Add Hugo-based (https://gohugo.io) documentation

Return results and errors in a variable instead of just printing them,
separate vitastor-cli main() from cli_tool_t, move positional argument
parsing to CLI main from command implementations.

CMakeLists.txt

@@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8)
 
 project(vitastor)
 
-set(VERSION "0.6.8")
+set(VERSION "0.6.17")
 
 add_subdirectory(src)

README-ru.md

@@ -51,13 +51,14 @@ Vitastor на данный момент находится в статусе п
 - Базовая поддержка OpenStack: драйвер Cinder, патчи для Nova и libvirt
 - Слияние снапшотов (vitastor-cli {snap-rm,flatten,merge})
 - Консольный интерфейс для управления образами (vitastor-cli {ls,create,modify})
+- Плагин для Proxmox
+- Упрощённая NFS-прокси для эмуляции файлового доступа к образам (подходит для VMWare)
 
 ## Планы развития
 
-- Поддержка удаления снапшотов (слияния слоёв)
 - Более корректные скрипты разметки дисков и автоматического запуска OSD
 - Другие инструменты администрирования
-- Плагины для OpenNebula, Proxmox и других облачных систем
+- Плагины для OpenNebula и других облачных систем
 - iSCSI-прокси
 - Более быстрое переключение при отказах
 - Фоновая проверка целостности без контрольных сумм (сверка реплик)
@@ -403,12 +404,29 @@ Vitastor с однопоточной NBD прокси на том же стен
   в этом случае пострадает.
 - Быстрая сеть, минимум 10 гбит/с
 - Для наилучшей производительности нужно отключить энергосбережение CPU: `cpupower idle-set -D 0 && cpupower frequency-set -g performance`.
-- Пропишите нужные вам значения вверху файлов `/usr/lib/vitastor/mon/make-units.sh` и `/usr/lib/vitastor/mon/make-osd.sh`.
-- Создайте юниты systemd для etcd и мониторов: `/usr/lib/vitastor/mon/make-units.sh`
-- Создайте юниты для OSD: `/usr/lib/vitastor/mon/make-osd.sh /dev/disk/by-partuuid/XXX [/dev/disk/by-partuuid/YYY ...]`
-- Вы можете поменять параметры OSD в юнитах systemd. Смысл некоторых параметров:
+- На хостах мониторов:
+  - Пропишите нужные вам значения в файле `/usr/lib/vitastor/mon/make-units.sh`
+  - Создайте юниты systemd для etcd и мониторов: `/usr/lib/vitastor/mon/make-units.sh`
+- Запустите etcd и мониторы: `systemctl start etcd vitastor-mon`
+- Пропишите etcd_address и osd_network в `/etc/vitastor/vitastor.conf`. Например:
+  ```
+  {
+    "etcd_address": ["10.200.1.10:2379","10.200.1.11:2379","10.200.1.12:2379"],
+    "osd_network": "10.200.1.0/24"
+  }
+  ```
+- Инициализуйте OSD:
+  - SSD: `/usr/lib/vitastor/make-osd.sh /dev/disk/by-partuuid/XXX [/dev/disk/by-partuuid/YYY ...]`
+  - Гибридные, HDD+SSD: `/usr/lib/vitastor/mon/make-osd-hybrid.js /dev/sda /dev/sdb ...` - передайте
+    все ваши SSD и HDD скрипту в командной строке подряд, скрипт автоматически выделит разделы под
+    журналы на SSD и данные на HDD. Скрипт пропускает HDD, на которых уже есть разделы
+    или вообще какие-то данные, поэтому если диски непустые, сначала очистите их с помощью
+    `wipefs -a`. SSD с таблицей разделов не пропускаются, но так как скрипт создаёт новые разделы
+    для журналов, на SSD должно быть доступно свободное нераспределённое место.
+- Вы можете менять параметры OSD в юнитах systemd или в `vitastor.conf`. Смысл некоторых параметров:
   - `disable_data_fsync 1` - отключает fsync, используется с SSD с конденсаторами.
   - `immediate_commit all` - используется с SSD с конденсаторами.
+    Внимание: если установлено, также нужно установить его в то же значение в etcd в /vitastor/config/global
   - `disable_device_lock 1` - отключает блокировку файла устройства, нужно, только если вы запускаете
     несколько OSD на одном блочном устройстве.
   - `flusher_count 256` - "flusher" - микропоток, удаляющий старые данные из журнала.
@@ -420,7 +438,6 @@ Vitastor с однопоточной NBD прокси на том же стен
     диски, используемые на одном из тестовых стендов - Intel D3-S4510 - очень сильно не любят такую
     перезапись, и для них была добавлена эта опция. Когда данный режим включён, также нужно поднимать
     значение `journal_sector_buffer_count`, так как иначе Vitastor не хватит буферов для записи в журнал.
-- Запустите все etcd: `systemctl start etcd`
 - Создайте глобальную конфигурацию в etcd: `etcdctl --endpoints=... put /vitastor/config/global '{"immediate_commit":"all"}'`
   (если все ваши диски - серверные с конденсаторами).
 - Создайте пулы: `etcdctl --endpoints=... put /vitastor/config/pools '{"1":{"name":"testpool","scheme":"replicated","pg_size":2,"pg_minsize":1,"pg_count":256,"failure_domain":"host"}}'`.
@@ -513,9 +530,48 @@ vitastor-nbd map --etcd_address 10.115.0.10:2379/v3 --image testimg
 Для обращения по номеру инода, аналогично другим командам, можно использовать опции
 `--pool <POOL> --inode <INODE> --size <SIZE>` вместо `--image testimg`.
 
