Release 2.4.1

- Optimize WA - reduce it from 4-5 to 3.x by batching journal writes
- Fix ls-pool showing wrong used % when osds are reweighted (#105)
- Fix vitastor-cli rm sometimes hanging when PGs are down (#99)
- Fix vitastor-cli ls displaying raw used space for all inodes when -p is specified (#101)
- Fix "Cannot set property of undefined" in monitor when deleting pool with live inode op stats (#103)
- Revert vitastor-kv change from 2.2.0 leading to crashes in vitastor-kv-stress (#100)
- Add pg_size change check for XOR pools
- Fix root access to VitastorFS files
- Add IPv6 support to make-etcd
- Fix IPv6 etcd address support in OSD & client library

.gitea/workflows/buildenv.Dockerfile

@@ -20,7 +20,7 @@ RUN echo 'deb http://deb.debian.org/debian bullseye-backports main' >> /etc/apt/
 
 RUN apt-get update
 RUN apt-get -y install etcd qemu-system-x86 qemu-block-extra qemu-utils fio libasan5 \
-    liburing1 liburing-dev libgoogle-perftools-dev devscripts libjerasure-dev cmake libibverbs-dev libisal-dev
+    libgoogle-perftools-dev devscripts libjerasure-dev cmake libibverbs-dev libisal-dev
 RUN apt-get -y build-dep fio qemu=`dpkg -s qemu-system-x86|grep ^Version:|awk '{print $2}'`
 RUN apt-get update && apt-get -y install jq lp-solve sudo nfs-common fdisk parted
 RUN apt-get --download-only source fio qemu=`dpkg -s qemu-system-x86|grep ^Version:|awk '{print $2}'`

.gitea/workflows/test.yml

@@ -810,6 +810,60 @@ jobs:
           echo ""
         done
 
+  test_reweight_half:
+    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_reweight_half.sh
+    - name: Print logs
+      if: always() && steps.test.outcome == 'failure'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
+  test_snapshot_pool2:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 3
+      run: /root/vitastor/tests/test_snapshot_pool2.sh
+    - name: Print logs
+      if: always() && steps.test.outcome == 'failure'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
+  test_snapshot_read_bitmap:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 3
+      run: /root/vitastor/tests/test_snapshot_read_bitmap.sh
+    - name: Print logs
+      if: always() && steps.test.outcome == 'failure'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
   test_heal_csum_32k_dmj:
     runs-on: ubuntu-latest
     needs: build
@@ -954,24 +1008,6 @@ jobs:
           echo ""
         done
 
-  test_snapshot_pool2:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 3
-      run: /root/vitastor/tests/test_snapshot_pool2.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_osd_tags:
     runs-on: ubuntu-latest
     needs: build

CMakeLists.txt

@@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8.12)
 
 project(vitastor)
 
-set(VITASTOR_VERSION "2.2.3")
+set(VITASTOR_VERSION "2.4.1")
 
 add_subdirectory(src)

README-ru.md

@@ -19,7 +19,7 @@ Vitastor нацелен в первую очередь на SSD и SSD+HDD кл
 TCP и RDMA и на хорошем железе может достигать задержки 4 КБ чтения и записи на уровне ~0.1 мс,
 что примерно в 10 раз быстрее, чем Ceph и другие популярные программные СХД.
 
-Vitastor поддерживает QEMU-драйвер, протоколы NBD и NFS, драйверы OpenStack, OpenNebula, Proxmox, Kubernetes.
+Vitastor поддерживает QEMU-драйвер, протоколы UBLK, NBD и NFS, драйверы OpenStack, OpenNebula, Proxmox, Kubernetes.
 Другие драйверы могут также быть легко реализованы.
 
 Подробности смотрите в документации по ссылкам. Можете начать отсюда: [Быстрый старт](docs/intro/quickstart.ru.md).
@@ -64,8 +64,9 @@ Vitastor поддерживает QEMU-драйвер, протоколы NBD и
   - [vitastor-cli](docs/usage/cli.ru.md) (консольный интерфейс)
   - [vitastor-disk](docs/usage/disk.ru.md) (управление дисками)
   - [fio](docs/usage/fio.ru.md) для тестов производительности
-  - [NBD](docs/usage/nbd.ru.md) для монтирования ядром
-  - [QEMU и qemu-img](docs/usage/qemu.ru.md)
+  - [UBLK](docs/usage/ublk.ru.md) для монтирования ядром
+  - [NBD](docs/usage/nbd.ru.md) - старый интерфейс для монтирования ядром
+  - [QEMU, qemu-img и VDUSE](docs/usage/qemu.ru.md)
   - [NFS](docs/usage/nfs.ru.md) кластерная файловая система и псевдо-ФС прокси
   - [Администрирование](docs/usage/admin.ru.md)
 - Производительность

README.md

@@ -19,7 +19,7 @@ supports TCP and RDMA and may achieve 4 KB read and write latency as low as ~0.1
 with proper hardware which is ~10 times faster than other popular SDS's like Ceph
 or internal systems of public clouds.
 
-Vitastor supports QEMU, NBD, NFS protocols, OpenStack, OpenNebula, Proxmox, Kubernetes drivers.
+Vitastor supports QEMU, UBLK, NBD, NFS protocols, OpenStack, OpenNebula, Proxmox, Kubernetes drivers.
 More drivers may be created easily.
 
 Read more details in the documentation. You can start from here: [Quick Start](docs/intro/quickstart.en.md).
@@ -64,8 +64,9 @@ Read more details in the documentation. You can start from here: [Quick Start](d
   - [vitastor-cli](docs/usage/cli.en.md) (command-line interface)
   - [vitastor-disk](docs/usage/disk.en.md) (disk management tool)
   - [fio](docs/usage/fio.en.md) for benchmarks
-  - [NBD](docs/usage/nbd.en.md) for kernel mounts
-  - [QEMU and qemu-img](docs/usage/qemu.en.md)
+  - [UBLK](docs/usage/ublk.en.md) for kernel mounts
+  - [NBD](docs/usage/nbd.en.md) - old interface for kernel mounts
+  - [QEMU, qemu-img and VDUSE](docs/usage/qemu.en.md)
   - [NFS](docs/usage/nfs.en.md) clustered file system and pseudo-FS proxy
   - [Administration](docs/usage/admin.en.md)
 - Performance

csi/Dockerfile

@@ -36,7 +36,7 @@ RUN (echo deb http://vitastor.io/debian bookworm main > /etc/apt/sources.list.d/
     ((echo 'Package: *'; echo 'Pin: origin "vitastor.io"'; echo 'Pin-Priority: 1000') > /etc/apt/preferences.d/vitastor.pref) && \
     wget -q -O /etc/apt/trusted.gpg.d/vitastor.gpg https://vitastor.io/debian/pubkey.gpg && \
     apt-get update && \
-    apt-get install -y vitastor-client && \
+    apt-get install -y vitastor-client ibverbs-providers && \
     wget https://vitastor.io/archive/qemu/qemu-bookworm-9.2.2%2Bds-1%2Bvitastor4/qemu-utils_9.2.2%2Bds-1%2Bvitastor4_amd64.deb && \
     wget https://vitastor.io/archive/qemu/qemu-bookworm-9.2.2%2Bds-1%2Bvitastor4/qemu-block-extra_9.2.2%2Bds-1%2Bvitastor4_amd64.deb && \
     dpkg -x qemu-utils*.deb tmp1 && \

csi/Dockerfile.local

@@ -0,0 +1,49 @@
+# Compile stage
+FROM golang:bookworm AS build
+
+ADD go.sum go.mod /app/
+RUN cd /app; CGO_ENABLED=1 GOOS=linux GOARCH=amd64 go mod download -x
+ADD . /app
+RUN perl -i -e '$/ = undef; while(<>) { s/\n\s*(\{\s*\n)/$1\n/g; s/\}(\s*\n\s*)else\b/$1} else/g; print; }' `find /app -name '*.go'` && \
+    cd /app && \
+    CGO_ENABLED=1 GOOS=linux GOARCH=amd64 go build -o vitastor-csi
+
+# Final stage
+FROM debian:bookworm
+
+LABEL maintainers="Vitaliy Filippov <vitalif@yourcmc.ru>"
+LABEL description="Vitastor CSI Driver"
+
+ENV NODE_ID=""
+ENV CSI_ENDPOINT=""
+
+RUN apt-get update && \
+    apt-get install -y wget && \
+    (echo "APT::Install-Recommends false;" > /etc/apt/apt.conf) && \
+    apt-get update && \
+    apt-get install -y e2fsprogs xfsprogs kmod iproute2 \
+        # NFS mount dependencies
+        nfs-common netbase \
+        # dependencies of qemu-storage-daemon
+        libnuma1 liburing2 libglib2.0-0 libfuse3-3 libaio1 libzstd1 libnettle8 \
+        libgmp10 libhogweed6 libp11-kit0 libidn2-0 libunistring2 libtasn1-6 libpcre2-8-0 libffi8 && \
+    apt-get clean && \
+    (echo options nbd nbds_max=128 > /etc/modprobe.d/nbd.conf)
+
+COPY --from=build /app/vitastor-csi /bin/
+
+ADD deb /deb
+
+RUN apt-get update && \
+    apt-get -y install /deb/vitastor-client_*.deb && \
+    wget https://vitastor.io/archive/qemu/qemu-bookworm-9.2.2%2Bds-1%2Bvitastor4/qemu-utils_9.2.2%2Bds-1%2Bvitastor4_amd64.deb && \
+    wget https://vitastor.io/archive/qemu/qemu-bookworm-9.2.2%2Bds-1%2Bvitastor4/qemu-block-extra_9.2.2%2Bds-1%2Bvitastor4_amd64.deb && \
+    dpkg -x qemu-utils*.deb tmp1 && \
+    dpkg -x qemu-block-extra*.deb tmp1 && \
+    cp -a tmp1/usr/bin/qemu-storage-daemon /usr/bin/ && \
+    mkdir -p /usr/lib/x86_64-linux-gnu/qemu && \
+    cp -a tmp1/usr/lib/x86_64-linux-gnu/qemu/block-vitastor.so /usr/lib/x86_64-linux-gnu/qemu/ && \
+    rm -rf tmp1 *.deb && \
+    apt-get clean
+
+ENTRYPOINT ["/bin/vitastor-csi"]

csi/Makefile

@@ -1,4 +1,4 @@
-VITASTOR_VERSION ?= v2.2.3
+VITASTOR_VERSION ?= v2.4.1
 
 all: build push
 

csi/deploy/004-csi-nodeplugin.yaml

@@ -49,7 +49,7 @@ spec:
             capabilities:
               add: ["SYS_ADMIN"]
             allowPrivilegeEscalation: true
-          image: vitalif/vitastor-csi:v2.2.3
+          image: vitalif/vitastor-csi:v2.4.1
           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:v2.2.3
+          image: vitalif/vitastor-csi:v2.4.1
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/src/config.go

@@ -5,7 +5,7 @@ package vitastor
 
 const (
     vitastorCSIDriverName    = "csi.vitastor.io"
-    vitastorCSIDriverVersion = "2.2.3"
+    vitastorCSIDriverVersion = "2.4.1"
 )
 
 // Config struct fills the parameters of request or user input

csi/src/nodeserver.go

@@ -33,7 +33,7 @@ import (
 type NodeServer struct
 {
     *Driver
-    useVduse        bool
+    method          MountMethod
     stateDir        string
     nfsStageDir     string
     mounter         mount.Interface
@@ -81,16 +81,23 @@ func NewNodeServer(driver *Driver) *NodeServer
     }
     ns := &NodeServer{
         Driver:      driver,
-        useVduse:    checkVduseSupport(),
+        method:      selectMountMethod(),
         stateDir:    stateDir,
         nfsStageDir: nfsStageDir,
         mounter:     mount.New(""),
         volumeLocks: make(map[string]bool),
     }
     ns.cond = sync.NewCond(&ns.mu)
-    if (ns.useVduse)
+    if (ns.method == MOUNT_VDUSE)
     {
         ns.restoreVduseDaemons()
+    }
+    else if (ns.method == MOUNT_UBLK)
+    {
+        ns.restoreUblkDaemons()
+    }
+    if (ns.method == MOUNT_VDUSE || ns.method == MOUNT_UBLK)
+    {
         dur, err := time.ParseDuration(os.Getenv("RESTART_INTERVAL"))
         if (err != nil)
         {
@@ -136,7 +143,14 @@ func (ns *NodeServer) restarter()
     for
     {
         <-ticker.C
-        ns.restoreVduseDaemons()
+        if (ns.method == MOUNT_VDUSE)
+        {
+            ns.restoreVduseDaemons()
+        }
+        else if (ns.method == MOUNT_UBLK)
+        {
+            ns.restoreUblkDaemons()
+        }
     }
 }
 
@@ -231,6 +245,78 @@ func (ns *NodeServer) checkVduseState(stateFile string, devs map[string]interfac
     }
 }
 
+func (ns *NodeServer) restoreUblkDaemons()
+{
+    pattern := ns.stateDir+"vitastor-ublk-*.json"
+    stateFiles, err := filepath.Glob(pattern)
+    if (err != nil)
+    {
+        klog.Errorf("failed to list %s: %v", pattern, err)
+    }
+    if (len(stateFiles) == 0)
+    {
+        return
+    }
+    for _, stateFile := range stateFiles
+    {
+        deviceNum := stateFile[len(ns.stateDir) + len("vitastor-ublk-") :]
+        deviceNum = deviceNum[0:len(deviceNum)-5]
+        ns.checkUblkState(deviceNum)
+    }
+}
+
+func (ns *NodeServer) checkUblkState(deviceNum string)
+{
+    // Check if the ublk daemon is still active
+
+    // Read state file
+    stateFile := ns.stateDir + "vitastor-ublk-" + deviceNum + ".json"
+    stateJSON, err := os.ReadFile(stateFile)
+    if (err != nil)
+    {
+        klog.Warningf("error reading state file %v: %v", stateFile, err)
+        return
+    }
+    var state DeviceState
+    err = json.Unmarshal(stateJSON, &state)
+    if (err != nil)
+    {
+        klog.Warningf("state file %v contains invalid JSON (error %v): %v", stateFile, err, string(stateJSON))
+        return
+    }
+
+    // Lock volume
+    ns.lockVolume(state.ConfigPath+":block:"+state.Image)
+    defer ns.unlockVolume(state.ConfigPath+":block:"+state.Image)
+
+    // Recheck state file after locking
+    _, err = os.ReadFile(stateFile)
+    if (err != nil)
+    {
+        klog.Warningf("state file %v disappeared, skipping volume", stateFile)
+        return
+    }
+
+    // Check if the vitastor-ublk process is still active
+    pidFile := ns.stateDir + "vitastor-ublk-" + deviceNum + ".pid"
+    exists := false
+    proc, err := findByPidFile(pidFile)
+    if (err == nil)
+    {
+        exists = proc.Signal(syscall.Signal(0)) == nil
+    }
+    if (!exists)
+    {
+        // Restart daemon
+        klog.Warningf("recovering UBLK device /dev/ublkb%v for volume %v", deviceNum, state.Image)
+        _, err = mapUblk(ns.stateDir, state.Image, state.ConfigPath, state.Readonly, "/dev/ublkb"+deviceNum)
+        if (err != nil)
+        {
+            klog.Warningf("failed to recover ublk device for volume %v: %v", state.Image, err)
+        }
+    }
+}
+
 func (ns *NodeServer) restoreNfsDaemons()
 {
     pattern := ns.stateDir+"vitastor-nfs-*.json"
@@ -417,14 +503,18 @@ func (ns *NodeServer) NodeStageVolume(ctx context.Context, req *csi.NodeStageVol
     }
 
     var devicePath, vdpaId string
-    if (!ns.useVduse)
+    if (ns.method == MOUNT_UBLK)
     {
-        devicePath, err = mapNbd(volName, ctxVars, false)
+        devicePath, err = mapUblk(ns.stateDir, volName, ctxVars["configPath"], false, "")
     }
-    else
+    else if (ns.method == MOUNT_VDUSE)
     {
         devicePath, vdpaId, err = mapVduse(ns.stateDir, volName, ctxVars, false)
     }
+    else /* if (ns.method == MOUNT_NBD) */
+    {
+        devicePath, err = mapNbd(volName, ctxVars, false)
+    }
     if (err != nil)
     {
         return nil, err
@@ -439,7 +529,8 @@ func (ns *NodeServer) NodeStageVolume(ctx context.Context, req *csi.NodeStageVol
     else
     {
         // Check existing format
-        existingFormat, err := diskMounter.GetDiskFormat(devicePath)
+        var existingFormat string
+        existingFormat, err = diskMounter.GetDiskFormat(devicePath)
         if (err != nil)
         {
             klog.Errorf("failed to get disk format for path %s, error: %v", err)
@@ -495,10 +586,6 @@ func (ns *NodeServer) NodeStageVolume(ctx context.Context, req *csi.NodeStageVol
                 case "xfs":
                     _, err = systemCombined("xfs_growfs", devicePath)
             }
-            if (err != nil)
-            {
-                goto unmap
-            }
         }
     }
     if (err != nil)
@@ -512,14 +599,18 @@ func (ns *NodeServer) NodeStageVolume(ctx context.Context, req *csi.NodeStageVol
     return &csi.NodeStageVolumeResponse{}, nil
 
 unmap:
-    if (!ns.useVduse || len(devicePath) >= 8 && devicePath[0:8] == "/dev/nbd")
+    if (ns.method == MOUNT_UBLK)
     {
-        unmapNbd(devicePath)
+        unmapUblk(ns.stateDir, devicePath)
     }
-    else
+    else if (ns.method == MOUNT_VDUSE)
     {
         unmapVduseById(ns.stateDir, vdpaId)
     }
+    else /* if (ns.method == MOUNT_NBD) */
+    {
+        unmapNbd(devicePath)
+    }
     return nil, err
 }
 
@@ -545,7 +636,7 @@ func (ns *NodeServer) NodeUnstageVolume(ctx context.Context, req *csi.NodeUnstag
     defer ns.unlockVolume(ctxVars["configPath"]+":block:"+volName)
 
     targetPath := req.GetStagingTargetPath()
-    devicePath, _, err := mount.GetDeviceNameFromMount(ns.mounter, targetPath)
+    devicePath, err := GetDeviceNameFromMount(targetPath)
     if (err != nil)
     {
         if (os.IsNotExist(err))
@@ -582,14 +673,18 @@ func (ns *NodeServer) NodeUnstageVolume(ctx context.Context, req *csi.NodeUnstag
     // unmap device
     if (len(refList) == 0)
     {
-        if (!ns.useVduse)
+        if (ns.method == MOUNT_UBLK)
         {
-            unmapNbd(devicePath)
+            unmapUblk(ns.stateDir, devicePath)
         }
-        else
+        else if (ns.method == MOUNT_VDUSE)
         {
             unmapVduse(ns.stateDir, devicePath)
         }
+        else /* if (ns.method == MOUNT_NBD) */
+        {
+            unmapNbd(devicePath)
+        }
     }
 
     return &csi.NodeUnstageVolumeResponse{}, nil
@@ -897,7 +992,7 @@ func (ns *NodeServer) NodeUnpublishVolume(ctx context.Context, req *csi.NodeUnpu
     }
 
     targetPath := req.GetTargetPath()
-    devicePath, _, err := mount.GetDeviceNameFromMount(ns.mounter, targetPath)
+    devicePath, err := GetDeviceNameFromMount(targetPath)
     if (err != nil)
     {
         if (os.IsNotExist(err))

csi/src/utils.go

@@ -16,10 +16,20 @@ import (
     "syscall"
 
     "k8s.io/klog"
+    "k8s.io/utils/mount"
+
     "google.golang.org/grpc/codes"
     "google.golang.org/grpc/status"
 )
 
+type MountMethod int
+
+const (
+    MOUNT_NBD   MountMethod = 0
+    MOUNT_VDUSE MountMethod = 1
+    MOUNT_UBLK  MountMethod = 2
+)
+
 func Contains(list []string, s string) bool
 {
     for i := 0; i < len(list); i++
@@ -32,29 +42,26 @@ func Contains(list []string, s string) bool
     return false
 }
 
-func checkVduseSupport() bool
+func selectMountMethod() MountMethod
 {
+    // Check UBLK support (ublk_drv kernel module)
+    if (checkModule("ublk_drv"))
+    {
+        klog.Infof("UBLK support enabled successfully")
+        return MOUNT_UBLK
+    }
+    klog.Errorf(
+        "Your host apparently has no UBLK support. UBLK support disabled."+
+        " For UBLK you need at least Linux 6.0 and the ublk_drv kernel module.",
+    )
     // Check VDUSE support (vdpa, vduse, virtio-vdpa kernel modules)
     vduse := true
     for _, mod := range []string{"vdpa", "vduse", "virtio-vdpa"}
     {
-        _, err := os.Stat("/sys/module/"+mod)
-        if (err != nil)
+        if (!checkModule(mod))
         {
-            if (!errors.Is(err, os.ErrNotExist))
-            {
-                klog.Errorf("failed to check /sys/module/%s: %v", mod, err)
-            }
-            c := exec.Command("/sbin/modprobe", mod)
-            c.Stdout = os.Stderr
-            c.Stderr = os.Stderr
-            err := c.Run()
-            if (err != nil)
-            {
-                klog.Errorf("/sbin/modprobe %s failed: %v", mod, err)
-                vduse = false
-                break
-            }
+            vduse = false
+            break
         }
     }
     // Check that vdpa tool functions
@@ -69,18 +76,38 @@ func checkVduseSupport() bool
             vduse = false
         }
     }
-    if (!vduse)
-    {
-        klog.Errorf(
-            "Your host apparently has no VDUSE support. VDUSE support disabled, NBD will be used to map devices."+
-            " For VDUSE you need at least Linux 5.15 and the following kernel modules: vdpa, virtio-vdpa, vduse.",
-        )
-    }
-    else
+    if (vduse)
     {
         klog.Infof("VDUSE support enabled successfully")
+        return MOUNT_VDUSE
     }
-    return vduse
+    klog.Errorf(
+        "Your host apparently has no VDUSE support. VDUSE support disabled, NBD will be used to map devices."+
+        " For VDUSE you need at least Linux 5.15 and the following kernel modules: vdpa, virtio-vdpa, vduse.",
+    )
+    return MOUNT_NBD
+}
+
+func checkModule(mod string) bool
+{
+    _, err := os.Stat("/sys/module/"+mod)
+    if (err != nil)
+    {
+        if (!errors.Is(err, os.ErrNotExist))
+        {
+            klog.Errorf("failed to check /sys/module/%s: %v", mod, err)
+        }
+        c := exec.Command("/sbin/modprobe", mod)
+        c.Stdout = os.Stderr
+        c.Stderr = os.Stderr
+        err := c.Run()
+        if (err != nil)
+        {
+            klog.Errorf("/sbin/modprobe %s failed: %v", mod, err)
+            return false
+        }
+    }
+    return true
 }
 
 func mapNbd(volName string, ctxVars map[string]string, readonly bool) (string, error)
@@ -217,6 +244,7 @@ func mapVduse(stateDir string, volName string, ctxVars map[string]string, readon
                     stateJSON, _ := json.Marshal(&DeviceState{
                         ConfigPath: ctxVars["configPath"],
                         VdpaId:     vdpaId,
+
                         Image:      volName,
                         Blockdev:   blockdev,
                         Readonly:   readonly,
@@ -309,6 +337,117 @@ func unmapVduseById(stateDir, vdpaId string)
     }
 }
 
