Add update() API to kv_db

Fix eviction when random_pos selects the end
Implement min/max list_count to make listings during performance test reasonable
2024-01-06 17:14:42 +03:00 · 2024-01-02 13:24:15 +03:00 · 2024-01-02 13:24:15 +03:00 · 2024-01-02 13:24:15 +03:00 · 2024-01-02 13:24:15 +03:00 · 2024-01-02 13:24:15 +03:00
73 changed files with 3366 additions and 1159 deletions
--- a/.gitea/workflows/test.yml
+++ b/.gitea/workflows/test.yml
@@ -395,7 +395,7 @@ jobs:
    steps:
    - name: Run test
      id: test
-      timeout-minutes: 6
+      timeout-minutes: 3
      run: SCHEME=ec /root/vitastor/tests/test_snapshot_chain.sh
    - name: Print logs
      if: always() && steps.test.outcome == 'failure'
@@ -532,24 +532,6 @@ jobs:
          echo ""
        done

-  test_switch_primary:
-    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_switch_primary.sh
-    - name: Print logs
-      if: always() && steps.test.outcome == 'failure'
-      run: |
-        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
-          echo "-------- $i --------"
-          cat $i
-          echo ""
-        done
-
  test_write:
    runs-on: ubuntu-latest
    needs: build
--- a/.gitea/workflows/tests-to-yaml.pl
+++ b/.gitea/workflows/tests-to-yaml.pl
@@ -39,10 +39,6 @@ for my $line (<>)
                $test_name .= '_'.lc($1).'_'.$2;
            }
        }
-        if ($test_name eq 'test_snapshot_chain_ec')
-        {
-            $timeout = 6;
-        }
        $line =~ s!\./test_!/root/vitastor/tests/test_!;
        # Gitea CI doesn't support artifacts yet, lol
        #- name: Upload results
--- a/CLA-en.md
+++ b/CLA-en.md
@@ -38,7 +38,7 @@ in the offer.
        on behalf of third parties, including on behalf of his employer.

 2. Subject of the Agreement. \
-   2.1. Subject of the Agreement shall be the Contributions sent to the Author by Contributors. \
+   2.1. Subject of the Agreement shall be the Contributions sent to the Author by Contributors.
   2.2. The Contributor grants to the Author the right to use Contributions at his own
        discretion and without any necessity to get a prior approval from Contributor or
        any other third party in any way, under a simple (non-exclusive), royalty-free,
@@ -86,7 +86,7 @@ in the offer.
        of their provision to the Author. \
   5.2. The Contributor represents and warrants that he legally owns exclusive
        intellectual property rights to the Contributions. \
-   5.3. The Contributor represents and warrants that any further use of
+   5.3. The Contributor represents and warrants that any further use of \
        Contributions by the Author as provided by Contributor under the terms
        of the Agreement does not infringe on intellectual and other rights and
        legitimate interests of third parties. \
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8.12)

 project(vitastor)

-set(VERSION "1.4.4")
+set(VERSION "1.3.1")

 add_subdirectory(src)
--- a/2
+++ b/2
--- a/csi/Makefile
+++ b/csi/Makefile
@@ -1,4 +1,4 @@
-VERSION ?= v1.4.4
+VERSION ?= v1.3.1

 all: build push

--- a/csi/deploy/004-csi-nodeplugin.yaml
+++ b/csi/deploy/004-csi-nodeplugin.yaml
@@ -49,7 +49,7 @@ spec:
            capabilities:
              add: ["SYS_ADMIN"]
            allowPrivilegeEscalation: true
-          image: vitalif/vitastor-csi:v1.4.4
+          image: vitalif/vitastor-csi:v1.3.1
          args:
            - "--node=$(NODE_ID)"
            - "--endpoint=$(CSI_ENDPOINT)"
--- a/csi/deploy/007-csi-provisioner.yaml
+++ b/csi/deploy/007-csi-provisioner.yaml
@@ -121,7 +121,7 @@ spec:
            privileged: true
            capabilities:
              add: ["SYS_ADMIN"]
-          image: vitalif/vitastor-csi:v1.4.4
+          image: vitalif/vitastor-csi:v1.3.1
          args:
            - "--node=$(NODE_ID)"
            - "--endpoint=$(CSI_ENDPOINT)"
--- a/csi/src/config.go
+++ b/csi/src/config.go
@@ -5,7 +5,7 @@ package vitastor

 const (
    vitastorCSIDriverName    = "csi.vitastor.io"
-    vitastorCSIDriverVersion = "1.4.4"
+    vitastorCSIDriverVersion = "1.3.1"
 )

 // Config struct fills the parameters of request or user input
--- a/csi/src/nodeserver.go
+++ b/csi/src/nodeserver.go
@@ -188,6 +188,7 @@ 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)
    {
@@ -208,7 +209,6 @@ func findByPidFile(pidFile string) (*os.Process, error)

 func killByPidFile(pidFile string) error
 {
-    klog.Infof("killing process with PID from file %s", pidFile)
    proc, err := findByPidFile(pidFile)
    if (err != nil)
    {
--- a/debian/changelog
+++ b/debian/changelog
@@ -1,4 +1,4 @@
-vitastor (1.4.4-1) unstable; urgency=medium
+vitastor (1.3.1-1) unstable; urgency=medium

  * Bugfixes

--- a/debian/vitastor.Dockerfile
+++ b/debian/vitastor.Dockerfile
@@ -35,8 +35,8 @@ RUN set -e -x; \
    mkdir -p /root/packages/vitastor-$REL; \
    rm -rf /root/packages/vitastor-$REL/*; \
    cd /root/packages/vitastor-$REL; \
-    cp -r /root/vitastor vitastor-1.4.4; \
-    cd vitastor-1.4.4; \
+    cp -r /root/vitastor vitastor-1.3.1; \
+    cd vitastor-1.3.1; \
    ln -s /root/fio-build/fio-*/ ./fio; \
    FIO=$(head -n1 fio/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
    ls /usr/include/linux/raw.h || cp ./debian/raw.h /usr/include/linux/raw.h; \
@@ -49,8 +49,8 @@ RUN set -e -x; \
    rm -rf a b; \
    echo "dep:fio=$FIO" > debian/fio_version; \
    cd /root/packages/vitastor-$REL; \
-    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_1.4.4.orig.tar.xz vitastor-1.4.4; \
-    cd vitastor-1.4.4; \
+    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_1.3.1.orig.tar.xz vitastor-1.3.1; \
+    cd vitastor-1.3.1; \
    V=$(head -n1 debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
    DEBFULLNAME="Vitaliy Filippov <vitalif@yourcmc.ru>" dch -D $REL -v "$V""$REL" "Rebuild for $REL"; \
    DEB_BUILD_OPTIONS=nocheck dpkg-buildpackage --jobs=auto -sa; \
--- a/docs/config/monitor.en.md
+++ b/docs/config/monitor.en.md
@@ -19,8 +19,8 @@ These parameters only apply to Monitors.
 ## etcd_mon_ttl

 - Type: seconds
- Default: 1
- Minimum: 5
+- Default: 30
+- Minimum: 10

 Monitor etcd lease refresh interval in seconds

--- a/docs/config/monitor.ru.md
+++ b/docs/config/monitor.ru.md
@@ -19,8 +19,8 @@
 ## etcd_mon_ttl

 - Тип: секунды
- Значение по умолчанию: 1
- Минимальное значение: 5
+- Значение по умолчанию: 30
+- Минимальное значение: 10

 Интервал обновления etcd резервации (lease) монитором

--- a/docs/config/network.en.md
+++ b/docs/config/network.en.md
@@ -215,8 +215,8 @@ is scheduled.
 ## up_wait_retry_interval

 - Type: milliseconds
- Default: 50
- Minimum: 10
+- Default: 500
+- Minimum: 50
 - Can be changed online: yes

 OSDs respond to clients with a special error code when they receive I/O
--- a/docs/config/network.ru.md
+++ b/docs/config/network.ru.md
@@ -224,8 +224,8 @@ OSD в любом случае согласовывают реальное зн
 ## up_wait_retry_interval

 - Тип: миллисекунды
- Значение по умолчанию: 50
- Минимальное значение: 10
+- Значение по умолчанию: 500
+- Минимальное значение: 50
 - Можно менять на лету: да

 Когда OSD получают от клиентов запросы ввода-вывода, относящиеся к не
--- a/docs/config/osd.en.md
+++ b/docs/config/osd.en.md
@@ -59,7 +59,6 @@ them, even without restarting by updating configuration in etcd.
 - [recovery_tune_client_util_high](#recovery_tune_client_util_high)
 - [recovery_tune_agg_interval](#recovery_tune_agg_interval)
 - [recovery_tune_sleep_min_us](#recovery_tune_sleep_min_us)
- [recovery_tune_sleep_cutoff_us](#recovery_tune_sleep_cutoff_us)

 ## etcd_report_interval

@@ -605,14 +604,5 @@ is usually fine.
 - Default: 10
 - Can be changed online: yes

-Minimum possible value for auto-tuned recovery_sleep_us. Lower values
-are changed to 0.
-
-## recovery_tune_sleep_cutoff_us
-
- Type: microseconds
- Default: 10000000
- Can be changed online: yes
-
-Maximum possible value for auto-tuned recovery_sleep_us. Higher values
-are treated as outliers and ignored in aggregation.
+Minimum possible value for auto-tuned recovery_sleep_us. Values lower
+than this value are changed to 0.
--- a/docs/config/osd.ru.md
+++ b/docs/config/osd.ru.md
@@ -60,7 +60,6 @@
 - [recovery_tune_client_util_high](#recovery_tune_client_util_high)
 - [recovery_tune_agg_interval](#recovery_tune_agg_interval)
 - [recovery_tune_sleep_min_us](#recovery_tune_sleep_min_us)
- [recovery_tune_sleep_cutoff_us](#recovery_tune_sleep_cutoff_us)

 ## etcd_report_interval

@@ -635,14 +634,4 @@ EC (кодов коррекции ошибок) с более, чем 1 диск
 - Можно менять на лету: да

 Минимальное возможное значение авто-подстроенного recovery_sleep_us.
-Меньшие значения заменяются на 0.
-
-## recovery_tune_sleep_cutoff_us
-
- Тип: микросекунды
- Значение по умолчанию: 10000000
- Можно менять на лету: да
-
-Максимальное возможное значение авто-подстроенного recovery_sleep_us.
-Большие значения считаются случайными выбросами и игнорируются в
-усреднении.
+Значения ниже данного заменяются на 0.
--- a/docs/config/src/monitor.yml
+++ b/docs/config/src/monitor.yml
@@ -1,7 +1,7 @@
 - name: etcd_mon_ttl
  type: sec
-  min: 5
-  default: 1
+  min: 10
+  default: 30
  info: Monitor etcd lease refresh interval in seconds
  info_ru: Интервал обновления etcd резервации (lease) монитором
 - name: etcd_mon_timeout
--- a/docs/config/src/network.yml
+++ b/docs/config/src/network.yml
@@ -245,8 +245,8 @@
    повторная попытка соединения.
 - name: up_wait_retry_interval
  type: ms
-  min: 10
-  default: 50
+  min: 50
+  default: 500
  online: true
  info: |
    OSDs respond to clients with a special error code when they receive I/O
--- a/docs/config/src/osd.yml
+++ b/docs/config/src/osd.yml
@@ -731,19 +731,8 @@
  default: 10
  online: true
  info: |
-    Minimum possible value for auto-tuned recovery_sleep_us. Lower values
-    are changed to 0.
+    Minimum possible value for auto-tuned recovery_sleep_us. Values lower
+    than this value are changed to 0.
  info_ru: |
    Минимальное возможное значение авто-подстроенного recovery_sleep_us.
-    Меньшие значения заменяются на 0.
- name: recovery_tune_sleep_cutoff_us
-  type: us
-  default: 10000000
-  online: true
-  info: |
-    Maximum possible value for auto-tuned recovery_sleep_us. Higher values
-    are treated as outliers and ignored in aggregation.
-  info_ru: |
-    Максимальное возможное значение авто-подстроенного recovery_sleep_us.
-    Большие значения считаются случайными выбросами и игнорируются в
-    усреднении.
+    Значения ниже данного заменяются на 0.
--- a/docs/installation/kubernetes.en.md
+++ b/docs/installation/kubernetes.en.md
@@ -37,7 +37,6 @@ Vitastor CSI supports:
 - Volume snapshots. Example: [snapshot class](../../csi/deploy/example-snapshot-class.yaml), [snapshot](../../csi/deploy/example-snapshot.yaml), [clone](../../csi/deploy/example-snapshot-clone.yaml)
 - [VDUSE](../usage/qemu.en.md#vduse) (preferred) and [NBD](../usage/nbd.en.md) device mapping methods
 - Upgrades with VDUSE - new handler processes are restarted when CSI pods are restarted themselves
- VDUSE daemon auto-restart - handler processes are automatically restarted if they crash due to a bug in Vitastor client code
 - Multiple clusters by using multiple configuration files in ConfigMap.

 Remember that to use snapshots with CSI you also have to install [Snapshot Controller and CRDs](https://kubernetes-csi.github.io/docs/snapshot-controller.html#deployment).
--- a/docs/installation/kubernetes.ru.md
+++ b/docs/installation/kubernetes.ru.md
@@ -37,7 +37,6 @@ CSI-плагин Vitastor поддерживает:
 - Снимки томов. Пример: [класс снимков](../../csi/deploy/example-snapshot-class.yaml), [снимок](../../csi/deploy/example-snapshot.yaml), [клон снимка](../../csi/deploy/example-snapshot-clone.yaml)
 - Способы подключения устройств [VDUSE](../usage/qemu.ru.md#vduse) (предпочитаемый) и [NBD](../usage/nbd.ru.md)
 - Обновление при использовании VDUSE - новые процессы-обработчики устройств успешно перезапускаются вместе с самими подами CSI
- Автоперезауск демонов VDUSE - процесс-обработчик автоматически перезапустится, если он внезапно упадёт из-за бага в коде клиента Vitastor
 - Несколько кластеров через задание нескольких файлов конфигурации в ConfigMap.

 Не забывайте, что для использования снимков нужно сначала установить [контроллер снимков и CRD](https://kubernetes-csi.github.io/docs/snapshot-controller.html#deployment).
--- a/docs/performance/theoretical.en.md
+++ b/docs/performance/theoretical.en.md
@@ -11,26 +11,19 @@ Replicated setups:
 - Single-threaded write+fsync latency:
  - With immediate commit: 2 network roundtrips + 1 disk write.
  - With lazy commit: 4 network roundtrips + 1 disk write + 1 disk flush.
- Linear read: `min(total network bandwidth, sum(disk read MB/s))`.
- Linear write: `min(total network bandwidth, sum(disk write MB/s / number of replicas))`.
- Saturated parallel read iops: `min(total network bandwidth, sum(disk read iops))`.
- Saturated parallel write iops: `min(total network bandwidth / number of replicas, sum(disk write iops / number of replicas / (write amplification = 4)))`.
+- Saturated parallel read iops: min(network bandwidth, sum(disk read iops)).
+- Saturated parallel write iops: min(network bandwidth, sum(disk write iops / number of replicas / write amplification)).

-EC/XOR setups (EC N+K):
+EC/XOR setups:
 - Single-threaded (T1Q1) read latency: 1.5 network roundtrips + 1 disk read.
 - Single-threaded write+fsync latency:
  - With immediate commit: 3.5 network roundtrips + 1 disk read + 2 disk writes.
  - With lazy commit: 5.5 network roundtrips + 1 disk read + 2 disk writes + 2 disk fsyncs.
-  - 0.5 in actually `(N-1)/N` which means that an additional roundtrip doesn't happen when
+  - 0.5 in actually (k-1)/k which means that an additional roundtrip doesn't happen when
    the read sub-operation can be served locally.
- Linear read: `min(total network bandwidth, sum(disk read MB/s))`.
- Linear write: `min(total network bandwidth, sum(disk write MB/s * N/(N+K)))`.
- Saturated parallel read iops: `min(total network bandwidth, sum(disk read iops))`.
- Saturated parallel write iops: roughly `total iops / (N+K) / WA`. More exactly,
-  `min(total network bandwidth * N/(N+K), sum(disk randrw iops / (N*4 + K*5 + 1)))` with
-  random read/write mix corresponding to `(N-1)/(N*4 + K*5 + 1)*100 % reads`.
-  - For example, with EC 2+1 it is: `(7% randrw iops) / 14`.
-  - With EC 6+3 it is: `(12.5% randrw iops) / 40`.
+- Saturated parallel read iops: min(network bandwidth, sum(disk read iops)).
+- Saturated parallel write iops: min(network bandwidth, sum(disk write iops * number of data drives / (number of data + parity drives) / write amplification)).
+  In fact, you should put disk write iops under the condition of ~10% reads / ~90% writes in this formula.

 Write amplification for 4 KB blocks is usually 3-5 in Vitastor:
 1. Journal block write
--- a/docs/performance/theoretical.ru.md
+++ b/docs/performance/theoretical.ru.md
@@ -11,27 +11,20 @@
 - Запись+fsync в 1 поток:
  - С мгновенным сбросом: 2 RTT + 1 запись.
  - С отложенным ("ленивым") сбросом: 4 RTT + 1 запись + 1 fsync.
- Линейное чтение: сумма МБ/с чтения всех дисков, либо общая производительность сети (сумма пропускной способности сети всех нод), если в сеть упрётся раньше.
- Линейная запись: сумма МБ/с записи всех дисков / число реплик, либо производительность сети / число реплик, если в сеть упрётся раньше.
- Параллельное случайное мелкое чтение: сумма IOPS чтения всех дисков, либо производительность сети, если в сеть упрётся раньше.
- Параллельная случайная мелкая запись: сумма IOPS записи всех дисков / число реплик / WA, либо производительность сети / число реплик, если в сеть упрётся раньше.
+- Параллельное чтение: сумма IOPS всех дисков либо производительность сети, если в сеть упрётся раньше.
+- Параллельная запись: сумма IOPS всех дисков / число реплик / WA либо производительность сети, если в сеть упрётся раньше.

