo->end*gran, use_cas ? 1+rwo->op.version : 0);
+                    write_subop(rwo, rwo->start*gran, rwo->end*gran, use_cas && to_num == target ? 1+rwo->op.version : 0);
                     rwo->start = rwo->end;
                     if (use_cas)
                     {
@@ -502,7 +503,7 @@ struct snap_merger_t
         {
             // write start->end
             rwo->todo++;
-            write_subop(rwo, rwo->start*gran, rwo->end*gran, use_cas ? 1+rwo->op.version : 0);
+            write_subop(rwo, rwo->start*gran, rwo->end*gran, use_cas && to_num == target ? 1+rwo->op.version : 0);
             rwo->start = rwo->end;
             if (use_cas)
             {
@@ -532,7 +533,7 @@ struct snap_merger_t
                 if (use_cas && subop->retval == -EINTR)
                 {
                     // CAS failure - reread and repeat optimistically
-                    rwo->start = subop->offset - rwo->offset;
+                    rwo->start = rwo->end = 0;
                     rwo_read(rwo);
                     delete subop;
                     return;
@@ -542,7 +543,7 @@ struct snap_merger_t
                 rwo->error_read = false;
             }
             // Increment CAS version
-            rwo->op.version++;
+            rwo->op.version = subop->version;
             if (use_cas)
                 next_write(rwo);
             else

src/cli_rm.cpp

@@ -65,6 +65,9 @@ struct snap_remover_t
     int current_child = 0;
     std::function<bool(cli_result_t &)> cb;
 
+    std::vector<std::string> rebased_images, deleted_images;
+    std::vector<uint64_t> deleted_ids;
+    std::string inverse_child_name, inverse_parent_name;
     cli_result_t result;
 
     bool is_done()
@@ -122,6 +125,7 @@ resume_1:
         {
             if (merge_children[current_child] == inverse_child)
                 continue;
+            rebased_images.push_back(parent->cli->st_cli.inode_config.at(merge_children[current_child]).name);
             start_merge_child(merge_children[current_child], merge_children[current_child]);
             if (state == 100)
                 return;
@@ -134,9 +138,12 @@ resume_2:
             cb = NULL;
             if (result.err)
             {
+                result.data = my_result(result.data);
                 state = 100;
                 return;
             }
+            else if (parent->progress)
+                printf("%s\n", result.text.c_str());
             parent->change_parent(merge_children[current_child], new_parent, &result);
             state = 3;
 resume_3:
@@ -144,6 +151,7 @@ resume_3:
                 return;
             if (result.err)
             {
+                result.data = my_result(result.data);
                 state = 100;
                 return;
             }
@@ -165,9 +173,12 @@ resume_4:
             cb = NULL;
             if (result.err)
             {
+                result.data = my_result(result.data);
                 state = 100;
                 return;
             }
+            else if (parent->progress)
+                printf("%s\n", result.text.c_str());
             // Delete "inverse" child data
             start_delete_source(inverse_child);
             if (state == 100)
@@ -181,9 +192,12 @@ resume_5:
             cb = NULL;
             if (result.err)
             {
+                result.data = my_result(result.data);
                 state = 100;
                 return;
             }
+            else if (parent->progress)
+                printf("%s\n", result.text.c_str());
             // Delete "inverse" child metadata, rename parent over it,
             // and also change parent links of the previous "inverse" child
             rename_inverse_parent();
@@ -199,6 +213,12 @@ resume_6:
         {
             if (chain_list[current_child] == inverse_parent)
                 continue;
+            {
+                auto parent_it = parent->cli->st_cli.inode_config.find(chain_list[current_child]);
+                if (parent_it != parent->cli->st_cli.inode_config.end())
+                    deleted_images.push_back(parent_it->second.name);
+                deleted_ids.push_back(chain_list[current_child]);
+            }
             start_delete_source(chain_list[current_child]);
 resume_7:
             while (!cb(result))
@@ -209,9 +229,12 @@ resume_7:
             cb = NULL;
             if (result.err)
             {
+                result.data = my_result(result.data);
                 state = 100;
                 return;
             }
+            else if (parent->progress)
+                printf("%s\n", result.text.c_str());
             delete_inode_config(chain_list[current_child]);
             if (state == 100)
                 return;
@@ -221,11 +244,26 @@ resume_8:
                 return;
         }
         state = 100;
+        result = (cli_result_t){
+            .text = "",
+            .data = my_result(result.data),
+        };
 resume_100:
         // Done
         return;
     }
 
+    json11::Json my_result(json11::Json src)
+    {
+        auto obj = src.object_items();
+        obj["deleted_ids"] = deleted_ids;
+        obj["deleted_images"] = deleted_images;
+        obj["rebased_images"] = rebased_images;
+        obj["renamed_from"] = inverse_parent_name;
+        obj["renamed_to"] = inverse_child_name;
+        return obj;
+    }
+
     void get_merge_children()
     {
         // Get all children of from..to
@@ -338,7 +376,11 @@ resume_100:
             }
             for (auto inode_result: data["responses"].array_items())
             {
-                auto kv = parent->cli->st_cli.parse_etcd_kv(inode_result["kvs"][0]);
+                if (inode_result["response_range"]["kvs"].array_items().size() == 0)
+                {
+                    continue;
+                }
+                auto kv = parent->cli->st_cli.parse_etcd_kv(inode_result["response_range"]["kvs"][0]);
                 pool_id_t pool_id = 0;
                 inode_t inode = 0;
                 char null_byte = 0;
@@ -377,7 +419,7 @@ resume_100:
             inode_t child = cp.first;
             uint64_t child_used = inode_used[child];
             int rank = cp.second;
-            for (int i = chain_list.size()-rank; i < chain_list.size(); i++)
+            for (int i = chain_list.size()-1-rank; i < chain_list.size(); i++)
             {
                 inode_t parent = chain_list[i];
                 uint64_t parent_used = inode_used[parent];
@@ -413,8 +455,8 @@ resume_100:
         }
         inode_config_t *child_cfg = &child_it->second;
         inode_config_t *target_cfg = &target_it->second;
-        std::string child_name = child_cfg->name;
-        std::string target_name = target_cfg->name;
+        inverse_child_name = child_cfg->name;
+        inverse_parent_name = target_cfg->name;
         std::string child_cfg_key = base64_encode(
             parent->cli->st_cli.etcd_prefix+
             "/config/inode/"+std::to_string(INODE_POOL(inverse_child))+
@@ -425,6 +467,9 @@ resume_100:
             "/config/inode/"+std::to_string(INODE_POOL(inverse_parent))+
             "/"+std::to_string(INODE_NO_POOL(inverse_parent))
         );
+        std::string target_idx_key = base64_encode(
+            parent->cli->st_cli.etcd_prefix+"/index/image/"+inverse_parent_name
+        );
         // Fill new configuration
         inode_config_t new_cfg = *child_cfg;
         new_cfg.num = target_cfg->num;
@@ -449,6 +494,11 @@ resume_100:
                     { "key", child_cfg_key },
                 } },
             },
+            json11::Json::object {
+                { "request_delete_range", json11::Json::object {
+                    { "key", target_idx_key },
+                } },
+            },
             json11::Json::object {
                 { "request_put", json11::Json::object {
                     { "key", target_cfg_key },
@@ -495,12 +545,12 @@ resume_100:
         parent->cli->st_cli.etcd_txn_slow(json11::Json::object {
             { "compare", cmp },
             { "success", txn },
-        }, [this, target_name, child_name](std::string err, json11::Json res)
+        }, [this](std::string err, json11::Json res)
         {
             parent->waiting--;
             if (err != "")
             {
-                result = (cli_result_t){ .err = EIO, .text = "Error renaming "+target_name+" to "+child_name+": "+err };
+                result = (cli_result_t){ .err = EIO, .text = "Error renaming "+inverse_parent_name+" to "+inverse_child_name+": "+err };
                 state = 100;
                 return;
             }
@@ -508,14 +558,14 @@ resume_100:
             {
                 result = (cli_result_t){
                     .err = EAGAIN,
-                    .text = "Parent ("+target_name+"), child ("+child_name+"), or one of its children"
+                    .text = "Parent ("+inverse_parent_name+"), child ("+inverse_child_name+"), or one of its children"
                         " configuration was modified during rename",
                 };
                 state = 100;
                 return;
             }
             if (parent->progress)
-                printf("Layer %s renamed to %s\n", target_name.c_str(), child_name.c_str());
+                printf("Layer %s renamed to %s\n", inverse_parent_name.c_str(), inverse_child_name.c_str());
             parent->ringloop->wakeup();
         });
     }

