Release 2.2.3

- Support Ubuntu 24.04 Noble
- Fix clients hanging on online PG count change with in-flight operations
- Fix volume_size_info in PVE VitastorPlugin
- Implement bdrv_refresh_filename for the QEMU driver
- Fix RDMA-CM broken in 2.2.0
- Fix possible "invalid %N$ use detected" OSD crashes
- Fix vitastor-nfs build without RDMA
- Fix docker build by adding the forgotten apt/preferences
- Fix libfio_blockstore.so
- Fix "trigger event loop automatically" API version check in the QEMU driver
- Add Content-Type header for prometheus metrics
- Add a patch for libvirt 11.5

.gitea/workflows/test.yml

@@ -144,6 +144,24 @@ jobs:
           echo ""
         done
 
+  test_change_pg_count_online:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 3
+      run: /root/vitastor/tests/test_change_pg_count_online.sh
+    - name: Print logs
+      if: always() && steps.test.outcome == 'failure'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
   test_change_pg_size:
     runs-on: ubuntu-latest
     needs: build
@@ -684,6 +702,24 @@ jobs:
           echo ""
         done
 
+  test_write_iothreads:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 3
+      run: TEST_NAME=iothreads GLOBAL_CONFIG=',"client_iothread_count":4' /root/vitastor/tests/test_write.sh
+    - name: Print logs
+      if: always() && steps.test.outcome == 'failure'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
   test_write_no_same:
     runs-on: ubuntu-latest
     needs: build

CMakeLists.txt

@@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8.12)
 
 project(vitastor)
 
-set(VITASTOR_VERSION "2.2.0")
+set(VITASTOR_VERSION "2.2.3")
 
 add_subdirectory(src)

csi/Makefile

@@ -1,4 +1,4 @@
-VITASTOR_VERSION ?= v2.2.0
+VITASTOR_VERSION ?= v2.2.3
 
 all: build push
 

csi/deploy/004-csi-nodeplugin.yaml

@@ -49,7 +49,7 @@ spec:
             capabilities:
               add: ["SYS_ADMIN"]
             allowPrivilegeEscalation: true
-          image: vitalif/vitastor-csi:v2.2.0
+          image: vitalif/vitastor-csi:v2.2.3
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/deploy/007-csi-provisioner.yaml

@@ -121,7 +121,7 @@ spec:
             privileged: true
             capabilities:
               add: ["SYS_ADMIN"]
-          image: vitalif/vitastor-csi:v2.2.0
+          image: vitalif/vitastor-csi:v2.2.3
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/src/config.go

@@ -5,7 +5,7 @@ package vitastor
 
 const (
     vitastorCSIDriverName    = "csi.vitastor.io"
-    vitastorCSIDriverVersion = "2.2.0"
+    vitastorCSIDriverVersion = "2.2.3"
 )
 
 // Config struct fills the parameters of request or user input

debian/build-vitastor-bookworm.sh

@@ -1,7 +1,4 @@
 #!/bin/bash
 
-cat < vitastor.Dockerfile > ../Dockerfile
+docker build --build-arg DISTRO=debian --build-arg REL=bookworm -t vitastor-buildenv:bookworm -f vitastor-buildenv.Dockerfile .
-cd ..
+docker run -i --rm -e REL=bookworm -v `dirname $0`/../:/root/vitastor vitastor-buildenv:bookworm /root/vitastor/debian/vitastor-build.sh
-mkdir -p packages
-sudo podman build --build-arg DISTRO=debian --build-arg REL=bookworm -v `pwd`/packages:/root/packages -f Dockerfile .
-rm Dockerfile

debian/build-vitastor-bullseye.sh

@@ -1,7 +1,4 @@
 #!/bin/bash
 
-cat < vitastor.Dockerfile > ../Dockerfile
+docker build --build-arg DISTRO=debian --build-arg REL=bullseye -t vitastor-buildenv:bullseye -f vitastor-buildenv.Dockerfile .
-cd ..
+docker run -i --rm -e REL=bullseye -v `dirname $0`/../:/root/vitastor vitastor-buildenv:bullseye /root/vitastor/debian/vitastor-build.sh
-mkdir -p packages
-sudo podman build --build-arg DISTRO=debian --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f Dockerfile .
-rm Dockerfile

debian/build-vitastor-buster.sh

@@ -1,7 +1,4 @@
 #!/bin/bash
 
-cat < vitastor.Dockerfile > ../Dockerfile
+docker build --build-arg DISTRO=debian --build-arg REL=buster -t vitastor-buildenv:buster -f vitastor-buildenv.Dockerfile .
-cd ..
+docker run -i --rm -e REL=buster -v `dirname $0`/../:/root/vitastor vitastor-buildenv:buster /root/vitastor/debian/vitastor-build.sh
-mkdir -p packages
-sudo podman build --build-arg DISTRO=debian --build-arg REL=buster -v `pwd`/packages:/root/packages -f Dockerfile .
-rm Dockerfile

debian/build-vitastor-ubuntu-jammy.sh

@@ -1,7 +1,5 @@
 #!/bin/bash
+# Ubuntu 22.04 Jammy Jellyfish
 
-cat < vitastor.Dockerfile > ../Dockerfile
+docker build --build-arg DISTRO=ubuntu --build-arg REL=jammy -t vitastor-buildenv:jammy -f vitastor-buildenv.Dockerfile .
-cd ..
+docker run -i --rm -e REL=jammy -v `dirname $0`/../:/root/vitastor vitastor-buildenv:jammy /root/vitastor/debian/vitastor-build.sh
-mkdir -p packages
-sudo podman build --build-arg DISTRO=ubuntu --build-arg REL=jammy -v `pwd`/packages:/root/packages -f Dockerfile .
-rm Dockerfile

debian/build-vitastor-ubuntu-noble.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+# 24.04 Noble Numbat
+
+docker build --build-arg DISTRO=ubuntu --build-arg REL=noble -t vitastor-buildenv:noble -f vitastor-buildenv.Dockerfile .
+docker run -i --rm -e REL=noble -v `dirname $0`/../:/root/vitastor vitastor-buildenv:noble /root/vitastor/debian/vitastor-build.sh

debian/changelog

@@ -1,4 +1,4 @@
-vitastor (2.2.0-1) unstable; urgency=medium
+vitastor (2.2.3-1) unstable; urgency=medium
 
   * Bugfixes
 

debian/vitastor-build.sh

@@ -0,0 +1,59 @@
+#!/bin/bash
+# To be ran inside buildenv docker
+
+set -e -x
+
+[ -e /usr/lib/x86_64-linux-gnu/pkgconfig/libisal.pc ] || cp /root/vitastor/debian/libisal.pc /usr/lib/x86_64-linux-gnu/pkgconfig
+
+mkdir -p /root/fio-build/
+cd /root/fio-build/
+rm -rf /root/fio-build/*
+dpkg-source -x /root/fio*.dsc
+
+FULLVER=`head -n1 /root/vitastor/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'`
+VER=${FULLVER%%-*}
+rm -rf /root/vitastor-$VER
+mkdir /root/vitastor-$VER
+cd /root/vitastor
+cp -a $(ls | grep -v packages) /root/vitastor-$VER
+
+rm -rf /root/vitastor/packages/vitastor-$REL
+mkdir -p /root/vitastor/packages/vitastor-$REL
+mv /root/vitastor-$VER /root/vitastor/packages/vitastor-$REL/
+
+cd /root/vitastor/packages/vitastor-$REL/vitastor-$VER
+
+rm -rf fio
+ln -s /root/fio-build/fio-*/ ./fio
+FIO=`head -n1 fio/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'`
+ls /usr/include/linux/raw.h || cp ./debian/raw.h /usr/include/linux/raw.h
+sh copy-fio-includes.sh
+rm fio
+mkdir -p a b debian/patches
+mv fio-copy b/fio
+diff -NaurpbB a b > debian/patches/fio-headers.patch || true
+echo fio-headers.patch >> debian/patches/series
+rm -rf a b
+
+echo "dep:fio=$FIO" > debian/fio_version
+
+cd /root/vitastor/packages/vitastor-$REL/vitastor-$VER
+mkdir mon/node_modules
+cd mon/node_modules
+curl -s https://git.yourcmc.ru/vitalif/antietcd/archive/master.tar.gz | tar -zx
+curl -s https://git.yourcmc.ru/vitalif/tinyraft/archive/master.tar.gz | tar -zx
+
+cd /root/vitastor/packages/vitastor-$REL
+tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_$VER.orig.tar.xz vitastor-$VER
+cd vitastor-$VER
+DEBEMAIL="Vitaliy Filippov <vitalif@yourcmc.ru>" dch -D $REL -v "$FULLVER""$REL" "Rebuild for $REL"
+DEB_BUILD_OPTIONS=nocheck dpkg-buildpackage --jobs=auto -sa
+rm -rf /root/vitastor/packages/vitastor-$REL/vitastor-*/
+
+# Why does ubuntu rename debug packages to *.ddeb?
+if ls *.ddeb >/dev/null; then
+    perl -i -pe 's/\.ddeb/.deb/' *.buildinfo *.changes
+    for i in *.ddeb; do
+        mv $i ${i%%.ddeb}.deb
+    done
+fi

debian/vitastor-buildenv.Dockerfile

@@ -0,0 +1,31 @@
+# Build environment for building Vitastor packages for Debian inside a container
+# cd ..
+# docker build --build-arg DISTRO=debian --build-arg REL=bullseye -f debian/vitastor.Dockerfile -t vitastor-buildenv:bullseye .
+# docker run --rm -e REL=bullseye -v ./:/root/vitastor /root/vitastor/debian/vitastor-build.sh
+
+ARG DISTRO=debian
+ARG REL=
+FROM $DISTRO:$REL
+ARG DISTRO=debian
+ARG REL=
+
+WORKDIR /root
+
+RUN set -e -x; \
+    if [ "$REL" = "buster" ]; then \
+        perl -i -pe 's/deb.debian.org/archive.debian.org/' /etc/apt/sources.list; \
+        apt-get update; \
+        apt-get -y install wget; \
+        wget https://vitastor.io/debian/pubkey.gpg -O /etc/apt/trusted.gpg.d/vitastor.gpg; \
+        echo "deb https://vitastor.io/debian $REL main" >> /etc/apt/sources.list; \
+    fi; \
+    grep '^deb ' /etc/apt/sources.list | perl -pe 's/^deb/deb-src/' >> /etc/apt/sources.list; \
+    perl -i -pe 's/Types: deb$/Types: deb deb-src/' /etc/apt/sources.list.d/*.sources || true; \
+    echo 'APT::Install-Recommends false;' >> /etc/apt/apt.conf; \
+    echo 'APT::Install-Suggests false;' >> /etc/apt/apt.conf
+
+RUN apt-get update && \
+    apt-get -y install fio liburing-dev libgoogle-perftools-dev devscripts libjerasure-dev cmake \
+        libibverbs-dev librdmacm-dev libisal-dev libnl-3-dev libnl-genl-3-dev curl nodejs npm node-nan node-bindings && \
+    apt-get -y build-dep fio && \
+    apt-get --download-only source fio

debian/vitastor.Dockerfile

@@ -1,65 +0,0 @@
-# Build Vitastor packages for Debian inside a container
-# cd ..; podman build --build-arg DISTRO=debian --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/vitastor.Dockerfile .
-
-ARG DISTRO=debian
-ARG REL=
-FROM $DISTRO:$REL
-ARG DISTRO=debian
-ARG REL=
-
-WORKDIR /root
-
-RUN set -e -x; \
-    if [ "$REL" = "buster" ]; then \
-        apt-get update; \
-        apt-get -y install wget; \
-        wget https://vitastor.io/debian/pubkey.gpg -O /etc/apt/trusted.gpg.d/vitastor.gpg; \
-        echo "deb https://vitastor.io/debian $REL main" >> /etc/apt/sources.list; \
-    fi; \
-    grep '^deb ' /etc/apt/sources.list | perl -pe 's/^deb/deb-src/' >> /etc/apt/sources.list; \
-    perl -i -pe 's/Types: deb$/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 && \
-    apt-get -y install fio liburing-dev libgoogle-perftools-dev devscripts libjerasure-dev cmake \
-        libibverbs-dev librdmacm-dev libisal-dev libnl-3-dev libnl-genl-3-dev curl nodejs npm node-nan node-bindings && \
-    apt-get -y build-dep fio && \
-    apt-get --download-only source fio
-
-ADD . /root/vitastor
-RUN set -e -x; \
-    [ -e /usr/lib/x86_64-linux-gnu/pkgconfig/libisal.pc ] || cp /root/vitastor/debian/libisal.pc /usr/lib/x86_64-linux-gnu/pkgconfig; \
-    mkdir -p /root/fio-build/; \
-    cd /root/fio-build/; \
-    rm -rf /root/fio-build/*; \
-    dpkg-source -x /root/fio*.dsc; \
-    mkdir -p /root/packages/vitastor-$REL; \
-    rm -rf /root/packages/vitastor-$REL/*; \
-    cd /root/packages/vitastor-$REL; \
-    FULLVER=$(head -n1 /root/vitastor/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
-    VER=${FULLVER%%-*}; \
-    cp -r /root/vitastor vitastor-$VER; \
-    cd vitastor-$VER; \
-    ln -s /root/fio-build/fio-*/ ./fio; \
-    FIO=$(head -n1 fio/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
-    ls /usr/include/linux/raw.h || cp ./debian/raw.h /usr/include/linux/raw.h; \
-    sh copy-fio-includes.sh; \
-    rm fio; \
-    mkdir -p a b debian/patches; \
-    mv fio-copy b/fio; \
-    diff -NaurpbB a b > debian/patches/fio-headers.patch || true; \
-    echo fio-headers.patch >> debian/patches/series; \
-    rm -rf a b; \
-    echo "dep:fio=$FIO" > debian/fio_version; \
-    cd /root/packages/vitastor-$REL/vitastor-$VER; \
-    mkdir mon/node_modules; \
-    cd mon/node_modules; \
-    curl -s https://git.yourcmc.ru/vitalif/antietcd/archive/master.tar.gz | tar -zx; \
-    curl -s https://git.yourcmc.ru/vitalif/tinyraft/archive/master.tar.gz | tar -zx; \
-    cd /root/packages/vitastor-$REL; \
-    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_$VER.orig.tar.xz vitastor-$VER; \
-    cd vitastor-$VER; \
-    DEBFULLNAME="Vitaliy Filippov <vitalif@yourcmc.ru>" dch -D $REL -v "$FULLVER""$REL" "Rebuild for $REL"; \
-    DEB_BUILD_OPTIONS=nocheck dpkg-buildpackage --jobs=auto -sa; \
-    rm -rf /root/packages/vitastor-$REL/vitastor-*/

docker/Makefile

@@ -1,4 +1,4 @@
-VITASTOR_VERSION ?= v2.2.0
+VITASTOR_VERSION ?= v2.2.3
 
 all: build push
 

docker/etc/apt/preferences

@@ -0,0 +1,3 @@
+Package: *
+Pin: release n=bookworm-backports
+Pin-Priority: 500

docker/etc/vitastor/docker.conf

@@ -4,7 +4,7 @@
 #
 
 # Desired Vitastor version
-VITASTOR_VERSION=v2.2.0
+VITASTOR_VERSION=v2.2.3
 
 # Additional arguments for all containers
 # For example, you may want to specify a custom logging driver here

docs/config/network.en.md

@@ -74,7 +74,7 @@ Consider `use_rdmacm` for such networks.
 ## use_rdmacm
 
 - Type: boolean
-- Default: true
+- Default: false
 
 Use an alternative implementation of RDMA through RDMA-CM (Connection
 Manager). Works with all RDMA networks: Infiniband, iWARP and

docs/config/network.ru.md

@@ -74,7 +74,7 @@ RDMA-устройства, но они не имеют соединения с
 ## use_rdmacm
 
 - Тип: булево (да/нет)
-- Значение по умолчанию: true
+- Значение по умолчанию: false
 
 Использовать альтернативную реализацию RDMA на основе RDMA-CM (Connection
 Manager). Работает со всеми типами RDMA-сетей: Infiniband, iWARP и

docs/config/src/network.yml

@@ -51,7 +51,7 @@
     Рассмотрите включение `use_rdmacm` для таких сетей.
 - name: use_rdmacm
   type: bool
-  default: true
+  default: false
   info: |
     Use an alternative implementation of RDMA through RDMA-CM (Connection
     Manager). Works with all RDMA networks: Infiniband, iWARP and

docs/installation/docker.en.md

@@ -26,9 +26,9 @@ at Vitastor Kubernetes operator: https://github.com/Antilles7227/vitastor-operat
 The instruction is very simple.
 