+### NFS
+
+В Vitastor реализована упрощённая NFS 3.0 прокси для эмуляции файлового доступа к образам.
+Это не полноценная файловая система, т.к. метаданные всех файлов (образов) сохраняются
+в etcd и всё время хранятся в оперативной памяти - то есть, положить туда много файлов
+не получится.
+
+Однако в качестве способа доступа к образам виртуальных машин NFS прокси прекрасно подходит
+и позволяет подключить Vitastor, например, к VMWare.
+
+При этом, если вы используете режим immediate_commit=all (для SSD с конденсаторами или HDD
+с отключённым кэшем), то NFS-сервер не имеет состояния и вы можете свободно поднять
+его в нескольких экземплярах и использовать поверх них сетевой балансировщик нагрузки или
+схему с отказоустойчивостью.
+
+Использование vitastor-nfs:
+
+```
+vitastor-nfs [--etcd_address ADDR] [ДРУГИЕ ОПЦИИ]
+
+--subdir <DIR>    экспортировать "поддиректорию" - образы с префиксом имени <DIR>/ (по умолчанию пусто - экспортировать все образы)
+--portmap 0       отключить сервис portmap/rpcbind на порту 111 (по умолчанию включён и требует root привилегий)
+--bind <IP>       принимать соединения по адресу <IP> (по умолчанию 0.0.0.0 - на всех)
+--nfspath <PATH>  установить путь NFS-экспорта в <PATH> (по умолчанию /)
+--port <PORT>     использовать порт <PORT> для NFS-сервисов (по умолчанию 2049)
+--pool <POOL>     исползовать пул <POOL> для новых образов (обязательно, если пул в кластере не один)
+--foreground 1    не уходить в фон после запуска
+```
+
+Пример монтирования Vitastor через NFS:
+
+```
+vitastor-nfs --etcd_address 192.168.5.10:2379 --portmap 0 --port 2050 --pool testpool
+```
+
+```
+mount localhost:/ /mnt/ -o port=2050,mountport=2050,nfsvers=3,soft,nolock,tcp
+```
+
 ### Kubernetes
 
-У Vitastor есть CSI-плагин для Kubernetes, поддерживающий RWO-тома.
+У Vitastor есть CSI-плагин для Kubernetes, поддерживающий RWO, а также блочные RWX, тома.
 
 Для установки возьмите манифесты из директории [csi/deploy/](csi/deploy/), поместите
 вашу конфигурацию подключения к Vitastor в [csi/deploy/001-csi-config-map.yaml](001-csi-config-map.yaml),
@@ -528,6 +584,75 @@ for i in ./???-*.yaml; do kubectl apply -f $i; done
 
 После этого вы сможете создавать PersistentVolume. Пример смотрите в файле [csi/deploy/example-pvc.yaml](csi/deploy/example-pvc.yaml).
 
+### OpenStack
+
+Чтобы подключить Vitastor к OpenStack:
+
+- Установите пакеты vitastor-client, libvirt и QEMU из DEB или RPM репозитория Vitastor
+- Примените патч `patches/nova-21.diff` или `patches/nova-23.diff` к вашей инсталляции Nova.
+  nova-21.diff подходит для Nova 21-22, nova-23.diff подходит для Nova 23-24.
+- Скопируйте `patches/cinder-vitastor.py` в инсталляцию Cinder как `cinder/volume/drivers/vitastor.py`
+- Создайте тип томов в cinder.conf (см. ниже)
+- Обязательно заблокируйте доступ от виртуальных машин к сети Vitastor (OSD и etcd), т.к. Vitastor (пока) не поддерживает аутентификацию
+- Перезапустите Cinder и Nova
+
+Пример конфигурации Cinder:
+
+```
+[DEFAULT]
+enabled_backends = lvmdriver-1, vitastor-testcluster
+# ...
+
+[vitastor-testcluster]
+volume_driver = cinder.volume.drivers.vitastor.VitastorDriver
+volume_backend_name = vitastor-testcluster
+image_volume_cache_enabled = True
+volume_clear = none
+vitastor_etcd_address = 192.168.7.2:2379
+vitastor_etcd_prefix =
+vitastor_config_path = /etc/vitastor/vitastor.conf
+vitastor_pool_id = 1
+image_upload_use_cinder_backend = True
+```
+
+Чтобы помещать в Vitastor Glance-образы, нужно использовать
+[https://docs.openstack.org/cinder/pike/admin/blockstorage-volume-backed-image.html](образы на основе томов Cinder),
+однако, поддержка этой функции ещё не проверялась.
+
+### Proxmox
+
+Чтобы подключить Vitastor к Proxmox Virtual Environment (поддерживаются версии 6.4 и 7.1):
+
+- Добавьте соответствующий Debian-репозиторий Vitastor в sources.list на хостах Proxmox
+  (buster для 6.4, bullseye для 7.1)
+- Установите пакеты vitastor-client, pve-qemu-kvm, pve-storage-vitastor (* или см. сноску) из репозитория Vitastor
+- Определите тип хранилища в `/etc/pve/storage.cfg` (см. ниже)
+- Обязательно заблокируйте доступ от виртуальных машин к сети Vitastor (OSD и etcd), т.к. Vitastor (пока) не поддерживает аутентификацию
+- Перезапустите демон Proxmox: `systemctl restart pvedaemon`
+
+Пример `/etc/pve/storage.cfg` (единственная обязательная опция - vitastor_pool, все остальные
+перечислены внизу для понимания значений по умолчанию):
+
+```
+vitastor: vitastor
+    # Пул, в который будут помещаться образы дисков
+    vitastor_pool testpool
+    # Путь к файлу конфигурации
+    vitastor_config_path /etc/vitastor/vitastor.conf
+    # Адрес(а) etcd, нужны, только если не указаны в vitastor.conf
+    vitastor_etcd_address 192.168.7.2:2379/v3
+    # Префикс ключей метаданных в etcd
+    vitastor_etcd_prefix /vitastor
+    # Префикс имён образов
+    vitastor_prefix pve/
+    # Монтировать образы через NBD прокси, через ядро (нужно только для контейнеров)
+    vitastor_nbd 0
+```
+
+\* Примечание: вместо установки пакета pve-storage-vitastor вы можете вручную скопировать файл
+[patches/PVE_VitastorPlugin.pm](patches/PVE_VitastorPlugin.pm) на хосты Proxmox как
+`/usr/share/perl5/PVE/Storage/Custom/VitastorPlugin.pm`.
+
 ## Известные проблемы
 
