Fix eviction when random_pos selects the end

- 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

CMakeLists.txt

@@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8.12)
 
 project(vitastor)
 
-set(VERSION "1.4.7")
+set(VERSION "1.4.8")
 
 add_subdirectory(src)

csi/Makefile

@@ -1,4 +1,4 @@
-VERSION ?= v1.4.7
+VERSION ?= v1.4.8
 
 all: build push
 

csi/deploy/004-csi-nodeplugin.yaml

@@ -49,7 +49,7 @@ spec:
             capabilities:
               add: ["SYS_ADMIN"]
             allowPrivilegeEscalation: true
-          image: vitalif/vitastor-csi:v1.4.7
+          image: vitalif/vitastor-csi:v1.4.8
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/deploy/007-csi-provisioner.yaml

@@ -121,7 +121,7 @@ spec:
             privileged: true
             capabilities:
               add: ["SYS_ADMIN"]
-          image: vitalif/vitastor-csi:v1.4.7
+          image: vitalif/vitastor-csi:v1.4.8
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/src/config.go

@@ -5,7 +5,7 @@ package vitastor
 
 const (
     vitastorCSIDriverName    = "csi.vitastor.io"
-    vitastorCSIDriverVersion = "1.4.7"
+    vitastorCSIDriverVersion = "1.4.8"
 )
 
 // Config struct fills the parameters of request or user input

debian/build-vitastor-bookworm.sh

@@ -3,5 +3,5 @@
 cat < vitastor.Dockerfile > ../Dockerfile
 cd ..
 mkdir -p packages
-sudo podman build --build-arg REL=bookworm -v `pwd`/packages:/root/packages -f Dockerfile .
+sudo podman build --build-arg DISTRO=debian --build-arg REL=bookworm -v `pwd`/packages:/root/packages -f Dockerfile .
 rm Dockerfile

debian/build-vitastor-bullseye.sh

@@ -3,5 +3,5 @@
 cat < vitastor.Dockerfile > ../Dockerfile
 cd ..
 mkdir -p packages
-sudo podman build --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f Dockerfile .
+sudo podman build --build-arg DISTRO=debian --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f Dockerfile .
 rm Dockerfile

debian/build-vitastor-buster.sh

@@ -3,5 +3,5 @@
 cat < vitastor.Dockerfile > ../Dockerfile
 cd ..
 mkdir -p packages
-sudo podman build --build-arg REL=buster -v `pwd`/packages:/root/packages -f Dockerfile .
+sudo podman build --build-arg DISTRO=debian --build-arg REL=buster -v `pwd`/packages:/root/packages -f Dockerfile .
 rm Dockerfile

debian/build-vitastor-ubuntu-jammy.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+cat < vitastor.Dockerfile > ../Dockerfile
+cd ..
+mkdir -p packages
+sudo podman build --build-arg DISTRO=ubuntu --build-arg REL=jammy -v `pwd`/packages:/root/packages -f Dockerfile .
+rm Dockerfile

debian/changelog

@@ -1,4 +1,4 @@
-vitastor (1.4.7-1) unstable; urgency=medium
+vitastor (1.4.8-1) unstable; urgency=medium
 
   * Bugfixes
 

debian/libvirt.Dockerfile

@@ -1,13 +1,14 @@
 # Build patched libvirt for Debian Buster or Bullseye/Sid inside a container
-# cd ..; podman build --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/libvirt.Dockerfile .
+# cd ..; podman build --build-arg DISTRO=debian --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/libvirt.Dockerfile .
 
+ARG DISTRO=
 ARG REL=
-FROM debian:$REL
+FROM $DISTRO:$REL
 ARG REL=
 
 WORKDIR /root
 
-RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" ]; then \
+RUN if ([ "${DISTRO}" = "debian" ]) && ( [ "${REL}" = "buster" -o "${REL}" = "bullseye" ] ); then \
         echo "deb http://deb.debian.org/debian $REL-backports main" >> /etc/apt/sources.list; \
         echo >> /etc/apt/preferences; \
         echo 'Package: *' >> /etc/apt/preferences; \
@@ -23,7 +24,7 @@ RUN apt-get -y build-dep libvirt0
 RUN apt-get -y install libglusterfs-dev
 RUN apt-get --download-only source libvirt
 
-ADD patches/libvirt-5.0-vitastor.diff patches/libvirt-7.0-vitastor.diff patches/libvirt-7.5-vitastor.diff patches/libvirt-7.6-vitastor.diff /root
+ADD patches/libvirt-5.0-vitastor.diff patches/libvirt-7.0-vitastor.diff patches/libvirt-7.5-vitastor.diff patches/libvirt-7.6-vitastor.diff patches/libvirt-8.0-vitastor.diff /root
 RUN set -e; \
     mkdir -p /root/packages/libvirt-$REL; \
     rm -rf /root/packages/libvirt-$REL/*; \

debian/vitastor.Dockerfile

@@ -1,8 +1,10 @@
 # Build Vitastor packages for Debian inside a container
-# cd ..; podman build --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/vitastor.Dockerfile .
+# cd ..; podman build --build-arg DISTRO=debian --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/vitastor.Dockerfile .
 
+ARG DISTRO=debian
 ARG REL=
-FROM debian:$REL
+FROM $DISTRO:$REL
+ARG DISTRO=debian
 ARG REL=
 
 WORKDIR /root
@@ -35,8 +37,8 @@ RUN set -e -x; \
     mkdir -p /root/packages/vitastor-$REL; \
     rm -rf /root/packages/vitastor-$REL/*; \
     cd /root/packages/vitastor-$REL; \
-    cp -r /root/vitastor vitastor-1.4.7; \
-    cd vitastor-1.4.7; \
+    cp -r /root/vitastor vitastor-1.4.8; \
+    cd vitastor-1.4.8; \
     ln -s /root/fio-build/fio-*/ ./fio; \
     FIO=$(head -n1 fio/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
     ls /usr/include/linux/raw.h || cp ./debian/raw.h /usr/include/linux/raw.h; \
@@ -49,8 +51,8 @@ RUN set -e -x; \
     rm -rf a b; \
     echo "dep:fio=$FIO" > debian/fio_version; \
     cd /root/packages/vitastor-$REL; \
-    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_1.4.7.orig.tar.xz vitastor-1.4.7; \
-    cd vitastor-1.4.7; \
+    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_1.4.8.orig.tar.xz vitastor-1.4.8; \
+    cd vitastor-1.4.8; \
     V=$(head -n1 debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
     DEBFULLNAME="Vitaliy Filippov <vitalif@yourcmc.ru>" dch -D $REL -v "$V""$REL" "Rebuild for $REL"; \
     DEB_BUILD_OPTIONS=nocheck dpkg-buildpackage --jobs=auto -sa; \

docs/config/client.en.md

@@ -9,6 +9,8 @@
 These parameters apply only to Vitastor clients (QEMU, fio, NBD and so on) and
 affect their interaction with the cluster.
 
+- [client_retry_interval](#client_retry_interval)
+- [client_eio_retry_interval](#client_eio_retry_interval)
 - [client_max_dirty_bytes](#client_max_dirty_bytes)
 - [client_max_dirty_ops](#client_max_dirty_ops)
 - [client_enable_writeback](#client_enable_writeback)
@@ -19,6 +21,26 @@ affect their interaction with the cluster.
 - [nbd_max_devices](#nbd_max_devices)
 - [nbd_max_part](#nbd_max_part)
 
+## client_retry_interval
+
+- Type: milliseconds
+- Default: 50
+- Minimum: 10
+- Can be changed online: yes
+
+Retry time for I/O requests failed due to inactive PGs or network
+connectivity errors.
+
+## client_eio_retry_interval
+
+- Type: milliseconds
+- Default: 1000
+- Can be changed online: yes
+
+Retry time for I/O requests failed due to data corruption or unfinished
+EC object deletions (has_incomplete PG state). 0 disables such retries
+and clients are not blocked and just get EIO error code instead.
+
 ## client_max_dirty_bytes
 
 - Type: integer

docs/config/client.ru.md

@@ -9,6 +9,8 @@
 Данные параметры применяются только к клиентам Vitastor (QEMU, fio, NBD и т.п.) и
 затрагивают логику их работы с кластером.
 
+- [client_retry_interval](#client_retry_interval)
+- [client_eio_retry_interval](#client_eio_retry_interval)
 - [client_max_dirty_bytes](#client_max_dirty_bytes)
 - [client_max_dirty_ops](#client_max_dirty_ops)
 - [client_enable_writeback](#client_enable_writeback)
@@ -19,6 +21,27 @@
 - [nbd_max_devices](#nbd_max_devices)
 - [nbd_max_part](#nbd_max_part)
 
+## client_retry_interval
+
+- Тип: миллисекунды
+- Значение по умолчанию: 50
+- Минимальное значение: 10
+- Можно менять на лету: да
+
+Время повтора запросов ввода-вывода, неудачных из-за неактивных PG или
+ошибок сети.
+
+## client_eio_retry_interval
+
+- Тип: миллисекунды
+- Значение по умолчанию: 1000
+- Можно менять на лету: да
+
+Время повтора запросов ввода-вывода, неудачных из-за повреждения данных
+или незавершённых удалений EC-объектов (состояния PG has_incomplete).
+0 отключает повторы таких запросов и клиенты не блокируются, а вместо
+этого просто получают код ошибки EIO.
+
 ## client_max_dirty_bytes
 
 - Тип: целое число

docs/config/network.en.md

@@ -25,7 +25,6 @@ between clients, OSDs and etcd.
 - [peer_connect_timeout](#peer_connect_timeout)
 - [osd_idle_timeout](#osd_idle_timeout)
 - [osd_ping_timeout](#osd_ping_timeout)
-- [up_wait_retry_interval](#up_wait_retry_interval)
 - [max_etcd_attempts](#max_etcd_attempts)
 - [etcd_quick_timeout](#etcd_quick_timeout)
 - [etcd_slow_timeout](#etcd_slow_timeout)
@@ -212,17 +211,6 @@ Maximum time to wait for OSD keepalive responses. If an OSD doesn't respond
 within this time, the connection to it is dropped and a reconnection attempt
 is scheduled.
 
-## up_wait_retry_interval
-
-- Type: milliseconds
-- Default: 50
-- Minimum: 10
-- Can be changed online: yes
-
-OSDs respond to clients with a special error code when they receive I/O
-requests for a PG that's not synchronized and started. This parameter sets
-the time for the clients to wait before re-attempting such I/O requests.
-
 ## max_etcd_attempts
 
 - Type: integer

docs/config/network.ru.md

@@ -25,7 +25,6 @@
 - [peer_connect_timeout](#peer_connect_timeout)
 - [osd_idle_timeout](#osd_idle_timeout)
 - [osd_ping_timeout](#osd_ping_timeout)
-- [up_wait_retry_interval](#up_wait_retry_interval)
 - [max_etcd_attempts](#max_etcd_attempts)
 - [etcd_quick_timeout](#etcd_quick_timeout)
 - [etcd_slow_timeout](#etcd_slow_timeout)
@@ -221,19 +220,6 @@ OSD в любом случае согласовывают реальное зн
 Если OSD не отвечает за это время, соединение отключается и производится
 повторная попытка соединения.
 
-## up_wait_retry_interval
-
-- Тип: миллисекунды
-- Значение по умолчанию: 50
-- Минимальное значение: 10
-- Можно менять на лету: да
-
-Когда OSD получают от клиентов запросы ввода-вывода, относящиеся к не
-поднятым на данный момент на них PG, либо к PG в процессе синхронизации,
-они отвечают клиентам специальным кодом ошибки, означающим, что клиент
-должен некоторое время подождать перед повторением запроса. Именно это время
-ожидания задаёт данный параметр.
-
 ## max_etcd_attempts
 
 - Тип: целое число

docs/config/pool.en.md

@@ -154,8 +154,25 @@ That is, if it becomes impossible to place PG data on at least (pg_minsize)
 OSDs, PG is deactivated for both read and write. So you know that a fresh
 write always goes to at least (pg_minsize) OSDs (disks).
 
-That is, pg_size minus pg_minsize sets the number of disk failures to tolerate
-without temporary downtime (for [osd_out_time](monitor.en.md#osd_out_time)).
+For example, the difference between pg_minsize 2 and 1 in a 3-way replicated
+pool (pg_size=3) is:
+- If 2 hosts go down with pg_minsize=2, the pool becomes inactive and remains
+  inactive for [osd_out_time](monitor.en.md#osd_out_time) (10 minutes). After
+  this timeout, the monitor selects replacement hosts/OSDs and the pool comes
+  up and starts to heal. Therefore, if you don't have replacement OSDs, i.e.
+  if you only have 3 hosts with OSDs and 2 of them are down, the pool remains
+  inactive until you add or return at least 1 host (or change failure_domain
+  to "osd").
+- If 2 hosts go down with pg_minsize=1, the pool only experiences a short
+  I/O pause until the monitor notices that OSDs are down (5-10 seconds with
+  the default [etcd_report_interval](osd.en.md#etcd_report_interval)). After
+  this pause, I/O resumes, but new data is temporarily written in only 1 copy.
+  Then, after osd_out_time, the monitor also selects replacement OSDs and the
+  pool starts to heal.
+
+So, pg_minsize regulates the number of failures that a pool can tolerate
+without temporary downtime for [osd_out_time](monitor.en.md#osd_out_time),
+but at a cost of slightly reduced storage reliability.
 
 FIXME: pg_minsize behaviour may be changed in the future to only make PGs
 read-only instead of deactivating them.
@@ -168,8 +185,8 @@ read-only instead of deactivating them.
 Number of PGs for this pool. The value should be big enough for the monitor /
 LP solver to be able to optimize data placement.
 
-"Enough" is usually around 64-128 PGs per OSD, i.e. you set pg_count for pool
-to (total OSD count * 100 / pg_size). You can round it to the closest power of 2,
+"Enough" is usually around 10-100 PGs per OSD, i.e. you set pg_count for pool
+to (total OSD count * 10 / pg_size). You can round it to the closest power of 2,
 because it makes it easier to reduce or increase PG count later by dividing or
 multiplying it by 2.
 

docs/config/pool.ru.md

@@ -157,9 +157,25 @@
 OSD, PG деактивируется на чтение и запись. Иными словами, всегда известно,
 что новые блоки данных всегда записываются как минимум на pg_minsize дисков.
 
-По сути, разница pg_size и pg_minsize задаёт число отказов дисков, которые пул
-может пережить без временной (на [osd_out_time](monitor.ru.md#osd_out_time))
-остановки обслуживания.
+Для примера, разница между pg_minsize 2 и 1 в реплицированном пуле с 3 копиями
+данных (pg_size=3), проявляется следующим образом:
+- Если 2 сервера отключаются при pg_minsize=2, пул становится неактивным и
+  остаётся неактивным в течение [osd_out_time](monitor.en.md#osd_out_time)
+  (10 минут), после чего монитор назначает другие OSD/серверы на замену, пул
+  поднимается и начинает восстанавливать недостающие копии данных. Соответственно,
+  если OSD на замену нет - то есть, если у вас всего 3 сервера с OSD и 2 из них
+  недоступны - пул так и остаётся недоступным до тех пор, пока вы не вернёте
+  или не добавите хотя бы 1 сервер (или не переключите failure_domain на "osd").
+- Если 2 сервера отключаются при pg_minsize=1, ввод-вывод лишь приостанавливается
+  на короткое время, до тех пор, пока монитор не поймёт, что OSD отключены
+  (что занимает 5-10 секунд при стандартном [etcd_report_interval](osd.en.md#etcd_report_interval)).
+  После этого ввод-вывод восстанавливается, но новые данные временно пишутся
+  всего в 1 копии. Когда же проходит osd_out_time, монитор точно так же назначает
+  другие OSD на замену выбывшим и пул начинает восстанавливать копии данных.
+
+То есть, pg_minsize регулирует число отказов, которые пул может пережить без
+временной остановки обслуживания на [osd_out_time](monitor.ru.md#osd_out_time),
+но ценой немного пониженных гарантий надёжности.
 
 FIXME: Поведение pg_minsize может быть изменено в будущем с полной деактивации
 PG на перевод их в режим только для чтения.
@@ -172,8 +188,8 @@ PG на перевод их в режим только для чтения.
 Число PG для данного пула. Число должно быть достаточно большим, чтобы монитор
 мог равномерно распределить по ним данные.
 
-Обычно это означает примерно 64-128 PG на 1 OSD, т.е. pg_count можно устанавливать
-равным (общему числу OSD * 100 / pg_size). Значение можно округлить до ближайшей
+Обычно это означает примерно 10-100 PG на 1 OSD, т.е. pg_count можно устанавливать
+равным (общему числу OSD * 10 / pg_size). Значение можно округлить до ближайшей
 степени 2, чтобы потом было легче уменьшать или увеличивать число PG, умножая
 или деля его на 2.
 

docs/config/src/client.yml

@@ -1,3 +1,27 @@
+- name: client_retry_interval
+  type: ms
+  min: 10
+  default: 50
+  online: true
+  info: |
+    Retry time for I/O requests failed due to inactive PGs or network
+    connectivity errors.
+  info_ru: |
+    Время повтора запросов ввода-вывода, неудачных из-за неактивных PG или
+    ошибок сети.
+- name: client_eio_retry_interval
+  type: ms
+  default: 1000
+  online: true
+  info: |
+    Retry time for I/O requests failed due to data corruption or unfinished
+    EC object deletions (has_incomplete PG state). 0 disables such retries
+    and clients are not blocked and just get EIO error code instead.
+  info_ru: |
+    Время повтора запросов ввода-вывода, неудачных из-за повреждения данных
+    или незавершённых удалений EC-объектов (состояния PG has_incomplete).
+    0 отключает повторы таких запросов и клиенты не блокируются, а вместо
+    этого просто получают код ошибки EIO.
 - name: client_max_dirty_bytes
   type: int
   default: 33554432

docs/config/src/network.yml

@@ -243,21 +243,6 @@
     Максимальное время ожидания ответа на запрос проверки состояния соединения.
     Если OSD не отвечает за это время, соединение отключается и производится
     повторная попытка соединения.
-- name: up_wait_retry_interval
-  type: ms
-  min: 10
-  default: 50
-  online: true
-  info: |
-    OSDs respond to clients with a special error code when they receive I/O
-    requests for a PG that's not synchronized and started. This parameter sets
-    the time for the clients to wait before re-attempting such I/O requests.
-  info_ru: |
-    Когда OSD получают от клиентов запросы ввода-вывода, относящиеся к не
-    поднятым на данный момент на них PG, либо к PG в процессе синхронизации,
-    они отвечают клиентам специальным кодом ошибки, означающим, что клиент
-    должен некоторое время подождать перед повторением запроса. Именно это время
-    ожидания задаёт данный параметр.
 - name: max_etcd_attempts
   type: int
   default: 5

docs/intro/quickstart.en.md

@@ -75,18 +75,16 @@ On the monitor hosts:
 
 ## Create a pool
 
-Create pool configuration in etcd:
+Create a pool using vitastor-cli:
 
 ```
-etcdctl --endpoints=... put /vitastor/config/pools '{"1":{"name":"testpool",
-  "scheme":"replicated","pg_size":2,"pg_minsize":1,"pg_count":256,"failure_domain":"host"}}'
+vitastor-cli create-pool testpool --pg_size 2 --pg_count 256
 ```
 
 For EC pools the configuration should look like the following:
 
 ```
-etcdctl --endpoints=... put /vitastor/config/pools '{"2":{"name":"ecpool",
-  "scheme":"ec","pg_size":4,"parity_chunks":2,"pg_minsize":2,"pg_count":256,"failure_domain":"host"}}'
+vitastor-cli create-pool testpool --ec 2+2 --pg_count 256
 ```
 
 After you do this, one of the monitors will configure PGs and OSDs will start them.

docs/intro/quickstart.ru.md

@@ -77,18 +77,16 @@
 
 ## Создайте пул
 
-Создайте конфигурацию пула с помощью etcdctl:
+Создайте пул с помощью vitastor-cli:
 
 ```
-etcdctl --endpoints=... put /vitastor/config/pools '{"1":{"name":"testpool",
-  "scheme":"replicated","pg_size":2,"pg_minsize":1,"pg_count":256,"failure_domain":"host"}}'
+vitastor-cli create-pool testpool --pg_size 2 --pg_count 256
 ```
 
 Для пулов с кодами коррекции ошибок конфигурация должна выглядеть примерно так:
 
 ```
-etcdctl --endpoints=... put /vitastor/config/pools '{"2":{"name":"ecpool",
-  "scheme":"ec","pg_size":4,"parity_chunks":2,"pg_minsize":2,"pg_count":256,"failure_domain":"host"}}'
+vitastor-cli create-pool testpool --ec 2+2 --pg_count 256
 ```
 
 После этого один из мониторов должен сконфигурировать PG, а OSD должны запустить их.

docs/usage/cli.en.md

@@ -24,6 +24,10 @@ It supports the following commands:
 - [fix](#fix)
 - [alloc-osd](#alloc-osd)
 - [rm-osd](#rm-osd)
+- [create-pool](#create-pool)
+- [modify-pool](#modify-pool)
+- [ls-pools](#ls-pools)
+- [rm-pool](#rm-pool)
 
 Global options:
 
@@ -131,19 +135,18 @@ See also about [how to export snapshots](qemu.en.md#exporting-snapshots).
 
 ## modify
 
-`vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force]`
+`vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force] [--down-ok]`
 
 Rename, resize image or change its readonly status. Images with children can't be made read-write.
 If the new size is smaller than the old size, extra data will be purged.
 You should resize file system in the image, if present, before shrinking it.
 