 1. Download a Docker image of the desired version: \
-   `docker pull vitastor:v2.2.0`
+   `docker pull vitalif/vitastor:v2.2.3`
 2. Install scripts to the host system: \
-   `docker run --rm -it -v /etc:/host-etc -v /usr/bin:/host-bin vitastor:v2.2.0 install.sh`
+   `docker run --rm -it -v /etc:/host-etc -v /usr/bin:/host-bin vitalif/vitastor:v2.2.3 install.sh`
 3. Reload udev rules: \
    `udevadm control --reload-rules`
 

docs/installation/docker.ru.md

@@ -25,9 +25,9 @@ Vitastor можно установить в Docker/Podman. При этом etcd,
 Инструкция по установке максимально простая.
 
 1. Скачайте Docker-образ желаемой версии: \
-   `docker pull vitastor:v2.2.0`
+   `docker pull vitalif/vitastor:v2.2.3`
 2. Установите скрипты в хост-систему командой: \
-   `docker run --rm -it -v /etc:/host-etc -v /usr/bin:/host-bin vitastor:v2.2.0 install.sh`
+   `docker run --rm -it -v /etc:/host-etc -v /usr/bin:/host-bin vitalif/vitastor:v2.2.3 install.sh`
 3. Перезагрузите правила udev: \
    `udevadm control --reload-rules`
 

docs/installation/packages.en.md

@@ -15,6 +15,7 @@
   - Debian 11 (Bullseye): `deb https://vitastor.io/debian bullseye main`
   - Debian 10 (Buster): `deb https://vitastor.io/debian buster main`
   - Ubuntu 22.04 (Jammy): `deb https://vitastor.io/debian jammy main`
+  - Ubuntu 24.04 (Noble): `deb https://vitastor.io/debian noble main`
   - Add `-oldstable` to bookworm/bullseye/buster in this line to install the last
     stable version from 0.9.x branch instead of 1.x
 - Install packages: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu-system-x86`

docs/installation/packages.ru.md

@@ -15,6 +15,7 @@
   - Debian 11 (Bullseye): `deb https://vitastor.io/debian bullseye main`
   - Debian 10 (Buster): `deb https://vitastor.io/debian buster main`
   - Ubuntu 22.04 (Jammy): `deb https://vitastor.io/debian jammy main`
+  - Ubuntu 24.04 (Noble): `deb https://vitastor.io/debian noble main`
   - Добавьте `-oldstable` к слову bookworm/bullseye/buster в этой строке, чтобы
     установить последнюю стабильную версию из ветки 0.9.x вместо 1.x
 - Установите пакеты: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu-system-x86`

docs/installation/proxmox.en.md

@@ -6,10 +6,10 @@
 
 # Proxmox VE
 
-To enable Vitastor support in Proxmox Virtual Environment (6.4-8.1 are supported):
+To enable Vitastor support in Proxmox Virtual Environment (6.4-8.x are supported):
 
 - Add the corresponding Vitastor Debian repository into sources.list on Proxmox hosts:
-  bookworm for 8.1, pve8.0 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
+  bookworm for 8.1+, pve8.0 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),

docs/installation/proxmox.ru.md

@@ -6,10 +6,10 @@
 
 # Proxmox VE
 
-Чтобы подключить Vitastor к Proxmox Virtual Environment (поддерживаются версии 6.4-8.1):
+Чтобы подключить Vitastor к Proxmox Virtual Environment (поддерживаются версии 6.4-8.x):
 
 - Добавьте соответствующий Debian-репозиторий Vitastor в sources.list на хостах Proxmox:
-  bookworm для 8.1, pve8.0 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
+  bookworm для 8.1+, pve8.0 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

docs/intro/author.en.md

@@ -10,8 +10,17 @@ Copyright (c) Vitaliy Filippov (vitalif [at] yourcmc.ru), 2019+
 
 Join Vitastor Telegram Chat: https://t.me/vitastor
 
-All server-side code (OSD, Monitor and so on) is licensed under the terms of
+License: VNPL 1.1 for server-side code and dual VNPL 1.1 + GPL 2.0+ for client tools.
-Vitastor Network Public License 1.1 (VNPL 1.1), a copyleft license based on
+
+Server-side code is licensed only under the terms of VNPL.
+
+Client libraries (cluster_client and so on) are dual-licensed under the same
+VNPL 1.1 and also GNU GPL 2.0 or later to allow for compatibility with GPLed
+software like QEMU and fio.
+
+## VNPL
+
+Vitastor Network Public License 1.1 (VNPL 1.1) is a copyleft license based on
 GNU GPLv3.0 with the additional "Network Interaction" clause which requires
 opensourcing all programs directly or indirectly interacting with Vitastor
 through a computer network and expressly designed to be used in conjunction
@@ -20,18 +29,83 @@ the terms of the same license, but also under the terms of any GPL-Compatible
 Free Software License, as listed by the Free Software Foundation.
 This is a stricter copyleft license than the Affero GPL.
 
-Please note that VNPL doesn't require you to open the code of proprietary
+The idea of VNPL is, in addition to modules linked to Vitastor code in a single
-software running inside a VM if it's not specially designed to be used with
+binary file, to extend copyleft action to micro-service modules only interacting
-Vitastor.
+with it over the network.
 
 Basically, you can't use the software in a proprietary environment to provide
 its functionality to users without opensourcing all intermediary components
 standing between the user and Vitastor or purchasing a commercial license
 from the author 😀.
 
-Client libraries (cluster_client and so on) are dual-licensed under the same
+At the same time, VNPL doesn't impose any restrictions on software *not specially designed*
-VNPL 1.1 and also GNU GPL 2.0 or later to allow for compatibility with GPLed
+to be used with Vitastor, for example, on Windows running inside a VM with a Vitastor disk.
-software like QEMU and fio.
 
-You can find the full text of VNPL-1.1 in the file [VNPL-1.1.txt](../../VNPL-1.1.txt).
+## Explanation
-GPL 2.0 is also included in this repository as [GPL-2.0.txt](../../GPL-2.0.txt).
+
+Network copyleft is governed by the clause **13. Remote Network Interaction** of VNPL.
+
+A program is considered to be a "Proxy Program" if it meets both conditions:
+- It is specially designed to be used with Vitastor. Basically, it means that the program
+  has any functionality specific to Vitastor and thus "knows" that it works with Vitastor,
+  not with something random.
+- It interacts with Vitastor directly or indirectly through any programming interface,
+  including API, CLI, network or any wrapper (also considered a Proxy Program itself).
+
+If, in addition to that:
+- You give any user an apportunity to interact with Vitastor directly or indirectly through
+  any computer interface including the network or any number of wrappers (Proxy Programs).
+
+Then VNPL requires you to publish the code of all above Proxy Programs to all above users
+under the terms of any GPL-compatible license - that is, GPL, LGPL, MIT/BSD or Apache 2,
+because "GPL compatibility" is treated as an ability to legally include licensed code in
+a GPL application.
+
+So, if you have a "Proxy Program", but it's not open to the user who directly or indirectly
+interacts with Vitastor - you are forbidden to use Vitastor under the terms of VNPL and you
+need a commercial license which doesn't contain open-source requirements.
+
+## Examples
+
+- Vitastor Kubernetes CSI driver which creates PersistentVolumes by calling `vitastor-cli create`.
+  - Yes, it interacts with Vitastor through vitastor-cli.
+  - Yes, it is designed specially for use with Vitastor (it has no sense otherwise).
+  - So, CSI driver **definitely IS** a Proxy Program and must be published under the terms of
+    a free software license.
+- Windows, installed in a VM with the system disk on Vitastor storage.
+  - Yes, it interacts with Vitastor indirectly - it reads and writes data through the block
+    device interface, emulated by QEMU.
+  - No, it definitely isn't designed specially for use with Vitastor - Windows was created long
+    ago before Vitastor and doesn't know anything about it.
+  - So, Windows **definitely IS NOT** a Proxy Program and VNPL doesn't require to open it.
+- Cloud control panel which makes requests to Vitastor Kubernetes CSI driver.
+  - Yes, it interacts with Vitastor indirectly through the CSI driver, which is a Proxy Program.
+  - May or may not be designed specially for use with Vitastor. How to determine exactly?
+    Imagine that Vitastor is replaced with any other storage (for example, with a proprietary).
+    Do control panel functions change in any way? If they do (for example, if snapshots stop working),
+    then the panel contains specific functionality and thus is designed specially for use with Vitastor.
+    Otherwise, the panel is universal and isn't designed specially for Vitastor.
+  - So, whether you are required to open-source the panel also **depends** on whether it
+    contains specific functionality or not.
+
+## Why?
+
+Because I believe into the spirit of copyleft (Linux wouldn't become so popular without GPL!)
+and, at the same time, I want to have a way to monetize the product.
+
+Existing licenses including AGPL are useless for it with an SDS - SDS is a very deeply
+internal software which is almost definitely invisible to the user and thus AGPL doesn't
+require anyone to open the code even if they make a proprietary fork.
+
+And, in fact, the current situation in the world where GPL is though to only restrict direct
+linking of programs into a single executable file, isn't much correct. Nowadays, programs
+are more often linked with network API calls, not with /usr/bin/ld, and a software product
+may consist of dozens of microservices interacting with each other over the network.
+
+That's why we need VNPL to keep the license sufficiently copyleft.
+
+## License Texts
+
+- VNPL 1.1 in English: [VNPL-1.1.txt](../../VNPL-1.1.txt)
+- VNPL 1.1 in Russian: [VNPL-1.1-RU.txt](../../VNPL-1.1-RU.txt)
+- GPL 2.0: [GPL-2.0.txt](../../GPL-2.0.txt)

docs/intro/author.ru.md

@@ -12,6 +12,14 @@
 
 Лицензия: VNPL 1.1 на серверный код и двойная VNPL 1.1 + GPL 2.0+ на клиентский.
 
+Серверные компоненты распространяются только на условиях VNPL.
+
+Клиентские библиотеки распространяются на условиях двойной лицензии VNPL 1.0
+и также на условиях GNU GPL 2.0 или более поздней версии. Так сделано в целях
+совместимости с таким ПО, как QEMU и fio.
+
+## VNPL
+
 VNPL - "сетевой копилефт", собственная свободная копилефт-лицензия
 Vitastor Network Public License 1.1, основанная на GNU GPL 3.0 с дополнительным
 условием "Сетевого взаимодействия", требующим распространять все программы,
@@ -29,9 +37,70 @@ Vitastor Network Public License 1.1, основанная на GNU GPL 3.0 с д
 На Windows и любое другое ПО, не разработанное *специально* для использования
 вместе с Vitastor, никакие ограничения не накладываются.
 
-Клиентские библиотеки распространяются на условиях двойной лицензии VNPL 1.0
+## Пояснение
-и также на условиях GNU GPL 2.0 или более поздней версии. Так сделано в целях
-совместимости с таким ПО, как QEMU и fio.
 
-Вы можете найти полный текст VNPL 1.1 на английском языке в файле [VNPL-1.1.txt](../../VNPL-1.1.txt),
+Сетевой копилефт регулируется пунктом лицензии **13. Удалённое сетевое взаимодействие**.
-VNPL 1.1 на русском языке в файле [VNPL-1.1-RU.txt](../../VNPL-1.1-RU.txt), а GPL 2.0 в файле [GPL-2.0.txt](../../GPL-2.0.txt).
+
+Программа считается "прокси-программой", если верны оба условия:
+- Она создана специально для работы вместе с Vitastor. По сути это означает, что программа
+  должна иметь специфичный для Vitastor функционал, то есть, "знать", что она взаимодействует
+  именно с Vitastor.
+- Она прямо или косвенно взаимодействует с Vitastor через абсолютно любой программный
+  интерфейс, включая любые способы вызова: API, CLI, сеть или через какую-то обёртку (в
+  свою очередь тоже являющуюся прокси-программой).
+
+Если в дополнение к этому также:
+- Вы предоставляете любому пользователю возможность взаимодействовать с Vitastor по сети,
+  опять-таки, через любой интерфейс или любую серию "обёрток" (прокси-программ)
+
+То, согласно VNPL, вы должны открыть код "прокси-программ" **таким пользователям** на условиях
+любой GPL-совместимой лицензии - то есть, GPL, LGPL, MIT/BSD или Apache 2 - "совместимость с GPL"
+понимается как возможность включать лицензируемый код в GPL-приложение.
+
+Соответственно, если у вас есть "прокси-программа", но её код не открыт пользователю,
+который прямо или косвенно взаимодействует с Vitastor - вам запрещено использовать Vitastor
+на условиях VNPL и вам нужна коммерческая лицензия, не содержащая требований об открытии кода.
+
+## Примеры
+
+- Kubernetes CSI-драйвер Vitastor, создающий PersistentVolume с помощью вызова `vitastor-cli create`.
+  - Да, взаимодействует с Vitastor через vitastor-cli.
+  - Да, создавался специально для работы с Vitastor (иначе в чём же ещё его смысл).
+  - Значит, CSI-драйвер **точно считается** "прокси-программой" и должен быть открыт под свободной
+    лицензией.
+- Windows, установленный в виртуальную машину на диске Vitastor.
+  - Да, взаимодействует с Vitastor "прямо или косвенно" - пишет и читает данные через интерфейс
+    блочного устройства, эмулируемый QEMU.
+  - Нет, точно не создан *специально для работы с Vitastor* - когда его создавали, никакого
+    Vitastor ещё и в помине не было.
+  - Значит, Windows **точно не считается** "прокси-программой" и на него требования VNPL не распространяются.
+- Панель управления облака, делающая запросы к Kubernetes CSI-драйверу Vitastor.
+  - Да, взаимодействует с Vitastor косвенно через CSI-драйвер, являющийся "прокси-программой".
+  - Сходу не известно, создавалась ли конкретно для работы с Vitastor. Как понять, да или нет?
+    Представьте, что Vitastor заменён на любую другую систему хранения (например, на проприетарную).
+    Работа панели управления изменится? Если да (например, перестанут работать снапшоты) - значит,
+    панель содержит специфичный функционал и "создана специально для работы с Vitastor".
+    Если нет - значит, специфичного функционала панель не содержит и в принципе она универсальна.
+  - Нужно ли открывать панель - **зависит** от того, содержит она специфичный функционал или нет.
+
+## Почему так?
+
+Потому что я одновременно верю в дух копилефт-лицензий (Linux не стал бы так популярен,
+если бы не GPL!) и хочу иметь возможность монетизации продукта.
+
+При этом использовать даже AGPL для программной СХД бессмысленно - это глубоко внутреннее
+ПО, которое пользователь почти наверняка не увидит вообще, поэтому и открывать код никому
+никогда не придётся, даже при создании производного продукта.
+
+Да и в целом сложившаяся в мире ситуация, при которой действие GPL ограничивается только
+прямым связыванием в один исполняемый файл, не очень корректна. В настоящее время программы
+гораздо чаще интегрируют сетевыми вызовами, а не с помощью /usr/bin/ld, и общий программный
+продукт может состоять из нескольких десятков микросервисов, взаимодействующих по сети.
+
+Поэтому для сохранения достаточной "копилефтности" и придумана VNPL.
+
+## Тексты лицензий
+
+- VNPL 1.1 на английском языке: [VNPL-1.1.txt](../../VNPL-1.1.txt)
+- VNPL 1.1 на русском языке: [VNPL-1.1-RU.txt](../../VNPL-1.1-RU.txt)
+- GPL 2.0: [GPL-2.0.txt](../../GPL-2.0.txt)

mon/mon.js

@@ -96,6 +96,7 @@ class Mon
                     }
                     else
                     {
+                        res.setHeader('Content-Type', 'text/plain; version=0.0.4; charset=utf-8');
                         res.write(export_prometheus_metrics(this.state));
                     }
                 }

mon/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vitastor-mon",
-  "version": "2.2.0",
+  "version": "2.2.3",
   "description": "Vitastor SDS monitor service",
   "main": "mon-main.js",
   "scripts": {

node-binding/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vitastor",
-  "version": "2.2.0",
+  "version": "2.2.3",
   "description": "Low-level native bindings to Vitastor client library",
   "main": "index.js",
   "keywords": [

patches/VitastorPlugin.pm

@@ -410,8 +410,8 @@ sub volume_size_info
     my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
     my ($vtype, $name, $vmid) = $class->parse_volname($volname);
     my $info = _process_list($scfg, $storeid, run_cli($scfg, [ 'ls', $prefix.$name ]))->[0];
-    #return wantarray ? ($size, $format, $used, $parent, $st->ctime) : $size;
+    # (size, format, used, parent, ctime)
-    return $info->{size};
+    return wantarray ? ($info->{size}, $info->{format}, $info->{size}, $info->{parent}, 0) : $info->{size};
 }
 
 sub volume_resize

patches/cinder-vitastor.py

@@ -50,7 +50,7 @@ from cinder.volume import configuration
 from cinder.volume import driver
 from cinder.volume import volume_utils
 