src/cli_rm_data.cpp

@@ -28,6 +28,7 @@ struct rm_inode_t
     cli_tool_t *parent = NULL;
     inode_list_t *lister = NULL;
     std::vector<rm_pg_t*> lists;
+    std::vector<osd_num_t> inactive_osds;
     uint64_t total_count = 0, total_done = 0, total_prev_pct = 0;
     uint64_t pgs_to_list = 0;
     bool lists_done = false;
@@ -86,6 +87,16 @@ struct rm_inode_t
             state = 100;
             return;
         }
+        inactive_osds = parent->cli->list_inode_get_inactive_osds(lister);
+        if (inactive_osds.size() && !parent->json_output)
+        {
+            fprintf(stderr, "Some data may remain after delete on OSDs which are currently down: ");
+            for (int i = 0; i < inactive_osds.size(); i++)
+            {
+                fprintf(stderr, i > 0 ? ", %lu" : "%lu", inactive_osds[i]);
+            }
+            fprintf(stderr, "\n");
+        }
         pgs_to_list = parent->cli->list_pg_count(lister);
         parent->cli->list_inode_next(lister, parent->parallel_osds);
     }
@@ -167,16 +178,33 @@ struct rm_inode_t
         }
         if (parent->progress && total_count > 0 && total_done*1000/total_count != total_prev_pct)
         {
-            printf("\rRemoved %lu/%lu objects, %lu more PGs to list...", total_done, total_count, pgs_to_list);
+            fprintf(stderr, "\rRemoved %lu/%lu objects, %lu more PGs to list...", total_done, total_count, pgs_to_list);
             total_prev_pct = total_done*1000/total_count;
         }
         if (lists_done && !lists.size())
         {
+            if (parent->progress && total_count > 0)
+            {
+                fprintf(stderr, "\n");
+            }
+            if (parent->progress && (total_done < total_count || inactive_osds.size() > 0))
+            {
+                fprintf(
+                    stderr, "Warning: Pool:%u,ID:%lu inode data may not have been fully removed.\n"
+                    " Use `vitastor-cli rm-data --pool %u --inode %lu` if you encounter it in listings.\n",
+                    pool_id, INODE_NO_POOL(inode), pool_id, INODE_NO_POOL(inode)
+                );
+            }
             result = (cli_result_t){
                 .err = error_count > 0 ? EIO : 0,
                 .text = error_count > 0 ? "Some blocks were not removed" : (
                     "Done, inode "+std::to_string(INODE_NO_POOL(inode))+" from pool "+
                     std::to_string(pool_id)+" removed"),
+                .data = json11::Json::object {
+                    { "removed_objects", total_done },
+                    { "total_objects", total_count },
+                    { "inactive_osds", inactive_osds },
+                },
             };
             state = 100;
         }

src/cli_status.cpp

@@ -12,7 +12,7 @@ static const char *obj_states[] = { "clean", "misplaced", "degraded", "incomplet
 // Print cluster status:
 // etcd, mon, osd states
 // raw/used space, object states, pool states, pg states
-// client io, recovery io, rebalance io
+// client io, recovery io, rebalance io, scrub io
 struct status_printer_t
 {
     cli_tool_t *parent;
@@ -252,18 +252,25 @@ resume_2:
         }
         more_states.resize(more_states.size()-2);
         std::string recovery_io;
+        int io_indent = 0;
         {
             uint64_t deg_bps = agg_stats["recovery_stats"]["degraded"]["bps"].uint64_value();
             uint64_t deg_iops = agg_stats["recovery_stats"]["degraded"]["iops"].uint64_value();
             uint64_t misp_bps = agg_stats["recovery_stats"]["misplaced"]["bps"].uint64_value();
             uint64_t misp_iops = agg_stats["recovery_stats"]["misplaced"]["iops"].uint64_value();
+            uint64_t scrub_bps = agg_stats["op_stats"]["scrub"]["bps"].uint64_value();
+            uint64_t scrub_iops = agg_stats["op_stats"]["scrub"]["iops"].uint64_value();
+            if (misp_iops > 0 || misp_bps > 0 || no_rebalance)
+                io_indent = 3;
+            else if (deg_iops > 0 || deg_bps > 0 || no_recovery)
+                io_indent = 2;
             if (deg_iops > 0 || deg_bps > 0)
             {
-                recovery_io += "    recovery:  "+std::string(no_recovery ? "disabled, " : "")+
+                recovery_io += "    recovery: "+str_repeat(" ", io_indent-2)+std::string(no_recovery ? "disabled, " : "")+
                     format_size(deg_bps)+"/s, "+format_size(deg_iops, true)+" op/s\n";
             }
             else if (no_recovery)
-                recovery_io += "    recovery:  disabled\n";
+                recovery_io += "    recovery: disabled\n";
             if (misp_iops > 0 || misp_bps > 0)
             {
                 recovery_io += "    rebalance: "+std::string(no_rebalance ? "disabled, " : "")+
@@ -271,6 +278,13 @@ resume_2:
             }
             else if (no_rebalance)
                 recovery_io += "    rebalance: disabled\n";
+            if (scrub_iops > 0 || scrub_bps > 0)
+            {
+                recovery_io += "    scrub: "+str_repeat(" ", io_indent+1)+std::string(no_scrub ? "disabled, " : "")+
+                    format_size(scrub_bps)+"/s, "+format_size(scrub_iops, true)+" op/s\n";
+            }
+            else if (no_scrub)
+                recovery_io += "    scrub: "+str_repeat(" ", io_indent+1)+"disabled\n";
         }
         printf(
             "  cluster:\n"
@@ -298,7 +312,7 @@ resume_2:
             pools_active, pool_count,
             pgs_by_state_str.c_str(),
             readonly ? " (read-only mode)" : "",
-            recovery_io.size() > 0 ? "   " : "",
+            str_repeat(" ", io_indent).c_str(),
             format_size(agg_stats["op_stats"]["primary_read"]["bps"].uint64_value()).c_str(),
             format_size(agg_stats["op_stats"]["primary_read"]["iops"].uint64_value(), true).c_str(),
             format_size(agg_stats["op_stats"]["primary_write"]["bps"].uint64_value()).c_str(),