-```
--f|--force  Proceed with shrinking or setting readwrite flag even if the image has children.
-```
+| `-f|--force` | Proceed with shrinking or setting readwrite flag even if the image has children. |
+| `--down-ok`  | Proceed with shrinking even if some data will be left on unavailable OSDs.       |
 
 ## rm
 
-`vitastor-cli rm <from> [<to>] [--writers-stopped]`
+`vitastor-cli rm <from> [<to>] [--writers-stopped] [--down-ok]`
 
 Remove `<from>` or all layers between `<from>` and `<to>` (`<to>` must be a child of `<from>`),
 rebasing all their children accordingly. --writers-stopped allows merging to be a bit
@@ -151,6 +154,10 @@ more effective in case of a single 'slim' read-write child and 'fat' removed par
 the child is merged into parent and parent is renamed to child in that case.
 In other cases parent layers are always merged into children.
 
+Other options:
+
+| `--down-ok` | Continue deletion/merging even if some data will be left on unavailable OSDs. |
+
 ## flatten
 
 `vitastor-cli flatten <layer>`
@@ -238,3 +245,84 @@ Refuses to remove OSDs with data without `--force` and `--allow-data-loss`.
 
 With `--dry-run` only checks if deletion is possible without data loss and
 redundancy degradation.
+
+## create-pool
+
+`vitastor-cli create-pool|pool-create <name> (-s <pg_size>|--ec <N>+<K>) -n <pg_count> [OPTIONS]`
+
+Create a pool. Required parameters:
+
+| `-s|--pg_size R`  | Number of replicas for replicated pools                                               |
+| `--ec N+K`        | Number of data (N) and parity (K) chunks for erasure-coded pools                      |
+| `-n|--pg_count N` | PG count for the new pool (start with 10*<OSD count>/pg_size rounded to a power of 2) |
+
+Optional parameters:
+
+| `--pg_minsize <number>`        | R or N+K minus number of failures to tolerate without downtime ([details](../config/pool.en.md#pg_minsize)) |
+| `--failure_domain host`        | Failure domain: host, osd or a level from placement_levels. Default: host  |
+| `--root_node <node>`           | Put pool only on child OSDs of this placement tree node                    |
+| `--osd_tags <tag>[,<tag>]...`  | Put pool only on OSDs tagged with all specified tags                       |
+| `--block_size 128k`            | Put pool only on OSDs with this data block size                            |
+| `--bitmap_granularity 4k`      | Put pool only on OSDs with this logical sector size                        |
+| `--immediate_commit none`      | Put pool only on OSDs with this or larger immediate_commit (none < small < all) |
+| `--primary_affinity_tags tags` | Prefer to put primary copies on OSDs with all specified tags               |
+| `--scrub_interval <time>`      | Enable regular scrubbing for this pool. Format: number + unit s/m/h/d/M/y  |
+| `--pg_stripe_size <number>`    | Increase object grouping stripe                                            |
+| `--max_osd_combinations 10000` | Maximum number of random combinations for LP solver input                  |
+| `--wait`                       | Wait for the new pool to come online                                       |
+| `-f|--force`                   | Do not check that cluster has enough OSDs to create the pool               |
+
+See also [Pool configuration](../config/pool.en.md) for detailed parameter descriptions.
+
+Examples:
+
+`vitastor-cli create-pool test_x4 -s 4 -n 32`
+
+`vitastor-cli create-pool test_ec42 --ec 4+2 -n 32`
+
+## modify-pool
+
+`vitastor-cli modify-pool|pool-modify <id|name> [--name <new_name>] [PARAMETERS...]`
+
+Modify an existing pool. Modifiable parameters:
+
+```
+[-s|--pg_size <number>] [--pg_minsize <number>] [-n|--pg_count <count>]
+[--failure_domain <level>] [--root_node <node>] [--osd_tags <tags>]
+[--max_osd_combinations <number>] [--primary_affinity_tags <tags>] [--scrub_interval <time>]
+```
+
+Non-modifiable parameters (changing them WILL lead to data loss):
+
+```
+[--block_size <size>] [--bitmap_granularity <size>]
+[--immediate_commit <all|small|none>] [--pg_stripe_size <size>]
+```
+
+These, however, can still be modified with -f|--force.
+
+See [create-pool](#create-pool) for parameter descriptions.
+
+Examples:
+
+`vitastor-cli modify-pool pool_A --name pool_B`
+
+`vitastor-cli modify-pool 2 --pg_size 4 -n 128`
+
+## rm-pool
+
+`vitastor-cli rm-pool|pool-rm [--force] <id|name>`
+
+Remove a pool. Refuses to remove pools with images without `--force`.
+
+## ls-pools
+
+`vitastor-cli ls-pools|pool-ls|ls-pool|pools [-l] [--detail] [--sort FIELD] [-r] [-n N] [--stats] [<glob> ...]`
+
+List pools (only matching <glob> patterns if passed).
+
+| `-l|--long`     | Also report I/O statistics                            |
+| `--detail`      | Use list format (not table), show all details         |
+| `--sort FIELD`  | Sort by specified field (see fields in --json output) |
+| `-r|--reverse`  | Sort in descending order                              |
+| `-n|--count N`  | Only list first N items                               |

docs/usage/cli.ru.md

@@ -23,6 +23,10 @@ vitastor-cli - интерфейс командной строки для адм
 - [merge-data](#merge-data)
 - [alloc-osd](#alloc-osd)
 - [rm-osd](#rm-osd)
+- [create-pool](#create-pool)
+- [modify-pool](#modify-pool)
+- [ls-pools](#ls-pools)
+- [rm-pool](#rm-pool)
 
 Глобальные опции:
 
@@ -85,8 +89,8 @@ kaveri    2/1     32   0 B      10 G    0 B        100%    0%
 
 `vitastor-cli ls [-l] [-p POOL] [--sort FIELD] [-r] [-n N] [<glob> ...]`
 
-Показать список образов, если переданы шаблоны `<glob>`, то только с именами,
-соответствующими этим шаблонам (стандартные ФС-шаблоны с * и ?).
+Показать список образов, если передан(ы) шаблон(ы) `<glob>`, то только с именами,
+соответствующими одному из шаблонов (стандартные ФС-шаблоны с * и ?).
 
 Опции:
 
@@ -132,7 +136,7 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
 
 ## modify
 
-`vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force]`
+`vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force] [--down-ok]`
 
 Изменить размер, имя образа или флаг "только для чтения". Снимать флаг "только для чтения"
 и уменьшать размер образов, у которых есть дочерние клоны, без `--force` нельзя.
@@ -140,13 +144,12 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
 Если новый размер меньше старого, "лишние" данные будут удалены, поэтому перед уменьшением
 образа сначала уменьшите файловую систему в нём.
 
-```
--f|--force  Разрешить уменьшение или перевод в чтение-запись образа, у которого есть клоны.
-```
+| -f|--force | Разрешить уменьшение или перевод в чтение-запись образа, у которого есть клоны.        |
+| --down-ok  | Разрешить уменьшение, даже если часть данных останется неудалённой на недоступных OSD. |
 
 ## rm
 
-`vitastor-cli rm <from> [<to>] [--writers-stopped]`
+`vitastor-cli rm <from> [<to>] [--writers-stopped] [--down-ok]`
 
 Удалить образ `<from>` или все слои от `<from>` до `<to>` (`<to>` должен быть дочерним
 образом `<from>`), одновременно меняя родительские образы их клонов (если таковые есть).
@@ -158,6 +161,10 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
 
 В других случаях родительские слои вливаются в дочерние.
 
+Другие опции:
+
+| `--down-ok` | Продолжать удаление/слияние, даже если часть данных останется неудалённой на недоступных OSD. |
+
 ## flatten
 
 `vitastor-cli flatten <layer>`
@@ -255,3 +262,85 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
 
 С опцией `--dry-run` только проверяет, возможно ли удаление без потери данных и деградации
 избыточности.
+
+## create-pool
+
+`vitastor-cli create-pool|pool-create <name> (-s <pg_size>|--ec <N>+<K>) -n <pg_count> [OPTIONS]`
+
+Создать пул. Обязательные параметры:
+
+| `-s|--pg_size R`  | Число копий данных для реплицированных пулов                                                |
+| `--ec N+K`        | Число частей данных (N) и чётности (K) для пулов с кодами коррекции ошибок                  |
+| `-n|--pg_count N` | Число PG для нового пула (начните с 10*<число OSD>/pg_size, округлённого до степени двойки) |
+
+Необязательные параметры:
+
+| `--pg_minsize <number>`        | (R или N+K) минус число разрешённых отказов без остановки пула ([подробнее](../config/pool.ru.md#pg_minsize)) |
+| `--failure_domain host`        | Домен отказа: host, osd или другой из placement_levels. По умолчанию: host |
+| `--root_node <node>`           | Использовать для пула только дочерние OSD этого узла дерева размещения     |
+| `--osd_tags <tag>[,<tag>]...`  | ...только OSD со всеми заданными тегами                                    |
+| `--block_size 128k`            | ...только OSD с данным размером блока                                      |
+| `--bitmap_granularity 4k`      | ...только OSD с данным размером логического сектора                        |
+| `--immediate_commit none`      | ...только OSD с этим или большим immediate_commit (none < small < all)     |
+| `--primary_affinity_tags tags` | Предпочитать OSD со всеми данными тегами для роли первичных                |
+| `--scrub_interval <time>`      | Включить скрабы с заданным интервалом времени (число + единица s/m/h/d/M/y) |
+| `--pg_stripe_size <number>`    | Увеличить блок группировки объектов по PG                                  |
+| `--max_osd_combinations 10000` | Максимальное число случайных комбинаций OSD для ЛП-солвера                 |
+| `--wait`                       | Подождать, пока новый пул будет активирован                                |
+| `-f|--force`                   | Не проверять, что в кластере достаточно доменов отказа для создания пула   |
+
+Подробно о параметрах см. [Конфигурация пулов](../config/pool.ru.md).
+
+Примеры:
+
+`vitastor-cli create-pool test_x4 -s 4 -n 32`
+
+`vitastor-cli create-pool test_ec42 --ec 4+2 -n 32`
+
+## modify-pool
+
+`vitastor-cli modify-pool|pool-modify <id|name> [--name <new_name>] [PARAMETERS...]`
+
+Изменить настройки существующего пула. Изменяемые параметры:
+
+```
+[-s|--pg_size <number>] [--pg_minsize <number>] [-n|--pg_count <count>]
+[--failure_domain <level>] [--root_node <node>] [--osd_tags <tags>]
+[--max_osd_combinations <number>] [--primary_affinity_tags <tags>] [--scrub_interval <time>]
+```
+
+Неизменяемые параметры (их изменение ПРИВЕДЁТ к потере данных):
+
+```
+[--block_size <size>] [--bitmap_granularity <size>]
+[--immediate_commit <all|small|none>] [--pg_stripe_size <size>]
+```
+
+Эти параметры можно изменить, только если явно передать опцию -f или --force.
+
+Описания параметров смотрите в [create-pool](#create-pool).
+
+Примеры:
+
+`vitastor-cli modify-pool pool_A --name pool_B`
+
+`vitastor-cli modify-pool 2 --pg_size 4 -n 128`
+
+## rm-pool
+
+`vitastor-cli rm-pool|pool-rm [--force] <id|name>`
+
+Удалить пул. Отказывается удалять пул, в котором ещё есть образы, без `--force`.
+
+## ls-pools
+
+`vitastor-cli ls-pools|pool-ls|ls-pool|pools [-l] [--detail] [--sort FIELD] [-r] [-n N] [--stats] [<glob> ...]`
+
+Показать список пулов. Если передан(ы) шаблон(ы) `<glob>`, то только с именами,
+соответствующими одному из шаблонов (стандартные ФС-шаблоны с * и ?).
+
+| `-l|--long`     | Вывести также статистику ввода-вывода                      |
+| `--detail`      | Максимально подробный вывод в виде списка (а не таблицы)   |
+| `--sort FIELD`  | Сортировать по заданному полю (поля см. в выводе с --json) |
+| `-r|--reverse`  | Сортировать в обратном порядке                             |
+| `-n|--count N`  | Выводить только первые N записей                           |

mon/mon.js

@@ -86,13 +86,14 @@ const etcd_tree = {
             client_max_buffered_bytes: 33554432,
             client_max_buffered_ops: 1024,
             client_max_writeback_iodepth: 256,
+            client_retry_interval: 50, // ms. min: 10
+            client_eio_retry_interval: 1000, // ms
             // client and osd - configurable online
             log_level: 0,
             peer_connect_interval: 5, // seconds. min: 1
             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
             max_etcd_attempts: 5,
             etcd_quick_timeout: 1000, // ms
             etcd_slow_timeout: 5000, // ms

mon/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vitastor-mon",
-  "version": "1.4.7",
+  "version": "1.4.8",
   "description": "Vitastor SDS monitor service",
   "main": "mon-main.js",
   "scripts": {

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 = '1.4.7'
+VERSION = '1.4.8'
 
 LOG = logging.getLogger(__name__)
 

patches/libvirt-8.0-vitastor.diff

@@ -0,0 +1,692 @@
+commit d85024bd803b3b91f15578ed22de4ce31856626f
+Author: Vitaliy Filippov <vitalif@yourcmc.ru>
+Date:   Wed Jan 24 18:07:43 2024 +0300
+
+    Add Vitastor support
+
+diff --git a/docs/schemas/domaincommon.rng b/docs/schemas/domaincommon.rng
+index 7fa5c2b8b5..2d77f391e7 100644
+--- a/docs/schemas/domaincommon.rng
++++ b/docs/schemas/domaincommon.rng
+@@ -1898,6 +1898,35 @@
+     </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">
+@@ -2154,6 +2183,7 @@
+       <ref name="diskSourceNetworkProtocolSimple"/>
+       <ref name="diskSourceNetworkProtocolVxHS"/>
+       <ref name="diskSourceNetworkProtocolNFS"/>
++      <ref name="diskSourceNetworkProtocolVitastor"/>
+     </choice>
+   </define>
+ 
+diff --git a/include/libvirt/libvirt-storage.h b/include/libvirt/libvirt-storage.h
+index f89856b93e..a8cb9387e2 100644
+--- a/include/libvirt/libvirt-storage.h
++++ b/include/libvirt/libvirt-storage.h
+@@ -246,6 +246,7 @@ typedef enum {
+     VIR_CONNECT_LIST_STORAGE_POOLS_ZFS           = 1 << 17,
+     VIR_CONNECT_LIST_STORAGE_POOLS_VSTORAGE      = 1 << 18,
+     VIR_CONNECT_LIST_STORAGE_POOLS_ISCSI_DIRECT  = 1 << 19,
++    VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR      = 1 << 20,
+ } virConnectListAllStoragePoolsFlags;
+ 
+ int                     virConnectListAllStoragePools(virConnectPtr conn,
+diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c
+index 5691b8d2d5..6669e8451d 100644
+--- a/src/conf/domain_conf.c
++++ b/src/conf/domain_conf.c
+@@ -8293,7 +8293,8 @@ 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)
+@@ -31267,6 +31268,7 @@ 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 a4271f1247..621c1b7b31 100644
+--- a/src/conf/domain_validate.c
++++ b/src/conf/domain_validate.c
+@@ -508,7 +508,7 @@ 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) {
+@@ -517,11 +517,15 @@ virDomainDiskDefValidateSourceChainOne(const virStorageSource *src)
+                              "only with 'rbd' disks"));
+             return -1;
+         }
+-
++    }
++    /* config files are currently supported only with rbd and vitastor: */
++    if (virStorageSourceGetActualType(src) != VIR_STORAGE_TYPE_NETWORK &&
++        src->protocol != VIR_STORAGE_NET_PROTOCOL_RBD &&
++        src->protocol != VIR_STORAGE_NET_PROTOCOL_VITASTOR) {
+         if (src->configFile) {
+             virReportError(VIR_ERR_XML_ERROR, "%s",
+                            _("<config> element is currently supported "
+-                             "only with 'rbd' disks"));
++                             "only with 'rbd' and 'vitastor' disks"));
+             return -1;
+         }
+     }
+diff --git a/src/conf/storage_conf.c b/src/conf/storage_conf.c
+index 6690d26ffd..2255df9d28 100644
+--- a/src/conf/storage_conf.c
++++ b/src/conf/storage_conf.c
+@@ -60,7 +60,7 @@ VIR_ENUM_IMPL(virStoragePool,
+               "logical", "disk", "iscsi",
+               "iscsi-direct", "scsi", "mpath",
+               "rbd", "sheepdog", "gluster",
+-              "zfs", "vstorage",
++              "zfs", "vstorage", "vitastor",
+ );
+ 
+ VIR_ENUM_IMPL(virStoragePoolFormatFileSystem,
+@@ -246,6 +246,18 @@ 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 |
+@@ -546,6 +558,11 @@ 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;
+@@ -1176,6 +1193,7 @@ 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 aaecf138d6..97172db38b 100644
+--- a/src/conf/storage_conf.h
++++ b/src/conf/storage_conf.h
+@@ -106,6 +106,7 @@ 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;
+@@ -466,6 +467,7 @@ 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 d42f715f26..29d8da3d10 100644
+--- a/src/conf/storage_source_conf.c
++++ b/src/conf/storage_source_conf.c
+@@ -86,6 +86,7 @@ VIR_ENUM_IMPL(virStorageNetProtocol,
+               "ssh",
+               "vxhs",
+               "nfs",
++              "vitastor",
+ );
+ 
+ 
+@@ -1265,6 +1266,7 @@ 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 c4a026881c..67568e9181 100644
+--- a/src/conf/storage_source_conf.h
++++ b/src/conf/storage_source_conf.h
+@@ -128,6 +128,7 @@ typedef enum {
+     VIR_STORAGE_NET_PROTOCOL_SSH,
+     VIR_STORAGE_NET_PROTOCOL_VXHS,
+     VIR_STORAGE_NET_PROTOCOL_NFS,
++    VIR_STORAGE_NET_PROTOCOL_VITASTOR,
+ 
+     VIR_STORAGE_NET_PROTOCOL_LAST
+ } virStorageNetProtocol;
+diff --git a/src/conf/virstorageobj.c b/src/conf/virstorageobj.c
+index 02903ac487..504df599fb 100644
+--- a/src/conf/virstorageobj.c
++++ b/src/conf/virstorageobj.c
+@@ -1481,6 +1481,7 @@ virStoragePoolObjSourceFindDuplicateCb(const void *payload,
+             return 1;
+         break;
+ 
++    case VIR_STORAGE_POOL_VITASTOR:
+     case VIR_STORAGE_POOL_RBD:
+     case VIR_STORAGE_POOL_LAST:
+         break;
+@@ -1978,6 +1979,8 @@ 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 cbc522b300..b4760fa58d 100644
+--- a/src/libvirt-storage.c
++++ b/src/libvirt-storage.c
+@@ -92,6 +92,7 @@ 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 1ac6253ad7..abe4587f94 100644
+--- a/src/libxl/libxl_conf.c
++++ b/src/libxl/libxl_conf.c
+@@ -962,6 +962,7 @@ 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 7604e3d534..6453bb9776 100644
+--- a/src/libxl/xen_xl.c
++++ b/src/libxl/xen_xl.c
+@@ -1506,6 +1506,7 @@ 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 e5ff653a60..884ecc79ea 100644
+--- a/src/qemu/qemu_block.c
++++ b/src/qemu/qemu_block.c
+@@ -943,6 +943,38 @@ 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 (virJSONValueObjectCreate(&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)
+ {
+@@ -1233,6 +1265,12 @@ 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)))
+@@ -2244,6 +2282,7 @@ 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:
+@@ -2626,6 +2665,12 @@ 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_command.c b/src/qemu/qemu_command.c
+index d822533ccb..afe2087303 100644
+--- a/src/qemu/qemu_command.c
++++ b/src/qemu/qemu_command.c
+@@ -1723,6 +1723,43 @@ qemuBuildNetworkDriveStr(virStorageSource *src,
+             ret = virBufferContentAndReset(&buf);
+             break;
+ 
++        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
++            if (strchr(src->path, ':')) {
++                virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
++                               _("':' not allowed in Vitastor source volume name '%s'"),
++                               src->path);
++                return NULL;
++            }
++
++            virBufferStrcat(&buf, "vitastor:image=", src->path, NULL);
++
++            if (src->nhosts > 0) {
++                virBufferAddLit(&buf, ":etcd-host=");
++                for (i = 0; i < src->nhosts; i++) {
++                    if (i)
++                        virBufferAddLit(&buf, ",");
++
++                    /* assume host containing : is ipv6 */
++                    if (strchr(src->hosts[i].name, ':'))
++                        virBufferEscape(&buf, '\\', ":", "[%s]",
++                                        src->hosts[i].name);
++                    else
++                        virBufferAsprintf(&buf, "%s", src->hosts[i].name);
++
++                    if (src->hosts[i].port)
++                        virBufferAsprintf(&buf, "\\:%u", src->hosts[i].port);
++                }
++            }
++
++            if (src->configFile)
++                virBufferEscape(&buf, '\\', ":", ":config-path=%s", src->configFile);
++
++            if (src->query)
++                virBufferEscape(&buf, '\\', ":", ":etcd-prefix=%s", src->query);
++
++            ret = virBufferContentAndReset(&buf);
++            break;
++
+         case VIR_STORAGE_NET_PROTOCOL_VXHS:
+             virReportError(VIR_ERR_INTERNAL_ERROR, "%s",
+                            _("VxHS protocol does not support URI syntax"));
+diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c
+index a8401bac30..3dc1fe6db0 100644
+--- a/src/qemu/qemu_domain.c
++++ b/src/qemu/qemu_domain.c
+@@ -4731,7 +4731,8 @@ 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;
+@@ -9919,6 +9920,7 @@ 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 f92e00f9c0..854a3fbc90 100644
+--- a/src/qemu/qemu_snapshot.c
++++ b/src/qemu/qemu_snapshot.c
+@@ -393,6 +393,7 @@ 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:
+@@ -485,6 +486,7 @@ qemuSnapshotPrepareDiskExternalActive(virDomainObj *vm,
+         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_ISCSI:
+         case VIR_STORAGE_NET_PROTOCOL_HTTP:
+@@ -638,6 +640,7 @@ 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 4df2c75a2b..5a5e48ef71 100644
+--- a/src/storage/storage_driver.c
++++ b/src/storage/storage_driver.c
+@@ -1643,6 +1643,7 @@ 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 e48ae725ab..2017ccc88c 100644
+--- a/src/storage_file/storage_source_backingstore.c
++++ b/src/storage_file/storage_source_backingstore.c
+@@ -284,6 +284,75 @@ virStorageSourceParseRBDColonString(const char *rbdstr,
+ }
+ 
+ 
++static int
++virStorageSourceParseVitastorColonString(const char *colonstr,
++                                         virStorageSource *src)
++{
++    char *p, *e, *next;
++    g_autofree char *options = NULL;
++
++    /* optionally skip the "vitastor:" prefix if provided */
++    if (STRPREFIX(colonstr, "vitastor:"))
++        colonstr += strlen("vitastor:");
++
++    options = g_strdup(colonstr);
++
++    p = options;
++    while (*p) {
++        /* find : delimiter or end of string */
++        for (e = p; *e && *e != ':'; ++e) {
++            if (*e == '\\') {
++                e++;
++                if (*e == '\0')
++                    break;
++            }
++        }
++        if (*e == '\0') {
++            next = e;    /* last kv pair */
++        } else {
++            next = e + 1;
++            *e = '\0';
++        }
++
++        if (STRPREFIX(p, "image=")) {
++            src->path = g_strdup(p + strlen("image="));
++        } else if (STRPREFIX(p, "etcd-prefix=")) {
++            src->query = g_strdup(p + strlen("etcd-prefix="));
++        } else if (STRPREFIX(p, "config-path=")) {
++            src->configFile = g_strdup(p + strlen("config-path="));
++        } else if (STRPREFIX(p, "etcd-host=")) {
++            char *h, *sep;
++
++            h = p + strlen("etcd-host=");
++            while (h < e) {
++                for (sep = h; sep < e; ++sep) {
++                    if (*sep == '\\' && (sep[1] == ',' ||
++                                         sep[1] == ';' ||
++                                         sep[1] == ' ')) {
++                        *sep = '\0';
++                        sep += 2;
++                        break;
++                    }
++                }
++
++                if (virStorageSourceRBDAddHost(src, h) < 0)
++                    return -1;
++
++                h = sep;
++            }
++        }
++
++        p = next;
++    }
++
++    if (!src->path) {
++        return -1;
++    }
++
++    return 0;
++}
++
++
+ static int
+ virStorageSourceParseNBDColonString(const char *nbdstr,
+                                     virStorageSource *src)
+@@ -396,6 +465,11 @@ virStorageSourceParseBackingColon(virStorageSource *src,
+             return -1;
+         break;
+ 
++    case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
++        if (virStorageSourceParseVitastorColonString(path, src) < 0)
++            return -1;
++        break;
++
+     case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
+     case VIR_STORAGE_NET_PROTOCOL_LAST:
+     case VIR_STORAGE_NET_PROTOCOL_NONE:
+@@ -984,6 +1058,54 @@ virStorageSourceParseBackingJSONRBD(virStorageSource *src,
+     return 0;
+ }
+ 
++static int
++virStorageSourceParseBackingJSONVitastor(virStorageSource *src,
++                                         virJSONValue *json,
++                                         const char *jsonstr G_GNUC_UNUSED,
++                                         int opaque G_GNUC_UNUSED)
++{
++    const char *filename;
++    const char *image = virJSONValueObjectGetString(json, "image");
++    const char *conf = virJSONValueObjectGetString(json, "config-path");
++    const char *etcd_prefix = virJSONValueObjectGetString(json, "etcd-prefix");
++    virJSONValue *servers = virJSONValueObjectGetArray(json, "server");
++    size_t nservers;
++    size_t i;
++
++    src->type = VIR_STORAGE_TYPE_NETWORK;
++    src->protocol = VIR_STORAGE_NET_PROTOCOL_VITASTOR;
++
++    /* legacy syntax passed via 'filename' option */
++    if ((filename = virJSONValueObjectGetString(json, "filename")))
++        return virStorageSourceParseVitastorColonString(filename, src);
++
++    if (!image) {
++        virReportError(VIR_ERR_INVALID_ARG, "%s",
++                       _("missing image name in Vitastor backing volume "
++                         "JSON specification"));
++        return -1;
++    }
++
++    src->path = g_strdup(image);
++    src->configFile = g_strdup(conf);
++    src->query = g_strdup(etcd_prefix);
++
++    if (servers) {
++        nservers = virJSONValueArraySize(servers);
++
++        src->hosts = g_new0(virStorageNetHostDef, nservers);
++        src->nhosts = nservers;
++
++        for (i = 0; i < nservers; i++) {
++            if (virStorageSourceParseBackingJSONInetSocketAddress(src->hosts + i,
++                                                                  virJSONValueArrayGet(servers, i)) < 0)
++                return -1;
++        }
++    }
++
++    return 0;
++}
++
+ static int
+ virStorageSourceParseBackingJSONRaw(virStorageSource *src,
+                                     virJSONValue *json,
+@@ -1162,6 +1284,7 @@ static const struct virStorageSourceJSONDriverParser jsonParsers[] = {
+     {"sheepdog", false, virStorageSourceParseBackingJSONSheepdog, 0},
+     {"ssh", false, virStorageSourceParseBackingJSONSSH, 0},
+     {"rbd", false, virStorageSourceParseBackingJSONRBD, 0},
++    {"vitastor", false, virStorageSourceParseBackingJSONVitastor, 0},
+     {"raw", true, virStorageSourceParseBackingJSONRaw, 0},
+     {"nfs", false, virStorageSourceParseBackingJSONNFS, 0},
+     {"vxhs", false, virStorageSourceParseBackingJSONVxHS, 0},
+diff --git a/src/test/test_driver.c b/src/test/test_driver.c
+index 0e93b79922..b4d33f5f56 100644
+--- a/src/test/test_driver.c
++++ b/src/test/test_driver.c
+@@ -7367,6 +7367,7 @@ 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 449b745519..7f95cc8e08 100644
+--- a/tests/storagepoolxml2argvtest.c
++++ b/tests/storagepoolxml2argvtest.c
+@@ -68,6 +68,7 @@ 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 d391257f6e..46799c4a90 100644
+--- a/tools/virsh-pool.c
++++ b/tools/virsh-pool.c
+@@ -1213,6 +1213,9 @@ cmdPoolList(vshControl *ctl, const vshCmd *cmd G_GNUC_UNUSED)
+             case VIR_STORAGE_POOL_VSTORAGE:
+                 flags |= VIR_CONNECT_LIST_STORAGE_POOLS_VSTORAGE;
+                 break;
++            case VIR_STORAGE_POOL_VITASTOR:
++                flags |= VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR;
++                break;
+             case VIR_STORAGE_POOL_LAST:
+                 break;
+             }