-VITASTOR_VERSION = '2.2.0'
+VITASTOR_VERSION = '2.2.3'
 
 LOG = logging.getLogger(__name__)
 

patches/libvirt-11.5-vitastor.diff

@@ -0,0 +1,637 @@
+diff --git a/include/libvirt/libvirt-storage.h b/include/libvirt/libvirt-storage.h
+index aaad4a3da1..5f5daa8341 100644
+--- a/include/libvirt/libvirt-storage.h
++++ b/include/libvirt/libvirt-storage.h
+@@ -326,6 +326,7 @@ typedef enum {
+     VIR_CONNECT_LIST_STORAGE_POOLS_ZFS           = 1 << 17, /* (Since: 1.2.8) */
+     VIR_CONNECT_LIST_STORAGE_POOLS_VSTORAGE      = 1 << 18, /* (Since: 3.1.0) */
+     VIR_CONNECT_LIST_STORAGE_POOLS_ISCSI_DIRECT  = 1 << 19, /* (Since: 5.6.0) */
++    VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR      = 1 << 20, /* (Since: 5.0.0) */
+ } virConnectListAllStoragePoolsFlags;
+ 
+ int                     virConnectListAllStoragePools(virConnectPtr conn,
+diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c
+index 1e24e41a48..ce359a4cf8 100644
+--- a/src/conf/domain_conf.c
++++ b/src/conf/domain_conf.c
+@@ -7435,7 +7435,8 @@ 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)
+@@ -31871,6 +31872,7 @@ 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 b28af7fa56..d1aae6e43e 100644
+--- a/src/conf/domain_validate.c
++++ b/src/conf/domain_validate.c
+@@ -504,6 +504,7 @@ 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:
+@@ -576,7 +577,7 @@ 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) {
+@@ -584,10 +585,14 @@ virDomainDiskDefValidateSourceChainOne(const virStorageSource *src)
+                            _("<snapshot> element is currently supported only with 'rbd' disks"));
+             return -1;
+         }
+-
++    }
++    /* config files are currently supported only with rbd and vitastor: */
++    if (virStorageSourceGetActualType(src) != VIR_STORAGE_TYPE_NETWORK &&
++        src->protocol != VIR_STORAGE_NET_PROTOCOL_RBD &&
++        src->protocol != VIR_STORAGE_NET_PROTOCOL_VITASTOR) {
+         if (src->configFile) {
+             virReportError(VIR_ERR_XML_ERROR, "%s",
+-                           _("<config> element is currently supported only with 'rbd' disks"));
++                           _("<config> element is currently supported only with 'rbd' and 'vitastor' disks"));
+             return -1;
+         }
+     }
+diff --git a/src/conf/schemas/domaincommon.rng b/src/conf/schemas/domaincommon.rng
+index 183dd5db5e..dcc0d1a778 100644
+--- a/src/conf/schemas/domaincommon.rng
++++ b/src/conf/schemas/domaincommon.rng
+@@ -2066,6 +2066,35 @@
+     </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">
+@@ -2416,6 +2445,7 @@
+       <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 1dc9365bf2..a8a736be81 100644
+--- a/src/conf/storage_conf.c
++++ b/src/conf/storage_conf.c
+@@ -56,7 +56,7 @@ VIR_ENUM_IMPL(virStoragePool,
+               "logical", "disk", "iscsi",
+               "iscsi-direct", "scsi", "mpath",
+               "rbd", "sheepdog", "gluster",
+-              "zfs", "vstorage",
++              "zfs", "vstorage", "vitastor",
+ );
+ 
+ VIR_ENUM_IMPL(virStoragePoolFormatFileSystem,
+@@ -242,6 +242,18 @@ static virStoragePoolTypeInfo poolTypeInfo[] = {
+           .formatToString = virStorageFileFormatTypeToString,
+       }
+     },
++    {.poolType = VIR_STORAGE_POOL_VITASTOR,
++     .poolOptions = {
++         .flags = (VIR_STORAGE_POOL_SOURCE_HOST |
++                   VIR_STORAGE_POOL_SOURCE_NETWORK |
++                   VIR_STORAGE_POOL_SOURCE_NAME),
++      },
++      .volOptions = {
++          .defaultFormat = VIR_STORAGE_FILE_RAW,
++          .formatFromString = virStorageVolumeFormatFromString,
++          .formatToString = virStorageFileFormatTypeToString,
++      }
++    },
+     {.poolType = VIR_STORAGE_POOL_SHEEPDOG,
+      .poolOptions = {
+          .flags = (VIR_STORAGE_POOL_SOURCE_HOST |
+@@ -538,6 +550,11 @@ virStoragePoolDefParseSource(xmlXPathContextPtr ctxt,
+                        _("element 'name' is mandatory for RBD pool"));
+         return -1;
+     }
++    if (pool_type == VIR_STORAGE_POOL_VITASTOR && source->name == NULL) {
++        virReportError(VIR_ERR_XML_ERROR, "%s",
++                       _("element 'name' is mandatory for Vitastor pool"));
++        return -1;
++    }
+ 
+     if (options->formatFromString) {
+         g_autofree char *format = NULL;
+@@ -1127,6 +1144,7 @@ virStoragePoolDefFormatBuf(virBuffer *buf,
+     /* RBD, Sheepdog, Gluster and Iscsi-direct devices are not local block devs nor
+      * files, so they don't have a target */
+     if (def->type != VIR_STORAGE_POOL_RBD &&
++        def->type != VIR_STORAGE_POOL_VITASTOR &&
+         def->type != VIR_STORAGE_POOL_SHEEPDOG &&
+         def->type != VIR_STORAGE_POOL_GLUSTER &&
+         def->type != VIR_STORAGE_POOL_ISCSI_DIRECT) {
+diff --git a/src/conf/storage_conf.h b/src/conf/storage_conf.h
+index fc67957cfe..720c07ef74 100644
+--- a/src/conf/storage_conf.h
++++ b/src/conf/storage_conf.h
+@@ -103,6 +103,7 @@ typedef enum {
+     VIR_STORAGE_POOL_GLUSTER,  /* Gluster device */
+     VIR_STORAGE_POOL_ZFS,      /* ZFS */
+     VIR_STORAGE_POOL_VSTORAGE, /* Virtuozzo Storage */
++    VIR_STORAGE_POOL_VITASTOR, /* Vitastor */
+ 
+     VIR_STORAGE_POOL_LAST,
+ } virStoragePoolType;
+@@ -454,6 +455,7 @@ VIR_ENUM_DECL(virStoragePartedFs);
+                  VIR_CONNECT_LIST_STORAGE_POOLS_SCSI     | \
+                  VIR_CONNECT_LIST_STORAGE_POOLS_MPATH    | \
+                  VIR_CONNECT_LIST_STORAGE_POOLS_RBD      | \
++                 VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR | \
+                  VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG | \
+                  VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER  | \
+                  VIR_CONNECT_LIST_STORAGE_POOLS_ZFS      | \
+diff --git a/src/conf/storage_source_conf.c b/src/conf/storage_source_conf.c
+index 8a063be244..dd9c7f11a2 100644
+--- a/src/conf/storage_source_conf.c
++++ b/src/conf/storage_source_conf.c
+@@ -89,6 +89,7 @@ VIR_ENUM_IMPL(virStorageNetProtocol,
+               "ssh",
+               "vxhs",
+               "nfs",
++              "vitastor",
+ );
+ 
+ 
+@@ -1314,6 +1315,7 @@ 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 ebddf28cd6..873a2be65c 100644
+--- a/src/conf/storage_source_conf.h
++++ b/src/conf/storage_source_conf.h
+@@ -130,6 +130,7 @@ typedef enum {
+     VIR_STORAGE_NET_PROTOCOL_SSH,
+     VIR_STORAGE_NET_PROTOCOL_VXHS,
+     VIR_STORAGE_NET_PROTOCOL_NFS,
++    VIR_STORAGE_NET_PROTOCOL_VITASTOR,
+ 
+     VIR_STORAGE_NET_PROTOCOL_LAST
+ } virStorageNetProtocol;
+diff --git a/src/conf/virstorageobj.c b/src/conf/virstorageobj.c
+index 59fa5da372..4739167f5f 100644
+--- a/src/conf/virstorageobj.c
++++ b/src/conf/virstorageobj.c
+@@ -1438,6 +1438,7 @@ virStoragePoolObjSourceFindDuplicateCb(const void *payload,
+             return 1;
+         break;
+ 
++    case VIR_STORAGE_POOL_VITASTOR:
+     case VIR_STORAGE_POOL_ISCSI_DIRECT:
+     case VIR_STORAGE_POOL_RBD:
+     case VIR_STORAGE_POOL_LAST:
+@@ -1921,6 +1922,8 @@ virStoragePoolObjMatch(virStoragePoolObj *obj,
+                (obj->def->type == VIR_STORAGE_POOL_MPATH))   ||
+               (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_RBD) &&
+                (obj->def->type == VIR_STORAGE_POOL_RBD))     ||
++              (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR) &&
++               (obj->def->type == VIR_STORAGE_POOL_VITASTOR)) ||
+               (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG) &&
+                (obj->def->type == VIR_STORAGE_POOL_SHEEPDOG)) ||
+               (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER) &&
+diff --git a/src/libvirt-storage.c b/src/libvirt-storage.c
+index db7660aac4..561df34709 100644
+--- a/src/libvirt-storage.c
++++ b/src/libvirt-storage.c
+@@ -94,6 +94,7 @@ virStoragePoolGetConnect(virStoragePoolPtr pool)
+  * VIR_CONNECT_LIST_STORAGE_POOLS_SCSI
+  * VIR_CONNECT_LIST_STORAGE_POOLS_MPATH
+  * VIR_CONNECT_LIST_STORAGE_POOLS_RBD
++ * VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR
+  * VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG
+  * VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER
+  * VIR_CONNECT_LIST_STORAGE_POOLS_ZFS
+diff --git a/src/libxl/libxl_conf.c b/src/libxl/libxl_conf.c
+index bdd30dd65a..5353e00b4a 100644
+--- a/src/libxl/libxl_conf.c
++++ b/src/libxl/libxl_conf.c
+@@ -1081,6 +1081,7 @@ 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 ec8de30c01..61eab9606d 100644
+--- a/src/libxl/xen_xl.c
++++ b/src/libxl/xen_xl.c
+@@ -1461,6 +1461,7 @@ 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 32568d4ae6..e625fa0720 100644
+--- a/src/qemu/qemu_block.c
++++ b/src/qemu/qemu_block.c
+@@ -731,6 +731,38 @@ 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 *
+ qemuBlockStorageSourceGetSshProps(virStorageSource *src)
+ {
+@@ -1082,6 +1114,12 @@ 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_SSH:
+             driver = "ssh";
+             if (!(fileprops = qemuBlockStorageSourceGetSshProps(src)))
+@@ -1985,6 +2023,7 @@ 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:
+@@ -2365,6 +2404,12 @@ 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_SSH:
+             if (srcPriv->nbdkitProcess) {
+                 /* disk creation not yet supported with nbdkit, and even if it
+diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c
+index 0d2548d8d4..91121d6e1f 100644
+--- a/src/qemu/qemu_domain.c
++++ b/src/qemu/qemu_domain.c
+@@ -4526,7 +4526,8 @@ 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;
+@@ -8954,6 +8955,7 @@ 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 8128154749..afb339b9b0 100644
+--- a/src/qemu/qemu_snapshot.c
++++ b/src/qemu/qemu_snapshot.c
+@@ -662,6 +662,7 @@ 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:
+@@ -887,6 +888,7 @@ 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 e19e032427..59f91f4710 100644
+--- a/src/storage/storage_driver.c
++++ b/src/storage/storage_driver.c
+@@ -1626,6 +1626,7 @@ storageVolLookupByPathCallback(virStoragePoolObj *obj,
+ 
+         case VIR_STORAGE_POOL_GLUSTER:
+         case VIR_STORAGE_POOL_RBD:
++        case VIR_STORAGE_POOL_VITASTOR:
+         case VIR_STORAGE_POOL_SHEEPDOG:
+         case VIR_STORAGE_POOL_ZFS:
+         case VIR_STORAGE_POOL_LAST:
+diff --git a/src/storage_file/storage_source_backingstore.c b/src/storage_file/storage_source_backingstore.c
+index 80681924ea..8a3ade9ec0 100644
+--- a/src/storage_file/storage_source_backingstore.c
++++ b/src/storage_file/storage_source_backingstore.c
+@@ -287,6 +287,75 @@ virStorageSourceParseRBDColonString(const char *rbdstr,
+ }
+ 
+ 
++static int
++virStorageSourceParseVitastorColonString(const char *colonstr,
++                                         virStorageSource *src)
++{
++    char *p, *e, *next;
++    g_autofree char *options = NULL;
++
++    /* optionally skip the "vitastor:" prefix if provided */
++    if (STRPREFIX(colonstr, "vitastor:"))
++        colonstr += strlen("vitastor:");
++
++    options = g_strdup(colonstr);
++
++    p = options;
++    while (*p) {
++        /* find : delimiter or end of string */
++        for (e = p; *e && *e != ':'; ++e) {
++            if (*e == '\\') {
++                e++;
++                if (*e == '\0')
++                    break;
++            }
++        }
++        if (*e == '\0') {
++            next = e;    /* last kv pair */
++        } else {
++            next = e + 1;
++            *e = '\0';
++        }
++
++        if (STRPREFIX(p, "image=")) {
++            src->path = g_strdup(p + strlen("image="));
++        } else if (STRPREFIX(p, "etcd-prefix=")) {
++            src->query = g_strdup(p + strlen("etcd-prefix="));
++        } else if (STRPREFIX(p, "config-path=")) {
++            src->configFile = g_strdup(p + strlen("config-path="));
++        } else if (STRPREFIX(p, "etcd-host=")) {
++            char *h, *sep;
++
++            h = p + strlen("etcd-host=");
++            while (h < e) {
++                for (sep = h; sep < e; ++sep) {
++                    if (*sep == '\\' && (sep[1] == ',' ||
++                                         sep[1] == ';' ||
++                                         sep[1] == ' ')) {
++                        *sep = '\0';
++                        sep += 2;
++                        break;
++                    }
++                }
++
++                if (virStorageSourceRBDAddHost(src, h) < 0)
++                    return -1;
++
++                h = sep;
++            }
++        }
++
++        p = next;
++    }
++
++    if (!src->path) {
++        return -1;
++    }
++
++    return 0;
++}
++
++
+ static int
+ virStorageSourceParseNBDColonString(const char *nbdstr,
+                                     virStorageSource *src)
+@@ -399,6 +468,11 @@ virStorageSourceParseBackingColon(virStorageSource *src,
+             return -1;
+         break;
+ 
++    case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
++        if (virStorageSourceParseVitastorColonString(path, src) < 0)
++            return -1;
++        break;
++
+     case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
+     case VIR_STORAGE_NET_PROTOCOL_LAST:
+     case VIR_STORAGE_NET_PROTOCOL_NONE:
+@@ -975,6 +1049,54 @@ virStorageSourceParseBackingJSONRBD(virStorageSource *src,
+     return 0;
+ }
+ 
++static int
++virStorageSourceParseBackingJSONVitastor(virStorageSource *src,
++                                         virJSONValue *json,
++                                         const char *jsonstr G_GNUC_UNUSED,
++                                         int opaque G_GNUC_UNUSED)
++{
++    const char *filename;
++    const char *image = virJSONValueObjectGetString(json, "image");
++    const char *conf = virJSONValueObjectGetString(json, "config-path");
++    const char *etcd_prefix = virJSONValueObjectGetString(json, "etcd-prefix");
++    virJSONValue *servers = virJSONValueObjectGetArray(json, "server");
++    size_t nservers;
++    size_t i;
++
++    src->type = VIR_STORAGE_TYPE_NETWORK;
++    src->protocol = VIR_STORAGE_NET_PROTOCOL_VITASTOR;
++
++    /* legacy syntax passed via 'filename' option */
++    if ((filename = virJSONValueObjectGetString(json, "filename")))
++        return virStorageSourceParseVitastorColonString(filename, src);
++
++    if (!image) {
++        virReportError(VIR_ERR_INVALID_ARG, "%s",
++                       _("missing image name in Vitastor backing volume "
++                         "JSON specification"));
++        return -1;
++    }
++
++    src->path = g_strdup(image);
++    src->configFile = g_strdup(conf);
++    src->query = g_strdup(etcd_prefix);
++
++    if (servers) {
++        nservers = virJSONValueArraySize(servers);
++
++        src->hosts = g_new0(virStorageNetHostDef, nservers);
++        src->nhosts = nservers;
++
++        for (i = 0; i < nservers; i++) {
++            if (virStorageSourceParseBackingJSONInetSocketAddress(src->hosts + i,
++                                                                  virJSONValueArrayGet(servers, i)) < 0)
++                return -1;
++        }
++    }
++
++    return 0;
++}
++
+ static int
+ virStorageSourceParseBackingJSONRaw(virStorageSource *src,
+                                     virJSONValue *json,
+@@ -1152,6 +1274,7 @@ static const struct virStorageSourceJSONDriverParser jsonParsers[] = {
+     {"sheepdog", false, virStorageSourceParseBackingJSONSheepdog, 0},
+     {"ssh", false, virStorageSourceParseBackingJSONSSH, 0},
+     {"rbd", false, virStorageSourceParseBackingJSONRBD, 0},
++    {"vitastor", false, virStorageSourceParseBackingJSONVitastor, 0},
+     {"raw", true, virStorageSourceParseBackingJSONRaw, 0},
+     {"nfs", false, virStorageSourceParseBackingJSONNFS, 0},
+     {"vxhs", false, virStorageSourceParseBackingJSONVxHS, 0},
+diff --git a/src/test/test_driver.c b/src/test/test_driver.c
+index 25335d9002..cf54069fbe 100644
+--- a/src/test/test_driver.c
++++ b/src/test/test_driver.c
+@@ -7340,6 +7340,7 @@ testStorageVolumeTypeForPool(int pooltype)
+     case VIR_STORAGE_POOL_ISCSI_DIRECT:
+     case VIR_STORAGE_POOL_GLUSTER:
+     case VIR_STORAGE_POOL_RBD:
++    case VIR_STORAGE_POOL_VITASTOR:
+         return VIR_STORAGE_VOL_NETWORK;
+     case VIR_STORAGE_POOL_LOGICAL:
+     case VIR_STORAGE_POOL_DISK:
+diff --git a/tests/storagepoolcapsschemadata/poolcaps-fs.xml b/tests/storagepoolcapsschemadata/poolcaps-fs.xml
+index eee75af746..8bd0a57bdd 100644
+--- a/tests/storagepoolcapsschemadata/poolcaps-fs.xml
++++ b/tests/storagepoolcapsschemadata/poolcaps-fs.xml
+@@ -204,4 +204,11 @@
+       </enum>
+     </volOptions>
+   </pool>
++  <pool type='vitastor' supported='no'>
++    <volOptions>
++      <defaultFormat type='raw'/>
++      <enum name='targetFormatType'>
++      </enum>
++    </volOptions>
++  </pool>
+ </storagepoolCapabilities>
+diff --git a/tests/storagepoolcapsschemadata/poolcaps-full.xml b/tests/storagepoolcapsschemadata/poolcaps-full.xml
+index 805950a937..852df0de16 100644
+--- a/tests/storagepoolcapsschemadata/poolcaps-full.xml
++++ b/tests/storagepoolcapsschemadata/poolcaps-full.xml
+@@ -204,4 +204,11 @@
+       </enum>
+     </volOptions>
+   </pool>
++  <pool type='vitastor' supported='yes'>
++    <volOptions>
++      <defaultFormat type='raw'/>
++      <enum name='targetFormatType'>
++      </enum>
++    </volOptions>
++  </pool>
+ </storagepoolCapabilities>
+diff --git a/tests/storagepoolxml2argvtest.c b/tests/storagepoolxml2argvtest.c
+index d5c2531ab8..b19308ac38 100644
+--- a/tests/storagepoolxml2argvtest.c
++++ b/tests/storagepoolxml2argvtest.c
+@@ -57,6 +57,7 @@ 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 2010ef1356..072e2ff9e8 100644
+--- a/tools/virsh-pool.c
++++ b/tools/virsh-pool.c
+@@ -1187,6 +1187,9 @@ cmdPoolList(vshControl *ctl, const vshCmd *cmd G_GNUC_UNUSED)
+             case VIR_STORAGE_POOL_VSTORAGE:
+                 flags |= VIR_CONNECT_LIST_STORAGE_POOLS_VSTORAGE;
+                 break;
++            case VIR_STORAGE_POOL_VITASTOR:
++                flags |= VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR;
++                break;
+             case VIR_STORAGE_POOL_LAST:
+                 break;
+             }