src/cluster_client.cpp

@@ -1209,6 +1209,10 @@ void cluster_client_t::handle_op_part(cluster_op_part_t *part)
             copy_part_bitmap(op, part);
             op->version = op->parts.size() == 1 ? part->op.reply.rw.version : 0;
         }
+        else if (op->opcode == OSD_OP_WRITE)
+        {
+            op->version = op->parts.size() == 1 ? part->op.reply.rw.version : 0;
+        }
         if (op->inflight_count == 0)
         {
             if (op->opcode == OSD_OP_SYNC)

src/cluster_client.h

@@ -130,6 +130,7 @@ public:
     inode_list_t *list_inode_start(inode_t inode,
         std::function<void(inode_list_t* lst, std::set<object_id>&& objects, pg_num_t pg_num, osd_num_t primary_osd, int status)> callback);
     int list_pg_count(inode_list_t *lst);
+    const std::vector<osd_num_t> & list_inode_get_inactive_osds(inode_list_t *lst);
     void list_inode_next(inode_list_t *lst, int next_pgs);
     //inline uint32_t get_bs_bitmap_granularity() { return st_cli.global_bitmap_granularity; }
     //inline uint64_t get_bs_block_size() { return st_cli.global_block_size; }

src/cluster_client_list.cpp

@@ -36,6 +36,7 @@ struct inode_list_t
     inode_t inode = 0;
     int done_pgs = 0;
     int want = 0;
+    std::vector<osd_num_t> inactive_osds;
     std::vector<inode_list_pg_t*> pgs;
     std::function<void(inode_list_t* lst, std::set<object_id>&& objects, pg_num_t pg_num, osd_num_t primary_osd, int status)> callback;
 };
@@ -60,6 +61,7 @@ inode_list_t* cluster_client_t::list_inode_start(inode_t inode,
     lst->inode = inode;
     lst->callback = callback;
     auto pool_cfg = st_cli.pool_config[pool_id];
+    std::set<osd_num_t> inactive_osd_set;
     for (auto & pg_item: pool_cfg.pg_config)
     {
         auto & pg = pg_item.second;
@@ -106,11 +108,18 @@ inode_list_t* cluster_client_t::list_inode_start(inode_t inode,
             }
             for (osd_num_t peer_osd: all_peers)
             {
-                r->list_osds.push_back((inode_list_osd_t){
-                    .pg = r,
-                    .osd_num = peer_osd,
-                    .sent = false,
-                });
+                if (st_cli.peer_states.find(peer_osd) != st_cli.peer_states.end())
+                {
+                    r->list_osds.push_back((inode_list_osd_t){
+                        .pg = r,
+                        .osd_num = peer_osd,
+                        .sent = false,
+                    });
+                }
+                else
+                {
+                    inactive_osd_set.insert(peer_osd);
+                }
             }
         }
         else
@@ -132,6 +141,7 @@ inode_list_t* cluster_client_t::list_inode_start(inode_t inode,
     {
         lst->pgs[i]->pos = i;
     }
+    lst->inactive_osds.insert(lst->inactive_osds.end(), inactive_osd_set.begin(), inactive_osd_set.end());
     lists.push_back(lst);
     return lst;
 }
@@ -141,6 +151,11 @@ int cluster_client_t::list_pg_count(inode_list_t *lst)
     return lst->pgs.size();
 }
 
+const std::vector<osd_num_t> & cluster_client_t::list_inode_get_inactive_osds(inode_list_t *lst)
+{
+    return lst->inactive_osds;
+}
+
 void cluster_client_t::list_inode_next(inode_list_t *lst, int next_pgs)
 {
     if (next_pgs >= 0)

src/messenger.h

@@ -132,6 +132,7 @@ protected:
     uint64_t rdma_max_msg = 0;
 #endif
 
+    bool has_send_loop = false;
     std::vector<int> read_ready_clients;
     std::vector<int> write_ready_clients;
     // We don't use ringloop->set_immediate here because we may have no ringloop in client :)
@@ -159,6 +160,7 @@ public:
     std::function<bool(osd_client_t*, json11::Json)> check_config_hook;
     void read_requests();
     void send_replies();
+    bool can_send();
     void accept_connections(int listen_fd);
     ~osd_messenger_t();
 
@@ -173,6 +175,8 @@ public:
     bool connect_rdma(int peer_fd, std::string rdma_address, uint64_t client_max_msg);
 #endif
 
+    void measure_exec(osd_op_t *cur_op);
+
 protected:
     void try_connect_peer(uint64_t osd_num);
     void try_connect_peer_addr(osd_num_t peer_osd, const char *peer_host, int peer_port);
@@ -184,7 +188,6 @@ protected:
     void cancel_op(osd_op_t *op);
 
     bool try_send(osd_client_t *cl);
-    void measure_exec(osd_op_t *cur_op);
     void handle_send(int result, osd_client_t *cl);
 
     bool handle_read(int result, osd_client_t *cl);

src/msgr_op.cpp

@@ -9,6 +9,10 @@ osd_op_t::~osd_op_t()
 {
     assert(!bs_op);
     assert(!op_data);
+    if (bitmap_buf)
+    {
+        free(bitmap_buf);
+    }
     if (rmw_buf)
     {
         free(rmw_buf);

src/msgr_op.h

@@ -165,6 +165,7 @@ struct osd_op_t
     void *bitmap = NULL;
     unsigned bitmap_len = 0;
     unsigned bmp_data = 0;
+    void *bitmap_buf = NULL;
     void *rmw_buf = NULL;
     osd_primary_op_data_t* op_data = NULL;
     std::function<void(osd_op_t*)> callback;

src/msgr_receive.cpp

@@ -369,7 +369,7 @@ bool osd_messenger_t::handle_reply_hdr(osd_client_t *cl)
         op->buf = malloc_or_die(op->reply.hdr.retval);
         cl->recv_list.push_back(op->buf, op->reply.hdr.retval);
     }
-    else if (op->reply.hdr.opcode == OSD_OP_DESCRIBE && op->reply.hdr.retval > 0)
+    else if (op->reply.hdr.opcode == OSD_OP_DESCRIBE && op->reply.describe.result_bytes > 0)
     {
         delete cl->read_op;
         cl->read_op = op;

src/msgr_send.cpp

@@ -84,9 +84,12 @@ void osd_messenger_t::outbox_push(osd_op_t *cur_op)
     {
         for (int i = 0; i < cur_op->iov.count; i++)
         {
-            assert(cur_op->iov.buf[i].iov_base);
-            to_send_list.push_back(cur_op->iov.buf[i]);
-            to_outbox.push_back((msgr_sendp_t){ .op = cur_op, .flags = 0 });
+            if (cur_op->iov.buf[i].iov_len > 0)
+            {
+                assert(cur_op->iov.buf[i].iov_base);
+                to_send_list.push_back(cur_op->iov.buf[i]);
+                to_outbox.push_back((msgr_sendp_t){ .op = cur_op, .flags = 0 });
+            }
         }
     }
     if (cur_op->req.hdr.opcode == OSD_OP_SEC_READ_BMP)
@@ -108,22 +111,28 @@ void osd_messenger_t::outbox_push(osd_op_t *cur_op)
         return;
     }
 #endif
-    if (!ringloop)
+    if (!ringloop && !has_send_loop)
     {
-        // FIXME: It's worse because it doesn't allow batching
+        // "Send loop" should be used, like in QEMU driver, or performance will suffer
+        // due to a large number of sendmsg() syscalls where they can be avoided.
+        // "Send loop" increases 4k T1Q128 randread from ~55k iops to ~90k on a 1 OSD.
+        // The difference is smaller when there are more OSDs though...
         while (cl->outbox.size())
         {
             try_send(cl);
         }
     }
-    else if (cl->write_msg.msg_iovlen > 0 || !try_send(cl))
+    else if (cl->write_msg.msg_iovlen > 0 || has_send_loop || !try_send(cl))
     {
         if (cl->write_state == 0)
         {
             cl->write_state = CL_WRITE_READY;
             write_ready_clients.push_back(cur_op->peer_fd);
         }
-        ringloop->wakeup();
+        if (ringloop)
+        {
+            ringloop->wakeup();
+        }
     }
 }
 