+func mapUblk(stateDir string, volName string, configPath string, readonly bool, recoverDev string) (string, error)
+{
+    pidFile := ""
+    if (recoverDev != "")
+    {
+        if (len(recoverDev) < 10 || recoverDev[0:10] != "/dev/ublkb")
+        {
+            return "", fmt.Errorf("recover: %s does not start with /dev/ublkb", recoverDev)
+        }
+        pidFile = stateDir + "vitastor-ublk-" + recoverDev[10:] + ".pid"
+    }
+    else
+    {
+        pidFd, err := os.CreateTemp(stateDir, "vitastor-tmp-*.pid")
+        if (err != nil)
+        {
+            return "", err
+        }
+        pidFile = pidFd.Name()
+        pidFd.Close()
+    }
+    // Map device via vitastor-ublk
+    args := []string{
+        "map", "--image", volName, "--pidfile", pidFile,
+    }
+    if (configPath != "")
+    {
+        args = append(args, "--config_path", configPath)
+    }
+    if (readonly)
+    {
+        args = append(args, "--readonly")
+    }
+    if (recoverDev != "")
+    {
+        args = append(args, "--recover", recoverDev)
+    }
+    stdout, stderr, err := system("/usr/bin/vitastor-ublk", args...)
+    if (err != nil)
+    {
+        return "", err
+    }
+    devicePath := strings.TrimSpace(string(stdout))
+    if (devicePath == "")
+    {
+        return "", fmt.Errorf("vitastor-ublk did not return the name of the device. output: %s", stderr)
+    }
+    if (len(devicePath) >= 10 && devicePath[0:10] == "/dev/ublkb")
+    {
+        // Generate state file
+        devNum := devicePath[10:]
+        pidNew := stateDir + "vitastor-ublk-" + devNum + ".pid"
+        if (pidFile != pidNew)
+        {
+            err := os.Rename(pidFile, pidNew)
+            if (err != nil)
+            {
+                klog.Errorf("Failed to rename PID file %s to %s: %v", pidFile, pidNew, err)
+            }
+            else
+            {
+                pidFile = pidNew
+            }
+        }
+        stateFile := stateDir + "vitastor-ublk-" + devNum + ".json"
+        stateJSON, _ := json.Marshal(&DeviceState{
+            ConfigPath: configPath,
+            Image:      volName,
+            Readonly:   readonly,
+            PidFile:    pidFile,
+        })
+        err = os.WriteFile(stateFile, stateJSON, 0600)
+        if (err == nil)
+        {
+            klog.Infof("Attached volume %s via UBLK as %s", volName, devicePath)
+            return devicePath, nil
+        }
+        os.Remove(stateFile)
+    }
+    killErr := killByPidFile(pidFile)
+    if (killErr != nil)
+    {
+        klog.Errorf("Failed to kill started vitastor-ublk: %v", killErr)
+    }
+    os.Remove(pidFile)
+    return "", err
+}
+
+func unmapUblk(stateDir, devicePath string)
+{
+    if (len(devicePath) < 10 || devicePath[0:10] != "/dev/ublkb")
+    {
+        klog.Errorf("%s does not start with /dev/ublkb", devicePath)
+        return
+    }
+    unmapOut, unmapErr := exec.Command("/usr/bin/vitastor-ublk", "unmap", devicePath).CombinedOutput()
+    if (unmapErr != nil)
+    {
+        klog.Errorf("failed to unmap UBLK device %s: %s, error: %v", devicePath, unmapOut, unmapErr)
+    }
+    for _, ext := range []string{"json", "pid"}
+    {
+        fn := stateDir + "vitastor-ublk-" + devicePath[10:] + "." + ext
+        err := os.Remove(fn)
+        if (err != nil)
+        {
+            klog.Errorf("failed to remove %s: %v", fn, err)
+        }
+    }
+}
+
 func system(program string, args ...string) ([]byte, []byte, error)
 {
     klog.Infof("Running "+program+" "+strings.Join(args, " "))
@@ -340,3 +479,43 @@ func systemCombined(program string, args ...string) ([]byte, error)
     }
     return out.Bytes(), nil
 }
+
+func GetDeviceNameFromMount(mountPath string) (string, error)
+{
+    // Use /proc/self/mountinfo to correctly parse bind mounts for block device files
+    mps, err := mount.ParseMountInfo("/proc/self/mountinfo")
+    if (err != nil)
+    {
+        return "", err
+    }
+
+    slTarget, err := filepath.EvalSymlinks(mountPath)
+    if (err != nil)
+    {
+        slTarget = mountPath
+    }
+
+    device := ""
+    for _, mp := range mps
+    {
+        if (mp.MountPoint == slTarget)
+        {
+            device = mp.Source
+            if (device[0] != '/' && mp.Root != "/")
+            {
+                // Handle {Source=udev Root=/vdb MountPoint=/var/lib/kubelet/tralaleylo/tralala}
+                for _, other := range mps
+                {
+                    if (other.Root == "/" && other.Source == mp.Source)
+                    {
+                        device = other.MountPoint + mp.Root
+                        break
+                    }
+                }
+            }
+            break
+        }
+    }
+
+    return device, nil
+}

debian/build-vitastor-trixie.sh

@@ -0,0 +1,4 @@
+#!/bin/bash
+
+docker build --build-arg DISTRO=debian --build-arg REL=trixie -t vitastor-buildenv:trixie -f vitastor-buildenv.Dockerfile .
+docker run -i --rm -e REL=trixie -v `dirname $0`/../:/root/vitastor vitastor-buildenv:trixie /root/vitastor/debian/vitastor-build.sh

debian/changelog

@@ -1,4 +1,4 @@
-vitastor (2.2.3-1) unstable; urgency=medium
+vitastor (2.4.1-1) unstable; urgency=medium
 
   * Bugfixes
 

debian/control

@@ -2,9 +2,9 @@ Source: vitastor
 Section: admin
 Priority: optional
 Maintainer: Vitaliy Filippov <vitalif@yourcmc.ru>
-Build-Depends: debhelper, liburing-dev (>= 0.6), g++ (>= 8), libstdc++6 (>= 8),
+Build-Depends: debhelper, g++ (>= 8), libstdc++6 (>= 8),
   linux-libc-dev, libgoogle-perftools-dev, libjerasure-dev, libgf-complete-dev,
-  libibverbs-dev, libisal-dev, cmake, pkg-config, libnl-3-dev, libnl-genl-3-dev,
+  libibverbs-dev, librdmacm-dev, libisal-dev, cmake, pkg-config, libnl-3-dev, libnl-genl-3-dev,
   node-bindings <!nocheck>, node-gyp, node-nan
 Standards-Version: 4.5.0
 Homepage: https://vitastor.io/

debian/patched-qemu.Dockerfile

@@ -26,7 +26,7 @@ RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" -o "$REL" = "bookworm" ]; then
     echo 'APT::Install-Suggests false;' >> /etc/apt/apt.conf
 
 RUN apt-get update
-RUN DEBIAN_FRONTEND=noninteractive TZ=Europe/Moscow apt-get -y install fio liburing-dev libgoogle-perftools-dev devscripts
+RUN DEBIAN_FRONTEND=noninteractive TZ=Europe/Moscow apt-get -y install fio libgoogle-perftools-dev devscripts
 RUN DEBIAN_FRONTEND=noninteractive TZ=Europe/Moscow apt-get -y build-dep qemu
 # To build a custom version
 #RUN cp /root/packages/qemu-orig/* /root

debian/vitastor-build.sh

@@ -51,6 +51,7 @@ 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?
+cd /root/vitastor/packages/vitastor-$REL
 if ls *.ddeb >/dev/null; then
     perl -i -pe 's/\.ddeb/.deb/' *.buildinfo *.changes
     for i in *.ddeb; do

debian/vitastor-buildenv.Dockerfile

@@ -25,7 +25,7 @@ RUN set -e -x; \
     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 \
+    apt-get -y install fio 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-client.install

@@ -2,6 +2,7 @@ usr/bin/vita
 usr/bin/vitastor-cli
 usr/bin/vitastor-rm
 usr/bin/vitastor-nbd
+usr/bin/vitastor-ublk
 usr/bin/vitastor-nfs
 usr/bin/vitastor-kv
 usr/bin/vitastor-kv-stress

docker/Dockerfile

@@ -3,7 +3,7 @@
 FROM debian:bookworm
 
 ADD etc/apt /etc/apt/
-RUN apt-get update && apt-get -y install vitastor udev systemd qemu-system-x86 qemu-system-common qemu-block-extra qemu-utils jq nfs-common && apt-get clean
+RUN apt-get update && apt-get -y install vitastor ibverbs-providers udev systemd qemu-system-x86 qemu-system-common qemu-block-extra qemu-utils jq nfs-common && apt-get clean
 ADD sleep.sh /usr/bin/
 ADD install.sh /usr/bin/
 ADD scripts /opt/scripts/

docker/Makefile

@@ -1,4 +1,4 @@
-VITASTOR_VERSION ?= v2.2.3
+VITASTOR_VERSION ?= v2.4.1
 
 all: build push
 

docker/etc/vitastor/docker.conf

@@ -4,7 +4,7 @@
 #
 
 # Desired Vitastor version
-VITASTOR_VERSION=v2.2.3
+VITASTOR_VERSION=v2.4.1
 
 # Additional arguments for all containers
 # For example, you may want to specify a custom logging driver here

docs/config/client.en.md

@@ -25,6 +25,9 @@ affect their interaction with the cluster.
 - [nbd_max_part](#nbd_max_part)
 - [osd_nearfull_ratio](#osd_nearfull_ratio)
 - [hostname](#hostname)
+- [ublk_queue_depth](#ublk_queue_depth)
+- [ublk_max_io_size](#ublk_max_io_size)
+- [qemu_file_mirror_path](#qemu_file_mirror_path)
 
 ## client_iothread_count
 
@@ -225,3 +228,28 @@ without destroying and recreating OSDs.
 Clients use host name to find their distance to OSDs when [localized reads](pool.en.md#local_reads)
 are enabled. By default, standard [gethostname](https://man7.org/linux/man-pages/man2/gethostname.2.html)
 function is used to determine host name, but you can also override it with this parameter.
+
+## ublk_queue_depth
+
+- Type: integer
+- Default: 256
+
+Default queue depth for [Vitastor ublk servers](../usage/ublk.en.md).
+
+## ublk_max_io_size
+
+- Type: integer
+
+Default maximum I/O size for Vitastor [ublk servers](../usage/ublk.en.md).
+The largest of 1 MB and pool block size multiplied by EC data chunk count is used if not specified.
+
+## qemu_file_mirror_path
+
+- Type: string
+
+When set to an FS directory path (for example, `/mnt/vitastor/`), `qemu-img info` and similar
+QAPI commands return the name of the image inside this directory instead of normal
+`vitastor://?image=abc` URI as `filename`.
+
+This allows to then mount this path using [vitastor-nfs](../usage/nfs.en.md) and trick
+third-party systems like Veeam which rely on `filename` in the image info but don't support Vitastor.

docs/config/client.ru.md

@@ -25,6 +25,9 @@
 - [nbd_max_part](#nbd_max_part)
 - [osd_nearfull_ratio](#osd_nearfull_ratio)
 - [hostname](#hostname)
+- [ublk_queue_depth](#ublk_queue_depth)
+- [ublk_max_io_size](#ublk_max_io_size)
+- [qemu_file_mirror_path](#qemu_file_mirror_path)
 
 ## client_iothread_count
 
@@ -230,3 +233,30 @@ RDMA и хотите повысить пиковую производитель
 [локальные чтения](pool.ru.md#local_reads). По умолчанию для определения имени
 хоста используется стандартная функция [gethostname](https://man7.org/linux/man-pages/man2/gethostname.2.html),
 но вы также можете задать имя хоста вручную данным параметром.
+
+## ublk_queue_depth
+
+- Тип: целое число
+- Значение по умолчанию: 256
+
+Глубина очереди по умолчанию для [ublk-серверов Vitastor](../usage/ublk.ru.md).
+
+## ublk_max_io_size
+
+- Тип: целое число
+
+Максимальный размер запроса ввода-вывода для [ublk-серверов Vitastor](../usage/ublk.ru.md).
+Если не задан, используется максимум из 1 МБ и размера блока пула, умноженного на число частей
+данных EC-пула.
+
+## qemu_file_mirror_path
+
+- Тип: строка
+
+Если установить эту опцию равной пути к каталогу в ФС, команда `qemu-img info` и подобные
+команды QAPI будут возвращать в поле `filename` имя образа внутри заданного каталога вместо
+обычного адреса типа `vitastor://?image=abc`.
+
+Это позволяет смонтировать этот путь с помощью [vitastor-nfs](../usage/nfs.ru.md) и обмануть
+сторонние системы типа Veeam, которые полагаются на поле `filename` в информации об образе QEMU,
+но не поддерживают Vitastor.

docs/config/src/client.yml

@@ -283,3 +283,36 @@
     [локальные чтения](pool.ru.md#local_reads). По умолчанию для определения имени
     хоста используется стандартная функция [gethostname](https://man7.org/linux/man-pages/man2/gethostname.2.html),
     но вы также можете задать имя хоста вручную данным параметром.
+- name: ublk_queue_depth
+  type: int
+  default: 256
+  online: false
+  info: Default queue depth for [Vitastor ublk servers](../usage/ublk.en.md).
+  info_ru: Глубина очереди по умолчанию для [ublk-серверов Vitastor](../usage/ublk.ru.md).
+- name: ublk_max_io_size
+  type: int
+  online: false
+  info: |
+    Default maximum I/O size for Vitastor [ublk servers](../usage/ublk.en.md).
+    The largest of 1 MB and pool block size multiplied by EC data chunk count is used if not specified.
+  info_ru: |
+    Максимальный размер запроса ввода-вывода для [ublk-серверов Vitastor](../usage/ublk.ru.md).
+    Если не задан, используется максимум из 1 МБ и размера блока пула, умноженного на число частей
+    данных EC-пула.
+- name: qemu_file_mirror_path
+  type: string
+  info: |
+    When set to an FS directory path (for example, `/mnt/vitastor/`), `qemu-img info` and similar
+    QAPI commands return the name of the image inside this directory instead of normal
+    `vitastor://?image=abc` URI as `filename`.
+
+    This allows to then mount this path using [vitastor-nfs](../usage/nfs.en.md) and trick
+    third-party systems like Veeam which rely on `filename` in the image info but don't support Vitastor.
+  info_ru: |
+    Если установить эту опцию равной пути к каталогу в ФС, команда `qemu-img info` и подобные
+    команды QAPI будут возвращать в поле `filename` имя образа внутри заданного каталога вместо
+    обычного адреса типа `vitastor://?image=abc`.
+
+    Это позволяет смонтировать этот путь с помощью [vitastor-nfs](../usage/nfs.ru.md) и обмануть
+    сторонние системы типа Veeam, которые полагаются на поле `filename` в информации об образе QEMU,
+    но не поддерживают Vitastor.

docs/config/src/included.en.md

@@ -24,6 +24,8 @@
 
 {{../../installation/kubernetes.en.md}}
 
+{{../../installation/s3.en.md}}
+
 {{../../installation/source.en.md}}
 
 {{../../config.en.md|indent=1}}
@@ -54,6 +56,8 @@
 
 {{../../usage/fio.en.md}}
 
+{{../../usage/ublk.en.md}}
+
 {{../../usage/nbd.en.md}}
 
 {{../../usage/qemu.en.md}}

docs/config/src/included.ru.md

@@ -26,6 +26,8 @@
 
 {{../../installation/source.ru.md}}
 
+{{../../installation/s3.ru.md}}
+
 {{../../config.ru.md|indent=1}}
 
 {{../../config/common.ru.md|indent=2}}
@@ -54,6 +56,8 @@
 
 {{../../usage/fio.ru.md}}
 
+{{../../usage/ublk.ru.md}}
+
 {{../../usage/nbd.ru.md}}
 
 {{../../usage/qemu.ru.md}}

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 vitalif/vitastor:v2.2.3`
+   `docker pull vitalif/vitastor:v2.4.1`
 2. Install scripts to the host system: \
-   `docker run --rm -it -v /etc:/host-etc -v /usr/bin:/host-bin vitalif/vitastor:v2.2.3 install.sh`
+   `docker run --rm -it -v /etc:/host-etc -v /usr/bin:/host-bin vitalif/vitastor:v2.4.1 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 vitalif/vitastor:v2.2.3`
+   `docker pull vitalif/vitastor:v2.4.1`
 2. Установите скрипты в хост-систему командой: \
-   `docker run --rm -it -v /etc:/host-etc -v /usr/bin:/host-bin vitalif/vitastor:v2.2.3 install.sh`
+   `docker run --rm -it -v /etc:/host-etc -v /usr/bin:/host-bin vitalif/vitastor:v2.4.1 install.sh`
 3. Перезагрузите правила udev: \
    `udevadm control --reload-rules`
 

docs/installation/openstack.en.md

@@ -30,7 +30,7 @@ volume_backend_name = vitastor-testcluster
 image_volume_cache_enabled = True
 volume_clear = none
 vitastor_etcd_address = 192.168.7.2:2379
-vitastor_etcd_prefix =
+vitastor_etcd_prefix = /vitastor
 vitastor_config_path = /etc/vitastor/vitastor.conf
 vitastor_pool_id = 1
 image_upload_use_cinder_backend = True

docs/installation/openstack.ru.md

@@ -29,7 +29,7 @@ volume_backend_name = vitastor-testcluster
 image_volume_cache_enabled = True
 volume_clear = none
 vitastor_etcd_address = 192.168.7.2:2379
-vitastor_etcd_prefix =
+vitastor_etcd_prefix = /vitastor
 vitastor_config_path = /etc/vitastor/vitastor.conf
 vitastor_pool_id = 1
 image_upload_use_cinder_backend = True

docs/installation/packages.en.md

@@ -11,13 +11,20 @@
 - Trust Vitastor package signing key:
   `wget https://vitastor.io/debian/pubkey.gpg -O /etc/apt/trusted.gpg.d/vitastor.gpg`
 - Add Vitastor package repository to your /etc/apt/sources.list:
-  - Debian 12 (Bookworm/Sid): `deb https://vitastor.io/debian bookworm main`
+  - Debian 13 (Trixie/Sid): `deb https://vitastor.io/debian trixie main`
+  - Debian 12 (Bookworm): `deb https://vitastor.io/debian bookworm main`
   - Debian 11 (Bullseye): `deb https://vitastor.io/debian bullseye main`
   - Debian 10 (Buster): `deb https://vitastor.io/debian buster main`
   - 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
+- To always prefer vitastor-patched QEMU and Libvirt versions, add the following to `/etc/apt/preferences`:
+  ```
+  Package: *
+  Pin: origin "vitastor.io"
+  Pin-Priority: 501
+  ```
 - Install packages: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu-system-x86`
 
 ## CentOS
@@ -43,7 +50,6 @@
   recommended because io_uring is a relatively new technology and there is
   at least one bug which reproduces with io_uring and HP SmartArray
   controllers in 5.4
-- liburing 0.4 or newer
 - lp_solve
 - etcd 3.4.15 or newer. Earlier versions won't work because of various bugs,
   for example [#12402](https://github.com/etcd-io/etcd/pull/12402).

docs/installation/packages.ru.md

@@ -11,13 +11,20 @@
 - Добавьте ключ репозитория Vitastor:
   `wget https://vitastor.io/debian/pubkey.gpg -O /etc/apt/trusted.gpg.d/vitastor.gpg`
 - Добавьте репозиторий Vitastor в /etc/apt/sources.list:
-  - Debian 12 (Bookworm/Sid): `deb https://vitastor.io/debian bookworm main`
+  - Debian 13 (Trixie/Sid): `deb https://vitastor.io/debian trixie main`
+  - Debian 12 (Bookworm): `deb https://vitastor.io/debian bookworm main`
   - Debian 11 (Bullseye): `deb https://vitastor.io/debian bullseye main`
   - Debian 10 (Buster): `deb https://vitastor.io/debian buster main`
   - 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
+- Чтобы всегда предпочитались версии пакетов QEMU и Libvirt с патчами Vitastor, добавьте в `/etc/apt/preferences`:
+  ```
+  Package: *
+  Pin: origin "vitastor.io"
+  Pin-Priority: 501
+  ```
 - Установите пакеты: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu-system-x86`
 
 ## CentOS
@@ -42,7 +49,6 @@
 - Ядро Linux 5.4 или новее, для поддержки io_uring. Рекомендуется даже 5.8,
   так как io_uring - относительно новый интерфейс и в версиях до 5.8 встречались
   некоторые баги, например, зависание с io_uring и контроллером HP SmartArray
-- liburing 0.4 или новее
 - lp_solve
 - etcd 3.4.15 или новее. Более старые версии не будут работать из-за разных багов,
   например, [#12402](https://github.com/etcd-io/etcd/pull/12402).

docs/installation/proxmox.en.md

@@ -9,7 +9,7 @@
 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
+  trixie for 9.0+, 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

@@ -9,7 +9,7 @@
 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
+  trixie для 9.0+, 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/installation/source.en.md

@@ -15,7 +15,7 @@
 - gcc and g++ 8 or newer, clang 10 or newer, or other compiler with C++11 plus
   designated initializers support from C++20
 - CMake
-- liburing, jerasure headers and libraries
+- jerasure headers and libraries
 - ISA-L, libibverbs and librdmacm headers and libraries (optional)
 - tcmalloc (google-perftools-dev)
 

docs/installation/source.ru.md

@@ -15,7 +15,7 @@
 - gcc и g++ >= 8, либо clang >= 10, либо другой компилятор с поддержкой C++11 плюс
   назначенных инициализаторов (designated initializers) из C++20
 - CMake
-- Заголовки и библиотеки liburing, jerasure
+- Заголовки и библиотеки jerasure
 - Опционально - заголовки и библиотеки ISA-L, libibverbs, librdmacm
 - tcmalloc (google-perftools-dev)
 

docs/intro/features.en.md

@@ -52,7 +52,7 @@
 - Generic user-space client library
 - [Native QEMU driver](../usage/qemu.en.md)
 - [Loadable fio engine for benchmarks](../usage/fio.en.md)
-- [NBD proxy for kernel mounts](../usage/nbd.en.md)
+- [UBLK](../usage/ublk.en.md) and [NBD](../usage/nbd.en.md) servers for kernel mounts
 - [Simplified NFS proxy for file-based image access emulation (suitable for VMWare)](../usage/nfs.en.md#pseudo-fs)
 
 ## Roadmap

docs/intro/features.ru.md

@@ -54,7 +54,7 @@
 - Общая пользовательская клиентская библиотека для работы с кластером
 - [Драйвер диска для QEMU](../usage/qemu.ru.md)
 - [Драйвер диска для утилиты тестирования производительности fio](../usage/fio.ru.md)
-- [NBD-прокси для монтирования образов ядром](../usage/nbd.ru.md) ("блочное устройство в режиме пользователя")
+- [UBLK](../usage/ublk.ru.md) и [NBD](../usage/nbd.ru.md) серверы для монтирования образов ядром ("блочное устройство в режиме пользователя")
 - [Упрощённая NFS-прокси для эмуляции файлового доступа к образам (подходит для VMWare)](../usage/nfs.ru.md#псевдо-фс)
 
 ## Планы развития

docs/usage/cli.en.md

@@ -100,12 +100,14 @@ List images (only matching `<glob>` pattern(s) if passed).
 Options:
 
 ```
+--exact         Do not match glob patterns as names, select only exact name matches.
 -p|--pool POOL  Filter images by pool ID or name
 -l|--long       Also report allocated size and I/O statistics
 --del           Also include delete operation statistics
 --sort FIELD    Sort by specified field (name, size, used_size, <read|write|delete>_<iops|bps|lat|queue>)
 -r|--reverse    Sort in descending order
 -n|--count N    Only list first N items
+--tree          Show image snapshot/clone tree
 ```
 
 Example output:

docs/usage/cli.ru.md

@@ -102,12 +102,14 @@ kaveri    2/1     32   0 B      10 G    0 B        100%    0%
 Опции:
 
 ```
+--exact         Не применять ФС-шаблоны к именам, выводить только точные совпадения
 -p|--pool POOL  Фильтровать образы по пулу (ID или имени)
 -l|--long       Также выводить статистику занятого места и ввода-вывода
 --del           Также выводить статистику операций удаления
 --sort FIELD    Сортировать по заданному полю (name, size, used_size, <read|write|delete>_<iops|bps|lat|queue>)
 -r|--reverse    Сортировать в обратном порядке
 -n|--count N    Показывать только первые N записей
+--tree          Вывести снапшоты и клоны в виде дерева
 ```
 
 Пример вывода:

docs/usage/disk.en.md

@@ -73,6 +73,8 @@ Options (automatic mode):
 --max_other 10%
   Use disks for OSD data even if they already have non-Vitastor partitions,
   but only if these take up no more than this percent of disk space.
+--dry-run
+  Check and print new OSD count for each disk but do not actually create them.
 ```
 
 Options (single-device mode):

docs/usage/disk.ru.md

@@ -74,6 +74,8 @@ vitastor-disk - инструмент командной строки для уп
 --max_other 10%
   Использовать диски под данные OSD, даже если на них уже есть не-Vitastor-овые
   разделы, но только в случае, если они занимают не более данного процента диска.
+--dry-run
+  Проверить и вывести число новых OSD для каждого диска, но не создавать их.
 ```
 
 Опции для режима одного OSD:

docs/usage/nfs.en.md

@@ -89,6 +89,8 @@ POSIX features currently not implemented in VitastorFS:
   instead of actually allocated space
 - Access times (`atime`) are not tracked (like `-o noatime`)
 - Modification time (`mtime`) is updated lazily every second (like `-o lazytime`)
+- Permission enforcement is disabled by default (and Linux NFS client doesn't
+  enforce them too). Use `--enforce 1` to enable it.
 
