Add relatime and lazytime for ext4 mounting

csi/Dockerfile

@@ -35,9 +35,9 @@ RUN (echo deb http://vitastor.io/debian bookworm main > /etc/apt/sources.list.d/
     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 download qemu-system-common && \
+    wget https://vitastor.io/archive/qemu/qemu-bookworm-8.1.2%2Bds-1%2Bvitastor1/qemu-utils_8.1.2%2Bds-1%2Bvitastor1_amd64.deb && \
-    apt-get download qemu-block-extra && \
+    wget https://vitastor.io/archive/qemu/qemu-bookworm-8.1.2%2Bds-1%2Bvitastor1/qemu-block-extra_8.1.2%2Bds-1%2Bvitastor1_amd64.deb && \
-    dpkg -x qemu-system-common*.deb tmp1 && \
+    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 && \

csi/src/controllerserver.go

@@ -97,6 +97,15 @@ func GetConnectionParams(params map[string]string) (map[string]string, error)
         }
     case []string:
         etcdUrl = config["etcd_address"].([]string)
+    case []interface{}:
+        for _, url := range config["etcd_address"].([]interface{})
+        {
+            s, ok := url.(string)
+            if (ok)
+            {
+                etcdUrl = append(etcdUrl, s)
+            }
+        }
     }
     if (len(etcdUrl) == 0)
     {
@@ -105,8 +114,9 @@ func GetConnectionParams(params map[string]string) (map[string]string, error)
     return ctxVars, nil
 }
 
-func system(program string, args ...string) ([]byte, error)
+func system(program string, args ...string) ([]byte, []byte, error)
 {
+    klog.Infof("Running "+program+" "+strings.Join(args, " "))
     c := exec.Command(program, args...)
     var stdout, stderr bytes.Buffer
     c.Stdout, c.Stderr = &stdout, &stderr
@@ -115,9 +125,9 @@ func system(program string, args ...string) ([]byte, error)
     {
         stdoutStr, stderrStr := string(stdout.Bytes()), string(stderr.Bytes())
         klog.Errorf(program+" "+strings.Join(args, " ")+" failed: %s, status %s\n", stdoutStr+stderrStr, err)
-        return nil, status.Error(codes.Internal, stdoutStr+stderrStr+" (status "+err.Error()+")")
+        return nil, nil, status.Error(codes.Internal, stdoutStr+stderrStr+" (status "+err.Error()+")")
     }
-    return stdout.Bytes(), nil
+    return stdout.Bytes(), stderr.Bytes(), nil
 }
 
 func invokeCLI(ctxVars map[string]string, args []string) ([]byte, error)
@@ -126,7 +136,8 @@ func invokeCLI(ctxVars map[string]string, args []string) ([]byte, error)
     {
         args = append(args, "--config_path", ctxVars["configPath"])
     }
-    return system("/usr/bin/vitastor-cli", args...)
+    stdout, _, err := system("/usr/bin/vitastor-cli", args...)
+    return stdout, err
 }
 
 // Create the volume

csi/src/nodeserver.go

@@ -7,6 +7,7 @@ import (
     "context"
     "errors"
     "encoding/json"
+    "fmt"
     "os"
     "os/exec"
     "path/filepath"
@@ -154,8 +155,13 @@ func (ns *NodeServer) mapNbd(volName string, ctxVars map[string]string, readonly
     {
         args = append(args, "--readonly", "1")
     }
-    dev, err := system("/usr/bin/vitastor-nbd", args...)
+    stdout, stderr, err := system("/usr/bin/vitastor-nbd", args...)
-    return strings.TrimSpace(string(dev)), err
+    dev := strings.TrimSpace(string(stdout))
+    if (dev == "")
+    {
+        return "", fmt.Errorf("vitastor-nbd did not return the name of NBD device. output: %s", stderr)
+    }
+    return dev, err
 }
 
 func (ns *NodeServer) unmapNbd(devicePath string)
@@ -170,6 +176,7 @@ func (ns *NodeServer) unmapNbd(devicePath string)
 