rpm/build-tarball.sh

@@ -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-1.4.7/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-1.4.7$(rpm --eval '%dist').tar.gz *
+tar --transform 's#^#vitastor-1.4.8/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-1.4.8$(rpm --eval '%dist').tar.gz *

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-1.4.7.el7.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-1.4.8.el7.tar.gz ~/rpmbuild/SOURCES; \
     cp vitastor-el7.spec ~/rpmbuild/SPECS/vitastor.spec; \
     cd ~/rpmbuild/SPECS/; \
     rpmbuild -ba vitastor.spec; \

rpm/vitastor-el7.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        1.4.7
+Version:        1.4.8
 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-1.4.7.el7.tar.gz
+Source0:        vitastor-1.4.8.el7.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

rpm/vitastor-el8.Dockerfile

@@ -35,7 +35,7 @@ ADD . /root/vitastor
 RUN set -e; \
     cd /root/vitastor/rpm; \
     sh build-tarball.sh; \
-    cp /root/vitastor-1.4.7.el8.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-1.4.8.el8.tar.gz ~/rpmbuild/SOURCES; \
     cp vitastor-el8.spec ~/rpmbuild/SPECS/vitastor.spec; \
     cd ~/rpmbuild/SPECS/; \
     rpmbuild -ba vitastor.spec; \

rpm/vitastor-el8.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        1.4.7
+Version:        1.4.8
 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-1.4.7.el8.tar.gz
+Source0:        vitastor-1.4.8.el8.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

rpm/vitastor-el9.Dockerfile

@@ -18,7 +18,7 @@ ADD . /root/vitastor
 RUN set -e; \
     cd /root/vitastor/rpm; \
     sh build-tarball.sh; \
-    cp /root/vitastor-1.4.7.el9.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-1.4.8.el9.tar.gz ~/rpmbuild/SOURCES; \
     cp vitastor-el9.spec ~/rpmbuild/SPECS/vitastor.spec; \
     cd ~/rpmbuild/SPECS/; \
     rpmbuild -ba vitastor.spec; \

rpm/vitastor-el9.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        1.4.7
+Version:        1.4.8
 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-1.4.7.el9.tar.gz
+Source0:        vitastor-1.4.8.el9.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

src/CMakeLists.txt

@@ -16,7 +16,7 @@ if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
 	set(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
 endif()
 
-add_definitions(-DVERSION="1.4.7")
+add_definitions(-DVERSION="1.4.8")
 add_definitions(-D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -Wall -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith -fdiagnostics-color=always -fno-omit-frame-pointer -I ${CMAKE_SOURCE_DIR}/src)
 add_link_options(-fno-omit-frame-pointer)
 if (${WITH_ASAN})
@@ -145,7 +145,6 @@ add_library(vitastor_client SHARED
 	cli_status.cpp
 	cli_describe.cpp
 	cli_fix.cpp
-	cli_df.cpp
 	cli_ls.cpp
 	cli_create.cpp
 	cli_modify.cpp
@@ -154,6 +153,11 @@ add_library(vitastor_client SHARED
 	cli_rm_data.cpp
 	cli_rm.cpp
 	cli_rm_osd.cpp
+	cli_pool_cfg.cpp
+	cli_pool_create.cpp
+	cli_pool_ls.cpp
+	cli_pool_modify.cpp
+	cli_pool_rm.cpp
 )
 set_target_properties(vitastor_client PROPERTIES PUBLIC_HEADER "vitastor_c.h")
 target_link_libraries(vitastor_client
@@ -181,6 +185,25 @@ 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

src/cli.cpp

@@ -46,18 +46,21 @@ static const char* help_text =
     "vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>\n"
     "  Create a snapshot of image <name>. May be used live if only a single writer is active.\n"
     "\n"
-    "vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force]\n"
+    "vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force] [--down-ok]\n"
     "  Rename, resize image or change its readonly status. Images with children can't be made read-write.\n"
     "  If the new size is smaller than the old size, extra data will be purged.\n"
     "  You should resize file system in the image, if present, before shrinking it.\n"
     "  -f|--force  Proceed with shrinking or setting readwrite flag even if the image has children.\n"
+    "  --down-ok   Proceed with shrinking even if some data will be left on unavailable OSDs.\n"
     "\n"
-    "vitastor-cli rm <from> [<to>] [--writers-stopped]\n"
+    "vitastor-cli rm <from> [<to>] [--writers-stopped] [--down-ok]\n"
     "  Remove <from> or all layers between <from> and <to> (<to> must be a child of <from>),\n"
     "  rebasing all their children accordingly. --writers-stopped allows merging to be a bit\n"
     "  more effective in case of a single 'slim' read-write child and 'fat' removed parent:\n"
     "  the child is merged into parent and parent is renamed to child in that case.\n"
     "  In other cases parent layers are always merged into children.\n"
+    "  Other options:\n"
+    "  --down-ok  Continue deletion/merging even if some data will be left on unavailable OSDs.\n"
     "\n"
     "vitastor-cli flatten <layer>\n"
     "  Flatten a layer, i.e. merge data and detach it from parents.\n"
@@ -113,6 +116,54 @@ static const char* help_text =
     "  With --dry-run only checks if deletion is possible without data loss and\n"
     "  redundancy degradation.\n"
     "\n"
+    "vitastor-cli create-pool|pool-create <name> (-s <pg_size>|--ec <N>+<K>) -n <pg_count> [OPTIONS]\n"
+    "  Create a pool. Required parameters:\n"
+    "    -s|--pg_size R   Number of replicas for replicated pools\n"
+    "    --ec N+K         Number of data (N) and parity (K) chunks for erasure-coded pools\n"
+    "    -n|--pg_count N  PG count for the new pool (start with 10*<OSD count>/pg_size rounded to a power of 2)\n"
+    "  Optional parameters:\n"
+    "    --pg_minsize <number>         R or N+K minus number of failures to tolerate without downtime\n"
+    "    --failure_domain host         Failure domain: host, osd or a level from placement_levels. Default: host\n"
+    "    --root_node <node>            Put pool only on child OSDs of this placement tree node\n"
+    "    --osd_tags <tag>[,<tag>]...   Put pool only on OSDs tagged with all specified tags\n"
+    "    --block_size 128k             Put pool only on OSDs with this data block size\n"
+    "    --bitmap_granularity 4k       Put pool only on OSDs with this logical sector size\n"
+    "    --immediate_commit none       Put pool only on OSDs with this or larger immediate_commit (none < small < all)\n"
+    "    --primary_affinity_tags tags  Prefer to put primary copies on OSDs with all specified tags\n"
+    "    --scrub_interval <time>       Enable regular scrubbing for this pool. Format: number + unit s/m/h/d/M/y\n"
+    "    --pg_stripe_size <number>     Increase object grouping stripe\n"
+    "    --max_osd_combinations 10000  Maximum number of random combinations for LP solver input\n"
+    "    --wait                        Wait for the new pool to come online\n"
+    "    -f|--force                    Do not check that cluster has enough OSDs to create the pool\n"
+    "  Examples:\n"
+    "    vitastor-cli create-pool test_x4 -s 4 -n 32\n"
+    "    vitastor-cli create-pool test_ec42 --ec 4+2 -n 32\n"
+    "\n"
+    "vitastor-cli modify-pool|pool-modify <id|name> [--name <new_name>] [PARAMETERS...]\n"
+    "  Modify an existing pool. Modifiable parameters:\n"
+    "    [-s|--pg_size <number>] [--pg_minsize <number>] [-n|--pg_count <count>]\n"
+    "    [--failure_domain <level>] [--root_node <node>] [--osd_tags <tags>]\n"
+    "    [--max_osd_combinations <number>] [--primary_affinity_tags <tags>] [--scrub_interval <time>]\n"
+    "  Non-modifiable parameters (changing them WILL lead to data loss):\n"
+    "    [--block_size <size>] [--bitmap_granularity <size>]\n"
+    "    [--immediate_commit <all|small|none>] [--pg_stripe_size <size>]\n"
+    "  These, however, can still be modified with -f|--force.\n"
+    "  See create-pool for parameter descriptions.\n"
+    "  Examples:\n"
+    "    vitastor-cli modify-pool pool_A --name pool_B\n"
+    "    vitastor-cli modify-pool 2 --pg_size 4 -n 128\n"
+    "\n"
+    "vitastor-cli rm-pool|pool-rm [--force] <id|name>\n"
+    "  Remove a pool. Refuses to remove pools with images without --force.\n"
+    "\n"
+    "vitastor-cli ls-pools|pool-ls|ls-pool|pools [-l] [--detail] [--sort FIELD] [-r] [-n N] [--stats] [<glob> ...]\n"
+    "  List pools (only matching <glob> patterns if passed).\n"
+    "  -l|--long       Also report I/O statistics\n"
+    "  --detail        Use list format (not table), show all details\n"
+    "  --sort FIELD    Sort by specified field (see fields in --json output)\n"
+    "  -r|--reverse    Sort in descending order\n"
+    "  -n|--count N    Only list first N items\n"
+    "\n"
     "Use vitastor-cli --help <command> for command details or vitastor-cli --help --all for all details.\n"
     "\n"
     "GLOBAL OPTIONS:\n"
@@ -122,7 +173,7 @@ static const char* help_text =
     "  --parallel_osds M   Work with M osds in parallel when possible (default 4)\n"
     "  --progress 1|0      Report progress (default 1)\n"
     "  --cas 1|0           Use CAS writes for flatten, merge, rm (default is decide automatically)\n"
-    "  --no-color          Disable colored output\n"
+    "  --color 1|0         Enable/disable colored output and CR symbols (default 1 if stdout is a terminal)\n"
     "  --json              JSON output\n"
 ;
 
@@ -133,6 +184,8 @@ static json11::Json::object parse_args(int narg, const char *args[])
     cfg["progress"] = "1";
     for (int i = 1; i < narg; i++)
     {
+        bool argHasValue = (!(i == narg-1) && (args[i+1][0] != '-'));
+
         if (args[i][0] == '-' && args[i][1] == 'h' && args[i][2] == 0)
         {
             cfg["help"] = "1";
@@ -143,15 +196,15 @@ static json11::Json::object parse_args(int narg, const char *args[])
         }
         else if (args[i][0] == '-' && args[i][1] == 'n' && args[i][2] == 0)
         {
-            cfg["count"] = args[++i];
+            cfg["count"] = argHasValue ? args[++i] : "";
         }
         else if (args[i][0] == '-' && args[i][1] == 'p' && args[i][2] == 0)
         {
-            cfg["pool"] = args[++i];
+            cfg["pool"] = argHasValue ? args[++i] : "";
         }
         else if (args[i][0] == '-' && args[i][1] == 's' && args[i][2] == 0)
         {
-            cfg["size"] = args[++i];
+            cfg["size"] = argHasValue ? args[++i] : "";
         }
         else if (args[i][0] == '-' && args[i][1] == 'r' && args[i][2] == 0)
         {
@@ -164,17 +217,24 @@ static json11::Json::object parse_args(int narg, const char *args[])
         else if (args[i][0] == '-' && args[i][1] == '-')
         {
             const char *opt = args[i]+2;
-            cfg[opt] = i == narg-1 || !strcmp(opt, "json") ||
+            if (!strcmp(opt, "json") || !strcmp(opt, "wait") ||
                 !strcmp(opt, "wait-list") || !strcmp(opt, "wait_list") ||
-                !strcmp(opt, "long") || !strcmp(opt, "del") ||
+                !strcmp(opt, "long") || !strcmp(opt, "detail") || !strcmp(opt, "del") ||
                 !strcmp(opt, "no-color") || !strcmp(opt, "no_color") ||
                 !strcmp(opt, "readonly") || !strcmp(opt, "readwrite") ||
                 !strcmp(opt, "force") || !strcmp(opt, "reverse") ||
                 !strcmp(opt, "allow-data-loss") || !strcmp(opt, "allow_data_loss") ||
+                !strcmp(opt, "down-ok") || !strcmp(opt, "down_ok") ||
                 !strcmp(opt, "dry-run") || !strcmp(opt, "dry_run") ||
                 !strcmp(opt, "help") || !strcmp(opt, "all") ||
-                (!strcmp(opt, "writers-stopped") || !strcmp(opt, "writers_stopped")) && strcmp("1", args[i+1]) != 0
-                ? "1" : args[++i];
+                !strcmp(opt, "writers-stopped") || !strcmp(opt, "writers_stopped"))
+            {
+                cfg[opt] = "1";
+            }
+            else
+            {
+                cfg[opt] = argHasValue ? args[++i] : "";
+            }
         }
         else
         {
@@ -217,7 +277,7 @@ static int run(cli_tool_t *p, json11::Json::object cfg)
     else if (cmd[0] == "df")
     {
         // Show pool space stats
-        action_cb = p->start_df(cfg);
+        action_cb = p->start_pool_ls(cfg);
     }
     else if (cmd[0] == "ls")
     {
@@ -324,6 +384,44 @@ static int run(cli_tool_t *p, json11::Json::object cfg)
         // Allocate a new OSD number
         action_cb = p->start_alloc_osd(cfg);
     }
+    else if (cmd[0] == "create-pool" || cmd[0] == "pool-create")
+    {
+        // Create a new pool
+        if (cmd.size() > 1 && cfg["name"].is_null())
+        {
+            cfg["name"] = cmd[1];
+        }
+        action_cb = p->start_pool_create(cfg);
+    }
+    else if (cmd[0] == "modify-pool" || cmd[0] == "pool-modify")
+    {
+        // Modify existing pool
+        if (cmd.size() > 1)
+        {
+            cfg["old_name"] = cmd[1];
+        }
+        action_cb = p->start_pool_modify(cfg);
+    }
+    else if (cmd[0] == "rm-pool" || cmd[0] == "pool-rm")
+    {
+        // Remove existing pool
+        if (cmd.size() > 1)
+        {
+            cfg["pool"] = cmd[1];
+        }
+        action_cb = p->start_pool_rm(cfg);
+    }
+    else if (cmd[0] == "ls-pool" || cmd[0] == "pool-ls" || cmd[0] == "ls-pools" || cmd[0] == "pools")
+    {
+        // Show pool list
+        cfg["show_recovery"] = 1;
+        if (cmd.size() > 1)
+        {
+            cmd.erase(cmd.begin(), cmd.begin()+1);
+            cfg["names"] = cmd;
+        }
+        action_cb = p->start_pool_ls(cfg);
+    }
     else
     {
         result = { .err = EINVAL, .text = "unknown command: "+cmd[0].string_value() };

src/cli.h

@@ -46,6 +46,7 @@ public:
     json11::Json etcd_result;
 
     void parse_config(json11::Json::object & cfg);
+    json11::Json parse_tags(std::string tags);
 
     void change_parent(inode_t cur, inode_t new_parent, cli_result_t *result);
     inode_config_t* get_inode_cfg(const std::string & name);
@@ -58,7 +59,6 @@ public:
     std::function<bool(cli_result_t &)> start_status(json11::Json);
     std::function<bool(cli_result_t &)> start_describe(json11::Json);
     std::function<bool(cli_result_t &)> start_fix(json11::Json);
-    std::function<bool(cli_result_t &)> start_df(json11::Json);
     std::function<bool(cli_result_t &)> start_ls(json11::Json);
     std::function<bool(cli_result_t &)> start_create(json11::Json);
     std::function<bool(cli_result_t &)> start_modify(json11::Json);
@@ -68,6 +68,10 @@ public:
     std::function<bool(cli_result_t &)> start_rm(json11::Json);
     std::function<bool(cli_result_t &)> start_rm_osd(json11::Json cfg);
     std::function<bool(cli_result_t &)> start_alloc_osd(json11::Json cfg);
+    std::function<bool(cli_result_t &)> start_pool_create(json11::Json);
+    std::function<bool(cli_result_t &)> start_pool_modify(json11::Json);
+    std::function<bool(cli_result_t &)> start_pool_rm(json11::Json);
+    std::function<bool(cli_result_t &)> start_pool_ls(json11::Json);
 