 Other notable missing features which should be addressed in the future:
 - Inode ID reuse. Currently inode IDs always grow, the limit is 2^48 inodes, so
@@ -258,4 +260,5 @@ Options:
 | `--nfspath <PATH>` | set NFS export path to \<PATH> (default is /)            |
 | `--pidfile <FILE>` | write process ID to the specified file                   |
 | `--logfile <FILE>` | log to the specified file                                |
+| `--enforce 1`      | enforce permissions at the server side (no by default)   |
 | `--foreground 1`   | stay in foreground, do not daemonize                     |

docs/usage/nfs.ru.md

@@ -91,6 +91,8 @@ JSON-формате :-). Для инспекции содержимого БД
   stat(2), так что `du` всегда показывает сумму размеров файлов, а не фактически занятое место
 - Времена доступа (`atime`) не отслеживаются (как будто ФС смонтирована с `-o noatime`)
 - Времена модификации (`mtime`) отслеживаются асинхронно (как будто ФС смонтирована с `-o lazytime`)
+- Привилегии доступа по умолчанию не проверяются сервером (клиент NFS Linux их также не проверяет).
+  Чтобы включить проверки, используйте опцию `--enforce 1`.
 
 Другие недостающие функции, которые нужно добавить в будущем:
 - Переиспользование номеров инодов. В текущей реализации номера инодов всё время
@@ -270,4 +272,5 @@ VitastorFS из GPUDirect.
 | `--nfspath <PATH>` | установить путь NFS-экспорта в \<PATH> (по умолчанию /) |
 | `--pidfile <FILE>` | записать ID процесса в заданный файл                    |
 | `--logfile <FILE>` | записывать логи в заданный файл                         |
+| `--enforce 1`      | проверять права доступа на стороне сервера (по умолчанию нет) |
 | `--foreground 1`   | не уходить в фон после запуска                          |

docs/usage/qemu.en.md

@@ -130,23 +130,16 @@ Linux kernel, starting with version 5.15, supports a new interface for attaching
 to the host - VDUSE (vDPA Device in Userspace). QEMU, starting with 7.2, has support for
 exporting QEMU block devices over this protocol using qemu-storage-daemon.
 
-VDUSE is currently the best interface to attach Vitastor disks as kernel devices because:
-- It avoids data copies and thus achieves much better performance than [NBD](nbd.en.md)
-- It doesn't have NBD timeout problem - the device doesn't die if an operation executes for too long
+VDUSE advantages:
+
+- VDUSE copies memory 1 time instead of 2, and is thus faster than [NBD](nbd.en.md) for linear read/write.
+- It doesn't have NBD timeout problem - the device doesn't die if an operation executes for too long.
 - It doesn't have hung device problem - if the userspace process dies it can be restarted (!)
-  and block device will continue operation
-- It doesn't seem to have the device number limit
+  and block device will continue operation (UBLK can do it too).
+- It doesn't seem to have the device number limit (UBLK also doesn't).
 
-Example performance comparison:
-
-|                      | direct fio  | NBD         | VDUSE       |
-|----------------------|-------------|-------------|-------------|
-| linear write         | 3.85 GB/s   | 1.12 GB/s   | 3.85 GB/s   |
-| 4k random write Q128 | 240000 iops | 120000 iops | 178000 iops |
-| 4k random write Q1   | 9500 iops   | 7620 iops   | 7640 iops   |
-| linear read          | 4.3 GB/s    | 1.8 GB/s    | 2.85 GB/s   |
-| 4k random read Q128  | 287000 iops | 140000 iops | 189000 iops |
-| 4k random read Q1    | 9600 iops   | 7640 iops   | 7780 iops   |
+At the same time, VDUSE may be slower or faster than [UBLK](ublk.en.md) for linear read/write,
+and iops-wise it's sometimes even slower than NBD. See performance comparison examples at the page [UBLK](ublk.en.md).
 
 To try VDUSE you need at least Linux 5.15, built with VDUSE support
 (CONFIG_VDPA=m, CONFIG_VDPA_USER=m, CONFIG_VIRTIO_VDPA=m).
@@ -193,3 +186,12 @@ To remove the device:
 vdpa dev del test1
 kill <qemu-storage-daemon_process_PID>
 ```
+
+## Veeam
+
+Vitastor QEMU driver has a feature that allows to trick third-party systems like Veeam not able to parse qemu-img
+vitastor URIs: [qemu_file_mirror_path](../config/client.en.md#qemu_file_mirror_path).
+
+To make such systems work, you should set this option to an FS directory path (for example, `/mnt/vitastor/`) and
+mount this directory using [`vitastor-nfs mount --block`](../usage/nfs.en.md). It will make them access
+your images using files and, hopefully, succeed in doing their normal job :).

docs/usage/qemu.ru.md

@@ -132,24 +132,16 @@ qemu-system-x86_64 -enable-kvm -m 2048 -M accel=kvm,memory-backend=mem \
 к системе - VDUSE (vDPA Device in Userspace), а в QEMU, начиная с версии 7.2, есть поддержка
 экспорта блочных устройств QEMU по этому протоколу через qemu-storage-daemon.
 
-VDUSE - на данный момент лучший интерфейс для подключения дисков Vitastor в виде блочных
-устройств на уровне ядра, ибо:
-- VDUSE не копирует данные и поэтому достигает значительно лучшей производительности, чем [NBD](nbd.ru.md)
-- Также оно не имеет проблемы NBD-таймаута - устройство не умирает, если операция выполняется слишком долго
-- Также оно не имеет проблемы подвисающих устройств - если процесс-обработчик умирает, его можно
-  перезапустить (!) и блочное устройство продолжит работать
-- По-видимому, у него нет предела числа подключаемых в систему устройств
+Преимущества VDUSE:
 
-Пример сравнения производительности:
+- VDUSE копирует данные 1 раз, а не 2, и поэтому он быстрее, чем [NBD](nbd.ru.md) при линейном доступе.
+- VDUSE не имеет проблемы NBD-таймаута - устройство не умирает, если операция выполняется слишком долго.
+- VDUSE не имеет проблемы подвисающих устройств - если процесс-обработчик умирает, его можно
+  перезапустить (!) и блочное устройство продолжит работать (в UBLK это тоже поддерживается).
+- По-видимому, у него нет предела числа подключаемых в систему устройств (в UBLK лимита тоже нет).
 
-|                          | Прямой fio  | NBD         | VDUSE       |
-|--------------------------|-------------|-------------|-------------|
-| линейная запись          | 3.85 GB/s   | 1.12 GB/s   | 3.85 GB/s   |
-| 4k случайная запись Q128 | 240000 iops | 120000 iops | 178000 iops |
-| 4k случайная запись Q1   | 9500 iops   | 7620 iops   | 7640 iops   |
-| линейное чтение          | 4.3 GB/s    | 1.8 GB/s    | 2.85 GB/s   |
-| 4k случайное чтение Q128 | 287000 iops | 140000 iops | 189000 iops |
-| 4k случайное чтение Q1   | 9600 iops   | 7640 iops   | 7780 iops   |
+Однако, при линейном доступе VDUSE может быть медленнее UBLK (а может быть и быстрее), а по iops
+VDUSE иногда даже медленнее NBD. Пример сравнения производительности смотрите на странице [UBLK](ublk.ru.md).
 
 Чтобы попробовать VDUSE, вам нужно ядро Linux как минимум версии 5.15, собранное с поддержкой
 VDUSE (CONFIG_VDPA=m, CONFIG_VDPA_USER=m, CONFIG_VIRTIO_VDPA=m).
@@ -196,3 +188,12 @@ vdpa dev add name test1 mgmtdev vduse
 vdpa dev del test1
 kill <PID_процесса_qemu-storage-daemon>
 ```
+
+## Veeam
+
+Драйвер Vitastor QEMU имеет функцию, которая позволяет обманывать сторонние системы типа Veeam, которые
+не могут сами по себе разобрать адреса дисков в vitastor: [qemu_file_mirror_path](../config/client.ru.md#qemu_file_mirror_path).
+
+Чтобы заставить такие системы работать, вам нужно установить эту опцию равной пути к некоторому каталогу
+в ФС (например, `/mnt/vitastor/`) и примонтировать этот каталог с помощью [`vitastor-nfs mount --block`](../usage/nfs.ru.md).
+Они начнут обращаться к образам как к файлам и, вероятно, смогут заработать корректно :).

docs/usage/ublk.en.md

@@ -0,0 +1,116 @@
+[Documentation](../../README.md#documentation) → Usage → UBLK
+
+-----
+
+[Читать на русском](ublk.ru.md)
+
+# UBLK
+
+[ublk](https://docs.kernel.org/block/ublk.html) is a new io_uring-based Linux interface
+for user-space block device drivers, available since Linux 6.0.
+
+It's not zero-copy, but it's still a fast implementation, outperforming both [NBD](nbd.en.md)
+and [VDUSE](qemu.en.md#vduse) iops-wise and may or may not outperform VDUSE in linear I/O MB/s.
+ublk also allows to recover devices even if the server (vitastor-ublk process) dies.
+
+## Example performance comparison
+
+TCP (100G), 3 hosts each with 6 NVMe OSDs, 3 replicas, single client
+
+|                      | direct fio  | NBD         | VDUSE      | UBLK        |
+|----------------------|-------------|-------------|------------|-------------|
+| linear write         | 3807 MB/s   | 1832 MB/s   | 3226 MB/s  | 3027 MB/s   |
+| linear read          | 3067 MB/s   | 1885 MB/s   | 1800 MB/s  | 2076 MB/s   |
+| 4k random write Q128 | 128624 iops | 91060 iops  | 94621 iops | 149450 iops |
+| 4k random read Q128  | 117769 iops | 153408 iops | 93157 iops | 171987 iops |
+| 4k random write Q1   | 8090 iops   | 6442 iops   | 6316 iops  | 7272 iops   |
+| 4k random read Q1    | 9474 iops   | 7200 iops   | 6840 iops  | 8038 iops   |
+
+RDMA (100G), 3 hosts each with 6 NVMe OSDs, 3 replicas, single client
+
+|                      | direct fio  | NBD         | VDUSE       | UBLK        |
+|----------------------|-------------|-------------|-------------|-------------|
+| linear write         | 6998 MB/s   | 1878 MB/s   | 4249 MB/s   | 3140 MB/s   |
+| linear read          | 8628 MB/s   | 3389 MB/s   | 5062 MB/s   | 3674 MB/s   |
+| 4k random write Q128 | 222541 iops | 181589 iops | 138281 iops | 218222 iops |
+| 4k random read Q128  | 412647 iops | 239987 iops | 151663 iops | 269583 iops |
+| 4k random write Q1   | 11601 iops  | 8592 iops   | 9111 iops   | 10000 iops  |
+| 4k random read Q1    | 10102 iops  | 7788 iops   | 8111 iops   | 8965 iops   |
+
+## Commands
+
+vitastor-ublk supports the following commands:
+
+- [map](#map)
+- [unmap](#unmap)
+- [ls](#ls)
+
+## map
+
+To create a local block device for a Vitastor image run:
+
+```
+vitastor-ublk map [/dev/ublkbN] --image testimg
+```
+
+It will output a block device name like /dev/ublkb0 which you can then use as a normal disk.
+
+You can also use `--pool <POOL> --inode <INODE> --size <SIZE>` instead of `--image <IMAGE>` if you want.
+
+vitastor-ublk supports all usual Vitastor configuration options like `--config_path <path_to_config>` plus ublk-specific:
+
+* `--recover` \
+  Recover a mapped device if the previous ublk server is dead.
+* `--queue_depth 256` \
+  Maximum queue size for the device.
+* `--max_io_size 1M` \
+  Maximum single I/O size for the device. Default: `max(1 MB, pool block size * EC part count)`.
+* `--readonly` \
+  Make the device read-only.
+* `--hdd` \
+  Mark the device as rotational.
+* `--logfile /path/to/log/file.txt` \
+  Write log messages to the specified file instead of dropping them (in background mode)
+  or printing them to the standard output (in foreground mode).
+* `--dev_num N` \
+  Use the specified device /dev/ublkbN instead of automatic selection (alternative syntax
+  to /dev/ublkbN positional parameter).
+* `--foreground 1` \
+  Stay in foreground, do not daemonize.
+
+Note that `ublk_queue_depth` and `ublk_max_io_size` may also be specified
+in `/etc/vitastor/vitastor.conf` or in other configuration file specified with `--config_path`.
+
+## unmap
+
+To unmap the device run:
+
+```
+vitastor-ublk unmap /dev/ublkb0
+```
+
+## ls
+
+```
+vitastor-ublk ls [--json]
+```
+
+List mapped images.
+
+Example output (normal format):
+
+```
+/dev/ublkb0
+image: bench
+pid: 584536
+
+/dev/ublkb1
+image: bench1
+pid: 584546
+```
+
+Example output (JSON format):
+
+```
+{"/dev/ublkb0": {"image": "bench", "pid": 584536}, "/dev/ublkb1": {"image": "bench1", "pid": 584546}}
+```

docs/usage/ublk.ru.md

@@ -0,0 +1,121 @@
+[Документация](../../README-ru.md#документация) → Использование → UBLK
+
+-----
+
+[Read in English](ublk.en.md)
+
+# UBLK
+
+[ublk](https://docs.kernel.org/block/ublk.html) - это новый Linux-интерфейс на основе io_uring
+для реализации блочных устройств в пространстве пользователя, доступный, начиная с Linux 6.0.
+
+ublk тоже копирует память (т.е. не является zero-copy), но по IOPS всё равно обгоняет и
+[NBD](nbd.ru.md), и [VDUSE](qemu.ru.md#vduse), и иногда может даже обгонять VDUSE по
+скорости линейного доступа. Также ublk позволяет оживлять устройства, у которых умер
+сервер (процесс-обработчик vitastor-ublk).
+
+## Пример сравнения производительности
+
+TCP (100G), 3 сервера с 6 NVMe OSD каждый, 3 реплики, один клиент
+
+|                          | Прямой fio  | NBD         | VDUSE      | UBLK        |
+|--------------------------|-------------|-------------|------------|-------------|
+| линейная запись          | 3807 MB/s   | 1832 MB/s   | 3226 MB/s  | 3027 MB/s   |
+| линейное чтение          | 3067 MB/s   | 1885 MB/s   | 1800 MB/s  | 2076 MB/s   |
+| 4k случайная запись Q128 | 128624 iops | 91060 iops  | 94621 iops | 149450 iops |
+| 4k случайное чтение Q128 | 117769 iops | 153408 iops | 93157 iops | 171987 iops |
+| 4k случайная запись Q1   | 8090 iops   | 6442 iops   | 6316 iops  | 7272 iops   |
+| 4k случайное чтение Q1   | 9474 iops   | 7200 iops   | 6840 iops  | 8038 iops   |
+
+RDMA (100G), 3 сервера с 6 NVMe OSD каждый, 3 реплики, один клиент
+
+|                          | Прямой fio  | NBD         | VDUSE       | UBLK        |
+|--------------------------|-------------|-------------|-------------|-------------|
+| линейная запись          | 6998 MB/s   | 1878 MB/s   | 4249 MB/s   | 3140 MB/s   |
+| линейное чтение          | 8628 MB/s   | 3389 MB/s   | 5062 MB/s   | 3674 MB/s   |
+| 4k случайная запись Q128 | 222541 iops | 181589 iops | 138281 iops | 218222 iops |
+| 4k случайное чтение Q128 | 412647 iops | 239987 iops | 151663 iops | 269583 iops |
+| 4k случайная запись Q1   | 11601 iops  | 8592 iops   | 9111 iops   | 10000 iops  |
+| 4k случайное чтение Q1   | 10102 iops  | 7788 iops   | 8111 iops   | 8965 iops   |
+
+## Команды
+
+vitastor-ublk поддерживает следующие команды:
+
+- [map](#map)
+- [unmap](#unmap)
+- [ls](#ls)
+
+## map
+
+Чтобы создать локальное блочное устройство для образа, выполните команду:
+
+```
+vitastor-ublk map [/dev/ublkbN] --image testimg
+```
+
+Команда напечатает название блочного устройства вида /dev/ublkb0, которое потом можно
+будет использовать как обычный диск.
+
+Для обращения по номеру инода, аналогично другим командам, можно использовать опции
+`--pool <POOL> --inode <INODE> --size <SIZE>` вместо `--image testimg`.
+
+vitastor-ublk поддерживает все обычные опции Vitastor, например, `--config_path <path_to_config>`,
+плюс специфичные для ublk:
+
+* `--recover` \
+  Восстановить ранее подключённое устройство, у которого умер обработчик.
+* `--queue_depth 256` \
+  Максимальная глубина очереди устройства.
+* `--max_io_size 1M` \
+  Максимальный размер запроса ввода-вывода для устройства. По умолчанию: `max(1 MB, блок данных пула * число частей данных EC)`.
+* `--readonly` \
+  Подключить устройство в режиме только для чтения.
+* `--hdd` \
+  Пометить устройство как вращающийся жёсткий диск (флаг rotational).
+* `--logfile /path/to/log/file.txt` \
+  Писать сообщения о процессе работы в заданный файл, вместо пропуска их
+  при фоновом режиме запуска или печати на стандартный вывод при запуске
+  в консоли с `--foreground 1`.
+* `--dev_num N` \
+  Использовать заданное устройство `/dev/ublkbN` вместо автоматического подбора.
+* `--foreground 1` \
+  Не уводить процесс в фоновый режим.
+
+Обратите внимание, что опции `ublk_queue_depth` и `ublk_max_io_size` можно
+также задавать в `/etc/vitastor/vitastor.conf` или в другом файле конфигурации,
+заданном опцией `--config_path`.
+
+## unmap
+
+Для отключения устройства выполните:
+
+```
+vitastor-ublk unmap /dev/ublkb0
+```
+
+## ls
+
+```
+vitastor-ublk ls [--json]
+```
+
+Вывести подключённые устройства.
+
+Пример вывода в обычном формате:
+
+```
+/dev/ublkb0
+image: bench
+pid: 584536
+
+/dev/ublkb1
+image: bench1
+pid: 584546
+```
+
+Пример вывода в JSON-формате:
+
+```
+{"/dev/ublkb0": {"image": "bench", "pid": 584536}, "/dev/ublkb1": {"image": "bench1", "pid": 584546}}
+```

mon/osd_tree.js

@@ -15,7 +15,7 @@ function get_osd_tree(global_config, state)
         const stat = state.osd.stats[osd_num];
         const osd_cfg = state.config.osd[osd_num];
         let reweight = osd_cfg == null ? 1 : Number(osd_cfg.reweight);
-        if (isNaN(reweight) || reweight < 0 || reweight > 0)
+        if (isNaN(reweight) || reweight < 0 || reweight > 1)
             reweight = 1;
         if (stat && stat.size && reweight && (state.osd.state[osd_num] || Number(stat.time) >= down_time ||
             osd_cfg && osd_cfg.noout))
@@ -179,7 +179,7 @@ function filter_osds_by_block_layout(orig_tree, osd_stats, block_size, bitmap_gr
         if (orig_tree[osd].level === 'osd')
         {
             const osd_stat = osd_stats[osd];
-            if (osd_stat && (osd_stat.bs_block_size && osd_stat.bs_block_size != block_size ||
+            if (osd_stat && (osd_stat.data_block_size && osd_stat.data_block_size != block_size ||
                 osd_stat.bitmap_granularity && osd_stat.bitmap_granularity != bitmap_granularity ||
                 osd_stat.immediate_commit == 'small' && immediate_commit == 'all' ||
                 osd_stat.immediate_commit == 'none' && immediate_commit != 'none'))

mon/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vitastor-mon",
-  "version": "2.2.3",
+  "version": "2.4.1",
   "description": "Vitastor SDS monitor service",
   "main": "mon-main.js",
   "scripts": {
@@ -9,7 +9,7 @@
   "author": "Vitaliy Filippov",
   "license": "UNLICENSED",
   "dependencies": {
-    "antietcd": "^1.1.2",
+    "antietcd": "^1.1.3",
     "sprintf-js": "^1.1.2",
     "ws": "^7.2.5"
   },

mon/scripts/make-etcd

@@ -52,15 +52,16 @@ async function run()
         process.exit(1);
     }
     const etcds = (config.etcd_address instanceof Array ? config.etcd_address : (''+config.etcd_address).split(/,/))
-        .map(s => (''+s).replace(/^https?:\/\/\[?|\]?(:\d+)?(\/.*)?$/g, '').toLowerCase());
+        .map(s => (''+s).replace(/^https?:\/\/|(:\d+)?(\/.*)?$/g, '').replace(/^\[(.*)\]$/, '$1').toLowerCase());
     const num = select_local_etcd(etcds);
     if (num < 0)
     {
         console.log('No matching IPs in etcd_address from '+config_path);
         process.exit(0);
     }
+    const etcd_url = 'http://' + (etcds[num].indexOf(':') >= 0 ? '['+etcds[num]+']' : etcds[num]);
     const etcd_name = 'etcd'+etcds[num].replace(/[^0-9a-z_]/ig, '_');
-    const etcd_cluster = etcds.map(e => `etcd${e.replace(/[^0-9a-z_]/ig, '_')}=http://${e}:2380`).join(',');
+    const etcd_cluster = etcds.map(e => `etcd${e.replace(/[^0-9a-z_]/ig, '_')}=${etcd_url}:2380`).join(',');
     if (in_docker)
     {
         let etcd_conf = fs.readFileSync("/etc/vitastor/etcd.conf", { encoding: 'utf-8' });
@@ -83,8 +84,8 @@ Wants=network-online.target local-fs.target time-sync.target
 Restart=always
 Environment=GOGC=50
 ExecStart=etcd --name ${etcd_name} --data-dir /var/lib/etcd/vitastor \\
-    --snapshot-count 10000 --advertise-client-urls http://${etcds[num]}:2379 --listen-client-urls http://${etcds[num]}:2379 \\
-    --initial-advertise-peer-urls http://${etcds[num]}:2380 --listen-peer-urls http://${etcds[num]}:2380 \\
+    --snapshot-count 10000 --advertise-client-urls ${etcd_url}:2379 --listen-client-urls ${etcd_url}:2379 \\
+    --initial-advertise-peer-urls ${etcd_url}:2380 --listen-peer-urls ${etcd_url}:2380 \\
     --initial-cluster-token vitastor-etcd-1 --initial-cluster ${etcd_cluster} \\
     --initial-cluster-state new --max-txn-ops=100000 --max-request-bytes=104857600 \\
     --auto-compaction-retention=10 --auto-compaction-mode=revision

mon/stats.js

@@ -276,6 +276,10 @@ function sum_inode_stats(state, prev_stats)
         }
         for (const pool_id in osd_diff.inode_stats)
         {
+            if (!inode_stats[pool_id])
+            {
+                continue;
+            }
             for (const inode_num in prev_stats.osd_diff[osd].inode_stats[pool_id])
             {
                 inode_stats[pool_id][inode_num] = inode_stats[pool_id][inode_num] || inode_stub();

node-binding/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vitastor",
-  "version": "2.2.3",
+  "version": "2.4.1",
   "description": "Low-level native bindings to Vitastor client library",
   "main": "index.js",
   "keywords": [

patches/VitastorPlugin.pm

@@ -261,7 +261,7 @@ sub free_image
     my ($vtype, $name, $vmid, undef, undef, undef) = $class->parse_volname($volname);
     $class->deactivate_volume($storeid, $scfg, $volname);
     my $full_list = run_cli($scfg, [ 'ls', '-l' ]);
-    my $list = _process_list($scfg, $storeid, $full_list);
+    my $list = _process_list($scfg, $storeid, $full_list, 0);
     # Remove image and all its snapshots
     my $rm_names = {
         map { ($prefix.$_->{name} => 1) }
@@ -269,6 +269,10 @@ sub free_image
         @$list
     };
     my $children = [ grep { $_->{parent_name} && $rm_names->{$_->{parent_name}} } @$full_list ];
+    $children = [ grep { 
+        substr($_->{name}, 0, length($prefix.$name)) ne $prefix.$name &&
+        substr($_->{name}, 0, length($prefix.$name)+1) ne $prefix.$name.'@'
+    } @$children ];
     die "Image has children: ".join(', ', map {
         substr($_->{name}, 0, length $prefix) eq $prefix
             ? substr($_->name, length $prefix)
@@ -288,14 +292,15 @@ sub free_image
 
 sub _process_list
 {
-    my ($scfg, $storeid, $result) = @_;
+    my ($scfg, $storeid, $result, $skip_snapshot) = @_;
+    $skip_snapshot = 1 if !defined $skip_snapshot;
     my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
     my $list = [];
     foreach my $el (@$result)
     {
         next if !$el->{name} || length($prefix) && substr($el->{name}, 0, length $prefix) ne $prefix;
         my $name = substr($el->{name}, length $prefix);
-        next if $name =~ /@/;
+        next if $skip_snapshot && $name =~ /@/;
         my ($owner) = $name =~ /^(?:vm|base)-(\d+)-/s;
         next if !defined $owner;
         my $parent = !defined $el->{parent_name}
@@ -494,4 +499,55 @@ sub rename_volume
     return "${storeid}:${base_name}${target_volname}";
 }
 