 func findByPidFile(pidFile string) (*os.Process, error)
 {
+    klog.Infof("killing process with PID from file %s", pidFile)
     pidBuf, err := os.ReadFile(pidFile)
     if (err != nil)
     {
@@ -221,7 +228,7 @@ func startStorageDaemon(vdpaId, volName, pidFile, configPath string, readonly bo
     {
         writable = "false"
     }
-    _, err := system(
+    _, _, err := system(
         "/usr/bin/qemu-storage-daemon", "--daemonize", "--pidfile", pidFile, "--blockdev", string(blockSpecJson),
         "--export", "vduse-blk,id="+vdpaId+",node-name=disk1,name="+vdpaId+",num-queues=16,queue-size=128,writable="+writable,
     )
@@ -234,7 +241,7 @@ func (ns *NodeServer) mapVduse(volName string, ctxVars map[string]string, readon
     stateFd, err := os.CreateTemp(ns.stateDir, "vitastor-vduse-*.json")
     if (err != nil)
     {
-        return "", "", status.Error(codes.Internal, err.Error())
+        return "", "", err
     }
     stateFile := stateFd.Name()
     stateFd.Close()
@@ -246,11 +253,12 @@ func (ns *NodeServer) mapVduse(volName string, ctxVars map[string]string, readon
     if (err == nil)
     {
         // Add device to VDPA bus
-        _, err = system("/sbin/vdpa", "-j", "dev", "add", "name", vdpaId, "mgmtdev", "vduse")
+        _, _, err = system("/sbin/vdpa", "-j", "dev", "add", "name", vdpaId, "mgmtdev", "vduse")
         if (err == nil)
         {
             // Find block device name
-            matches, err := filepath.Glob("/sys/bus/vdpa/devices/"+vdpaId+"/virtio*/block/*")
+            var matches []string
+            matches, err = filepath.Glob("/sys/bus/vdpa/devices/"+vdpaId+"/virtio*/block/*")
             if (err == nil && len(matches) == 0)
             {
                 err = errors.New("/sys/bus/vdpa/devices/"+vdpaId+"/virtio*/block/* is not found")
@@ -277,21 +285,14 @@ func (ns *NodeServer) mapVduse(volName string, ctxVars map[string]string, readon
                     }
                 }
             }
-            if (err != nil)
-            {
-                err = status.Error(codes.Internal, err.Error())
-            }
         }
-        if (err != nil)
+        killErr := killByPidFile(pidFile)
+        if (killErr != nil)
         {
-            killErr := killByPidFile(pidFile)
+            klog.Errorf("Failed to kill started qemu-storage-daemon: %v", killErr)
-            if (killErr != nil)
-            {
-                klog.Errorf("Failed to kill started qemu-storage-daemon: %v", killErr)
-            }
-            os.Remove(stateFile)
-            os.Remove(pidFile)
         }
+        os.Remove(stateFile)
+        os.Remove(pidFile)
     }
     return "", "", err
 }
@@ -337,7 +338,7 @@ func (ns *NodeServer) unmapVduseById(vdpaId string)
     }
     else
     {
-        _, _ = system("/sbin/vdpa", "-j", "dev", "del", vdpaId)
+        _, _, _ = system("/sbin/vdpa", "-j", "dev", "del", vdpaId)
     }
     stateFile := ns.stateDir + vdpaId + ".json"
     os.Remove(stateFile)
@@ -377,7 +378,7 @@ func (ns *NodeServer) restoreVduseDaemons()
     }
     devList := make(map[string]interface{})
     // example output: {"dev":{"test1":{"type":"block","mgmtdev":"vduse","vendor_id":0,"max_vqs":16,"max_vq_size":128}}}
-    devListJSON, err := system("/sbin/vdpa", "-j", "dev", "list")
+    devListJSON, _, err := system("/sbin/vdpa", "-j", "dev", "list")
     if (err != nil)
     {
         return
@@ -456,13 +457,13 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
                 if (err != nil)
                 {
                     klog.Errorf("failed to create block device mount target %s with error: %v", targetPath, err)
-                    return nil, status.Error(codes.Internal, err.Error())
+                    return nil, err
                 }
                 err = pathFile.Close()
                 if (err != nil)
                 {
                     klog.Errorf("failed to close %s with error: %v", targetPath, err)
-                    return nil, status.Error(codes.Internal, err.Error())
+                    return nil, err
                 }
             }
             else
@@ -471,13 +472,13 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
                 if (err != nil)
                 {
                     klog.Errorf("failed to create fs mount target %s with error: %v", targetPath, err)
-                    return nil, status.Error(codes.Internal, err.Error())
+                    return nil, err
                 }
             }
         }
         else
         {
-            return nil, status.Error(codes.Internal, err.Error())
+            return nil, err
         }
     }
 