rpm/build-tarball.sh

@@ -7,22 +7,24 @@ set -e
 VITASTOR=$(dirname $0)
 VITASTOR=$(realpath "$VITASTOR/..")
 
-EL=$(rpm --eval '%dist')
+REL=$(rpm --eval '%dist')
-if [ "$EL" = ".el8" ]; then
+REL=${REL##.}
+if [ "$REL" = "el8" ]; then
     # CentOS 8
     . /opt/rh/gcc-toolset-9/enable
-elif [ "$EL" = ".el7" ]; then
+elif [ "$REL" = "el7" ]; then
     # CentOS 7
     . /opt/rh/devtoolset-9/enable
 fi
 cd ~/rpmbuild/SPECS
 rpmbuild -bp fio.spec
 cd $VITASTOR
-VER=$(grep ^Version: rpm/vitastor-el7.spec | awk '{print $2}')
+VER=$(grep ^Version: rpm/vitastor-$REL.spec | awk '{print $2}')
+rm -rf fio
 ln -s ~/rpmbuild/BUILD/fio*/ fio
 sh copy-fio-includes.sh
 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
+perl -i -pe 's/(Requires:\s*fio)([^\n]+)?/$1 = '$FIO'/' $VITASTOR/rpm/vitastor-$REL.spec
-tar --transform "s#^#vitastor-$VER/#" --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-$VER$(rpm --eval '%dist').tar.gz *
+tar --transform "s#^#vitastor-$VER/#" --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-$VER.$REL.tar.gz $(ls | grep -v packages)

rpm/vitastor-build.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+set -e -x
+REL=$(rpm --eval '%dist')
+REL=${REL##.}
+cd /root/vitastor/rpm
+./build-tarball.sh
+VER=$(grep ^Version: vitastor-$REL.spec | awk '{print $2}')
+cp /root/vitastor-$VER.$REL.tar.gz ~/rpmbuild/SOURCES
+cp vitastor-$REL.spec ~/rpmbuild/SPECS/vitastor.spec
+cd ~/rpmbuild/SPECS/
+rpmbuild -ba vitastor.spec
+mkdir -p /root/vitastor/packages/vitastor-$REL
+rm -rf /root/vitastor/packages/vitastor-$REL/*
+cp ~/rpmbuild/RPMS/*/*vitastor* /root/vitastor/packages/vitastor-$REL/
+cp ~/rpmbuild/SRPMS/vitastor* /root/vitastor/packages/vitastor-$REL/

rpm/vitastor-el7.Dockerfile

@@ -1,5 +1,8 @@
 # Build packages for CentOS 7 inside a container
-# cd ..; podman build -t vitastor-el7 -v `pwd`/packages:/root/packages -f rpm/vitastor-el7.Dockerfile .
+# cd ..
+# docker build -t vitastor-buildenv:el7 -f rpm/vitastor-el7.Dockerfile .
+# docker run -i --rm -v ./:/root/vitastor vitastor-buildenv:el7 /root/vitastor/rpm/vitastor-build.sh
+
 # localedef -i ru_RU -f UTF-8 ru_RU.UTF-8
 
 FROM centos:7
@@ -7,7 +10,9 @@ FROM centos:7
 WORKDIR /root
 
 RUN rm -f /etc/yum.repos.d/CentOS-Media.repo
+RUN sed -i 's/^mirrorlist=/#mirrorlist=/; s!#baseurl=http://mirror.centos.org/centos/\$releasever!baseurl=http://vault.centos.org/7.9.2009!' /etc/yum.repos.d/*.repo
 RUN yum -y --enablerepo=extras install centos-release-scl epel-release yum-utils rpm-build
+RUN perl -i -pe 's!mirrorlist=!#mirrorlist=!s; s!#\s*baseurl=http://mirror.centos.org!baseurl=http://vault.centos.org!' /etc/yum.repos.d/CentOS-SCLo-scl*.repo
 RUN yum -y install https://vitastor.io/rpms/centos/7/vitastor-release-1.0-1.el7.noarch.rpm
 RUN yum -y install devtoolset-9-gcc-c++ devtoolset-9-libatomic-devel gcc make cmake gperftools-devel \
     fio rh-nodejs12 jerasure-devel libisa-l-devel gf-complete-devel rdma-core-devel libnl3-devel
@@ -30,18 +35,3 @@ RUN set -e; \
     cp ~/rpmbuild/SRPMS/liburing* /root/packages/liburing-el7/
 
 RUN rpm -i `ls /root/packages/liburing-el7/liburing-*.x86_64.rpm | grep -v debug`
-
-ADD . /root/vitastor
-
-RUN set -e; \
-    cd /root/vitastor/rpm; \
-    sh build-tarball.sh; \
-    VER=$(grep ^Version: vitastor-el7.spec | awk '{print $2}'); \
-    cp /root/vitastor-$VER.el7.tar.gz ~/rpmbuild/SOURCES; \
-    cp vitastor-el7.spec ~/rpmbuild/SPECS/vitastor.spec; \
-    cd ~/rpmbuild/SPECS/; \
-    rpmbuild -ba vitastor.spec; \
-    mkdir -p /root/packages/vitastor-el7; \
-    rm -rf /root/packages/vitastor-el7/*; \
-    cp ~/rpmbuild/RPMS/*/*vitastor* /root/packages/vitastor-el7/; \
-    cp ~/rpmbuild/SRPMS/vitastor* /root/packages/vitastor-el7/

rpm/vitastor-el7.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        2.2.0
+Version:        2.2.3
 Release:        1%{?dist}
 Summary:        Vitastor, a fast software-defined clustered block storage
 
 License:        Vitastor Network Public License 1.1
 URL:            https://vitastor.io/
-Source0:        vitastor-2.2.0.el7.tar.gz
+Source0:        vitastor-2.2.3.el7.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel
@@ -82,7 +82,7 @@ Vitastor library headers for development.
 Summary:        Vitastor - fio drivers
 Group:          Development/Libraries
 Requires:       vitastor-client = %{version}-%{release}
-Requires:       fio = 3.7-1.el7
+Requires:       fio = 3.7-2.el7
 
 
 %description -n vitastor-fio

rpm/vitastor-el8.Dockerfile

@@ -1,5 +1,7 @@
 # Build packages for CentOS 8 inside a container
-# cd ..; podman build -t vitastor-el8 -v `pwd`/packages:/root/packages -f rpm/vitastor-el8.Dockerfile .
+# cd ..
+# docker build -t vitastor-buildenv:el8 -f rpm/vitastor-el8.Dockerfile .
+# docker run -i --rm -v ./:/root/vitastor vitastor-buildenv:el8 /root/vitastor/rpm/vitastor-build.sh
 
 FROM centos:8
 
@@ -29,18 +31,3 @@ RUN set -e; \
     cp ~/rpmbuild/SRPMS/liburing* /root/packages/liburing-el8/
 
 RUN rpm -i `ls /root/packages/liburing-el8/liburing-*.x86_64.rpm | grep -v debug`
-
-ADD . /root/vitastor
-
-RUN set -e; \
-    cd /root/vitastor/rpm; \
-    sh build-tarball.sh; \
-    VER=$(grep ^Version: vitastor-el8.spec | awk '{print $2}'); \
-    cp /root/vitastor-$VER.el8.tar.gz ~/rpmbuild/SOURCES; \
-    cp vitastor-el8.spec ~/rpmbuild/SPECS/vitastor.spec; \
-    cd ~/rpmbuild/SPECS/; \
-    rpmbuild -ba vitastor.spec; \
-    mkdir -p /root/packages/vitastor-el8; \
-    rm -rf /root/packages/vitastor-el8/*; \
-    cp ~/rpmbuild/RPMS/*/*vitastor* /root/packages/vitastor-el8/; \
-    cp ~/rpmbuild/SRPMS/vitastor* /root/packages/vitastor-el8/

rpm/vitastor-el8.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        2.2.0
+Version:        2.2.3
 Release:        1%{?dist}
 Summary:        Vitastor, a fast software-defined clustered block storage
 
 License:        Vitastor Network Public License 1.1
 URL:            https://vitastor.io/
-Source0:        vitastor-2.2.0.el8.tar.gz
+Source0:        vitastor-2.2.3.el8.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel
@@ -80,7 +80,7 @@ Vitastor library headers for development.
 Summary:        Vitastor - fio drivers
 Group:          Development/Libraries
 Requires:       vitastor-client = %{version}-%{release}
-Requires:       fio = 3.7-3.el8
+Requires:       fio = 3.19-3.el8
 
 
 %description -n vitastor-fio

rpm/vitastor-el9.Dockerfile

@@ -1,5 +1,7 @@
 # Build packages for AlmaLinux 9 inside a container
-# cd ..; podman build -t vitastor-el9 -v `pwd`/packages:/root/packages -f rpm/vitastor-el9.Dockerfile .
+# cd ..
+# docker build -t vitastor-buildenv:el9 -f rpm/vitastor-el9.Dockerfile .
+# docker run -i --rm -v ./:/root/vitastor vitastor-buildenv:el9 /root/vitastor/rpm/vitastor-build.sh
 
 FROM almalinux:9
 
@@ -12,18 +14,3 @@ RUN dnf -y install gcc-c++ gperftools-devel fio nodejs rpm-build jerasure-devel
 RUN dnf download --source fio
 RUN rpm --nomd5 -i fio*.src.rpm
 RUN cd ~/rpmbuild/SPECS && dnf builddep -y --spec fio.spec
-
-ADD . /root/vitastor
-
-RUN set -e; \
-    cd /root/vitastor/rpm; \
-    sh build-tarball.sh; \
-    VER=$(grep ^Version: vitastor-el9.spec | awk '{print $2}'); \
-    cp /root/vitastor-$VER.el9.tar.gz ~/rpmbuild/SOURCES; \
-    cp vitastor-el9.spec ~/rpmbuild/SPECS/vitastor.spec; \
-    cd ~/rpmbuild/SPECS/; \
-    rpmbuild -ba vitastor.spec; \
-    mkdir -p /root/packages/vitastor-el9; \
-    rm -rf /root/packages/vitastor-el9/*; \
-    cp ~/rpmbuild/RPMS/*/*vitastor* /root/packages/vitastor-el9/; \
-    cp ~/rpmbuild/SRPMS/vitastor* /root/packages/vitastor-el9/

rpm/vitastor-el9.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        2.2.0
+Version:        2.2.3
 Release:        1%{?dist}
 Summary:        Vitastor, a fast software-defined clustered block storage
 