-При использовании кодов коррекции ошибок (EC N+K):
+При использовании кодов коррекции ошибок (EC):
 - Задержка чтения в 1 поток (T1Q1): 1.5 RTT + 1 чтение.
 - Запись+fsync в 1 поток:
  - С мгновенным сбросом: 3.5 RTT + 1 чтение + 2 записи.
  - С отложенным ("ленивым") сбросом: 5.5 RTT + 1 чтение + 2 записи + 2 fsync.
- Под 0.5 на самом деле подразумевается (N-1)/N, где N - число дисков данных,
+- Под 0.5 на самом деле подразумевается (k-1)/k, где k - число дисков данных,
  что означает, что дополнительное обращение по сети не нужно, когда операция
  чтения обслуживается локально.
- Линейное чтение: сумма МБ/с чтения всех дисков, либо общая производительность сети, если в сеть упрётся раньше.
- Линейная запись: сумма МБ/с записи всех дисков * N/(N+K), либо производительность сети * N / (N+K), если в сеть упрётся раньше.
- Параллельное случайное мелкое чтение: сумма IOPS чтения всех дисков либо производительность сети, если в сеть упрётся раньше.
- Параллельная случайная мелкая запись: грубо `(сумма IOPS / (N+K) / WA)`. Если точнее, то:
-  сумма смешанного IOPS всех дисков при `(N-1)/(N*4 + K*5 + 1)*100 %` чтения, делённая на `(N*4 + K*5 + 1)`.
-  Либо, производительность сети * N/(N+K), если в сеть упрётся раньше.
-  - Например, при EC 2+1 это: `(сумма IOPS при 7% чтения) / 14`.
-  - При EC 6+3 это: `(сумма IOPS при 12.5% чтения) / 40`.
+- Параллельное чтение: сумма IOPS всех дисков либо производительность сети, если в сеть упрётся раньше.
+- Параллельная запись: сумма IOPS всех дисков / общее число дисков данных и чётности / WA либо производительность сети, если в сеть упрётся раньше.
+  Примечание: IOPS дисков в данном случае надо брать в смешанном режиме чтения/записи в пропорции, аналогичной формулам выше.

 WA (мультипликатор записи) для 4 КБ блоков в Vitastor обычно составляет 3-5:
 1. Запись метаданных в журнал
--- a/mon/mon.js
+++ b/mon/mon.js
@@ -55,7 +55,7 @@ const etcd_tree = {
            // etcd connection - configurable online
            etcd_address: "10.0.115.10:2379/v3",
            // mon
-            etcd_mon_ttl: 5, // min: 1
+            etcd_mon_ttl: 30, // min: 10
            etcd_mon_timeout: 1000, // ms. min: 0
            etcd_mon_retries: 5, // min: 0
            mon_change_timeout: 1000, // ms. min: 100
@@ -92,7 +92,7 @@ const etcd_tree = {
            peer_connect_timeout: 5, // seconds. min: 1
            osd_idle_timeout: 5, // seconds. min: 1
            osd_ping_timeout: 5, // seconds. min: 1
-            up_wait_retry_interval: 50, // ms. min: 10
+            up_wait_retry_interval: 500, // ms. min: 50
            max_etcd_attempts: 5,
            etcd_quick_timeout: 1000, // ms
            etcd_slow_timeout: 5000, // ms
@@ -390,8 +390,7 @@ class Mon
 {
    constructor(config)
    {
-        this.failconnect = (e) => this._die(e, 2);
-        this.die = (e) => this._die(e, 1);
+        this.die = (e) => this._die(e);
        if (fs.existsSync(config.config_path||'/etc/vitastor/vitastor.conf'))
        {
            config = {
@@ -480,10 +479,10 @@ class Mon

    check_config()
    {
-        this.config.etcd_mon_ttl = Number(this.config.etcd_mon_ttl) || 5;
-        if (this.config.etcd_mon_ttl < 1)
+        this.config.etcd_mon_ttl = Number(this.config.etcd_mon_ttl) || 30;
+        if (this.config.etcd_mon_ttl < 10)
        {
-            this.config.etcd_mon_ttl = 1;
+            this.config.etcd_mon_ttl = 10;
        }
        this.config.etcd_mon_timeout = Number(this.config.etcd_mon_timeout) || 0;
        if (this.config.etcd_mon_timeout <= 0)
@@ -605,7 +604,7 @@ class Mon
        }
        if (!this.ws)
        {
-            this.failconnect('Failed to open etcd watch websocket');
+            this.die('Failed to open etcd watch websocket');
        }
        const cur_addr = this.selected_etcd_url;
        this.ws_alive = true;
@@ -675,12 +674,7 @@ class Mon
                {
                    this.parse_kv(e.kv);
                    const key = e.kv.key.substr(this.etcd_prefix.length);
-                    if (key.substr(0, 11) == '/osd/state/')
-                    {
-                        stats_changed = true;
-                        changed = true;
-                    }
-                    else if (key.substr(0, 11) == '/osd/stats/' || key.substr(0, 10) == '/pg/stats/' || key.substr(0, 16) == '/osd/inodestats/')
+                    if (key.substr(0, 11) == '/osd/stats/' || key.substr(0, 10) == '/pg/stats/' || key.substr(0, 16) == '/osd/inodestats/')
                    {
                        stats_changed = true;
                    }
@@ -797,9 +791,9 @@ class Mon
            const res = await this.etcd_call('/lease/keepalive', { ID: this.etcd_lease_id }, this.config.etcd_mon_timeout, this.config.etcd_mon_retries);
            if (!res.result.TTL)
            {
-                this.failconnect('Lease expired');
+                this.die('Lease expired');
            }
-        }, this.config.etcd_mon_ttl*1000);
+        }, this.config.etcd_mon_timeout);
        if (!this.signals_set)
        {
            process.on('SIGINT', this.on_stop_cb);
@@ -1420,14 +1414,7 @@ class Mon
            }
            if (changed)
            {
-                const ok = await this.save_pg_config(new_config_pgs);
-                if (ok)
-                    console.log('PG configuration successfully changed');
-                else
-                {
-                    console.log('Someone changed PG configuration while we also tried to change it. Retrying in '+this.config.mon_change_timeout+' ms');
-                    this.schedule_recheck();
-                }
+                await this.save_pg_config(new_config_pgs);
            }
        }
        this.recheck_pgs_active = false;
@@ -1508,11 +1495,6 @@ class Mon
            this.save_new_pgs_txn(new_config_pgs, etcd_request, pool_id, up_osds, osd_tree, real_prev_pgs, pool_res.pgs, pg_history);
        }
        new_config_pgs.hash = tree_hash;
-        return await this.save_pg_config(new_config_pgs, etcd_request);
-    }
-
-    async save_pg_config(new_config_pgs, etcd_request = { compare: [], success: [] })
-    {
        etcd_request.compare.push(
            { key: b64(this.etcd_prefix+'/mon/master'), target: 'LEASE', lease: ''+this.etcd_lease_id },
            { key: b64(this.etcd_prefix+'/config/pgs'), target: 'MOD', mod_revision: ''+this.etcd_watch_revision, result: 'LESS' },
@@ -1640,13 +1622,9 @@ class Mon
        }
        const sum_diff = { op_stats: {}, subop_stats: {}, recovery_stats: {} };
        // Sum derived values instead of deriving summed
-        for (const osd in this.state.osd.state)
+        for (const osd in this.state.osd.stats)
        {
            const derived = this.prev_stats.osd_diff[osd];
-            if (!this.state.osd.state[osd] || !derived)
-            {
-                continue;
-            }
            for (const type in sum_diff)
            {
                for (const op in derived[type]||{})
@@ -1747,13 +1725,9 @@ class Mon
            const used = this.state.pool.stats[pool_id].used_raw_tb;
            this.state.pool.stats[pool_id].used_raw_tb = Number(used)/1024/1024/1024/1024;
        }
-        for (const osd_num in this.state.osd.state)
+        for (const osd_num in this.state.osd.inodestats)
        {
            const ist = this.state.osd.inodestats[osd_num];
-            if (!ist || !this.state.osd.state[osd_num])
-            {
-                continue;
-            }
            for (const pool_id in ist)
            {
                inode_stats[pool_id] = inode_stats[pool_id] || {};
@@ -1769,14 +1743,9 @@ class Mon
                }
            }
        }
-        for (const osd in this.state.osd.state)
+        for (const osd in this.prev_stats.osd_diff)
        {
-            const osd_diff = this.prev_stats.osd_diff[osd];
-            if (!osd_diff || !this.state.osd.state[osd])
-            {
-                continue;
-            }
-            for (const pool_id in osd_diff.inode_stats)
+            for (const pool_id in this.prev_stats.osd_diff[osd].inode_stats)
            {
                for (const inode_num in this.prev_stats.osd_diff[osd].inode_stats[pool_id])
                {
@@ -2016,14 +1985,14 @@ class Mon
                return res.json;
            }
        }
-        this.failconnect();
+        this.die();
    }

-    _die(err, code)
+    _die(err)
    {
        // In fact we can just try to rejoin
        console.error(new Error(err || 'Cluster connection failed'));
-        process.exit(code || 2);
+        process.exit(1);
    }

    local_ips(all)
--- a/mon/package.json
+++ b/mon/package.json
@@ -1,6 +1,6 @@
 {
  "name": "vitastor-mon",
-  "version": "1.4.4",
+  "version": "1.3.1",
  "description": "Vitastor SDS monitor service",
  "main": "mon-main.js",
  "scripts": {
--- a/mon/vitastor-osd@.service
+++ b/mon/vitastor-osd@.service
@@ -8,9 +8,7 @@ PartOf=vitastor.target
 LimitNOFILE=1048576
 LimitNPROC=1048576
 LimitMEMLOCK=infinity
-# Use the following for direct logs to files
-#ExecStart=bash -c 'exec vitastor-disk exec-osd /dev/vitastor/osd%i-data >>/var/log/vitastor/osd%i.log 2>&1'
-ExecStart=vitastor-disk exec-osd /dev/vitastor/osd%i-data
+ExecStart=bash -c 'exec vitastor-disk exec-osd /dev/vitastor/osd%i-data >>/var/log/vitastor/osd%i.log 2>&1'
 ExecStartPre=+vitastor-disk pre-exec /dev/vitastor/osd%i-data
 WorkingDirectory=/
 User=vitastor
--- a/patches/cinder-vitastor.py
+++ b/patches/cinder-vitastor.py
@@ -50,7 +50,7 @@ from cinder.volume import configuration
 from cinder.volume import driver
 from cinder.volume import volume_utils

-VERSION = '1.4.4'
+VERSION = '1.3.1'

 LOG = logging.getLogger(__name__)