 - Запросы удаления объектов могут в данный момент приводить к "неполным" объектам в EC-пулах,

README.md

@@ -45,13 +45,14 @@ breaking changes in the future. However, the following is implemented:
 - Basic OpenStack support: Cinder driver, Nova and libvirt patches
 - Snapshot merge tool (vitastor-cli {snap-rm,flatten,merge})
 - Image management CLI (vitastor-cli {ls,create,modify})
+- Proxmox storage plugin
+- Simplified NFS proxy for file-based image access emulation (suitable for VMWare)
 
 ## Roadmap
 
-- Snapshot deletion (layer merge) support
 - Better OSD creation and auto-start tools
 - Other administrative tools
-- Plugins for OpenNebula, Proxmox and other cloud systems
+- Plugins for OpenNebula and other cloud systems
 - iSCSI proxy
 - Faster failover
 - Scrubbing without checksums (verification of replicas)
@@ -356,13 +357,28 @@ and calculate disk offsets almost by hand. This will be fixed in near future.
   with lazy fsync, but prepare for inferior single-thread latency.
 - Get a fast network (at least 10 Gbit/s).
 - Disable CPU powersaving: `cpupower idle-set -D 0 && cpupower frequency-set -g performance`.
-- Check `/usr/lib/vitastor/mon/make-units.sh` and `/usr/lib/vitastor/mon/make-osd.sh` and
-  put desired values into the variables at the top of these files.
-- Create systemd units for the monitor and etcd: `/usr/lib/vitastor/mon/make-units.sh`
-- Create systemd units for your OSDs: `/usr/lib/vitastor/mon/make-osd.sh /dev/disk/by-partuuid/XXX [/dev/disk/by-partuuid/YYY ...]`
-- You can edit the units and change OSD configuration. Notable configuration variables:
+- On the monitor hosts:
+  - Edit variables at the top of `/usr/lib/vitastor/mon/make-units.sh` to desired values.
+  - Create systemd units for the monitor and etcd: `/usr/lib/vitastor/mon/make-units.sh`
+- Start etcd and monitors: `systemctl start etcd vitastor-mon`
+- Put etcd_address and osd_network into `/etc/vitastor/vitastor.conf`. Example:
+  ```
+  {
+    "etcd_address": ["10.200.1.10:2379","10.200.1.11:2379","10.200.1.12:2379"],
+    "osd_network": "10.200.1.0/24"
+  }
+  ```
+- Initialize OSDs:
+  - Simplest, SSD-only: `/usr/lib/vitastor/mon/make-osd.sh /dev/disk/by-partuuid/XXX [/dev/disk/by-partuuid/YYY ...]`
+  - Hybrid, HDD+SSD: `/usr/lib/vitastor/mon/make-osd-hybrid.js /dev/sda /dev/sdb ...` - pass all your
+    devices (HDD and SSD) to this script - it will partition disks and initialize journals on its own.
+    This script skips HDDs which are already partitioned so if you want to use non-empty disks for
+    Vitastor you should first wipe them with `wipefs -a`. SSDs with GPT partition table are not skipped,
+    but some free unpartitioned space must be available because the script creates new partitions for journals.
+- You can change OSD configuration in units or in `vitastor.conf`. Notable configuration variables:
   - `disable_data_fsync 1` - only safe with server-grade drives with capacitors.
   - `immediate_commit all` - use this if all your drives are server-grade.
+    If all OSDs have it set to all then you should also put the same value in etcd into /vitastor/config/global
   - `disable_device_lock 1` - only required if you run multiple OSDs on one block device.
   - `flusher_count 256` - flusher is a micro-thread that removes old data from the journal.
     You don't have to worry about this parameter anymore, 256 is enough.
@@ -463,9 +479,49 @@ It will output the device name, like /dev/nbd0 which you can then format and mou
 
 Again, you can use `--pool <POOL> --inode <INODE> --size <SIZE>` insteaf of `--image <IMAGE>` if you want.
 