 License:        Vitastor Network Public License 1.1
 URL:            https://vitastor.io/
-Source0:        vitastor-2.2.0.el9.tar.gz
+Source0:        vitastor-2.2.3.el9.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

src/CMakeLists.txt

@@ -19,7 +19,7 @@ if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
 	set(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
 endif()
 
-add_definitions(-DVITASTOR_VERSION="2.2.0")
+add_definitions(-DVITASTOR_VERSION="2.2.3")
 add_definitions(-D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -Wall -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith -fdiagnostics-color=always -fno-omit-frame-pointer -I ${CMAKE_SOURCE_DIR}/src)
 add_link_options(-fno-omit-frame-pointer)
 if (${WITH_ASAN})

src/blockstore/blockstore.h

@@ -42,8 +42,7 @@
 #define BS_OP_DELETE 6
 #define BS_OP_LIST 7
 #define BS_OP_ROLLBACK 8
-#define BS_OP_SYNC_STAB_ALL 9
+#define BS_OP_MAX 8
-#define BS_OP_MAX 9
 
 #define BS_OP_PRIVATE_DATA_SIZE 256
 
@@ -113,14 +112,6 @@ Input:
 Output:
 - retval = 0 or negative error number (-ENOENT if no such version for stabilize)
 
-## BS_OP_SYNC_STAB_ALL
-
-ONLY FOR TESTS! Sync and mark all unstable object versions as stable, at once.
-
-Input: Nothing except opcode
-Output:
-- retval = 0 or negative error number (-EINVAL)
-
 ## BS_OP_LIST
 
 Get a list of all objects in this Blockstore.
@@ -147,7 +138,7 @@ Output:
 struct blockstore_op_t
 {
     // operation
-    uint64_t opcode;
+    uint64_t opcode = 0;
     // finish callback
     std::function<void (blockstore_op_t*)> callback;
     union __attribute__((__packed__))
@@ -171,9 +162,9 @@ struct blockstore_op_t
             uint32_t list_stable_limit;
         };
     };
-    void *buf;
+    void *buf = NULL;
-    void *bitmap;
+    void *bitmap = NULL;
-    int retval;
+    int retval = 0;
 
     uint8_t private_data[BS_OP_PRIVATE_DATA_SIZE];
 };

src/blockstore/blockstore_impl.cpp

@@ -343,44 +343,6 @@ void blockstore_impl_t::enqueue_op(blockstore_op_t *op)
         ringloop->set_immediate([op]() { std::function<void (blockstore_op_t*)>(op->callback)(op); });
         return;
     }
-    if (op->opcode == BS_OP_SYNC_STAB_ALL)
-    {
-        std::function<void(blockstore_op_t*)> *old_callback = new std::function<void(blockstore_op_t*)>(op->callback);
-        op->opcode = BS_OP_SYNC;
-        op->callback = [this, old_callback](blockstore_op_t *op)
-        {
-            if (op->retval >= 0 && unstable_writes.size() > 0)
-            {
-                op->opcode = BS_OP_STABLE;
-                op->len = unstable_writes.size();
-                obj_ver_id *vers = new obj_ver_id[op->len];
-                op->buf = vers;
-                int i = 0;
-                for (auto it = unstable_writes.begin(); it != unstable_writes.end(); it++, i++)
-                {
-                    vers[i] = {
-                        .oid = it->first,
-                        .version = it->second,
-                    };
-                }
-                unstable_writes.clear();
-                op->callback = [old_callback](blockstore_op_t *op)
-                {
-                    obj_ver_id *vers = (obj_ver_id*)op->buf;
-                    delete[] vers;
-                    op->buf = NULL;
-                    (*old_callback)(op);
-                    delete old_callback;
-                };
-                this->enqueue_op(op);
-            }
-            else
-            {
-                (*old_callback)(op);
-                delete old_callback;
-            }
-        };
-    }
     if ((op->opcode == BS_OP_WRITE || op->opcode == BS_OP_WRITE_STABLE || op->opcode == BS_OP_DELETE) && !enqueue_write(op))
     {
         ringloop->set_immediate([op]() { std::function<void (blockstore_op_t*)>(op->callback)(op); });

src/blockstore/fio_engine.cpp

@@ -5,14 +5,14 @@
 //
 // Initialize storage for tests:
 //
-// dd if=/dev/zero of=test_data.bin bs=1024 count=1048576
+// dd if=/dev/zero of=test_data.bin bs=1M count=1024
-// dd if=/dev/zero of=test_meta.bin bs=1024 count=256
-// dd if=/dev/zero of=test_journal.bin bs=1024 count=4096
 //
 // Random write:
 //
-// fio -thread -ioengine=./libfio_blockstore.so -name=test -bs=4k -direct=1 -fsync=16 -iodepth=16 -rw=randwrite \
+// [LD_PRELOAD=libasan.so.8] \
-//     -bs_config='{"data_device":"./test_data.bin"}' -size=1000M
+// fio -name=test -thread -ioengine=../build/src/blockstore/libfio_vitastor_blk.so \
+//     -bs=4k -direct=1 -rw=randwrite -iodepth=16 -size=900M -loops=10 \
+//     -bs_config='{"data_device":"./test_data.bin","meta_offset":0,"journal_offset":16777216,"data_offset":33554432,"disable_data_fsync":true,"immediate_commit":"all","journal_no_same_sector_overwrites":true}'
 //
 // Linear write:
 //
@@ -38,12 +38,14 @@ struct bs_data
     std::vector<io_u*> completed;
     int op_n = 0, inflight = 0;
     bool last_sync = false;
+    bool trace = false;
 };
 
 struct bs_options
 {
     int __pad;
     char *json_config = NULL;
+    int trace = 0;
 };
 
 static struct fio_option options[] = {
@@ -56,6 +58,16 @@ static struct fio_option options[] = {
         .category = FIO_OPT_C_ENGINE,
         .group  = FIO_OPT_G_FILENAME,
     },
+    {
+        .name   = "bs_trace",
+        .lname  = "trace",
+        .type   = FIO_OPT_BOOL,
+        .off1   = offsetof(struct bs_options, trace),
+        .help   = "Trace operations",
+        .def    = "0",
+        .category = FIO_OPT_C_ENGINE,
+        .group  = FIO_OPT_G_FILENAME,
+    },
     {
         .name = NULL,
     },
@@ -63,6 +75,7 @@ static struct fio_option options[] = {
 
 static int bs_setup(struct thread_data *td)
 {
+    bs_options *o = (bs_options*)td->eo;
     bs_data *bsd;
     //fio_file *f;
     //int r;
@@ -83,6 +96,8 @@ static int bs_setup(struct thread_data *td)
         td->o.open_files++;
     }
 
+    bsd->trace = o->trace ? true : false;
+
     //f = td->files[0];
     //f->real_file_size = size;
     return 0;
@@ -176,20 +191,19 @@ static enum fio_q_status bs_queue(struct thread_data *td, struct io_u *io)
         op->version = UINT64_MAX; // last unstable
         op->offset = io->offset % bsd->bs->get_block_size();
         op->len = io->xfer_buflen;
-        op->callback = [io](blockstore_op_t *op)
+        op->callback = [io, n = bsd->op_n](blockstore_op_t *op)
         {
             io->error = op->retval < 0 ? -op->retval : 0;
             bs_data *bsd = (bs_data*)io->engine_data;
             bsd->inflight--;
             bsd->completed.push_back(io);
-#ifdef BLOCKSTORE_DEBUG
+            if (bsd->trace)
-            printf("--- OP_READ %llx n=%d retval=%d\n", io, n, op->retval);
+                printf("--- OP_READ %zx n=%d retval=%d\n", (size_t)op, n, op->retval);
-#endif
             delete op;
         };
         break;
     case DDIR_WRITE:
-        op->opcode = BS_OP_WRITE;
+        op->opcode = BS_OP_WRITE_STABLE;
         op->buf = io->xfer_buf;
         op->oid = {
             .inode = 1,
@@ -198,30 +212,28 @@ static enum fio_q_status bs_queue(struct thread_data *td, struct io_u *io)
         op->version = 0; // assign automatically
         op->offset = io->offset % bsd->bs->get_block_size();
         op->len = io->xfer_buflen;
-        op->callback = [io](blockstore_op_t *op)
+        op->callback = [io, n = bsd->op_n](blockstore_op_t *op)
         {
             io->error = op->retval < 0 ? -op->retval : 0;
             bs_data *bsd = (bs_data*)io->engine_data;
             bsd->inflight--;
             bsd->completed.push_back(io);
-#ifdef BLOCKSTORE_DEBUG
+            if (bsd->trace)
-            printf("--- OP_WRITE %llx n=%d retval=%d\n", io, n, op->retval);
+                printf("--- OP_WRITE %zx n=%d retval=%d\n", (size_t)op, n, op->retval);
-#endif
             delete op;
         };
         bsd->last_sync = false;
         break;
     case DDIR_SYNC:
-        op->opcode = BS_OP_SYNC_STAB_ALL;
+        op->opcode = BS_OP_SYNC;
-        op->callback = [io](blockstore_op_t *op)
+        op->callback = [io, n = bsd->op_n](blockstore_op_t *op)
         {
             bs_data *bsd = (bs_data*)io->engine_data;
             io->error = op->retval < 0 ? -op->retval : 0;
             bsd->completed.push_back(io);
             bsd->inflight--;
-#ifdef BLOCKSTORE_DEBUG
+            if (bsd->trace)
-            printf("--- OP_SYNC %llx n=%d retval=%d\n", io, n, op->retval);
+                printf("--- OP_SYNC %zx n=%d retval=%d\n", (size_t)op, n, op->retval);
-#endif
             delete op;
         };
         bsd->last_sync = true;
@@ -232,9 +244,8 @@ static enum fio_q_status bs_queue(struct thread_data *td, struct io_u *io)
         return FIO_Q_COMPLETED;
     }
 
-#ifdef BLOCKSTORE_DEBUG
+    if (bsd->trace)
-    printf("+++ %s %llx n=%d\n", op->opcode == OP_READ ? "OP_READ" : (op->opcode == OP_WRITE ? "OP_WRITE" : "OP_SYNC"), io, n);
+        printf("+++ %s %zx n=%d\n", op->opcode == BS_OP_READ ? "OP_READ" : (op->opcode == BS_OP_WRITE_STABLE ? "OP_WRITE" : "OP_SYNC"), (size_t)op, bsd->op_n);
-#endif
     io->error = 0;
     bsd->inflight++;
     bsd->bs->enqueue_op(op);

src/client/cluster_client.cpp

@@ -57,6 +57,7 @@ cluster_client_t::cluster_client_t(ring_loop_t *ringloop, timerfd_manager_t *tfd
     st_cli.on_load_config_hook = [this](json11::Json::object & cfg) { on_load_config_hook(cfg); };
     st_cli.on_change_osd_state_hook = [this](uint64_t peer_osd) { on_change_osd_state_hook(peer_osd); };
     st_cli.on_change_pool_config_hook = [this]() { on_change_pool_config_hook(); };
+    st_cli.on_change_pg_config_hook = [this]() { on_change_pool_config_hook(); };
     st_cli.on_change_pg_state_hook = [this](pool_id_t pool_id, pg_num_t pg_num, osd_num_t prev_primary) { on_change_pg_state_hook(pool_id, pg_num, prev_primary); };
     st_cli.on_change_node_placement_hook = [this]() { on_change_node_placement_hook(); };
     st_cli.on_load_pgs_hook = [this](bool success) { on_load_pgs_hook(success); };
@@ -563,7 +564,7 @@ osd_num_t cluster_client_t::select_nearest_osd(const std::vector<osd_num_t> & os
 
 void cluster_client_t::on_load_pgs_hook(bool success)
 {
-    for (auto pool_item: st_cli.pool_config)
+    for (auto & pool_item: st_cli.pool_config)
     {
         pg_counts[pool_item.first] = pool_item.second.real_pg_count;
     }
@@ -583,10 +584,15 @@ void cluster_client_t::on_load_pgs_hook(bool success)
 
 void cluster_client_t::on_change_pool_config_hook()
 {
-    for (auto pool_item: st_cli.pool_config)
+    for (auto & pool_item: st_cli.pool_config)
     {
         if (pg_counts[pool_item.first] != pool_item.second.real_pg_count)
         {
+            if (log_level > 2 && pg_counts[pool_item.first])
+            {
+                printf("Pool %u (%s) PG count changed from %lu to %lu\n", pool_item.first, pool_item.second.name.c_str(),
+                    pg_counts[pool_item.first], pool_item.second.real_pg_count);
+            }
             // At this point, all pool operations should have been suspended
             // And now they have to be resliced!
             for (auto op = op_queue_head; op; op = op->next)

src/client/etcd_state_client.cpp

@@ -1056,6 +1056,10 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
             }
             pool_item.second.real_pg_count = n;
         }
+        if (on_change_pg_config_hook)
+        {
+            on_change_pg_config_hook();
+        }
     }
     else if (key.substr(0, etcd_prefix.length()+12) == etcd_prefix+"/pg/history/")
     {
@@ -1182,9 +1186,7 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
         osd_num_t peer_osd = std::stoull(key.substr(etcd_prefix.length()+11));
         if (peer_osd > 0)
         {
-            if (value.is_object() && value["state"] == "up" &&
+            if (value.is_object() && value["state"] == "up")
-                value["addresses"].is_array() &&
-                value["port"].int64_value() > 0 && value["port"].int64_value() < 65536)
             {
                 this->peer_states[peer_osd] = value;
                 this->seen_peers.insert(peer_osd);

src/client/etcd_state_client.h

@@ -142,6 +142,7 @@ public:
     std::function<json11::Json()> load_pgs_checks_hook;
     std::function<void(bool)> on_load_pgs_hook;
     std::function<void()> on_change_pool_config_hook;
+    std::function<void()> on_change_pg_config_hook;
     std::function<void(pool_id_t)> on_change_backfillfull_hook;
     std::function<void(pool_id_t, pg_num_t, osd_num_t)> on_change_pg_state_hook;
     std::function<void(pool_id_t, pg_num_t)> on_change_pg_history_hook;

src/client/messenger.cpp

@@ -188,7 +188,7 @@ void osd_messenger_t::init()
             auto cl = cl_it->second;
             cl_it++;
             auto peer_fd = cl->peer_fd;
-            if (!cl->osd_num || cl->peer_state != PEER_CONNECTED && cl->peer_state != PEER_RDMA)
+            if (!cl->osd_num && !cl->in_osd_num || cl->peer_state != PEER_CONNECTED && cl->peer_state != PEER_RDMA)
             {
                 // Do not run keepalive on regular clients
                 continue;
@@ -199,7 +199,7 @@ void osd_messenger_t::init()
                 if (!cl->ping_time_remaining)
                 {
                     // Ping timed out, stop the client
-                    fprintf(stderr, "Ping timed out for OSD %ju (client %d), disconnecting peer\n", cl->osd_num, cl->peer_fd);
+                    fprintf(stderr, "Ping timed out for OSD %ju (client %d), disconnecting peer\n", cl->in_osd_num ? cl->in_osd_num : cl->osd_num, cl->peer_fd);
                     stop_client(peer_fd, true);
                     // Restart iterator because it may be invalidated
                     cl_it = clients.upper_bound(peer_fd);
@@ -230,7 +230,7 @@ void osd_messenger_t::init()
                             return;
                         }
                         int fail_fd = (op->reply.hdr.retval != 0 ? op->peer_fd : -1);
-                        auto fail_osd_num = cl->osd_num;
+                        auto fail_osd_num = cl->in_osd_num ? cl->in_osd_num : cl->osd_num;
                         cl->ping_time_remaining = 0;
                         delete op;
                         if (fail_fd >= 0)

src/client/messenger.h

@@ -60,6 +60,7 @@ struct osd_client_t
     int ping_time_remaining = 0;
     int idle_time_remaining = 0;
     osd_num_t osd_num = 0;
+    osd_num_t in_osd_num = 0;
     bool is_incoming = false;
 
     void *in_buf = NULL;
@@ -98,6 +99,7 @@ struct osd_client_t
     std::vector<osd_op_t*> zc_free_list;
 