     // Should be called like loop_and_wait(start_status(), <completion callback>)
     void loop_and_wait(std::function<bool(cli_result_t &)> loop_cb, std::function<void(const cli_result_t &)> complete_cb);
@@ -77,8 +81,13 @@ public:
 
 std::string print_table(json11::Json items, json11::Json header, bool use_esc);
 
+size_t print_detail_title_len(json11::Json item, std::vector<std::pair<std::string, std::string>> names, size_t prev_len);
+std::string print_detail(json11::Json item, std::vector<std::pair<std::string, std::string>> names, size_t title_len, bool use_esc);
+
 std::string format_lat(uint64_t lat);
 
 std::string format_q(double depth);
 
 bool stupid_glob(const std::string str, const std::string glob);
+
+std::string implode(const std::string & sep, json11::Json array);

src/cli_common.cpp

@@ -1,6 +1,7 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 (see README.md for details)
 
+#include <unistd.h>
 #include "str_util.h"
 #include "cluster_client.h"
 #include "cli.h"
@@ -113,7 +114,12 @@ void cli_tool_t::parse_config(json11::Json::object & cfg)
         else
             kv_it++;
     }
+    if (cfg.find("no_color") != cfg.end())
         color = !cfg["no_color"].bool_value();
+    else if (cfg.find("color") != cfg.end())
+        color = cfg["color"].bool_value();
+    else
+        color = isatty(1);
     json_output = cfg["json"].bool_value();
     iodepth = cfg["iodepth"].uint64_value();
     if (!iodepth)

src/cli_create.cpp

@@ -183,7 +183,16 @@ resume_3:
         // Save into inode_config for library users to be able to take it from there immediately
         new_cfg.mod_revision = parent->etcd_result["responses"][0]["response_put"]["header"]["revision"].uint64_value();
         parent->cli->st_cli.insert_inode_config(new_cfg);
-        result = (cli_result_t){ .err = 0, .text = "Image "+image_name+" created" };
+        result = (cli_result_t){
+            .err = 0,
+            .text = "Image "+image_name+" created",
+            .data = json11::Json::object {
+                { "name", image_name },
+                { "pool", new_pool_name },
+                { "parent", new_parent },
+                { "size", size },
+            }
+        };
         state = 100;
     }
 
@@ -251,7 +260,16 @@ resume_4:
         // Save into inode_config for library users to be able to take it from there immediately
         new_cfg.mod_revision = parent->etcd_result["responses"][0]["response_put"]["header"]["revision"].uint64_value();
         parent->cli->st_cli.insert_inode_config(new_cfg);
-        result = (cli_result_t){ .err = 0, .text = "Snapshot "+image_name+"@"+new_snap+" created" };
+        result = (cli_result_t){
+            .err = 0,
+            .text = "Snapshot "+image_name+"@"+new_snap+" created",
+            .data = json11::Json::object {
+                { "name", image_name+"@"+new_snap },
+                { "pool", (uint64_t)new_pool_id },
+                { "parent", new_parent },
+                { "size", size },
+            }
+        };
         state = 100;
     }
 

src/cli_df.cpp

@@ -1,243 +0,0 @@
-// Copyright (c) Vitaliy Filippov, 2019+
-// License: VNPL-1.1 (see README.md for details)
-
-#include "cli.h"
-#include "cluster_client.h"
-#include "str_util.h"
-
-// List pools with space statistics
-struct pool_lister_t
-{
-    cli_tool_t *parent;
-
-    int state = 0;
-    json11::Json space_info;
-    cli_result_t result;
-    std::map<pool_id_t, json11::Json::object> pool_stats;
-
-    bool is_done()
-    {
-        return state == 100;
-    }
-
-    void get_stats()
-    {
-        if (state == 1)
-            goto resume_1;
-        // Space statistics - pool/stats/<pool>
-        parent->etcd_txn(json11::Json::object {
-            { "success", json11::Json::array {
-                json11::Json::object {
-                    { "request_range", json11::Json::object {
-                        { "key", base64_encode(
-                            parent->cli->st_cli.etcd_prefix+"/pool/stats/"
-                        ) },
-                        { "range_end", base64_encode(
-                            parent->cli->st_cli.etcd_prefix+"/pool/stats0"
-                        ) },
-                    } },
-                },
-                json11::Json::object {
-                    { "request_range", json11::Json::object {
-                        { "key", base64_encode(
-                            parent->cli->st_cli.etcd_prefix+"/osd/stats/"
-                        ) },
-                        { "range_end", base64_encode(
-                            parent->cli->st_cli.etcd_prefix+"/osd/stats0"
-                        ) },
-                    } },
-                },
-            } },
-        });
-        state = 1;
-resume_1:
-        if (parent->waiting > 0)
-            return;
-        if (parent->etcd_err.err)
-        {
-            result = parent->etcd_err;
-            state = 100;
-            return;
-        }
-        space_info = parent->etcd_result;
-        std::map<pool_id_t, uint64_t> osd_free;
-        for (auto & kv_item: space_info["responses"][0]["response_range"]["kvs"].array_items())
-        {
-            auto kv = parent->cli->st_cli.parse_etcd_kv(kv_item);
-            // pool ID
-            pool_id_t pool_id;
-            char null_byte = 0;
-            int scanned = sscanf(kv.key.substr(parent->cli->st_cli.etcd_prefix.length()).c_str(), "/pool/stats/%u%c", &pool_id, &null_byte);
-            if (scanned != 1 || !pool_id || pool_id >= POOL_ID_MAX)
-            {
-                fprintf(stderr, "Invalid key in etcd: %s\n", kv.key.c_str());
-                continue;
-            }
-            // pool/stats/<N>
-            pool_stats[pool_id] = kv.value.object_items();
-        }
-        for (auto & kv_item: space_info["responses"][1]["response_range"]["kvs"].array_items())
-        {
-            auto kv = parent->cli->st_cli.parse_etcd_kv(kv_item);
-            // osd ID
-            osd_num_t osd_num;
-            char null_byte = 0;
-            int scanned = sscanf(kv.key.substr(parent->cli->st_cli.etcd_prefix.length()).c_str(), "/osd/stats/%ju%c", &osd_num, &null_byte);
-            if (scanned != 1 || !osd_num || osd_num >= POOL_ID_MAX)
-            {
-                fprintf(stderr, "Invalid key in etcd: %s\n", kv.key.c_str());
-                continue;
-            }
-            // osd/stats/<N>::free
-            osd_free[osd_num] = kv.value["free"].uint64_value();
-        }
-        // Calculate max_avail for each pool
-        for (auto & pp: parent->cli->st_cli.pool_config)
-        {
-            auto & pool_cfg = pp.second;
-            uint64_t pool_avail = UINT64_MAX;
-            std::map<osd_num_t, uint64_t> pg_per_osd;
-            for (auto & pgp: pool_cfg.pg_config)
-            {
-                for (auto pg_osd: pgp.second.target_set)
-                {
-                    if (pg_osd != 0)
-                    {
-                        pg_per_osd[pg_osd]++;
-                    }
-                }
-            }
-            for (auto pg_per_pair: pg_per_osd)
-            {
-                uint64_t pg_free = osd_free[pg_per_pair.first] * pool_cfg.real_pg_count / pg_per_pair.second;
-                if (pool_avail > pg_free)
-                {
-                    pool_avail = pg_free;
-                }
-            }
-            if (pool_avail == UINT64_MAX)
-            {
-                pool_avail = 0;
-            }
-            if (pool_cfg.scheme != POOL_SCHEME_REPLICATED)
-            {
-                pool_avail *= (pool_cfg.pg_size - pool_cfg.parity_chunks);
-            }
-            pool_stats[pool_cfg.id] = json11::Json::object {
-                { "id", (uint64_t)pool_cfg.id },
-                { "name", pool_cfg.name },
-                { "pg_count", pool_cfg.pg_count },
-                { "real_pg_count", pool_cfg.real_pg_count },
-                { "scheme", pool_cfg.scheme == POOL_SCHEME_REPLICATED ? "replicated" : "ec" },
-                { "scheme_name", pool_cfg.scheme == POOL_SCHEME_REPLICATED
-                    ? std::to_string(pool_cfg.pg_size)+"/"+std::to_string(pool_cfg.pg_minsize)
-                    : "EC "+std::to_string(pool_cfg.pg_size-pool_cfg.parity_chunks)+"+"+std::to_string(pool_cfg.parity_chunks) },
-                { "used_raw", (uint64_t)(pool_stats[pool_cfg.id]["used_raw_tb"].number_value() * ((uint64_t)1<<40)) },
-                { "total_raw", (uint64_t)(pool_stats[pool_cfg.id]["total_raw_tb"].number_value() * ((uint64_t)1<<40)) },
-                { "max_available", pool_avail },
-                { "raw_to_usable", pool_stats[pool_cfg.id]["raw_to_usable"].number_value() },
-                { "space_efficiency", pool_stats[pool_cfg.id]["space_efficiency"].number_value() },
-                { "pg_real_size", pool_stats[pool_cfg.id]["pg_real_size"].uint64_value() },
-                { "failure_domain", pool_cfg.failure_domain },
-            };
-        }
-    }
-
-    json11::Json::array to_list()
-    {
-        json11::Json::array list;
-        for (auto & kv: pool_stats)
-        {
-            list.push_back(kv.second);
-        }
-        return list;
-    }
-
-    void loop()
-    {
-        get_stats();
-        if (parent->waiting > 0)
-            return;
-        if (state == 100)
-            return;
-        if (parent->json_output)
-        {
-            // JSON output
-            result.data = to_list();
-            state = 100;
-            return;
-        }
-        // Table output: name, scheme_name, pg_count, total, used, max_avail, used%, efficiency
-        json11::Json::array cols;
-        cols.push_back(json11::Json::object{
-            { "key", "name" },
-            { "title", "NAME" },
-        });
-        cols.push_back(json11::Json::object{
-            { "key", "scheme_name" },
-            { "title", "SCHEME" },
-        });
-        cols.push_back(json11::Json::object{
-            { "key", "pg_count_fmt" },
-            { "title", "PGS" },
-        });
-        cols.push_back(json11::Json::object{
-            { "key", "total_fmt" },
-            { "title", "TOTAL" },
-        });
-        cols.push_back(json11::Json::object{
-            { "key", "used_fmt" },
-            { "title", "USED" },
-        });
-        cols.push_back(json11::Json::object{
-            { "key", "max_avail_fmt" },
-            { "title", "AVAILABLE" },
-        });
-        cols.push_back(json11::Json::object{
-            { "key", "used_pct" },
-            { "title", "USED%" },
-        });
-        cols.push_back(json11::Json::object{
-            { "key", "eff_fmt" },
-            { "title", "EFFICIENCY" },
-        });
-        json11::Json::array list;
-        for (auto & kv: pool_stats)
-        {
-            double raw_to = kv.second["raw_to_usable"].number_value();
-            if (raw_to < 0.000001 && raw_to > -0.000001)
-                raw_to = 1;
-            kv.second["pg_count_fmt"] = kv.second["real_pg_count"] == kv.second["pg_count"]
-                ? kv.second["real_pg_count"].as_string()
-                : kv.second["real_pg_count"].as_string()+"->"+kv.second["pg_count"].as_string();
-            kv.second["total_fmt"] = format_size(kv.second["total_raw"].uint64_value() / raw_to);
-            kv.second["used_fmt"] = format_size(kv.second["used_raw"].uint64_value() / raw_to);
-            kv.second["max_avail_fmt"] = format_size(kv.second["max_available"].uint64_value());
-            kv.second["used_pct"] = format_q(kv.second["total_raw"].uint64_value()
-                ? (100 - 100*kv.second["max_available"].uint64_value() *
-                    kv.second["raw_to_usable"].number_value() / kv.second["total_raw"].uint64_value())
-                : 100)+"%";
-            kv.second["eff_fmt"] = format_q(kv.second["space_efficiency"].number_value()*100)+"%";
-        }
-        result.data = to_list();
-        result.text = print_table(result.data, cols, parent->color);
-        state = 100;
-    }
-};
-
-std::function<bool(cli_result_t &)> cli_tool_t::start_df(json11::Json cfg)
-{
-    auto lister = new pool_lister_t();
-    lister->parent = this;
-    return [lister](cli_result_t & result)
-    {
-        lister->loop();
-        if (lister->is_done())
-        {
-            result = lister->result;
-            delete lister;
-            return true;
-        }
-        return false;
-    };
-}

src/cli_merge.cpp

@@ -275,7 +275,9 @@ struct snap_merger_t
                 processed++;
                 if (parent->progress && !(processed % 128))
                 {
-                    printf("\rFiltering target blocks: %ju/%ju", processed, to_process);
+                    fprintf(stderr, parent->color
+                        ? "\rFiltering target blocks: %ju/%ju"
+                        : "Filtering target blocks: %ju/%ju\n", processed, to_process);
                 }
             }
             if (in_flight > 0 || oit != merge_offsets.end())
@@ -285,7 +287,9 @@ struct snap_merger_t
             }
             if (parent->progress)
             {
-                printf("\r%ju full blocks of target filtered out\n", to_process-merge_offsets.size());
+                fprintf(stderr, parent->color
+                    ? "\r%ju full blocks of target filtered out\n"
+                    : "%ju full blocks of target filtered out\n", to_process-merge_offsets.size());
             }
         }
         state = 3;
@@ -320,7 +324,9 @@ struct snap_merger_t
             processed++;
             if (parent->progress && !(processed % 128))
             {
-                printf("\rOverwriting blocks: %ju/%ju", processed, to_process);
+                fprintf(stderr, parent->color
+                    ? "\rOverwriting blocks: %ju/%ju"
+                    : "Overwriting blocks: %ju/%ju\n", processed, to_process);
             }
         }
         if (in_flight == 0 && rwo_error.size())
@@ -339,10 +345,16 @@ struct snap_merger_t
         }
         if (parent->progress)
         {
-            printf("\rOverwriting blocks: %ju/%ju\n", to_process, to_process);
+            fprintf(stderr, parent->color
+                ? "\rOverwriting blocks: %ju/%ju\n"
+                : "Overwriting blocks: %ju/%ju\n", to_process, to_process);
         }
         // Done
-        result = (cli_result_t){ .text = "Done, layers from "+from_name+" to "+to_name+" merged into "+target_name };
+        result = (cli_result_t){ .text = "Done, layers from "+from_name+" to "+to_name+" merged into "+target_name, .data = json11::Json::object {
+            { "from", from_name },
+            { "to", to_name },
+            { "into", target_name },
+        }};
         state = 100;
     resume_100:
         return;

src/cli_modify.cpp

@@ -15,6 +15,7 @@ struct image_changer_t
     uint64_t new_size = 0;
     bool force_size = false, inc_size = false;
     bool set_readonly = false, set_readwrite = false, force = false;
+    bool down_ok = false;
     // interval between fsyncs
     int fsync_interval = 128;
 
@@ -84,7 +85,10 @@ struct image_changer_t
             (!new_size && !force_size || cfg.size == new_size || cfg.size >= new_size && inc_size) &&
             (new_name == "" || new_name == image_name))
         {
-            result = (cli_result_t){ .text = "No change" };
+            result = (cli_result_t){ .err = 0, .text = "No change", .data = json11::Json::object {
+                { "error_code", 0 },
+                { "error_text", "No change" },
+            }};
             state = 100;
             return;
         }
@@ -105,6 +109,7 @@ struct image_changer_t
                     { "pool", (uint64_t)INODE_POOL(inode_num) },
                     { "fsync-interval", fsync_interval },
                     { "min-offset", ((new_size+4095)/4096)*4096 },
+                    { "down-ok", down_ok },
                 });
 resume_1:
                 while (!cb(result))
@@ -220,7 +225,16 @@ resume_2:
             parent->cli->st_cli.inode_by_name.erase(image_name);
         }
         parent->cli->st_cli.insert_inode_config(cfg);
-        result = (cli_result_t){ .err = 0, .text = "Image "+image_name+" modified" };
+        result = (cli_result_t){
+            .err = 0,
+            .text = "Image "+image_name+" modified",
+            .data = json11::Json::object {
+                { "name", image_name },
+                { "inode", INODE_NO_POOL(inode_num) },
+                { "pool", (uint64_t)INODE_POOL(inode_num) },
+                { "size", new_size },
+            }
+        };
         state = 100;
     }
 };
@@ -240,6 +254,7 @@ std::function<bool(cli_result_t &)> cli_tool_t::start_modify(json11::Json cfg)
     changer->fsync_interval = cfg["fsync_interval"].uint64_value();
     if (!changer->fsync_interval)
         changer->fsync_interval = 128;
+    changer->down_ok = cfg["down_ok"].bool_value();
     // FIXME Check that the image doesn't have children when shrinking
     return [changer](cli_result_t & result)
     {