--- a/patches/libvirt-9.10-vitastor.diff
+++ b/patches/libvirt-9.10-vitastor.diff
@@ -1,643 +0,0 @@
-commit c1cd026e211e94b120028e7c98a6e4ce5afe9846
-Author: Vitaliy Filippov <vitalif@yourcmc.ru>
-Date:   Wed Jan 24 22:04:50 2024 +0300
-
-    Add Vitastor support
-
-diff --git a/include/libvirt/libvirt-storage.h b/include/libvirt/libvirt-storage.h
-index aaad4a3da1..5f5daa8341 100644
--- a/include/libvirt/libvirt-storage.h
-+++ b/include/libvirt/libvirt-storage.h
-@@ -326,6 +326,7 @@ typedef enum {
-     VIR_CONNECT_LIST_STORAGE_POOLS_ZFS           = 1 << 17, /* (Since: 1.2.8) */
-     VIR_CONNECT_LIST_STORAGE_POOLS_VSTORAGE      = 1 << 18, /* (Since: 3.1.0) */
-     VIR_CONNECT_LIST_STORAGE_POOLS_ISCSI_DIRECT  = 1 << 19, /* (Since: 5.6.0) */
-+    VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR      = 1 << 20, /* (Since: 5.0.0) */
- } virConnectListAllStoragePoolsFlags;
- 
- int                     virConnectListAllStoragePools(virConnectPtr conn,
-diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c
-index 22ad43e1d7..56c81d6852 100644
--- a/src/conf/domain_conf.c
-+++ b/src/conf/domain_conf.c
-@@ -7185,7 +7185,8 @@ virDomainDiskSourceNetworkParse(xmlNodePtr node,
-     src->configFile = virXPathString("string(./config/@file)", ctxt);
- 
-     if (src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTP ||
-        src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTPS)
-+        src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTPS ||
-+        src->protocol == VIR_STORAGE_NET_PROTOCOL_VITASTOR)
-         src->query = virXMLPropString(node, "query");
- 
-     if (virDomainStorageNetworkParseHosts(node, ctxt, &src->hosts, &src->nhosts) < 0)
-@@ -30618,6 +30619,7 @@ virDomainStorageSourceTranslateSourcePool(virStorageSource *src,
- 
-     case VIR_STORAGE_POOL_MPATH:
-     case VIR_STORAGE_POOL_RBD:
-+    case VIR_STORAGE_POOL_VITASTOR:
-     case VIR_STORAGE_POOL_SHEEPDOG:
-     case VIR_STORAGE_POOL_GLUSTER:
-     case VIR_STORAGE_POOL_LAST:
-diff --git a/src/conf/domain_validate.c b/src/conf/domain_validate.c
-index c72108886e..c739ed6c43 100644
--- a/src/conf/domain_validate.c
-+++ b/src/conf/domain_validate.c
-@@ -495,6 +495,7 @@ virDomainDiskDefValidateSourceChainOne(const virStorageSource *src)
-         case VIR_STORAGE_NET_PROTOCOL_RBD:
-             break;
- 
-+        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
-         case VIR_STORAGE_NET_PROTOCOL_NBD:
-         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
-         case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
-@@ -541,7 +542,7 @@ virDomainDiskDefValidateSourceChainOne(const virStorageSource *src)
-         }
-     }
- 
-    /* internal snapshots and config files are currently supported only with rbd: */
-+    /* internal snapshots are currently supported only with rbd: */
-     if (virStorageSourceGetActualType(src) != VIR_STORAGE_TYPE_NETWORK &&
-         src->protocol != VIR_STORAGE_NET_PROTOCOL_RBD) {
-         if (src->snapshot) {
-@@ -549,10 +550,15 @@ virDomainDiskDefValidateSourceChainOne(const virStorageSource *src)
-                            _("<snapshot> element is currently supported only with 'rbd' disks"));
-             return -1;
-         }
-+    }
- 
-+    /* config files are currently supported only with rbd and vitastor: */
-+    if (virStorageSourceGetActualType(src) != VIR_STORAGE_TYPE_NETWORK &&
-+        src->protocol != VIR_STORAGE_NET_PROTOCOL_RBD &&
-+        src->protocol != VIR_STORAGE_NET_PROTOCOL_VITASTOR) {
-         if (src->configFile) {
-             virReportError(VIR_ERR_XML_ERROR, "%s",
-                           _("<config> element is currently supported only with 'rbd' disks"));
-+                           _("<config> element is currently supported only with 'rbd' and 'vitastor' disks"));
-             return -1;
-         }
-     }
-diff --git a/src/conf/schemas/domaincommon.rng b/src/conf/schemas/domaincommon.rng
-index b98a2ae602..7d7a872e01 100644
--- a/src/conf/schemas/domaincommon.rng
-+++ b/src/conf/schemas/domaincommon.rng
-@@ -1997,6 +1997,35 @@
-     </element>
-   </define>
- 
-+  <define name="diskSourceNetworkProtocolVitastor">
-+    <element name="source">
-+      <interleave>
-+        <attribute name="protocol">
-+          <value>vitastor</value>
-+        </attribute>
-+        <ref name="diskSourceCommon"/>
-+        <optional>
-+          <attribute name="name"/>
-+        </optional>
-+        <optional>
-+          <attribute name="query"/>
-+        </optional>
-+        <zeroOrMore>
-+          <ref name="diskSourceNetworkHost"/>
-+        </zeroOrMore>
-+        <optional>
-+          <element name="config">
-+            <attribute name="file">
-+              <ref name="absFilePath"/>
-+            </attribute>
-+            <empty/>
-+          </element>
-+        </optional>
-+        <empty/>
-+      </interleave>
-+    </element>
-+  </define>
-+
-   <define name="diskSourceNetworkProtocolISCSI">
-     <element name="source">
-       <attribute name="protocol">
-@@ -2347,6 +2376,7 @@
-       <ref name="diskSourceNetworkProtocolSimple"/>
-       <ref name="diskSourceNetworkProtocolVxHS"/>
-       <ref name="diskSourceNetworkProtocolNFS"/>
-+      <ref name="diskSourceNetworkProtocolVitastor"/>
-     </choice>
-   </define>
- 
-diff --git a/src/conf/storage_conf.c b/src/conf/storage_conf.c
-index 68842004b7..1d69a788b6 100644
--- a/src/conf/storage_conf.c
-+++ b/src/conf/storage_conf.c
-@@ -56,7 +56,7 @@ VIR_ENUM_IMPL(virStoragePool,
-               "logical", "disk", "iscsi",
-               "iscsi-direct", "scsi", "mpath",
-               "rbd", "sheepdog", "gluster",
-              "zfs", "vstorage",
-+              "zfs", "vstorage", "vitastor",
- );
- 
- VIR_ENUM_IMPL(virStoragePoolFormatFileSystem,
-@@ -242,6 +242,18 @@ static virStoragePoolTypeInfo poolTypeInfo[] = {
-           .formatToString = virStorageFileFormatTypeToString,
-       }
-     },
-+    {.poolType = VIR_STORAGE_POOL_VITASTOR,
-+     .poolOptions = {
-+         .flags = (VIR_STORAGE_POOL_SOURCE_HOST |
-+                   VIR_STORAGE_POOL_SOURCE_NETWORK |
-+                   VIR_STORAGE_POOL_SOURCE_NAME),
-+      },
-+      .volOptions = {
-+          .defaultFormat = VIR_STORAGE_FILE_RAW,
-+          .formatFromString = virStorageVolumeFormatFromString,
-+          .formatToString = virStorageFileFormatTypeToString,
-+      }
-+    },
-     {.poolType = VIR_STORAGE_POOL_SHEEPDOG,
-      .poolOptions = {
-          .flags = (VIR_STORAGE_POOL_SOURCE_HOST |
-@@ -538,6 +550,11 @@ virStoragePoolDefParseSource(xmlXPathContextPtr ctxt,
-                        _("element 'name' is mandatory for RBD pool"));
-         return -1;
-     }
-+    if (pool_type == VIR_STORAGE_POOL_VITASTOR && source->name == NULL) {
-+        virReportError(VIR_ERR_XML_ERROR, "%s",
-+                       _("element 'name' is mandatory for Vitastor pool"));
-+        return -1;
-+    }
- 
-     if (options->formatFromString) {
-         g_autofree char *format = NULL;
-@@ -1127,6 +1144,7 @@ virStoragePoolDefFormatBuf(virBuffer *buf,
-     /* RBD, Sheepdog, Gluster and Iscsi-direct devices are not local block devs nor
-      * files, so they don't have a target */
-     if (def->type != VIR_STORAGE_POOL_RBD &&
-+        def->type != VIR_STORAGE_POOL_VITASTOR &&
-         def->type != VIR_STORAGE_POOL_SHEEPDOG &&
-         def->type != VIR_STORAGE_POOL_GLUSTER &&
-         def->type != VIR_STORAGE_POOL_ISCSI_DIRECT) {
-diff --git a/src/conf/storage_conf.h b/src/conf/storage_conf.h
-index fc67957cfe..720c07ef74 100644
--- a/src/conf/storage_conf.h
-+++ b/src/conf/storage_conf.h
-@@ -103,6 +103,7 @@ typedef enum {
-     VIR_STORAGE_POOL_GLUSTER,  /* Gluster device */
-     VIR_STORAGE_POOL_ZFS,      /* ZFS */
-     VIR_STORAGE_POOL_VSTORAGE, /* Virtuozzo Storage */
-+    VIR_STORAGE_POOL_VITASTOR, /* Vitastor */
- 
-     VIR_STORAGE_POOL_LAST,
- } virStoragePoolType;
-@@ -454,6 +455,7 @@ VIR_ENUM_DECL(virStoragePartedFs);
-                  VIR_CONNECT_LIST_STORAGE_POOLS_SCSI     | \
-                  VIR_CONNECT_LIST_STORAGE_POOLS_MPATH    | \
-                  VIR_CONNECT_LIST_STORAGE_POOLS_RBD      | \
-+                 VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR | \
-                  VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG | \
-                  VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER  | \
-                  VIR_CONNECT_LIST_STORAGE_POOLS_ZFS      | \
-diff --git a/src/conf/storage_source_conf.c b/src/conf/storage_source_conf.c
-index f974a521b1..cd394d0a9f 100644
--- a/src/conf/storage_source_conf.c
-+++ b/src/conf/storage_source_conf.c
-@@ -88,6 +88,7 @@ VIR_ENUM_IMPL(virStorageNetProtocol,
-               "ssh",
-               "vxhs",
-               "nfs",
-+              "vitastor",
- );
- 
- 
-@@ -1301,6 +1302,7 @@ virStorageSourceNetworkDefaultPort(virStorageNetProtocol protocol)
-         case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
-             return 24007;
- 
-+        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
-         case VIR_STORAGE_NET_PROTOCOL_RBD:
-             /* we don't provide a default for RBD */
-             return 0;
-diff --git a/src/conf/storage_source_conf.h b/src/conf/storage_source_conf.h
-index 5e7d127453..283709eeb3 100644
--- a/src/conf/storage_source_conf.h
-+++ b/src/conf/storage_source_conf.h
-@@ -129,6 +129,7 @@ typedef enum {
-     VIR_STORAGE_NET_PROTOCOL_SSH,
-     VIR_STORAGE_NET_PROTOCOL_VXHS,
-     VIR_STORAGE_NET_PROTOCOL_NFS,
-+    VIR_STORAGE_NET_PROTOCOL_VITASTOR,
- 
-     VIR_STORAGE_NET_PROTOCOL_LAST
- } virStorageNetProtocol;
-diff --git a/src/conf/virstorageobj.c b/src/conf/virstorageobj.c
-index 59fa5da372..4739167f5f 100644
--- a/src/conf/virstorageobj.c
-+++ b/src/conf/virstorageobj.c
-@@ -1438,6 +1438,7 @@ virStoragePoolObjSourceFindDuplicateCb(const void *payload,
-             return 1;
-         break;
- 
-+    case VIR_STORAGE_POOL_VITASTOR:
-     case VIR_STORAGE_POOL_ISCSI_DIRECT:
-     case VIR_STORAGE_POOL_RBD:
-     case VIR_STORAGE_POOL_LAST:
-@@ -1921,6 +1922,8 @@ virStoragePoolObjMatch(virStoragePoolObj *obj,
-                (obj->def->type == VIR_STORAGE_POOL_MPATH))   ||
-               (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_RBD) &&
-                (obj->def->type == VIR_STORAGE_POOL_RBD))     ||
-+              (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR) &&
-+               (obj->def->type == VIR_STORAGE_POOL_VITASTOR)) ||
-               (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG) &&
-                (obj->def->type == VIR_STORAGE_POOL_SHEEPDOG)) ||
-               (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER) &&
-diff --git a/src/libvirt-storage.c b/src/libvirt-storage.c
-index db7660aac4..561df34709 100644
--- a/src/libvirt-storage.c
-+++ b/src/libvirt-storage.c
-@@ -94,6 +94,7 @@ virStoragePoolGetConnect(virStoragePoolPtr pool)
-  * VIR_CONNECT_LIST_STORAGE_POOLS_SCSI
-  * VIR_CONNECT_LIST_STORAGE_POOLS_MPATH
-  * VIR_CONNECT_LIST_STORAGE_POOLS_RBD
-+ * VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR
-  * VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG
-  * VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER
-  * VIR_CONNECT_LIST_STORAGE_POOLS_ZFS
-diff --git a/src/libxl/libxl_conf.c b/src/libxl/libxl_conf.c
-index 62e1be6672..71a1d42896 100644
--- a/src/libxl/libxl_conf.c
-+++ b/src/libxl/libxl_conf.c
-@@ -979,6 +979,7 @@ libxlMakeNetworkDiskSrcStr(virStorageSource *src,
-     case VIR_STORAGE_NET_PROTOCOL_SSH:
-     case VIR_STORAGE_NET_PROTOCOL_VXHS:
-     case VIR_STORAGE_NET_PROTOCOL_NFS:
-+    case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
-     case VIR_STORAGE_NET_PROTOCOL_LAST:
-     case VIR_STORAGE_NET_PROTOCOL_NONE:
-         virReportError(VIR_ERR_NO_SUPPORT,
-diff --git a/src/libxl/xen_xl.c b/src/libxl/xen_xl.c
-index f175359307..8efcf4c329 100644
--- a/src/libxl/xen_xl.c
-+++ b/src/libxl/xen_xl.c
-@@ -1456,6 +1456,7 @@ xenFormatXLDiskSrcNet(virStorageSource *src)
-     case VIR_STORAGE_NET_PROTOCOL_SSH:
-     case VIR_STORAGE_NET_PROTOCOL_VXHS:
-     case VIR_STORAGE_NET_PROTOCOL_NFS:
-+    case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
-     case VIR_STORAGE_NET_PROTOCOL_LAST:
-     case VIR_STORAGE_NET_PROTOCOL_NONE:
-         virReportError(VIR_ERR_NO_SUPPORT,
-diff --git a/src/qemu/qemu_block.c b/src/qemu/qemu_block.c
-index 7e9daf0bdc..825b4a3006 100644
--- a/src/qemu/qemu_block.c
-+++ b/src/qemu/qemu_block.c
-@@ -758,6 +758,38 @@ qemuBlockStorageSourceGetRBDProps(virStorageSource *src,
- }
- 
- 
-+static virJSONValue *
-+qemuBlockStorageSourceGetVitastorProps(virStorageSource *src)
-+{
-+    virJSONValue *ret = NULL;
-+    virStorageNetHostDef *host;
-+    size_t i;
-+    g_auto(virBuffer) buf = VIR_BUFFER_INITIALIZER;
-+    g_autofree char *etcd = NULL;
-+
-+    for (i = 0; i < src->nhosts; i++) {
-+        host = src->hosts + i;
-+        if ((virStorageNetHostTransport)host->transport != VIR_STORAGE_NET_HOST_TRANS_TCP) {
-+            return NULL;
-+        }
-+        virBufferAsprintf(&buf, i > 0 ? ",%s:%u" : "%s:%u", host->name, host->port);
-+    }
-+    if (src->nhosts > 0) {
-+        etcd = virBufferContentAndReset(&buf);
-+    }
-+
-+    if (virJSONValueObjectAdd(&ret,
-+                              "S:etcd-host", etcd,
-+                              "S:etcd-prefix", src->query,
-+                              "S:config-path", src->configFile,
-+                              "s:image", src->path,
-+                              NULL) < 0)
-+        return NULL;
-+
-+    return ret;
-+}
-+
-+
- static virJSONValue *
- qemuBlockStorageSourceGetSheepdogProps(virStorageSource *src)
- {
-@@ -1140,6 +1172,12 @@ qemuBlockStorageSourceGetBackendProps(virStorageSource *src,
-                 return NULL;
-             break;
- 
-+        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
-+            driver = "vitastor";
-+            if (!(fileprops = qemuBlockStorageSourceGetVitastorProps(src)))
-+                return NULL;
-+            break;
-+
-         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
-             driver = "sheepdog";
-             if (!(fileprops = qemuBlockStorageSourceGetSheepdogProps(src)))
-@@ -2032,6 +2070,7 @@ qemuBlockGetBackingStoreString(virStorageSource *src,
- 
-             case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
-             case VIR_STORAGE_NET_PROTOCOL_RBD:
-+            case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
-             case VIR_STORAGE_NET_PROTOCOL_VXHS:
-             case VIR_STORAGE_NET_PROTOCOL_NFS:
-             case VIR_STORAGE_NET_PROTOCOL_SSH:
-@@ -2415,6 +2454,12 @@ qemuBlockStorageSourceCreateGetStorageProps(virStorageSource *src,
-                 return -1;
-             break;
- 
-+        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
-+            driver = "vitastor";
-+            if (!(location = qemuBlockStorageSourceGetVitastorProps(src)))
-+                return -1;
-+            break;
-+
-         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
-             driver = "sheepdog";
-             if (!(location = qemuBlockStorageSourceGetSheepdogProps(src)))
-diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c
-index 953808fcfe..62860283d8 100644
--- a/src/qemu/qemu_domain.c
-+++ b/src/qemu/qemu_domain.c
-@@ -5215,7 +5215,8 @@ qemuDomainValidateStorageSource(virStorageSource *src,
-     if (src->query &&
-         (actualType != VIR_STORAGE_TYPE_NETWORK ||
-          (src->protocol != VIR_STORAGE_NET_PROTOCOL_HTTPS &&
-          src->protocol != VIR_STORAGE_NET_PROTOCOL_HTTP))) {
-+          src->protocol != VIR_STORAGE_NET_PROTOCOL_HTTP &&
-+          src->protocol != VIR_STORAGE_NET_PROTOCOL_VITASTOR))) {
-         virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
-                        _("query is supported only with HTTP(S) protocols"));
-         return -1;
-@@ -10340,6 +10341,7 @@ qemuDomainPrepareStorageSourceTLS(virStorageSource *src,
-         break;
- 
-     case VIR_STORAGE_NET_PROTOCOL_RBD:
-+    case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
-     case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
-     case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
-     case VIR_STORAGE_NET_PROTOCOL_ISCSI:
-diff --git a/src/qemu/qemu_snapshot.c b/src/qemu/qemu_snapshot.c
-index 73ff533827..e9c799ca8f 100644
--- a/src/qemu/qemu_snapshot.c
-+++ b/src/qemu/qemu_snapshot.c
-@@ -423,6 +423,7 @@ qemuSnapshotPrepareDiskExternalInactive(virDomainSnapshotDiskDef *snapdisk,
-         case VIR_STORAGE_NET_PROTOCOL_NONE:
-         case VIR_STORAGE_NET_PROTOCOL_NBD:
-         case VIR_STORAGE_NET_PROTOCOL_RBD:
-+        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
-         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
-         case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
-         case VIR_STORAGE_NET_PROTOCOL_ISCSI:
-@@ -648,6 +649,7 @@ qemuSnapshotPrepareDiskInternal(virDomainDiskDef *disk,
-         case VIR_STORAGE_NET_PROTOCOL_NONE:
-         case VIR_STORAGE_NET_PROTOCOL_NBD:
-         case VIR_STORAGE_NET_PROTOCOL_RBD:
-+        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
-         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
-         case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
-         case VIR_STORAGE_NET_PROTOCOL_ISCSI:
-diff --git a/src/storage/storage_driver.c b/src/storage/storage_driver.c
-index 314fe930e0..fb615a8b4e 100644
--- a/src/storage/storage_driver.c
-+++ b/src/storage/storage_driver.c
-@@ -1626,6 +1626,7 @@ storageVolLookupByPathCallback(virStoragePoolObj *obj,
- 
-         case VIR_STORAGE_POOL_GLUSTER:
-         case VIR_STORAGE_POOL_RBD:
-+        case VIR_STORAGE_POOL_VITASTOR:
-         case VIR_STORAGE_POOL_SHEEPDOG:
-         case VIR_STORAGE_POOL_ZFS:
-         case VIR_STORAGE_POOL_LAST:
-diff --git a/src/storage_file/storage_source_backingstore.c b/src/storage_file/storage_source_backingstore.c
-index 80681924ea..8a3ade9ec0 100644
--- a/src/storage_file/storage_source_backingstore.c
-+++ b/src/storage_file/storage_source_backingstore.c
-@@ -287,6 +287,75 @@ virStorageSourceParseRBDColonString(const char *rbdstr,
- }
- 
- 
-+static int
-+virStorageSourceParseVitastorColonString(const char *colonstr,
-+                                         virStorageSource *src)
-+{
-+    char *p, *e, *next;
-+    g_autofree char *options = NULL;
-+
-+    /* optionally skip the "vitastor:" prefix if provided */
-+    if (STRPREFIX(colonstr, "vitastor:"))
-+        colonstr += strlen("vitastor:");
-+
-+    options = g_strdup(colonstr);
-+
-+    p = options;
-+    while (*p) {
-+        /* find : delimiter or end of string */
-+        for (e = p; *e && *e != ':'; ++e) {
-+            if (*e == '\\') {
-+                e++;
-+                if (*e == '\0')
-+                    break;
-+            }
-+        }
-+        if (*e == '\0') {
-+            next = e;    /* last kv pair */
-+        } else {
-+            next = e + 1;
-+            *e = '\0';
-+        }
-+
-+        if (STRPREFIX(p, "image=")) {
-+            src->path = g_strdup(p + strlen("image="));
-+        } else if (STRPREFIX(p, "etcd-prefix=")) {
-+            src->query = g_strdup(p + strlen("etcd-prefix="));
-+        } else if (STRPREFIX(p, "config-path=")) {
-+            src->configFile = g_strdup(p + strlen("config-path="));
-+        } else if (STRPREFIX(p, "etcd-host=")) {
-+            char *h, *sep;
-+
-+            h = p + strlen("etcd-host=");
-+            while (h < e) {
-+                for (sep = h; sep < e; ++sep) {
-+                    if (*sep == '\\' && (sep[1] == ',' ||
-+                                         sep[1] == ';' ||
-+                                         sep[1] == ' ')) {
-+                        *sep = '\0';
-+                        sep += 2;
-+                        break;
-+                    }
-+                }
-+
-+                if (virStorageSourceRBDAddHost(src, h) < 0)
-+                    return -1;
-+
-+                h = sep;
-+            }
-+        }
-+
-+        p = next;
-+    }
-+
-+    if (!src->path) {
-+        return -1;
-+    }
-+
-+    return 0;
-+}
-+
-+
- static int
- virStorageSourceParseNBDColonString(const char *nbdstr,
-                                     virStorageSource *src)
-@@ -399,6 +468,11 @@ virStorageSourceParseBackingColon(virStorageSource *src,
-             return -1;
-         break;
- 
-+    case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
-+        if (virStorageSourceParseVitastorColonString(path, src) < 0)
-+            return -1;
-+        break;
-+
-     case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
-     case VIR_STORAGE_NET_PROTOCOL_LAST:
-     case VIR_STORAGE_NET_PROTOCOL_NONE:
-@@ -975,6 +1049,54 @@ virStorageSourceParseBackingJSONRBD(virStorageSource *src,
-     return 0;
- }
- 
-+static int
-+virStorageSourceParseBackingJSONVitastor(virStorageSource *src,
-+                                         virJSONValue *json,
-+                                         const char *jsonstr G_GNUC_UNUSED,
-+                                         int opaque G_GNUC_UNUSED)
-+{
-+    const char *filename;
-+    const char *image = virJSONValueObjectGetString(json, "image");
-+    const char *conf = virJSONValueObjectGetString(json, "config-path");
-+    const char *etcd_prefix = virJSONValueObjectGetString(json, "etcd-prefix");
-+    virJSONValue *servers = virJSONValueObjectGetArray(json, "server");
-+    size_t nservers;
-+    size_t i;
-+
-+    src->type = VIR_STORAGE_TYPE_NETWORK;
-+    src->protocol = VIR_STORAGE_NET_PROTOCOL_VITASTOR;
-+
-+    /* legacy syntax passed via 'filename' option */
-+    if ((filename = virJSONValueObjectGetString(json, "filename")))
-+        return virStorageSourceParseVitastorColonString(filename, src);
-+
-+    if (!image) {
-+        virReportError(VIR_ERR_INVALID_ARG, "%s",
-+                       _("missing image name in Vitastor backing volume "
-+                         "JSON specification"));
-+        return -1;
-+    }
-+
-+    src->path = g_strdup(image);
-+    src->configFile = g_strdup(conf);
-+    src->query = g_strdup(etcd_prefix);
-+
-+    if (servers) {
-+        nservers = virJSONValueArraySize(servers);
-+
-+        src->hosts = g_new0(virStorageNetHostDef, nservers);
-+        src->nhosts = nservers;
-+
-+        for (i = 0; i < nservers; i++) {
-+            if (virStorageSourceParseBackingJSONInetSocketAddress(src->hosts + i,
-+                                                                  virJSONValueArrayGet(servers, i)) < 0)
-+                return -1;
-+        }
-+    }
-+
-+    return 0;
-+}
-+
- static int
- virStorageSourceParseBackingJSONRaw(virStorageSource *src,
-                                     virJSONValue *json,
-@@ -1152,6 +1274,7 @@ static const struct virStorageSourceJSONDriverParser jsonParsers[] = {
-     {"sheepdog", false, virStorageSourceParseBackingJSONSheepdog, 0},
-     {"ssh", false, virStorageSourceParseBackingJSONSSH, 0},
-     {"rbd", false, virStorageSourceParseBackingJSONRBD, 0},
-+    {"vitastor", false, virStorageSourceParseBackingJSONVitastor, 0},
-     {"raw", true, virStorageSourceParseBackingJSONRaw, 0},
-     {"nfs", false, virStorageSourceParseBackingJSONNFS, 0},
-     {"vxhs", false, virStorageSourceParseBackingJSONVxHS, 0},
-diff --git a/src/test/test_driver.c b/src/test/test_driver.c
-index e87d7cfd44..ccc05d7aae 100644
--- a/src/test/test_driver.c
-+++ b/src/test/test_driver.c
-@@ -7335,6 +7335,7 @@ testStorageVolumeTypeForPool(int pooltype)
-     case VIR_STORAGE_POOL_ISCSI_DIRECT:
-     case VIR_STORAGE_POOL_GLUSTER:
-     case VIR_STORAGE_POOL_RBD:
-+    case VIR_STORAGE_POOL_VITASTOR:
-         return VIR_STORAGE_VOL_NETWORK;
-     case VIR_STORAGE_POOL_LOGICAL:
-     case VIR_STORAGE_POOL_DISK:
-diff --git a/tests/storagepoolcapsschemadata/poolcaps-fs.xml b/tests/storagepoolcapsschemadata/poolcaps-fs.xml
-index eee75af746..8bd0a57bdd 100644
--- a/tests/storagepoolcapsschemadata/poolcaps-fs.xml
-+++ b/tests/storagepoolcapsschemadata/poolcaps-fs.xml
-@@ -204,4 +204,11 @@
-       </enum>
-     </volOptions>
-   </pool>
-+  <pool type='vitastor' supported='no'>
-+    <volOptions>
-+      <defaultFormat type='raw'/>
-+      <enum name='targetFormatType'>
-+      </enum>
-+    </volOptions>
-+  </pool>
- </storagepoolCapabilities>
-diff --git a/tests/storagepoolcapsschemadata/poolcaps-full.xml b/tests/storagepoolcapsschemadata/poolcaps-full.xml
-index 805950a937..852df0de16 100644
--- a/tests/storagepoolcapsschemadata/poolcaps-full.xml
-+++ b/tests/storagepoolcapsschemadata/poolcaps-full.xml
-@@ -204,4 +204,11 @@
-       </enum>
-     </volOptions>
-   </pool>
-+  <pool type='vitastor' supported='yes'>
-+    <volOptions>
-+      <defaultFormat type='raw'/>
-+      <enum name='targetFormatType'>
-+      </enum>
-+    </volOptions>
-+  </pool>
- </storagepoolCapabilities>
-diff --git a/tests/storagepoolxml2argvtest.c b/tests/storagepoolxml2argvtest.c
-index e8e40d695e..db55fe5f3a 100644
--- a/tests/storagepoolxml2argvtest.c
-+++ b/tests/storagepoolxml2argvtest.c
-@@ -65,6 +65,7 @@ testCompareXMLToArgvFiles(bool shouldFail,
-     case VIR_STORAGE_POOL_GLUSTER:
-     case VIR_STORAGE_POOL_ZFS:
-     case VIR_STORAGE_POOL_VSTORAGE:
-+    case VIR_STORAGE_POOL_VITASTOR:
-     case VIR_STORAGE_POOL_LAST:
-     default:
-         VIR_TEST_DEBUG("pool type '%s' has no xml2argv test", defTypeStr);
-diff --git a/tools/virsh-pool.c b/tools/virsh-pool.c
-index 36f00cf643..5f5bd3464e 100644
--- a/tools/virsh-pool.c
-+++ b/tools/virsh-pool.c
-@@ -1223,6 +1223,9 @@ cmdPoolList(vshControl *ctl, const vshCmd *cmd G_GNUC_UNUSED)
-             case VIR_STORAGE_POOL_VSTORAGE:
-                 flags |= VIR_CONNECT_LIST_STORAGE_POOLS_VSTORAGE;
-                 break;
-+            case VIR_STORAGE_POOL_VITASTOR:
-+                flags |= VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR;
-+                break;
-             case VIR_STORAGE_POOL_LAST:
-                 break;
-             }
--- a/pull_request_template.yml
+++ b/pull_request_template.yml
@@ -1,28 +0,0 @@
-name: Pull Request
-about: Submit a pull request
-body:
-  - type: textarea
-    id: description
-    attributes:
-      label: Description
-      description: Describe your pull request
-      placeholder: ""
-      value: ""
-    validations:
-      required: true
-  - type: input
-    id: author
-    attributes:
-      label: Contributor Name
-      description: Contributor Name or Company Details if the Contributor is a company
-      placeholder: ""
-    validations:
-      required: false
-  - type: checkboxes
-    id: terms
-    attributes:
-      label: CLA
-      description: By submitting this pull request, I accept [Vitastor CLA](https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-en.md)
-      options:
-        - label: "I accept Vitastor CLA agreement: https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-en.md"
-          required: true
--- a/rpm/build-tarball.sh
+++ b/rpm/build-tarball.sh
@@ -24,4 +24,4 @@ rm fio
 mv fio-copy fio
 FIO=`rpm -qi fio | perl -e 'while(<>) { /^Epoch[\s:]+(\S+)/ && print "$1:"; /^Version[\s:]+(\S+)/ && print $1; /^Release[\s:]+(\S+)/ && print "-$1"; }'`
 perl -i -pe 's/(Requires:\s*fio)([^\n]+)?/$1 = '$FIO'/' $VITASTOR/rpm/vitastor-el$EL.spec
-tar --transform 's#^#vitastor-1.4.4/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-1.4.4$(rpm --eval '%dist').tar.gz *
+tar --transform 's#^#vitastor-1.3.1/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-1.3.1$(rpm --eval '%dist').tar.gz *
--- a/rpm/vitastor-el7.Dockerfile
+++ b/rpm/vitastor-el7.Dockerfile
@@ -36,7 +36,7 @@ ADD . /root/vitastor
 RUN set -e; \
    cd /root/vitastor/rpm; \
    sh build-tarball.sh; \
-    cp /root/vitastor-1.4.4.el7.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-1.3.1.el7.tar.gz ~/rpmbuild/SOURCES; \
    cp vitastor-el7.spec ~/rpmbuild/SPECS/vitastor.spec; \
    cd ~/rpmbuild/SPECS/; \
    rpmbuild -ba vitastor.spec; \
--- a/rpm/vitastor-el7.spec
+++ b/rpm/vitastor-el7.spec
@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        1.4.4
+Version:        1.3.1
 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-1.4.4.el7.tar.gz
+Source0:        vitastor-1.3.1.el7.tar.gz