     ~osd_client_t();
+    void cancel_ops();
 };
 
 struct osd_wanted_peer_t
@@ -235,6 +237,7 @@ public:
     void outbox_push(osd_op_t *cur_op);
     std::function<void(osd_op_t*)> exec_op;
     std::function<void(osd_num_t)> repeer_pgs;
+    std::function<void(osd_num_t)> break_pg_locks;
     std::function<bool(osd_client_t*, json11::Json)> check_config_hook;
     void read_requests();
     void send_replies();

src/client/msgr_op.h

@@ -173,6 +173,7 @@ struct osd_op_t
     osd_op_buf_list_t iov;
 
     ~osd_op_t();
+    void cancel();
 
     bool is_recovery_related();
 };

src/client/msgr_rdmacm.cpp

@@ -510,7 +510,6 @@ void osd_messenger_t::rdmacm_established(rdma_cm_event *ev)
     rc->qp = conn->cmid->qp;
     // And an osd_client_t
     auto cl = new osd_client_t();
-    cl->is_incoming = true;
     cl->peer_addr = conn->parsed_addr;
     cl->peer_port = conn->rdmacm_port;
     cl->peer_fd = conn->peer_fd;

src/client/msgr_receive.cpp

@@ -8,11 +8,12 @@ void osd_messenger_t::read_requests()
     for (int i = 0; i < read_ready_clients.size(); i++)
     {
         int peer_fd = read_ready_clients[i];
-        osd_client_t *cl = clients[peer_fd];
+        auto cl_it = clients.find(peer_fd);
-        if (cl->read_msg.msg_iovlen)
+        if (cl_it == clients.end() || !cl_it->second || cl_it->second->read_msg.msg_iovlen)
         {
             continue;
         }
+        auto cl = cl_it->second;
         if (cl->read_remaining < receive_buffer_size)
         {
             cl->read_iov.iov_base = cl->in_buf;
@@ -33,8 +34,12 @@ void osd_messenger_t::read_requests()
             auto iothread = iothreads.size() ? iothreads[peer_fd % iothreads.size()] : NULL;
             io_uring_sqe sqe_local;
             ring_data_t data_local;
-            sqe_local.user_data = (uint64_t)&data_local;
             io_uring_sqe* sqe = (iothread ? &sqe_local : ringloop->get_sqe());
+            if (iothread)
+            {
+                sqe_local = { .user_data = (uint64_t)&data_local };
+                data_local = {};
+            }
             if (!sqe)
             {
                 cl->read_msg.msg_iovlen = 0;
@@ -56,7 +61,8 @@ void osd_messenger_t::read_requests()
             {
                 result = -errno;
             }
-            handle_read(result, cl);
+            // like set_immediate
+            tfd->set_timer_us(0, false, [this, result, cl](int){ handle_read(result, cl); });
         }
     }
     read_ready_clients.clear();
@@ -228,7 +234,7 @@ bool osd_messenger_t::handle_finished_read(osd_client_t *cl)
             {
                 if (cl->read_op->req.hdr.id != cl->read_op_id)
                 {
-                    fprintf(stderr, "Warning: operation sequencing is broken on client %d, stopping client\n", cl->peer_fd);
+                    fprintf(stderr, "Warning: operation sequencing is broken on client %d: expected num %ju, got %ju, stopping client\n", cl->peer_fd, cl->read_op_id, cl->read_op->req.hdr.id);
                     stop_client(cl->peer_fd);
                     return false;
                 }

src/client/msgr_send.cpp

@@ -194,12 +194,14 @@ bool osd_messenger_t::try_send(osd_client_t *cl)
         auto iothread = iothreads.size() ? iothreads[peer_fd % iothreads.size()] : NULL;
         io_uring_sqe sqe_local;
         ring_data_t data_local;
-        sqe_local.user_data = (uint64_t)&data_local;
         io_uring_sqe* sqe = (iothread ? &sqe_local : ringloop->get_sqe());
-        if (!sqe)
+        if (iothread)
         {
-            return false;
+            sqe_local = { .user_data = (uint64_t)&data_local };
+            data_local = {};
         }
+        if (!sqe)
+            return false;
         cl->write_msg.msg_iov = cl->send_list.data();
         cl->write_msg.msg_iovlen = cl->send_list.size() < IOV_MAX ? cl->send_list.size() : IOV_MAX;
         cl->refs++;
@@ -237,7 +239,8 @@ bool osd_messenger_t::try_send(osd_client_t *cl)
         {
             result = -errno;
         }
-        handle_send(result, false, false, cl);
+        // like set_immediate
+        tfd->set_timer_us(0, false, [this, result, cl](int){ handle_send(result, false, false, cl); });
     }
     return true;
 }

src/client/msgr_stop.cpp

@@ -9,38 +9,37 @@
 #include "msgr_rdma.h"
 #endif
 
-void osd_messenger_t::cancel_osd_ops(osd_client_t *cl)
+void osd_client_t::cancel_ops()
 {
     std::vector<osd_op_t*> cancel_ops;
-    cancel_ops.resize(cl->sent_ops.size());
+    cancel_ops.resize(sent_ops.size());
     int i = 0;
-    for (auto p: cl->sent_ops)
+    for (auto p: sent_ops)
     {
         cancel_ops[i++] = p.second;
     }
-    cl->sent_ops.clear();
+    sent_ops.clear();
-    cl->outbox.clear();
     for (auto op: cancel_ops)
     {
-        cancel_op(op);
+        op->cancel();
     }
 }
 
-void osd_messenger_t::cancel_op(osd_op_t *op)
+void osd_op_t::cancel()
 {
-    if (op->op_type == OSD_OP_OUT)
+    if (op_type == OSD_OP_OUT && callback)
     {
-        op->reply.hdr.magic = SECONDARY_OSD_REPLY_MAGIC;
+        reply.hdr.magic = SECONDARY_OSD_REPLY_MAGIC;
-        op->reply.hdr.id = op->req.hdr.id;
+        reply.hdr.id = req.hdr.id;
-        op->reply.hdr.opcode = op->req.hdr.opcode;
+        reply.hdr.opcode = req.hdr.opcode;
-        op->reply.hdr.retval = -EPIPE;
+        reply.hdr.retval = -EPIPE;
-        // Copy lambda to be unaffected by `delete op`
+        // Copy lambda to be unaffected by `delete this`
-        std::function<void(osd_op_t*)>(op->callback)(op);
+        (std::function<void(osd_op_t*)>(callback))(this);
     }
     else
     {
         // This function is only called in stop_client(), so it's fine to destroy the operation
-        delete op;
+        delete this;
     }
 }
 
@@ -63,6 +62,10 @@ void osd_messenger_t::stop_client(int peer_fd, bool force, bool force_delete)
         {
             fprintf(stderr, "[OSD %ju] Stopping client %d (OSD peer %ju)\n", osd_num, peer_fd, cl->osd_num);
         }
+        else if (cl->in_osd_num)
+        {
+            fprintf(stderr, "[OSD %ju] Stopping client %d (incoming OSD peer %ju)\n", osd_num, peer_fd, cl->in_osd_num);
+        }
         else
         {
             fprintf(stderr, "[OSD %ju] Stopping client %d (regular client)\n", osd_num, peer_fd);
@@ -73,8 +76,12 @@ void osd_messenger_t::stop_client(int peer_fd, bool force, bool force_delete)
     cl->peer_state = PEER_STOPPED;
     if (cl->osd_num)
     {
-        // ...and forget OSD peer
+        auto osd_it = osd_peer_fds.find(cl->osd_num);
-        osd_peer_fds.erase(cl->osd_num);
+        if (osd_it != osd_peer_fds.end() && osd_it->second == cl->peer_fd)
+        {
+            // ...and forget OSD peer
+            osd_peer_fds.erase(osd_it);
+        }
     }
 #ifndef __MOCK__
     // Then remove FD from the eventloop so we don't accidentally read something
@@ -101,30 +108,17 @@ void osd_messenger_t::stop_client(int peer_fd, bool force, bool force_delete)
         }
     }
 #endif
+    if (cl->in_osd_num && break_pg_locks)
+    {
+        // Break PG locks
+        break_pg_locks(cl->in_osd_num);
+    }
     if (cl->osd_num)
     {
         // Then repeer PGs because cancel_op() callbacks can try to perform
         // some actions and we need correct PG states to not do something silly
         repeer_pgs(cl->osd_num);
     }
-    // Then cancel all operations
-    if (cl->read_op)
-    {
-        if (!cl->read_op->callback)
-        {
-            delete cl->read_op;
-        }
-        else
-        {
-            cancel_op(cl->read_op);
-        }
-        cl->read_op = NULL;
-    }
-    if (cl->osd_num)
-    {
-        // Cancel outbound operations
-        cancel_osd_ops(cl);
-    }
     // Find the item again because it can be invalidated at this point
     it = clients.find(peer_fd);
     if (it != clients.end())
@@ -149,6 +143,17 @@ osd_client_t::~osd_client_t()
         close(peer_fd);
         peer_fd = -1;
     }
+    // Then cancel all operations
+    // Operations have to be canceled only after clearing all references to osd_client_t
+    // because otherwise their buffers may be still present in io_uring asynchronous requests
+    if (read_op)
+    {
+        // read_op may be an incoming op or a continued response for an outbound op
+        read_op->cancel();
+        read_op = NULL;
+    }
+    // Cancel outbound ops
+    cancel_ops();
 #ifndef __MOCK__
 #ifdef WITH_RDMA
     if (rdma_conn)

src/client/qemu_driver.c

@@ -58,6 +58,7 @@ typedef struct VitastorClient
 {
     void *proxy;
     int uring_eventfd;
+    int auto_loop;
 
     void *watch;
     char *config_path;
@@ -155,16 +156,19 @@ static void qemu_vitastor_unescape(char *src)
 // vitastor[:key=value]*
 // vitastor[:etcd_host=127.0.0.1]:inode=1:pool=1[:rdma_gid_index=3]
 // vitastor:config_path=/etc/vitastor/vitastor.conf:image=testimg
+// vitastor://?config_path=/etc/vitastor/vitastor.conf&image=testimg
 static void vitastor_parse_filename(const char *filename, QDict *options, Error **errp)
 {
     const char *start;
     char *p, *buf;
 
-    if (!strstart(filename, "vitastor:", &start))
+    int url_style = strstart(filename, "vitastor://?", &start);
+    if (!url_style && !strstart(filename, "vitastor:", &start))
     {
         error_setg(errp, "File name must start with 'vitastor:'");
         return;
     }
+    char delim = url_style ? '&' : ':';
 
     buf = g_strdup(start);
     p = buf;
@@ -184,7 +188,7 @@ static void vitastor_parse_filename(const char *filename, QDict *options, Error
             if (name[i] == '_')
                 name[i] = '-';
         qemu_vitastor_unescape(name);
-        value = qemu_vitastor_next_tok(p, ':', &p);
+        value = qemu_vitastor_next_tok(p, delim, &p);
         qemu_vitastor_unescape(value);
         if (!strcmp(name, "inode") ||
             !strcmp(name, "pool") ||
@@ -294,9 +298,8 @@ static void coroutine_fn vitastor_co_get_metadata(VitastorRPC *task)
 
     qemu_mutex_lock(&client->mutex);
     vitastor_c_watch_inode(client->proxy, client->image, vitastor_co_generic_cb, task);
-#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+    if (!client->auto_loop)
-    vitastor_schedule_uring_handler(client);
+        vitastor_schedule_uring_handler(client);
-#endif
     qemu_mutex_unlock(&client->mutex);
 
     while (!task->complete)
@@ -449,6 +452,9 @@ static int vitastor_file_open(BlockDriverState *bs, QDict *options, int flags, E
     client->ctx = bdrv_get_aio_context(bs);
 #if defined VITASTOR_C_API_VERSION && VITASTOR_C_API_VERSION >= 2
     str_array opt = {};
+    char version_buffer[32];
+    memset(version_buffer, ' ', sizeof(version_buffer));
+    version_buffer[sizeof(version_buffer)-1] = '\0';
     strarray_push_kv(&opt, "config_path", qdict_get_try_str(options, "config-path"));
     strarray_push_kv(&opt, "etcd_address", qdict_get_try_str(options, "etcd-host"));
     strarray_push_kv(&opt, "etcd_prefix", qdict_get_try_str(options, "etcd-prefix"));
@@ -458,7 +464,9 @@ static int vitastor_file_open(BlockDriverState *bs, QDict *options, int flags, E
     strarray_push_kv(&opt, "rdma_gid_index", qdict_get_try_str(options, "rdma-gid-index"));
     strarray_push_kv(&opt, "rdma_mtu", qdict_get_try_str(options, "rdma-mtu"));
     strarray_push_kv(&opt, "client_writeback_allowed", (flags & BDRV_O_NOCACHE) ? "0" : "1");
+    strarray_push_kv(&opt, "__version_check_buffer", version_buffer);
     client->proxy = vitastor_c_create_uring_json(opt.items, opt.len);
+    client->auto_loop = 0;
     strarray_free(&opt);
     if (client->proxy)
     {
@@ -471,6 +479,12 @@ static int vitastor_file_open(BlockDriverState *bs, QDict *options, int flags, E
             return -1;
         }
         universal_aio_set_fd_handler(client->ctx, client->uring_eventfd, vitastor_uring_handler, NULL, client);
+        int vitastor_version[3] = { 0 };
+        if (sscanf(version_buffer, "%d.%d.%d", &vitastor_version[0], &vitastor_version[1], &vitastor_version[2]) == 3 &&
+            vitastor_version[0] >= 2)
+        {
+            client->auto_loop = 1;
+        }
     }
     else
     {
@@ -604,6 +618,29 @@ static void vitastor_close(BlockDriverState *bs)
     client->last_bitmap = NULL;
 }
 