@@ -150,8 +159,10 @@ void osd_messenger_t::measure_exec(osd_op_t *cur_op)
         (cur_op->tv_end.tv_nsec - cur_op->tv_begin.tv_nsec)/1000
     );
     if (cur_op->req.hdr.opcode == OSD_OP_READ ||
-        cur_op->req.hdr.opcode == OSD_OP_WRITE)
+        cur_op->req.hdr.opcode == OSD_OP_WRITE ||
+        cur_op->req.hdr.opcode == OSD_OP_SCRUB)
     {
+        // req.rw.len is internally set to the full object size for scrubs
         stats.op_stat_bytes[cur_op->req.hdr.opcode] += cur_op->req.rw.len;
     }
     else if (cur_op->req.hdr.opcode == OSD_OP_SEC_READ ||
@@ -213,6 +224,12 @@ void osd_messenger_t::send_replies()
     write_ready_clients.clear();
 }
 
+bool osd_messenger_t::can_send()
+{
+    has_send_loop = true;
+    return write_ready_clients.size() > 0;
+}
+
 void osd_messenger_t::handle_send(int result, osd_client_t *cl)
 {
     cl->write_msg.msg_iovlen = 0;

src/nbd_proxy.cpp

@@ -149,7 +149,7 @@ public:
             "  --dev_num N\n"
             "    Use the specified device /dev/nbdN instead of automatic selection.\n"
             "  --foreground 1\n"
-            "    Stay in foreground, do not daemonize.n",
+            "    Stay in foreground, do not daemonize.\n",
             exe_name, exe_name, exe_name
         );
         exit(0);

src/osd_ops.h

@@ -220,7 +220,7 @@ struct __attribute__((__packed__)) osd_reply_rw_t
     // for reads: bitmap length
     uint32_t bitmap_len;
     uint32_t pad0;
-    // for reads: object version
+    // for reads and writes: object version
     uint64_t version;
 };
 

src/osd_peering.cpp

@@ -240,21 +240,20 @@ void osd_t::start_pg_peering(pg_t & pg)
         // (PG history is kept up to the latest active+clean state)
         for (auto & history_set: pg.target_history)
         {
-            bool found = true;
+            int nonzero = 0, found = 0;
             for (auto history_osd: history_set)
             {
                 if (history_osd != 0)
                 {
-                    found = false;
+                    nonzero++;
                     if (history_osd == this->osd_num ||
                         msgr.osd_peer_fds.find(history_osd) != msgr.osd_peer_fds.end())
                     {
-                        found = true;
-                        break;
+                        found++;
                     }
                 }
             }
-            if (!found)
+            if (found < (nonzero >= pg.pg_data_size ? pg.pg_data_size : 1))
             {
                 pg.state = PG_INCOMPLETE;
                 report_pg_state(pg);
@@ -486,6 +485,10 @@ void osd_t::report_pg_state(pg_t & pg)
 {
     pg.print_state();
     this->pg_state_dirty.insert({ .pool_id = pg.pool_id, .pg_num = pg.pg_num });
+    if (pg.state & PG_ACTIVE)
+    {
+        plan_scrub(pg, false);
+    }
     if (pg.state == PG_ACTIVE && (pg.target_history.size() > 0 || pg.all_peers.size() > pg.target_set.size()))
     {
         // Clear history of active+clean PGs
@@ -494,7 +497,6 @@ void osd_t::report_pg_state(pg_t & pg)
         pg.all_peers = pg.target_set;
         std::sort(pg.all_peers.begin(), pg.all_peers.end());
         pg.cur_peers = pg.target_set;
-        plan_scrub(pg, false);
         // Change pg_config at the same time, otherwise our PG reconciling loop may try to apply the old metadata
         auto & pg_cfg = st_cli.pool_config[pg.pool_id].pg_config[pg.pg_num];
         pg_cfg.target_history = pg.target_history;
@@ -538,7 +540,6 @@ void osd_t::report_pg_state(pg_t & pg)
                 pg.cur_peers.push_back(pg_osd);
             }
         }
-        plan_scrub(pg, false);
         auto & pg_cfg = st_cli.pool_config[pg.pool_id].pg_config[pg.pg_num];
         pg_cfg.target_history = pg.target_history;
         pg_cfg.all_peers = pg.all_peers;

src/osd_primary.cpp

@@ -87,8 +87,7 @@ bool osd_t::prepare_primary_rw(osd_op_t *cur_op)
         // - op_data
         1, sizeof(osd_primary_op_data_t) +
         // - stripes
-        // - resulting bitmap buffers
-        stripe_count * (clean_entry_bitmap_size + sizeof(osd_rmw_stripe_t)) +
+        stripe_count * sizeof(osd_rmw_stripe_t) +
         chain_size * (
             // - copy of the chain
             sizeof(inode_t) +
@@ -110,11 +109,12 @@ bool osd_t::prepare_primary_rw(osd_op_t *cur_op)
     op_data->pg_size = pg_it->second.pg_size;
     cur_op->op_data = op_data;
     split_stripes(pg_data_size, bs_block_size, (uint32_t)(cur_op->req.rw.offset - oid.stripe), cur_op->req.rw.len, op_data->stripes);
-    // Allocate bitmaps along with stripes to avoid extra allocations and fragmentation
+    // Resulting bitmaps have to survive op_data and be freed with the op itself
+    assert(!cur_op->bitmap_buf);
+    cur_op->bitmap_buf = calloc_or_die(1, clean_entry_bitmap_size * stripe_count);
     for (int i = 0; i < stripe_count; i++)
     {
-        op_data->stripes[i].bmp_buf = data_buf;
-        data_buf = (uint8_t*)data_buf + clean_entry_bitmap_size;
+        op_data->stripes[i].bmp_buf = (uint8_t*)cur_op->bitmap_buf + clean_entry_bitmap_size * i;
     }
     op_data->chain_size = chain_size;
     if (chain_size > 0)
@@ -129,16 +129,19 @@ bool osd_t::prepare_primary_rw(osd_op_t *cur_op)
         data_buf = (uint8_t*)data_buf + chain_size * (pool_cfg.scheme == POOL_SCHEME_REPLICATED ? 0 : pg_it->second.pg_size);
         // Copy chain
         int chain_num = 0;
-        op_data->read_chain[chain_num++] = cur_op->req.rw.inode;
+        op_data->read_chain[chain_num] = cur_op->req.rw.inode;
+        op_data->chain_states[chain_num] = NULL;
+        chain_num++;
         auto inode_it = st_cli.inode_config.find(cur_op->req.rw.inode);
         while (inode_it != st_cli.inode_config.end() && inode_it->second.parent_id &&
             INODE_POOL(inode_it->second.parent_id) == pg_it->second.pool_id &&
             // Check for loops
             inode_it->second.parent_id != cur_op->req.rw.inode)
         {
-            op_data->read_chain[chain_num++] = inode_it->second.parent_id;
-            op_data->chain_states[chain_num++] = NULL;
+            op_data->read_chain[chain_num] = inode_it->second.parent_id;
+            op_data->chain_states[chain_num] = NULL;
             inode_it = st_cli.inode_config.find(inode_it->second.parent_id);
+            chain_num++;
         }
     }
     pg_it->second.inflight++;
@@ -644,12 +647,6 @@ void osd_t::continue_primary_del(osd_op_t *cur_op)
     else if (op_data->st == 4) goto resume_4;
     else if (op_data->st == 5) goto resume_5;
     assert(op_data->st == 0);
-    // Delete is forbidden even in active PGs if they're also degraded or have previous dead OSDs
-    if (pg.state & (PG_DEGRADED | PG_LEFT_ON_DEAD))
-    {
-        finish_op(cur_op, -EBUSY);
-        return;
-    }
     if (!check_write_queue(cur_op, pg))
     {
         return;