+### NFS
+
+Vitastor has a simplified NFS 3.0 proxy for file-based image access emulation. It's not
+suitable as a full-featured file system, at least because all file/image metadata is stored
+in etcd and kept in memory all the time - thus you can't put a lot of files in it.
+
+However, NFS proxy is totally fine as a method to provide VM image access and allows to
+plug Vitastor into, for example, VMWare. It's important to note that for VMWare it's a much
+better access method than iSCSI, because with iSCSI we'd have to put all VM images into one
+Vitastor image exported as a LUN to VMWare and formatted with VMFS. VMWare doesn't use VMFS
+over NFS.
+
+NFS proxy is stateless if you use immediate_commit=all mode (for SSD with capacitors or
+HDDs with disabled cache), so you can run multiple NFS proxies and use a network load
+balancer or any failover method you want to in that case.
+
+vitastor-nfs usage:
+
+```
+vitastor-nfs [--etcd_address ADDR] [OTHER OPTIONS]
+
+--subdir <DIR>    export images prefixed <DIR>/ (default empty - export all images)
+--portmap 0       do not listen on port 111 (portmap/rpcbind, requires root)
+--bind <IP>       bind service to <IP> address (default 0.0.0.0)
+--nfspath <PATH>  set NFS export path to <PATH> (default is /)
+--port <PORT>     use port <PORT> for NFS services (default is 2049)
+--pool <POOL>     use <POOL> as default pool for new files (images)
+--foreground 1    stay in foreground, do not daemonize
+```
+
+Example start and mount commands:
+
+```
+vitastor-nfs --etcd_address 192.168.5.10:2379 --portmap 0 --port 2050 --pool testpool
+```
+
+```
+mount localhost:/ /mnt/ -o port=2050,mountport=2050,nfsvers=3,soft,nolock,tcp
+```
+
 ### Kubernetes
 
-Vitastor has a CSI plugin for Kubernetes which supports RWO volumes.
+Vitastor has a CSI plugin for Kubernetes which supports RWO (and block RWX) volumes.
 
 To deploy it, take manifests from [csi/deploy/](csi/deploy/) directory, put your
 Vitastor configuration in [csi/deploy/001-csi-config-map.yaml](001-csi-config-map.yaml),
@@ -478,6 +534,73 @@ for i in ./???-*.yaml; do kubectl apply -f $i; done
 
 After that you'll be able to create PersistentVolumes. See example in [csi/deploy/example-pvc.yaml](csi/deploy/example-pvc.yaml).
 
+### OpenStack
+
+To enable Vitastor support in an OpenStack installation:
+
+- Install vitastor-client, patched QEMU and libvirt packages from Vitastor DEB or RPM repository
+- Use `patches/nova-21.diff` or `patches/nova-23.diff` to patch your Nova installation.
+  Patch 21 fits Nova 21-22, patch 23 fits Nova 23-24.
+- Install `patches/cinder-vitastor.py` as `..../cinder/volume/drivers/vitastor.py`
+- Define a volume type in cinder.conf (see below)
+- Block network access from VMs to Vitastor network (to OSDs and etcd), because Vitastor doesn't support authentication (yet)
+- Restart Cinder and Nova
+
+Cinder volume type configuration example:
+
+```
+[DEFAULT]
+enabled_backends = lvmdriver-1, vitastor-testcluster
+# ...
+
+[vitastor-testcluster]
+volume_driver = cinder.volume.drivers.vitastor.VitastorDriver
+volume_backend_name = vitastor-testcluster
+image_volume_cache_enabled = True
+volume_clear = none
+vitastor_etcd_address = 192.168.7.2:2379
+vitastor_etcd_prefix =
+vitastor_config_path = /etc/vitastor/vitastor.conf
+vitastor_pool_id = 1
+image_upload_use_cinder_backend = True
+```
+
+To put Glance images in Vitastor, use [https://docs.openstack.org/cinder/pike/admin/blockstorage-volume-backed-image.html](volume-backed images),
+although the support has not been verified yet.
+
+### Proxmox
+
+To enable Vitastor support in Proxmox Virtual Environment (6.4 and 7.1 are supported):
+
+- Add the corresponding Vitastor Debian repository into sources.list on Proxmox hosts
+  (buster for 6.4, bullseye for 7.1)
+- Install vitastor-client, pve-qemu-kvm, pve-storage-vitastor (* or see note) packages from Vitastor repository
+- Define storage in `/etc/pve/storage.cfg` (see below)
+- Block network access from VMs to Vitastor network (to OSDs and etcd), because Vitastor doesn't support authentication (yet)
+- Restart pvedaemon: `systemctl restart pvedaemon`
+
+`/etc/pve/storage.cfg` example (the only required option is vitastor_pool, all others
+are listed below with their default values):
+
+```
+vitastor: vitastor
+    # pool to put new images into
+    vitastor_pool testpool
+    # path to the configuration file
+    vitastor_config_path /etc/vitastor/vitastor.conf
+    # etcd address(es), required only if missing in the configuration file
+    vitastor_etcd_address 192.168.7.2:2379/v3
+    # prefix for keys in etcd
+    vitastor_etcd_prefix /vitastor
+    # prefix for images
+    vitastor_prefix pve/
+    # use NBD mounter (only required for containers)
+    vitastor_nbd 0
+```
+
+\* Note: you can also manually copy [patches/PVE_VitastorPlugin.pm](patches/PVE_VitastorPlugin.pm) to Proxmox hosts
+as `/usr/share/perl5/PVE/Storage/Custom/VitastorPlugin.pm` instead of installing pve-storage-vitastor.
+
 ## Known Problems
 