 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel
--- a/rpm/vitastor-el8.Dockerfile
+++ b/rpm/vitastor-el8.Dockerfile
@@ -35,7 +35,7 @@ ADD . /root/vitastor
 RUN set -e; \
    cd /root/vitastor/rpm; \
    sh build-tarball.sh; \
-    cp /root/vitastor-1.4.4.el8.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-1.3.1.el8.tar.gz ~/rpmbuild/SOURCES; \
    cp vitastor-el8.spec ~/rpmbuild/SPECS/vitastor.spec; \
    cd ~/rpmbuild/SPECS/; \
    rpmbuild -ba vitastor.spec; \
--- a/rpm/vitastor-el8.spec
+++ b/rpm/vitastor-el8.spec
@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        1.4.4
+Version:        1.3.1
 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-1.4.4.el8.tar.gz
+Source0:        vitastor-1.3.1.el8.tar.gz

 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel
--- a/rpm/vitastor-el9.Dockerfile
+++ b/rpm/vitastor-el9.Dockerfile
@@ -18,7 +18,7 @@ ADD . /root/vitastor
 RUN set -e; \
    cd /root/vitastor/rpm; \
    sh build-tarball.sh; \
-    cp /root/vitastor-1.4.4.el9.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-1.3.1.el9.tar.gz ~/rpmbuild/SOURCES; \
    cp vitastor-el9.spec ~/rpmbuild/SPECS/vitastor.spec; \
    cd ~/rpmbuild/SPECS/; \
    rpmbuild -ba vitastor.spec; \
--- a/rpm/vitastor-el9.spec
+++ b/rpm/vitastor-el9.spec
@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        1.4.4
+Version:        1.3.1
 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-1.4.4.el9.tar.gz
+Source0:        vitastor-1.3.1.el9.tar.gz

 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel
--- a/src/CMakeLists.txt
+++ b/src/CMakeLists.txt
@@ -16,7 +16,7 @@ if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
 	set(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
 endif()

-add_definitions(-DVERSION="1.4.4")
+add_definitions(-DVERSION="1.3.1")
 add_definitions(-Wall -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith -fdiagnostics-color=always -fno-omit-frame-pointer -I ${CMAKE_SOURCE_DIR}/src)
 add_link_options(-fno-omit-frame-pointer)
 if (${WITH_ASAN})
@@ -181,6 +181,25 @@ target_link_libraries(vitastor-nbd
 	vitastor_client
 )

+# vitastor-kv
+add_executable(vitastor-kv
+	kv_cli.cpp
+	kv_db.cpp
+	kv_db.h
+)
+target_link_libraries(vitastor-kv
+	vitastor_client
+)
+
+add_executable(vitastor-kv-stress
+	kv_stress.cpp
+	kv_db.cpp
+	kv_db.h
+)
+target_link_libraries(vitastor-kv-stress
+	vitastor_client
+)
+
 # vitastor-nfs
 add_executable(vitastor-nfs
 	nfs_proxy.cpp
--- a/src/blockstore_flush.cpp
+++ b/src/blockstore_flush.cpp
@@ -184,7 +184,8 @@ void journal_flusher_t::mark_trim_possible()
    if (trim_wanted > 0)
    {
        dequeuing = true;
-        journal_trim_counter = 0;
+        if (!journal_trim_counter)
+            journal_trim_counter = journal_trim_interval;
        bs->ringloop->wakeup();
    }
 }
@@ -365,7 +366,7 @@ resume_0:
        !flusher->flush_queue.size() || !flusher->dequeuing)
    {
 stop_flusher:
-        if (flusher->trim_wanted > 0 && !flusher->journal_trim_counter)
+        if (flusher->trim_wanted > 0 && flusher->journal_trim_counter > 0)
        {
            // Attempt forced trim
            flusher->active_flushers++;
@@ -1345,6 +1346,7 @@ bool journal_flusher_co::trim_journal(int wait_base)
    else if (wait_state == wait_base+2) goto resume_2;
    else if (wait_state == wait_base+3) goto resume_3;
    else if (wait_state == wait_base+4) goto resume_4;
+    flusher->journal_trim_counter = 0;
    new_trim_pos = bs->journal.get_trim_pos();
    if (new_trim_pos != bs->journal.used_start)
    {
@@ -1417,7 +1419,6 @@ bool journal_flusher_co::trim_journal(int wait_base)
                exit(0);
            }
        }
-        flusher->journal_trim_counter = 0;
        flusher->trimming = false;
    }
    return true;
--- a/src/blockstore_impl.cpp
+++ b/src/blockstore_impl.cpp
@@ -163,10 +163,20 @@ void blockstore_impl_t::loop()
            }
            else if (op->opcode == BS_OP_SYNC)
            {
-                // sync only completed writes?
+                // wait for all small writes to be submitted
+                // wait for all big writes to complete, submit data device fsync
                // wait for the data device fsync to complete, then submit journal writes for big writes
                // then submit an fsync operation
+                if (has_writes)
+                {
+                    // Can't submit SYNC before previous writes
+                    continue;
+                }
                wr_st = continue_sync(op);
+                if (wr_st != 2)
+                {
+                    has_writes = wr_st > 0 ? 1 : 2;
+                }
            }
            else if (op->opcode == BS_OP_STABLE)
            {
@@ -195,10 +205,6 @@ void blockstore_impl_t::loop()
                    // ring is full, stop submission
                    break;
                }
-                else if (PRIV(op)->wait_for == WAIT_JOURNAL)
-                {
-                    PRIV(op)->wait_detail2 = (unstable_writes.size()+unstable_unsynced);
-                }
            }
        }
        if (op_idx != new_idx)
@@ -277,8 +283,7 @@ void blockstore_impl_t::check_wait(blockstore_op_t *op)
    }
    else if (PRIV(op)->wait_for == WAIT_JOURNAL)
    {
-        if (journal.used_start == PRIV(op)->wait_detail &&
-            (unstable_writes.size()+unstable_unsynced) == PRIV(op)->wait_detail2)
+        if (journal.used_start == PRIV(op)->wait_detail)
        {
            // do not submit
 #ifdef BLOCKSTORE_DEBUG
@@ -553,14 +558,13 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
            if (stable_count >= stable_alloc)
            {
                stable_alloc *= 2;
-                obj_ver_id* nst = (obj_ver_id*)realloc(stable, sizeof(obj_ver_id) * stable_alloc);
-                if (!nst)
+                stable = (obj_ver_id*)realloc(stable, sizeof(obj_ver_id) * stable_alloc);
+                if (!stable)
                {
                    op->retval = -ENOMEM;
                    FINISH_OP(op);
                    return;
                }
-                stable = nst;
            }
            stable[stable_count++] = {
                .oid = clean_it->first,
@@ -638,8 +642,8 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
                            if (stable_count >= stable_alloc)
                            {
                                stable_alloc += 32768;
-                                obj_ver_id *nst = (obj_ver_id*)realloc(stable, sizeof(obj_ver_id) * stable_alloc);
-                                if (!nst)
+                                stable = (obj_ver_id*)realloc(stable, sizeof(obj_ver_id) * stable_alloc);
+                                if (!stable)
                                {
                                    if (unstable)
                                        free(unstable);
@@ -647,7 +651,6 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
                                    FINISH_OP(op);
                                    return;
                                }
-                                stable = nst;
                            }
                            stable[stable_count++] = dirty_it->first;
                        }
@@ -663,8 +666,8 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
                    if (unstable_count >= unstable_alloc)
                    {
                        unstable_alloc += 32768;
-                        obj_ver_id *nst = (obj_ver_id*)realloc(unstable, sizeof(obj_ver_id) * unstable_alloc);
-                        if (!nst)
+                        unstable = (obj_ver_id*)realloc(unstable, sizeof(obj_ver_id) * unstable_alloc);
+                        if (!unstable)
                        {
                            if (stable)
                                free(stable);
@@ -672,7 +675,6 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
                            FINISH_OP(op);
                            return;
                        }
-                        unstable = nst;
                    }
                    unstable[unstable_count++] = dirty_it->first;
                }
@@ -692,8 +694,8 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
    if (stable_count+unstable_count > stable_alloc)
    {
        stable_alloc = stable_count+unstable_count;
-        obj_ver_id *nst = (obj_ver_id*)realloc(stable, sizeof(obj_ver_id) * stable_alloc);
-        if (!nst)
+        stable = (obj_ver_id*)realloc(stable, sizeof(obj_ver_id) * stable_alloc);
+        if (!stable)
        {
            if (unstable)
                free(unstable);
@@ -701,7 +703,6 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
            FINISH_OP(op);
            return;
        }
-        stable = nst;
    }
    // Copy unstable entries
    for (int i = 0; i < unstable_count; i++)
--- a/src/blockstore_impl.h
+++ b/src/blockstore_impl.h
@@ -55,7 +55,6 @@
 #define IS_JOURNAL(st) (((st) & 0x0F) == BS_ST_SMALL_WRITE)
 #define IS_BIG_WRITE(st) (((st) & 0x0F) == BS_ST_BIG_WRITE)
 #define IS_DELETE(st) (((st) & 0x0F) == BS_ST_DELETE)
-#define IS_INSTANT(st) (((st) & BS_ST_TYPE_MASK) == BS_ST_DELETE || ((st) & BS_ST_INSTANT))

 #define BS_SUBMIT_CHECK_SQES(n) \
    if (ringloop->sqes_left() < (n))\
@@ -202,7 +201,7 @@ struct blockstore_op_private_t
 {
    // Wait status
    int wait_for;
-    uint64_t wait_detail, wait_detail2;
+    uint64_t wait_detail;
    int pending_ops;
    int op_state;

@@ -378,7 +377,7 @@ class blockstore_impl_t
    // Stabilize
    int dequeue_stable(blockstore_op_t *op);
    int continue_stable(blockstore_op_t *op);
-    void mark_stable(obj_ver_id ov, bool forget_dirty = false);
+    void mark_stable(const obj_ver_id & ov, bool forget_dirty = false);
    void stabilize_object(object_id oid, uint64_t max_ver);
    blockstore_op_t* selective_sync(blockstore_op_t *op);
    int split_stab_op(blockstore_op_t *op, std::function<int(obj_ver_id v)> decider);
--- a/src/blockstore_open.cpp
+++ b/src/blockstore_open.cpp
@@ -19,7 +19,7 @@ void blockstore_impl_t::parse_config(blockstore_config_t & config, bool init)
    throttle_target_mbs = strtoull(config["throttle_target_mbs"].c_str(), NULL, 10);
    throttle_target_parallelism = strtoull(config["throttle_target_parallelism"].c_str(), NULL, 10);
    throttle_threshold_us = strtoull(config["throttle_threshold_us"].c_str(), NULL, 10);
-    if (config["autosync_writes"] != "")
+    if (config.find("autosync_writes") != config.end())
    {
        autosync_writes = strtoull(config["autosync_writes"].c_str(), NULL, 10);
    }
--- a/src/blockstore_stable.cpp
+++ b/src/blockstore_stable.cpp
@@ -412,40 +412,11 @@ resume_4:
    return 2;
 }

-void blockstore_impl_t::mark_stable(obj_ver_id v, bool forget_dirty)
+void blockstore_impl_t::mark_stable(const obj_ver_id & v, bool forget_dirty)
 {
    auto dirty_it = dirty_db.find(v);
    if (dirty_it != dirty_db.end())
    {
-        if (IS_INSTANT(dirty_it->second.state))
-        {
-            // 'Instant' (non-EC) operations may complete and try to become stable out of order. Prevent it.
-            auto back_it = dirty_it;
-            while (back_it != dirty_db.begin())
-            {
-                back_it--;
-                if (back_it->first.oid != v.oid)
-                {
-                    break;
-                }
-                if (!IS_STABLE(back_it->second.state))
-                {
-                    // There are preceding unstable versions, can't flush <v>
-                    return;
-                }
-            }
-            while (true)
-            {
-                dirty_it++;
-                if (dirty_it == dirty_db.end() || dirty_it->first.oid != v.oid ||
-                    !IS_SYNCED(dirty_it->second.state))
-                {
-                    dirty_it--;
-                    break;
-                }
-                v.version = dirty_it->first.version;
-            }
-        }
        while (1)
        {
            bool was_stable = IS_STABLE(dirty_it->second.state);
--- a/src/blockstore_sync.cpp
+++ b/src/blockstore_sync.cpp
@@ -76,7 +76,6 @@ int blockstore_impl_t::continue_sync(blockstore_op_t *op)
        // 2nd step: Data device is synced, prepare & write journal entries
        // Check space in the journal and journal memory buffers
        blockstore_journal_check_t space_check(this);
-        auto reservation = (unstable_writes.size()+unstable_unsynced+PRIV(op)->sync_big_writes.size())*journal.block_size;
        if (dsk.csum_block_size)
        {
            // More complex check because all journal entries have different lengths
@@ -86,14 +85,16 @@ int blockstore_impl_t::continue_sync(blockstore_op_t *op)
                left--;
                auto & dirty_entry = dirty_db.at(sbw);
                uint64_t dyn_size = dsk.dirty_dyn_size(dirty_entry.offset, dirty_entry.len);
-                if (!space_check.check_available(op, 1, sizeof(journal_entry_big_write) + dyn_size, left ? 0 : reservation))
+                if (!space_check.check_available(op, 1, sizeof(journal_entry_big_write) + dyn_size,
+                    (unstable_writes.size()+unstable_unsynced)*journal.block_size))
                {
                    return 0;
                }
            }
        }
        else if (!space_check.check_available(op, PRIV(op)->sync_big_writes.size(),
-            sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size, reservation))
+            sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size,
+            (unstable_writes.size()+unstable_unsynced)*journal.block_size))
        {
            return 0;
        }
--- a/src/blockstore_write.cpp
+++ b/src/blockstore_write.cpp
@@ -129,7 +129,7 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
    }
    bool imm = (op->len < dsk.data_block_size ? (immediate_commit != IMMEDIATE_NONE) : (immediate_commit == IMMEDIATE_ALL));
    if (wait_big && !is_del && !deleted && op->len < dsk.data_block_size && !imm ||
-        !imm && autosync_writes && unsynced_queued_ops >= autosync_writes)
+        !imm && unsynced_queued_ops >= autosync_writes)
    {
        // Issue an additional sync so that the previous big write can reach the journal
        blockstore_op_t *sync_op = new blockstore_op_t;
@@ -320,7 +320,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
        blockstore_journal_check_t space_check(this);
        if (!space_check.check_available(op, unsynced_big_write_count + 1,
            sizeof(journal_entry_big_write) + dsk.clean_dyn_size,
-            (unstable_writes.size()+unstable_unsynced+((dirty_it->second.state & BS_ST_INSTANT) ? 0 : 1))*journal.block_size))
+            (unstable_writes.size()+unstable_unsynced)*journal.block_size))
        {
            return 0;
        }
@@ -412,7 +412,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
                sizeof(journal_entry_big_write) + dsk.clean_dyn_size, 0)
            || !space_check.check_available(op, 1,
                sizeof(journal_entry_small_write) + dyn_size,
-                op->len + (unstable_writes.size()+unstable_unsynced+((dirty_it->second.state & BS_ST_INSTANT) ? 0 : 1))*journal.block_size))
+                op->len + (unstable_writes.size()+unstable_unsynced)*journal.block_size))
        {
            return 0;
        }
@@ -549,7 +549,7 @@ resume_2:
        uint64_t dyn_size = dsk.dirty_dyn_size(op->offset, op->len);
        blockstore_journal_check_t space_check(this);
        if (!space_check.check_available(op, 1, sizeof(journal_entry_big_write) + dyn_size,
-            (unstable_writes.size()+unstable_unsynced+((dirty_it->second.state & BS_ST_INSTANT) ? 0 : 1))*journal.block_size))
+            (unstable_writes.size()+unstable_unsynced)*journal.block_size))
        {
            return 0;
        }
@@ -593,7 +593,7 @@ resume_4:
 #endif
        bool is_big = (dirty_it->second.state & BS_ST_TYPE_MASK) == BS_ST_BIG_WRITE;
        bool imm = is_big ? (immediate_commit == IMMEDIATE_ALL) : (immediate_commit != IMMEDIATE_NONE);
-        bool is_instant = IS_INSTANT(dirty_it->second.state);
+        bool is_instant = ((dirty_it->second.state & BS_ST_TYPE_MASK) == BS_ST_DELETE || (dirty_it->second.state & BS_ST_INSTANT));
        if (imm)
        {
            auto & unstab = unstable_writes[op->oid];
--- a/src/cli_rm_data.cpp
+++ b/src/cli_rm_data.cpp
@@ -17,7 +17,6 @@ struct rm_pg_t
    uint64_t obj_count = 0, obj_done = 0;
    int state = 0;
    int in_flight = 0;
-    bool synced = false;
 };