src/cli_pool_cfg.cpp

@@ -0,0 +1,264 @@
+// Copyright (c) Vitaliy Filippov, 2024
+// License: VNPL-1.1 (see README.md for details)
+
+#include "cli_pool_cfg.h"
+#include "etcd_state_client.h"
+#include "str_util.h"
+
+std::string validate_pool_config(json11::Json::object & new_cfg, json11::Json old_cfg,
+    uint64_t global_block_size, uint64_t global_bitmap_granularity, bool force)
+{
+    // short option names
+    if (new_cfg.find("count") != new_cfg.end())
+    {
+        new_cfg["pg_count"] = new_cfg["count"];
+        new_cfg.erase("count");
+    }
+    if (new_cfg.find("size") != new_cfg.end())
+    {
+        new_cfg["pg_size"] = new_cfg["size"];
+        new_cfg.erase("size");
+    }
+
+    // --ec shortcut
+    if (new_cfg.find("ec") != new_cfg.end())
+    {
+        if (new_cfg.find("scheme") != new_cfg.end() ||
+            new_cfg.find("pg_size") != new_cfg.end() ||
+            new_cfg.find("parity_chunks") != new_cfg.end())
+        {
+            return "--ec can't be used with --pg_size, --parity_chunks or --scheme";
+        }
+        // pg_size = N+K
+        // parity_chunks = K
+        uint64_t data_chunks = 0, parity_chunks = 0;
+        char null_byte = 0;
+        int ret = sscanf(new_cfg["ec"].string_value().c_str(), "%ju+%ju%c", &data_chunks, &parity_chunks, &null_byte);
+        if (ret != 2 || !data_chunks || !parity_chunks)
+        {
+            return "--ec should be <N>+<K> format (<N>, <K> - numbers)";
+        }
+        new_cfg.erase("ec");
+        new_cfg["scheme"] = "ec";
+        new_cfg["pg_size"] = data_chunks+parity_chunks;
+        new_cfg["parity_chunks"] = parity_chunks;
+    }
+
+    if (old_cfg.is_null() && new_cfg["scheme"].string_value() == "")
+    {
+        // Default scheme
+        new_cfg["scheme"] = "replicated";
+    }
+    if (new_cfg.find("pg_minsize") == new_cfg.end() && (old_cfg.is_null() || new_cfg.find("pg_size") != new_cfg.end()))
+    {
+        // Default pg_minsize
+        if (new_cfg["scheme"] == "replicated")
+        {
+            // pg_minsize = (N+K > 2) ? 2 : 1
+            new_cfg["pg_minsize"] = new_cfg["pg_size"].uint64_value() > 2 ? 2 : 1;
+        }
+        else // ec or xor
+        {
+            // pg_minsize = (K > 1) ? N + 1 : N
+            new_cfg["pg_minsize"] = new_cfg["pg_size"].uint64_value() - new_cfg["parity_chunks"].uint64_value() +
+                (new_cfg["parity_chunks"].uint64_value() > 1 ? 1 : 0);
+        }
+    }
+    if (new_cfg["scheme"] != "ec")
+    {
+        new_cfg.erase("parity_chunks");
+    }
+
+    // Check integer values and unknown keys
+    for (auto kv_it = new_cfg.begin(); kv_it != new_cfg.end(); )
+    {
+        auto & key = kv_it->first;
+        auto & value = kv_it->second;
+        if (key == "pg_size" || key == "parity_chunks" || key == "pg_minsize" ||
+            key == "pg_count" || key == "max_osd_combinations" || key == "block_size" ||
+            key == "bitmap_granularity" || key == "pg_stripe_size")
+        {
+            if (value.is_number() && value.uint64_value() != value.number_value() ||
+                value.is_string() && !value.uint64_value() && value.string_value() != "0")
+            {
+                return key+" must be a non-negative integer";
+            }
+            value = value.uint64_value();
+        }
+        else if (key == "name" || key == "scheme" || key == "immediate_commit" ||
+            key == "failure_domain" || key == "root_node" || key == "scrub_interval")
+        {
+            // OK
+        }
+        else if (key == "osd_tags" || key == "primary_affinity_tags")
+        {
+            if (value.is_string())
+            {
+                value = explode(",", value.string_value(), true);
+            }
+        }
+        else
+        {
+            // Unknown parameter
+            new_cfg.erase(kv_it++);
+            continue;
+        }
+        kv_it++;
+    }
+
+    // Merge with the old config
+    if (!old_cfg.is_null())
+    {
+        for (auto & kv: old_cfg.object_items())
+        {
+            if (new_cfg.find(kv.first) == new_cfg.end())
+            {
+                new_cfg[kv.first] = kv.second;
+            }
+        }
+    }
+
+    // Prevent autovivification of object keys. Now we don't modify the config, we just check it
+    json11::Json cfg = new_cfg;
+
+    // Validate changes
+    if (!old_cfg.is_null() && !force)
+    {
+        if (old_cfg["scheme"] != cfg["scheme"])
+        {
+            return "Changing scheme for an existing pool will lead to data loss. Use --force to proceed";
+        }
+        if (etcd_state_client_t::parse_scheme(old_cfg["scheme"].string_value()) == POOL_SCHEME_EC)
+        {
+            uint64_t old_data_chunks = old_cfg["pg_size"].uint64_value() - old_cfg["parity_chunks"].uint64_value();
+            uint64_t new_data_chunks = cfg["pg_size"].uint64_value() - cfg["parity_chunks"].uint64_value();
+            if (old_data_chunks != new_data_chunks)
+            {
+                return "Changing EC data chunk count for an existing pool will lead to data loss. Use --force to proceed";
+            }
+        }
+        if (old_cfg["block_size"] != cfg["block_size"] ||
+            old_cfg["bitmap_granularity"] != cfg["bitmap_granularity"] ||
+            old_cfg["immediate_commit"] != cfg["immediate_commit"])
+        {
+            return "Changing block_size, bitmap_granularity or immediate_commit"
+                " for an existing pool will lead to incomplete PGs. Use --force to proceed";
+        }
+        if (old_cfg["pg_stripe_size"] != cfg["pg_stripe_size"])
+        {
+            return "Changing pg_stripe_size for an existing pool will lead to data loss. Use --force to proceed";
+        }
+    }
+
+    // Validate values
+    if (cfg["name"].string_value() == "")
+    {
+        return "Non-empty pool name is required";
+    }
+
+    // scheme
+    auto scheme = etcd_state_client_t::parse_scheme(cfg["scheme"].string_value());
+    if (!scheme)
+    {
+        return "Scheme must be one of \"replicated\", \"ec\" or \"xor\"";
+    }
+
+    // pg_size
+    auto pg_size = cfg["pg_size"].uint64_value();
+    if (!pg_size)
+    {
+        return "Non-zero PG size is required";
+    }
+    if (scheme != POOL_SCHEME_REPLICATED && pg_size < 3)
+    {
+        return "PG size can't be smaller than 3 for EC/XOR pools";
+    }
+    if (pg_size > 256)
+    {
+        return "PG size can't be greater than 256";
+    }
+
+    // parity_chunks
+    uint64_t parity_chunks = 1;
+    if (scheme == POOL_SCHEME_EC)
+    {
+        parity_chunks = cfg["parity_chunks"].uint64_value();
+        if (!parity_chunks)
+        {
+            return "Non-zero parity_chunks is required";
+        }
+        if (parity_chunks > pg_size-2)
+        {
+            return "parity_chunks can't be greater than "+std::to_string(pg_size-2)+" (PG size - 2)";
+        }
+    }
+
+    // pg_minsize
+    auto pg_minsize = cfg["pg_minsize"].uint64_value();
+    if (!pg_minsize)
+    {
+        return "Non-zero pg_minsize is required";
+    }
+    else if (pg_minsize > pg_size)
+    {
+        return "pg_minsize can't be greater than "+std::to_string(pg_size)+" (PG size)";
+    }
+    else if (scheme != POOL_SCHEME_REPLICATED && pg_minsize < pg_size-parity_chunks)
+    {
+        return "pg_minsize can't be smaller than "+std::to_string(pg_size-parity_chunks)+
+            " (pg_size - parity_chunks) for XOR/EC pool";
+    }
+
+    // pg_count
+    if (!cfg["pg_count"].uint64_value())
+    {
+        return "Non-zero pg_count is required";
+    }
+
+    // max_osd_combinations
+    if (!cfg["max_osd_combinations"].is_null() && cfg["max_osd_combinations"].uint64_value() < 100)
+    {
+        return "max_osd_combinations must be at least 100, but it is "+cfg["max_osd_combinations"].as_string();
+    }
+
+    // block_size
+    auto block_size = cfg["block_size"].uint64_value();
+    if (!cfg["block_size"].is_null() && ((block_size & (block_size-1)) ||
+        block_size < MIN_DATA_BLOCK_SIZE || block_size > MAX_DATA_BLOCK_SIZE))
+    {
+        return "block_size must be a power of two between "+std::to_string(MIN_DATA_BLOCK_SIZE)+
+            " and "+std::to_string(MAX_DATA_BLOCK_SIZE)+", but it is "+std::to_string(block_size);
+    }
+    block_size = (block_size ? block_size : global_block_size);
+
+    // bitmap_granularity
+    auto bitmap_granularity = cfg["bitmap_granularity"].uint64_value();
+    if (!cfg["bitmap_granularity"].is_null() && (!bitmap_granularity || (bitmap_granularity % 512)))
+    {
+        return "bitmap_granularity must be a multiple of 512, but it is "+std::to_string(bitmap_granularity);
+    }
+    bitmap_granularity = (bitmap_granularity ? bitmap_granularity : global_bitmap_granularity);
+    if (block_size % bitmap_granularity)
+    {
+        return "bitmap_granularity must divide data block size ("+std::to_string(block_size)+"), but it is "+std::to_string(bitmap_granularity);
+    }
+
+    // immediate_commit
+    if (!cfg["immediate_commit"].is_null() && !etcd_state_client_t::parse_immediate_commit(cfg["immediate_commit"].string_value()))
+    {
+        return "immediate_commit must be one of \"all\", \"small\", or \"none\", but it is "+cfg["scrub_interval"].as_string();
+    }
+
+    // scrub_interval
+    if (!cfg["scrub_interval"].is_null())
+    {
+        bool ok;
+        parse_time(cfg["scrub_interval"].string_value(), &ok);
+        if (!ok)
+        {
+            return "scrub_interval must be a time interval (number + unit s/m/h/d/M/y), but it is "+cfg["scrub_interval"].as_string();
+        }
+    }
+
+    return "";
+}

src/cli_pool_cfg.h

@@ -0,0 +1,10 @@
+// Copyright (c) Vitaliy Filippov, 2024
+// License: VNPL-1.1 (see README.md for details)
+
+#pragma once
+
+#include "json11/json11.hpp"
+#include <stdint.h>
+
+std::string validate_pool_config(json11::Json::object & new_cfg, json11::Json old_cfg,
+    uint64_t global_block_size, uint64_t global_bitmap_granularity, bool force);

src/cli_pool_create.cpp

@@ -0,0 +1,622 @@
+// Copyright (c) MIND Software LLC, 2023 (info@mindsw.io)
+// I accept Vitastor CLA: see CLA-en.md for details
+// Copyright (c) Vitaliy Filippov, 2024
+// License: VNPL-1.1 (see README.md for details)
+
+#include <ctype.h>
+#include "cli.h"
+#include "cli_pool_cfg.h"
+#include "cluster_client.h"
+#include "epoll_manager.h"
+#include "pg_states.h"
+#include "str_util.h"
+
+struct pool_creator_t
+{
+    cli_tool_t *parent;
+    json11::Json::object cfg;
+
+    bool force = false;
+    bool wait = false;
+
+    int state = 0;
+    cli_result_t result;
+
+    struct {
+        uint32_t retries = 5;
+        uint32_t interval = 0;
+        bool passed = false;
+    } create_check;
+
+    uint64_t new_id = 1;
+    uint64_t new_pools_mod_rev;
+    json11::Json state_node_tree;
+    json11::Json new_pools;
+
+    bool is_done() { return state == 100; }
+
+    void loop()
+    {
+        if (state == 1)
+            goto resume_1;
+        else if (state == 2)
+            goto resume_2;
+        else if (state == 3)
+            goto resume_3;
+        else if (state == 4)
+            goto resume_4;
+        else if (state == 5)
+            goto resume_5;
+        else if (state == 6)
+            goto resume_6;
+        else if (state == 7)
+            goto resume_7;
+        else if (state == 8)
+            goto resume_8;
+
+        // Validate pool parameters
+        result.text = validate_pool_config(cfg, json11::Json(), parent->cli->st_cli.global_block_size,
+            parent->cli->st_cli.global_bitmap_granularity, force);
+        if (result.text != "")
+        {
+            result.err = EINVAL;
+            state = 100;
+            return;
+        }
+        state = 1;
+resume_1:
+        // If not forced, check that we have enough osds for pg_size
+        if (!force)
+        {
+            // Get node_placement configuration from etcd
+            parent->etcd_txn(json11::Json::object {
+                { "success", json11::Json::array {
+                    json11::Json::object {
+                        { "request_range", json11::Json::object {
+                            { "key", base64_encode(parent->cli->st_cli.etcd_prefix+"/config/node_placement") },
+                        } }
+                    },
+                } },
+            });
+
+            state = 2;
+resume_2:
+            if (parent->waiting > 0)
+                return;
+            if (parent->etcd_err.err)
+            {
+                result = parent->etcd_err;
+                state = 100;
+                return;
+            }
+
+            // Get state_node_tree based on node_placement and osd peer states
+            {
+                auto kv = parent->cli->st_cli.parse_etcd_kv(parent->etcd_result["responses"][0]["response_range"]["kvs"][0]);
+                state_node_tree = get_state_node_tree(kv.value.object_items());
+            }
+
+            // Skip tag checks, if pool has none
+            if (cfg["osd_tags"].array_items().size())
+            {
+                // Get osd configs (for tags) of osds in state_node_tree
+                {
+                    json11::Json::array osd_configs;
+                    for (auto osd_num: state_node_tree["osds"].array_items())
+                    {
+                        osd_configs.push_back(json11::Json::object {
+                            { "request_range", json11::Json::object {
+                                { "key", base64_encode(parent->cli->st_cli.etcd_prefix+"/config/osd/"+osd_num.as_string()) },
+                            } }
+                        });
+                    }
+                    parent->etcd_txn(json11::Json::object { { "success", osd_configs, }, });
+                }
+
+                state = 3;
+resume_3:
+                if (parent->waiting > 0)
+                    return;
+                if (parent->etcd_err.err)
+                {
+                    result = parent->etcd_err;
+                    state = 100;
+                    return;
+                }
+
+                // Filter out osds from state_node_tree based on pool/osd tags
+                {
+                    std::vector<json11::Json> osd_configs;
+                    for (auto & ocr: parent->etcd_result["responses"].array_items())
+                    {
+                        auto kv = parent->cli->st_cli.parse_etcd_kv(ocr["response_range"]["kvs"][0]);
+                        osd_configs.push_back(kv.value);
+                    }
+                    state_node_tree = filter_state_node_tree_by_tags(state_node_tree, osd_configs);
+                }
+            }
+
+            // Get stats (for block_size, bitmap_granularity, ...) of osds in state_node_tree
+            {
+                json11::Json::array osd_stats;
+
+                for (auto osd_num: state_node_tree["osds"].array_items())
+                {
+                    osd_stats.push_back(json11::Json::object {
+                        { "request_range", json11::Json::object {
+                            { "key", base64_encode(parent->cli->st_cli.etcd_prefix+"/osd/stats/"+osd_num.as_string()) },
+                        } }
+                    });
+                }
+
+                parent->etcd_txn(json11::Json::object { { "success", osd_stats, }, });
+            }
+
+            state = 4;
+resume_4:
+            if (parent->waiting > 0)
+                return;
+            if (parent->etcd_err.err)
+            {
+                result = parent->etcd_err;
+                state = 100;
+                return;
+            }
+
+            // Filter osds from state_node_tree based on pool parameters and osd stats
+            {
+                std::vector<json11::Json> osd_stats;
+                for (auto & ocr: parent->etcd_result["responses"].array_items())
+                {
+                    auto kv = parent->cli->st_cli.parse_etcd_kv(ocr["response_range"]["kvs"][0]);
+                    osd_stats.push_back(kv.value);
+                }
+                state_node_tree = filter_state_node_tree_by_stats(state_node_tree, osd_stats);
+            }
+
+            // Check that pg_size <= max_pg_size
+            {
+                auto failure_domain = cfg["failure_domain"].string_value() == ""
+                    ? "host" : cfg["failure_domain"].string_value();
+                uint64_t max_pg_size = get_max_pg_size(state_node_tree["nodes"].object_items(),
+                    failure_domain, cfg["root_node"].string_value());
+
+                if (cfg["pg_size"].uint64_value() > max_pg_size)
+                {
+                    result = (cli_result_t){
+                        .err = EINVAL,
+                        .text =
+                            "There are "+std::to_string(max_pg_size)+" \""+failure_domain+"\" failure domains with OSDs matching tags and"
+                            " block_size/bitmap_granularity/immediate_commit parameters, but you want to create a"
+                            " pool with "+cfg["pg_size"].as_string()+" OSDs from different failure domains in a PG."
+                            " Change parameters or add --force if you want to create a degraded pool and add OSDs later."
+                    };
+                    state = 100;
+                    return;
+                }
+            }
+        }
+        // Create pool
+        state = 5;
+resume_5:
+        // Get pools from etcd
+        parent->etcd_txn(json11::Json::object {
+            { "success", json11::Json::array {
+                json11::Json::object {
+                    { "request_range", json11::Json::object {
+                        { "key", base64_encode(parent->cli->st_cli.etcd_prefix+"/config/pools") },
+                    } }
+                },
+            } },
+        });
+        state = 6;
+resume_6:
+        if (parent->waiting > 0)
+            return;
+        if (parent->etcd_err.err)
+        {
+            result = parent->etcd_err;
+            state = 100;
+            return;
+        }
+        {
+            // Add new pool
+            auto kv = parent->cli->st_cli.parse_etcd_kv(parent->etcd_result["responses"][0]["response_range"]["kvs"][0]);
+            new_pools = create_pool(kv);
+            if (new_pools.is_string())
+            {
+                result = (cli_result_t){ .err = EEXIST, .text = new_pools.string_value() };
+                state = 100;
+                return;
+            }
+            new_pools_mod_rev = kv.mod_revision;
+        }
+        // Update pools in etcd
+        parent->etcd_txn(json11::Json::object {
+            { "compare", json11::Json::array {
+                json11::Json::object {
+                    { "target", "MOD" },
+                    { "key", base64_encode(parent->cli->st_cli.etcd_prefix+"/config/pools") },
+                    { "result", "LESS" },
+                    { "mod_revision", new_pools_mod_rev+1 },
+                }
+            } },
+            { "success", json11::Json::array {
+                json11::Json::object {
+                    { "request_put", json11::Json::object {
+                        { "key", base64_encode(parent->cli->st_cli.etcd_prefix+"/config/pools") },
+                        { "value", base64_encode(new_pools.dump()) },
+                    } },
+                },
+            } },
+        });
+        state = 7;
+resume_7:
+        if (parent->waiting > 0)
+            return;
+        if (parent->etcd_err.err)
+        {
+            result = parent->etcd_err;
+            state = 100;
+            return;
+        }
+
+        // Perform final create-check
+        create_check.interval = parent->cli->config["mon_change_timeout"].uint64_value();
+        if (!create_check.interval)
+            create_check.interval = 1000;
+
+        state = 8;
+resume_8:
+        if (parent->waiting > 0)
+            return;
+
+        // Unless forced, check that pool was created and is active
+        if (!wait)
+        {
+            create_check.passed = true;
+        }
+        else if (create_check.retries)
+        {
+            create_check.retries--;
+            parent->waiting++;
+            parent->epmgr->tfd->set_timer(create_check.interval, false, [this](int timer_id)
+            {
+                if (parent->cli->st_cli.pool_config.find(new_id) != parent->cli->st_cli.pool_config.end())
+                {
+                    auto & pool_cfg = parent->cli->st_cli.pool_config[new_id];
+                    create_check.passed = pool_cfg.real_pg_count > 0;
+                    for (auto pg_it = pool_cfg.pg_config.begin(); pg_it != pool_cfg.pg_config.end(); pg_it++)
+                    {
+                        if (!(pg_it->second.cur_state & PG_ACTIVE))
+                        {
+                            create_check.passed = false;
+                            break;
+                        }
+                    }
+                    if (create_check.passed)
+                        create_check.retries = 0;
+                }
+                parent->waiting--;
+                parent->ringloop->wakeup();
+            });
+            return;
+        }
+
+        if (!create_check.passed)
+        {
+            result = (cli_result_t) {
+                .err = EAGAIN,
+                .text = "Pool "+cfg["name"].string_value()+" was created, but failed to become active."
+                    " This may indicate that cluster state has changed while the pool was being created."
+                    " Please check the current state and adjust the pool configuration if necessary.",
+            };
+        }
+        else
+        {
+            result = (cli_result_t){
+                .err = 0,
+                .text = "Pool "+cfg["name"].string_value()+" created",
+                .data = new_pools[std::to_string(new_id)],
+            };
+        }
+        state = 100;
+    }
+
+    // Returns a JSON object of form {"nodes": {...}, "osds": [...]} that
+    // contains: all nodes (osds, hosts, ...) based on node_placement config
+    // and current peer state, and a list of active peer osds.
+    json11::Json get_state_node_tree(json11::Json::object node_placement)
+    {
+        // Erase non-peer osd nodes from node_placement
+        for (auto np_it = node_placement.begin(); np_it != node_placement.end();)
+        {
+            // Numeric nodes are osds
+            osd_num_t osd_num = stoull_full(np_it->first);
+
+            // If node is osd and it is not in peer states, erase it
+            if (osd_num > 0 &&
+                parent->cli->st_cli.peer_states.find(osd_num) == parent->cli->st_cli.peer_states.end())
+            {
+                node_placement.erase(np_it++);
+            }
+            else
+                np_it++;
+        }
+
+        // List of peer osds
+        std::vector<std::string> peer_osds;
+
+        // Record peer osds and add missing osds/hosts to np
+        for (auto & ps: parent->cli->st_cli.peer_states)
+        {
+            std::string osd_num = std::to_string(ps.first);
+
+            // Record peer osd
+            peer_osds.push_back(osd_num);
+
+            // Add osd, if necessary
+            if (node_placement.find(osd_num) == node_placement.end())
+            {
+                std::string osd_host = ps.second["host"].as_string();
+
+                // Add host, if necessary
+                if (node_placement.find(osd_host) == node_placement.end())
+                {
+                    node_placement[osd_host] = json11::Json::object {
+                        { "level", "host" }
+                    };
+                }
+
+                node_placement[osd_num] = json11::Json::object {
+                    { "parent", osd_host }
+                };
+            }
+        }
+
+        return json11::Json::object { { "osds", peer_osds }, { "nodes", node_placement } };
+    }
+
+    // Returns new state_node_tree based on given state_node_tree with osds
+    // filtered out by tags in given osd_configs and current pool config.
+    // Requires: state_node_tree["osds"] must match osd_configs 1-1
+    json11::Json filter_state_node_tree_by_tags(const json11::Json & state_node_tree, std::vector<json11::Json> & osd_configs)
+    {
+        auto & osds = state_node_tree["osds"].array_items();
+
+        // Accepted state_node_tree nodes
+        auto accepted_nodes = state_node_tree["nodes"].object_items();
+
+        // List of accepted osds
+        std::vector<std::string> accepted_osds;
+
+        for (size_t i = 0; i < osd_configs.size(); i++)
+        {
+            auto & oc = osd_configs[i].object_items();
+
+            // Get osd number
+            auto osd_num = osds[i].as_string();
+
+            // We need tags in config to check against pool tags
+            if (oc.find("tags") == oc.end())
+            {
+                // Exclude osd from state_node_tree nodes
+                accepted_nodes.erase(osd_num);
+                continue;
+            }
+            else
+            {
+                // If all pool tags are in osd tags, accept osd
+                if (all_in_tags(osd_configs[i]["tags"], cfg["osd_tags"]))
+                {
+                    accepted_osds.push_back(osd_num);
+                }
+                // Otherwise, exclude osd
+                else
+                {
+                    // Exclude osd from state_node_tree nodes
+                    accepted_nodes.erase(osd_num);
+                }
+            }
+        }
+
+        return json11::Json::object { { "osds", accepted_osds }, { "nodes", accepted_nodes } };
+    }
+
+    // Returns new state_node_tree based on given state_node_tree with osds
+    // filtered out by stats parameters (block_size, bitmap_granularity) in
+    // given osd_stats and current pool config.
+    // Requires: state_node_tree["osds"] must match osd_stats 1-1
+    json11::Json filter_state_node_tree_by_stats(const json11::Json & state_node_tree, std::vector<json11::Json> & osd_stats)
+    {
+        auto & osds = state_node_tree["osds"].array_items();
+
+        // Accepted state_node_tree nodes
+        auto accepted_nodes = state_node_tree["nodes"].object_items();
+
+        // List of accepted osds
+        std::vector<std::string> accepted_osds;
+
+        uint64_t p_block_size = cfg["block_size"].uint64_value()
+            ? cfg["block_size"].uint64_value()
+            : parent->cli->st_cli.global_block_size;
+        uint64_t p_bitmap_granularity = cfg["bitmap_granularity"].uint64_value()
+            ? cfg["bitmap_granularity"].uint64_value()
+            : parent->cli->st_cli.global_bitmap_granularity;
+        uint32_t p_immediate_commit = cfg["immediate_commit"].is_string()
+            ? etcd_state_client_t::parse_immediate_commit(cfg["immediate_commit"].string_value())
+            : parent->cli->st_cli.global_immediate_commit;
+
+        for (size_t i = 0; i < osd_stats.size(); i++)
+        {
+            auto & os = osd_stats[i];
+            // Get osd number
+            auto osd_num = osds[i].as_string();
+            if (!os["data_block_size"].is_null() && os["data_block_size"] != p_block_size ||
+                !os["bitmap_granularity"].is_null() && os["bitmap_granularity"] != p_bitmap_granularity ||
+                !os["immediate_commit"].is_null() &&
+                etcd_state_client_t::parse_immediate_commit(os["immediate_commit"].string_value()) < p_immediate_commit)
+            {
+                accepted_nodes.erase(osd_num);
+            }
+            else
+            {
+                accepted_osds.push_back(osd_num);
+            }
+        }
+
+        return json11::Json::object { { "osds", accepted_osds }, { "nodes", accepted_nodes } };
+    }
+
+    // Returns maximum pg_size possible for given node_tree and failure_domain, starting at parent_node
+    uint64_t get_max_pg_size(json11::Json::object node_tree, const std::string & level, const std::string & parent_node)
+    {
+        uint64_t max_pg_sz = 0;
+
+        std::vector<std::string> nodes;
+
+        // Check if parent node is an osd (numeric)
+        if (parent_node != "" && stoull_full(parent_node))
+        {
+            // Add it to node list if osd is in node tree
+            if (node_tree.find(parent_node) != node_tree.end())
+                nodes.push_back(parent_node);
+        }
+        // If parent node given, ...
+        else if (parent_node != "")
+        {
+            // ... look for children nodes of this parent
+            for (auto & sn: node_tree)
+            {
+                auto & props = sn.second.object_items();
+
+                auto parent_prop = props.find("parent");
+                if (parent_prop != props.end() && (parent_prop->second.as_string() == parent_node))
+                {
+                    nodes.push_back(sn.first);
+
+                    // If we're not looking for all osds, we only need a single
+                    // child osd node
+                    if (level != "osd" && stoull_full(sn.first))
+                        break;
+                }
+            }
+        }
+        // No parent node given, and we're not looking for all osds
+        else if (level != "osd")
+        {
+            // ... look for all level nodes
+            for (auto & sn: node_tree)
+            {
+                auto & props = sn.second.object_items();
+
+                auto level_prop = props.find("level");
+                if (level_prop != props.end() && (level_prop->second.as_string() == level))
+                {
+                    nodes.push_back(sn.first);
+                }
+            }
+        }
+        // Otherwise, ...
+        else
+        {
+            // ... we're looking for osd nodes only
+            for (auto & sn: node_tree)
+            {
+                if (stoull_full(sn.first))
+                {
+                    nodes.push_back(sn.first);
+                }
+            }
+        }
+
+        // Process gathered nodes
+        for (auto & node: nodes)
+        {
+            // Check for osd node, return constant max size
+            if (stoull_full(node))
+            {
+                max_pg_sz += 1;
+            }
+            // Otherwise, ...
+            else
+            {
+                // ... exclude parent node from tree, and ...
+                node_tree.erase(parent_node);
+
+                // ... descend onto the resulting tree
+                max_pg_sz += get_max_pg_size(node_tree, level, node);
+            }
+        }
+
+        return max_pg_sz;
+    }
+
+    json11::Json create_pool(const etcd_kv_t & kv)
+    {
+        for (auto & p: kv.value.object_items())
+        {
+            // ID
+            uint64_t pool_id = stoull_full(p.first);
+            new_id = std::max(pool_id+1, new_id);
+            // Name
+            if (p.second["name"].string_value() == cfg["name"].string_value())
+            {
+                return "Pool with name \""+cfg["name"].string_value()+"\" already exists (ID "+std::to_string(pool_id)+")";
+            }
+        }
+        auto res = kv.value.object_items();
+        res[std::to_string(new_id)] = cfg;
+        return res;
+    }
+
+    // Checks whether tags2 tags are all in tags1 tags
+    bool all_in_tags(json11::Json tags1, json11::Json tags2)
+    {
+        if (!tags2.is_array())
+        {
+            tags2 = json11::Json::array{ tags2.string_value() };
+        }
+        if (!tags1.is_array())
+        {
+            tags1 = json11::Json::array{ tags1.string_value() };
+        }
+        for (auto & tag2: tags2.array_items())
+        {
+            bool found = false;
+            for (auto & tag1: tags1.array_items())
+            {
+                if (tag1 == tag2)
+                {
+                    found = true;
+                    break;
+                }
+            }
+            if (!found)
+            {
+                return false;
+            }
+        }
+        return true;
+    }
+};
+
+std::function<bool(cli_result_t &)> cli_tool_t::start_pool_create(json11::Json cfg)
+{
+    auto pool_creator = new pool_creator_t();
+    pool_creator->parent = this;
+    pool_creator->cfg = cfg.object_items();
+    pool_creator->force = cfg["force"].bool_value();
+    pool_creator->wait = cfg["wait"].bool_value();
+    return [pool_creator](cli_result_t & result)
+    {
+        pool_creator->loop();
+        if (pool_creator->is_done())
+        {
+            result = pool_creator->result;
+            delete pool_creator;
+            return true;
+        }
+        return false;
+    };
+}