 - Object deletion requests may currently lead to 'incomplete' objects in EC pools

csi/Makefile

@@ -1,4 +1,4 @@
-VERSION ?= v0.6.8
+VERSION ?= v0.6.17
 
 all: build push
 

csi/deploy/004-csi-nodeplugin.yaml

@@ -49,7 +49,7 @@ spec:
             capabilities:
               add: ["SYS_ADMIN"]
             allowPrivilegeEscalation: true
-          image: vitalif/vitastor-csi:v0.6.8
+          image: vitalif/vitastor-csi:v0.6.17
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/deploy/007-csi-provisioner.yaml

@@ -116,7 +116,7 @@ spec:
             privileged: true
             capabilities:
               add: ["SYS_ADMIN"]
-          image: vitalif/vitastor-csi:v0.6.8
+          image: vitalif/vitastor-csi:v0.6.17
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/deploy/example-pvc-block.yaml

@@ -0,0 +1,13 @@
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: test-vitastor-pvc-block
+spec:
+  storageClassName: vitastor
+  volumeMode: Block
+  accessModes:
+    - ReadWriteMany
+  resources:
+    requests:
+      storage: 10Gi

csi/deploy/example-test-pod-block.yaml

@@ -0,0 +1,17 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: vitastor-test-block-pvc
+  namespace: default
+spec:
+  containers:
+  - name: vitastor-test-block-pvc
+    image: nginx
+    volumeDevices:
+      - name: data
+        devicePath: /dev/xvda
+  volumes:
+  - name: data
+    persistentVolumeClaim:
+      claimName: test-vitastor-pvc-block
+      readOnly: false

csi/deploy/example-test-pod.yaml

@@ -0,0 +1,17 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: vitastor-test-nginx
+  namespace: default
+spec:
+  containers:
+   - name: vitastor-test-nginx
+     image: nginx
+     volumeMounts:
+       - mountPath: /usr/share/nginx/html/s3
+         name: data
+  volumes:
+   - name: data
+     persistentVolumeClaim:
+       claimName: test-vitastor-pvc
+       readOnly: false

csi/src/config.go

@@ -5,7 +5,7 @@ package vitastor
 
 const (
     vitastorCSIDriverName    = "csi.vitastor.io"
-    vitastorCSIDriverVersion = "0.6.8"
+    vitastorCSIDriverVersion = "0.6.17"
 )
 
 // Config struct fills the parameters of request or user input

csi/src/nodeserver.go

@@ -67,29 +67,44 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
     klog.Infof("received node publish volume request %+v", protosanitizer.StripSecrets(req))
 
     targetPath := req.GetTargetPath()
+    isBlock := req.GetVolumeCapability().GetBlock() != nil
 
     // Check that it's not already mounted
-    free, error := mount.IsNotMountPoint(ns.mounter, targetPath)
+    _, error := mount.IsNotMountPoint(ns.mounter, targetPath)
     if (error != nil)
     {
         if (os.IsNotExist(error))
         {
-            error := os.MkdirAll(targetPath, 0777)
-            if (error != nil)
+            if (isBlock)
             {
-                return nil, status.Error(codes.Internal, error.Error())
+                pathFile, err := os.OpenFile(targetPath, os.O_CREATE|os.O_RDWR, 0o600)
+                if (err != nil)
+                {
+                    klog.Errorf("failed to create block device mount target %s with error: %v", targetPath, err)
+                    return nil, status.Error(codes.Internal, err.Error())
+                }
+                err = pathFile.Close()
+                if (err != nil)
+                {
+                    klog.Errorf("failed to close %s with error: %v", targetPath, err)
+                    return nil, status.Error(codes.Internal, err.Error())
+                }
+            }
+            else
+            {
+                err := os.MkdirAll(targetPath, 0777)
+                if (err != nil)
+                {
+                    klog.Errorf("failed to create fs mount target %s with error: %v", targetPath, err)
+                    return nil, status.Error(codes.Internal, err.Error())
+                }
             }
-            free = true
         }
         else
         {
             return nil, status.Error(codes.Internal, error.Error())
         }
     }
-    if (!free)
-    {
-        return &csi.NodePublishVolumeResponse{}, nil
-    }
 
     ctxVars := make(map[string]string)
     err := json.Unmarshal([]byte(req.VolumeId), &ctxVars)
@@ -149,7 +164,6 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
 