 struct rm_inode_t
@@ -49,7 +48,6 @@ struct rm_inode_t
                .objects = objects,
                .obj_count = objects.size(),
                .obj_done = 0,
-                .synced = parent->cli->get_immediate_commit(inode),
            });
            if (min_offset == 0)
            {
@@ -153,37 +151,6 @@ struct rm_inode_t
            }
            cur_list->obj_pos++;
        }
-        if (cur_list->in_flight == 0 && cur_list->obj_pos == cur_list->objects.end() &&
-            !cur_list->synced)
-        {
-            osd_op_t *op = new osd_op_t();
-            op->op_type = OSD_OP_OUT;
-            op->peer_fd = parent->cli->msgr.osd_peer_fds.at(cur_list->rm_osd_num);
-            op->req = (osd_any_op_t){
-                .sync = {
-                    .header = {
-                        .magic = SECONDARY_OSD_OP_MAGIC,
-                        .id = parent->cli->next_op_id(),
-                        .opcode = OSD_OP_SYNC,
-                    },
-                },
-            };
-            op->callback = [this, cur_list](osd_op_t *op)
-            {
-                cur_list->in_flight--;
-                cur_list->synced = true;
-                if (op->reply.hdr.retval < 0)
-                {
-                    fprintf(stderr, "Failed to sync OSD %lu (retval=%ld)\n",
-                        cur_list->rm_osd_num, op->reply.hdr.retval);
-                    error_count++;
-                }
-                delete op;
-                continue_delete();
-            };
-            cur_list->in_flight++;
-            parent->cli->msgr.outbox_push(op);
-        }
    }

    void continue_delete()
@@ -194,8 +161,7 @@ struct rm_inode_t
        }
        for (int i = 0; i < lists.size(); i++)
        {
-            if (!lists[i]->in_flight && lists[i]->obj_pos == lists[i]->objects.end() &&
-                lists[i]->synced)
+            if (!lists[i]->in_flight && lists[i]->obj_pos == lists[i]->objects.end())
            {
                delete lists[i];
                lists.erase(lists.begin()+i, lists.begin()+i+1);
@@ -221,7 +187,7 @@ struct rm_inode_t
            {
                fprintf(stderr, "\n");
            }
-            if (parent->progress && (total_done < total_count || inactive_osds.size() > 0 || error_count > 0))
+            if (parent->progress && (total_done < total_count || inactive_osds.size() > 0))
            {
                fprintf(
                    stderr, "Warning: Pool:%u,ID:%lu inode data may not have been fully removed.\n"
--- a/src/cli_status.cpp
+++ b/src/cli_status.cpp
@@ -106,7 +106,7 @@ resume_2:
            if (etcd_states[i]["error"].is_null())
            {
                etcd_alive++;
-                etcd_db_size = etcd_states[i]["dbSize"].uint64_value();
+                etcd_db_size = etcd_states[i]["dbSizeInUse"].uint64_value();
            }
        }
        int mon_count = 0;
--- a/src/cluster_client.cpp
+++ b/src/cluster_client.cpp
@@ -6,7 +6,7 @@
 #include "cluster_client_impl.h"
 #include "http_client.h" // json_is_true

-cluster_client_t::cluster_client_t(ring_loop_t *ringloop, timerfd_manager_t *tfd, json11::Json & config)
+cluster_client_t::cluster_client_t(ring_loop_t *ringloop, timerfd_manager_t *tfd, json11::Json config)
 {
    wb = new writeback_cache_t();

@@ -353,11 +353,11 @@ void cluster_client_t::on_load_config_hook(json11::Json::object & etcd_global_co
    up_wait_retry_interval = config["up_wait_retry_interval"].uint64_value();
    if (!up_wait_retry_interval)
    {
-        up_wait_retry_interval = 50;
+        up_wait_retry_interval = 500;
    }
-    else if (up_wait_retry_interval < 10)
+    else if (up_wait_retry_interval < 50)
    {
-        up_wait_retry_interval = 10;
+        up_wait_retry_interval = 50;
    }
    // log_level
    log_level = config["log_level"].uint64_value();
@@ -534,7 +534,7 @@ void cluster_client_t::execute_internal(cluster_op_t *op)
        return;
    }
    if (op->opcode == OSD_OP_WRITE && enable_writeback && !(op->flags & OP_FLUSH_BUFFER) &&
-        !op->version /* FIXME no CAS writeback */)
+        !op->version /* no CAS writeback */)
    {
        if (wb->writebacks_active >= client_max_writeback_iodepth)
        {
@@ -555,7 +555,7 @@ void cluster_client_t::execute_internal(cluster_op_t *op)
    }
    if (op->opcode == OSD_OP_WRITE && !(op->flags & OP_IMMEDIATE_COMMIT))
    {
-        if (!(op->flags & OP_FLUSH_BUFFER))
+        if (!(op->flags & OP_FLUSH_BUFFER) && !op->version /* no CAS write-repeat */)
        {
            wb->copy_write(op, CACHE_WRITTEN);
        }
@@ -1161,7 +1161,7 @@ void cluster_client_t::handle_op_part(cluster_op_part_t *part)
                );
            }
        }
-        else
+        else if (log_level > 0)
        {
            fprintf(
                stderr, "%s operation failed on OSD %lu: retval=%ld (expected %d)\n",
--- a/src/cluster_client.h
+++ b/src/cluster_client.h
@@ -121,7 +121,7 @@ public:
    json11::Json::object cli_config, file_config, etcd_global_config;
    json11::Json::object config;

-    cluster_client_t(ring_loop_t *ringloop, timerfd_manager_t *tfd, json11::Json & config);
+    cluster_client_t(ring_loop_t *ringloop, timerfd_manager_t *tfd, json11::Json config);
    ~cluster_client_t();
    void execute(cluster_op_t *op);
    void execute_raw(osd_num_t osd_num, osd_op_t *op);
--- a/src/etcd_state_client.h
+++ b/src/etcd_state_client.h
@@ -28,7 +28,7 @@ struct etcd_kv_t
 {
    std::string key;
    json11::Json value;
-    uint64_t mod_revision = 0;
+    uint64_t mod_revision;
 };