+sub _monkey_patch_qemu_blockdev_options
+{
+    my ($cfg, $volid, $machine_version, $options) = @_;
+    my ($storeid, $volname) = PVE::Storage::parse_volume_id($volid);
+
+    my $scfg = PVE::Storage::storage_config($cfg, $storeid);
+
+    my $plugin = PVE::Storage::Plugin->lookup($scfg->{type});
+
+    my ($vtype) = $plugin->parse_volname($volname);
+    die "cannot use volume of type '$vtype' as a QEMU blockdevice\n"
+        if $vtype ne 'images' && $vtype ne 'iso' && $vtype ne 'import';
+
+    return $plugin->qemu_blockdev_options($scfg, $storeid, $volname, $machine_version, $options);
+}
+
+sub qemu_blockdev_options
+{
+    my ($class, $scfg, $storeid, $volname, $machine_version, $options) = @_;
+    my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
+    my ($vtype, $name, $vmid) = $class->parse_volname($volname);
+    $name .= '@'.$options->{'snapshot-name'} if $options->{'snapshot-name'};
+    if ($scfg->{vitastor_nbd})
+    {
+        my $mapped = run_cli($scfg, [ 'ls' ], binary => '/usr/bin/vitastor-nbd');
+        my ($kerneldev) = grep { $mapped->{$_}->{image} eq $prefix.$name } keys %$mapped;
+        die "Image not mapped via NBD" if !$kerneldev;
+        return { driver => 'host_device', filename => $kerneldev };
+    }
+    my $blockdev = {
+        driver => 'vitastor',
+        image => $prefix.$name,
+    };
+    if ($scfg->{vitastor_config_path})
+    {
+        $blockdev->{'config-path'} = $scfg->{vitastor_config_path};
+    }
+    if ($scfg->{vitastor_etcd_address})
+    {
+        # FIXME This is the only exception: etcd_address -> etcd_host for qemu
+        $blockdev->{'etcd-host'} = $scfg->{vitastor_etcd_address};
+    }
+    if ($scfg->{vitastor_etcd_prefix})
+    {
+        $blockdev->{'etcd-prefix'} = $scfg->{vitastor_etcd_prefix};
+    }
+    return $blockdev;
+}
+
+*PVE::Storage::qemu_blockdev_options = *_monkey_patch_qemu_blockdev_options;
+
 1;

patches/cinder-vitastor.py

@@ -50,7 +50,7 @@ from cinder.volume import configuration
 from cinder.volume import driver
 from cinder.volume import volume_utils
 
-VITASTOR_VERSION = '2.2.3'
+VITASTOR_VERSION = '2.4.1'
 
 LOG = logging.getLogger(__name__)
 

patches/pve-qemu-10.0-vitastor.patch

@@ -0,0 +1,172 @@
+Index: pve-qemu-kvm-10.0.2/block/meson.build
+===================================================================
+--- pve-qemu-kvm-10.0.2.orig/block/meson.build
++++ pve-qemu-kvm-10.0.2/block/meson.build
+@@ -126,6 +126,7 @@ foreach m : [
+   [libnfs, 'nfs', files('nfs.c')],
+   [libssh, 'ssh', files('ssh.c')],
+   [rbd, 'rbd', files('rbd.c')],
++  [vitastor, 'vitastor', files('vitastor.c')],
+ ]
+   if m[0].found()
+     module_ss = ss.source_set()
+Index: pve-qemu-kvm-10.0.2/meson.build
+===================================================================
+--- pve-qemu-kvm-10.0.2.orig/meson.build
++++ pve-qemu-kvm-10.0.2/meson.build
+@@ -1622,6 +1622,26 @@ if not get_option('rbd').auto() or have_
+   endif
+ endif
+ 
++vitastor = not_found
++if not get_option('vitastor').auto() or have_block
++  libvitastor_client = cc.find_library('vitastor_client', has_headers: ['vitastor_c.h'],
++    required: get_option('vitastor'))
++  if libvitastor_client.found()
++    if cc.links('''
++      #include <vitastor_c.h>
++      int main(void) {
++        vitastor_c_create_qemu(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
++        return 0;
++      }''', dependencies: libvitastor_client)
++      vitastor = declare_dependency(dependencies: libvitastor_client)
++    elif get_option('vitastor').enabled()
++      error('could not link libvitastor_client')
++    else
++      warning('could not link libvitastor_client, disabling')
++    endif
++  endif
++endif
++
+ glusterfs = not_found
+ glusterfs_ftruncate_has_stat = false
+ glusterfs_iocb_has_stat = false
+@@ -2514,6 +2534,7 @@ endif
+ config_host_data.set('CONFIG_OPENGL', opengl.found())
+ config_host_data.set('CONFIG_PLUGIN', get_option('plugins'))
+ config_host_data.set('CONFIG_RBD', rbd.found())
++config_host_data.set('CONFIG_VITASTOR', vitastor.found())
+ config_host_data.set('CONFIG_RDMA', rdma.found())
+ config_host_data.set('CONFIG_RELOCATABLE', get_option('relocatable'))
+ config_host_data.set('CONFIG_SAFESTACK', get_option('safe_stack'))
+@@ -4812,6 +4833,7 @@ summary_info += {'fdt support':       fd
+ summary_info += {'libcap-ng support': libcap_ng}
+ summary_info += {'bpf support':       libbpf}
+ summary_info += {'rbd support':       rbd}
++summary_info += {'vitastor support':  vitastor}
+ summary_info += {'smartcard support': cacard}
+ summary_info += {'U2F support':       u2f}
+ summary_info += {'libusb':            libusb}
+Index: pve-qemu-kvm-10.0.2/meson_options.txt
+===================================================================
+--- pve-qemu-kvm-10.0.2.orig/meson_options.txt
++++ pve-qemu-kvm-10.0.2/meson_options.txt
+@@ -202,6 +202,8 @@ option('pvg', type: 'feature', value: 'a
+        description: 'macOS paravirtualized graphics support')
+ option('rbd', type : 'feature', value : 'auto',
+        description: 'Ceph block device driver')
++option('vitastor', type : 'feature', value : 'auto',
++       description: 'Vitastor block device driver')
+ option('opengl', type : 'feature', value : 'auto',
+        description: 'OpenGL support')
+ option('rdma', type : 'feature', value : 'auto',
+Index: pve-qemu-kvm-10.0.2/qapi/block-core.json
+===================================================================
+--- pve-qemu-kvm-10.0.2.orig/qapi/block-core.json
++++ pve-qemu-kvm-10.0.2/qapi/block-core.json
+@@ -3599,7 +3599,7 @@
+             'raw', 'rbd',
+             { 'name': 'replication', 'if': 'CONFIG_REPLICATION' },
+             'pbs',
+-            'ssh', 'throttle', 'vdi', 'vhdx',
++            'ssh', 'throttle', 'vdi', 'vhdx', 'vitastor',
+             { 'name': 'virtio-blk-vfio-pci', 'if': 'CONFIG_BLKIO' },
+             { 'name': 'virtio-blk-vhost-user', 'if': 'CONFIG_BLKIO' },
+             { 'name': 'virtio-blk-vhost-vdpa', 'if': 'CONFIG_BLKIO' },
+@@ -4725,6 +4725,28 @@
+             '*server': ['InetSocketAddressBase'] } }
+ 
+ ##
++# @BlockdevOptionsVitastor:
++#
++# Driver specific block device options for vitastor
++#
++# @image:       Image name
++# @inode:       Inode number
++# @pool:        Pool ID
++# @size:        Desired image size in bytes
++# @config-path: Path to Vitastor configuration
++# @etcd-host:   etcd connection address(es)
++# @etcd-prefix: etcd key/value prefix
++##
++{ 'struct': 'BlockdevOptionsVitastor',
++  'data': { '*inode': 'uint64',
++            '*pool': 'uint64',
++            '*size': 'uint64',
++            '*image': 'str',
++            '*config-path': 'str',
++            '*etcd-host': 'str',
++            '*etcd-prefix': 'str' } }
++
++##
+ # @ReplicationMode:
+ #
+ # An enumeration of replication modes.
+@@ -5194,6 +5216,7 @@
+       'throttle':   'BlockdevOptionsThrottle',
+       'vdi':        'BlockdevOptionsGenericFormat',
+       'vhdx':       'BlockdevOptionsGenericFormat',
++      'vitastor':   'BlockdevOptionsVitastor',
+       'virtio-blk-vfio-pci':
+                     { 'type': 'BlockdevOptionsVirtioBlkVfioPci',
+                       'if': 'CONFIG_BLKIO' },
+@@ -5674,6 +5697,20 @@
+             '*encrypt' :        'RbdEncryptionCreateOptions' } }
+ 
+ ##
++# @BlockdevCreateOptionsVitastor:
++#
++# Driver specific image creation options for Vitastor.
++#
++# @location: Where to store the new image file.  This location cannot
++#     point to a snapshot.
++#
++# @size: Size of the virtual disk in bytes
++##
++{ 'struct': 'BlockdevCreateOptionsVitastor',
++  'data': { 'location':         'BlockdevOptionsVitastor',
++            'size':             'size' } }
++
++##
+ # @BlockdevVmdkSubformat:
+ #
+ # Subformat options for VMDK images
+@@ -5895,6 +5932,7 @@
+       'ssh':            'BlockdevCreateOptionsSsh',
+       'vdi':            'BlockdevCreateOptionsVdi',
+       'vhdx':           'BlockdevCreateOptionsVhdx',
++      'vitastor':       'BlockdevCreateOptionsVitastor',
+       'vmdk':           'BlockdevCreateOptionsVmdk',
+       'vpc':            'BlockdevCreateOptionsVpc'
+   } }
+Index: pve-qemu-kvm-10.0.2/scripts/meson-buildoptions.sh
+===================================================================
+--- pve-qemu-kvm-10.0.2.orig/scripts/meson-buildoptions.sh
++++ pve-qemu-kvm-10.0.2/scripts/meson-buildoptions.sh
+@@ -175,6 +175,7 @@ meson_options_help() {
+   printf "%s\n" '  qga-vss         build QGA VSS support (broken with MinGW)'
+   printf "%s\n" '  qpl             Query Processing Library support'
+   printf "%s\n" '  rbd             Ceph block device driver'
++  printf "%s\n" '  vitastor        Vitastor block device driver'
+   printf "%s\n" '  rdma            Enable RDMA-based migration'
+   printf "%s\n" '  replication     replication support'
+   printf "%s\n" '  rust            Rust support'
+@@ -458,6 +459,8 @@ _meson_option_parse() {
+     --disable-qpl) printf "%s" -Dqpl=disabled ;;
+     --enable-rbd) printf "%s" -Drbd=enabled ;;
+     --disable-rbd) printf "%s" -Drbd=disabled ;;
++    --enable-vitastor) printf "%s" -Dvitastor=enabled ;;
++    --disable-vitastor) printf "%s" -Dvitastor=disabled ;;
+     --enable-rdma) printf "%s" -Drdma=enabled ;;
+     --disable-rdma) printf "%s" -Drdma=disabled ;;
+     --enable-relocatable) printf "%s" -Drelocatable=true ;;

patches/qemu-10.0-vitastor.patch

@@ -0,0 +1,172 @@
+diff --git a/block/meson.build b/block/meson.build
+index 34b1b2a306..24ca0f1e52 100644
+--- a/block/meson.build
++++ b/block/meson.build
+@@ -114,6 +114,7 @@ foreach m : [
+   [libnfs, 'nfs', files('nfs.c')],
+   [libssh, 'ssh', files('ssh.c')],
+   [rbd, 'rbd', files('rbd.c')],
++  [vitastor, 'vitastor', files('vitastor.c')],
+ ]
+   if m[0].found()
+     module_ss = ss.source_set()
+diff --git a/meson.build b/meson.build
+index 41f68d3806..29eaed9ba4 100644
+--- a/meson.build
++++ b/meson.build
+@@ -1622,6 +1622,26 @@ if not get_option('rbd').auto() or have_block
+   endif
+ endif
+ 
++vitastor = not_found
++if not get_option('vitastor').auto() or have_block
++  libvitastor_client = cc.find_library('vitastor_client', has_headers: ['vitastor_c.h'],
++    required: get_option('vitastor'))
++  if libvitastor_client.found()
++    if cc.links('''
++      #include <vitastor_c.h>
++      int main(void) {
++        vitastor_c_create_qemu(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
++        return 0;
++      }''', dependencies: libvitastor_client)
++      vitastor = declare_dependency(dependencies: libvitastor_client)
++    elif get_option('vitastor').enabled()
++      error('could not link libvitastor_client')
++    else
++      warning('could not link libvitastor_client, disabling')
++    endif
++  endif
++endif
++
+ glusterfs = not_found
+ glusterfs_ftruncate_has_stat = false
+ glusterfs_iocb_has_stat = false
+@@ -2506,6 +2526,7 @@ endif
+ config_host_data.set('CONFIG_OPENGL', opengl.found())
+ config_host_data.set('CONFIG_PLUGIN', get_option('plugins'))
+ config_host_data.set('CONFIG_RBD', rbd.found())
++config_host_data.set('CONFIG_VITASTOR', vitastor.found())
+ config_host_data.set('CONFIG_RDMA', rdma.found())
+ config_host_data.set('CONFIG_RELOCATABLE', get_option('relocatable'))
+ config_host_data.set('CONFIG_SAFESTACK', get_option('safe_stack'))
+@@ -4813,6 +4834,7 @@ summary_info += {'fdt support':       fdt_opt == 'internal' ? 'internal' : fdt}
+ summary_info += {'libcap-ng support': libcap_ng}
+ summary_info += {'bpf support':       libbpf}
+ summary_info += {'rbd support':       rbd}
++summary_info += {'vitastor support':  vitastor}
+ summary_info += {'smartcard support': cacard}
+ summary_info += {'U2F support':       u2f}
+ summary_info += {'libusb':            libusb}
+diff --git a/meson_options.txt b/meson_options.txt
+index 59d973bca0..a3e7123980 100644
+--- a/meson_options.txt
++++ b/meson_options.txt
+@@ -202,6 +202,8 @@ option('pvg', type: 'feature', value: 'auto',
+        description: 'macOS paravirtualized graphics support')
+ option('rbd', type : 'feature', value : 'auto',
+        description: 'Ceph block device driver')
++option('vitastor', type : 'feature', value : 'auto',
++       description: 'Vitastor block device driver')
+ option('opengl', type : 'feature', value : 'auto',
+        description: 'OpenGL support')
+ option('rdma', type : 'feature', value : 'auto',
+diff --git a/qapi/block-core.json b/qapi/block-core.json
+index b1937780e1..a511193620 100644
+--- a/qapi/block-core.json
++++ b/qapi/block-core.json
+@@ -3216,7 +3216,7 @@
+             'parallels', 'preallocate', 'qcow', 'qcow2', 'qed', 'quorum',
+             'raw', 'rbd',
+             { 'name': 'replication', 'if': 'CONFIG_REPLICATION' },
+-            'ssh', 'throttle', 'vdi', 'vhdx',
++            'ssh', 'throttle', 'vdi', 'vhdx', 'vitastor',
+             { 'name': 'virtio-blk-vfio-pci', 'if': 'CONFIG_BLKIO' },
+             { 'name': 'virtio-blk-vhost-user', 'if': 'CONFIG_BLKIO' },
+             { 'name': 'virtio-blk-vhost-vdpa', 'if': 'CONFIG_BLKIO' },
+@@ -4299,6 +4299,28 @@
+             '*key-secret': 'str',
+             '*server': ['InetSocketAddressBase'] } }
+ 
++##
++# @BlockdevOptionsVitastor:
++#
++# Driver specific block device options for vitastor
++#
++# @image:       Image name
++# @inode:       Inode number
++# @pool:        Pool ID
++# @size:        Desired image size in bytes
++# @config-path: Path to Vitastor configuration
++# @etcd-host:   etcd connection address(es)
++# @etcd-prefix: etcd key/value prefix
++##
++{ 'struct': 'BlockdevOptionsVitastor',
++  'data': { '*inode': 'uint64',
++            '*pool': 'uint64',
++            '*size': 'uint64',
++            '*image': 'str',
++            '*config-path': 'str',
++            '*etcd-host': 'str',
++            '*etcd-prefix': 'str' } }
++
+ ##
+ # @ReplicationMode:
+ #
+@@ -4767,6 +4789,7 @@
+       'throttle':   'BlockdevOptionsThrottle',
+       'vdi':        'BlockdevOptionsGenericFormat',
+       'vhdx':       'BlockdevOptionsGenericFormat',
++      'vitastor':   'BlockdevOptionsVitastor',
+       'virtio-blk-vfio-pci':
+                     { 'type': 'BlockdevOptionsVirtioBlkVfioPci',
+                       'if': 'CONFIG_BLKIO' },
+@@ -5240,6 +5263,20 @@
+             '*cluster-size' :   'size',
+             '*encrypt' :        'RbdEncryptionCreateOptions' } }
+ 
++##
++# @BlockdevCreateOptionsVitastor:
++#
++# Driver specific image creation options for Vitastor.
++#
++# @location: Where to store the new image file.  This location cannot
++#     point to a snapshot.
++#
++# @size: Size of the virtual disk in bytes
++##
++{ 'struct': 'BlockdevCreateOptionsVitastor',
++  'data': { 'location':         'BlockdevOptionsVitastor',
++            'size':             'size' } }
++
+ ##
+ # @BlockdevVmdkSubformat:
+ #
+@@ -5462,6 +5499,7 @@
+       'ssh':            'BlockdevCreateOptionsSsh',
+       'vdi':            'BlockdevCreateOptionsVdi',
+       'vhdx':           'BlockdevCreateOptionsVhdx',
++      'vitastor':       'BlockdevCreateOptionsVitastor',
+       'vmdk':           'BlockdevCreateOptionsVmdk',
+       'vpc':            'BlockdevCreateOptionsVpc'
+   } }
+diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh
+index 3e8e00852b..45aff3b6a9 100644
+--- a/scripts/meson-buildoptions.sh
++++ b/scripts/meson-buildoptions.sh
+@@ -175,6 +175,7 @@ meson_options_help() {
+   printf "%s\n" '  qga-vss         build QGA VSS support (broken with MinGW)'
+   printf "%s\n" '  qpl             Query Processing Library support'
+   printf "%s\n" '  rbd             Ceph block device driver'
++  printf "%s\n" '  vitastor        Vitastor block device driver'
+   printf "%s\n" '  rdma            Enable RDMA-based migration'
+   printf "%s\n" '  replication     replication support'
+   printf "%s\n" '  rust            Rust support'
+@@ -458,6 +459,8 @@ _meson_option_parse() {
+     --disable-qpl) printf "%s" -Dqpl=disabled ;;
+     --enable-rbd) printf "%s" -Drbd=enabled ;;
+     --disable-rbd) printf "%s" -Drbd=disabled ;;
++    --enable-vitastor) printf "%s" -Dvitastor=enabled ;;
++    --disable-vitastor) printf "%s" -Dvitastor=disabled ;;
+     --enable-rdma) printf "%s" -Drdma=enabled ;;
+     --disable-rdma) printf "%s" -Drdma=disabled ;;
+     --enable-relocatable) printf "%s" -Drelocatable=true ;;

rpm/vitastor-el7.Dockerfile

@@ -21,17 +21,3 @@ RUN rpm --nomd5 -i fio*.src.rpm
 RUN rm -f /etc/yum.repos.d/CentOS-Media.repo
 RUN cd ~/rpmbuild/SPECS && yum-builddep -y fio.spec
 RUN yum -y install cmake3
-
-ADD https://vitastor.io/rpms/liburing-el7/liburing-0.7-2.el7.src.rpm /root
-
-RUN set -e; \
-    rpm -i liburing*.src.rpm; \
-    cd ~/rpmbuild/SPECS/; \
-    . /opt/rh/devtoolset-9/enable; \
-    rpmbuild -ba liburing.spec; \
-    mkdir -p /root/packages/liburing-el7; \
-    rm -rf /root/packages/liburing-el7/*; \
-    cp ~/rpmbuild/RPMS/*/liburing* /root/packages/liburing-el7/; \
-    cp ~/rpmbuild/SRPMS/liburing* /root/packages/liburing-el7/
-
-RUN rpm -i `ls /root/packages/liburing-el7/liburing-*.x86_64.rpm | grep -v debug`

rpm/vitastor-el7.spec

@@ -1,13 +1,12 @@
 Name:           vitastor
-Version:        2.2.3
+Version:        2.4.1
 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-2.2.3.el7.tar.gz
+Source0:        vitastor-2.4.1.el7.tar.gz
 
-BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel
 BuildRequires:  devtoolset-9-gcc-c++
 BuildRequires:  rh-nodejs12
@@ -35,8 +34,6 @@ size with configurable redundancy (replication or erasure codes/XOR).
 Summary:        Vitastor - OSD
 Requires:       libJerasure2
 Requires:       libisa-l
-Requires:       liburing >= 0.6
-Requires:       liburing < 2
 Requires:       vitastor-client = %{version}-%{release}
 Requires:       util-linux
 Requires:       parted
@@ -60,8 +57,6 @@ scheduling cluster-level operations.
 