     // Format the device (ext4 or xfs)
     fsType := req.GetVolumeCapability().GetMount().GetFsType()
-    isBlock := req.GetVolumeCapability().GetBlock() != nil
     opt := req.GetVolumeCapability().GetMount().GetMountFlags()
     opt = append(opt, "_netdev")
     if ((req.VolumeCapability.AccessMode.Mode == csi.VolumeCapability_AccessMode_MULTI_NODE_READER_ONLY ||

debian/changelog

@@ -1,4 +1,4 @@
-vitastor (0.6.8-1) unstable; urgency=medium
+vitastor (0.6.17-1) unstable; urgency=medium
 
   * RDMA support
   * Bugfixes

debian/control

@@ -9,7 +9,7 @@ Rules-Requires-Root: no
 
 Package: vitastor
 Architecture: amd64
-Depends: vitastor-osd, vitastor-mon, vitastor-client, vitastor-client-dev, vitastor-fio, vitastor-qemu
+Depends: vitastor-osd, vitastor-mon, vitastor-client, vitastor-client-dev, vitastor-fio
 Description: Vitastor, a fast software-defined clustered block storage
  Vitastor is a small, simple and fast clustered block storage (storage for VM drives),
  architecturally similar to Ceph which means strong consistency, primary-replication,
@@ -48,8 +48,8 @@ Depends: ${shlibs:Depends}, ${misc:Depends}, vitastor-client (= ${binary:Version
 Description: Vitastor, a fast software-defined clustered block storage - fio drivers
  Vitastor fio drivers for benchmarking.
 
-Package: vitastor-qemu
+Package: pve-storage-vitastor
 Architecture: amd64
-Depends: ${shlibs:Depends}, ${misc:Depends}, vitastor-client (= ${binary:Version}), qemu (= ${dep:qemu})
-Description: Vitastor, a fast software-defined clustered block storage - QEMU driver
- Vitastor QEMU block device driver.
+Depends: ${shlibs:Depends}, ${misc:Depends}, vitastor-client (= ${binary:Version})
+Description: Vitastor Proxmox Virtual Environment storage plugin
+ Vitastor storage plugin for Proxmox Virtual Environment.

debian/fio_version

@@ -0,0 +1 @@
+dep:fio=3.16-1

debian/libvirt.Dockerfile

@@ -0,0 +1,40 @@
+# 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 .
+
+ARG REL=
+FROM debian:$REL
+ARG REL=
+
+WORKDIR /root
+
+RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" ]; then \
+        echo "deb http://deb.debian.org/debian $REL-backports main" >> /etc/apt/sources.list; \
+        echo >> /etc/apt/preferences; \
+        echo 'Package: *' >> /etc/apt/preferences; \
+        echo "Pin: release a=$REL-backports" >> /etc/apt/preferences; \
+        echo 'Pin-Priority: 500' >> /etc/apt/preferences; \
+    fi; \
+    grep '^deb ' /etc/apt/sources.list | perl -pe 's/^deb/deb-src/' >> /etc/apt/sources.list; \
+    echo 'APT::Install-Recommends false;' >> /etc/apt/apt.conf; \
+    echo 'APT::Install-Suggests false;' >> /etc/apt/apt.conf
+
+RUN apt-get update; apt-get -y install devscripts
+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
+RUN set -e; \
+    mkdir -p /root/packages/libvirt-$REL; \
+    rm -rf /root/packages/libvirt-$REL/*; \
+    cd /root/packages/libvirt-$REL; \
+    dpkg-source -x /root/libvirt*.dsc; \
+    D=$(ls -d libvirt-*/); \
+    V=$(ls -d libvirt-*/ | perl -pe 's/libvirt-(\d+\.\d+).*/$1/'); \
+    cp /root/libvirt-$V-vitastor.diff $D/debian/patches; \
+    echo libvirt-$V-vitastor.diff >> $D/debian/patches/series; \
+    cd $D; \
+    V=$(head -n1 debian/changelog | perl -pe 's/^.*\((.*?)(~bpo[\d\+]*)?(\+deb[u\d]+)?\).*$/$1/')+vitastor2; \
+    DEBEMAIL="Vitaliy Filippov <vitalif@yourcmc.ru>" dch -D $REL -v $V 'Add Vitastor support'; \
+    DEB_BUILD_OPTIONS=nocheck dpkg-buildpackage --jobs=auto -sa; \
+    rm -rf /root/packages/libvirt-$REL/$D

debian/patched-qemu.Dockerfile

@@ -7,11 +7,11 @@ ARG REL=
 
 WORKDIR /root
 
-RUN if [ "$REL" = "buster" ]; then \
-        echo 'deb http://deb.debian.org/debian buster-backports main' >> /etc/apt/sources.list; \
+RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" ]; then \
+        echo "deb http://deb.debian.org/debian $REL-backports main" >> /etc/apt/sources.list; \
         echo >> /etc/apt/preferences; \
         echo 'Package: *' >> /etc/apt/preferences; \
-        echo 'Pin: release a=buster-backports' >> /etc/apt/preferences; \
+        echo "Pin: release a=$REL-backports" >> /etc/apt/preferences; \
         echo 'Pin-Priority: 500' >> /etc/apt/preferences; \
     fi; \
     grep '^deb ' /etc/apt/sources.list | perl -pe 's/^deb/deb-src/' >> /etc/apt/sources.list; \
@@ -21,28 +21,41 @@ RUN if [ "$REL" = "buster" ]; then \
 RUN apt-get update
 RUN apt-get -y install qemu fio liburing1 liburing-dev libgoogle-perftools-dev devscripts
 RUN apt-get -y build-dep qemu
-RUN apt-get -y build-dep fio
 # To build a custom version
 #RUN cp /root/packages/qemu-orig/* /root
 RUN apt-get --download-only source qemu
-RUN apt-get --download-only source fio
 