 struct pg_config_t
--- a/src/kv_cli.cpp
+++ b/src/kv_cli.cpp
@@ -0,0 +1,401 @@
+// Copyright (c) Vitaliy Filippov, 2019+
+// License: VNPL-1.1 (see README.md for details)
+//
+// Vitastor shared key/value database test CLI
+
+#define _XOPEN_SOURCE
+#include <limits.h>
+
+#include <netinet/tcp.h>
+#include <sys/epoll.h>
+#include <unistd.h>
+#include <fcntl.h>
+//#include <signal.h>
+
+#include "epoll_manager.h"
+#include "str_util.h"
+#include "kv_db.h"
+
+const char *exe_name = NULL;
+
+class kv_cli_t
+{
+public:
+    kv_dbw_t *db = NULL;
+    ring_loop_t *ringloop = NULL;
+    epoll_manager_t *epmgr = NULL;
+    cluster_client_t *cli = NULL;
+    bool interactive = false;
+    int in_progress = 0;
+    char *cur_cmd = NULL;
+    int cur_cmd_size = 0, cur_cmd_alloc = 0;
+    bool finished = false, eof = false;
+    json11::Json::object cfg;
+
+    ~kv_cli_t();
+
+    static json11::Json::object parse_args(int narg, const char *args[]);
+    void run(const json11::Json::object & cfg);
+    void read_cmd();
+    void next_cmd();
+    void handle_cmd(const std::string & cmd, std::function<void()> cb);
+};
+
+kv_cli_t::~kv_cli_t()
+{
+    if (cur_cmd)
+    {
+        free(cur_cmd);
+        cur_cmd = NULL;
+    }
+    cur_cmd_alloc = 0;
+    if (db)
+        delete db;
+    if (cli)
+    {
+        cli->flush();
+        delete cli;
+    }
+    if (epmgr)
+        delete epmgr;
+    if (ringloop)
+        delete ringloop;
+}
+
+json11::Json::object kv_cli_t::parse_args(int narg, const char *args[])
+{
+    json11::Json::object cfg;
+    for (int i = 1; i < narg; i++)
+    {
+        if (!strcmp(args[i], "-h") || !strcmp(args[i], "--help"))
+        {
+            printf(
+                "Vitastor Key/Value CLI\n"
+                "(c) Vitaliy Filippov, 2023+ (VNPL-1.1)\n"
+                "\n"
+                "USAGE: %s [--etcd_address ADDR] [OTHER OPTIONS]\n",
+                exe_name
+            );
+            exit(0);
+        }
+        else if (args[i][0] == '-' && args[i][1] == '-')
+        {
+            const char *opt = args[i]+2;
+            cfg[opt] = !strcmp(opt, "json") || i == narg-1 ? "1" : args[++i];
+        }
+    }
+    return cfg;
+}
+
+void kv_cli_t::run(const json11::Json::object & cfg)
+{
+    // Create client
+    ringloop = new ring_loop_t(512);
+    epmgr = new epoll_manager_t(ringloop);
+    cli = new cluster_client_t(ringloop, epmgr->tfd, cfg);
+    db = new kv_dbw_t(cli);
+    // Load image metadata
+    while (!cli->is_ready())
+    {
+        ringloop->loop();
+        if (cli->is_ready())
+            break;
+        ringloop->wait();
+    }
+    // Run
+    fcntl(0, F_SETFL, fcntl(0, F_GETFL, 0) | O_NONBLOCK);
+    try
+    {
+        epmgr->tfd->set_fd_handler(0, false, [this](int fd, int events)
+        {
+            if (events & EPOLLIN)
+            {
+                read_cmd();
+            }
+            if (events & EPOLLRDHUP)
+            {
+                epmgr->tfd->set_fd_handler(0, false, NULL);
+                finished = true;
+            }
+        });
+        interactive = true;
+        printf("> ");
+    }
+    catch (std::exception & e)
+    {
+        // Can't add to epoll, STDIN is probably a file
+        read_cmd();
+    }
+    while (!finished)
+    {
+        ringloop->loop();
+        if (!finished)
+            ringloop->wait();
+    }
+    // Destroy the client
+    delete db;
+    db = NULL;
+    cli->flush();
+    delete cli;
+    delete epmgr;
+    delete ringloop;
+    cli = NULL;
+    epmgr = NULL;
+    ringloop = NULL;
+}
+
+void kv_cli_t::read_cmd()
+{
+    if (!cur_cmd_alloc)
+    {
+        cur_cmd_alloc = 65536;
+        cur_cmd = (char*)malloc_or_die(cur_cmd_alloc);
+    }
+    while (cur_cmd_size < cur_cmd_alloc)
+    {
+        int r = read(0, cur_cmd+cur_cmd_size, cur_cmd_alloc-cur_cmd_size);
+        if (r < 0 && errno != EAGAIN)
+            fprintf(stderr, "Error reading from stdin: %s\n", strerror(errno));
+        if (r > 0)
+            cur_cmd_size += r;
+        if (r == 0)
+            eof = true;
+        if (r <= 0)
+            break;
+    }
+    next_cmd();
+}
+
+void kv_cli_t::next_cmd()
+{
+    if (in_progress > 0)
+    {
+        return;
+    }
+    int pos = 0;
+    for (; pos < cur_cmd_size; pos++)
+    {
+        if (cur_cmd[pos] == '\n' || cur_cmd[pos] == '\r')
+        {
+            auto cmd = trim(std::string(cur_cmd, pos));
+            pos++;
+            memmove(cur_cmd, cur_cmd+pos, cur_cmd_size-pos);
+            cur_cmd_size -= pos;
+            in_progress++;
+            handle_cmd(cmd, [this]()
+            {
+                in_progress--;
+                if (interactive)
+                    printf("> ");
+                next_cmd();
+                if (!in_progress)
+                    read_cmd();
+            });
+            break;
+        }
+    }
+    if (eof && !in_progress)
+    {
+        finished = true;
+    }
+}
+
+void kv_cli_t::handle_cmd(const std::string & cmd, std::function<void()> cb)
+{
+    if (cmd == "")
+    {
+        cb();
+        return;
+    }
+    auto pos = cmd.find_first_of(" \t");
+    if (pos != std::string::npos)
+    {
+        while (pos < cmd.size()-1 && (cmd[pos+1] == ' ' || cmd[pos+1] == '\t'))
+            pos++;
+    }
+    auto opname = strtolower(pos == std::string::npos ? cmd : cmd.substr(0, pos));
+    if (opname == "open")
+    {
+        uint64_t pool_id = 0;
+        inode_t inode_id = 0;
+        uint32_t kv_block_size = 0;
+        int scanned = sscanf(cmd.c_str() + pos+1, "%lu %lu %u", &pool_id, &inode_id, &kv_block_size);
+        if (scanned == 2)
+        {
+            kv_block_size = 4096;
+        }
+        if (scanned < 2 || !pool_id || !inode_id || !kv_block_size || (kv_block_size & (kv_block_size-1)) != 0)
+        {
+            fprintf(stderr, "Usage: open <pool_id> <inode_id> [block_size]. Block size must be a power of 2. Default is 4096.\n");
+            cb();
+            return;
+        }
+        cfg["kv_block_size"] = (uint64_t)kv_block_size;
+        db->open(INODE_WITH_POOL(pool_id, inode_id), cfg, [=](int res)
+        {
+            if (res < 0)
+                fprintf(stderr, "Error opening index: %s (code %d)\n", strerror(-res), res);
+            else
+                printf("Index opened. Current size: %lu bytes\n", db->get_size());
+            cb();
+        });
+    }
+    else if (opname == "config")
+    {
+        auto pos2 = cmd.find_first_of(" \t", pos+1);
+        if (pos2 == std::string::npos)
+        {
+            fprintf(stderr, "Usage: config <property> <value>\n");
+            cb();
+            return;
+        }
+        auto key = trim(cmd.substr(pos+1, pos2-pos-1));
+        auto value = parse_size(trim(cmd.substr(pos2+1)));
+        if (key != "kv_memory_limit" &&
+            key != "kv_allocate_blocks" &&
+            key != "kv_evict_max_misses" &&
+            key != "kv_evict_attempts_per_level" &&
+            key != "kv_evict_unused_age" &&
+            key != "kv_log_level")
+        {
+            fprintf(
+                stderr, "Allowed properties: kv_memory_limit, kv_allocate_blocks,"
+                " kv_evict_max_misses, kv_evict_attempts_per_level, kv_evict_unused_age, kv_log_level\n"
+            );
+        }
+        else
+        {
+            cfg[key] = value;
+            db->set_config(cfg);
+        }
+        cb();
+    }
+    else if (opname == "get" || opname == "set" || opname == "del")
+    {
+        if (opname == "get" || opname == "del")
+        {
+            if (pos == std::string::npos)
+            {
+                fprintf(stderr, "Usage: %s <key>\n", opname.c_str());
+                cb();
+                return;
+            }
+            auto key = trim(cmd.substr(pos+1));
+            if (opname == "get")
+            {
+                db->get(key, [this, cb](int res, const std::string & value)
+                {
+                    if (res < 0)
+                        fprintf(stderr, "Error: %s (code %d)\n", strerror(-res), res);
+                    else
+                    {
+                        write(1, value.c_str(), value.size());
+                        write(1, "\n", 1);
+                    }
+                    cb();
+                });
+            }
+            else
+            {
+                db->del(key, [this, cb](int res)
+                {
+                    if (res < 0)
+                        fprintf(stderr, "Error: %s (code %d)\n", strerror(-res), res);
+                    else
+                        printf("OK\n");
+                    cb();
+                });
+            }
+        }
+        else
+        {
+            auto pos2 = cmd.find_first_of(" \t", pos+1);
+            if (pos2 == std::string::npos)
+            {
+                fprintf(stderr, "Usage: set <key> <value>\n");
+                cb();
+                return;
+            }
+            auto key = trim(cmd.substr(pos+1, pos2-pos-1));
+            auto value = trim(cmd.substr(pos2+1));
+            db->set(key, value, [this, cb](int res)
+            {
+                if (res < 0)
+                    fprintf(stderr, "Error: %s (code %d)\n", strerror(-res), res);
+                else
+                    printf("OK\n");
+                cb();
+            });
+        }
+    }
+    else if (opname == "list")
+    {
+        std::string start, end;
+        if (pos != std::string::npos)
+        {
+            auto pos2 = cmd.find_first_of(" \t", pos+1);
+            if (pos2 != std::string::npos)
+            {
+                start = trim(cmd.substr(pos+1, pos2-pos-1));
+                end = trim(cmd.substr(pos2+1));
+            }
+            else
+            {
+                start = trim(cmd.substr(pos+1));
+            }
+        }
+        void *handle = db->list_start(start);
+        db->list_next(handle, [=](int res, const std::string & key, const std::string & value)
+        {
+            if (res < 0)
+            {
+                if (res != -ENOENT)
+                {
+                    fprintf(stderr, "Error: %s (code %d)\n", strerror(-res), res);
+                }
+                db->list_close(handle);
+                cb();
+            }
+            else
+            {
+                printf("%s = %s\n", key.c_str(), value.c_str());
+                db->list_next(handle, NULL);
+            }
+        });
+    }
+    else if (opname == "close")
+    {
+        db->close([=]()
+        {
+            printf("Index closed\n");
+            cb();
+        });
+    }
+    else if (opname == "quit" || opname == "q")
+    {
+        ::close(0);
+        finished = true;
+    }
+    else
+    {
+        fprintf(
+            stderr, "Unknown operation: %s. Supported operations:\n"
+            "open <pool_id> <inode_id> [block_size]\n"
+            "config <property> <value>\n"
+            "get <key>\nset <key> <value>\ndel <key>\nlist [<start> [end]]\n"
+            "close\nquit\n", opname.c_str()
+        );
+        cb();
+    }
+}
+
+int main(int narg, const char *args[])
+{
+    setvbuf(stdout, NULL, _IONBF, 0);
+    setvbuf(stderr, NULL, _IONBF, 0);
+    exe_name = args[0];
+    kv_cli_t *p = new kv_cli_t();
+    p->run(kv_cli_t::parse_args(narg, args));
+    delete p;
+    return 0;
+}
--- a/src/kv_db.cpp
+++ b/src/kv_db.cpp
--- a/src/kv_db.h
+++ b/src/kv_db.h
@@ -0,0 +1,39 @@
+// Copyright (c) Vitaliy Filippov, 2019+
+// License: VNPL-1.1 (see README.md for details)
+//
+// Vitastor shared key/value database
+// Parallel optimistic B-Tree O:-)
+
+#pragma once
+
+#include "cluster_client.h"
+
+struct kv_db_t;
+
+struct kv_dbw_t
+{
+    kv_dbw_t(cluster_client_t *cli);
+    ~kv_dbw_t();
+
+    void open(inode_t inode_id, json11::Json cfg, std::function<void(int)> cb);
+    void set_config(json11::Json cfg);
+    void close(std::function<void()> cb);
+
+    uint64_t get_size();
+
+    void get(const std::string & key, std::function<void(int res, const std::string & value)> cb,
+        bool allow_old_cached = false);
+    void set(const std::string & key, const std::string & value, std::function<void(int res)> cb,
+        std::function<bool(int res, const std::string & value)> cas_compare = NULL);
+    void del(const std::string & key, std::function<void(int res)> cb,
+        std::function<bool(int res, const std::string & value)> cas_compare = NULL);
+    void update(const std::string & key,
+        std::function<int(int res, const std::string & old_value, std::string & new_value)> cas_compare,
+        std::function<bool(int res)> cb);
+
+    void* list_start(const std::string & start);
+    void list_next(void *handle, std::function<void(int res, const std::string & key, const std::string & value)> cb);
+    void list_close(void *handle);
+
+    kv_db_t *db;
+};
--- a/src/kv_stress.cpp
+++ b/src/kv_stress.cpp
@@ -0,0 +1,697 @@
+// Copyright (c) Vitaliy Filippov, 2019+
+// License: VNPL-1.1 (see README.md for details)
+//
+// Vitastor shared key/value database stress tester / benchmark
+
+#define _XOPEN_SOURCE
+#include <limits.h>
+
+#include <netinet/tcp.h>
+#include <sys/epoll.h>
+#include <unistd.h>
+#include <fcntl.h>
+//#include <signal.h>
+
+#include "epoll_manager.h"
+#include "str_util.h"
+#include "kv_db.h"
+
+const char *exe_name = NULL;
+
+struct kv_test_listing_t
+{
+    uint64_t count = 0, done = 0;
+    void *handle = NULL;
+    std::string next_after;
+    std::set<std::string> inflights;
+    timespec tv_begin;
+    bool error = false;
+};
+
+struct kv_test_lat_t
+{
+    const char *name = NULL;
+    uint64_t usec = 0, count = 0;
+};
+
+struct kv_test_stat_t
+{
+    kv_test_lat_t get, add, update, del, list;
+    uint64_t list_keys = 0;
+};
+
+class kv_test_t
+{
+public:
+    // Config
+    json11::Json::object kv_cfg;
+    std::string key_prefix, key_suffix;
+    uint64_t inode_id = 0;
+    uint64_t op_count = 1000000;
+    uint64_t runtime_sec = 0;
+    uint64_t parallelism = 4;
+    uint64_t reopen_prob = 1;
+    uint64_t get_prob = 30000;
+    uint64_t add_prob = 20000;
+    uint64_t update_prob = 20000;
+    uint64_t del_prob = 5000;
+    uint64_t list_prob = 300;
+    uint64_t min_key_len = 10;
+    uint64_t max_key_len = 70;
+    uint64_t min_value_len = 50;
+    uint64_t max_value_len = 300;
+    uint64_t min_list_count = 10;
+    uint64_t max_list_count = 1000;
+    uint64_t print_stats_interval = 1;
+    bool json_output = false;
+    uint64_t log_level = 1;
+    bool trace = false;
+    bool stop_on_error = false;
+    // FIXME: Multiple clients
+    kv_test_stat_t stat, prev_stat;
+    timespec prev_stat_time, start_stat_time;
+
+    // State
+    kv_dbw_t *db = NULL;
+    ring_loop_t *ringloop = NULL;
+    epoll_manager_t *epmgr = NULL;
+    cluster_client_t *cli = NULL;
+    ring_consumer_t consumer;
+    bool finished = false;
+    uint64_t total_prob = 0;
+    uint64_t ops_sent = 0, ops_done = 0;
+    int stat_timer_id = -1;
+    int in_progress = 0;
+    bool reopening = false;
+    std::set<kv_test_listing_t*> listings;
+    std::set<std::string> changing_keys;
+    std::map<std::string, std::string> values;
+
+    ~kv_test_t();
+
+    static json11::Json::object parse_args(int narg, const char *args[]);
+    void parse_config(json11::Json cfg);
+    void run(json11::Json cfg);
+    void loop();
+    void print_stats(kv_test_stat_t & prev_stat, timespec & prev_stat_time);
+    void print_total_stats();
+    void start_change(const std::string & key);
+    void stop_change(const std::string & key);
+    void add_stat(kv_test_lat_t & stat, timespec tv_begin);
+};
+
+kv_test_t::~kv_test_t()
+{
+    if (db)
+        delete db;
+    if (cli)
+    {
+        cli->flush();
+        delete cli;
+    }
+    if (epmgr)
+        delete epmgr;
+    if (ringloop)
+        delete ringloop;
+}
+
+json11::Json::object kv_test_t::parse_args(int narg, const char *args[])
+{
+    json11::Json::object cfg;
+    for (int i = 1; i < narg; i++)
+    {
+        if (!strcmp(args[i], "-h") || !strcmp(args[i], "--help"))
+        {
+            printf(
+                "Vitastor Key/Value DB stress tester / benchmark\n"
+                "(c) Vitaliy Filippov, 2023+ (VNPL-1.1)\n"
+                "\n"
+                "USAGE: %s --pool_id POOL_ID --inode_id INODE_ID [OPTIONS]\n"
+                "  --op_count 1000000\n"
+                "    Total operations to run during test. 0 means unlimited\n"
+                "  --key_prefix \"\"\n"
+                "    Prefix for all keys read or written (to avoid collisions)\n"
+                "  --key_suffix \"\"\n"
+                "    Suffix for all keys read or written (to avoid collisions, but scan all DB)\n"
+                "  --runtime 0\n"
+                "    Run for this number of seconds. 0 means unlimited\n"
+                "  --parallelism 4\n"
+                "    Run this number of operations in parallel\n"
+                "  --get_prob 30000\n"
+                "    Fraction of key retrieve operations\n"
+                "  --add_prob 20000\n"
+                "    Fraction of key addition operations\n"
+                "  --update_prob 20000\n"
+                "    Fraction of key update operations\n"
+                "  --del_prob 30000\n"
+                "    Fraction of key delete operations\n"
+                "  --list_prob 300\n"
+                "    Fraction of listing operations\n"
+                "  --min_key_len 10\n"
+                "    Minimum key size in bytes\n"
+                "  --max_key_len 70\n"
+                "    Maximum key size in bytes\n"
+                "  --min_value_len 50\n"
+                "    Minimum value size in bytes\n"
+                "  --max_value_len 300\n"
+                "    Maximum value size in bytes\n"
+                "  --min_list_count 10\n"
+                "    Minimum number of keys read in listing (0 = all keys)\n"
+                "  --max_list_count 1000\n"
+                "    Maximum number of keys read in listing\n"
+                "  --print_stats 1\n"
+                "    Print operation statistics every this number of seconds\n"
+                "  --json\n"
+                "    JSON output\n"
+                "  --stop_on_error 0\n"
+                "    Stop on first execution error, mismatch, lost key or extra key during listing\n"
+                "  --kv_memory_limit 128M\n"
+                "    Maximum memory to use for vitastor-kv index cache\n"
+                "  --kv_allocate_blocks 4\n"
+                "    Number of PG blocks used for new tree block allocation in parallel\n"
+                "  --kv_evict_max_misses 10\n"
+                "    Eviction algorithm parameter: retry eviction from another random spot\n"
+                "    if this number of keys is used currently or was used recently\n"
+                "  --kv_evict_attempts_per_level 3\n"
+                "    Retry eviction at most this number of times per tree level, starting\n"
+                "    with bottom-most levels\n"
+                "  --kv_evict_unused_age 1000\n"
+                "    Evict only keys unused during this number of last operations\n"
+                "  --kv_log_level 1\n"
+                "    Log level. 0 = errors, 1 = warnings, 10 = trace operations\n",
+                exe_name
+            );
+            exit(0);
+        }
+        else if (args[i][0] == '-' && args[i][1] == '-')
+        {
+            const char *opt = args[i]+2;
+            cfg[opt] = !strcmp(opt, "json") || i == narg-1 ? "1" : args[++i];
+        }
+    }
+    return cfg;
+}
+
+void kv_test_t::parse_config(json11::Json cfg)
+{
+    inode_id = INODE_WITH_POOL(cfg["pool_id"].uint64_value(), cfg["inode_id"].uint64_value());
+    if (cfg["op_count"].uint64_value() > 0)
+        op_count = cfg["op_count"].uint64_value();
+    key_prefix = cfg["key_prefix"].string_value();
+    key_suffix = cfg["key_suffix"].string_value();
+    if (cfg["runtime"].uint64_value() > 0)
+        runtime_sec = cfg["runtime"].uint64_value();
+    if (cfg["parallelism"].uint64_value() > 0)
+        parallelism = cfg["parallelism"].uint64_value();
+    if (!cfg["reopen_prob"].is_null())
+        reopen_prob = cfg["reopen_prob"].uint64_value();
+    if (!cfg["get_prob"].is_null())
+        get_prob = cfg["get_prob"].uint64_value();
+    if (!cfg["add_prob"].is_null())
+        add_prob = cfg["add_prob"].uint64_value();
+    if (!cfg["update_prob"].is_null())
+        update_prob = cfg["update_prob"].uint64_value();
+    if (!cfg["del_prob"].is_null())
+        del_prob = cfg["del_prob"].uint64_value();
+    if (!cfg["list_prob"].is_null())
+        list_prob = cfg["list_prob"].uint64_value();
+    if (!cfg["min_key_len"].is_null())
+        min_key_len = cfg["min_key_len"].uint64_value();
+    if (cfg["max_key_len"].uint64_value() > 0)
+        max_key_len = cfg["max_key_len"].uint64_value();
+    if (!cfg["min_value_len"].is_null())
+        min_value_len = cfg["min_value_len"].uint64_value();
+    if (cfg["max_value_len"].uint64_value() > 0)
+        max_value_len = cfg["max_value_len"].uint64_value();
+    if (!cfg["min_list_count"].is_null())
+        min_list_count = cfg["min_list_count"].uint64_value();
+    if (!cfg["max_list_count"].is_null())
+        max_list_count = cfg["max_list_count"].uint64_value();
+    if (!cfg["print_stats"].is_null())
+        print_stats_interval = cfg["print_stats"].uint64_value();
+    if (!cfg["json"].is_null())
+        json_output = true;
+    if (!cfg["stop_on_error"].is_null())
+        stop_on_error = cfg["stop_on_error"].bool_value();
+    if (!cfg["kv_memory_limit"].is_null())
+        kv_cfg["kv_memory_limit"] = cfg["kv_memory_limit"];
+    if (!cfg["kv_allocate_blocks"].is_null())
+        kv_cfg["kv_allocate_blocks"] = cfg["kv_allocate_blocks"];
+    if (!cfg["kv_evict_max_misses"].is_null())
+        kv_cfg["kv_evict_max_misses"] = cfg["kv_evict_max_misses"];
+    if (!cfg["kv_evict_attempts_per_level"].is_null())
+        kv_cfg["kv_evict_attempts_per_level"] = cfg["kv_evict_attempts_per_level"];
+    if (!cfg["kv_evict_unused_age"].is_null())
+        kv_cfg["kv_evict_unused_age"] = cfg["kv_evict_unused_age"];
+    if (!cfg["kv_log_level"].is_null())
+    {
+        log_level = cfg["kv_log_level"].uint64_value();
+        trace = log_level >= 10;
+        kv_cfg["kv_log_level"] = cfg["kv_log_level"];
+    }
+    total_prob = reopen_prob+get_prob+add_prob+update_prob+del_prob+list_prob;
+    stat.get.name = "get";
+    stat.add.name = "add";
+    stat.update.name = "update";
+    stat.del.name = "del";
+    stat.list.name = "list";
+}
+
+void kv_test_t::run(json11::Json cfg)
+{
+    srand48(time(NULL));
+    parse_config(cfg);
+    // Create client
+    ringloop = new ring_loop_t(512);
+    epmgr = new epoll_manager_t(ringloop);
+    cli = new cluster_client_t(ringloop, epmgr->tfd, cfg);
+    db = new kv_dbw_t(cli);
+    // Load image metadata
+    while (!cli->is_ready())
+    {
+        ringloop->loop();
+        if (cli->is_ready())
+            break;
+        ringloop->wait();
+    }
+    // Run
+    reopening = true;
+    db->open(inode_id, kv_cfg, [this](int res)
+    {
+        reopening = false;
+        if (res < 0)
+        {
+            fprintf(stderr, "ERROR: Open index: %d (%s)\n", res, strerror(-res));
+            exit(1);
+        }
+        if (trace)
+            printf("Index opened\n");
+        ringloop->wakeup();
+    });
+    consumer.loop = [this]() { loop(); };
+    ringloop->register_consumer(&consumer);
+    if (print_stats_interval)
+        stat_timer_id = epmgr->tfd->set_timer(print_stats_interval*1000, true, [this](int) { print_stats(prev_stat, prev_stat_time); });
+    clock_gettime(CLOCK_REALTIME, &start_stat_time);
+    prev_stat_time = start_stat_time;
+    while (!finished)
+    {
+        ringloop->loop();
+        if (!finished)
+            ringloop->wait();
+    }
+    if (stat_timer_id >= 0)
+        epmgr->tfd->clear_timer(stat_timer_id);
+    ringloop->unregister_consumer(&consumer);
+    // Print total stats
+    print_total_stats();
+    // Destroy the client
+    delete db;
+    db = NULL;
+    cli->flush();
+    delete cli;
+    delete epmgr;
+    delete ringloop;
+    cli = NULL;
+    epmgr = NULL;
+    ringloop = NULL;
+}
+
+static const char *base64_chars = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789@+/";
+
+std::string random_str(int len)
+{
+    std::string str;
+    str.resize(len);
+    for (int i = 0; i < len; i++)
+    {
+        str[i] = base64_chars[lrand48() % 64];
+    }
+    return str;
+}
+
+void kv_test_t::loop()
+{
+    if (reopening)
+    {
+        return;
+    }
+    if (ops_done >= op_count)
+    {
+        finished = true;
+    }
+    while (!finished && ops_sent < op_count && in_progress < parallelism)
+    {
+        uint64_t dice = (lrand48() % total_prob);
+        if (dice < reopen_prob)
+        {
+            reopening = true;
+            db->close([this]()
+            {
+                if (trace)
+                    printf("Index closed\n");
+                db->open(inode_id, kv_cfg, [this](int res)
+                {
+                    reopening = false;
+                    if (res < 0)
+                    {
+                        fprintf(stderr, "ERROR: Reopen index: %d (%s)\n", res, strerror(-res));
+                        finished = true;
+                        return;
+                    }
+                    if (trace)
+                        printf("Index reopened\n");
+                    ringloop->wakeup();
+                });
+            });
+            return;
+        }
+        else if (dice < reopen_prob+get_prob)
+        {
+            // get existing
+            auto key = random_str(max_key_len);
+            auto k_it = values.lower_bound(key);
+            if (k_it == values.end())
+                continue;
+            key = k_it->first;
+            if (changing_keys.find(key) != changing_keys.end())
+                continue;
+            in_progress++;
+            ops_sent++;
+            if (trace)
+                printf("get %s\n", key.c_str());
+            timespec tv_begin;
+            clock_gettime(CLOCK_REALTIME, &tv_begin);
+            db->get(key, [this, key, tv_begin](int res, const std::string & value)
+            {
+                add_stat(stat.get, tv_begin);
+                ops_done++;
+                in_progress--;
+                auto it = values.find(key);
+                if (res != (it == values.end() ? -ENOENT : 0))
+                {
+                    fprintf(stderr, "ERROR: get %s: %d (%s)\n", key.c_str(), res, strerror(-res));
+                    if (stop_on_error)
+                        exit(1);
+                }
+                else if (it != values.end() && value != it->second)
+                {
+                    fprintf(stderr, "ERROR: get %s: mismatch: %s vs %s\n", key.c_str(), value.c_str(), it->second.c_str());
+                    if (stop_on_error)
+                        exit(1);
+                }
+                ringloop->wakeup();
+            });
+        }
+        else if (dice < reopen_prob+get_prob+add_prob+update_prob)
+        {
+            bool is_add = false;
+            std::string key;
+            if (dice < reopen_prob+get_prob+add_prob)
+            {
+                // add
+                is_add = true;
+                uint64_t key_len = min_key_len + (max_key_len > min_key_len ? lrand48() % (max_key_len-min_key_len) : 0);
+                key = key_prefix + random_str(key_len) + key_suffix;
+            }
+            else
+            {
+                // update
+                key = random_str(max_key_len);
+                auto k_it = values.lower_bound(key);
+                if (k_it == values.end())
+                    continue;
+                key = k_it->first;
+            }
+            if (changing_keys.find(key) != changing_keys.end())
+                continue;
+            uint64_t value_len = min_value_len + (max_value_len > min_value_len ? lrand48() % (max_value_len-min_value_len) : 0);
+            auto value = random_str(value_len);
+            start_change(key);
+            ops_sent++;
+            in_progress++;
+            if (trace)
+                printf("set %s = %s\n", key.c_str(), value.c_str());
+            timespec tv_begin;
+            clock_gettime(CLOCK_REALTIME, &tv_begin);
+            db->set(key, value, [this, key, value, tv_begin, is_add](int res)
+            {
+                add_stat(is_add ? stat.add : stat.update, tv_begin);
+                stop_change(key);
+                ops_done++;
+                in_progress--;
+                if (res != 0)
+                {
+                    fprintf(stderr, "ERROR: set %s = %s: %d (%s)\n", key.c_str(), value.c_str(), res, strerror(-res));
+                    if (stop_on_error)
+                        exit(1);
+                }
+                else
+                {
+                    values[key] = value;
+                }
+                ringloop->wakeup();
+            }, NULL);
+        }
+        else if (dice < reopen_prob+get_prob+add_prob+update_prob+del_prob)
+        {
+            // delete
+            auto key = random_str(max_key_len);
+            auto k_it = values.lower_bound(key);
+            if (k_it == values.end())
+                continue;
+            key = k_it->first;
+            if (changing_keys.find(key) != changing_keys.end())
+                continue;
+            start_change(key);
+            ops_sent++;
+            in_progress++;
+            if (trace)
+                printf("del %s\n", key.c_str());
+            timespec tv_begin;
+            clock_gettime(CLOCK_REALTIME, &tv_begin);
+            db->del(key, [this, key, tv_begin](int res)
+            {
+                add_stat(stat.del, tv_begin);
+                stop_change(key);
+                ops_done++;
+                in_progress--;
+                if (res != 0)
+                {
+                    fprintf(stderr, "ERROR: del %s: %d (%s)\n", key.c_str(), res, strerror(-res));
+                    if (stop_on_error)
+                        exit(1);
+                }
+                else
+                {
+                    values.erase(key);
+                }
+                ringloop->wakeup();
+            }, NULL);
+        }
+        else if (dice < reopen_prob+get_prob+add_prob+update_prob+del_prob+list_prob)
+        {
+            // list
+            ops_sent++;
+            in_progress++;
+            auto key = random_str(max_key_len);
+            auto lst = new kv_test_listing_t;
+            auto k_it = values.lower_bound(key);
+            lst->count = min_list_count + (max_list_count > min_list_count ? lrand48() % (max_list_count-min_list_count) : 0);
+            lst->handle = db->list_start(k_it == values.begin() ? key_prefix : key);
+            lst->next_after = k_it == values.begin() ? key_prefix : key;
+            lst->inflights = changing_keys;
+            listings.insert(lst);
+            if (trace)
+                printf("list from %s\n", key.c_str());
+            clock_gettime(CLOCK_REALTIME, &lst->tv_begin);
+            db->list_next(lst->handle, [this, lst](int res, const std::string & key, const std::string & value)
+            {
+                if (log_level >= 11)
+                    printf("list: %s = %s\n", key.c_str(), value.c_str());
+                if (res >= 0 && key_prefix.size() && (key.size() < key_prefix.size() ||
+                    key.substr(0, key_prefix.size()) != key_prefix))
+                {
+                    // stop at this key
+                    res = -ENOENT;
+                }
+                if (res < 0 || (lst->count > 0 && lst->done >= lst->count))
+                {
+                    add_stat(stat.list, lst->tv_begin);
+                    if (res == 0)
+                    {
+                        // ok (done >= count)
+                    }
+                    else if (res != -ENOENT)
+                    {
+                        fprintf(stderr, "ERROR: list: %d (%s)\n", res, strerror(-res));
+                        lst->error = true;
+                    }
+                    else
+                    {
+                        auto k_it = lst->next_after == "" ? values.begin() : values.upper_bound(lst->next_after);
+                        while (k_it != values.end())
+                        {
+                            while (k_it != values.end() && lst->inflights.find(k_it->first) != lst->inflights.end())
+                                k_it++;
+                            if (k_it != values.end())
+                            {
+                                fprintf(stderr, "ERROR: list: missing key %s\n", (k_it++)->first.c_str());
+                                lst->error = true;
+                            }
+                        }
+                    }
+                    if (lst->error && stop_on_error)
+                        exit(1);
+                    ops_done++;
+                    in_progress--;
+                    db->list_close(lst->handle);
+                    delete lst;
+                    listings.erase(lst);
+                    ringloop->wakeup();
+                }
+                else
+                {
+                    stat.list_keys++;
+                    // Do not check modified keys in listing
+                    // Listing may return their old or new state
+                    if ((!key_suffix.size() || key.size() >= key_suffix.size() &&
+                        key.substr(key.size()-key_suffix.size()) == key_suffix) &&
+                        lst->inflights.find(key) == lst->inflights.end())
+                    {
+                        lst->done++;
+                        auto k_it = lst->next_after == "" ? values.begin() : values.upper_bound(lst->next_after);
+                        while (true)
+                        {
+                            while (k_it != values.end() && lst->inflights.find(k_it->first) != lst->inflights.end())
+                            {
+                                k_it++;
+                            }
+                            if (k_it == values.end() || k_it->first > key)
+                            {
+                                fprintf(stderr, "ERROR: list: extra key %s\n", key.c_str());
+                                lst->error = true;
+                                break;
+                            }
+                            else if (k_it->first < key)
+                            {
+                                fprintf(stderr, "ERROR: list: missing key %s\n", k_it->first.c_str());
+                                lst->error = true;
+                                lst->next_after = k_it->first;
+                                k_it++;
+                            }
+                            else
+                            {
+                                if (k_it->second != value)
+                                {
+                                    fprintf(stderr, "ERROR: list: mismatch: %s = %s but should be %s\n",
+                                        key.c_str(), value.c_str(), k_it->second.c_str());
+                                    lst->error = true;
+                                }
+                                lst->next_after = k_it->first;
+                                break;
+                            }
+                        }
+                    }
+                    db->list_next(lst->handle, NULL);
+                }
+            });
+        }
+    }
+}
+
+void kv_test_t::add_stat(kv_test_lat_t & stat, timespec tv_begin)
+{
+    timespec tv_end;
+    clock_gettime(CLOCK_REALTIME, &tv_end);
+    int64_t usec = (tv_end.tv_sec - tv_begin.tv_sec)*1000000 +
+        (tv_end.tv_nsec - tv_begin.tv_nsec)/1000;
+    if (usec > 0)
+    {
+        stat.usec += usec;
+        stat.count++;
+    }
+}
+
+void kv_test_t::print_stats(kv_test_stat_t & prev_stat, timespec & prev_stat_time)
+{
+    timespec cur_stat_time;
+    clock_gettime(CLOCK_REALTIME, &cur_stat_time);
+    int64_t usec = (cur_stat_time.tv_sec - prev_stat_time.tv_sec)*1000000 +
+        (cur_stat_time.tv_nsec - prev_stat_time.tv_nsec)/1000;
+    if (usec > 0)
+    {
+        kv_test_lat_t *lats[] = { &stat.get, &stat.add, &stat.update, &stat.del, &stat.list };
+        kv_test_lat_t *prev[] = { &prev_stat.get, &prev_stat.add, &prev_stat.update, &prev_stat.del, &prev_stat.list };
+        if (!json_output)
+        {
+            char buf[128] = { 0 };
+            for (int i = 0; i < sizeof(lats)/sizeof(lats[0]); i++)
+            {
+                snprintf(buf, sizeof(buf)-1, "%.1f %s/s (%lu us)", (lats[i]->count-prev[i]->count)*1000000.0/usec,
+                    lats[i]->name, (lats[i]->usec-prev[i]->usec)/(lats[i]->count-prev[i]->count > 0 ? lats[i]->count-prev[i]->count : 1));
+                int k;
+                for (k = strlen(buf); k < strlen(lats[i]->name)+21; k++)
+                    buf[k] = ' ';
+                buf[k] = 0;
+                printf("%s", buf);
+            }
+            printf("\n");
+        }
+        else
+        {
+            int64_t runtime = (cur_stat_time.tv_sec - start_stat_time.tv_sec)*1000000 +
+                (cur_stat_time.tv_nsec - start_stat_time.tv_nsec)/1000;
+            printf("{\"runtime\":%.1f", (double)runtime/1000000.0);
+            for (int i = 0; i < sizeof(lats)/sizeof(lats[0]); i++)
+            {
+                if (lats[i]->count > prev[i]->count)
+                {
+                    printf(
+                        ",\"%s\":{\"avg\":{\"iops\":%.1f,\"usec\":%lu},\"total\":{\"count\":%lu,\"usec\":%lu}}",
+                        lats[i]->name, (lats[i]->count-prev[i]->count)*1000000.0/usec,
+                        (lats[i]->usec-prev[i]->usec)/(lats[i]->count-prev[i]->count),
+                        lats[i]->count, lats[i]->usec
+                    );
+                }
+            }
+            printf("}\n");
+        }
+    }
+    prev_stat = stat;
+    prev_stat_time = cur_stat_time;
+}
+
+void kv_test_t::print_total_stats()
+{
+    if (!json_output)
+        printf("Total:\n");
+    kv_test_stat_t start_stats;
+    timespec start_stat_time = this->start_stat_time;
+    print_stats(start_stats, start_stat_time);
+}
+
+void kv_test_t::start_change(const std::string & key)
+{
+    changing_keys.insert(key);
+    for (auto lst: listings)
+    {
+        lst->inflights.insert(key);
+    }
+}
+
+void kv_test_t::stop_change(const std::string & key)
+{
+    changing_keys.erase(key);
+}
+
+int main(int narg, const char *args[])
+{
+    setvbuf(stdout, NULL, _IONBF, 0);
+    setvbuf(stderr, NULL, _IONBF, 0);
+    exe_name = args[0];
+    kv_test_t *p = new kv_test_t();
+    p->run(kv_test_t::parse_args(narg, args));
+    delete p;
+    return 0;
+}
--- a/src/osd.cpp
+++ b/src/osd.cpp
@@ -22,7 +22,7 @@ static blockstore_config_t json_to_bs(const json11::Json::object & config)
    {
        if (kv.second.is_string())
            bs[kv.first] = kv.second.string_value();
-        else if (!kv.second.is_null())
+        else
            bs[kv.first] = kv.second.dump();
    }
    return bs;
@@ -194,8 +194,7 @@ void osd_t::parse_config(bool init)
        if (autosync_interval > MAX_AUTOSYNC_INTERVAL)
            autosync_interval = DEFAULT_AUTOSYNC_INTERVAL;
    }
-    if (config["autosync_writes"].is_number() ||
-        config["autosync_writes"].string_value() != "")
+    if (!config["autosync_writes"].is_null())
    {
        // Allow to set it to 0
        autosync_writes = config["autosync_writes"].uint64_value();
@@ -233,8 +232,6 @@ void osd_t::parse_config(bool init)
        ? 10 : config["recovery_tune_agg_interval"].uint64_value();
    recovery_tune_sleep_min_us = config["recovery_tune_sleep_min_us"].is_null()
        ? 10 : config["recovery_tune_sleep_min_us"].uint64_value();
-    recovery_tune_sleep_cutoff_us = config["recovery_tune_sleep_cutoff_us"].is_null()
-        ? 10000000 : config["recovery_tune_sleep_cutoff_us"].uint64_value();
    recovery_pg_switch = config["recovery_pg_switch"].uint64_value();
    if (recovery_pg_switch < 1)
        recovery_pg_switch = DEFAULT_RECOVERY_PG_SWITCH;
--- a/src/osd.h
+++ b/src/osd.h
@@ -125,7 +125,6 @@ class osd_t
    int recovery_tune_interval = 1;
    int recovery_tune_agg_interval = 10;
    int recovery_tune_sleep_min_us = 10;
-    int recovery_tune_sleep_cutoff_us = 10000000;
    int recovery_pg_switch = DEFAULT_RECOVERY_PG_SWITCH;
    int recovery_sync_batch = DEFAULT_RECOVERY_BATCH;
    int inode_vanish_time = 60;
@@ -283,7 +282,6 @@ class osd_t
    void exec_sync_stab_all(osd_op_t *cur_op);
    void exec_show_config(osd_op_t *cur_op);
    void exec_secondary(osd_op_t *cur_op);
-    void exec_secondary_real(osd_op_t *cur_op);
    void secondary_op_callback(osd_op_t *cur_op);