src/cli_pool_ls.cpp

@@ -0,0 +1,721 @@
+// Copyright (c) Vitaliy Filippov, 2019+
+// License: VNPL-1.1 (see README.md for details)
+
+#include <algorithm>
+#include "cli.h"
+#include "cluster_client.h"
+#include "str_util.h"
+#include "pg_states.h"
+
+// List pools with space statistics
+// - df - minimal list with % used space
+// - pool-ls - same but with PG state and recovery %
+// - pool-ls -l - same but also include I/O statistics
+// - pool-ls --detail - use list format, include PG states, I/O stats and all pool parameters
+struct pool_lister_t
+{
+    cli_tool_t *parent;
+    std::string sort_field;
+    std::set<std::string> only_names;
+    bool reverse = false;
+    int max_count = 0;
+    bool show_recovery = false;
+    bool show_stats = false;
+    bool detailed = false;
+
+    int state = 0;
+    cli_result_t result;
+    std::map<pool_id_t, json11::Json::object> pool_stats;
+    struct io_stats_t
+    {
+        uint64_t count = 0;
+        uint64_t read_iops = 0;
+        uint64_t read_bps = 0;
+        uint64_t read_lat = 0;
+        uint64_t write_iops = 0;
+        uint64_t write_bps = 0;
+        uint64_t write_lat = 0;
+        uint64_t delete_iops = 0;
+        uint64_t delete_bps = 0;
+        uint64_t delete_lat = 0;
+    };
+    struct object_counts_t
+    {
+        uint64_t object_count = 0;
+        uint64_t misplaced_count = 0;
+        uint64_t degraded_count = 0;
+        uint64_t incomplete_count = 0;
+    };
+
+    bool is_done()
+    {
+        return state == 100;
+    }
+
+    void get_pool_stats(int base_state)
+    {
+        if (state == base_state+1)
+            goto resume_1;
+        // Space statistics - pool/stats/<pool>
+        parent->etcd_txn(json11::Json::object {
+            { "success", json11::Json::array {
+                json11::Json::object {
+                    { "request_range", json11::Json::object {
+                        { "key", base64_encode(
+                            parent->cli->st_cli.etcd_prefix+"/pool/stats/"
+                        ) },
+                        { "range_end", base64_encode(
+                            parent->cli->st_cli.etcd_prefix+"/pool/stats0"
+                        ) },
+                    } },
+                },
+                json11::Json::object {
+                    { "request_range", json11::Json::object {
+                        { "key", base64_encode(
+                            parent->cli->st_cli.etcd_prefix+"/osd/stats/"
+                        ) },
+                        { "range_end", base64_encode(
+                            parent->cli->st_cli.etcd_prefix+"/osd/stats0"
+                        ) },
+                    } },
+                },
+                json11::Json::object {
+                    { "request_range", json11::Json::object {
+                        { "key", base64_encode(
+                            parent->cli->st_cli.etcd_prefix+"/config/pools"
+                        ) },
+                    } },
+                },
+            } },
+        });
+        state = base_state+1;
+resume_1:
+        if (parent->waiting > 0)
+            return;
+        if (parent->etcd_err.err)
+        {
+            result = parent->etcd_err;
+            state = 100;
+            return;
+        }
+        auto space_info = parent->etcd_result;
+        auto config_pools = space_info["responses"][2]["response_range"]["kvs"][0];
+        if (!config_pools.is_null())
+        {
+            config_pools = parent->cli->st_cli.parse_etcd_kv(config_pools).value;
+        }
+        for (auto & kv_item: space_info["responses"][0]["response_range"]["kvs"].array_items())
+        {
+            auto kv = parent->cli->st_cli.parse_etcd_kv(kv_item);
+            // pool ID
+            pool_id_t pool_id;
+            char null_byte = 0;
+            int scanned = sscanf(kv.key.substr(parent->cli->st_cli.etcd_prefix.length()).c_str(), "/pool/stats/%u%c", &pool_id, &null_byte);
+            if (scanned != 1 || !pool_id || pool_id >= POOL_ID_MAX)
+            {
+                fprintf(stderr, "Invalid key in etcd: %s\n", kv.key.c_str());
+                continue;
+            }
+            // pool/stats/<N>
+            pool_stats[pool_id] = kv.value.object_items();
+        }
+        std::map<pool_id_t, uint64_t> osd_free;
+        for (auto & kv_item: space_info["responses"][1]["response_range"]["kvs"].array_items())
+        {
+            auto kv = parent->cli->st_cli.parse_etcd_kv(kv_item);
+            // osd ID
+            osd_num_t osd_num;
+            char null_byte = 0;
+            int scanned = sscanf(kv.key.substr(parent->cli->st_cli.etcd_prefix.length()).c_str(), "/osd/stats/%ju%c", &osd_num, &null_byte);
+            if (scanned != 1 || !osd_num || osd_num >= POOL_ID_MAX)
+            {
+                fprintf(stderr, "Invalid key in etcd: %s\n", kv.key.c_str());
+                continue;
+            }
+            // osd/stats/<N>::free
+            osd_free[osd_num] = kv.value["free"].uint64_value();
+        }
+        // Calculate max_avail for each pool
+        for (auto & pp: parent->cli->st_cli.pool_config)
+        {
+            auto & pool_cfg = pp.second;
+            uint64_t pool_avail = UINT64_MAX;
+            std::map<osd_num_t, uint64_t> pg_per_osd;
+            bool active = pool_cfg.real_pg_count > 0;
+            uint64_t pg_states = 0;
+            for (auto & pgp: pool_cfg.pg_config)
+            {
+                if (!(pgp.second.cur_state & PG_ACTIVE))
+                {
+                    active = false;
+                }
+                pg_states |= pgp.second.cur_state;
+                for (auto pg_osd: pgp.second.target_set)
+                {
+                    if (pg_osd != 0)
+                    {
+                        pg_per_osd[pg_osd]++;
+                    }
+                }
+            }
+            for (auto pg_per_pair: pg_per_osd)
+            {
+                uint64_t pg_free = osd_free[pg_per_pair.first] * pool_cfg.real_pg_count / pg_per_pair.second;
+                if (pool_avail > pg_free)
+                {
+                    pool_avail = pg_free;
+                }
+            }
+            if (pool_avail == UINT64_MAX)
+            {
+                pool_avail = 0;
+            }
+            if (pool_cfg.scheme != POOL_SCHEME_REPLICATED)
+            {
+                pool_avail *= (pool_cfg.pg_size - pool_cfg.parity_chunks);
+            }
+            // incomplete > has_incomplete > degraded > has_degraded > has_misplaced
+            std::string status;
+            if (!active)
+                status = "inactive";
+            else if (pg_states & PG_INCOMPLETE)
+                status = "incomplete";
+            else if (pg_states & PG_HAS_INCOMPLETE)
+                status = "has_incomplete";
+            else if (pg_states & PG_DEGRADED)
+                status = "degraded";
+            else if (pg_states & PG_HAS_DEGRADED)
+                status = "has_degraded";
+            else if (pg_states & PG_HAS_MISPLACED)
+                status = "has_misplaced";
+            else
+                status = "active";
+            pool_stats[pool_cfg.id] = json11::Json::object {
+                { "id", (uint64_t)pool_cfg.id },
+                { "name", pool_cfg.name },
+                { "status", status },
+                { "pg_count", pool_cfg.pg_count },
+                { "real_pg_count", pool_cfg.real_pg_count },
+                { "scheme_name", pool_cfg.scheme == POOL_SCHEME_REPLICATED
+                    ? std::to_string(pool_cfg.pg_size)+"/"+std::to_string(pool_cfg.pg_minsize)
+                    : "EC "+std::to_string(pool_cfg.pg_size-pool_cfg.parity_chunks)+"+"+std::to_string(pool_cfg.parity_chunks) },
+                { "used_raw", (uint64_t)(pool_stats[pool_cfg.id]["used_raw_tb"].number_value() * ((uint64_t)1<<40)) },
+                { "total_raw", (uint64_t)(pool_stats[pool_cfg.id]["total_raw_tb"].number_value() * ((uint64_t)1<<40)) },
+                { "max_available", pool_avail },
+                { "raw_to_usable", pool_stats[pool_cfg.id]["raw_to_usable"].number_value() },
+                { "space_efficiency", pool_stats[pool_cfg.id]["space_efficiency"].number_value() },
+                { "pg_real_size", pool_stats[pool_cfg.id]["pg_real_size"].uint64_value() },
+                { "osd_count", pg_per_osd.size() },
+            };
+        }
+        // Include full pool config
+        for (auto & pp: config_pools.object_items())
+        {
+            if (!pp.second.is_object())
+            {
+                continue;
+            }
+            auto pool_id = stoull_full(pp.first);
+            auto & st = pool_stats[pool_id];
+            for (auto & kv: pp.second.object_items())
+            {
+                if (st.find(kv.first) == st.end())
+                    st[kv.first] = kv.second;
+            }
+        }
+    }
+
+    void get_pg_stats(int base_state)
+    {
+        if (state == base_state+1)
+            goto resume_1;
+        // Space statistics - pool/stats/<pool>
+        parent->etcd_txn(json11::Json::object {
+            { "success", json11::Json::array {
+                json11::Json::object {
+                    { "request_range", json11::Json::object {
+                        { "key", base64_encode(
+                            parent->cli->st_cli.etcd_prefix+"/pg/stats/"
+                        ) },
+                        { "range_end", base64_encode(
+                            parent->cli->st_cli.etcd_prefix+"/pg/stats0"
+                        ) },
+                    } },
+                },
+            } },
+        });
+        state = base_state+1;
+resume_1:
+        if (parent->waiting > 0)
+            return;
+        if (parent->etcd_err.err)
+        {
+            result = parent->etcd_err;
+            state = 100;
+            return;
+        }
+        auto pg_stats = parent->etcd_result["responses"][0]["response_range"]["kvs"];
+        // Calculate recovery percent
+        std::map<pool_id_t, object_counts_t> counts;
+        for (auto & kv_item: pg_stats.array_items())
+        {
+            auto kv = parent->cli->st_cli.parse_etcd_kv(kv_item);
+            // pool ID & pg number
+            pool_id_t pool_id;
+            pg_num_t pg_num = 0;
+            char null_byte = 0;
+            int scanned = sscanf(kv.key.substr(parent->cli->st_cli.etcd_prefix.length()).c_str(),
+                "/pg/stats/%u/%u%c", &pool_id, &pg_num, &null_byte);
+            if (scanned != 2 || !pool_id || pool_id >= POOL_ID_MAX)
+            {
+                fprintf(stderr, "Invalid key in etcd: %s\n", kv.key.c_str());
+                continue;
+            }
+            auto & cnt = counts[pool_id];
+            cnt.object_count += kv.value["object_count"].uint64_value();
+            cnt.misplaced_count += kv.value["misplaced_count"].uint64_value();
+            cnt.degraded_count += kv.value["degraded_count"].uint64_value();
+            cnt.incomplete_count += kv.value["incomplete_count"].uint64_value();
+        }
+        for (auto & pp: pool_stats)
+        {
+            auto & cnt = counts[pp.first];
+            auto & st = pp.second;
+            st["object_count"] = cnt.object_count;
+            st["misplaced_count"] = cnt.misplaced_count;
+            st["degraded_count"] = cnt.degraded_count;
+            st["incomplete_count"] = cnt.incomplete_count;
+        }
+    }
+
+    void get_inode_stats(int base_state)
+    {
+        if (state == base_state+1)
+            goto resume_1;
+        // Space statistics - pool/stats/<pool>
+        parent->etcd_txn(json11::Json::object {
+            { "success", json11::Json::array {
+                json11::Json::object {
+                    { "request_range", json11::Json::object {
+                        { "key", base64_encode(
+                            parent->cli->st_cli.etcd_prefix+"/inode/stats/"
+                        ) },
+                        { "range_end", base64_encode(
+                            parent->cli->st_cli.etcd_prefix+"/inode/stats0"
+                        ) },
+                    } },
+                },
+            } },
+        });
+        state = base_state+1;
+resume_1:
+        if (parent->waiting > 0)
+            return;
+        if (parent->etcd_err.err)
+        {
+            result = parent->etcd_err;
+            state = 100;
+            return;
+        }
+        auto inode_stats = parent->etcd_result["responses"][0]["response_range"]["kvs"];
+        // Performance statistics
+        std::map<pool_id_t, io_stats_t> pool_io;
+        for (auto & kv_item: inode_stats.array_items())
+        {
+            auto kv = parent->cli->st_cli.parse_etcd_kv(kv_item);
+            // pool ID & inode number
+            pool_id_t pool_id;
+            inode_t only_inode_num;
+            char null_byte = 0;
+            int scanned = sscanf(kv.key.substr(parent->cli->st_cli.etcd_prefix.length()).c_str(),
+                "/inode/stats/%u/%ju%c", &pool_id, &only_inode_num, &null_byte);
+            if (scanned != 2 || !pool_id || pool_id >= POOL_ID_MAX || INODE_POOL(only_inode_num) != 0)
+            {
+                fprintf(stderr, "Invalid key in etcd: %s\n", kv.key.c_str());
+                continue;
+            }
+            auto & io = pool_io[pool_id];
+            io.read_iops += kv.value["read"]["iops"].uint64_value();
+            io.read_bps += kv.value["read"]["bps"].uint64_value();
+            io.read_lat += kv.value["read"]["lat"].uint64_value();
+            io.write_iops += kv.value["write"]["iops"].uint64_value();
+            io.write_bps += kv.value["write"]["bps"].uint64_value();
+            io.write_lat += kv.value["write"]["lat"].uint64_value();
+            io.delete_iops += kv.value["delete"]["iops"].uint64_value();
+            io.delete_bps += kv.value["delete"]["bps"].uint64_value();
+            io.delete_lat += kv.value["delete"]["lat"].uint64_value();
+            io.count++;
+        }
+        for (auto & pp: pool_stats)
+        {
+            auto & io = pool_io[pp.first];
+            if (io.count > 0)
+            {
+                io.read_lat /= io.count;
+                io.write_lat /= io.count;
+                io.delete_lat /= io.count;
+            }
+            auto & st = pp.second;
+            st["read_iops"] = io.read_iops;
+            st["read_bps"] = io.read_bps;
+            st["read_lat"] = io.read_lat;
+            st["write_iops"] = io.write_iops;
+            st["write_bps"] = io.write_bps;
+            st["write_lat"] = io.write_lat;
+            st["delete_iops"] = io.delete_iops;
+            st["delete_bps"] = io.delete_bps;
+            st["delete_lat"] = io.delete_lat;
+        }
+    }
+
+    json11::Json::array to_list()
+    {
+        json11::Json::array list;
+        for (auto & kv: pool_stats)
+        {
+            if (!only_names.size())
+            {
+                list.push_back(kv.second);
+            }
+            else
+            {
+                for (auto glob: only_names)
+                {
+                    if (stupid_glob(kv.second["name"].string_value(), glob))
+                    {
+                        list.push_back(kv.second);
+                        break;
+                    }
+                }
+            }
+        }
+        if (sort_field == "name" || sort_field == "scheme" ||
+            sort_field == "scheme_name" || sort_field == "status")
+        {
+            std::sort(list.begin(), list.end(), [this](json11::Json a, json11::Json b)
+            {
+                auto av = a[sort_field].as_string();
+                auto bv = b[sort_field].as_string();
+                return reverse ? av > bv : av < bv;
+            });
+        }
+        else
+        {
+            std::sort(list.begin(), list.end(), [this](json11::Json a, json11::Json b)
+            {
+                auto av = a[sort_field].number_value();
+                auto bv = b[sort_field].number_value();
+                return reverse ? av > bv : av < bv;
+            });
+        }
+        if (max_count > 0 && list.size() > max_count)
+        {
+            list.resize(max_count);
+        }
+        return list;
+    }
+
+    void loop()
+    {
+        if (state == 1)
+            goto resume_1;
+        if (state == 2)
+            goto resume_2;
+        if (state == 3)
+            goto resume_3;
+        if (state == 100)
+            return;
+        show_stats = show_stats || detailed;
+        show_recovery = show_recovery || detailed;
+resume_1:
+        get_pool_stats(0);
+        if (parent->waiting > 0)
+            return;
+        if (show_stats)
+        {
+resume_2:
+            get_inode_stats(1);
+            if (parent->waiting > 0)
+                return;
+        }
+        if (show_recovery)
+        {
+resume_3:
+            get_pg_stats(2);
+            if (parent->waiting > 0)
+                return;
+        }
+        if (parent->json_output)
+        {
+            // JSON output
+            result.data = to_list();
+            state = 100;
+            return;
+        }
+        json11::Json::array list;
+        for (auto & kv: pool_stats)
+        {
+            auto & st = kv.second;
+            double raw_to = st["raw_to_usable"].number_value();
+            if (raw_to < 0.000001 && raw_to > -0.000001)
+                raw_to = 1;
+            st["pg_count_fmt"] = st["real_pg_count"] == st["pg_count"]
+                ? st["real_pg_count"].as_string()
+                : st["real_pg_count"].as_string()+"->"+st["pg_count"].as_string();
+            st["total_fmt"] = format_size(st["total_raw"].uint64_value() / raw_to);
+            st["used_fmt"] = format_size(st["used_raw"].uint64_value() / raw_to);
+            st["max_avail_fmt"] = format_size(st["max_available"].uint64_value());
+            st["used_pct"] = format_q(st["total_raw"].uint64_value()
+                ? (100 - 100*st["max_available"].uint64_value() *
+                    st["raw_to_usable"].number_value() / st["total_raw"].uint64_value())
+                : 100)+"%";
+            st["eff_fmt"] = format_q(st["space_efficiency"].number_value()*100)+"%";
+            if (show_stats)
+            {
+                st["read_bw"] = format_size(st["read_bps"].uint64_value())+"/s";
+                st["write_bw"] = format_size(st["write_bps"].uint64_value())+"/s";
+                st["delete_bw"] = format_size(st["delete_bps"].uint64_value())+"/s";
+                st["read_iops"] = format_q(st["read_iops"].number_value());
+                st["write_iops"] = format_q(st["write_iops"].number_value());
+                st["delete_iops"] = format_q(st["delete_iops"].number_value());
+                st["read_lat_f"] = format_lat(st["read_lat"].uint64_value());
+                st["write_lat_f"] = format_lat(st["write_lat"].uint64_value());
+                st["delete_lat_f"] = format_lat(st["delete_lat"].uint64_value());
+            }
+            if (show_recovery)
+            {
+                auto object_count = st["object_count"].uint64_value();
+                auto recovery_pct = 100.0 * (object_count - (st["misplaced_count"].uint64_value() +
+                    st["degraded_count"].uint64_value() + st["incomplete_count"].uint64_value())) /
+                    (object_count ? object_count : 1);
+                st["recovery_fmt"] = format_q(recovery_pct)+"%";
+            }
+        }
+        if (detailed)
+        {
+            for (auto & kv: pool_stats)
+            {
+                auto & st = kv.second;
+                auto total = st["object_count"].uint64_value();
+                auto obj_size = st["block_size"].uint64_value();
+                if (!obj_size)
+                    obj_size = parent->cli->st_cli.global_block_size;
+                if (st["scheme"] == "ec")
+                    obj_size *= st["pg_size"].uint64_value() - st["parity_chunks"].uint64_value();
+                else if (st["scheme"] == "xor")
+                    obj_size *= st["pg_size"].uint64_value() - 1;
+                auto n = st["misplaced_count"].uint64_value();
+                if (n > 0)
+                    st["misplaced_fmt"] = format_size(n * obj_size) + " / " + format_q(100.0 * n / total);
+                n = st["degraded_count"].uint64_value();
+                if (n > 0)
+                    st["degraded_fmt"] = format_size(n * obj_size) + " / " + format_q(100.0 * n / total);
+                n = st["incomplete_count"].uint64_value();
+                if (n > 0)
+                    st["incomplete_fmt"] = format_size(n * obj_size) + " / " + format_q(100.0 * n / total);
+                st["read_fmt"] = st["read_bw"].string_value()+", "+st["read_iops"].string_value()+" op/s, "+
+                    st["read_lat_f"].string_value()+" lat";
+                st["write_fmt"] = st["write_bw"].string_value()+", "+st["write_iops"].string_value()+" op/s, "+
+                    st["write_lat_f"].string_value()+" lat";
+                st["delete_fmt"] = st["delete_bw"].string_value()+", "+st["delete_iops"].string_value()+" op/s, "+
+                    st["delete_lat_f"].string_value()+" lat";
+                if (st["scheme"] == "replicated")
+                    st["scheme_name"] = "x"+st["pg_size"].as_string();
+                if (st["failure_domain"].string_value() == "")
+                    st["failure_domain"] = "host";
+                st["osd_tags_fmt"] = implode(", ", st["osd_tags"]);
+                st["primary_affinity_tags_fmt"] = implode(", ", st["primary_affinity_tags"]);
+                if (st["block_size"].uint64_value())
+                    st["block_size_fmt"] = format_size(st["block_size"].uint64_value());
+                if (st["bitmap_granularity"].uint64_value())
+                    st["bitmap_granularity_fmt"] = format_size(st["bitmap_granularity"].uint64_value());
+            }
+            // All pool parameters are only displayed in the "detailed" mode
+            // because there's too many of them to show them in table
+            auto cols = std::vector<std::pair<std::string, std::string>>{
+                { "name", "Name" },
+                { "id", "ID" },
+                { "scheme_name", "Scheme" },
+                { "status", "Status" },
+                { "pg_count_fmt", "PGs" },
+                { "pg_minsize", "PG minsize" },
+                { "failure_domain", "Failure domain" },
+                { "root_node", "Root node" },
+                { "osd_tags_fmt", "OSD tags" },
+                { "primary_affinity_tags_fmt", "Primary affinity" },
+                { "block_size_fmt", "Block size" },
+                { "bitmap_granularity_fmt", "Bitmap granularity" },
+                { "immediate_commit", "Immediate commit" },
+                { "scrub_interval", "Scrub interval" },
+                { "pg_stripe_size", "PG stripe size" },
+                { "max_osd_combinations", "Max OSD combinations" },
+                { "total_fmt", "Total" },
+                { "used_fmt", "Used" },
+                { "max_avail_fmt", "Available" },
+                { "used_pct", "Used%" },
+                { "eff_fmt", "Efficiency" },
+                { "osd_count", "OSD count" },
+                { "misplaced_fmt", "Misplaced" },
+                { "degraded_fmt", "Degraded" },
+                { "incomplete_fmt", "Incomplete" },
+                { "read_fmt", "Read" },
+                { "write_fmt", "Write" },
+                { "delete_fmt", "Delete" },
+            };
+            auto list = to_list();
+            size_t title_len = 0;
+            for (auto & item: list)
+            {
+                title_len = print_detail_title_len(item, cols, title_len);
+            }
+            for (auto & item: list)
+            {
+                if (result.text != "")
+                    result.text += "\n";
+                result.text += print_detail(item, cols, title_len, parent->color);
+            }
+            state = 100;
+            return;
+        }
+        // Table output: name, scheme_name, pg_count, total, used, max_avail, used%, efficiency
+        json11::Json::array cols;
+        cols.push_back(json11::Json::object{
+            { "key", "name" },
+            { "title", "NAME" },
+        });
+        cols.push_back(json11::Json::object{
+            { "key", "scheme_name" },
+            { "title", "SCHEME" },
+        });
+        cols.push_back(json11::Json::object{
+            { "key", "status" },
+            { "title", "STATUS" },
+        });
+        cols.push_back(json11::Json::object{
+            { "key", "pg_count_fmt" },
+            { "title", "PGS" },
+        });
+        cols.push_back(json11::Json::object{
+            { "key", "total_fmt" },
+            { "title", "TOTAL" },
+        });
+        cols.push_back(json11::Json::object{
+            { "key", "used_fmt" },
+            { "title", "USED" },
+        });
+        cols.push_back(json11::Json::object{
+            { "key", "max_avail_fmt" },
+            { "title", "AVAILABLE" },
+        });
+        cols.push_back(json11::Json::object{
+            { "key", "used_pct" },
+            { "title", "USED%" },
+        });
+        cols.push_back(json11::Json::object{
+            { "key", "eff_fmt" },
+            { "title", "EFFICIENCY" },
+        });
+        if (show_recovery)
+        {
+            cols.push_back(json11::Json::object{ { "key", "recovery_fmt" }, { "title", "RECOVERY" } });
+        }
+        if (show_stats)
+        {
+            cols.push_back(json11::Json::object{ { "key", "read_bw" }, { "title", "READ" } });
+            cols.push_back(json11::Json::object{ { "key", "read_iops" }, { "title", "IOPS" } });
+            cols.push_back(json11::Json::object{ { "key", "read_lat_f" }, { "title", "LAT" } });
+            cols.push_back(json11::Json::object{ { "key", "write_bw" }, { "title", "WRITE" } });
+            cols.push_back(json11::Json::object{ { "key", "write_iops" }, { "title", "IOPS" } });
+            cols.push_back(json11::Json::object{ { "key", "write_lat_f" }, { "title", "LAT" } });
+            cols.push_back(json11::Json::object{ { "key", "delete_bw" }, { "title", "DELETE" } });
+            cols.push_back(json11::Json::object{ { "key", "delete_iops" }, { "title", "IOPS" } });
+            cols.push_back(json11::Json::object{ { "key", "delete_lat_f" }, { "title", "LAT" } });
+        }
+        result.data = to_list();
+        result.text = print_table(result.data, cols, parent->color);
+        state = 100;
+    }
+};
+
+size_t print_detail_title_len(json11::Json item, std::vector<std::pair<std::string, std::string>> names, size_t prev_len)
+{
+    size_t title_len = prev_len;
+    for (auto & kv: names)
+    {
+        if (!item[kv.first].is_null() && (!item[kv.first].is_string() || item[kv.first].string_value() != ""))
+        {
+            size_t len = utf8_length(kv.second);
+            title_len = title_len < len ? len : title_len;
+        }
+    }
+    return title_len;
+}
+
+std::string print_detail(json11::Json item, std::vector<std::pair<std::string, std::string>> names, size_t title_len, bool use_esc)
+{
+    std::string str;
+    for (auto & kv: names)
+    {
+        if (!item[kv.first].is_null() && (!item[kv.first].is_string() || item[kv.first].string_value() != ""))
+        {
+            str += kv.second;
+            str += ": ";
+            size_t len = utf8_length(kv.second);
+            for (int j = 0; j < title_len-len; j++)
+                str += ' ';
+            if (use_esc)
+                str += "\033[1m";
+            str += item[kv.first].as_string();
+            if (use_esc)
+                str += "\033[0m";
+            str += "\n";
+        }
+    }
+    return str;
+}
+
+std::function<bool(cli_result_t &)> cli_tool_t::start_pool_ls(json11::Json cfg)
+{
+    auto lister = new pool_lister_t();
+    lister->parent = this;
+    lister->show_recovery = cfg["show_recovery"].bool_value();
+    lister->show_stats = cfg["long"].bool_value();
+    lister->detailed = cfg["detail"].bool_value();
+    lister->sort_field = cfg["sort"].string_value();
+    if ((lister->sort_field == "osd_tags") ||
+        (lister->sort_field == "primary_affinity_tags" ))
+        lister->sort_field = lister->sort_field + "_fmt";
+    lister->reverse = cfg["reverse"].bool_value();
+    lister->max_count = cfg["count"].uint64_value();
+    for (auto & item: cfg["names"].array_items())
+    {
+        lister->only_names.insert(item.string_value());
+    }
+    return [lister](cli_result_t & result)
+    {
+        lister->loop();
+        if (lister->is_done())
+        {
+            result = lister->result;
+            delete lister;
+            return true;
+        }
+        return false;
+    };
+}
+
+std::string implode(const std::string & sep, json11::Json array)
+{
+    if (array.is_number() || array.is_bool() || array.is_string())
+    {
+        return array.as_string();
+    }
+    std::string res;
+    bool first = true;
+    for (auto & item: array.array_items())
+    {
+        res += (first ? item.as_string() : sep+item.as_string());
+        first = false;
+    }
+    return res;
+}