src/osd_primary_subops.cpp

@@ -87,6 +87,7 @@ void osd_t::finish_op(osd_op_t *cur_op, int retval)
     cur_op->reply.hdr.retval = retval;
     if (cur_op->peer_fd == -1)
     {
+        msgr.measure_exec(cur_op);
         // Copy lambda to be unaffected by `delete op`
         std::function<void(osd_op_t*)>(cur_op->callback)(cur_op);
     }

src/osd_primary_write.cpp

@@ -83,11 +83,13 @@ retry_1:
             // Object is degraded/misplaced and will be moved to <write_osd_set>
             op_data->stripes[0].read_start = 0;
             op_data->stripes[0].read_end = bs_block_size;
+            assert(!cur_op->rmw_buf);
             cur_op->rmw_buf = op_data->stripes[0].read_buf = memalign_or_die(MEM_ALIGNMENT, bs_block_size);
         }
     }
     else
     {
+        assert(!cur_op->rmw_buf);
         cur_op->rmw_buf = calc_rmw(cur_op->buf, op_data->stripes, op_data->prev_set,
             pg.pg_size, op_data->pg_data_size, pg.pg_cursize, pg.cur_set.data(), bs_block_size, clean_entry_bitmap_size);
         if (!cur_op->rmw_buf)

src/osd_scrub.cpp

@@ -115,6 +115,10 @@ int osd_t::pick_next_scrub(object_id & next_oid)
         }
         return 0;
     }
+    if (scrub_list_op)
+    {
+        return 1;
+    }
     timespec tv_now;
     clock_gettime(CLOCK_REALTIME, &tv_now);
     bool rescan = scrub_last_pg.pool_id != 0 || scrub_last_pg.pg_num != 0;
@@ -127,7 +131,7 @@ int osd_t::pick_next_scrub(object_id & next_oid)
     }
     while (pg_it != pgs.end())
     {
-        if ((pg_it->second.state & PG_ACTIVE) && pg_it->second.next_scrub && pg_it->second.next_scrub < tv_now.tv_sec)
+        if ((pg_it->second.state & PG_ACTIVE) && pg_it->second.next_scrub && pg_it->second.next_scrub <= tv_now.tv_sec)
         {
             // Continue scrubbing from the next object
             if (scrub_last_pg == pg_it->first)
@@ -346,7 +350,7 @@ void osd_t::schedule_scrub(pg_t & pg)
             tfd->clear_timer(scrub_timer_id);
             scrub_timer_id = -1;
         }
-        if (tv_now.tv_sec > scrub_nearest_ts)
+        if (tv_now.tv_sec >= scrub_nearest_ts)
         {
             scrub_nearest_ts = 0;
             peering_state = peering_state | OSD_SCRUBBING;
@@ -376,6 +380,7 @@ void osd_t::continue_primary_scrub(osd_op_t *cur_op)
         goto resume_2;
     {
         auto & pg = pgs.at({ .pool_id = INODE_POOL(op_data->oid.inode), .pg_num = op_data->pg_num });
+        cur_op->req.rw.len = bs_block_size * pg.pg_data_size;
         // Determine version
         auto vo_it = pg.ver_override.find(op_data->oid);
         op_data->target_ver = vo_it != pg.ver_override.end() ? vo_it->second : UINT64_MAX;

src/qemu_driver.c

@@ -35,6 +35,11 @@
 #define qdict_put_str(options, name, value) qdict_put_obj(options, name, QOBJECT(qstring_from_str(value)))
 #define qobject_unref QDECREF
 #endif
+#if QEMU_VERSION_MAJOR == 4 && QEMU_VERSION_MINOR >= 2 || QEMU_VERSION_MAJOR > 4
+#include "sysemu/replay.h"
+#else
+#include "sysemu/sysemu.h"
+#endif
 
 #include "vitastor_c.h"
 
@@ -48,6 +53,8 @@ void DSO_STAMP_FUN(void)
 }
 #endif
 
+typedef struct VitastorFdData VitastorFdData;
+
 typedef struct VitastorClient
 {
     void *proxy;
@@ -67,12 +74,24 @@ typedef struct VitastorClient
     int rdma_gid_index;
     int rdma_mtu;
     QemuMutex mutex;
+    AioContext *ctx;
+    VitastorFdData **fds;
+    int fd_count, fd_alloc;
+    int bh_send_all_scheduled;
 
     uint64_t last_bitmap_inode, last_bitmap_offset, last_bitmap_len;
     uint32_t last_bitmap_granularity;
     uint8_t *last_bitmap;
 } VitastorClient;
 
+typedef struct VitastorFdData
+{
+    VitastorClient *cli;
+    int fd;
+    IOHandler *fd_read, *fd_write;
+    void *opaque;
+} VitastorFdData;
+
 typedef struct VitastorRPC
 {
     BlockDriverState *bs;
@@ -83,10 +102,21 @@ typedef struct VitastorRPC
     uint64_t inode, offset, len;
     uint32_t bitmap_granularity;
     uint8_t *bitmap;
+#if QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR < 8
+    QEMUBH *bh;
+#endif
 } VitastorRPC;
 
+#if QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR < 8
+typedef struct VitastorBH
+{
+    VitastorClient *cli;
+    QEMUBH *bh;
+} VitastorBH;
+#endif
+
 static void vitastor_co_init_task(BlockDriverState *bs, VitastorRPC *task);
-static void vitastor_co_generic_bh_cb(void *opaque, long retval);
+static void vitastor_co_generic_cb(void *opaque, long retval);
 static void vitastor_co_read_cb(void *opaque, long retval, uint64_t version);
 static void vitastor_close(BlockDriverState *bs);
 