@@ -538,6 +539,10 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
         {
             opt = append(opt, "nouuid")
         }
+        if (fsType == "ext4")
+        {
+            opt = append(opt, "relatime","lazytime")
+        }
         readOnly := Contains(opt, "ro")
         if (existingFormat == "" && !readOnly)
         {
@@ -597,7 +602,7 @@ unmap:
     {
         ns.unmapVduseById(vdpaId)
     }
-    return nil, status.Error(codes.Internal, err.Error())
+    return nil, err
 }
 
 // NodeUnpublishVolume unmounts the volume from the target path
@@ -612,7 +617,7 @@ func (ns *NodeServer) NodeUnpublishVolume(ctx context.Context, req *csi.NodeUnpu
         {
             return nil, status.Error(codes.NotFound, "Target path not found")
         }
-        return nil, status.Error(codes.Internal, err.Error())
+        return nil, err
     }
     if (devicePath == "")
     {
@@ -625,7 +630,7 @@ func (ns *NodeServer) NodeUnpublishVolume(ctx context.Context, req *csi.NodeUnpu
     err = mount.CleanupMountPoint(targetPath, ns.mounter, false)
     if (err != nil)
     {
-        return nil, status.Error(codes.Internal, err.Error())
+        return nil, err
     }
     // unmap NBD device
     if (refCount == 1)

debian/patched-qemu.Dockerfile

@@ -7,7 +7,7 @@ ARG REL=
 
 WORKDIR /root
 
-RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" ]; then \
+RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" -o "$REL" = "bookworm" ]; then \
         echo "deb http://deb.debian.org/debian $REL-backports main" >> /etc/apt/sources.list; \
         echo >> /etc/apt/preferences; \
         echo 'Package: *' >> /etc/apt/preferences; \
@@ -45,7 +45,7 @@ RUN set -e; \
     rm -rf /root/packages/qemu-$REL/*; \
     cd /root/packages/qemu-$REL; \
     dpkg-source -x /root/qemu*.dsc; \
-    QEMU_VER=$(ls -d qemu*/ | perl -pe 's!^.*(\d+\.\d+).*!$1!'); \
+    QEMU_VER=$(ls -d qemu*/ | perl -pe 's!^.*?(\d+\.\d+).*!$1!'); \
     D=$(ls -d qemu*/); \
     cp /root/vitastor/patches/qemu-$QEMU_VER-vitastor.patch ./qemu-*/debian/patches; \
     echo qemu-$QEMU_VER-vitastor.patch >> $D/debian/patches/series; \

docs/installation/packages.en.md

@@ -18,7 +18,7 @@
     stable version from 0.9.x branch instead of 1.x
 - For Debian 10 (Buster) also enable backports repository:
   `deb http://deb.debian.org/debian buster-backports main`
-- Install packages: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu`
+- Install packages: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu-system-x86`
 
 ## CentOS
 

docs/installation/packages.ru.md

@@ -18,7 +18,7 @@
     установить последнюю стабильную версию из ветки 0.9.x вместо 1.x
 - Для Debian 10 (Buster) также включите репозиторий backports:
   `deb http://deb.debian.org/debian buster-backports main`
-- Установите пакеты: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu`
+- Установите пакеты: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu-system-x86`
 
 ## CentOS
 

docs/usage/disk.en.md

@@ -17,6 +17,7 @@ It supports the following commands:
 - [purge](#purge)
 - [read-sb](#read-sb)
 - [write-sb](#write-sb)
+- [update-sb](#update-sb)
 - [udev](#udev)
 - [exec-osd](#exec-osd)
 - [pre-exec](#pre-exec)
@@ -182,6 +183,14 @@ Try to read Vitastor OSD superblock from `<device>` and print it in JSON format.
 