src/cli_pool_modify.cpp

@@ -0,0 +1,185 @@
+// Copyright (c) MIND Software LLC, 2023 (info@mindsw.io)
+// I accept Vitastor CLA: see CLA-en.md for details
+// Copyright (c) Vitaliy Filippov, 2024
+// License: VNPL-1.1 (see README.md for details)
+
+#include <ctype.h>
+#include "cli.h"
+#include "cli_pool_cfg.h"
+#include "cluster_client.h"
+#include "str_util.h"
+
+struct pool_changer_t
+{
+    cli_tool_t *parent;
+
+    // Required parameters (id/name)
+    pool_id_t pool_id = 0;
+    std::string pool_name;
+    json11::Json::object cfg;
+    json11::Json::object new_cfg;
+    bool force = false;
+
+    json11::Json old_cfg;
+
+    int state = 0;
+    cli_result_t result;
+
+    // Updated pools
+    json11::Json new_pools;
+
+    // Expected pools mod revision
+    uint64_t pools_mod_rev;
+
+    bool is_done() { return state == 100; }
+
+    void loop()
+    {
+        if (state == 1)
+            goto resume_1;
+        else if (state == 2)
+            goto resume_2;
+        pool_id = stoull_full(cfg["old_name"].string_value());
+        if (!pool_id)
+        {
+            pool_name = cfg["old_name"].string_value();
+            if (pool_name == "")
+            {
+                result = (cli_result_t){ .err = ENOENT, .text = "Pool ID or name is required to modify it" };
+                state = 100;
+                return;
+            }
+        }
+resume_0:
+        // Get pools from etcd
+        parent->etcd_txn(json11::Json::object {
+            { "success", json11::Json::array {
+                json11::Json::object {
+                    { "request_range", json11::Json::object {
+                        { "key", base64_encode(parent->cli->st_cli.etcd_prefix+"/config/pools") },
+                    } }
+                },
+            } },
+        });
+        state = 1;
+resume_1:
+        if (parent->waiting > 0)
+            return;
+        if (parent->etcd_err.err)
+        {
+            result = parent->etcd_err;
+            state = 100;
+            return;
+        }
+        {
+            // Parse received pools from etcd
+            auto kv = parent->cli->st_cli.parse_etcd_kv(parent->etcd_result["responses"][0]["response_range"]["kvs"][0]);
+
+            // Get pool by name or ID
+            old_cfg = json11::Json();
+            if (pool_name != "")
+            {
+                for (auto & pce: kv.value.object_items())
+                {
+                    if (pce.second["name"] == pool_name)
+                    {
+                        pool_id = stoull_full(pce.first);
+                        old_cfg = pce.second;
+                        break;
+                    }
+                }
+            }
+            else
+            {
+                pool_name = std::to_string(pool_id);
+                old_cfg = kv.value[pool_name];
+            }
+            if (!old_cfg.is_object())
+            {
+                result = (cli_result_t){ .err = ENOENT, .text = "Pool "+pool_name+" does not exist" };
+                state = 100;
+                return;
+            }
+
+            // Update pool
+            new_cfg = cfg;
+            result.text = validate_pool_config(new_cfg, old_cfg, parent->cli->st_cli.global_block_size,
+                parent->cli->st_cli.global_bitmap_granularity, force);
+            if (result.text != "")
+            {
+                result.err = EINVAL;
+                state = 100;
+                return;
+            }
+
+            // Update pool
+            auto pls = kv.value.object_items();
+            pls[std::to_string(pool_id)] = new_cfg;
+            new_pools = pls;
+
+            // Expected pools mod revision
+            pools_mod_rev = kv.mod_revision;
+        }
+        // Update pools in etcd
+        parent->etcd_txn(json11::Json::object {
+            { "compare", json11::Json::array {
+                json11::Json::object {
+                    { "target", "MOD" },
+                    { "key", base64_encode(parent->cli->st_cli.etcd_prefix+"/config/pools") },
+                    { "result", "LESS" },
+                    { "mod_revision", pools_mod_rev+1 },
+                }
+            } },
+            { "success", json11::Json::array {
+                json11::Json::object {
+                    { "request_put", json11::Json::object {
+                        { "key", base64_encode(parent->cli->st_cli.etcd_prefix+"/config/pools") },
+                        { "value", base64_encode(new_pools.dump()) },
+                    } },
+                },
+            } },
+        });
+        state = 2;
+resume_2:
+        if (parent->waiting > 0)
+            return;
+        if (parent->etcd_err.err)
+        {
+            result = parent->etcd_err;
+            state = 100;
+            return;
+        }
+        if (!parent->etcd_result["succeeded"].bool_value())
+        {
+            // CAS failure - retry
+            fprintf(stderr, "Warning: pool configuration was modified in the meantime by someone else\n");
+            goto resume_0;
+        }
+        // Successfully updated pool
+        result = (cli_result_t){
+            .err = 0,
+            .text = "Pool "+pool_name+" updated",
+            .data = new_pools,
+        };
+        state = 100;
+    }
+};
+
+std::function<bool(cli_result_t &)> cli_tool_t::start_pool_modify(json11::Json cfg)
+{
+    auto pool_changer = new pool_changer_t();
+    pool_changer->parent = this;
+    pool_changer->cfg = cfg.object_items();
+    pool_changer->force = cfg["force"].bool_value();
+    return [pool_changer](cli_result_t & result)
+    {
+        pool_changer->loop();
+        if (pool_changer->is_done())
+        {
+            result = pool_changer->result;
+            delete pool_changer;
+            return true;
+        }
+        return false;
+    };
+}

src/cli_pool_rm.cpp

@@ -0,0 +1,226 @@
+// Copyright (c) MIND Software LLC, 2023 (info@mindsw.io)
+// I accept Vitastor CLA: see CLA-en.md for details
+// Copyright (c) Vitaliy Filippov, 2024
+// License: VNPL-1.1 (see README.md for details)
+
+#include <ctype.h>
+#include "cli.h"
+#include "cluster_client.h"
+#include "str_util.h"
+
+struct pool_remover_t
+{
+    cli_tool_t *parent;
+
+    // Required parameters (id/name)
+
+    pool_id_t pool_id = 0;
+    std::string pool_name;
+
+    // Force removal
+    bool force;
+
+    int state = 0;
+    cli_result_t result;
+
+    // Is pool valid?
+    bool pool_valid = false;
+
+    // Updated pools
+    json11::Json new_pools;
+
+    // Expected pools mod revision
+    uint64_t pools_mod_rev;
+
+    bool is_done() { return state == 100; }
+
+    void loop()
+    {
+        if (state == 1)
+            goto resume_1;
+        else if (state == 2)
+            goto resume_2;
+        else if (state == 3)
+            goto resume_3;
+
+        // Pool name (or id) required
+        if (!pool_id && pool_name == "")
+        {
+            result = (cli_result_t){ .err = EINVAL, .text = "Pool name or id must be given" };
+            state = 100;
+            return;
+        }
+
+        // Validate pool name/id
+
+        // Get pool id by name (if name given)
+        if (pool_name != "")
+        {
+            for (auto & ic: parent->cli->st_cli.pool_config)
+            {
+                if (ic.second.name == pool_name)
+                {
+                    pool_id = ic.first;
+                    pool_valid = 1;
+                    break;
+                }
+            }
+        }
+        // Otherwise, check if given pool id is valid
+        else
+        {
+            // Set pool name from id (for easier logging)
+            pool_name = "id " + std::to_string(pool_id);
+
+            // Look-up pool id in pool_config
+            if (parent->cli->st_cli.pool_config.find(pool_id) != parent->cli->st_cli.pool_config.end())
+            {
+                pool_valid = 1;
+            }
+        }
+
+        // Need a valid pool to proceed
+        if (!pool_valid)
+        {
+            result = (cli_result_t){ .err = ENOENT, .text = "Pool "+pool_name+" does not exist" };
+            state = 100;
+            return;
+        }
+
+        // Unless forced, check if pool has associated Images/Snapshots
+        if (!force)
+        {
+            std::string images;
+
+            for (auto & ic: parent->cli->st_cli.inode_config)
+            {
+                if (pool_id && INODE_POOL(ic.second.num) != pool_id)
+                {
+                    continue;
+                }
+                images += ((images != "") ? ", " : "") + ic.second.name;
+            }
+
+            if (images != "")
+            {
+                result = (cli_result_t){
+                    .err = ENOTEMPTY,
+                    .text =
+                        "Pool "+pool_name+" cannot be removed as it still has the following "
+                        "images/snapshots associated with it: "+images
+                };
+                state = 100;
+                return;
+            }
+        }
+
+        // Proceed to deleting the pool
+        state = 1;
+        do
+        {
+resume_1:
+            // Get pools from etcd
+            parent->etcd_txn(json11::Json::object {
+                { "success", json11::Json::array {
+                    json11::Json::object {
+                        { "request_range", json11::Json::object {
+                            { "key", base64_encode(parent->cli->st_cli.etcd_prefix+"/config/pools") },
+                        } }
+                    },
+                } },
+            });
+            state = 2;
+resume_2:
+            if (parent->waiting > 0)
+                return;
+            if (parent->etcd_err.err)
+            {
+                result = parent->etcd_err;
+                state = 100;
+                return;
+            }
+            {
+                // Parse received pools from etcd
+                auto kv = parent->cli->st_cli.parse_etcd_kv(parent->etcd_result["responses"][0]["response_range"]["kvs"][0]);
+
+                // Remove pool
+                auto p = kv.value.object_items();
+                if (p.erase(std::to_string(pool_id)) != 1)
+                {
+                    result = (cli_result_t){
+                        .err = ENOENT,
+                        .text = "Failed to erase pool "+pool_name+" from: "+kv.value.string_value()
+                    };
+                    state = 100;
+                    return;
+                }
+
+                // Record updated pools
+                new_pools = p;
+
+                // Expected pools mod revision
+                pools_mod_rev = kv.mod_revision;
+            }
+            // Update pools in etcd
+            parent->etcd_txn(json11::Json::object {
+                { "compare", json11::Json::array {
+                    json11::Json::object {
+                        { "target", "MOD" },
+                        { "key", base64_encode(parent->cli->st_cli.etcd_prefix+"/config/pools") },
+                        { "result", "LESS" },
+                        { "mod_revision", pools_mod_rev+1 },
+                    }
+                } },
+                { "success", json11::Json::array {
+                    json11::Json::object {
+                        { "request_put", json11::Json::object {
+                            { "key", base64_encode(parent->cli->st_cli.etcd_prefix+"/config/pools") },
+                            { "value", base64_encode(new_pools.dump()) },
+                        } },
+                    },
+                } },
+            });
+            state = 3;
+resume_3:
+            if (parent->waiting > 0)
+                return;
+            if (parent->etcd_err.err)
+            {
+                result = parent->etcd_err;
+                state = 100;
+                return;
+            }
+        } while (!parent->etcd_result["succeeded"].bool_value());
+
+        // Successfully deleted pool
+        result = (cli_result_t){
+            .err = 0,
+            .text = "Pool "+pool_name+" deleted",
+            .data = new_pools
+        };
+        state = 100;
+    }
+};
+
+std::function<bool(cli_result_t &)> cli_tool_t::start_pool_rm(json11::Json cfg)
+{
+    auto pool_remover = new pool_remover_t();
+    pool_remover->parent = this;
+
+    pool_remover->pool_id = cfg["pool"].uint64_value();
+    pool_remover->pool_name = pool_remover->pool_id ? "" : cfg["pool"].as_string();
+
+    pool_remover->force = !cfg["force"].is_null();
+
+    return [pool_remover](cli_result_t & result)
+    {
+        pool_remover->loop();
+        if (pool_remover->is_done())
+        {
+            result = pool_remover->result;
+            delete pool_remover;
+            return true;
+        }
+        return false;
+    };
+}