@@ -202,6 +232,49 @@ out:
     return;
 }
 
+#if defined VITASTOR_C_API_VERSION && VITASTOR_C_API_VERSION >= 2
+static void vitastor_bh_send_all(void *opaque)
+{
+#if QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR < 8
+    VitastorBH *vbh = opaque;
+    VitastorClient *client = vbh->cli;
+#else
+    VitastorClient *client = opaque;
+#endif
+    qemu_mutex_lock(&client->mutex);
+    client->bh_send_all_scheduled = 0;
+    vitastor_c_qemu_send_all(client->proxy);
+    qemu_mutex_unlock(&client->mutex);
+#if QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR < 8
+    qemu_bh_delete(vbh->bh);
+    free(vbh);
+#endif
+}
+#endif
+
+static void vitastor_schedule_send_all(VitastorClient *client)
+{
+#if defined VITASTOR_C_API_VERSION && VITASTOR_C_API_VERSION >= 2
+    if (!client->bh_send_all_scheduled)
+    {
+        client->bh_send_all_scheduled = 1;
+#if QEMU_VERSION_MAJOR > 4 || QEMU_VERSION_MAJOR == 4 && QEMU_VERSION_MINOR >= 2
+        replay_bh_schedule_oneshot_event(client->ctx, vitastor_bh_send_all, client);
+#elif QEMU_VERSION_MAJOR >= 3 || QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR >= 8
+        aio_bh_schedule_oneshot(client->ctx, vitastor_bh_send_all, client);
+#elif QEMU_VERSION_MAJOR >= 2
+        VitastorBH *vbh = (VitastorBH*)malloc(sizeof(VitastorBH));
+        vbh->cli = client;
+        vbh->bh = aio_bh_new(bdrv_get_aio_context(task->bs), vitastor_bh_send_all, vbh);
+        qemu_bh_schedule(vbh->bh);
+#else
+        client->bh_send_all_scheduled = 0;
+        vitastor_c_qemu_send_all(client->proxy);
+#endif
+    }
+#endif
+}
+
 static void coroutine_fn vitastor_co_get_metadata(VitastorRPC *task)
 {
     BlockDriverState *bs = task->bs;
@@ -209,7 +282,8 @@ static void coroutine_fn vitastor_co_get_metadata(VitastorRPC *task)
     task->co = qemu_coroutine_self();
 
     qemu_mutex_lock(&client->mutex);
-    vitastor_c_watch_inode(client->proxy, client->image, vitastor_co_generic_bh_cb, task);
+    vitastor_c_watch_inode(client->proxy, client->image, vitastor_co_generic_cb, task);
+    vitastor_schedule_send_all(client);
     qemu_mutex_unlock(&client->mutex);
 
     while (!task->complete)
@@ -218,14 +292,72 @@ static void coroutine_fn vitastor_co_get_metadata(VitastorRPC *task)
     }
 }
 
-// FIXME: Fix thread safety of the driver - now it segfaults when iothread is enabled in QEMU
-static void vitastor_aio_set_fd_handler(void *ctx, int fd, int unused1, IOHandler *fd_read, IOHandler *fd_write, void *unused2, void *opaque)
+static void vitastor_aio_fd_read(void *fddv)
 {
-    aio_set_fd_handler(ctx, fd,
+    VitastorFdData *fdd = (VitastorFdData*)fddv;
+    qemu_mutex_lock(&fdd->cli->mutex);
+    fdd->fd_read(fdd->opaque);
+    vitastor_schedule_send_all(fdd->cli);
+    qemu_mutex_unlock(&fdd->cli->mutex);
+}
+
+static void vitastor_aio_fd_write(void *fddv)
+{
+    VitastorFdData *fdd = (VitastorFdData*)fddv;
+    qemu_mutex_lock(&fdd->cli->mutex);
+    fdd->fd_write(fdd->opaque);
+    vitastor_schedule_send_all(fdd->cli);
+    qemu_mutex_unlock(&fdd->cli->mutex);
+}
+
+static void vitastor_aio_set_fd_handler(void *vcli, int fd, int unused1, IOHandler *fd_read, IOHandler *fd_write, void *unused2, void *opaque)
+{
+    VitastorClient *client = (VitastorClient*)vcli;
+    VitastorFdData *fdd = NULL;
+    int i;
+    for (i = 0; i < client->fd_count; i++)
+    {
+        if (client->fds[i]->fd == fd)
+        {
+            if (fd_read || fd_write)
+            {
+                fdd = client->fds[i];
+                fdd->opaque = opaque;
+                fdd->fd_read = fd_read;
+                fdd->fd_write = fd_write;
+            }
+            else
+            {
+                for (int j = i+1; j < client->fd_count; j++)
+                    client->fds[j-1] = client->fds[j];
+                client->fd_count--;
+            }
+            break;
+        }
+    }
+    if ((fd_read || fd_write) && !fdd)
+    {
+        fdd = (VitastorFdData*)malloc(sizeof(VitastorFdData));
+        fdd->cli = client;
+        fdd->fd = fd;
+        fdd->fd_read = fd_read;
+        fdd->fd_write = fd_write;
+        fdd->opaque = opaque;
+        if (client->fd_count >= client->fd_alloc)
+        {
+            client->fd_alloc = client->fd_alloc*2;
+            if (client->fd_alloc < 16)
+                client->fd_alloc = 16;
+            client->fds = (VitastorFdData**)realloc(client->fds, sizeof(VitastorFdData*) * client->fd_alloc);
+        }
+        client->fds[client->fd_count++] = fdd;
+    }
+    aio_set_fd_handler(client->ctx, fd,
 #if QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR >= 5 || QEMU_VERSION_MAJOR >= 3
         0 /*is_external*/,
 #endif
-        fd_read, fd_write,
+        fd_read ? vitastor_aio_fd_read : NULL,
+        fd_write ? vitastor_aio_fd_write : NULL,
 #if QEMU_VERSION_MAJOR == 1 && QEMU_VERSION_MINOR <= 6 || QEMU_VERSION_MAJOR < 1
         NULL /*io_flush*/,
 #endif
@@ -235,7 +367,7 @@ static void vitastor_aio_set_fd_handler(void *ctx, int fd, int unused1, IOHandle
 #if QEMU_VERSION_MAJOR >= 7
         NULL /*io_poll_ready*/,
 #endif
-        opaque);
+        fdd);
 }
 
 static int vitastor_file_open(BlockDriverState *bs, QDict *options, int flags, Error **errp)
@@ -255,8 +387,9 @@ static int vitastor_file_open(BlockDriverState *bs, QDict *options, int flags, E
     client->rdma_port_num = qdict_get_try_int(options, "rdma-port-num", 0);
     client->rdma_gid_index = qdict_get_try_int(options, "rdma-gid-index", 0);
     client->rdma_mtu = qdict_get_try_int(options, "rdma-mtu", 0);
+    client->ctx = bdrv_get_aio_context(bs);
     client->proxy = vitastor_c_create_qemu(
-        vitastor_aio_set_fd_handler, bdrv_get_aio_context(bs), client->config_path, client->etcd_host, client->etcd_prefix,
+        vitastor_aio_set_fd_handler, client, client->config_path, client->etcd_host, client->etcd_prefix,
         client->use_rdma, client->rdma_device, client->rdma_port_num, client->rdma_gid_index, client->rdma_mtu, 0
     );
     image = client->image = g_strdup(qdict_get_try_str(options, "image"));
@@ -338,6 +471,12 @@ static void vitastor_close(BlockDriverState *bs)
 {
     VitastorClient *client = bs->opaque;
     vitastor_c_destroy(client->proxy);
+    if (client->fds)
+    {
+        free(client->fds);
+        client->fds = NULL;
+        client->fd_alloc = client->fd_count = 0;
+    }
     qemu_mutex_destroy(&client->mutex);
     if (client->config_path)
         g_free(client->config_path);
@@ -454,25 +593,43 @@ static void vitastor_co_init_task(BlockDriverState *bs, VitastorRPC *task)
     };
 }
 