 Read JSON from STDIN and write it into Vitastor OSD superblock on `<device>`.
 
+## update-sb
+
+`vitastor-disk update-sb <device> [--force] [--<parameter> <value>] [...]`
+
+Read Vitastor OSD superblock from <device>, update parameters in it and write it back.
+
+`--force` allows to ignore validation errors.
+
 ## udev
 
 `vitastor-disk udev <device>`

docs/usage/disk.ru.md

@@ -17,6 +17,7 @@ vitastor-disk - инструмент командной строки для уп
 - [purge](#purge)
 - [read-sb](#read-sb)
 - [write-sb](#write-sb)
+- [update-sb](#update-sb)
 - [udev](#udev)
 - [exec-osd](#exec-osd)
 - [pre-exec](#pre-exec)
@@ -187,6 +188,15 @@ throttle_target_mbs, throttle_target_parallelism, throttle_threshold_us.
 
 Прочитать JSON со стандартного ввода и записать его в суперблок OSD на диск `<device>`.
 
+## update-sb
+
+`vitastor-disk update-sb <device> [--force] [--<параметр> <значение>] [...]`
+
+Прочитать суперблок OSD с диска `<device>`, изменить в нём заданные параметры и записать обратно.
+
+Опция `--force` позволяет читать суперблок, даже если он считается некорректным
+из-за ошибок валидации.
+
 ## udev
 
 `vitastor-disk udev <device>`

docs/usage/qemu.en.md

@@ -146,7 +146,7 @@ Example performance comparison:
 | 4k random read Q1    | 9600 iops   | 7640 iops   | 7780 iops   |
 
 To try VDUSE you need at least Linux 5.15, built with VDUSE support
-(CONFIG_VIRTIO_VDPA=m, CONFIG_VDPA_USER=m, CONFIG_VIRTIO_VDPA=m).
+(CONFIG_VDPA=m, CONFIG_VDPA_USER=m, CONFIG_VIRTIO_VDPA=m).
 
 Debian Linux kernels have these options disabled by now, so if you want to try it on Debian,
 use a kernel from Ubuntu [kernel-ppa/mainline](https://kernel.ubuntu.com/~kernel-ppa/mainline/), Proxmox,

docs/usage/qemu.ru.md

@@ -149,7 +149,7 @@ VDUSE - на данный момент лучший интерфейс для п
 | 4k случайное чтение Q1   | 9600 iops   | 7640 iops   | 7780 iops   |
 
 Чтобы попробовать VDUSE, вам нужно ядро Linux как минимум версии 5.15, собранное с поддержкой
-VDUSE (CONFIG_VIRTIO_VDPA=m, CONFIG_VDPA_USER=m, CONFIG_VIRTIO_VDPA=m).
+VDUSE (CONFIG_VDPA=m, CONFIG_VDPA_USER=m, CONFIG_VIRTIO_VDPA=m).
 
 В ядрах в Debian Linux поддержка пока отключена по умолчанию, так что чтобы попробовать VDUSE
 на Debian, поставьте ядро из Ubuntu [kernel-ppa/mainline](https://kernel.ubuntu.com/~kernel-ppa/mainline/),