src/cli_rm.cpp

@@ -53,6 +53,8 @@ struct snap_remover_t
     int use_cas = 1;
     // interval between fsyncs
     int fsync_interval = 128;
+    // ignore deletion errors
+    bool down_ok = false;
 
     std::map<inode_t,int> sources;
     std::map<inode_t,uint64_t> inode_used;
@@ -245,6 +247,7 @@ resume_8:
         }
         state = 100;
         result = (cli_result_t){
+            .err = 0,
             .text = "",
             .data = my_result(result.data),
         };
@@ -679,6 +682,7 @@ resume_100:
             { "inode", inode },
             { "pool", (uint64_t)INODE_POOL(inode) },
             { "fsync-interval", fsync_interval },
+            { "down-ok", down_ok },
         });
     }
 };
@@ -690,6 +694,7 @@ std::function<bool(cli_result_t &)> cli_tool_t::start_rm(json11::Json cfg)
     snap_remover->from_name = cfg["from"].string_value();
     snap_remover->to_name = cfg["to"].string_value();
     snap_remover->fsync_interval = cfg["fsync_interval"].uint64_value();
+    snap_remover->down_ok = cfg["down_ok"].bool_value();
     if (!snap_remover->fsync_interval)
         snap_remover->fsync_interval = 128;
     if (!cfg["cas"].is_null())

src/cli_rm_data.cpp

@@ -25,6 +25,7 @@ struct rm_inode_t
     uint64_t inode = 0;
     pool_id_t pool_id = 0;
     uint64_t min_offset = 0;
+    bool down_ok = false;
 
     cli_tool_t *parent = NULL;
     inode_list_t *lister = NULL;
@@ -212,7 +213,9 @@ struct rm_inode_t
         }
         if (parent->progress && total_count > 0 && total_done*1000/total_count != total_prev_pct)
         {
-            fprintf(stderr, "\rRemoved %ju/%ju objects, %ju more PGs to list...", total_done, total_count, pgs_to_list);
+            fprintf(stderr, parent->color
+                ? "\rRemoved %ju/%ju objects, %ju more PGs to list..."
+                : "Removed %ju/%ju objects, %ju more PGs to list...\n", total_done, total_count, pgs_to_list);
             total_prev_pct = total_done*1000/total_count;
         }
         if (lists_done && !lists.size())
@@ -221,17 +224,18 @@ struct rm_inode_t
             {
                 fprintf(stderr, "\n");
             }
-            if (parent->progress && (total_done < total_count || inactive_osds.size() > 0 || error_count > 0))
+            bool is_error = (total_done < total_count || inactive_osds.size() > 0 || error_count > 0);
+            if (parent->progress && is_error)
             {
                 fprintf(
                     stderr, "Warning: Pool:%u,ID:%ju inode data may not have been fully removed.\n"
-                    " Use `vitastor-cli rm-data --pool %u --inode %ju` if you encounter it in listings.\n",
+                    "Use `vitastor-cli rm-data --pool %u --inode %ju` if you encounter it in listings.\n",
                     pool_id, INODE_NO_POOL(inode), pool_id, INODE_NO_POOL(inode)
                 );
             }
             result = (cli_result_t){
-                .err = error_count > 0 ? EIO : 0,
-                .text = error_count > 0 ? "Some blocks were not removed" : (
+                .err = is_error && !down_ok ? EIO : 0,
+                .text = is_error ? "Some blocks were not removed" : (
                     "Done, inode "+std::to_string(INODE_NO_POOL(inode))+" from pool "+
                     std::to_string(pool_id)+" removed"),
                 .data = json11::Json::object {
@@ -280,6 +284,7 @@ std::function<bool(cli_result_t &)> cli_tool_t::start_rm_data(json11::Json cfg)
     {
         remover->inode = (remover->inode & (((uint64_t)1 << (64-POOL_ID_BITS)) - 1)) | (((uint64_t)remover->pool_id) << (64-POOL_ID_BITS));
     }
+    remover->down_ok = cfg["down_ok"].bool_value();
     remover->pool_id = INODE_POOL(remover->inode);
     remover->min_offset = cfg["min_offset"].uint64_value();
     return [remover](cli_result_t & result)

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();
 
@@ -265,7 +265,7 @@ void cluster_client_t::erase_op(cluster_op_t *op)
     }
 }
 
-void cluster_client_t::continue_ops(bool up_retry)
+void cluster_client_t::continue_ops(int time_passed)
 {
     if (!pgs_loaded)
     {
@@ -277,22 +277,27 @@ void cluster_client_t::continue_ops(bool up_retry)
         // Attempt to reenter the function
         return;
     }
+    int reset_duration = 0;
 restart:
     continuing_ops = 1;
     for (auto op = op_queue_head; op; )
     {
         cluster_op_t *next_op = op->next;
-        if (!op->up_wait || up_retry)
+        if (op->retry_after && time_passed)
         {
-            op->up_wait = false;
-            if (!op->prev_wait)
+            op->retry_after = op->retry_after > time_passed ? op->retry_after-time_passed : 0;
+            if (op->retry_after && (!reset_duration || op->retry_after < reset_duration))
+            {
+                reset_duration = op->retry_after;
+            }
+        }
+        if (!op->retry_after && !op->prev_wait)
         {
             if (op->opcode == OSD_OP_SYNC)
                 continue_sync(op);
             else
                 continue_rw(op);
         }
-        }
         op = next_op;
         if (continuing_ops == 2)
         {
@@ -300,6 +305,27 @@ restart:
         }
     }
     continuing_ops = 0;
+    reset_retry_timer(reset_duration);
+}
+
+void cluster_client_t::reset_retry_timer(int new_duration)
+{
+    if (retry_timeout_duration && retry_timeout_duration <= new_duration || !new_duration)
+    {
+        return;
+    }
+    if (retry_timeout_id)
+    {
+        tfd->clear_timer(retry_timeout_id);
+    }
+    retry_timeout_duration = new_duration;
+    retry_timeout_id = tfd->set_timer(retry_timeout_duration, false, [this](int)
+    {
+        int time_passed = retry_timeout_duration;
+        retry_timeout_id = 0;
+        retry_timeout_duration = 0;
+        continue_ops(time_passed);
+    });
 }
 
 void cluster_client_t::on_load_config_hook(json11::Json::object & etcd_global_config)
@@ -349,15 +375,25 @@ void cluster_client_t::on_load_config_hook(json11::Json::object & etcd_global_co
     {
         client_max_writeback_iodepth = DEFAULT_CLIENT_MAX_WRITEBACK_IODEPTH;
     }
-    // up_wait_retry_interval
-    up_wait_retry_interval = config["up_wait_retry_interval"].uint64_value();
-    if (!up_wait_retry_interval)
+    // client_retry_interval
+    client_retry_interval = config["client_retry_interval"].uint64_value();
+    if (!client_retry_interval)
     {
-        up_wait_retry_interval = 50;
+        client_retry_interval = 50;
     }
-    else if (up_wait_retry_interval < 10)
+    else if (client_retry_interval < 10)
     {
-        up_wait_retry_interval = 10;
+        client_retry_interval = 10;
+    }
+    // client_eio_retry_interval
+    client_eio_retry_interval = 1000;
+    if (!config["client_eio_retry_interval"].is_null())
+    {
+        client_eio_retry_interval = config["client_eio_retry_interval"].uint64_value();
+        if (client_eio_retry_interval && client_eio_retry_interval < 10)
+        {
+            client_eio_retry_interval = 10;
+        }
     }
     // log_level
     log_level = config["log_level"].uint64_value();
@@ -534,7 +570,7 @@ 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 +591,7 @@ 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);
         }
@@ -716,15 +752,8 @@ resume_1:
                 // We'll need to retry again
                 if (op->parts[i].flags & PART_RETRY)
                 {
-                    op->up_wait = true;
-                    if (!retry_timeout_id)
-                    {
-                        retry_timeout_id = tfd->set_timer(up_wait_retry_interval, false, [this](int)
-                        {
-                            retry_timeout_id = 0;
-                            continue_ops(true);
-                        });
-                    }
+                    op->retry_after = client_retry_interval;
+                    reset_retry_timer(client_retry_interval);
                 }
                 op->state = 1;
             }
@@ -780,10 +809,9 @@ resume_2:
         return 1;
     }
     else if (op->retval != 0 && !(op->flags & OP_FLUSH_BUFFER) &&
-        op->retval != -EPIPE && op->retval != -EIO && op->retval != -ENOSPC)
+        op->retval != -EPIPE && (op->retval != -EIO || !client_eio_retry_interval) && op->retval != -ENOSPC)
     {
         // Fatal error (neither -EPIPE, -EIO nor -ENOSPC)
-        // FIXME: Add a parameter to allow to not wait for EIOs (incomplete or corrupted objects) to heal
         erase_op(op);
         return 1;
     }
@@ -1161,7 +1189,7 @@ 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 %ju: retval=%jd (expected %d)\n",
@@ -1171,16 +1199,12 @@ void cluster_client_t::handle_op_part(cluster_op_part_t *part)
         // All next things like timer, continue_sync/rw and stop_client may affect the operation again
         // So do all these things after modifying operation state, otherwise we may hit reenterability bugs
         // FIXME postpone such things to set_immediate here to avoid bugs
-        // Mark op->up_wait = true to retry operation after a short pause (not immediately)
-        op->up_wait = true;
-        if (!retry_timeout_id)
+        // Set op->retry_after to retry operation after a short pause (not immediately)
+        if (!op->retry_after)
         {
-            retry_timeout_id = tfd->set_timer(up_wait_retry_interval, false, [this](int)
-            {
-                retry_timeout_id = 0;
-                continue_ops(true);
-            });
+            op->retry_after = op->retval == -EIO ? client_eio_retry_interval : client_retry_interval;
         }
+        reset_retry_timer(op->retry_after);
         if (op->inflight_count == 0)
         {
             if (op->opcode == OSD_OP_SYNC)

src/cluster_client.h

@@ -59,7 +59,7 @@ protected:
     void *buf = NULL;
     cluster_op_t *orig_op = NULL;
     bool needs_reslice = false;
-    bool up_wait = false;
+    int retry_after = 0;
     int inflight_count = 0, done_count = 0;
     std::vector<cluster_op_part_t> parts;
     void *part_bitmaps = NULL;
@@ -92,9 +92,11 @@ class cluster_client_t
     uint64_t client_max_writeback_iodepth = 0;
 
     int log_level = 0;
-    int up_wait_retry_interval = 500; // ms
+    int client_retry_interval = 50; // ms
+    int client_eio_retry_interval = 1000; // ms
 
     int retry_timeout_id = 0;
+    int retry_timeout_duration = 0;
     std::vector<cluster_op_t*> offline_ops;
     cluster_op_t *op_queue_head = NULL, *op_queue_tail = NULL;
     writeback_cache_t *wb = NULL;
@@ -121,7 +123,7 @@ 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);
@@ -131,7 +133,7 @@ public:
 
     bool get_immediate_commit(uint64_t inode);
 
-    void continue_ops(bool up_retry = false);
+    void continue_ops(int time_passed = 0);
     inode_list_t *list_inode_start(inode_t inode,
         std::function<void(inode_list_t* lst, std::set<object_id>&& objects, pg_num_t pg_num, osd_num_t primary_osd, int status)> callback);
     int list_pg_count(inode_list_t *lst);
@@ -152,6 +154,7 @@ protected:
     int continue_rw(cluster_op_t *op);
     bool check_rw(cluster_op_t *op);
     void slice_rw(cluster_op_t *op);
+    void reset_retry_timer(int new_duration);
     bool try_send(cluster_op_t *op, int i);
     int continue_sync(cluster_op_t *op);
     void send_sync(cluster_op_t *op, cluster_op_part_t *part);

src/etcd_state_client.cpp

@@ -573,8 +573,7 @@ void etcd_state_client_t::load_global_config()
         {
             global_bitmap_granularity = DEFAULT_BITMAP_GRANULARITY;
         }
-        global_immediate_commit = global_config["immediate_commit"].string_value() == "all"
-            ? IMMEDIATE_ALL : (global_config["immediate_commit"].string_value() == "small" ? IMMEDIATE_SMALL : IMMEDIATE_NONE);
+        global_immediate_commit = parse_immediate_commit(global_config["immediate_commit"].string_value());
         on_load_config_hook(global_config);
     });
 }
@@ -782,13 +781,8 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
             // Failure Domain
             pc.failure_domain = pool_item.second["failure_domain"].string_value();
             // Coding Scheme
-            if (pool_item.second["scheme"] == "replicated")
-                pc.scheme = POOL_SCHEME_REPLICATED;
-            else if (pool_item.second["scheme"] == "xor")
-                pc.scheme = POOL_SCHEME_XOR;
-            else if (pool_item.second["scheme"] == "ec" || pool_item.second["scheme"] == "jerasure")
-                pc.scheme = POOL_SCHEME_EC;
-            else
+            pc.scheme = parse_scheme(pool_item.second["scheme"].string_value());
+            if (!pc.scheme)
             {
                 fprintf(stderr, "Pool %u has invalid coding scheme (one of \"xor\", \"replicated\", \"ec\" or \"jerasure\" required), skipping pool\n", pool_id);
                 continue;
@@ -871,9 +865,7 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
                 pc.scrub_interval = 0;
             // Immediate Commit Mode
             pc.immediate_commit = pool_item.second["immediate_commit"].is_string()
-                ? (pool_item.second["immediate_commit"].string_value() == "all"
-                    ? IMMEDIATE_ALL : (pool_item.second["immediate_commit"].string_value() == "small"
-                        ? IMMEDIATE_SMALL : IMMEDIATE_NONE))
+                ? parse_immediate_commit(pool_item.second["immediate_commit"].string_value())
                 : global_immediate_commit;
             // PG Stripe Size
             pc.pg_stripe_size = pool_item.second["pg_stripe_size"].uint64_value();
@@ -1167,6 +1159,23 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
     }
 }
 
+uint32_t etcd_state_client_t::parse_immediate_commit(const std::string & immediate_commit_str)
+{
+    return immediate_commit_str == "all" ? IMMEDIATE_ALL :
+        (immediate_commit_str == "small" ? IMMEDIATE_SMALL : IMMEDIATE_NONE);
+}
+
+uint32_t etcd_state_client_t::parse_scheme(const std::string & scheme)
+{
+    if (scheme == "replicated")
+        return POOL_SCHEME_REPLICATED;
+    else if (scheme == "xor")
+        return POOL_SCHEME_XOR;
+    else if (scheme == "ec" || scheme == "jerasure")
+        return POOL_SCHEME_EC;
+    return 0;
+}
+
 void etcd_state_client_t::insert_inode_config(const inode_config_t & cfg)
 {
     this->inode_config[cfg.num] = cfg;

src/etcd_state_client.h

@@ -151,4 +151,7 @@ public:
     void close_watch(inode_watch_t* watch);
     int address_count();
     ~etcd_state_client_t();
+
+    static uint32_t parse_immediate_commit(const std::string & immediate_commit_str);
+    static uint32_t parse_scheme(const std::string & scheme_str);
 };

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;
+}

src/kv_db.h

@@ -0,0 +1,36 @@
+// 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* 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;
+};

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;
+}

src/osd.cpp

@@ -48,6 +48,15 @@ osd_t::osd_t(const json11::Json & config, ring_loop_t *ringloop)
     {
         auto bs_cfg = json_to_bs(this->config);
         this->bs = new blockstore_t(bs_cfg, ringloop, tfd);
+        // Wait for blockstore initialisation before actually starting OSD logic
+        // to prevent peering timeouts during restart with filled databases
+        while (!bs->is_started())
+        {
+            ringloop->loop();
+            if (bs->is_started())
+                break;
+            ringloop->wait();
+        }
         // Autosync based on the number of unstable writes to prevent stalls due to insufficient journal space
         uint64_t max_autosync = bs->get_journal_size() / bs->get_block_size() / 2;
         if (autosync_writes > max_autosync)

src/osd_id.h

@@ -3,6 +3,8 @@
 
 #pragma once
 
+#include "object_id.h"
+
 #define POOL_SCHEME_REPLICATED 1
 #define POOL_SCHEME_XOR 2
 #define POOL_SCHEME_EC 3

src/str_util.cpp

@@ -214,7 +214,10 @@ void print_help(const char *help_text, std::string exe_name, std::string cmd, bo
             else if (*next_line && isspace(*next_line))
                 started = true;
             else if (cmd_start && matched)
+            {
                 filtered_text += std::string(cmd_start, next_line-cmd_start);
+                matched = started = false;
+            }
         }
         while (filtered_text.size() > 1 &&
             filtered_text[filtered_text.size()-1] == '\n' &&
@@ -324,3 +327,24 @@ size_t utf8_length(const char *s)
         len += (*s & 0xC0) != 0x80;
     return len;
 }
+
+std::vector<std::string> explode(const std::string & sep, const std::string & value, bool trim)
+{
+    std::vector<std::string> res;
+    size_t prev = 0;
+    while (prev < value.size())
+    {
+        while (trim && prev < value.size() && isspace(value[prev]))
+            prev++;
+        size_t pos = value.find(sep, prev);
+        if (pos == std::string::npos)
+            pos = value.size();
+        size_t next = pos+sep.size();
+        while (trim && pos > prev && isspace(value[pos-1]))
+            pos--;
+        if (!trim || pos > prev)
+            res.push_back(value.substr(prev, pos-prev));
+        prev = next;
+    }
+    return res;
+}

src/str_util.h

@@ -4,6 +4,7 @@
 #pragma once
 #include <stdint.h>
 #include <string>
+#include <vector>
 
 std::string base64_encode(const std::string &in);
 std::string base64_decode(const std::string &in);
@@ -20,3 +21,4 @@ std::string read_all_fd(int fd);
 std::string str_repeat(const std::string & str, int times);
 size_t utf8_length(const std::string & s);
 size_t utf8_length(const char *s);
+std::vector<std::string> explode(const std::string & sep, const std::string & value, bool trim);

src/vitastor.pc.in

@@ -6,7 +6,7 @@ includedir=${prefix}/@CMAKE_INSTALL_INCLUDEDIR@
 
 Name: Vitastor
 Description: Vitastor client library
-Version: 1.4.7
+Version: 1.4.8
 Libs: -L${libdir} -lvitastor_client
 Cflags: -I${includedir}
 

tests/test_failure_domain.sh

@@ -13,7 +13,14 @@ $ETCDCTL put /vitastor/osd/stats/5 '{"host":"host3","size":1073741824,"time":"'$
 $ETCDCTL put /vitastor/osd/stats/6 '{"host":"host3","size":1073741824,"time":"'$TIME'"}'
 $ETCDCTL put /vitastor/osd/stats/7 '{"host":"host4","size":1073741824,"time":"'$TIME'"}'
 $ETCDCTL put /vitastor/osd/stats/8 '{"host":"host4","size":1073741824,"time":"'$TIME'"}'
-$ETCDCTL put /vitastor/config/pools '{"1":{"name":"testpool","scheme":"replicated","pg_size":2,"pg_minsize":1,"pg_count":4,"failure_domain":"rack"}}'
+build/src/vitastor-cli --etcd_address $ETCD_URL create-pool testpool --ec 3+2 -n 32 --failure_domain rack --force
+$ETCDCTL get --print-value-only /vitastor/config/pools | jq -s -e '. == [{"1": {"failure_domain": "rack", "name": "testpool", "parity_chunks": 2, "pg_count": 32, "pg_minsize": 4, "pg_size": 5, "scheme": "ec"}}]'
+build/src/vitastor-cli --etcd_address $ETCD_URL modify-pool testpool --ec 3+3 --failure_domain host
+$ETCDCTL get --print-value-only /vitastor/config/pools | jq -s -e '. == [{"1": {"failure_domain": "host", "name": "testpool", "parity_chunks": 3, "pg_count": 32, "pg_minsize": 4, "pg_size": 6, "scheme": "ec"}}]'
+build/src/vitastor-cli --etcd_address $ETCD_URL rm-pool testpool
+$ETCDCTL get --print-value-only /vitastor/config/pools | jq -s -e '. == [{}]'
+build/src/vitastor-cli --etcd_address $ETCD_URL create-pool testpool -s 2 -n 4 --failure_domain rack --force
+$ETCDCTL get --print-value-only /vitastor/config/pools | jq -s -e '. == [{"1":{"name":"testpool","scheme":"replicated","pg_size":2,"pg_minsize":1,"pg_count":4,"failure_domain":"rack"}}]'
 
 node mon/mon-main.js --etcd_address $ETCD_URL --etcd_prefix "/vitastor" >>./testdata/mon.log 2>&1 &
 MON_PID=$!