    // primary ops
--- a/src/osd_cluster.cpp
+++ b/src/osd_cluster.cpp
@@ -262,8 +262,7 @@ void osd_t::report_statistics()
    for (auto st_it = inode_stats.begin(); st_it != inode_stats.end(); )
    {
        auto & kv = *st_it;
-        auto spc_it = bs_inode_space.find(kv.first);
-        if (spc_it == bs_inode_space.end() || !spc_it->second) // prevent autovivification
+        if (!bs_inode_space[kv.first])
        {
            // Is it an empty inode?
            if (!tv_now.tv_sec)
--- a/src/osd_flush.cpp
+++ b/src/osd_flush.cpp
@@ -422,10 +422,6 @@ void osd_t::tune_recovery()
    rtune_avg_lat = total_recovery_usec/recovery_count;
    uint64_t target_lat = rtune_avg_lat * rtune_avg_lat/1000000.0 * recovery_count/recovery_tune_interval / rtune_target_util;
    auto sleep_us = target_lat > rtune_avg_lat+recovery_tune_sleep_min_us ? target_lat-rtune_avg_lat : 0;
-    if (sleep_us > recovery_tune_sleep_cutoff_us)
-    {
-        return;
-    }
    if (recovery_target_sleep_items.size() != recovery_tune_agg_interval)
    {
        recovery_target_sleep_items.resize(recovery_tune_agg_interval);
@@ -442,7 +438,7 @@ void osd_t::tune_recovery()
    if (recovery_target_sleep_count < recovery_tune_agg_interval)
        recovery_target_sleep_count++;
    recovery_target_sleep_us = recovery_target_sleep_total / recovery_target_sleep_count;
-    if (log_level > 1)
+    if (log_level > 4)
    {
        printf(
            "[OSD %lu] auto-tune: client util: %.2f, recovery util: %.2f, lat: %lu us -> target util %.2f, delay %lu us\n",
--- a/src/osd_peering.cpp
+++ b/src/osd_peering.cpp
@@ -222,9 +222,6 @@ void osd_t::start_pg_peering(pg_t & pg)
    }
    if (pg.pg_cursize < pg.pg_minsize)
    {
-        // FIXME: Incomplete EC PGs may currently easily lead to write hangs ("slow ops" in OSD logs)
-        // because such PGs don't flush unstable entries on secondary OSDs so they can't remove these
-        // entries from their journals...
        pg.state = PG_INCOMPLETE;
        report_pg_state(pg);
        return;
--- a/src/osd_primary.cpp
+++ b/src/osd_primary.cpp
@@ -706,26 +706,6 @@ resume_5:
        remove_object_from_state(op_data->oid, &op_data->object_state, pg);
        deref_object_state(pg, &op_data->object_state, true);
    }
-    // Mark PG and OSDs as dirty
-    for (auto & chunk: (op_data->object_state ? op_data->object_state->osd_set : pg.cur_loc_set))
-    {
-        this->dirty_osds.insert(chunk.osd_num);
-    }
-    for (auto cl_it = msgr.clients.find(cur_op->peer_fd); cl_it != msgr.clients.end(); )
-    {
-        cl_it->second->dirty_pgs.insert({ .pool_id = pg.pool_id, .pg_num = pg.pg_num });
-        break;
-    }
-    dirty_pgs.insert({ .pool_id = pg.pool_id, .pg_num = pg.pg_num });
-    if (immediate_commit == IMMEDIATE_NONE)
-    {
-        unstable_write_count++;
-        if (unstable_write_count >= autosync_writes)
-        {
-            unstable_write_count = 0;
-            autosync();
-        }
-    }
    pg.total_count--;
    cur_op->reply.hdr.retval = 0;
 continue_others:
--- a/src/osd_rmw.cpp
+++ b/src/osd_rmw.cpp
@@ -861,15 +861,15 @@ static void calc_rmw_parity_copy_mod(osd_rmw_stripe_t *stripes, int pg_size, int
 static void calc_rmw_parity_copy_parity(osd_rmw_stripe_t *stripes, int pg_size, int pg_minsize,
    uint64_t *read_osd_set, uint64_t *write_osd_set, uint32_t chunk_size, uint32_t start, uint32_t end)
 {
-    if (write_osd_set != read_osd_set && end != 0)
+    if (write_osd_set != read_osd_set)
    {
        for (int role = pg_minsize; role < pg_size; role++)
        {
-            if (write_osd_set[role] != read_osd_set[role] && write_osd_set[role] != 0 && (start != 0 || end != chunk_size))
+            if (write_osd_set[role] != read_osd_set[role] && (start != 0 || end != chunk_size))
            {
                // Copy new parity into the read buffer to write it back
                memcpy(
-                    (uint8_t*)stripes[role].read_buf + start - stripes[role].read_start,
+                    (uint8_t*)stripes[role].read_buf + start,
                    stripes[role].write_buf,
                    end - start
                );
--- a/src/osd_rmw_test.cpp
+++ b/src/osd_rmw_test.cpp
@@ -30,7 +30,6 @@ void test16();
 void test_recover_22_d2();
 void test_ec43_error_bruteforce();
 void test_recover_53_d5();
-void test_recover_22();