 %package -n vitastor-client
 Summary:        Vitastor - client
-Requires:       liburing >= 0.6
-Requires:       liburing < 2
 
 
 %description -n vitastor-client
@@ -169,6 +164,7 @@ chown vitastor:vitastor /var/lib/vitastor
 
 %files -n vitastor-client
 %_bindir/vitastor-nbd
+%_bindir/vitastor-ublk
 %_bindir/vitastor-nfs
 %_bindir/vitastor-cli
 %_bindir/vitastor-rm

rpm/vitastor-el8.Dockerfile

@@ -17,17 +17,3 @@ RUN dnf -y install gcc-toolset-9 gcc-toolset-9-gcc-c++ gperftools-devel \
 RUN dnf download --source fio
 RUN rpm --nomd5 -i fio*.src.rpm
 RUN cd ~/rpmbuild/SPECS && dnf builddep -y --enablerepo=powertools --spec fio.spec
-
-ADD https://vitastor.io/rpms/liburing-el7/liburing-0.7-2.el7.src.rpm /root
-
-RUN set -e; \
-    rpm -i liburing*.src.rpm; \
-    cd ~/rpmbuild/SPECS/; \
-    . /opt/rh/gcc-toolset-9/enable; \
-    rpmbuild -ba liburing.spec; \
-    mkdir -p /root/packages/liburing-el8; \
-    rm -rf /root/packages/liburing-el8/*; \
-    cp ~/rpmbuild/RPMS/*/liburing* /root/packages/liburing-el8/; \
-    cp ~/rpmbuild/SRPMS/liburing* /root/packages/liburing-el8/
-
-RUN rpm -i `ls /root/packages/liburing-el8/liburing-*.x86_64.rpm | grep -v debug`

rpm/vitastor-el8.spec

@@ -1,13 +1,12 @@
 Name:           vitastor
-Version:        2.2.3
+Version:        2.4.1
 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-2.2.3.el8.tar.gz
+Source0:        vitastor-2.4.1.el8.tar.gz
 
-BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel
 BuildRequires:  gcc-toolset-9-gcc-c++
 BuildRequires:  nodejs >= 10
@@ -34,8 +33,6 @@ size with configurable redundancy (replication or erasure codes/XOR).
 Summary:        Vitastor - OSD
 Requires:       libJerasure2
 Requires:       libisa-l
-Requires:       liburing >= 0.6
-Requires:       liburing < 2
 Requires:       vitastor-client = %{version}-%{release}
 Requires:       util-linux
 Requires:       parted
@@ -58,8 +55,6 @@ scheduling cluster-level operations.
 
 %package -n vitastor-client
 Summary:        Vitastor - client
-Requires:       liburing >= 0.6
-Requires:       liburing < 2
 
 
 %description -n vitastor-client
@@ -166,6 +161,7 @@ chown vitastor:vitastor /var/lib/vitastor
 
 %files -n vitastor-client
 %_bindir/vitastor-nbd
+%_bindir/vitastor-ublk
 %_bindir/vitastor-nfs
 %_bindir/vitastor-cli
 %_bindir/vitastor-rm

rpm/vitastor-el9.Dockerfile

@@ -10,7 +10,7 @@ WORKDIR /root
 RUN sed -i 's/enabled=0/enabled=1/' /etc/yum.repos.d/*.repo
 RUN dnf -y install epel-release dnf-plugins-core
 RUN dnf -y install https://vitastor.io/rpms/centos/9/vitastor-release-1.0-1.el9.noarch.rpm
-RUN dnf -y install gcc-c++ gperftools-devel fio nodejs rpm-build jerasure-devel libisa-l-devel gf-complete-devel rdma-core-devel libarchive liburing-devel cmake libnl3-devel
+RUN dnf -y install gcc-c++ gperftools-devel fio nodejs rpm-build jerasure-devel libisa-l-devel gf-complete-devel rdma-core-devel libarchive cmake libnl3-devel
 RUN dnf download --source fio
 RUN rpm --nomd5 -i fio*.src.rpm
 RUN cd ~/rpmbuild/SPECS && dnf builddep -y --spec fio.spec

rpm/vitastor-el9.spec

@@ -1,13 +1,12 @@
 Name:           vitastor
-Version:        2.2.3
+Version:        2.4.1
 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-2.2.3.el9.tar.gz
+Source0:        vitastor-2.4.1.el9.tar.gz
 
-BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel
 BuildRequires:  gcc-c++
 BuildRequires:  nodejs >= 10
@@ -159,6 +158,7 @@ chown vitastor:vitastor /var/lib/vitastor
 
 %files -n vitastor-client
 %_bindir/vitastor-nbd
+%_bindir/vitastor-ublk
 %_bindir/vitastor-nfs
 %_bindir/vitastor-cli
 %_bindir/vitastor-rm

src/CMakeLists.txt

@@ -12,6 +12,7 @@ set(WITH_QEMU false CACHE BOOL "Build QEMU driver inside Vitastor source tree")
 set(WITH_FIO true CACHE BOOL "Build FIO driver")
 set(QEMU_PLUGINDIR qemu CACHE STRING "QEMU plugin directory suffix (qemu-kvm on RHEL)")
 set(WITH_ASAN false CACHE BOOL "Build with AddressSanitizer")
+set(WITH_SYSTEM_LIBURING false CACHE BOOL "Use system liburing")
 if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
 	if(EXISTS "/etc/debian_version")
 		set(CMAKE_INSTALL_LIBDIR "lib/${CMAKE_LIBRARY_ARCHITECTURE}")
@@ -19,13 +20,16 @@ if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
 	set(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
 endif()
 
-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_definitions(-DVITASTOR_VERSION="2.4.1")
+add_definitions(-D_GNU_SOURCE -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 -fvisibility=hidden -I ${CMAKE_SOURCE_DIR}/src)
 add_link_options(-fno-omit-frame-pointer)
 if (${WITH_ASAN})
 	add_definitions(-fsanitize=address)
 	add_link_options(-fsanitize=address -fno-omit-frame-pointer)
 endif (${WITH_ASAN})
+set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -fvisibility-inlines-hidden")
+set(CMAKE_CXX_FLAGS_MINSIZEREL "${CMAKE_CXX_FLAGS_MINSIZEREL} -fvisibility-inlines-hidden")
+set(CMAKE_CXX_FLAGS_RELWITHDEBINFO "${CMAKE_CXX_FLAGS_RELWITHDEBINFO} -fvisibility-inlines-hidden")
 
 set(CMAKE_BUILD_TYPE RelWithDebInfo)
 string(REGEX REPLACE "([\\/\\-]O)[^ \t\r\n]*" "\\13" CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE}")
@@ -49,7 +53,6 @@ endmacro(install_symlink)
 check_include_file("linux/nbd-netlink.h" HAVE_NBD_NETLINK_H)
 
 find_package(PkgConfig)
-pkg_check_modules(LIBURING REQUIRED liburing)
 if (${WITH_QEMU})
 	pkg_check_modules(GLIB REQUIRED glib-2.0)
 endif (${WITH_QEMU})
@@ -66,6 +69,15 @@ if (RDMACM_LIBRARIES)
 	add_definitions(-DWITH_RDMACM)
 endif (RDMACM_LIBRARIES)
 
+if (${WITH_SYSTEM_LIBURING})
+	pkg_check_modules(LIBURING REQUIRED liburing>=2.10)
+	include_directories(${LIBURING_INCLUDE_DIRS})
+else()
+	include_directories(${CMAKE_SOURCE_DIR}/src/liburing/include)
+	add_subdirectory(liburing)
+	set(LIBURING_LIBRARIES uring)
+endif (${WITH_SYSTEM_LIBURING})
+
 add_custom_target(build_tests)
 add_custom_target(test
 	COMMAND
@@ -86,7 +98,6 @@ include_directories(
 	${CMAKE_SOURCE_DIR}/src/test
 	${CMAKE_SOURCE_DIR}/src/util
 	/usr/include/jerasure
-	${LIBURING_INCLUDE_DIRS}
 	${IBVERBS_INCLUDE_DIRS}
 )
 
@@ -101,7 +112,7 @@ add_subdirectory(test)
 
 ### Install
 
-install(TARGETS vitastor-osd vitastor-disk vitastor-nbd vitastor-nfs vitastor-cli vitastor-kv vitastor-kv-stress RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
+install(TARGETS vitastor-osd vitastor-disk vitastor-nbd vitastor-ublk vitastor-nfs vitastor-cli vitastor-kv vitastor-kv-stress RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
 install_symlink(vitastor-disk ${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_BINDIR}/vitastor-dump-journal)
 install_symlink(vitastor-cli ${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_BINDIR}/vitastor-rm)
 install_symlink(vitastor-cli ${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_BINDIR}/vita)

src/blockstore/CMakeLists.txt

@@ -9,6 +9,7 @@ add_library(vitastor_blk SHARED
 )
 target_link_libraries(vitastor_blk
 	${LIBURING_LIBRARIES}
+	${ISAL_LIBRARIES}
 	tcmalloc_minimal
 	# for timerfd_manager
 	vitastor_common

src/blockstore/blockstore.h

@@ -135,7 +135,7 @@ Output:
 
 */
 
-struct blockstore_op_t
+struct __attribute__ ((visibility("default"))) blockstore_op_t
 {
     // operation
     uint64_t opcode = 0;
@@ -173,7 +173,7 @@ typedef std::map<std::string, std::string> blockstore_config_t;
 
 class blockstore_impl_t;
 
-class blockstore_t
+class __attribute__((visibility("default"))) blockstore_t
 {
     blockstore_impl_t *impl;
 public:

src/blockstore/blockstore_flush.cpp

@@ -361,6 +361,10 @@ bool journal_flusher_co::loop()
     else if (wait_state == 28) goto resume_28;
     else if (wait_state == 29) goto resume_29;
     else if (wait_state == 30) goto resume_30;
+    else if (wait_state == 31) goto resume_31;
+    else if (wait_state == 32) goto resume_32;
+    else if (wait_state == 33) goto resume_33;
+    else if (wait_state == 34) goto resume_34;
 resume_0:
     if (flusher->flush_queue.size() < flusher->min_flusher_count && !flusher->trim_wanted ||
         !flusher->flush_queue.size() || !flusher->dequeuing)
@@ -486,13 +490,14 @@ resume_2:
     resume_10:
     resume_11:
     resume_12:
+    resume_13:
         if (fill_incomplete && !clear_incomplete_csum_block_bits(5))
             return false;
         // Wait for journal data reads if the journal is not inmemory
-    resume_13:
+    resume_14:
         if (wait_journal_count > 0)
         {
-            wait_state = wait_base+13;
+            wait_state = wait_base+14;
             return false;
         }
         if (bs->dsk.csum_block_size)
@@ -509,31 +514,26 @@ resume_2:
         {
             if (it->copy_flags == COPY_BUF_JOURNAL || it->copy_flags == (COPY_BUF_JOURNAL|COPY_BUF_COALESCED))
             {
-                await_sqe(14);
+                await_sqe(15);
                 data->iov = (struct iovec){ it->buf, (size_t)it->len };
                 data->callback = simple_callback_w;
-                my_uring_prep_writev(
+                io_uring_prep_writev(
                     sqe, bs->dsk.data_fd, &data->iov, 1, bs->dsk.data_offset + clean_loc + it->offset
                 );
                 wait_count++;
             }
         }
         // Wait for data writes and metadata reads
-    resume_15:
     resume_16:
-        if (!wait_meta_reads(15))
+    resume_17:
+        if (!wait_meta_reads(16))
             return false;
         // Sync data before writing metadata
-    resume_17:
     resume_18:
     resume_19:
-        if (copy_count && !fsync_batch(false, 17))
+    resume_20:
+        if (copy_count && !fsync_batch(false, 18))
             return false;
-        // Modify the new metadata entry
-        update_metadata_entry();
-        // Update clean_db - it must be equal to the metadata entry
-        update_clean_db();
-        // And write metadata entries
         if (old_clean_loc != UINT64_MAX && old_clean_loc != clean_loc)
         {
             // zero out old metadata entry
@@ -548,26 +548,56 @@ resume_2:
                 }
             }
             memset((uint8_t*)meta_old.buf + meta_old.pos*bs->dsk.clean_entry_size, 0, bs->dsk.clean_entry_size);
-    resume_20:
-            if (meta_old.sector != meta_new.sector && !write_meta_block(meta_old, 20))
-                return false;
-        }
+            if (meta_old.sector != meta_new.sector)
+            {
     resume_21:
-        if (!write_meta_block(meta_new, 21))
-            return false;
+                if (flusher->inflight_meta_sectors.find(meta_old.sector) != flusher->inflight_meta_sectors.end())
+                {
+                    wait_state = wait_base+21;
+                    return false;
+                }
+                flusher->inflight_meta_sectors.insert(meta_old.sector);
     resume_22:
+                if (!write_meta_block(meta_old, 22))
+                    return false;
+    resume_23:
+                if (wait_count > 0)
+                {
+                    wait_state = wait_base+23;
+                    return false;
+                }
+                flusher->inflight_meta_sectors.erase(meta_old.sector);
+            }
+        }
+    resume_24:
+        if (flusher->inflight_meta_sectors.find(meta_new.sector) != flusher->inflight_meta_sectors.end())
+        {
+            wait_state = wait_base+24;
+            return false;
+        }
+        flusher->inflight_meta_sectors.insert(meta_new.sector);
+        // Modify the new metadata entry
+        update_metadata_entry();
+        // Update clean_db - it must be equal to the metadata entry
+        update_clean_db();
+        // And write metadata entries
+    resume_25:
+        if (!write_meta_block(meta_new, 25))
+            return false;
+    resume_26:
         if (wait_count > 0)
         {
-            wait_state = wait_base+22;
+            wait_state = wait_base+26;
             return false;
         }
+        flusher->inflight_meta_sectors.erase(meta_new.sector);
         // Done, free all buffers
         free_buffers();
         // And sync metadata (in batches - not per each operation!)
-    resume_23:
-    resume_24:
-    resume_25:
-        if (!fsync_batch(true, 23))
+    resume_27:
+    resume_28:
+    resume_29:
+        if (!fsync_batch(true, 27))
             return false;
         // Free the data block only when metadata is synced
         free_data_blocks();
@@ -590,12 +620,12 @@ resume_2:
         if (bs->journal_trim_interval && !((++flusher->journal_trim_counter) % bs->journal_trim_interval) ||
             flusher->trim_wanted > 0)
         {
-    resume_26:
-    resume_27:
-    resume_28:
-    resume_29:
     resume_30:
-            if (!trim_journal(26))
+    resume_31:
+    resume_32:
+    resume_33:
+    resume_34:
+            if (!trim_journal(30))
                 return false;
         }
         // All done
@@ -716,7 +746,7 @@ bool journal_flusher_co::write_meta_block(flusher_meta_write_t & meta_block, int
     await_sqe(0);
     data->iov = (struct iovec){ meta_block.buf, (size_t)bs->dsk.meta_block_size };
     data->callback = simple_callback_w;
-    my_uring_prep_writev(
+    io_uring_prep_writev(
         sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + bs->dsk.meta_block_size + meta_block.sector
     );
     wait_count++;
@@ -734,6 +764,7 @@ bool journal_flusher_co::clear_incomplete_csum_block_bits(int wait_base)
     else if (wait_state == wait_base+5) goto resume_5;
     else if (wait_state == wait_base+6) goto resume_6;
     else if (wait_state == wait_base+7) goto resume_7;
+    else if (wait_state == wait_base+8) goto resume_8;
     cleared_incomplete = false;
     for (auto it = v.begin(); it != v.end(); it++)
     {
@@ -754,11 +785,18 @@ bool journal_flusher_co::clear_incomplete_csum_block_bits(int wait_base)
         if (!wait_meta_reads(wait_base+0))
             return false;
     resume_2:
-        if (wait_journal_count > 0)
+        if (flusher->inflight_meta_sectors.find(meta_new.sector) != flusher->inflight_meta_sectors.end())
         {
             wait_state = wait_base+2;
             return false;
         }
+        flusher->inflight_meta_sectors.insert(meta_new.sector);
+    resume_3:
+        if (wait_journal_count > 0)
+        {
+            wait_state = wait_base+3;
+            return false;
+        }
         // Verify data checksums
         for (i = v.size()-1; i >= 0 && (v[i].copy_flags & COPY_BUF_CSUM_FILL); i--)
         {
@@ -837,19 +875,20 @@ bool journal_flusher_co::clear_incomplete_csum_block_bits(int wait_base)
             }
         }
         // Write and fsync the modified metadata entry
-    resume_3:
-        if (!write_meta_block(meta_new, wait_base+3))
-            return false;
     resume_4:
+        if (!write_meta_block(meta_new, wait_base+4))
+            return false;
+    resume_5:
         if (wait_count > 0)
         {
-            wait_state = wait_base+4;
+            wait_state = wait_base+5;
             return false;
         }
-    resume_5:
+        flusher->inflight_meta_sectors.erase(meta_new.sector);
     resume_6:
     resume_7:
-        if (!fsync_batch(true, wait_base+5))
+    resume_8:
+        if (!fsync_batch(true, wait_base+6))
             return false;
     }
     return true;
@@ -1090,7 +1129,7 @@ bool journal_flusher_co::read_dirty(int wait_base)
         vi.buf = memalign_or_die(MEM_ALIGNMENT, vi.len);
         data->iov = (struct iovec){ vi.buf, (size_t)vi.len };
         data->callback = simple_callback_r;
-        my_uring_prep_readv(
+        io_uring_prep_readv(
             sqe, bs->dsk.data_fd, &data->iov, 1, bs->dsk.data_offset + old_clean_loc + vi.offset
         );
         wait_count++;
@@ -1122,7 +1161,7 @@ bool journal_flusher_co::read_dirty(int wait_base)
                 await_sqe(1);
                 data->iov = (struct iovec){ v[i].buf, (size_t)v[i].len };
                 data->callback = simple_callback_rj;
-                my_uring_prep_readv(
+                io_uring_prep_readv(
                     sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset + v[i].disk_offset
                 );
                 wait_journal_count++;
@@ -1215,7 +1254,7 @@ bool journal_flusher_co::modify_meta_read(uint64_t meta_loc, flusher_meta_write_
         data->iov = (struct iovec){ wr.it->second.buf, (size_t)bs->dsk.meta_block_size };
         data->callback = simple_callback_r;
         wr.submitted = true;
-        my_uring_prep_readv(
+        io_uring_prep_readv(
             sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + bs->dsk.meta_block_size + wr.sector
         );
         wait_count++;
@@ -1313,7 +1352,7 @@ bool journal_flusher_co::fsync_batch(bool fsync_meta, int wait_base)
                 await_sqe(0);
                 data->iov = { 0 };
                 data->callback = simple_callback_w;
-                my_uring_prep_fsync(sqe, fsync_meta ? bs->dsk.meta_fd : bs->dsk.data_fd, IORING_FSYNC_DATASYNC);
+                io_uring_prep_fsync(sqe, fsync_meta ? bs->dsk.meta_fd : bs->dsk.data_fd, IORING_FSYNC_DATASYNC);
                 cur_sync->state = 1;
                 wait_count++;
             resume_2:
@@ -1383,7 +1422,7 @@ bool journal_flusher_co::trim_journal(int wait_base)
             ((journal_entry_start*)flusher->journal_superblock)->crc32 = je_crc32((journal_entry*)flusher->journal_superblock);
             data->iov = (struct iovec){ flusher->journal_superblock, (size_t)bs->dsk.journal_block_size };
             data->callback = simple_callback_w;
-            my_uring_prep_writev(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset);
+            io_uring_prep_writev(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset);
             wait_count++;
         resume_2:
             if (wait_count > 0)
@@ -1394,7 +1433,7 @@ bool journal_flusher_co::trim_journal(int wait_base)
             if (!bs->disable_journal_fsync)
             {
                 await_sqe(3);
-                my_uring_prep_fsync(sqe, bs->dsk.journal_fd, IORING_FSYNC_DATASYNC);
+                io_uring_prep_fsync(sqe, bs->dsk.journal_fd, IORING_FSYNC_DATASYNC);
                 data->iov = { 0 };
                 data->callback = simple_callback_w;
                 wait_count++;

src/blockstore/blockstore_flush.h

@@ -119,7 +119,8 @@ class journal_flusher_t
 
     std::map<uint64_t, meta_sector_t> meta_sectors;
     std::deque<object_id> flush_queue;
-    std::map<object_id, uint64_t> flush_versions; // FIXME: consider unordered_map?
+    std::unordered_map<object_id, uint64_t> flush_versions;
+    std::unordered_set<uint64_t> inflight_meta_sectors;
 
     bool try_find_older(std::map<obj_ver_id, dirty_entry>::iterator & dirty_end, obj_ver_id & cur);
     bool try_find_other(std::map<obj_ver_id, dirty_entry>::iterator & dirty_end, obj_ver_id & cur);

src/blockstore/blockstore_impl.cpp

@@ -229,6 +229,8 @@ void blockstore_impl_t::loop()
         {
             // Mark journal sector writes as submitted
             journal.sector_info[s].submit_id = 0;
+            if (journal.sector_info[s].submit_id)
+                journal.sector_info[s].written = true;
         }
         journal.submitting_sectors.clear();
         if ((initial_ring_space - ringloop->space_left()) > 0)

src/blockstore/blockstore_impl.h

@@ -19,6 +19,7 @@
 #include <deque>
 #include <new>
 #include <unordered_map>
+#include <unordered_set>
 
 #include "cpp-btree/btree_map.h"
 

src/blockstore/blockstore_init.cpp

@@ -66,7 +66,7 @@ int blockstore_init_meta::loop()
     last_read_offset = 0;
     data->iov = { metadata_buffer, (size_t)bs->dsk.meta_block_size };
     data->callback = [this](ring_data_t *data) { handle_event(data, -1); };
-    my_uring_prep_readv(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset);
+    io_uring_prep_readv(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset);
     bs->ringloop->submit();
     submitted++;
 resume_1:
@@ -104,7 +104,7 @@ resume_1:
             last_read_offset = 0;
             data->iov = (struct iovec){ metadata_buffer, (size_t)bs->dsk.meta_block_size };
             data->callback = [this](ring_data_t *data) { handle_event(data, -1); };
-            my_uring_prep_writev(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset);
+            io_uring_prep_writev(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset);
             bs->ringloop->submit();
             submitted++;
         resume_3:
@@ -213,12 +213,12 @@ resume_2:
                 data->iov = { bufs[i].buf, (size_t)bufs[i].size };
                 data->callback = [this, i](ring_data_t *data) { handle_event(data, i); };
                 if (!zero_on_init)
-                    my_uring_prep_readv(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + bufs[i].offset);
+                    io_uring_prep_readv(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + bufs[i].offset);
                 else
                 {
                     // Fill metadata with zeroes
                     memset(data->iov.iov_base, 0, data->iov.iov_len);
-                    my_uring_prep_writev(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + bufs[i].offset);
+                    io_uring_prep_writev(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + bufs[i].offset);
                 }
                 bs->ringloop->submit();
                 break;
@@ -245,7 +245,7 @@ resume_2:
                 assert(bufs[i].size <= 0x7fffffff);
                 data->iov = { bufs[i].buf, (size_t)bufs[i].size };
                 data->callback = [this, i](ring_data_t *data) { handle_event(data, i); };
-                my_uring_prep_writev(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + bufs[i].offset);
+                io_uring_prep_writev(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + bufs[i].offset);
                 bs->ringloop->submit();
                 bufs[i].state = INIT_META_WRITING;
                 submitted++;
@@ -274,7 +274,7 @@ resume_2:
             last_read_offset = (1+next_offset)*bs->dsk.meta_block_size;
             data->iov = { metadata_buffer, (size_t)bs->dsk.meta_block_size };
             data->callback = [this](ring_data_t *data) { handle_event(data, -1); };
-            my_uring_prep_readv(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + (1+next_offset)*bs->dsk.meta_block_size);
+            io_uring_prep_readv(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + (1+next_offset)*bs->dsk.meta_block_size);
             bs->ringloop->submit();
             submitted++;
 resume_5:
@@ -291,7 +291,7 @@ resume_5:
             GET_SQE();
             data->iov = { metadata_buffer, (size_t)bs->dsk.meta_block_size };
             data->callback = [this](ring_data_t *data) { handle_event(data, -1); };
-            my_uring_prep_writev(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + (1+next_offset)*bs->dsk.meta_block_size);
+            io_uring_prep_writev(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + (1+next_offset)*bs->dsk.meta_block_size);
             bs->ringloop->submit();
             submitted++;
 resume_6:
@@ -313,7 +313,7 @@ resume_6:
     if (zero_on_init && !bs->disable_meta_fsync)
     {
         GET_SQE();
-        my_uring_prep_fsync(sqe, bs->dsk.meta_fd, IORING_FSYNC_DATASYNC);
+        io_uring_prep_fsync(sqe, bs->dsk.meta_fd, IORING_FSYNC_DATASYNC);
         last_read_offset = 0;
         data->iov = { 0 };
         data->callback = [this](ring_data_t *data) { handle_event(data, -1); };
@@ -495,7 +495,7 @@ int blockstore_init_journal::loop()
     data = ((ring_data_t*)sqe->user_data);
     data->iov = { submitted_buf, (size_t)bs->journal.block_size };
     data->callback = simple_callback;
-    my_uring_prep_readv(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset);
+    io_uring_prep_readv(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset);
     bs->ringloop->submit();
     wait_count = 1;
 resume_1:
@@ -536,7 +536,7 @@ resume_1:
             GET_SQE();
             data->iov = (struct iovec){ submitted_buf, (size_t)(2*bs->journal.block_size) };
             data->callback = simple_callback;
-            my_uring_prep_writev(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset);
+            io_uring_prep_writev(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset);
             wait_count++;
             bs->ringloop->submit();
         resume_6:
@@ -548,7 +548,7 @@ resume_1:
             if (!bs->disable_journal_fsync)
             {
                 GET_SQE();
-                my_uring_prep_fsync(sqe, bs->dsk.journal_fd, IORING_FSYNC_DATASYNC);
+                io_uring_prep_fsync(sqe, bs->dsk.journal_fd, IORING_FSYNC_DATASYNC);
                 data->iov = { 0 };
                 data->callback = simple_callback;
                 wait_count++;
@@ -636,7 +636,7 @@ resume_1:
                     (size_t)(end - journal_pos < JOURNAL_BUFFER_SIZE ? end - journal_pos : JOURNAL_BUFFER_SIZE),
                 };
                 data->callback = [this](ring_data_t *data1) { handle_event(data1); };
-                my_uring_prep_readv(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset + journal_pos);
+                io_uring_prep_readv(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset + journal_pos);
                 bs->ringloop->submit();
             }
             while (done.size() > 0)
@@ -651,7 +651,7 @@ resume_1:
                         GET_SQE();
                         data->iov = { init_write_buf, (size_t)bs->journal.block_size };
                         data->callback = simple_callback;
-                        my_uring_prep_writev(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset + init_write_sector);
+                        io_uring_prep_writev(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset + init_write_sector);
                         wait_count++;
                         bs->ringloop->submit();
                     resume_7:
@@ -665,7 +665,7 @@ resume_1:
                             GET_SQE();
                             data->iov = { 0 };
                             data->callback = simple_callback;
-                            my_uring_prep_fsync(sqe, bs->dsk.journal_fd, IORING_FSYNC_DATASYNC);
+                            io_uring_prep_fsync(sqe, bs->dsk.journal_fd, IORING_FSYNC_DATASYNC);
                             wait_count++;
                             bs->ringloop->submit();
                         }