+#if QEMU_VERSION_MAJOR >= 3 || QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR >= 2
+static void vitastor_refresh_filename(BlockDriverState *bs)
+{
+    VitastorClient *client = bs->opaque;
+    size_t len = 0;
+    int n = 0;
+    len = snprintf(bs->exact_filename, sizeof(bs->exact_filename), "vitastor://");
+    if (len < sizeof(bs->exact_filename))
+    {
+        if (client->image)
+            len += snprintf(bs->exact_filename+len, sizeof(bs->exact_filename)-len, "%cimage=%s", (n++ ? '&' : '?'), client->image);
+        else
+            len += snprintf(bs->exact_filename+len, sizeof(bs->exact_filename)-len, "%cpool=%ju&inode=%ju&size=%ju", (n++ ? '&' : '?'), client->pool, client->inode, client->size);
+    }
+    if (client->config_path && len < sizeof(bs->exact_filename))
+        len += snprintf(bs->exact_filename+len, sizeof(bs->exact_filename)-len, "%cconfig_path=%s", (n++ ? '&' : '?'), client->config_path);
+    if (client->etcd_host && len < sizeof(bs->exact_filename))
+        len += snprintf(bs->exact_filename+len, sizeof(bs->exact_filename)-len, "%cetcd_host=%s", (n++ ? '&' : '?'), client->etcd_host);
+    if (client->etcd_prefix && len < sizeof(bs->exact_filename))
+        len += snprintf(bs->exact_filename+len, sizeof(bs->exact_filename)-len, "%cetcd_prefix=%s", (n++ ? '&' : '?'), client->etcd_prefix);
+}
+#endif
+
 #if QEMU_VERSION_MAJOR >= 3 || QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR > 2
 static int vitastor_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz)
 {
@@ -767,9 +804,8 @@ 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);
-#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+    if (!client->auto_loop)
-    vitastor_schedule_uring_handler(client);
+        vitastor_schedule_uring_handler(client);
-#endif
     qemu_mutex_unlock(&client->mutex);
 
     while (!task.complete)
@@ -803,9 +839,8 @@ 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_cb, &task);
-#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+    if (!client->auto_loop)
-    vitastor_schedule_uring_handler(client);
+        vitastor_schedule_uring_handler(client);
-#endif
     qemu_mutex_unlock(&client->mutex);
 
     while (!task.complete)
@@ -885,9 +920,8 @@ 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);
-#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+        if (!client->auto_loop)
-        vitastor_schedule_uring_handler(client);
+            vitastor_schedule_uring_handler(client);
-#endif
         qemu_mutex_unlock(&client->mutex);
         while (!task.complete)
         {
@@ -974,9 +1008,8 @@ static int coroutine_fn vitastor_co_flush(BlockDriverState *bs)
 
     qemu_mutex_lock(&client->mutex);
     vitastor_c_sync(client->proxy, vitastor_co_generic_cb, &task);
-#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+    if (!client->auto_loop)
-    vitastor_schedule_uring_handler(client);
+        vitastor_schedule_uring_handler(client);
-#endif
     qemu_mutex_unlock(&client->mutex);
 
     while (!task.complete)
@@ -1038,6 +1071,9 @@ static BlockDriver bdrv_vitastor = {
     .bdrv_get_info                  = vitastor_get_info,
     .bdrv_getlength                 = vitastor_getlength,
 #endif
+#if QEMU_VERSION_MAJOR >= 3 || QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR >= 2
+    .bdrv_refresh_filename          = vitastor_refresh_filename,
+#endif
 #if QEMU_VERSION_MAJOR >= 3 || QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR > 2
     .bdrv_probe_blocksizes          = vitastor_probe_blocksizes,
 #endif

src/client/vitastor.pc.in

@@ -6,7 +6,7 @@ includedir=${prefix}/@CMAKE_INSTALL_INCLUDEDIR@
 
 Name: Vitastor
 Description: Vitastor client library
-Version: 2.2.0
+Version: 2.2.3
 Libs: -L${libdir} -lvitastor_client
 Cflags: -I${includedir}
 

src/client/vitastor_c.cpp

@@ -178,7 +178,14 @@ vitastor_c *vitastor_c_create_uring_json(const char **options, int options_len)
     json11::Json::object cfg;
     for (int i = 0; i < options_len-1; i += 2)
     {
-        cfg[options[i]] = std::string(options[i+1]);
+        if (!strcmp(options[i], "__version_check_buffer"))
+        {
+            int buf_size = strlen(options[i+1])+1;
+            if (buf_size > strlen(VITASTOR_VERSION))
+                strncpy((char*)options[i+1], VITASTOR_VERSION, buf_size);
+        }
+        else
+            cfg[options[i]] = std::string(options[i+1]);
     }
     json11::Json cfg_json(cfg);
     vitastor_c *self = new vitastor_c;

src/client/vitastor_c.h

@@ -7,7 +7,7 @@
 #define VITASTOR_QEMU_PROXY_H
 
 // C API wrapper version
-#define VITASTOR_C_API_VERSION 5
+#define VITASTOR_C_API_VERSION 4
 
 #ifndef POOL_ID_BITS
 #define POOL_ID_BITS 16

src/cmd/cli_rm_osd.cpp

@@ -70,7 +70,7 @@ struct rm_osd_t
         {
             if (parent->cli->st_cli.peer_states.find(osd_id) != parent->cli->st_cli.peer_states.end())
             {
-                is_warning = true;
+                is_warning = !allow_up;
                 still_up.push_back(osd_id);
             }
         }

src/nfs/nfs_proxy.cpp

@@ -72,12 +72,14 @@ static const char* help_text =
     "  --port <PORT>         use port <PORT> for NFS services (default is 2049)\n"
     "                        specify \"auto\" to auto-select and print port\n"
     "  --portmap 0           do not listen on port 111 (portmap/rpcbind, requires root)\n"
+#ifdef WITH_RDMACM
     "  --nfs_rdma <PORT>     enable NFS-RDMA at RDMA-CM port <PORT> (you can try 20049)\n"
     "                        if RDMA is enabled and --port is set to 0, TCP will be disabled\n"
     "  --nfs_rdma_credit 16  maximum operation credit for RDMA clients (max iodepth)\n"
     "  --nfs_rdma_send 1024  maximum RDMA send operation count (should be larger than iodepth)\n"
     "  --nfs_rdma_alloc 1M   RDMA memory allocation rounding\n"
     "  --nfs_rdma_gc 64M     maximum unused RDMA buffers\n"
+#endif
     "\n"
     "vitastor-nfs --fs <NAME> upgrade\n"
     "  Upgrade FS metadata. Can be run online, but server(s) should be restarted\n"
@@ -205,12 +207,15 @@ void nfs_proxy_t::run(json11::Json cfg)
     default_pool = cfg["pool"].as_string();
     portmap_enabled = !json_is_false(cfg["portmap"]);
     nfs_port = cfg["port"].uint64_value() & 0xffff;
+#ifdef WITH_RDMACM
     nfs_rdma_port = cfg["nfs_rdma"].uint64_value() & 0xffff;
+#endif
     // Allow RDMA-only mode if port is explicitly set to 0
     // Allow port auto-selection in server mode if explicitly set to --port auto
     nfs_port_auto = cfg["port"] == "auto";
     if (!nfs_port)
         nfs_port = nfs_port_auto ? 0 : (!cfg["port"].is_null() && nfs_rdma_port ? -1 : 2049);
+#ifdef WITH_RDMACM
     nfs_rdma_credit = cfg["nfs_rdma_credit"].uint64_value();
     if (!nfs_rdma_credit)
         nfs_rdma_credit = 16;
@@ -223,6 +228,7 @@ void nfs_proxy_t::run(json11::Json cfg)
     nfs_rdma_gc = cfg["nfs_rdma_gc"].uint64_value();
     if (!nfs_rdma_gc)
         nfs_rdma_gc = 64*1048576;
+#endif
     export_root = cfg["nfspath"].string_value();
     if (!export_root.size())
         export_root = "/";
@@ -391,10 +397,12 @@ void nfs_proxy_t::run_server(json11::Json cfg)
             }
         });
     }
+#ifdef WITH_RDMACM
     if (nfs_rdma_port)
     {
         rdma_context = create_rdma(bind_address, nfs_rdma_port, nfs_rdma_credit, nfs_rdma_max_send, nfs_rdma_alloc, nfs_rdma_gc);
     }
+#endif
     if (mountpoint != "")
     {
         mount_fs();

src/osd/osd.cpp

@@ -85,6 +85,7 @@ osd_t::osd_t(const json11::Json & config, ring_loop_t *ringloop)
     msgr.ringloop = this->ringloop;
     msgr.exec_op = [this](osd_op_t *op) { exec_op(op); };
     msgr.repeer_pgs = [this](osd_num_t peer_osd) { repeer_pgs(peer_osd); };
+    msgr.break_pg_locks = [this](osd_num_t peer_osd) { break_pg_locks(peer_osd); };
     msgr.check_config_hook = [this](osd_client_t *cl, json11::Json conf) { return check_peer_config(cl, conf); };
     msgr.init();
 
@@ -195,7 +196,6 @@ void osd_t::parse_config(bool init)
             etcd_stats_interval = 30;
         readonly = json_is_true(config["readonly"]);
         run_primary = !json_is_false(config["run_primary"]);
-        allow_test_ops = json_is_true(config["allow_test_ops"]);
     }
     log_level = config["log_level"].uint64_value();
     auto old_no_rebalance = no_rebalance;
@@ -469,11 +469,7 @@ void osd_t::exec_op(osd_op_t *cur_op)
         finish_op(cur_op, -EROFS);
         return;
     }
-    if (cur_op->req.hdr.opcode == OSD_OP_TEST_SYNC_STAB_ALL)
+    if (cur_op->req.hdr.opcode == OSD_OP_SHOW_CONFIG)
-    {
-        exec_sync_stab_all(cur_op);
-    }
-    else if (cur_op->req.hdr.opcode == OSD_OP_SHOW_CONFIG)
     {
         exec_show_config(cur_op);
     }

src/osd/osd.h

@@ -119,7 +119,6 @@ class osd_t
     bool disable_tcp = false;
     // FIXME: Implement client queue depth limit
     int client_queue_depth = 128;
-    bool allow_test_ops = false;
     int print_stats_interval = 3;
     int slow_log_interval = 10;
     int immediate_commit = IMMEDIATE_NONE;
@@ -278,6 +277,8 @@ class osd_t
     void handle_peers();
     bool check_peer_config(osd_client_t *cl, json11::Json conf);
     void repeer_pgs(osd_num_t osd_num);
+    void repeer_pg(pg_t & pg);
+    void break_pg_locks(osd_num_t osd_num);
     void start_pg_peering(pg_t & pg);
     void drop_dirty_pg_connections(pool_pg_num_t pg);
     void record_pg_lock(pg_t & pg, osd_num_t peer_osd, uint64_t pg_state);
@@ -317,7 +318,6 @@ class osd_t
 
     // secondary ops
     bool sec_check_pg_lock(osd_num_t primary_osd, const object_id &oid);
-    void exec_sync_stab_all(osd_op_t *cur_op);
     void exec_show_config(osd_op_t *cur_op);
     void exec_secondary(osd_op_t *cur_op);
     void exec_secondary_real(osd_op_t *cur_op);

src/osd/osd_cluster.cpp

@@ -432,9 +432,16 @@ void osd_t::apply_pg_locks_localize_only()
         }
         auto & pool_cfg = pool_it->second;
         auto & pg = pp.second;
+        auto old_disable_pg_locks = pg.disable_pg_locks;
         pg.disable_pg_locks = pg_locks_localize_only &&
-            pool_cfg.scheme == POOL_SCHEME_REPLICATED &&
+            (pool_cfg.scheme != POOL_SCHEME_REPLICATED ||
-            pool_cfg.local_reads == POOL_LOCAL_READ_PRIMARY;
+            pool_cfg.local_reads == POOL_LOCAL_READ_PRIMARY);
+        if (!pg.disable_pg_locks && old_disable_pg_locks)
+        {
+            // Relock PG
+            printf("[PG %u/%u] Repeer to enable PG locks\n", pg.pool_id, pg.pg_num);
+            repeer_pg(pg);
+        }
     }
 }
 
@@ -877,8 +884,8 @@ void osd_t::apply_pg_config()
                 pg.next_scrub = pg_cfg.next_scrub;
                 pg.target_set = pg_cfg.target_set;
                 pg.disable_pg_locks = pg_locks_localize_only &&
-                    pool_item.second.scheme == POOL_SCHEME_REPLICATED &&
+                    (pool_item.second.scheme != POOL_SCHEME_REPLICATED ||
-                    pool_item.second.local_reads == POOL_LOCAL_READ_PRIMARY;
+                    pool_item.second.local_reads == POOL_LOCAL_READ_PRIMARY);
                 if (pg.scheme == POOL_SCHEME_EC)
                 {
                     use_ec(pg.pg_size, pg.pg_data_size, true);

src/osd/osd_flush.cpp

@@ -189,7 +189,7 @@ bool osd_t::submit_flush_op(pool_id_t pool_id, pg_num_t pg_num, pg_flush_batch_t
             {
                 .len = (uint32_t)count,
             },
-            .buf = op->buf,
+            .buf = (uint8_t*)op->buf,
         });
         bs->enqueue_op(op->bs_op);
     }

src/osd/osd_peering.cpp

@@ -73,18 +73,25 @@ void osd_t::handle_peers()
     }
 }
 
+void osd_t::break_pg_locks(osd_num_t peer_osd)
+{
+    for (auto lock_it = pg_locks.begin(); lock_it != pg_locks.end(); )
+    {
+        if (lock_it->second.primary_osd == peer_osd)
+        {
+            if (log_level > 3)
+            {
+                printf("Break PG %u/%u lock on disconnection of OSD %ju\n", lock_it->first.pool_id, lock_it->first.pg_num, peer_osd);
+            }
+            pg_locks.erase(lock_it++);
+        }
+        else
+            lock_it++;
+    }
+}
+
 void osd_t::repeer_pgs(osd_num_t peer_osd)
 {
-    if (msgr.osd_peer_fds.find(peer_osd) == msgr.osd_peer_fds.end())
-    {
-        for (auto lock_it = pg_locks.begin(); lock_it != pg_locks.end(); )
-        {
-            if (lock_it->second.primary_osd == peer_osd)
-                pg_locks.erase(lock_it++);
-            else
-                lock_it++;
-        }
-    }
     // Re-peer affected PGs
     for (auto & p: pgs)
     {
@@ -104,21 +111,26 @@ void osd_t::repeer_pgs(osd_num_t peer_osd)
             {
                 // Repeer this pg
                 printf("[PG %u/%u] Repeer because of OSD %ju\n", pg.pool_id, pg.pg_num, peer_osd);
-                if (!(pg.state & (PG_ACTIVE | PG_REPEERING)) || pg.can_repeer())
+                repeer_pg(pg);
-                {
-                    start_pg_peering(pg);
-                }
-                else
-                {
-                    // Stop accepting new operations, wait for current ones to finish or fail
-                    pg.state = pg.state & ~PG_ACTIVE | PG_REPEERING;
-                    report_pg_state(pg);
-                }
             }
         }
     }
 }
 
+void osd_t::repeer_pg(pg_t & pg)
+{
+    if (!(pg.state & (PG_ACTIVE | PG_REPEERING)) || pg.can_repeer())
+    {
+        start_pg_peering(pg);
+    }
+    else
+    {
+        // Stop accepting new operations, wait for current ones to finish or fail
+        pg.state = pg.state & ~PG_ACTIVE | PG_REPEERING;
+        report_pg_state(pg);
+    }
+}
+
 // Reset PG state (when peering or stopping)
 void osd_t::reset_pg(pg_t & pg)
 {
@@ -466,6 +478,7 @@ void osd_t::relock_pg(pg_t & pg)
             auto pg_it = pgs.find(pg_id);
             if (pg_it == pgs.end())
             {
+                printf("Warning: PG %u/%u is gone during lock attempt\n", pg_id.pool_id, pg_id.pg_num);
                 return;
             }
             auto & pg = pg_it->second;
@@ -475,15 +488,14 @@ void osd_t::relock_pg(pg_t & pg)
             }
             else if (op->reply.hdr.retval != -EPIPE)
             {
-                printf(
+                printf("Failed to %s PG %u/%u on OSD %ju - ", op->req.sec_lock.flags == OSD_SEC_UNLOCK_PG ? "unlock" : "lock",
-                    (op->reply.hdr.retval == -ENOENT
+                    pg_id.pool_id, pg_id.pg_num, peer_osd);
-                        ? "Failed to %1$s PG %2$u/%3$u on OSD %4$ju - peer didn't load PG info yet\n"
+                if (op->reply.hdr.retval == -ENOENT)
-                        : (op->reply.sec_lock.cur_primary
+                    printf("peer didn't load PG info yet\n");
-                            ? "Failed to %1$s PG %2$u/%3$u on OSD %4$ju - taken by OSD %6$ju (retval=%5$jd)\n"
+                else if (op->reply.sec_lock.cur_primary)
-                            : "Failed to %1$s PG %2$u/%3$u on OSD %4$ju - retval=%5$jd\n")),
+                    printf("taken by OSD %ju (retval=%jd)\n", op->reply.sec_lock.cur_primary, op->reply.hdr.retval);
-                    op->req.sec_lock.flags == OSD_SEC_UNLOCK_PG ? "unlock" : "lock",
+                else
-                    pg_id.pool_id, pg_id.pg_num, peer_osd, op->reply.hdr.retval, op->reply.sec_lock.cur_primary
+                    printf("retval=%jd\n", op->reply.hdr.retval);
-                );
                 // Retry relocking/unlocking PG after a short time
                 pg.lock_waiting = true;
                 tfd->set_timer(pg_lock_retry_interval_ms, false, [this, pg_id](int)