 int main(int narg, char *args[])
 {
@@ -71,8 +70,6 @@ int main(int narg, char *args[])
    test_ec43_error_bruteforce();
    // Test 19
    test_recover_53_d5();
-    // Test 20
-    test_recover_22();
    // End
    printf("all ok\n");
    return 0;
@@ -1247,99 +1244,3 @@ void test_recover_53_d5()
    // Done
    use_ec(8, 5, false);
 }
-
-void test_recover_22()
-{
-    const int bmp = 128*1024 / 4096 / 8;
-    use_ec(4, 2, true);
-    osd_num_t osd_set[4] = { 1, 2, 3, 4 };
-    osd_num_t write_osd_set[4] = { 5, 0, 3, 0 };
-    osd_rmw_stripe_t stripes[4] = {};
-    unsigned bitmaps[4] = { 0 };
-    // split
-    void *write_buf = (uint8_t*)malloc_or_die(4096);
-    set_pattern(write_buf, 4096, PATTERN0);
-    split_stripes(2, 128*1024, 120*1024, 4096, stripes);
-    assert(stripes[0].req_start == 120*1024 && stripes[0].req_end == 124*1024);
-    assert(stripes[1].req_start == 0 && stripes[1].req_end == 0);
-    assert(stripes[2].req_start == 0 && stripes[2].req_end == 0);
-    assert(stripes[3].req_start == 0 && stripes[3].req_end == 0);
-    // calc_rmw
-    void *rmw_buf = calc_rmw(write_buf, stripes, osd_set, 4, 2, 2, write_osd_set, 128*1024, bmp);
-    for (int i = 0; i < 4; i++)
-        stripes[i].bmp_buf = bitmaps+i;
-    assert(rmw_buf);
-    assert(stripes[0].read_start == 0 && stripes[0].read_end == 128*1024);
-    assert(stripes[1].read_start == 120*1024 && stripes[1].read_end == 124*1024);
-    assert(stripes[2].read_start == 0 && stripes[2].read_end == 0);
-    assert(stripes[3].read_start == 0 && stripes[3].read_end == 0);
-    assert(stripes[0].write_start == 120*1024 && stripes[0].write_end == 124*1024);
-    assert(stripes[1].write_start == 0 && stripes[1].write_end == 0);
-    assert(stripes[2].write_start == 120*1024 && stripes[2].write_end == 124*1024);
-    assert(stripes[3].write_start == 0 && stripes[3].write_end == 0);
-    assert(stripes[0].read_buf == (uint8_t*)rmw_buf+4*1024);
-    assert(stripes[1].read_buf == (uint8_t*)rmw_buf+132*1024);
-    assert(stripes[2].read_buf == NULL);
-    assert(stripes[3].read_buf == NULL);
-    assert(stripes[0].write_buf == write_buf);
-    assert(stripes[1].write_buf == NULL);
-    assert(stripes[2].write_buf == (uint8_t*)rmw_buf);
-    assert(stripes[3].write_buf == NULL);
-    // encode
-    set_pattern(stripes[0].read_buf, 128*1024, PATTERN1);
-    set_pattern(stripes[1].read_buf, 4*1024, PATTERN2);
-    memset(stripes[0].bmp_buf, 0xff, bmp);
-    memset(stripes[1].bmp_buf, 0xff, bmp);
-    calc_rmw_parity_ec(stripes, 4, 2, osd_set, write_osd_set, 128*1024, bmp);
-    assert(*(uint32_t*)stripes[2].bmp_buf == 0);
-    assert(stripes[0].write_start == 0 && stripes[0].write_end == 128*1024);
-    assert(stripes[1].write_start == 0 && stripes[1].write_end == 0);
-    assert(stripes[2].write_start == 120*1024 && stripes[2].write_end == 124*1024);
-    assert(stripes[3].write_start == 0 && stripes[3].write_end == 0);
-    assert(stripes[0].write_buf == stripes[0].read_buf);
-    assert(stripes[1].write_buf == NULL);
-    assert(stripes[2].write_buf == (uint8_t*)rmw_buf);
-    assert(stripes[3].write_buf == NULL);
-    check_pattern(stripes[2].write_buf, 4*1024, PATTERN0^PATTERN2);
-    // decode and verify
-    memset(stripes, 0, sizeof(stripes));
-    split_stripes(2, 128*1024, 0, 256*1024, stripes);
-    assert(stripes[0].req_start == 0 && stripes[0].req_end == 128*1024);
-    assert(stripes[1].req_start == 0 && stripes[1].req_end == 128*1024);
-    assert(stripes[2].req_start == 0 && stripes[2].req_end == 0);
-    assert(stripes[3].req_start == 0 && stripes[3].req_end == 0);
-    for (int role = 0; role < 4; role++)
-    {
-        stripes[role].read_start = stripes[role].req_start;
-        stripes[role].read_end = stripes[role].req_end;
-    }
-    assert(extend_missing_stripes(stripes, write_osd_set, 2, 4) == 0);
-    assert(stripes[0].read_start == 0 && stripes[0].read_end == 128*1024);
-    assert(stripes[1].read_start == 0 && stripes[1].read_end == 128*1024);
-    assert(stripes[2].read_start == 0 && stripes[2].read_end == 128*1024);
-    assert(stripes[3].read_start == 0 && stripes[3].read_end == 0);
-    void *read_buf = alloc_read_buffer(stripes, 4, 0);
-    for (int i = 0; i < 4; i++)
-        stripes[i].bmp_buf = bitmaps+i;
-    assert(read_buf);
-    assert(stripes[0].read_buf == read_buf);
-    assert(stripes[1].read_buf == (uint8_t*)read_buf+128*1024);
-    assert(stripes[2].read_buf == (uint8_t*)read_buf+2*128*1024);
-    set_pattern(stripes[0].read_buf, 128*1024, PATTERN1);
-    set_pattern(stripes[0].read_buf+120*1024, 4*1024, PATTERN0);
-    set_pattern(stripes[2].read_buf, 128*1024, PATTERN1^PATTERN2);
-    set_pattern(stripes[2].read_buf+120*1024, 4*1024, PATTERN0^PATTERN2);
-    memset(stripes[0].bmp_buf, 0xff, bmp);
-    memset(stripes[2].bmp_buf, 0, bmp);
-    bitmaps[1] = 0;
-    bitmaps[3] = 0;
-    reconstruct_stripes_ec(stripes, 4, 2, bmp);
-    assert(bitmaps[0] == 0xFFFFFFFF);
-    assert(*(uint32_t*)stripes[1].bmp_buf == 0xFFFFFFFF);
-    check_pattern(stripes[1].read_buf, 128*1024, PATTERN2);
-    free(read_buf);
-    // Done
-    free(rmw_buf);
-    free(write_buf);
-    use_ec(4, 2, false);
-}
--- a/src/osd_secondary.cpp
+++ b/src/osd_secondary.cpp
@@ -42,10 +42,8 @@ void osd_t::secondary_op_callback(osd_op_t *op)
    int retval = op->bs_op->retval;
    delete op->bs_op;
    op->bs_op = NULL;
-    if (op->is_recovery_related() && recovery_target_sleep_us &&
-        op->req.hdr.opcode == OSD_OP_SEC_STABILIZE)
+    if (op->is_recovery_related() && recovery_target_sleep_us)
    {
-        // Apply pause AFTER commit. Do not apply pause to SYNC at all
        if (!op->tv_end.tv_sec)
        {
            clock_gettime(CLOCK_REALTIME, &op->tv_end);
@@ -61,25 +59,7 @@ void osd_t::secondary_op_callback(osd_op_t *op)
    }
 }

-void osd_t::exec_secondary(osd_op_t *op)
-{
-    if (op->is_recovery_related() && recovery_target_sleep_us &&
-        op->req.hdr.opcode != OSD_OP_SEC_STABILIZE && op->req.hdr.opcode != OSD_OP_SEC_SYNC)
-    {
-        // Apply pause BEFORE write/delete
-        tfd->set_timer_us(recovery_target_sleep_us, false, [this, op](int timer_id)
-        {
-            clock_gettime(CLOCK_REALTIME, &op->tv_begin);
-            exec_secondary_real(op);
-        });
-    }
-    else
-    {
-        exec_secondary_real(op);
-    }
-}
-
-void osd_t::exec_secondary_real(osd_op_t *cur_op)
+void osd_t::exec_secondary(osd_op_t *cur_op)
 {
    if (cur_op->req.hdr.opcode == OSD_OP_SEC_READ_BMP)
    {
--- a/src/vitastor.pc.in
+++ b/src/vitastor.pc.in
@@ -6,7 +6,7 @@ includedir=${prefix}/@CMAKE_INSTALL_INCLUDEDIR@

 Name: Vitastor
 Description: Vitastor client library
-Version: 1.4.4
+Version: 1.3.1
 Libs: -L${libdir} -lvitastor_client
 Cflags: -I${includedir}

--- a/tests/run_3osds.sh
+++ b/tests/run_3osds.sh
@@ -10,7 +10,6 @@ SCHEME=${SCHEME:-replicated}
 # OFFSET_ARGS
 # PG_SIZE
 # PG_MINSIZE
-# GLOBAL_CONFIG

 if [ "$SCHEME" = "ec" ]; then
    OSD_COUNT=${OSD_COUNT:-5}
@@ -20,10 +19,10 @@ fi

 if [ "$IMMEDIATE_COMMIT" != "" ]; then
    NO_SAME="--journal_no_same_sector_overwrites true --journal_sector_buffer_count 1024 --disable_data_fsync 1 --immediate_commit all --log_level 10 --etcd_stats_interval 5"
-    $ETCDCTL put /vitastor/config/global '{"recovery_queue_depth":1,"recovery_tune_util_low":1,"immediate_commit":"all","client_enable_writeback":true,"client_max_writeback_iodepth":32'$GLOBAL_CONFIG'}'
+    $ETCDCTL put /vitastor/config/global '{"recovery_queue_depth":1,"recovery_tune_util_low":1,"osd_out_time":1,"immediate_commit":"all","client_enable_writeback":true}'
 else
    NO_SAME="--journal_sector_buffer_count 1024 --log_level 10 --etcd_stats_interval 5"
-    $ETCDCTL put /vitastor/config/global '{"recovery_queue_depth":1,"recovery_tune_util_low":1,"client_enable_writeback":true,"client_max_writeback_iodepth":32'$GLOBAL_CONFIG'}'
+    $ETCDCTL put /vitastor/config/global '{"recovery_queue_depth":1,"recovery_tune_util_low":1,"osd_out_time":1,"client_enable_writeback":true}'
 fi

 start_osd_on()
@@ -54,7 +53,7 @@ for i in $(seq 1 $OSD_COUNT); do
    start_osd $i
 done

-(while true; do set +e; node mon/mon-main.js --etcd_address $ETCD_URL --etcd_prefix "/vitastor" --verbose 1; if [[ $? -ne 2 ]]; then break; fi; done) >>./testdata/mon.log 2>&1 &
+(while true; do node mon/mon-main.js --etcd_address $ETCD_URL --etcd_prefix "/vitastor" --verbose 1 || true; done) >>./testdata/mon.log 2>&1 &
 MON_PID=$!

 if [ "$SCHEME" = "ec" ]; then
--- a/tests/run_tests.sh
+++ b/tests/run_tests.sh
@@ -45,8 +45,6 @@ IMMEDIATE_COMMIT=1 ./test_rebalance_verify.sh
 SCHEME=ec ./test_rebalance_verify.sh
 SCHEME=ec IMMEDIATE_COMMIT=1 ./test_rebalance_verify.sh

-./test_switch_primary.sh
-
 ./test_write.sh
 SCHEME=xor ./test_write.sh

--- a/tests/test_add_osd.sh
+++ b/tests/test_add_osd.sh
@@ -1,7 +1,7 @@
 #!/bin/bash -ex

 PG_COUNT=2048
-GLOBAL_CONFIG=',"osd_out_time":1'
+
 . `dirname $0`/run_3osds.sh

 LD_PRELOAD="build/src/libfio_vitastor.so" \
--- a/tests/test_heal.sh
+++ b/tests/test_heal.sh
@@ -9,7 +9,6 @@ if [[ "$SCHEME" = "ec" ]]; then
 fi
 OSD_COUNT=${OSD_COUNT:-7}
 PG_COUNT=32
-GLOBAL_CONFIG=',"osd_out_time":1'
 . `dirname $0`/run_3osds.sh
 check_qemu

--- a/tests/test_minsize_1.sh
+++ b/tests/test_minsize_1.sh
@@ -2,7 +2,6 @@

 PG_MINSIZE=1
 SCHEME=replicated
-GLOBAL_CONFIG=',"osd_out_time":1'

 . `dirname $0`/run_3osds.sh

--- a/tests/test_scrub.sh
+++ b/tests/test_scrub.sh
@@ -20,9 +20,6 @@ LD_PRELOAD="build/src/libfio_vitastor.so" \
    fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bs=1M -direct=1 -iodepth=4 \
        -mirror_file=./testdata/mirror.bin -end_fsync=1 -rw=write -etcd=$ETCD_URL -image=testimg

-# Save PG primary
-primary=$($ETCDCTL get --print-value-only /vitastor/config/pgs | jq -r '.items["1"]["1"].primary')
-
 # Intentionally corrupt OSD data and restart it
 zero_osd_pid=OSD${ZERO_OSD}_PID
 kill ${!zero_osd_pid}
@@ -37,9 +34,6 @@ start_osd $ZERO_OSD
 # Wait until start
 wait_up 10

-# Wait until PG is back on the same primary
-wait_condition 10 "$ETCDCTL"$' get --print-value-only /vitastor/config/pgs | jq -s -e \'.[0].items["1"]["1"].primary == "'$primary'"'"'"
-
 # Trigger scrub
 $ETCDCTL put /vitastor/pg/history/1/1 `$ETCDCTL get --print-value-only /vitastor/pg/history/1/1 | jq -s -c '(.[0] // {}) + {"next_scrub":1}'`

--- a/tests/test_splitbrain.sh
+++ b/tests/test_splitbrain.sh
@@ -4,7 +4,6 @@ OSD_COUNT=2
 PG_SIZE=2
 PG_MINSIZE=1
 SCHEME=replicated
-GLOBAL_CONFIG=',"osd_out_time":1'

 . `dirname $0`/run_3osds.sh

--- a/tests/test_switch_primary.sh
+++ b/tests/test_switch_primary.sh
@@ -1,18 +0,0 @@
-#!/bin/bash -ex
-
-. `dirname $0`/run_3osds.sh
-
-primary=$($ETCDCTL get --print-value-only /vitastor/config/pgs | jq -r '.items["1"]["1"].primary')
-primary_pid=OSD${primary}_PID
-kill -9 ${!primary_pid}
-
-sleep 15
-wait_condition 10 "$ETCDCTL get --print-value-only /vitastor/config/pgs | jq -s -e '.[0].items[\"1\"][\"1\"].primary != \"$primary\"'"
-
-newprim=$($ETCDCTL get --print-value-only /vitastor/config/pgs | jq -r '.items["1"]["1"].primary')
-
-if [ "$newprim" = "$primary" ]; then
-    format_error Primary not switched
-fi
-
-format_green OK
Author	SHA1	Message	Date
Vitaliy Filippov	a9ef9a86c0	Add update() API to kv_db	2024-01-06 17:14:42 +03:00
Vitaliy Filippov	25832cb7e4	Fix eviction when random_pos selects the end	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	e6326c6539	Implement min/max list_count to make listings during performance test reasonable	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	e32f382815	Fix and improve parallel allocation - Do not try to allocate more DB blocks in an inode block until it's "confirmed" and "locked" by the first write - Do not recheck for new zero DB blocks on first write into an inode block - a CAS failure means someone else is already writing into it - Throw new allocation blocks away regardless of whether the known_version is 0 on a CAS failure	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	fb23d94000	Implement key_prefix for K/V stress test	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	ee462c2dad	More fixes - do not overwrite a block with older version if known version is newer (read may start before update and end after update) - invalidated block versions can't be remembered and trusted - right boundary for split blocks is right_half when diving down, not key_lt - restart update also when block is "invalidated", not just on version mismatch - copy callback in listings to avoid closure destruction bugs too	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	16e4c767f1	Add logging and one more assert	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	9e2b677499	Make get_block() wait for updating when unrelated block is found along the path	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	fd57096d2d	Fix a race condition where changed blocks were parsed over existing cached blocks and getting a mix of data	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	e5ae907256	Simplify code by removing an unneeded "optimisation"	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	64fd6f1c56	Add kv_log_level, print warnings on level 1, trace ops on level 10	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	6e76e09d16	Fix duplicate keys in listings on parallel updates -- do not rewind key "iterator position"	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	0964aeebd2	Implement key suffix to avoid collisions of multiple test workers	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	facff20ca1	Do not complain on empty first block	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	16e09745f0	Add JSON output for stress-tester	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	442f44a64f	Print total stats	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	c67e3d56cb	Do not send more than op_count operations (fix segfault on finish)	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	de41e46335	Add some more resiliency to serialize()	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	bf9a279ff9	Invalidate blocks being updated too	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	b7a41e6394	Change new block allocation method: make each writer choose multiple empty PG blocks and place blocks in them	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	4175cb3720	Remove blocks from cache on unsuccessful updates	2024-01-02 13:24:15 +03:00
Vitaliy Filippov	3a4b71b0cd	Allow to track multiple updates per block (it should never happen though)	2024-01-02 13:24:14 +03:00
Vitaliy Filippov	34969c5919	Do not call stop_updating after failed write_new_block and after clear_block (both delete the item)	2024-01-02 13:24:14 +03:00
Vitaliy Filippov	02a8df6586	Track versions of parent blocks and recheck if changed during update	2024-01-02 13:24:14 +03:00
Vitaliy Filippov	86c6482cf3	Fix resume_split condition (key_lt can also be "")	2024-01-02 13:24:14 +03:00
Vitaliy Filippov	4dd68c543c	Experiment: transform offsets for better sharding	2024-01-02 13:24:14 +03:00
Vitaliy Filippov	10ad96c56c	More post-stress-test fixes - Prevent _split types of new blocks - Stop updating new blocks only after the whole update, otherwise pointers may become invalid - Use recheck_none for updates initially - Use UINT64_MAX as initial block version when postponing ops, otherwise the check fails when the block is initially empty. This for example leads to writing both leaf items & block pointers (which is incorrect) into the root block when starting stress-test with --parallelism 32 - Fix -EINTR comparison	2024-01-02 13:24:14 +03:00
Vitaliy Filippov	6e451117ce	Print operation statistics	2024-01-02 13:24:14 +03:00
Vitaliy Filippov	85f35bdf30	K/V fixes after stress-test :-) - track block versions correctly - per inode block (128kb) instead of tree block (4kb) - prevent multiple parallel CAS writes of the same inode block - add logging for EILSEQ which means invalid data in the tree - fix get_block updated flag which was true for blocks already in cache and was leading to infinite loops on "unrelated block" errors - apply changes to blocks in cache only after successful writes (using "virtual changes") - do not replace cached block with an older version from disk - recheck "unrelated blocks" (read/update collisions) until data stops changing - track tree path correctly - do not treat split block as parent of its right half - correctly move blocks when finding new empty place on disk - restart updates from the beginning when one of blocks is changed by a parallel update - fix delete using SET opcode and setting key to the empty value instead - prevent changing the same key more than 1 time in parallel - fix listing verification - resume continue_updates in update_find (required because it uses continue_update itself) - add allow_old_cached parameter to get()	2024-01-02 13:24:14 +03:00
Vitaliy Filippov	09adaf62fd	Implement K/V DB stress tester	2024-01-02 13:24:14 +03:00
Vitaliy Filippov	af93f8323c	Evict blocks based on memory limit & block usage	2024-01-02 13:24:14 +03:00
Vitaliy Filippov	3d29c76ff4	Track blocks per level	2024-01-02 13:24:14 +03:00
Vitaliy Filippov	19275379c1	Track block level	2024-01-02 13:24:14 +03:00
Vitaliy Filippov	96ad3c7c50	Experimental B-Tree Vitastor embedded K/V database implementation!	2024-01-02 13:24:14 +03:00