src/blockstore/blockstore_journal.cpp

@@ -178,7 +178,7 @@ void blockstore_impl_t::prepare_journal_sector_write(int cur_sector, blockstore_
         // Caller must ensure availability of an SQE
         assert(sqe != NULL);
         ring_data_t *data = ((ring_data_t*)sqe->user_data);
-        journal.sector_info[cur_sector].written = true;
+        // <written> flag will be set at the moment of actual submission
         journal.sector_info[cur_sector].submit_id = ++journal.submit_id;
         assert(journal.submit_id != 0); // check overflow
         journal.submitting_sectors.push_back(cur_sector);
@@ -190,7 +190,7 @@ void blockstore_impl_t::prepare_journal_sector_write(int cur_sector, blockstore_
             (size_t)journal.block_size
         };
         data->callback = [this, flush_id = journal.submit_id](ring_data_t *data) { handle_journal_write(data, flush_id); };
-        my_uring_prep_writev(
+        io_uring_prep_writev(
             sqe, dsk.journal_fd, &data->iov, 1, journal.offset + journal.sector_info[cur_sector].offset
         );
     }
@@ -326,31 +326,3 @@ void journal_t::dump_diagnostics()
         journal_used_it == used_sectors.end() ? 0 : journal_used_it->second
     );
 }
-
-static uint64_t zero_page[4096];
-
-uint32_t crc32c_pad(uint32_t prev_crc, const void *buf, size_t len, size_t left_pad, size_t right_pad)
-{
-    uint32_t r = prev_crc;
-    while (left_pad >= 4096)
-    {
-        r = crc32c(r, zero_page, 4096);
-        left_pad -= 4096;
-    }
-    if (left_pad > 0)
-        r = crc32c(r, zero_page, left_pad);
-    r = crc32c(r, buf, len);
-    while (right_pad >= 4096)
-    {
-        r = crc32c(r, zero_page, 4096);
-        right_pad -= 4096;
-    }
-    if (left_pad > 0)
-        r = crc32c(r, zero_page, right_pad);
-    return r;
-}
-
-uint32_t crc32c_nopad(uint32_t prev_crc, const void *buf, size_t len, size_t left_pad, size_t right_pad)
-{
-    return crc32c(0, buf, len);
-}

src/blockstore/blockstore_journal.h

@@ -216,6 +216,3 @@ struct blockstore_journal_check_t
 };
 
 journal_entry* prefill_single_journal_entry(journal_t & journal, uint16_t type, uint32_t size);
-
-uint32_t crc32c_pad(uint32_t prev_crc, const void *buf, size_t len, size_t left_pad, size_t right_pad);
-uint32_t crc32c_nopad(uint32_t prev_crc, const void *buf, size_t len, size_t left_pad, size_t right_pad);

src/blockstore/blockstore_read.cpp

@@ -27,7 +27,7 @@ int blockstore_impl_t::fulfill_read_push(blockstore_op_t *op, void *buf, uint64_
     BS_SUBMIT_GET_SQE(sqe, data);
     data->iov = (struct iovec){ buf, (size_t)len };
     PRIV(op)->pending_ops++;
-    my_uring_prep_readv(
+    io_uring_prep_readv(
         sqe,
         IS_JOURNAL(item_state) ? dsk.journal_fd : dsk.data_fd,
         &data->iov, 1,
@@ -356,7 +356,7 @@ bool blockstore_impl_t::read_checksum_block(blockstore_op_t *op, int rv_pos, uin
         int n_cur = n_iov-n_pos < IOV_MAX ? n_iov-n_pos : IOV_MAX;
         BS_SUBMIT_GET_SQE(sqe, data);
         PRIV(op)->pending_ops++;
-        my_uring_prep_readv(sqe, submit_fd, iov + n_pos, n_cur, submit_offset + clean_loc + item_start + d_pos);
+        io_uring_prep_readv(sqe, submit_fd, iov + n_pos, n_cur, submit_offset + clean_loc + item_start + d_pos);
         data->callback = [this, op](ring_data_t *data) { handle_read_event(data, op); };
         if (n_pos > 0 || n_pos + IOV_MAX < n_iov)
         {
@@ -702,7 +702,7 @@ uint8_t* blockstore_impl_t::read_clean_meta_block(blockstore_op_t *op, uint64_t
     BS_SUBMIT_GET_SQE(sqe, data);
     data->iov = (struct iovec){ buf, (size_t)dsk.meta_block_size };
     PRIV(op)->pending_ops++;
-    my_uring_prep_readv(sqe, dsk.meta_fd, &data->iov, 1, dsk.meta_offset + dsk.meta_block_size + sector);
+    io_uring_prep_readv(sqe, dsk.meta_fd, &data->iov, 1, dsk.meta_offset + dsk.meta_block_size + sector);
     data->callback = [this, op](ring_data_t *data) { handle_read_event(data, op); };
     // return pointer to checksums + bitmap
     return buf + pos + sizeof(clean_disk_entry);

src/blockstore/blockstore_rollback.cpp

@@ -101,7 +101,7 @@ resume_2:
     if (!disable_journal_fsync)
     {
         BS_SUBMIT_GET_SQE(sqe, data);
-        my_uring_prep_fsync(sqe, dsk.journal_fd, IORING_FSYNC_DATASYNC);
+        io_uring_prep_fsync(sqe, dsk.journal_fd, IORING_FSYNC_DATASYNC);
         data->iov = { 0 };
         data->callback = [this, op](ring_data_t *data) { handle_write_event(data, op); };
         PRIV(op)->min_flushed_journal_sector = PRIV(op)->max_flushed_journal_sector = 0;

src/blockstore/blockstore_stable.cpp

@@ -400,7 +400,7 @@ resume_2:
     if (!disable_journal_fsync)
     {
         BS_SUBMIT_GET_SQE(sqe, data);
-        my_uring_prep_fsync(sqe, dsk.journal_fd, IORING_FSYNC_DATASYNC);
+        io_uring_prep_fsync(sqe, dsk.journal_fd, IORING_FSYNC_DATASYNC);
         data->iov = { 0 };
         data->callback = [this, op](ring_data_t *data) { handle_write_event(data, op); };
         PRIV(op)->min_flushed_journal_sector = PRIV(op)->max_flushed_journal_sector = 0;

src/blockstore/blockstore_sync.cpp

@@ -58,7 +58,7 @@ int blockstore_impl_t::continue_sync(blockstore_op_t *op)
         if (!disable_data_fsync)
         {
             BS_SUBMIT_GET_SQE(sqe, data);
-            my_uring_prep_fsync(sqe, dsk.data_fd, IORING_FSYNC_DATASYNC);
+            io_uring_prep_fsync(sqe, dsk.data_fd, IORING_FSYNC_DATASYNC);
             data->iov = { 0 };
             data->callback = [this, op](ring_data_t *data) { handle_write_event(data, op); };
             PRIV(op)->min_flushed_journal_sector = PRIV(op)->max_flushed_journal_sector = 0;
@@ -149,7 +149,7 @@ int blockstore_impl_t::continue_sync(blockstore_op_t *op)
         if (!disable_journal_fsync)
         {
             BS_SUBMIT_GET_SQE(sqe, data);
-            my_uring_prep_fsync(sqe, dsk.journal_fd, IORING_FSYNC_DATASYNC);
+            io_uring_prep_fsync(sqe, dsk.journal_fd, IORING_FSYNC_DATASYNC);
             data->iov = { 0 };
             data->callback = [this, op](ring_data_t *data) { handle_write_event(data, op); };
             PRIV(op)->min_flushed_journal_sector = PRIV(op)->max_flushed_journal_sector = 0;

src/blockstore/blockstore_write.cpp

@@ -169,26 +169,7 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
         if (op->opcode == BS_OP_WRITE_STABLE)
             state |= BS_ST_INSTANT;
         if (op->bitmap)
-        {
-            // Only allow to overwrite part of the object bitmap respective to the write's offset/len
-            uint32_t bit = op->offset/dsk.bitmap_granularity;
-            uint32_t bits_left = op->len/dsk.bitmap_granularity;
-            while (!(bit % 8) && bits_left >= 8)
-            {
-                // Copy bytes
-                dyn_ptr[bit/8] = ((uint8_t*)op->bitmap)[bit/8];
-                bit += 8;
-                bits_left -= 8;
-            }
-            while (bits_left > 0)
-            {
-                // Copy bits
-                dyn_ptr[bit/8] = (dyn_ptr[bit/8] & ~(1 << (bit%8)))
-                    | (((uint8_t*)op->bitmap)[bit/8] & (1 << bit%8));
-                bit++;
-                bits_left--;
-            }
-        }
+            memcpy(dyn_ptr, op->bitmap, dsk.clean_entry_bitmap_size);
     }
     // Calculate checksums
     // FIXME: Allow to receive checksums from outside?
@@ -384,7 +365,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
         }
         data->iov.iov_len = op->len + stripe_offset + stripe_end; // to check it in the callback
         data->callback = [this, op](ring_data_t *data) { handle_write_event(data, op); };
-        my_uring_prep_writev(
+        io_uring_prep_writev(
             sqe, dsk.data_fd, PRIV(op)->iov_zerofill, vcnt, dsk.data_offset + (loc << dsk.block_order) + op->offset - stripe_offset
         );
         PRIV(op)->pending_ops = 1;
@@ -511,7 +492,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
                 .op = op,
             });
             data2->callback = [this, flush_id = journal.submit_id](ring_data_t *data) { handle_journal_write(data, flush_id); };
-            my_uring_prep_writev(
+            io_uring_prep_writev(
                 sqe2, dsk.journal_fd, &data2->iov, 1, journal.offset + journal.next_free
             );
             PRIV(op)->pending_ops++;

src/blockstore/fio_engine.cpp

@@ -26,6 +26,7 @@
 
 #include "blockstore.h"
 #include "epoll_manager.h"
+#include "malloc_or_die.h"
 #include "json11/json11.hpp"
 #include "fio_headers.h"
 
@@ -37,6 +38,8 @@ struct bs_data
     /* The list of completed io_u structs. */
     std::vector<io_u*> completed;
     int op_n = 0, inflight = 0;
+    bool ec = false;
+    bool imm = true;
     bool last_sync = false;
     bool trace = false;
 };
@@ -45,6 +48,7 @@ struct bs_options
 {
     int __pad;
     char *json_config = NULL;
+    int ec = 0;
     int trace = 0;
 };
 
@@ -58,6 +62,16 @@ static struct fio_option options[] = {
         .category = FIO_OPT_C_ENGINE,
         .group  = FIO_OPT_G_FILENAME,
     },
+    {
+        .name   = "ec",
+        .lname  = "Use EC write method",
+        .type   = FIO_OPT_BOOL,
+        .off1   = offsetof(struct bs_options, ec),
+        .help   = "Use EC write method",
+        .def    = "0",
+        .category = FIO_OPT_C_ENGINE,
+        .group  = FIO_OPT_G_FILENAME,
+    },
     {
         .name   = "bs_trace",
         .lname  = "trace",
@@ -88,6 +102,7 @@ static int bs_setup(struct thread_data *td)
         return 1;
     }
     td->io_ops_data = bsd;
+    bsd->ec = o->ec;
 
     if (!td->files_index)
     {
@@ -148,6 +163,8 @@ static int bs_init(struct thread_data *td)
     bsd->ringloop = new ring_loop_t(RINGLOOP_DEFAULT_SIZE);
     bsd->epmgr = new epoll_manager_t(bsd->ringloop);
     bsd->bs = new blockstore_t(config, bsd->ringloop, bsd->epmgr->tfd);
+    bsd->imm = config.find("immediate_commit") == config.end() ||
+        config["immediate_commit"] == "all";
     while (1)
     {
         bsd->ringloop->loop();
@@ -203,7 +220,7 @@ static enum fio_q_status bs_queue(struct thread_data *td, struct io_u *io)
         };
         break;
     case DDIR_WRITE:
-        op->opcode = BS_OP_WRITE_STABLE;
+        op->opcode = bsd->ec ? BS_OP_WRITE : BS_OP_WRITE_STABLE;
         op->buf = io->xfer_buf;
         op->oid = {
             .inode = 1,
@@ -212,16 +229,57 @@ 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, n = bsd->op_n](blockstore_op_t *op)
+        if (bsd->ec)
         {
-            io->error = op->retval < 0 ? -op->retval : 0;
-            bs_data *bsd = (bs_data*)io->engine_data;
-            bsd->inflight--;
-            bsd->completed.push_back(io);
-            if (bsd->trace)
-                printf("--- OP_WRITE %zx n=%d retval=%d\n", (size_t)op, n, op->retval);
-            delete op;
-        };
+            op->callback = [io, n = bsd->op_n](blockstore_op_t *op)
+            {
+                bs_data *bsd = (bs_data*)io->engine_data;
+                if (bsd->trace)
+                    printf("--- OP_WRITE %zx n=%d retval=%d\n", (size_t)op, n, op->retval);
+                if (op->retval < 0)
+                {
+                    io->error = op->retval < 0 ? -op->retval : 0;
+                    bsd->inflight--;
+                    bsd->completed.push_back(io);
+                    delete op;
+                }
+                else
+                {
+                    auto stab_op = new blockstore_op_t;
+                    stab_op->opcode = BS_OP_STABLE;
+                    stab_op->buf = malloc_or_die(sizeof(obj_ver_id));
+                    obj_ver_id *ver = (obj_ver_id *)stab_op->buf;
+                    ver[0].oid = op->oid;
+                    ver[0].version = op->version;
+                    stab_op->len = 1;
+                    stab_op->callback = [io, n](blockstore_op_t *op)
+                    {
+                        bs_data *bsd = (bs_data*)io->engine_data;
+                        if (bsd->trace)
+                            printf("--- OP_STABLE %zx n=%d retval=%d\n", (size_t)op, n, op->retval);
+                        io->error = op->retval < 0 ? -op->retval : 0;
+                        bsd->inflight--;
+                        bsd->completed.push_back(io);
+                        delete op;
+                    };
+                    bsd->bs->enqueue_op(stab_op);
+                    delete op;
+                }
+            };
+        }
+        else
+        {
+            op->callback = [io, n = bsd->op_n](blockstore_op_t *op)
+            {
+                bs_data *bsd = (bs_data*)io->engine_data;
+                if (bsd->trace)
+                    printf("--- OP_WRITE_STABLE %zx n=%d retval=%d\n", (size_t)op, n, op->retval);
+                io->error = op->retval < 0 ? -op->retval : 0;
+                bsd->inflight--;
+                bsd->completed.push_back(io);
+                delete op;
+            };
+        }
         bsd->last_sync = false;
         break;
     case DDIR_SYNC:
@@ -301,7 +359,7 @@ static int bs_invalidate(struct thread_data *td, struct fio_file *f)
     return 0;
 }
 
-struct ioengine_ops ioengine = {
+struct ioengine_ops __attribute__((visibility("default"))) ioengine = {
     .name               = "vitastor_blockstore",
     .version            = FIO_IOOPS_VERSION,
     .flags              = FIO_MEMALIGN | FIO_DISKLESSIO | FIO_NOEXTEND,

src/client/CMakeLists.txt

@@ -68,6 +68,12 @@ if (HAVE_NBD_NETLINK_H AND NL3_LIBRARIES)
 	target_compile_definitions(vitastor-nbd PUBLIC HAVE_NBD_NETLINK_H)
 endif (HAVE_NBD_NETLINK_H AND NL3_LIBRARIES)
 
+# vitastor-ublk
+add_executable(vitastor-ublk
+	ublk_server.cpp
+)
+target_link_libraries(vitastor-ublk vitastor_client)
+
 if (${WITH_QEMU})
 	# qemu_driver.so
 	add_library(qemu_vitastor SHARED

src/client/cluster_client.cpp

@@ -1317,7 +1317,8 @@ int cluster_client_t::try_send(cluster_op_t *op, int i)
     auto & pool_cfg = st_cli.pool_config.at(INODE_POOL(op->cur_inode));
     auto pg_it = pool_cfg.pg_config.find(part->pg_num);
     if (pg_it != pool_cfg.pg_config.end() &&
-        !pg_it->second.pause && pg_it->second.cur_primary)
+        !pg_it->second.pause && pg_it->second.cur_primary &&
+        (pg_it->second.cur_state & PG_ACTIVE))
     {
         osd_num_t primary_osd = pg_it->second.cur_primary;
         if (pool_cfg.local_reads != POOL_LOCAL_READ_PRIMARY &&

src/client/cluster_client.h

@@ -31,7 +31,7 @@ struct cluster_op_part_t
     osd_op_t op;
 };
 
-struct cluster_op_t
+struct __attribute__((visibility("default"))) cluster_op_t
 {
     uint64_t opcode; // OSD_OP_READ, OSD_OP_WRITE, OSD_OP_SYNC, OSD_OP_DELETE, OSD_OP_READ_BITMAP, OSD_OP_READ_CHAIN_BITMAP
     uint64_t inode;
@@ -81,7 +81,7 @@ struct inode_list_pg_t;
 class writeback_cache_t;
 
 // FIXME: Split into public and private interfaces
-class cluster_client_t
+class __attribute__((visibility("default"))) cluster_client_t
 {
 #ifdef __MOCK__
 public:
@@ -127,7 +127,7 @@ public:
     ring_consumer_t consumer;
     std::vector<std::function<void(void)>> on_ready_hooks;
     int list_retry_timeout_id = -1;
-    timespec list_retry_time;
+    timespec list_retry_time = {};
     std::vector<inode_list_t*> lists;
     std::multimap<osd_num_t, osd_op_t*> raw_ops;
     int continuing_ops = 0;

src/client/cluster_client_list.cpp

@@ -31,7 +31,7 @@ struct inode_list_pg_t
     osd_num_t cur_primary = 0;
     int state = 0;
     int inflight_ops = 0;
-    timespec wait_until;
+    timespec wait_until = {};
     std::vector<inode_list_osd_t> list_osds;
 
     bool has_unstable = false;
@@ -177,6 +177,9 @@ void cluster_client_t::retry_start_pg_listing(inode_list_pg_t *pg)
         if (tv.tv_sec < pg->wait_until.tv_sec ||
             tv.tv_sec == pg->wait_until.tv_sec && tv.tv_nsec < pg->wait_until.tv_nsec)
         {
+            // Ensure that the retry timer is set
+            set_list_retry_timeout(pg->wait_until.tv_sec*1000 - tv.tv_sec*1000 +
+                (pg->wait_until.tv_nsec - tv.tv_nsec)/1000000, pg->wait_until);
             return;
         }
     }

src/client/etcd_state_client.cpp

@@ -1167,7 +1167,7 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
             if (!cur_primary || !value["state"].is_array() || !state ||
                 (state & PG_OFFLINE) && state != PG_OFFLINE ||
                 (state & PG_PEERING) && state != PG_PEERING ||
-                (state & PG_INCOMPLETE) && state != PG_INCOMPLETE)
+                (state & PG_INCOMPLETE) && state != PG_INCOMPLETE && state != (PG_INCOMPLETE|PG_HAS_INVALID))
             {
                 fprintf(stderr, "Unexpected pool %u PG %u state in etcd: primary=%ju, state=%s\n", pool_id, pg_num, cur_primary, value["state"].dump().c_str());
                 return;

src/client/etcd_state_client.h

@@ -92,7 +92,7 @@ struct inode_watch_t
 
 struct http_co_t;
 
-struct etcd_state_client_t
+struct __attribute__((visibility("default"))) etcd_state_client_t
 {
 protected:
     std::vector<std::string> local_ips;

src/client/fio_cluster.cpp

@@ -525,7 +525,7 @@ static int sec_invalidate(struct thread_data *td, struct fio_file *f)
     return 0;
 }
 
-struct ioengine_ops ioengine = {
+struct ioengine_ops __attribute__((visibility("default"))) ioengine = {
     .name               = "vitastor_cluster",
     .version            = FIO_IOOPS_VERSION,
     .flags              = FIO_MEMALIGN | FIO_DISKLESSIO | FIO_NOEXTEND,

src/client/fio_sec_osd.cpp

@@ -437,7 +437,7 @@ static int sec_invalidate(struct thread_data *td, struct fio_file *f)
     return 0;
 }
 
-struct ioengine_ops ioengine = {
+struct ioengine_ops __attribute__((visibility("default"))) ioengine = {
     .name               = "vitastor_secondary_osd",
     .version            = FIO_IOOPS_VERSION,
     .flags              = FIO_MEMALIGN | FIO_DISKLESSIO | FIO_NOEXTEND,

src/client/messenger.cpp

@@ -70,7 +70,7 @@ void msgr_iothread_t::add_to_ringloop(ring_loop_t *outer_loop)
     assert(sqe != NULL);
     this->outer_loop = outer_loop;
     this->outer_loop_data = ((ring_data_t*)sqe->user_data);
-    my_uring_prep_poll_add(sqe, eventfd, POLLIN);
+    io_uring_prep_poll_add(sqe, eventfd, POLLIN);
     outer_loop_data->callback = [this](ring_data_t *data)
     {
         if (data->res < 0)

src/client/messenger.h

@@ -174,7 +174,7 @@ struct osd_messenger_t;
 struct rdmacm_connecting_t;
 #endif
 
-struct osd_messenger_t
+struct __attribute__((visibility("default"))) osd_messenger_t
 {
 protected:
     int keepalive_timer_id = -1;

src/client/msgr_op.h

@@ -152,7 +152,7 @@ struct blockstore_op_t;
 
 struct osd_primary_op_data_t;
 