src/osd/osd_primary_subops.cpp

@@ -209,8 +209,8 @@ void osd_t::submit_primary_subop(osd_op_t *cur_op, osd_op_t *subop,
                 .offset = wr ? si->write_start : si->read_start,
                 .len = subop_len,
             } },
-            .buf = wr ? si->write_buf : si->read_buf,
+            .buf = (uint8_t*)(wr ? si->write_buf : si->read_buf),
-            .bitmap = si->bmp_buf,
+            .bitmap = (uint8_t*)si->bmp_buf,
         });
 #ifdef OSD_DEBUG
          printf(
@@ -290,7 +290,6 @@ static uint64_t bs_op_to_osd_op[] = {
     OSD_OP_SEC_DELETE,          // BS_OP_DELETE = 6
     OSD_OP_SEC_LIST,            // BS_OP_LIST = 7
     OSD_OP_SEC_ROLLBACK,        // BS_OP_ROLLBACK = 8
-    OSD_OP_TEST_SYNC_STAB_ALL,  // BS_OP_SYNC_STAB_ALL = 9
 };
 
 void osd_t::handle_primary_bs_subop(osd_op_t *subop)
@@ -417,16 +416,17 @@ void osd_t::handle_primary_subop(osd_op_t *subop, osd_op_t *cur_op)
     if (retval != expected)
     {
         int64_t peer_osd = (msgr.clients.find(subop->peer_fd) != msgr.clients.end()
-            ? msgr.clients[subop->peer_fd]->osd_num : -subop->peer_fd);
+            ? msgr.clients[subop->peer_fd]->osd_num : 0);
         if (opcode == OSD_OP_SEC_READ || opcode == OSD_OP_SEC_WRITE || opcode == OSD_OP_SEC_WRITE_STABLE)
         {
-            printf(
+            printf("%s subop to %jx:%jx v%ju failed ", osd_op_names[opcode],
-                subop->peer_fd >= 0
+                subop->req.sec_rw.oid.inode, subop->req.sec_rw.oid.stripe, subop->req.sec_rw.version);
-                    ? "%1$s subop to %2$jx:%3$jx v%4$ju failed on osd %7$jd: retval = %5$d (expected %6$d)\n"
+            if (subop->peer_fd >= 0 && peer_osd > 0)
-                    : "%1$s subop to %2$jx:%3$jx v%4$ju failed locally: retval = %5$d (expected %6$d)\n",
+                printf("on osd %ju: retval = %d (expected %d)\n", peer_osd, retval, expected);
-                osd_op_names[opcode], subop->req.sec_rw.oid.inode, subop->req.sec_rw.oid.stripe, subop->req.sec_rw.version,
+            else if (peer_osd > 0)
-                retval, expected, peer_osd
+                printf("on peer %d: retval = %d (expected %d)\n", subop->peer_fd, retval, expected);
-            );
+            else
+                printf("locally: retval = %d (expected %d)\n", retval, expected);
         }
         else if (opcode == OSD_OP_SEC_DELETE)
         {
@@ -702,7 +702,7 @@ void osd_t::submit_primary_stab_subops(osd_op_t *cur_op)
                 {
                     .len = (uint32_t)stab_osd.len,
                 },
-                .buf = (void*)(op_data->unstable_writes + stab_osd.start),
+                .buf = (uint8_t*)(op_data->unstable_writes + stab_osd.start),
             });
             bs->enqueue_op(subops[i].bs_op);
         }
@@ -789,7 +789,7 @@ void osd_t::submit_primary_rollback_subops(osd_op_t *cur_op, const uint64_t* osd
                     {
                         .len = 1,
                     },
-                    .buf = (void*)(op_data->unstable_writes + i),
+                    .buf = (uint8_t*)(op_data->unstable_writes + i),
                 });
 #ifdef OSD_DEBUG
                 printf(

src/osd/osd_secondary.cpp

@@ -91,16 +91,17 @@ bool osd_t::sec_check_pg_lock(osd_num_t primary_osd, const object_id &oid)
     {
         return false;
     }
+    auto & pool_cfg = pool_cfg_it->second;
+    if (pg_locks_localize_only && (pool_cfg.scheme != POOL_SCHEME_REPLICATED || pool_cfg.local_reads == POOL_LOCAL_READ_PRIMARY))
+    {
+        return true;
+    }
     auto ppg = (pool_pg_num_t){ .pool_id = pool_id, .pg_num = map_to_pg(oid, pool_cfg_it->second.pg_stripe_size) };
     auto pg_it = pgs.find(ppg);
     if (pg_it != pgs.end() && pg_it->second.state != PG_OFFLINE)
     {
         return false;
     }
-    if (pg_it->second.disable_pg_locks)
-    {
-        return true;
-    }
     auto lock_it = pg_locks.find(ppg);
     return lock_it != pg_locks.end() && lock_it->second.primary_osd == primary_osd;
 }
@@ -140,7 +141,7 @@ void osd_t::exec_secondary_real(osd_op_t *cur_op)
         cur_op->req.hdr.opcode == OSD_OP_SEC_WRITE_STABLE)
     {
         if (!(cur_op->req.sec_rw.flags & OSD_OP_IGNORE_PG_LOCK) &&
-            !sec_check_pg_lock(cl->osd_num, cur_op->req.sec_rw.oid))
+            !sec_check_pg_lock(cl->in_osd_num, cur_op->req.sec_rw.oid))
         {
             cur_op->bs_op->retval = -EPIPE;
             secondary_op_callback(cur_op);
@@ -160,8 +161,8 @@ void osd_t::exec_secondary_real(osd_op_t *cur_op)
         cur_op->bs_op->version = cur_op->req.sec_rw.version;
         cur_op->bs_op->offset = cur_op->req.sec_rw.offset;
         cur_op->bs_op->len = cur_op->req.sec_rw.len;
-        cur_op->bs_op->buf = cur_op->buf;
+        cur_op->bs_op->buf = (uint8_t*)cur_op->buf;
-        cur_op->bs_op->bitmap = cur_op->bitmap;
+        cur_op->bs_op->bitmap = (uint8_t*)cur_op->bitmap;
 #ifdef OSD_STUB
         cur_op->bs_op->retval = cur_op->bs_op->len;
 #endif
@@ -169,7 +170,7 @@ void osd_t::exec_secondary_real(osd_op_t *cur_op)
     else if (cur_op->req.hdr.opcode == OSD_OP_SEC_DELETE)
     {
         if (!(cur_op->req.sec_del.flags & OSD_OP_IGNORE_PG_LOCK) &&
-            !sec_check_pg_lock(cl->osd_num, cur_op->req.sec_del.oid))
+            !sec_check_pg_lock(cl->in_osd_num, cur_op->req.sec_del.oid))
         {
             cur_op->bs_op->retval = -EPIPE;
             secondary_op_callback(cur_op);
@@ -185,7 +186,7 @@ void osd_t::exec_secondary_real(osd_op_t *cur_op)
         cur_op->req.hdr.opcode == OSD_OP_SEC_ROLLBACK)
     {
         cur_op->bs_op->len = cur_op->req.sec_stab.len/sizeof(obj_ver_id);
-        cur_op->bs_op->buf = cur_op->buf;
+        cur_op->bs_op->buf = (uint8_t*)cur_op->buf;
 #ifdef OSD_STUB
         cur_op->bs_op->retval = 0;
 #endif
@@ -193,7 +194,7 @@ void osd_t::exec_secondary_real(osd_op_t *cur_op)
         {
             for (int i = 0; i < cur_op->bs_op->len; i++)
             {
-                if (!sec_check_pg_lock(cl->osd_num, ((obj_ver_id*)cur_op->buf)[i].oid))
+                if (!sec_check_pg_lock(cl->in_osd_num, ((obj_ver_id*)cur_op->buf)[i].oid))
                 {
                     cur_op->bs_op->retval = -EPIPE;
                     secondary_op_callback(cur_op);
@@ -247,7 +248,7 @@ void osd_t::exec_sec_read_bmp(osd_op_t *cur_op)
         void *cur_buf = reply_buf;
         for (int i = 0; i < n; i++)
         {
-            if (!sec_check_pg_lock(cl->osd_num, ov[i].oid) &&
+            if (!sec_check_pg_lock(cl->in_osd_num, ov[i].oid) &&
                 !(cur_op->req.sec_read_bmp.flags & OSD_OP_IGNORE_PG_LOCK))
             {
                 free(reply_buf);
@@ -269,7 +270,7 @@ void osd_t::exec_sec_lock(osd_op_t *cur_op)
 {
     cur_op->reply.sec_lock.cur_primary = 0;
     auto cl = msgr.clients.at(cur_op->peer_fd);
-    if (!cl->osd_num ||
+    if (!cl->in_osd_num ||
         cur_op->req.sec_lock.flags != OSD_SEC_LOCK_PG &&
         cur_op->req.sec_lock.flags != OSD_SEC_UNLOCK_PG ||
         cur_op->req.sec_lock.pool_id > ((uint64_t)1<<POOL_ID_BITS) ||
@@ -290,7 +291,7 @@ void osd_t::exec_sec_lock(osd_op_t *cur_op)
     auto lock_it = pg_locks.find(ppg);
     if (cur_op->req.sec_lock.flags == OSD_SEC_LOCK_PG)
     {
-        if (lock_it != pg_locks.end() && lock_it->second.primary_osd != cl->osd_num)
+        if (lock_it != pg_locks.end() && lock_it->second.primary_osd != cl->in_osd_num)
         {
             cur_op->reply.sec_lock.cur_primary = lock_it->second.primary_osd;
             finish_op(cur_op, -EBUSY);
@@ -303,13 +304,21 @@ void osd_t::exec_sec_lock(osd_op_t *cur_op)
             finish_op(cur_op, -EBUSY);
             return;
         }
+        if (log_level > 3)
+        {
+            printf("Lock PG %u/%u for OSD %ju\n", ppg.pool_id, ppg.pg_num, cl->in_osd_num);
+        }
         pg_locks[ppg] = (osd_pg_lock_t){
-            .primary_osd = cl->osd_num,
+            .primary_osd = cl->in_osd_num,
             .state = cur_op->req.sec_lock.pg_state,
         };
     }
-    else if (lock_it != pg_locks.end() && lock_it->second.primary_osd == cl->osd_num)
+    else if (lock_it != pg_locks.end() && lock_it->second.primary_osd == cl->in_osd_num)
     {
+        if (log_level > 3)
+        {
+            printf("Unlock PG %u/%u by OSD %ju\n", ppg.pool_id, ppg.pg_num, cl->in_osd_num);
+        }
         pg_locks.erase(lock_it);
     }
     finish_op(cur_op, 0);
@@ -323,7 +332,7 @@ void osd_t::exec_show_config(osd_op_t *cur_op)
         : json11::Json();
     auto peer_osd_num = req_json["osd_num"].uint64_value();
     auto cl = msgr.clients.at(cur_op->peer_fd);
-    cl->osd_num = peer_osd_num;
+    cl->in_osd_num = peer_osd_num;
     if (req_json["features"]["check_sequencing"].bool_value())
     {
         cl->check_sequencing = true;
@@ -369,27 +378,3 @@ void osd_t::exec_show_config(osd_op_t *cur_op)
     cur_op->iov.push_back(cur_op->buf, cfg_str.size()+1);
     finish_op(cur_op, cfg_str.size()+1);
 }
-
-void osd_t::exec_sync_stab_all(osd_op_t *cur_op)
-{
-    // Sync and stabilize all objects
-    // This command is only valid for tests
-    cur_op->bs_op = new blockstore_op_t();
-    if (!allow_test_ops)
-    {
-        cur_op->bs_op->retval = -EINVAL;
-        secondary_op_callback(cur_op);
-        return;
-    }
-    cur_op->bs_op->opcode = BS_OP_SYNC_STAB_ALL;
-    cur_op->bs_op->callback = [this, cur_op](blockstore_op_t *bs_op)
-    {
-        secondary_op_callback(cur_op);
-    };
-#ifdef OSD_STUB
-    cur_op->bs_op->retval = 0;
-    secondary_op_callback(cur_op);
-#else
-    bs->enqueue_op(cur_op->bs_op);
-#endif
-}

src/test/test_cluster_client.cpp

@@ -121,6 +121,7 @@ void pretend_connected(cluster_client_t *cli, osd_num_t osd_num)
     cli->msgr.osd_peer_fds[osd_num] = peer_fd;
     cli->msgr.clients[peer_fd] = new osd_client_t();
     cli->msgr.clients[peer_fd]->osd_num = osd_num;
+    cli->msgr.clients[peer_fd]->peer_fd = peer_fd;
     cli->msgr.clients[peer_fd]->peer_state = PEER_CONNECTED;
     cli->msgr.wanted_peers.erase(osd_num);
     cli->msgr.repeer_pgs(osd_num);

src/util/ringloop.cpp

@@ -125,6 +125,8 @@ void ring_loop_t::loop()
         if (cqe->flags & IORING_CQE_F_MORE)
         {
             // There will be a second notification
+            if (mt)
+                mu.unlock();
             d->res = cqe->res;
             d->more = true;
             if (d->callback)

tests/run_tests.sh

@@ -10,6 +10,8 @@ cd $(dirname $0)
 ./test_change_pg_count.sh
 SCHEME=ec ./test_change_pg_count.sh
 
+./test_change_pg_count_online.sh
+
 ./test_change_pg_size.sh
 
 ./test_create_nomaxid.sh
@@ -59,6 +61,7 @@ SCHEME=ec IMMEDIATE_COMMIT=1 ./test_rebalance_verify.sh
 
 ./test_write.sh
 SCHEME=xor ./test_write.sh
+TEST_NAME=iothreads GLOBAL_CONFIG=',"client_iothread_count":4' ./test_write.sh
 
 ./test_write_no_same.sh
 

tests/test_change_pg_count_online.sh

@@ -0,0 +1,61 @@
+#!/bin/bash -ex
+
+OSD_COUNT=${OSD_COUNT:-6}
+PG_COUNT=16
+GLOBAL_CONFIG=',"client_retry_interval":1000'
+
+. `dirname $0`/run_3osds.sh
+
+LD_PRELOAD="build/src/client/libfio_vitastor.so" \
+fio -thread -name=test -ioengine=build/src/client/libfio_vitastor.so -bs=4M -direct=1 -iodepth=1 -fsync=1 -rw=write \
+    -etcd=$ETCD_URL -pool=1 -inode=2 -size=128M
+
+LD_PRELOAD="build/src/client/libfio_vitastor.so" \
+fio -thread -name=test -ioengine=build/src/client/libfio_vitastor.so -bs=4k -direct=1 -iodepth=4 -rw=randrw \
+    -etcd=$ETCD_URL -pool=1 -inode=2 -size=128M -loops=100 -cluster_log_level=3 -runtime=60 &>./testdata/fio.log &
+FIO_PID=$!
+
+try_change()
+{
+    n=$1
+
+    for i in {1..6}; do
+        echo --- Change PG count to $n --- >>testdata/osd$i.log
+    done
+    echo --- Change PG count to $n --- >>testdata/mon.log
+
+    $ETCDCTL put /vitastor/config/pools '{"1":{'$POOLCFG',"pg_size":'$PG_SIZE',"pg_minsize":'$PG_MINSIZE',"pg_count":'$n'}}'
+    echo "Pool 1 (testpool) PG count changed from $PG_COUNT to $n" >> testdata/pgr.log
+    PG_COUNT=$n
+
+    sleep 10
+}
+
+sleep 5
+
+# 16 -> 32
+
+try_change 32
+
+# 32 -> 16
+
+try_change 16
+
+# 16 -> 25
+
+try_change 25
+
+# 25 -> 17
+
+try_change 17
+
+# 17 -> 16
+
+try_change 16
+
+wait $FIO_PID
+
+grep -P 'Pool 1 \(testpool\) PG count changed from \d+ to \d+' testdata/fio.log > testdata/pgc.log
+diff testdata/pgr.log testdata/pgc.log
+
+format_green OK