-ADD patches/qemu-5.0-vitastor.patch patches/qemu-5.1-vitastor.patch /root/vitastor/patches/
+ADD patches/qemu-5.0-vitastor.patch patches/qemu-5.1-vitastor.patch patches/qemu-6.1-vitastor.patch src/qemu_driver.c /root/vitastor/patches/
 RUN set -e; \
+    apt-get install -y wget; \
+    wget -q -O /etc/apt/trusted.gpg.d/vitastor.gpg https://vitastor.io/debian/pubkey.gpg; \
+    (echo deb http://vitastor.io/debian $REL main > /etc/apt/sources.list.d/vitastor.list); \
+    (echo "APT::Install-Recommends false;" > /etc/apt/apt.conf) && \
+    apt-get update; \
+    apt-get install -y vitastor-client vitastor-client-dev quilt; \
     mkdir -p /root/packages/qemu-$REL; \
     rm -rf /root/packages/qemu-$REL/*; \
     cd /root/packages/qemu-$REL; \
     dpkg-source -x /root/qemu*.dsc; \
-    if [ -d /root/packages/qemu-$REL/qemu-5.0 ]; then \
-        cp /root/vitastor/patches/qemu-5.0-vitastor.patch /root/packages/qemu-$REL/qemu-5.0/debian/patches; \
-        echo qemu-5.0-vitastor.patch >> /root/packages/qemu-$REL/qemu-5.0/debian/patches/series; \
+    if ls -d /root/packages/qemu-$REL/qemu-5.0*; then \
+        D=$(ls -d /root/packages/qemu-$REL/qemu-5.0*); \
+        cp /root/vitastor/patches/qemu-5.0-vitastor.patch $D/debian/patches; \
+        echo qemu-5.0-vitastor.patch >> $D/debian/patches/series; \
+    elif ls /root/packages/qemu-$REL/qemu-6.1*; then \
+        D=$(ls -d /root/packages/qemu-$REL/qemu-6.1*); \
+        cp /root/vitastor/patches/qemu-6.1-vitastor.patch $D/debian/patches; \
+        echo qemu-6.1-vitastor.patch >> $D/debian/patches/series; \
     else \
         cp /root/vitastor/patches/qemu-5.1-vitastor.patch /root/packages/qemu-$REL/qemu-*/debian/patches; \
         P=`ls -d /root/packages/qemu-$REL/qemu-*/debian/patches`; \
         echo qemu-5.1-vitastor.patch >> $P/series; \
     fi; \
     cd /root/packages/qemu-$REL/qemu-*/; \
+    quilt push -a; \
+    quilt add block/vitastor.c; \
+    cp /root/vitastor/patches/qemu_driver.c block/vitastor.c; \
+    quilt refresh; \
     V=$(head -n1 debian/changelog | perl -pe 's/^.*\((.*?)(~bpo[\d\+]*)?\).*$/$1/')+vitastor1; \
-    DEBFULLNAME="Vitaliy Filippov <vitalif@yourcmc.ru>" dch -D $REL -v $V 'Plug Vitastor block driver'; \
+    DEBEMAIL="Vitaliy Filippov <vitalif@yourcmc.ru>" dch -D $REL -v $V 'Plug Vitastor block driver'; \
     DEB_BUILD_OPTIONS=nocheck dpkg-buildpackage --jobs=auto -sa; \
     rm -rf /root/packages/qemu-$REL/qemu-*/

debian/pve-storage-vitastor.install

@@ -0,0 +1 @@
+patches/PVE_VitastorPlugin.pm usr/share/perl5/PVE/Storage/Custom/VitastorPlugin.pm

debian/raw.h

@@ -0,0 +1,19 @@
+/* Removed in Linux 5.14 */
+
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_RAW_H
+#define __LINUX_RAW_H
+
+#include <linux/types.h>
+
+#define RAW_SETBIND	_IO( 0xac, 0 )
+#define RAW_GETBIND	_IO( 0xac, 1 )
+
+struct raw_config_request 
+{
+	int	raw_minor;
+	__u64	block_major;
+	__u64	block_minor;
+};
+
+#endif /* __LINUX_RAW_H */

debian/rules

@@ -6,5 +6,5 @@ export DH_VERBOSE = 1
 
 override_dh_installdeb:
 	cat debian/fio_version >> debian/vitastor-fio.substvars
-	cat debian/qemu_version >> debian/vitastor-qemu.substvars
+	[ -f debian/qemu_version ] && (cat debian/qemu_version >> debian/vitastor-qemu.substvars) || true
 	dh_installdeb

debian/vitastor-client.install

@@ -2,4 +2,6 @@ usr/bin/vita
 usr/bin/vitastor-cli
 usr/bin/vitastor-rm
 usr/bin/vitastor-nbd
+usr/bin/vitastor-nfs
 usr/lib/*/libvitastor*.so*
+mon/make-osd.sh /usr/lib/vitastor