-static void vitastor_co_generic_bh_cb(void *opaque, long retval)
+static void vitastor_co_generic_bh_cb(void *opaque)
 {
     VitastorRPC *task = opaque;
-    task->ret = retval;
     task->complete = 1;
     if (qemu_coroutine_self() != task->co)
     {
 #if QEMU_VERSION_MAJOR >= 3 || QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR > 8
         aio_co_wake(task->co);
 #else
+#if QEMU_VERSION_MAJOR == 2
+        qemu_bh_delete(task->bh);
+#endif
         qemu_coroutine_enter(task->co, NULL);
         qemu_aio_release(task);
 #endif
     }
 }
 
+static void vitastor_co_generic_cb(void *opaque, long retval)
+{
+    VitastorRPC *task = opaque;
+    task->ret = retval;
+#if QEMU_VERSION_MAJOR > 4 || QEMU_VERSION_MAJOR == 4 && QEMU_VERSION_MINOR >= 2
+    replay_bh_schedule_oneshot_event(bdrv_get_aio_context(task->bs), vitastor_co_generic_bh_cb, opaque);
+#elif QEMU_VERSION_MAJOR >= 3 || QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR >= 8
+    aio_bh_schedule_oneshot(bdrv_get_aio_context(task->bs), vitastor_co_generic_bh_cb, opaque);
+#elif QEMU_VERSION_MAJOR >= 2
+    task->bh = aio_bh_new(bdrv_get_aio_context(task->bs), vitastor_co_generic_bh_cb, opaque);
+    qemu_bh_schedule(task->bh);
+#else
+    vitastor_co_generic_bh_cb(opaque);
+#endif
+}
+
 static void vitastor_co_read_cb(void *opaque, long retval, uint64_t version)
 {
-    vitastor_co_generic_bh_cb(opaque, retval);
+    vitastor_co_generic_cb(opaque, retval);
 }
 
 static int coroutine_fn vitastor_co_preadv(BlockDriverState *bs,
@@ -491,6 +648,7 @@ static int coroutine_fn vitastor_co_preadv(BlockDriverState *bs,
     uint64_t inode = client->watch ? vitastor_c_inode_get_num(client->watch) : client->inode;
     qemu_mutex_lock(&client->mutex);
     vitastor_c_read(client->proxy, inode, offset, bytes, iov->iov, iov->niov, vitastor_co_read_cb, &task);
+    vitastor_schedule_send_all(client);
     qemu_mutex_unlock(&client->mutex);
 
     while (!task.complete)
@@ -523,7 +681,8 @@ static int coroutine_fn vitastor_co_pwritev(BlockDriverState *bs,
 
     uint64_t inode = client->watch ? vitastor_c_inode_get_num(client->watch) : client->inode;
     qemu_mutex_lock(&client->mutex);
-    vitastor_c_write(client->proxy, inode, offset, bytes, 0, iov->iov, iov->niov, vitastor_co_generic_bh_cb, &task);
+    vitastor_c_write(client->proxy, inode, offset, bytes, 0, iov->iov, iov->niov, vitastor_co_generic_cb, &task);
+    vitastor_schedule_send_all(client);
     qemu_mutex_unlock(&client->mutex);
 
     while (!task.complete)
@@ -602,6 +761,7 @@ static int coroutine_fn vitastor_co_block_status(
         task.bitmap = client->last_bitmap = NULL;
         qemu_mutex_lock(&client->mutex);
         vitastor_c_read_bitmap(client->proxy, task.inode, task.offset, task.len, !client->skip_parents, vitastor_co_read_bitmap_cb, &task);
+        vitastor_schedule_send_all(client);
         qemu_mutex_unlock(&client->mutex);
         while (!task.complete)
         {
@@ -687,7 +847,8 @@ static int coroutine_fn vitastor_co_flush(BlockDriverState *bs)
     vitastor_co_init_task(bs, &task);
 
     qemu_mutex_lock(&client->mutex);
-    vitastor_c_sync(client->proxy, vitastor_co_generic_bh_cb, &task);
+    vitastor_c_sync(client->proxy, vitastor_co_generic_cb, &task);
+    vitastor_schedule_send_all(client);
     qemu_mutex_unlock(&client->mutex);
 
     while (!task.complete)

src/str_util.cpp

@@ -300,3 +300,11 @@ std::string read_all_fd(int fd)
     res.resize(res_size);
     return res;
 }
+
+std::string str_repeat(const std::string & str, int times)
+{
+    std::string r;
+    for (int i = 0; i < times; i++)
+        r += str;
+    return r;
+}

src/str_util.h

@@ -17,3 +17,4 @@ std::string format_size(uint64_t size, bool nobytes = false);
 void print_help(const char *help_text, std::string exe_name, std::string cmd, bool all);
 uint64_t parse_time(std::string time_str, bool *ok = NULL);
 std::string read_all_fd(int fd);
+std::string str_repeat(const std::string & str, int times);

src/vitastor.pc.in

@@ -6,7 +6,7 @@ includedir=${prefix}/@CMAKE_INSTALL_INCLUDEDIR@
 
 Name: Vitastor
 Description: Vitastor client library
-Version: 0.9.1
+Version: 0.9.2
 Libs: -L${libdir} -lvitastor_client
 Cflags: -I${includedir}
 

src/vitastor_c.cpp

@@ -166,6 +166,14 @@ void vitastor_c_uring_wait_events(vitastor_c *client)
     client->ringloop->wait();
 }
 
+void vitastor_c_qemu_send_all(vitastor_c *client)
+{
+    while (client->cli->msgr.can_send())
+    {
+        client->cli->msgr.send_replies();
+    }
+}
+
 void vitastor_c_read(vitastor_c *client, uint64_t inode, uint64_t offset, uint64_t len,
     struct iovec *iov, int iovcnt, VitastorReadHandler cb, void *opaque)
 {

src/vitastor_c.h

@@ -7,7 +7,7 @@
 #define VITASTOR_QEMU_PROXY_H
 
 // C API wrapper version
-#define VITASTOR_C_API_VERSION 1
+#define VITASTOR_C_API_VERSION 2
 
 #ifndef POOL_ID_BITS
 #define POOL_ID_BITS 16
@@ -42,6 +42,7 @@ int vitastor_c_is_ready(vitastor_c *client);
 void vitastor_c_uring_wait_ready(vitastor_c *client);
 void vitastor_c_uring_handle_events(vitastor_c *client);
 void vitastor_c_uring_wait_events(vitastor_c *client);
+void vitastor_c_qemu_send_all(vitastor_c *client);
 void vitastor_c_read(vitastor_c *client, uint64_t inode, uint64_t offset, uint64_t len,
     struct iovec *iov, int iovcnt, VitastorReadHandler cb, void *opaque);
 void vitastor_c_write(vitastor_c *client, uint64_t inode, uint64_t offset, uint64_t len, uint64_t check_version,

tests/run_3osds.sh

@@ -36,9 +36,6 @@ for i in $(seq 1 $OSD_COUNT); do
     start_osd $i
 done
 
-cd mon
-npm install
-cd ..
 (while true; do node mon/mon-main.js --etcd_url $ETCD_URL --etcd_prefix "/vitastor" --verbose 1 || true; done) &>./testdata/mon.log &
 MON_PID=$!
 