-struct osd_op_t
+struct __attribute__((visibility("default"))) osd_op_t
 {
     timespec tv_begin = { 0 }, tv_end = { 0 };
     uint64_t op_type = OSD_OP_IN;

src/client/msgr_receive.cpp

@@ -48,7 +48,7 @@ void osd_messenger_t::read_requests()
             }
             ring_data_t* data = ((ring_data_t*)sqe->user_data);
             data->callback = [this, cl](ring_data_t *data) { handle_read(data->res, cl); };
-            my_uring_prep_recvmsg(sqe, peer_fd, &cl->read_msg, 0);
+            io_uring_prep_recvmsg(sqe, peer_fd, &cl->read_msg, 0);
             if (iothread)
             {
                 iothread->add_sqe(sqe_local);
@@ -109,6 +109,7 @@ bool osd_messenger_t::handle_read(int result, osd_client_t *cl)
             if (!handle_read_buffer(cl, cl->in_buf, result))
             {
                 clear_immediate_ops(peer_fd);
+                handle_immediate_ops();
                 return false;
             }
         }
@@ -122,6 +123,7 @@ bool osd_messenger_t::handle_read(int result, osd_client_t *cl)
                 if (!handle_finished_read(cl))
                 {
                     clear_immediate_ops(peer_fd);
+                    handle_immediate_ops();
                     return false;
                 }
             }
@@ -140,7 +142,7 @@ void osd_messenger_t::clear_immediate_ops(int peer_fd)
     size_t i = 0, j = 0;
     while (i < set_immediate_ops.size())
     {
-        if (set_immediate_ops[i]->peer_fd == peer_fd)
+        if (set_immediate_ops[i]->peer_fd == peer_fd && set_immediate_ops[i]->op_type == OSD_OP_IN)
         {
             delete set_immediate_ops[i];
         }

src/client/msgr_send.cpp

@@ -218,11 +218,11 @@ bool osd_messenger_t::try_send(osd_client_t *cl)
         }
         if (use_zc)
         {
-            my_uring_prep_sendmsg_zc(sqe, peer_fd, &cl->write_msg, MSG_WAITALL);
+            io_uring_prep_sendmsg_zc(sqe, peer_fd, &cl->write_msg, MSG_WAITALL);
         }
         else
         {
-            my_uring_prep_sendmsg(sqe, peer_fd, &cl->write_msg, MSG_WAITALL);
+            io_uring_prep_sendmsg(sqe, peer_fd, &cl->write_msg, MSG_WAITALL);
         }
         if (iothread)
         {

src/client/msgr_stop.cpp

@@ -52,6 +52,7 @@ void osd_messenger_t::stop_client(int peer_fd, bool force, bool force_delete)
         return;
     }
     osd_client_t *cl = it->second;
+    // FIXME: This 'force' flag is probably an ugly reenterability hack - check its logic and maybe remove it
     if (cl->peer_state == PEER_CONNECTING && !force || cl->peer_state == PEER_STOPPED)
     {
         return;
@@ -73,6 +74,7 @@ void osd_messenger_t::stop_client(int peer_fd, bool force, bool force_delete)
     }
     // First set state to STOPPED so another stop_client() call doesn't try to free it again
     cl->refs++;
+    int prev_state = cl->peer_state;
     cl->peer_state = PEER_STOPPED;
     if (cl->osd_num)
     {
@@ -113,10 +115,12 @@ void osd_messenger_t::stop_client(int peer_fd, bool force, bool force_delete)
         // Break PG locks
         break_pg_locks(cl->in_osd_num);
     }
-    if (cl->osd_num)
+    if (cl->osd_num && prev_state != PEER_CONNECTING)
     {
         // Then repeer PGs because cancel_op() callbacks can try to perform
         // some actions and we need correct PG states to not do something silly
+        // PEER_CONNECTING has neither 'just dropped the connection' nor 'just connected'
+        // so do not repeer on it.
         repeer_pgs(cl->osd_num);
     }
     // Find the item again because it can be invalidated at this point

src/client/nbd_proxy.cpp

@@ -272,6 +272,8 @@ const char *help_text =
     "  --dev_num N\n"
     "    Use the specified device /dev/nbdN instead of automatic selection (alternative syntax\n"
     "    to /dev/nbdN positional parameter).\n"
+    "  --readonly\n"
+    "    Make the device read-only.\n"
     "  --foreground 1\n"
     "    Stay in foreground, do not daemonize.\n"
     "\n"
@@ -372,7 +374,7 @@ public:
             else if (args[i][0] == '-' && args[i][1] == '-')
             {
                 const char *opt = args[i]+2;
-                cfg[opt] = !strcmp(opt, "json") || !strcmp(opt, "all") ||
+                cfg[opt] = !strcmp(opt, "json") || !strcmp(opt, "all") || !strcmp(opt, "readonly") ||
                     !strcmp(opt, "force") || i == narg-1 ? "1" : args[++i];
             }
             else if (pos == 0)
@@ -695,20 +697,6 @@ help:
             ringloop->loop();
             ringloop->wait();
         }
-        stop = false;
-        cluster_op_t *close_sync = new cluster_op_t;
-        close_sync->opcode = OSD_OP_SYNC;
-        close_sync->callback = [&stop](cluster_op_t *op)
-        {
-            stop = true;
-            delete op;
-        };
-        cli->execute(close_sync);
-        while (!stop)
-        {
-            ringloop->loop();
-            ringloop->wait();
-        }
         cli->flush();
         delete cli;
         delete epmgr;
@@ -912,7 +900,7 @@ protected:
             int r, nbd = open(path, O_RDWR), qd_fd;
             if (nbd < 0)
             {
-                write(notifyfd[1], &errno, sizeof(errno));
+                (void)write(notifyfd[1], &errno, sizeof(errno));
                 exit(1);
             }
             r = ioctl(nbd, NBD_SET_SOCK, sockfd[1]);
@@ -954,7 +942,7 @@ protected:
             close(qd_fd);
             // Notify parent
             errno = 0;
-            write(notifyfd[1], &errno, sizeof(errno));
+            (void)write(notifyfd[1], &errno, sizeof(errno));
             close(notifyfd[1]);
             close(sockfd[0]);
             if (bg)
@@ -971,11 +959,11 @@ protected:
             ioctl(nbd, NBD_CLEAR_SOCK);
             exit(0);
     end_close:
-            write(notifyfd[1], &errno, sizeof(errno));
+            (void)write(notifyfd[1], &errno, sizeof(errno));
             close(nbd);
             exit(2);
     end_unmap:
-            write(notifyfd[1], &errno, sizeof(errno));
+            (void)write(notifyfd[1], &errno, sizeof(errno));
             ioctl(nbd, NBD_CLEAR_SOCK);
             close(nbd);
             exit(3);
@@ -1008,7 +996,7 @@ protected:
         data->callback = [this](ring_data_t *data) { handle_send(data->res); };
         send_msg.msg_iov = send_list.data();
         send_msg.msg_iovlen = send_list.size();
-        my_uring_prep_sendmsg(sqe, nbd_fd, &send_msg, MSG_ZEROCOPY);
+        io_uring_prep_sendmsg(sqe, nbd_fd, &send_msg, MSG_ZEROCOPY);
     }
 
     void handle_send(int result)
@@ -1076,7 +1064,7 @@ protected:
         }
         read_msg.msg_iov = &read_iov;
         read_msg.msg_iovlen = 1;
-        my_uring_prep_recvmsg(sqe, nbd_fd, &read_msg, 0);
+        io_uring_prep_recvmsg(sqe, nbd_fd, &read_msg, 0);
     }
 
     void handle_read(int result)

src/client/pg_states.h

@@ -3,6 +3,8 @@
 
 #pragma once
 
+#pragma GCC visibility push(default)
+
 // Placement group states
 // STARTING -> [acquire lock] -> PEERING -> INCOMPLETE|ACTIVE
 // ACTIVE -> REPEERING -> PEERING
@@ -50,3 +52,5 @@ extern const int pg_state_bit_count;
 extern const int object_state_bits[];
 extern const char *object_state_names[];
 extern const int object_state_bit_count;
+
+#pragma GCC visibility pop

src/client/qemu_driver.c

@@ -5,7 +5,6 @@
 
 #ifdef VITASTOR_SOURCE_TREE
 #define BUILD_DSO
-#define _GNU_SOURCE
 #endif
 #include "qemu/osdep.h"
 #include "qemu/main-loop.h"
@@ -14,27 +13,42 @@
 #endif
 #include "block/block_int.h"
 #include "qapi/error.h"
-#include "qapi/qmp/qdict.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/error-report.h"
 #include "qemu/module.h"
 #include "qemu/option.h"
 
-#if QEMU_VERSION_MAJOR >= 3
-#include "qemu/units.h"
-#include "block/qdict.h"
-#include "qemu/cutils.h"
-#elif QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR >= 10
-#include "qemu/cutils.h"
+#if QEMU_VERSION_MAJOR >= 10
+#include "qobject/qstring.h"
+#include "qobject/qdict.h"
+#include "qobject/qobject.h"
+#include "qobject/qjson.h"
+#elif QEMU_VERSION_MAJOR >= 3 || QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR >= 10
 #include "qapi/qmp/qstring.h"
+#include "qapi/qmp/qdict.h"
+#include "qapi/qmp/qobject.h"
 #include "qapi/qmp/qjson.h"
 #else
+#include "qapi/qmp/qstring.h"
 #include "qapi/qmp/qint.h"
+#include "qapi/qmp/qdict.h"
+#include "qapi/qmp/qobject.h"
+#include "qapi/qmp/qjson.h"
 #define qdict_put_int(options, name, num_val) qdict_put_obj(options, name, QOBJECT(qint_from_int(num_val)))
 #define qdict_put_str(options, name, value) qdict_put_obj(options, name, QOBJECT(qstring_from_str(value)))
 #define qobject_unref QDECREF
 #endif
-#if QEMU_VERSION_MAJOR == 4 && QEMU_VERSION_MINOR >= 2 || QEMU_VERSION_MAJOR > 4
+
+// parse_uint_full()
+#if QEMU_VERSION_MAJOR >= 3 || QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR >= 6
+#include "qemu/cutils.h"
+#else
+#include "qemu-common.h"
+#endif
+
+#if QEMU_VERSION_MAJOR >= 10
+#include "system/replay.h"
+#elif QEMU_VERSION_MAJOR == 4 && QEMU_VERSION_MINOR >= 2 || QEMU_VERSION_MAJOR > 4
 #include "sysemu/replay.h"
 #else
 #include "sysemu/sysemu.h"
@@ -43,11 +57,11 @@
 #include "vitastor_c.h"
 
 #ifdef VITASTOR_SOURCE_TREE
-void qemu_module_dummy(void)
+void __attribute__((visibility("default"))) qemu_module_dummy(void)
 {
 }
 
-void DSO_STAMP_FUN(void)
+void __attribute__((visibility("default"))) DSO_STAMP_FUN(void)
 {
 }
 #endif
@@ -65,6 +79,7 @@ typedef struct VitastorClient
     char *etcd_host;
     char *etcd_prefix;
     char *image;
+    char *file_mirror_path;
     int skip_parents;
     uint64_t inode;
     uint64_t pool;
@@ -432,6 +447,74 @@ static void strarray_free(str_array *a)
 }
 #endif
 
+static void check_config(VitastorClient *client)
+{
+    size_t bufsize = 64*1024, maxsize = 1024*1024, done = 0;
+    ssize_t r = 0;
+    char *data = NULL;
+    QObject *obj = NULL;
+    QDict *qd = NULL;
+    int fd = open(client->config_path, O_RDONLY);
+    if (fd < 0)
+    {
+        fprintf(stderr, "vitastor: failed to read %s: %s\n", client->config_path, strerror(errno));
+        return;
+    }
+    data = (char*)malloc(bufsize);
+    if (!data)
+    {
+        fprintf(stderr, "vitastor: memory allocation failed\n");
+        goto end_free;
+    }
+    while (1)
+    {
+        if (bufsize <= done)
+        {
+            if (bufsize >= maxsize)
+            {
+                fprintf(stderr, "vitastor: config file exceeds %zu bytes\n", maxsize);
+                goto end_free;
+            }
+            bufsize *= 2;
+            data = (char*)realloc(data, bufsize);
+            if (!data)
+            {
+                fprintf(stderr, "vitastor: memory allocation failed\n");
+                goto end_free;
+            }
+        }
+        r = read(fd, data+done, bufsize-done);
+        if (r < 0)
+        {
+            if (errno == EAGAIN || errno == EINTR)
+                continue;
+            fprintf(stderr, "vitastor: failed to read %s: %s\n", client->config_path, strerror(errno));
+            break;
+        }
+        if (!r)
+        {
+            break;
+        }
+        done += r;
+    }
+    obj = qobject_from_json(data
+#if QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR >= 9 || QEMU_VERSION_MAJOR >= 3
+        , NULL
+#endif
+    );
+    qd = qobject_to(QDict, obj);
+    if (qd)
+    {
+        client->file_mirror_path = g_strdup(qdict_get_try_str(qd, "qemu_file_mirror_path"));
+    }
+end_free:
+    if (obj)
+        qobject_unref(obj);
+    if (data)
+        free(data);
+    close(fd);
+}
+
 static int vitastor_file_open(BlockDriverState *bs, QDict *options, int flags, Error **errp)
 {
     VitastorRPC task;
@@ -450,6 +533,10 @@ static int vitastor_file_open(BlockDriverState *bs, QDict *options, int flags, E
     client->rdma_gid_index = qdict_get_try_int(options, "rdma-gid-index", 0);
     client->rdma_mtu = qdict_get_try_int(options, "rdma-mtu", 0);
     client->ctx = bdrv_get_aio_context(bs);
+    if (client->config_path && strlen(client->config_path))
+    {
+        check_config(client);
+    }
 #if defined VITASTOR_C_API_VERSION && VITASTOR_C_API_VERSION >= 2
     str_array opt = {};
     char version_buffer[32];
@@ -624,6 +711,11 @@ static void vitastor_refresh_filename(BlockDriverState *bs)
     VitastorClient *client = bs->opaque;
     size_t len = 0;
     int n = 0;
+    if (client->image && client->file_mirror_path)
+    {
+        len = snprintf(bs->exact_filename, sizeof(bs->exact_filename), "%s%s", client->file_mirror_path, client->image);
+        return;
+    }
     len = snprintf(bs->exact_filename, sizeof(bs->exact_filename), "vitastor://");
     if (len < sizeof(bs->exact_filename))
     {