src/blockstore_init.cpp

@@ -732,8 +732,9 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
     resume:
         while (pos < bs->journal.block_size)
         {
-            journal_entry *je = (journal_entry*)((uint8_t*)buf + proc_pos - done_pos + pos);
+            auto buf_pos = proc_pos - done_pos + pos;
-            if (je->magic != JOURNAL_MAGIC || je_crc32(je) != je->crc32 ||
+            journal_entry *je = (journal_entry*)((uint8_t*)buf + buf_pos);
+            if (je->magic != JOURNAL_MAGIC || buf_pos+je->size > len || je_crc32(je) != je->crc32 ||
                 je->type < JE_MIN || je->type > JE_MAX || started && je->crc32_prev != crc32_last)
             {
                 if (pos == 0)

src/disk_tool.cpp

@@ -127,6 +127,10 @@ static const char *help_text =
     "vitastor-disk write-sb <device>\n"
     "  Read JSON from STDIN and write it into Vitastor OSD superblock on <device>.\n"
     "\n"
+    "vitastor-disk update-sb <device> [--force] [--<parameter> <value>] [...]\n"
+    "  Read Vitastor OSD superblock from <device>, update parameters in it and write it back.\n"
+    "  --force allows to ignore validation errors.\n"
+    "\n"
     "vitastor-disk udev <device>\n"
     "  Try to read Vitastor OSD superblock from <device> and print variables for udev.\n"
     "\n"
@@ -363,6 +367,15 @@ int main(int argc, char *argv[])
         }
         return self.write_sb(cmd[1]);
     }
+    else if (!strcmp(cmd[0], "update-sb"))
+    {
+        if (cmd.size() != 2)
+        {
+            fprintf(stderr, "Exactly 1 device path argument is required\n");
+            return 1;
+        }
+        return self.update_sb(cmd[1]);
+    }
     else if (!strcmp(cmd[0], "start") || !strcmp(cmd[0], "stop") ||
         !strcmp(cmd[0], "restart") || !strcmp(cmd[0], "enable") || !strcmp(cmd[0], "disable"))
     {

src/disk_tool.h

@@ -109,6 +109,7 @@ struct disk_tool_t
     int udev_import(std::string device);
     int read_sb(std::string device);
     int write_sb(std::string device);
+    int update_sb(std::string device);
     int exec_osd(std::string device);
     int systemd_start_stop_osds(const std::vector<std::string> & cmd, const std::vector<std::string> & devices);
     int pre_exec_osd(std::string device);

src/disk_tool_udev.cpp

@@ -86,6 +86,24 @@ int disk_tool_t::write_sb(std::string device)
     return !write_osd_superblock(device, params);
 }
 
+int disk_tool_t::update_sb(std::string device)
+{
+    json11::Json sb = read_osd_superblock(device, true, options.find("force") != options.end());
+    if (sb.is_null())
+    {
+        return 1;
+    }
+    auto sb_obj = sb["params"].object_items();
+    for (auto & kv: options)
+    {
+        if (kv.first != "force")
+        {
+            sb_obj[kv.first] = kv.second;
+        }
+    }
+    return !write_osd_superblock(device, sb_obj);
+}
+
 uint32_t disk_tool_t::write_osd_superblock(std::string device, json11::Json params)
 {
     std::string json_data = params.dump();

src/etcd_state_client.cpp

@@ -135,8 +135,8 @@ void etcd_state_client_t::etcd_call(std::string api, json11::Json payload, int t
             {
                 if (this->log_level > 0)
                 {
-                    printf(
+                    fprintf(
-                        "Warning: etcd request failed: %s, retrying %d more times\n",
+                        stderr, "Warning: etcd request failed: %s, retrying %d more times\n",
                         err.c_str(), retries
                     );
                 }
@@ -333,7 +333,7 @@ void etcd_state_client_t::start_etcd_watcher()
         etcd_watch_ws = NULL;
     }
     if (this->log_level > 1)
-        printf("Trying to connect to etcd websocket at %s\n", etcd_address.c_str());
+        fprintf(stderr, "Trying to connect to etcd websocket at %s\n", etcd_address.c_str());
     etcd_watch_ws = open_websocket(tfd, etcd_address, etcd_api_path+"/watch", etcd_slow_timeout,
         [this, cur_addr = selected_etcd_address](const http_response_t *msg)
     {