tests/run_tests.sh

@@ -16,29 +16,35 @@ SCHEME=ec ./test_change_pg_count.sh
 
 ./test_etcd_fail.sh
 
-./test_failure_domain.sh
-
 ./test_interrupted_rebalance.sh
 IMMEDIATE_COMMIT=1 ./test_interrupted_rebalance.sh
 SCHEME=ec ./test_interrupted_rebalance.sh
 SCHEME=ec IMMEDIATE_COMMIT=1 ./test_interrupted_rebalance.sh
 
+./test_failure_domain.sh
+
+./test_snapshot.sh
+SCHEME=ec ./test_snapshot.sh
+
 ./test_minsize_1.sh
 
 ./test_move_reappear.sh
 
+./test_rm.sh
+
+./test_snapshot_chain.sh
+SCHEME=ec ./test_snapshot_chain.sh
+
+./test_snapshot_down.sh
+SCHEME=ec ./test_snapshot_down.sh
+
+./test_splitbrain.sh
+
 ./test_rebalance_verify.sh
 IMMEDIATE_COMMIT=1 ./test_rebalance_verify.sh
 SCHEME=ec ./test_rebalance_verify.sh
 SCHEME=ec IMMEDIATE_COMMIT=1 ./test_rebalance_verify.sh
 
-./test_rm.sh
-
-./test_snapshot.sh
-SCHEME=ec ./test_snapshot.sh
-
-./test_splitbrain.sh
-
 ./test_write.sh
 SCHEME=xor ./test_write.sh
 

tests/test_change_pg_count.sh

@@ -85,7 +85,7 @@ try_change 16
 
 # Monitor should report non-zero overall statistics at least once
 
-if ! (grep /vitastor/stats ./testdata/mon.log | jq -s -e '[ .[] | select((.kv.value.op_stats.primary_write.count | tonumber) > 0) ] | length > 0'); then
+if ! (grep /vitastor/stats ./testdata/mon.log | jq -s -e '[ .[] | select((.kv.value.op_stats.primary_write.count // 0 | tonumber) > 0) ] | length > 0'); then
     format_error "FAILED: monitor doesn't aggregate stats"
 fi
 

tests/test_failure_domain.sh

@@ -15,9 +15,6 @@ $ETCDCTL put /vitastor/osd/stats/7 '{"host":"host4","size":1073741824,"time":"'$
 $ETCDCTL put /vitastor/osd/stats/8 '{"host":"host4","size":1073741824,"time":"'$TIME'"}'
 $ETCDCTL put /vitastor/config/pools '{"1":{"name":"testpool","scheme":"replicated","pg_size":2,"pg_minsize":1,"pg_count":4,"failure_domain":"rack"}}'
 
-cd mon
-npm install
-cd ..
 node mon/mon-main.js --etcd_url $ETCD_URL --etcd_prefix "/vitastor" &>./testdata/mon.log &
 MON_PID=$!
 

tests/test_snapshot_chain.sh

@@ -0,0 +1,48 @@
+#!/bin/bash -ex
+
+. `dirname $0`/run_3osds.sh
+check_qemu
+
+# Test multiple snapshots
+
+build/src/vitastor-cli --etcd_address $ETCD_URL create -s 32M testchain
+
+LD_PRELOAD="build/src/libfio_vitastor.so" \
+    fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bs=4M -direct=1 -iodepth=1 -fsync=1 -rw=write \
+        -etcd=$ETCD_URL -image=testchain -mirror_file=./testdata/mirror.bin
+
+for i in {1..10}; do
+    # Create a snapshot
+    build/src/vitastor-cli --etcd_address $ETCD_URL snap-create testchain@$i
+    # Check that the new snapshot is see-through
+    qemu-img convert -p \
+        -f raw "vitastor:etcd_host=127.0.0.1\:$ETCD_PORT/v3:image=testchain" \
+        -O raw ./testdata/check.bin
+    cmp ./testdata/check.bin ./testdata/mirror.bin
+    # Write something to it
+    LD_PRELOAD="build/src/libfio_vitastor.so" \
+    fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bs=4k -direct=1 -iodepth=1 -fsync=32 -rw=randwrite \
+        -randrepeat=$((i <= 2)) -buffer_pattern=0x$((10+i))$((10+i))$((10+i))$((10+i)) \
+        -etcd=$ETCD_URL -image=testchain -number_ios=1024 -mirror_file=./testdata/mirror.bin
+    # Check the new content
+    qemu-img convert -p \
+        -f raw "vitastor:etcd_host=127.0.0.1\:$ETCD_PORT/v3:image=testchain" \
+        -O raw ./testdata/layer1.bin
+    cmp ./testdata/layer1.bin ./testdata/mirror.bin
+done
+
+build/src/vitastor-cli --etcd_address $ETCD_URL rm testchain@1 testchain@9
+
+# Check the final image
+qemu-img convert -p \
+    -f raw "vitastor:etcd_host=127.0.0.1\:$ETCD_PORT/v3:image=testchain" \
+    -O raw ./testdata/layer1.bin
+cmp ./testdata/layer1.bin ./testdata/mirror.bin
+
+# Check the last remaining snapshot
+qemu-img convert -p \
+    -f raw "vitastor:etcd_host=127.0.0.1\:$ETCD_PORT/v3:image=testchain@10" \
+    -O raw ./testdata/layer0.bin
+cmp ./testdata/layer0.bin ./testdata/check.bin
+
+format_green OK

tests/test_snapshot_down.sh

@@ -0,0 +1,37 @@
+#!/bin/bash -ex
+
+. `dirname $0`/run_3osds.sh
+check_qemu
+
+# Test merge to child (without "inverse rename" optimisation)
+
+build/src/vitastor-cli --etcd_address $ETCD_URL create -s 128M testchain
+
+LD_PRELOAD="build/src/libfio_vitastor.so" \
+    fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bs=4M -direct=1 -iodepth=1 -fsync=1 -rw=write \
+        -etcd=$ETCD_URL -image=testchain -mirror_file=./testdata/mirror.bin
+
+# Create a snapshot
+build/src/vitastor-cli --etcd_address $ETCD_URL snap-create testchain@0
+
+# Write something to it
+LD_PRELOAD="build/src/libfio_vitastor.so" \
+fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bs=1M -direct=1 -iodepth=4 -rw=randwrite \
+    -randrepeat=0 -etcd=$ETCD_URL -image=testchain -number_ios=8 -mirror_file=./testdata/mirror.bin
+
+# Check the new content
+qemu-img convert -p \
+    -f raw "vitastor:etcd_host=127.0.0.1\:$ETCD_PORT/v3:image=testchain" \
+    -O raw ./testdata/layer1.bin
+cmp ./testdata/layer1.bin ./testdata/mirror.bin
+
+# Merge
+build/src/vitastor-cli --etcd_address $ETCD_URL rm testchain@0
+
+# Check the final image
+qemu-img convert -p \
+    -f raw "vitastor:etcd_host=127.0.0.1\:$ETCD_PORT/v3:image=testchain" \
+    -O raw ./testdata/layer1.bin
+cmp ./testdata/layer1.bin ./testdata/mirror.bin
+
+format_green OK