src/client/ublk_server.cpp

@@ -0,0 +1,906 @@
+// Copyright (c) Vitaliy Filippov, 2019+
+// License: VNPL-1.1 (see README.md for details)
+// ublk-based Vitastor block device in userspace
+
+#include <errno.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <sys/ioctl.h>
+#include <dirent.h>
+
+#include <fcntl.h>
+#include <signal.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+#include <sys/mman.h>
+#include <unistd.h>
+
+#include "../liburing/include/ublk_cmd.h"
+#include "cluster_client.h"
+#include "epoll_manager.h"
+#include "str_util.h"
+
+const char *exe_name = NULL;
+
+const char *help_text =
+    "Vitastor ublk server " VITASTOR_VERSION "\n"
+    "(c) Vitaliy Filippov, 2025+ (VNPL-1.1)\n"
+    "\n"
+    "COMMANDS:\n"
+    "\n"
+    "vitastor-ublk map [OPTIONS] (--image <image> | --pool <pool> --inode <inode> --size <size in bytes>)\n"
+    "  Map a ublk device. Options:\n"
+    "  --recover\n"
+    "    Recover a mapped device if the previous ublk server is dead.\n"
+    "  --queue_depth 256\n"
+    "    Maximum queue size for the device.\n"
+    "  --max_io_size 1M\n"
+    "    Maximum single I/O size for the device. Default: max(1 MB, pool block size * EC part count).\n"
+    "  --readonly\n"
+    "    Make the device read-only.\n"
+    "  --hdd\n"
+    "    Mark the device as rotational.\n"
+    "  --dev_num N\n"
+    "    Use the specified device /dev/ublkbN instead of automatic selection (alternative syntax\n"
+    "    to /dev/ublkbN positional parameter).\n"
+    "  --pidfile /run/ublk_pid_file.pid\n"
+    "    Write process ID to the specified file.\n"
+    "  --logfile /path/to/log/file.txt\n"
+    "    Write log messages to the specified file instead of dropping them (in background mode)\n"
+    "    or printing them to the standard output (in foreground mode).\n"
+    "  --foreground 1\n"
+    "    Stay in foreground, do not daemonize.\n"
+    "\n"
+    "vitastor-ublk unmap [--force] /dev/ublkb<N>\n"
+    "  Unmap a Vitastor ublk device. Do not check if it's actually mapped if --force is specified.\n"
+    "\n"
+    "vitastor-ublk ls [--json]\n"
+    "  List mapped Vitastor ublk devices, optionally in JSON format.\n"
+    "\n"
+    "Use vitastor-ublk --help <command> for command details or vitastor-ublk --help --all for all details.\n"
+    "\n"
+    "All usual Vitastor config options like --config_path <path_to_config> may also be specified in CLI.\n"
+;
+
+class ublk_server
+{
+protected:
+    std::string image_name;
+    uint64_t inode = 0;
+    uint64_t device_size = 0;
+    int req_dev_num = -1;
+    bool readonly = false;
+    bool hdd = false;
+    bool recover = false;
+    uint16_t queue_depth = 256;
+    uint32_t max_io_size = 0;
+
+    ring_loop_t *ringloop = NULL;
+    epoll_manager_t *epmgr = NULL;
+    cluster_client_t *cli = NULL;
+    inode_watch_t *watch = NULL;
+
+    std::string logfile = "/dev/null";
+    std::string pidfile;
+
+public:
+    ublk_server()
+    {
+        ringloop = new ring_loop_t(RINGLOOP_DEFAULT_SIZE, false, true);
+    }
+
+    ~ublk_server()
+    {
+        if (ctrl_fd >= 0)
+        {
+            close(ctrl_fd);
+            ctrl_fd = -1;
+        }
+        if (cdev_fd >= 0)
+        {
+            close(cdev_fd);
+            cdev_fd = -1;
+        }
+        for (auto & buf: buffers)
+        {
+            free(buf);
+        }
+        buffers.clear();
+        if (ringloop)
+        {
+            delete ringloop;
+            ringloop = NULL;
+        }
+    }
+
+    static json11::Json::object parse_args(int narg, const char *args[])
+    {
+        json11::Json::object cfg;
+        int pos = 0;
+        for (int i = 1; i < narg; i++)
+        {
+            if (!strcmp(args[i], "-h") || !strcmp(args[i], "--help"))
+            {
+                cfg["help"] = 1;
+            }
+            else if (args[i][0] == '-' && args[i][1] == '-')
+            {
+                const char *opt = args[i]+2;
+                cfg[opt] = !strcmp(opt, "json") || !strcmp(opt, "all") ||
+                    !strcmp(opt, "readonly") || !strcmp(opt, "hdd") || !strcmp(opt, "recover") ||
+                    !strcmp(opt, "force") || i == narg-1 ? "1" : args[++i];
+            }
+            else if (pos == 0)
+            {
+                cfg["command"] = args[i];
+                pos++;
+            }
+            else if (pos == 1)
+            {
+                char c = 0;
+                int n = 0;
+                if (sscanf(args[i], "/dev/ublkb%d%c", &n, &c) == 1)
+                    cfg["dev_num"] = n;
+                else if (sscanf(args[i], "/dev/ublkc%d%c", &n, &c) == 1)
+                    cfg["dev_num"] = n;
+                else
+                    cfg["dev_num"] = args[i];
+                pos++;
+            }
+        }
+        return cfg;
+    }
+
+    void exec(json11::Json cfg)
+    {
+        if (cfg["help"].bool_value())
+        {
+            goto help;
+        }
+        if (cfg["command"] == "map")
+        {
+            start(cfg);
+        }
+        else if (cfg["command"] == "unmap")
+        {
+            if (!cfg["dev_num"].is_number() &&
+                cfg["dev_num"].string_value() != "0" &&
+                !cfg["dev_num"].uint64_value())
+            {
+                fprintf(stderr, "device name or number is missing\n");
+                exit(1);
+            }
+            open_control();
+            unmap_device(cfg["dev_num"].uint64_value(), cfg["unpriv"].bool_value(), cfg["wait"].bool_value());
+        }
+        else if (cfg["command"] == "ls" || cfg["command"] == "list" || cfg["command"] == "list-mapped")
+        {
+            auto mapped = list_mapped();
+            print_mapped(mapped, !cfg["json"].is_null());
+        }
+        else
+        {
+help:
+            print_help(help_text, "vitastor-ublk", cfg["command"].string_value(), cfg["all"].bool_value());
+            exit(0);
+        }
+    }
+
+    void start(json11::Json cfg)
+    {
+        // Check options
+        if (cfg["dev_num"].string_value() != "" || cfg["dev_num"].is_number())
+        {
+            req_dev_num = cfg["dev_num"].uint64_value();
+        }
+        if (cfg["image"].string_value() != "")
+        {
+            // Use image name
+            image_name = cfg["image"].string_value();
+            inode = 0;
+        }
+        else
+        {
+            // Use pool, inode number and size
+            device_size = cfg["size"].is_string()
+                ? parse_size(cfg["size"].string_value())
+                : cfg["size"].uint64_value();
+            if (!device_size)
+            {
+                fprintf(stderr, "device size is missing\n");
+                exit(1);
+            }
+            inode = cfg["inode"].uint64_value();
+            uint64_t pool = cfg["pool"].uint64_value();
+            if (pool)
+            {
+                inode = INODE_WITH_POOL(pool, inode);
+            }
+            if (!INODE_POOL(inode))
+            {
+                fprintf(stderr, "pool is missing\n");
+                exit(1);
+            }
+        }
+        if (cfg["client_writeback_allowed"].is_null())
+        {
+            // ublk is always aware of fsync, so we allow write-back cache
+            // by default if it's enabled
+            auto obj = cfg.object_items();
+            obj["client_writeback_allowed"] = true;
+            cfg = obj;
+        }
+        readonly = cfg["readonly"].bool_value();
+        hdd = cfg["hdd"].bool_value();
+        recover = cfg["recover"].bool_value();
+        if (recover && req_dev_num < 0)
+        {
+            fprintf(stderr, "device is missing\n");
+            exit(1);
+        }
+
+        // Create client
+        epmgr = new epoll_manager_t(ringloop);
+        cli = new cluster_client_t(ringloop, epmgr->tfd, cfg);
+
+        // cli->config contains merged config
+        if (!cfg["queue_depth"].is_null())
+        {
+            queue_depth = cfg["queue_depth"].uint64_value();
+        }
+        else if (cli->config.find("ublk_queue_depth") != cli->config.end())
+        {
+            queue_depth = cli->config["ublk_queue_depth"].uint64_value();
+        }
+        if (!cfg["max_io_size"].is_null())
+        {
+            max_io_size = parse_size(cfg["max_io_size"].string_value());
+        }
+        else if (cli->config.find("ublk_max_io_size") != cli->config.end())
+        {
+            max_io_size = cli->config["ublk_max_io_size"].is_string()
+                ? parse_size(cli->config["ublk_max_io_size"].string_value())
+                : cli->config["ublk_max_io_size"].uint64_value();
+        }
+
+        // Load image metadata
+        while (!cli->is_ready())
+        {
+            ringloop->loop();
+            if (cli->is_ready())
+                break;
+            ringloop->wait();
+        }
+        if (!inode)
+        {
+            watch = cli->st_cli.watch_inode(image_name);
+            device_size = watch->cfg.size;
+            if (!watch->cfg.num || !device_size)
+            {
+                // Image does not exist
+                fprintf(stderr, "Image %s does not exist\n", image_name.c_str());
+                exit(1);
+            }
+        }
+        const bool writeback = cli->get_immediate_commit(inode);
+        auto pool_it = cli->st_cli.pool_config.find(INODE_POOL(inode ? inode : watch->cfg.num));
+        if (pool_it == cli->st_cli.pool_config.end())
+        {
+            fprintf(stderr, "Pool %u does not exist\n", INODE_POOL(inode ? inode : watch->cfg.num));
+            exit(1);
+        }
+        auto & pool_cfg = pool_it->second;
+        uint32_t pg_data_size = pool_cfg.data_block_size * (pool_cfg.scheme == POOL_SCHEME_REPLICATED
+            ? 1 : pool_cfg.pg_size-pool_cfg.parity_chunks);
+        if (max_io_size & (max_io_size-1))
+        {
+            fprintf(stderr, "max_io_size must be a power of 2\n");
+            exit(1);
+        }
+        uint32_t buf_size = max_io_size ? max_io_size : (1024*1024 < pg_data_size ? pg_data_size : 1024*1024);
+        uint32_t bitmap_granularity = pool_cfg.bitmap_granularity;
+
+        load_module();
+
+        bool bg = cfg["foreground"].is_null();
+        logfile = cfg["logfile"].string_value();
+        pidfile = cfg["pidfile"].string_value();
+
+        open_control();
+        if (recover)
+        {
+            recover_device(req_dev_num);
+        }
+        else
+        {
+            add_device(
+                req_dev_num,
+                (writeback ? UBLK_ATTR_VOLATILE_CACHE : 0) |
+                (readonly ? UBLK_ATTR_READ_ONLY : 0) | (hdd ? UBLK_ATTR_ROTATIONAL : 0),
+                queue_depth, bitmap_granularity, buf_size, pg_data_size, device_size
+            );
+        }
+        int notifyfd[2] = { -1, -1 };
+        if (bg)
+        {
+            if (socketpair(AF_UNIX, SOCK_STREAM, 0, notifyfd) < 0)
+            {
+                perror("socketpair");
+                exit(1);
+            }
+            daemonize_fork(notifyfd);
+            close(notifyfd[0]);
+        }
+        start_device(recover);
+        if (pidfile != "")
+            write_pid();
+        if (bg)
+        {
+            daemonize_reopen_stdio();
+            int ok = 0;
+            (void)write(notifyfd[1], &ok, sizeof(ok));
+            close(notifyfd[1]);
+        }
+        else
+            printf("/dev/ublkb%d\n", ublk_dev.dev_id);
+        stop = false;
+        while (!stop)
+        {
+            ringloop->loop();
+            ringloop->wait();
+        }
+        cli->flush();
+        delete cli;
+        delete epmgr;
+        cli = NULL;
+        epmgr = NULL;
+    }
+
+    void load_module()
+    {
+        if (access("/sys/module/ublk_drv", F_OK) == 0)
+        {
+            return;
+        }
+        int r;
+        if ((r = system("modprobe ublk_drv")) != 0)
+        {
+            if (r < 0)
+                perror("Failed to load ublk_drv kernel module");
+            else
+                fprintf(stderr, "Failed to load ublk_drv kernel module\n");
+            exit(1);
+        }
+    }
+
+    void daemonize_fork(int *notifyfd)
+    {
+        if (fork())
+        {
+            // Parent - check status
+            close(notifyfd[1]);
+            int child_errno = 1;
+            (void)read(notifyfd[0], &child_errno, sizeof(child_errno));
+            if (!child_errno)
+                printf("/dev/ublkb%d\n", ublk_dev.dev_id);
+            exit(child_errno);
+        }
+        setsid();
+        if (fork())
+            exit(0);
+    }
+
+    void daemonize_reopen_stdio()
+    {
+        close(0);
+        close(1);
+        close(2);
+        open("/dev/null", O_RDONLY);
+        open(logfile.c_str(), O_WRONLY|O_APPEND|O_CREAT, 0666);
+        open(logfile.c_str(), O_WRONLY|O_APPEND|O_CREAT, 0666);
+        if (chdir("/") != 0)
+            fprintf(stderr, "Warning: Failed to chdir into /\n");
+    }
+
+    void write_pid()
+    {
+        int fd = open(pidfile.c_str(), O_WRONLY|O_CREAT|O_TRUNC, 0666);
+        if (fd < 0)
+        {
+            fprintf(stderr, "Failed to create pid file %s: %s (code %d)\n", pidfile.c_str(), strerror(errno), errno);
+            return;
+        }
+        auto pid = std::to_string(getpid());
+        if (write(fd, pid.c_str(), pid.size()) < 0)
+        {
+            fprintf(stderr, "Failed to write pid to %s: %s (code %d)\n", pidfile.c_str(), strerror(errno), errno);
+        }
+        close(fd);
+    }
+
+    json11::Json::object list_mapped()
+    {
+        int n_in_dev = 0;
+        DIR *d = opendir("/dev");
+        if (!d)
+        {
+            fprintf(stderr, "Failed to list /dev: %s (code %d)\n", strerror(errno), errno);
+            exit(1);
+        }
+        dirent *ent;
+        while ((ent = readdir(d)) != NULL)
+        {
+            if (!strncmp(ent->d_name, "ublkc", strlen("ublkc")))
+                n_in_dev++;
+        }
+        closedir(d);
+        json11::Json::object mapped;
+        const char *self_filename = exe_name;
+        for (int i = 0; exe_name[i] != 0; i++)
+        {
+            if (exe_name[i] == '/')
+                self_filename = exe_name+i+1;
+        }
+        char path[64] = { 0 };
+        int dev_num = -1, n_in_ctrl = 0;
+        open_control();
+        while (true)
+        {
+            dev_num++;
+            int res = get_dev_info(dev_num, false);
+            if (res == -ENODEV)
+            {
+                if (n_in_ctrl >= n_in_dev)
+                    break;
+                continue;
+            }
+            n_in_ctrl++;
+            sprintf(path, "/proc/%d/cmdline", ublk_dev.ublksrv_pid);
+            std::string cmdline = read_file(path);
+            if (cmdline == "")
+            {
+                // Process is dead
+                mapped["/dev/ublkb"+std::to_string(dev_num)] = json11::Json::object{{"dead", true}};
+                continue;
+            }
+            std::vector<const char*> argv;
+            int last = 0;
+            for (int i = 0; i < cmdline.size(); i++)
+            {
+                if (cmdline[i] == 0)
+                {
+                    argv.push_back(cmdline.c_str()+last);
+                    last = i+1;
+                }
+            }
+            if (argv.size() > 0)
+            {
+                const char *pid_filename = argv[0];
+                for (int i = 0; argv[0][i] != 0; i++)
+                {
+                    if (argv[0][i] == '/')
+                        pid_filename = argv[0]+i+1;
+                }
+                if (!strcmp(pid_filename, self_filename))
+                {
+                    json11::Json::object cfg = ublk_server::parse_args(argv.size(), argv.data());
+                    if (cfg["command"] == "map")
+                    {
+                        cfg.erase("command");
+                        cfg["pid"] = ublk_dev.ublksrv_pid;
+                        mapped["/dev/ublkb"+std::to_string(dev_num)] = cfg;
+                    }
+                }
+            }
+        }
+        return mapped;
+    }
+
+    void print_mapped(json11::Json mapped, bool json)
+    {
+        if (json)
+        {
+            printf("%s\n", mapped.dump().c_str());
+        }
+        else
+        {
+            for (auto & dev: mapped.object_items())
+            {
+                printf("%s\n", dev.first.c_str());
+                for (auto & k: dev.second.object_items())
+                {
+                    printf("%s: %s\n", k.first.c_str(), k.second.as_string().c_str());
+                }
+                printf("\n");
+            }
+        }
+    }
+
+    std::string read_file(char *path)
+    {
+        int fd = open(path, O_RDONLY);
+        if (fd < 0)
+        {
+            if (errno == ENOENT)
+                return "";
+            auto err = "open "+std::string(path);
+            perror(err.c_str());
+            exit(1);
+        }
+        std::string r;
+        while (true)
+        {
+            int l = r.size();
+            r.resize(l + 1024);
+            int rd = read(fd, (void*)(r.c_str() + l), 1024);
+            if (rd <= 0)
+            {
+                r.resize(l);
+                break;
+            }
+            r.resize(l + rd);
+        }
+        close(fd);
+        return r;
+    }
+
+protected:
+    bool stop = false;
+    bool new_opcodes = true;
+    uint64_t ublk_features = 0;
+    int max_wait_time_ms = 5000;
+    int ctrl_fd = -1, cdev_fd = -1;
+    ublksrv_ctrl_dev_info ublk_dev = {};
+    ublksrv_io_desc *ublk_queue = NULL;
+    std::vector<uint8_t*> buffers;
+
+    void open_control()
+    {
+        ctrl_fd = open("/dev/ublk-control", O_RDWR);
+        if (ctrl_fd < 0)
+        {
+            fprintf(stderr, "Failed to open /dev/ublk-control: %s (code %d)\n", strerror(errno), errno);
+            exit(1);
+        }
+        // Check features
+        int res = sync_ublk_cmd(UBLK_U_CMD_GET_FEATURES, &ublk_features, 8, 0);
+        if (res == -EOPNOTSUPP)
+        {
+            new_opcodes = false;
+        }
+        else if (res != 0)
+        {
+            fprintf(stderr, "Failed to get ublk features: %s (code %d)\n", strerror(-res), res);
+            exit(1);
+        }
+    }
+
+    void add_device(int32_t dev_num, uint32_t attrs, uint16_t queue_depth, uint32_t phys_block_size,
+        uint32_t max_io_buf_bytes, uint64_t opt_block_size, uint64_t device_size)
+    {
+        // Add device
+        ublk_dev.dev_id = dev_num;
+        ublk_dev.nr_hw_queues = 1;
+        ublk_dev.queue_depth = queue_depth;
+        ublk_dev.max_io_buf_bytes = max_io_buf_bytes;
+        ublk_dev.flags = UBLK_F_USER_RECOVERY | UBLK_F_USER_RECOVERY_REISSUE;
+        int res = sync_ublk_cmd(new_opcodes ? UBLK_U_CMD_ADD_DEV : UBLK_CMD_ADD_DEV, &ublk_dev, sizeof(ublk_dev));
+        if (res != 0)
+        {
+            fprintf(stderr, "Failed to add ublk device: %s (code %d)\n", strerror(-res), res);
+            exit(1);
+        }
+        // Wait until the device appears
+        std::string ublkc_path = "/dev/ublkc"+std::to_string(ublk_dev.dev_id);
+        int wait_time = 0;
+        while (wait_time < max_wait_time_ms)
+        {
+            cdev_fd = open(ublkc_path.c_str(), O_RDWR);
+            if (cdev_fd >= 0)
+                break;
+            else if (errno != ENOENT)
+            {
+                fprintf(stderr, "Failed to open %s: %s (code %d)", ublkc_path.c_str(), strerror(errno), errno);
+                exit(1);
+            }
+            usleep(100);
+            wait_time += 100;
+        }
+        close(cdev_fd);
+        cdev_fd = -1;
+        // Set device params
+        uint8_t io_opt_shift = 0;
+        while ((opt_block_size >> io_opt_shift) > 1)
+        {
+            io_opt_shift++;
+        }
+        uint8_t phys_shift = 0;
+        while ((phys_block_size >> phys_shift) > 1)
+        {
+            phys_shift++;
+        }
+        ublk_params params = {
+            .len = sizeof(ublk_params),
+            .types = UBLK_PARAM_TYPE_BASIC,
+            .basic = {
+                .attrs = attrs, // UBLK_ATTR_READ_ONLY | UBLK_ATTR_ROTATIONAL | UBLK_ATTR_VOLATILE_CACHE | UBLK_ATTR_FUA
+                .logical_bs_shift = phys_shift,
+                .physical_bs_shift = phys_shift,
+                .io_opt_shift = io_opt_shift,
+                .io_min_shift = phys_shift,
+                .max_sectors = max_io_buf_bytes / 512,
+                .chunk_sectors = 0,
+                .dev_sectors = device_size / 512,
+                .virt_boundary_mask = 0,
+            },
+            .discard = {
+                .discard_alignment = 0,
+                .discard_granularity = 0,
+                .max_discard_sectors = 0,
+                .max_write_zeroes_sectors = 0,
+                .max_discard_segments = 0,
+            },
+        };
+        res = sync_unpriv_cmd(false, new_opcodes ? UBLK_U_CMD_SET_PARAMS : UBLK_CMD_SET_PARAMS, &params, sizeof(params));
+        if (res != 0)
+        {
+            fprintf(stderr, "Failed to set ublk device params: %s (code %d)\n", strerror(-res), res);
+            exit(1);
+        }
+    }
+
+    void map_ublk_queue()
+    {
+        const unsigned page_sz = getpagesize();
+        size_t cmd_buf_size = (ublk_dev.queue_depth * sizeof(ublksrv_io_desc) + page_sz-1) / page_sz * page_sz;
+        //const unsigned queue_offset = (UBLK_MAX_QUEUE_DEPTH * sizeof(ublksrv_io_desc) + page_sz-1) / page_sz * page_sz;
+        //off = q_id * queue_offset;
+        ublk_queue = (ublksrv_io_desc*)mmap(0, cmd_buf_size, PROT_READ, MAP_SHARED | MAP_POPULATE, cdev_fd, 0);
+        if ((void*)ublk_queue == MAP_FAILED)
+        {
+            fprintf(stderr, "Failed to mmap() ublk queue buffer\n");
+            exit(1);
+        }
+    }
+
+    void recover_device(uint32_t dev_num)
+    {
+        ublk_dev.dev_id = dev_num;
+        int res = sync_ublk_cmd(new_opcodes ? UBLK_U_CMD_GET_DEV_INFO : UBLK_CMD_GET_DEV_INFO, &ublk_dev, sizeof(ublk_dev));
+        if (res != 0)
+        {
+            fprintf(stderr, "Failed to get /dev/ublkb%u device info: %s (code %d)\n", dev_num, strerror(-res), res);
+            exit(1);
+        }
+        if (ublk_dev.nr_hw_queues != 1)
+        {
+            fprintf(stderr, "Device /dev/ublkb%u is not supported because it has %d queues\n", dev_num, ublk_dev.nr_hw_queues);
+            exit(1);
+        }
+        if (ublk_dev.ublksrv_pid != 0)
+        {
+            res = kill(ublk_dev.ublksrv_pid, 0);
+            if (res == 0)
+            {
+                fprintf(stderr, "Device /dev/ublkb%u is still alive, daemon PID is %u\n", dev_num, ublk_dev.ublksrv_pid);
+                exit(1);
+            }
+            else if (errno != ESRCH)
+            {
+                fprintf(stderr, "Device /dev/ublkb%u is still alive, failed to check if the daemon with PID %u is running: %s (code %d)\n",
+                    dev_num, ublk_dev.ublksrv_pid, strerror(errno), errno);
+                exit(1);
+            }
+        }
+        // Send the "start recovery" command
+        res = sync_unpriv_cmd(false, new_opcodes ? UBLK_U_CMD_START_USER_RECOVERY : UBLK_CMD_START_USER_RECOVERY, NULL, 0);
+        if (res != 0)
+        {
+            fprintf(stderr, "Failed to start /dev/ublkb%u device recovery: %s (code %d)\n", dev_num, strerror(-res), res);
+            exit(1);
+        }
+    }
+
+    void start_device(bool recover)
+    {
+        std::string ublkc_path = "/dev/ublkc"+std::to_string(ublk_dev.dev_id);
+        cdev_fd = open(ublkc_path.c_str(), O_RDWR|O_NONBLOCK);
+        if (cdev_fd < 0)
+        {
+            fprintf(stderr, "Failed to open %s: %s (code %d)", ublkc_path.c_str(), strerror(errno), errno);
+            exit(1);
+        }
+        // FIXME Here we could optionally do ublk_get_queue_affinity
+        // Map queue command buffer
+        map_ublk_queue();
+        // submit initial fetch requests to ublk driver
+        for (int i = 0; i < ublk_dev.queue_depth; i++)
+        {
+            buffers.push_back((uint8_t*)memalign_or_die(MEM_ALIGNMENT, ublk_dev.max_io_buf_bytes));
+            submit_request(new_opcodes ? UBLK_U_IO_FETCH_REQ : UBLK_IO_FETCH_REQ, i, 0);
+        }
+        ringloop->submit();
+        // start device
+        ublk_dev.ublksrv_pid = getpid();
+        int res = sync_unpriv_cmd(false, (recover
+            ? (new_opcodes ? UBLK_U_CMD_END_USER_RECOVERY : UBLK_CMD_END_USER_RECOVERY)
+            : (new_opcodes ? UBLK_U_CMD_START_DEV : UBLK_CMD_START_DEV)), NULL, 0, ublk_dev.ublksrv_pid);
+        if (res != 0)
+        {
+            fprintf(stderr, "Failed to start ublk device: %s (code %d)\n", strerror(-res), res);
+            exit(1);
+        }
+        close(ctrl_fd);
+        ctrl_fd = -1;
+    }
+
+    void submit_request(uint64_t ublk_cmd, int i, int res)
+    {
+        io_uring_sqe *sqe = ringloop->get_sqe();
+        ring_data_t* data = ((ring_data_t*)sqe->user_data);
+        sqe->fd = cdev_fd;
+        sqe->opcode = IORING_OP_URING_CMD;
+        //sqe->flags = IOSQE_FIXED_FILE;
+        sqe->flags = 0;
+        sqe->rw_flags = 0;
+        sqe->off = ublk_cmd;
+        ublksrv_io_cmd *cmd = (ublksrv_io_cmd *)&sqe->addr3; // sqe128 command buffer address
+        cmd->q_id = 0;
+        cmd->tag = i;
+        cmd->addr = (uint64_t)buffers[i];
+        cmd->result = res;
+        data->callback = [this, i](ring_data_t *data) { exec_request(data->res, i); };
+    }
+
+    void exec_request(int res, int i)
+    {
+        if (res != 0)
+        {
+            // Note: res may be also UBLK_IO_RES_NEED_GET_DATA if UBLK_F_NEED_GET_DATA is enabled,
+            // in this case you should submit_request(UBLK_IO_NEED_GET_DATA, i) again with buffer
+            if (res == -ENODEV)
+            {
+                // ublk device is removed
+                stop = true;
+                return;
+            }
+            fprintf(stderr, "Fetching ublk request failed: %s (code %d)\n", strerror(-res), res);
+            exit(1);
+        }
+        ublksrv_io_desc *iod = &ublk_queue[i];
+        uint8_t opcode = ublksrv_get_op(iod);
+        if (opcode == UBLK_IO_OP_FLUSH)
+        {
+            cluster_op_t *op = new cluster_op_t;
+            op->opcode = OSD_OP_SYNC;
+            op->callback = [this, i](cluster_op_t *op)
+            {
+                submit_request(new_opcodes ? UBLK_U_IO_COMMIT_AND_FETCH_REQ : UBLK_IO_COMMIT_AND_FETCH_REQ, i, op->retval);
+                delete op;
+            };
+            cli->execute(op);
+        }
+        else if (opcode == UBLK_IO_OP_WRITE_ZEROES || opcode == UBLK_IO_OP_DISCARD)
+        {
+            submit_request(new_opcodes ? UBLK_U_IO_COMMIT_AND_FETCH_REQ : UBLK_IO_COMMIT_AND_FETCH_REQ, i, -EINVAL);
+        }
+        else if (opcode == UBLK_IO_OP_READ || opcode == UBLK_IO_OP_WRITE)
+        {
+            cluster_op_t *op = new cluster_op_t;
+            op->opcode = opcode == UBLK_IO_OP_READ ? OSD_OP_READ : OSD_OP_WRITE;
+            op->inode = inode ? inode : watch->cfg.num;
+            op->offset = iod->start_sector * 512;
+            op->len = iod->nr_sectors * 512;
+            op->iov.push_back(buffers[i], op->len);
+            op->callback = [this, i](cluster_op_t *op)
+            {
+                submit_request(new_opcodes ? UBLK_U_IO_COMMIT_AND_FETCH_REQ : UBLK_IO_COMMIT_AND_FETCH_REQ, i, op->retval);
+                delete op;
+            };
+            cli->execute(op);
+        }
+        else
+        {
+            submit_request(new_opcodes ? UBLK_U_IO_COMMIT_AND_FETCH_REQ : UBLK_IO_COMMIT_AND_FETCH_REQ, i, -EINVAL);
+        }
+    }
+
+    int get_dev_info(int dev_num, bool unpriv)
+    {
+        // Get device info
+        ublk_dev.dev_id = dev_num;
+        int res = unpriv
+            ? sync_unpriv_cmd(true, new_opcodes ? UBLK_U_CMD_GET_DEV_INFO2 : UBLK_CMD_GET_DEV_INFO2, &ublk_dev, sizeof(ublk_dev))
+            : sync_ublk_cmd(new_opcodes ? UBLK_U_CMD_GET_DEV_INFO : UBLK_CMD_GET_DEV_INFO, &ublk_dev, sizeof(ublk_dev));
+        if (res != 0 && res != -ENODEV)
+        {
+            fprintf(stderr, "Failed to get device info from /dev/ublkc%d: %s (code %d)\n", dev_num, strerror(-res), res);
+            exit(1);
+        }
+        return res;
+    }
+
+    void unmap_device(int dev_num, bool unpriv, bool wait)
+    {
+        int res = 0;
+        // Stop the device
+        ublk_dev.dev_id = dev_num;
+        res = sync_unpriv_cmd(unpriv, new_opcodes ? UBLK_U_CMD_STOP_DEV : UBLK_CMD_STOP_DEV, NULL, 0);
+        if (res != 0)
+        {
+            fprintf(stderr, "Failed to stop device /dev/ublkc%d: %s (code %d)\n", dev_num, strerror(-res), res);
+            exit(1);
+        }
+        // Delete the device
+        res = sync_unpriv_cmd(unpriv, new_opcodes ? (wait ? UBLK_U_CMD_DEL_DEV : UBLK_U_CMD_DEL_DEV_ASYNC) : UBLK_CMD_DEL_DEV, NULL, 0);
+        if (res != 0)
+        {
+            fprintf(stderr, "Failed to delete device /dev/ublkc%d: %s (code %d)\n", dev_num, strerror(-res), res);
+            exit(1);
+        }
+    }
+
+    int sync_unpriv_cmd(bool unpriv, uint32_t cmd_op, void *addr, uint32_t len, uint64_t data0 = 0)
+    {
+        int res;
+        if (unpriv)
+        {
+            static const int path_max = 64;
+            char buf[path_max + len];
+            memset(buf, 0, path_max);
+            memcpy(buf + path_max, addr, len);
+            snprintf(buf, path_max, "/dev/ublkc%d", ublk_dev.dev_id);
+            res = sync_ublk_cmd(cmd_op, buf, sizeof(buf), path_max, data0);
+            if (!res)
+                memcpy(addr, buf + path_max, len);
+        }
+        else
+        {
+            res = sync_ublk_cmd(cmd_op, addr, len, 0, data0);
+        }
+        return res;
+    }
+
+    int sync_ublk_cmd(uint32_t cmd_op, void *addr, uint32_t len, uint16_t dev_path_len = 0, uint64_t data0 = 0)
+    {
+        io_uring_sqe *sqe = ringloop->get_sqe();
+        sqe->fd = ctrl_fd;
+        sqe->opcode = IORING_OP_URING_CMD;
+        sqe->ioprio = 0;
+        sqe->off = cmd_op;
+        ublksrv_ctrl_cmd *cmd = (ublksrv_ctrl_cmd *)&sqe->addr3; // sqe128 command buffer address
+        cmd->dev_id = ublk_dev.dev_id;
+        cmd->queue_id = -1;
+        cmd->addr = (uint64_t)addr;
+        cmd->len = len;
+        cmd->data[0] = data0;
+        cmd->dev_path_len = dev_path_len;
+        ring_data_t* data = ((ring_data_t*)sqe->user_data);
+        bool done = false;
+        int res = 0;
+        data->callback = [&](ring_data_t *data)
+        {
+            res = data->res;
+            done = true;
+        };
+        ringloop->submit();
+        while (!done)
+        {
+            ringloop->loop();
+            if (!done)
+                ringloop->wait();
+        }
+        return res;
+    }
+};
+
+int main(int narg, const char *args[])
+{
+    setvbuf(stdout, NULL, _IONBF, 0);
+    setvbuf(stderr, NULL, _IONBF, 0);
+    exe_name = args[0];
+    ublk_server *p = new ublk_server();
+    p->exec(ublk_server::parse_args(narg, args));
+    delete p;
+    return 0;
+}

src/client/vitastor.pc.in

@@ -6,7 +6,7 @@ includedir=${prefix}/@CMAKE_INSTALL_INCLUDEDIR@
 
 Name: Vitastor
 Description: Vitastor client library
-Version: 2.2.3
+Version: 2.4.1
 Libs: -L${libdir} -lvitastor_client
 Cflags: -I${includedir}