debian/vitastor-osd.install

@@ -1,3 +1,2 @@
 usr/bin/vitastor-osd
 usr/bin/vitastor-dump-journal
-mon/make-osd.sh /usr/lib/vitastor

debian/vitastor-qemu.install

@@ -1 +0,0 @@
-usr/lib/*/qemu/*

debian/vitastor.Dockerfile

@@ -7,11 +7,11 @@ ARG REL=
 
 WORKDIR /root
 
-RUN if [ "$REL" = "buster" ]; then \
-        echo 'deb http://deb.debian.org/debian buster-backports main' >> /etc/apt/sources.list; \
+RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" ]; then \
+        echo "deb http://deb.debian.org/debian $REL-backports main" >> /etc/apt/sources.list; \
         echo >> /etc/apt/preferences; \
         echo 'Package: *' >> /etc/apt/preferences; \
-        echo 'Pin: release a=buster-backports' >> /etc/apt/preferences; \
+        echo "Pin: release a=$REL-backports" >> /etc/apt/preferences; \
         echo 'Pin-Priority: 500' >> /etc/apt/preferences; \
     fi; \
     grep '^deb ' /etc/apt/sources.list | perl -pe 's/^deb/deb-src/' >> /etc/apt/sources.list; \
@@ -19,10 +19,8 @@ RUN if [ "$REL" = "buster" ]; then \
     echo 'APT::Install-Suggests false;' >> /etc/apt/apt.conf
 
 RUN apt-get update
-RUN apt-get -y install qemu fio liburing1 liburing-dev libgoogle-perftools-dev devscripts
-RUN apt-get -y build-dep qemu
+RUN apt-get -y install fio liburing1 liburing-dev libgoogle-perftools-dev devscripts
 RUN apt-get -y build-dep fio
-RUN apt-get --download-only source qemu
 RUN apt-get --download-only source fio
 RUN apt-get update && apt-get -y install libjerasure-dev cmake libibverbs-dev
 
@@ -32,37 +30,25 @@ RUN set -e -x; \
     cd /root/fio-build/; \
     rm -rf /root/fio-build/*; \
     dpkg-source -x /root/fio*.dsc; \
-    cd /root/packages/qemu-$REL/; \
-    rm -rf qemu*/; \
-    dpkg-source -x qemu*.dsc; \
-    cd /root/packages/qemu-$REL/qemu*/; \
-    debian/rules b/configure-stamp; \
-    cd b/qemu; \
-    make -j8 qapi/qapi-builtin-types.h; \
     mkdir -p /root/packages/vitastor-$REL; \
     rm -rf /root/packages/vitastor-$REL/*; \
     cd /root/packages/vitastor-$REL; \
-    cp -r /root/vitastor vitastor-0.6.8; \
-    ln -s /root/packages/qemu-$REL/qemu-*/ vitastor-0.6.8/qemu; \
-    ln -s /root/fio-build/fio-*/ vitastor-0.6.8/fio; \
-    cd vitastor-0.6.8; \
+    cp -r /root/vitastor vitastor-0.6.17; \
+    cd vitastor-0.6.17; \
+    ln -s /root/fio-build/fio-*/ ./fio; \
     FIO=$(head -n1 fio/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
-    QEMU=$(head -n1 qemu/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
-    sh copy-qemu-includes.sh; \
+    ls /usr/include/linux/raw.h || cp ./debian/raw.h /usr/include/linux/raw.h; \
     sh copy-fio-includes.sh; \
-    rm qemu fio; \
+    rm fio; \
     mkdir -p a b debian/patches; \
-    mv qemu-copy b/qemu; \
     mv fio-copy b/fio; \
-    diff -NaurpbB a b > debian/patches/qemu-fio-headers.patch || true; \
-    echo qemu-fio-headers.patch >> debian/patches/series; \
+    diff -NaurpbB a b > debian/patches/fio-headers.patch || true; \
+    echo fio-headers.patch >> debian/patches/series; \
     rm -rf a b; \
-    rm -rf /root/packages/qemu-$REL/qemu*/; \
     echo "dep:fio=$FIO" > debian/fio_version; \
-    echo "dep:qemu=$QEMU" > debian/qemu_version; \
     cd /root/packages/vitastor-$REL; \
-    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_0.6.8.orig.tar.xz vitastor-0.6.8; \
-    cd vitastor-0.6.8; \
+    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_0.6.17.orig.tar.xz vitastor-0.6.17; \
+    cd vitastor-0.6.17; \
     V=$(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/gen-docs.js

@@ -0,0 +1,55 @@
+#!/usr/bin/nodejs
+
+const fs = require('fs');
+const yaml = require('yaml');
+
+const L = {
+    en: {},
+    ru: {
+        Type: 'Тип',
+        Default: 'Значение по умолчанию',
+        Minimum: 'Минимальное значение',
+    },
+};
+const types = {
+    en: {
+        string: 'string',
+        bool: 'boolean',
+        int: 'integer',
+        sec: 'seconds',
+        ms: 'milliseconds',
+        us: 'microseconds',
+    },
+    ru: {
+        string: 'строка',
+        bool: 'булево (да/нет)',
+        int: 'целое число',
+        sec: 'секунды',
+        ms: 'миллисекунды',
+        us: 'микросекунды',
+    },
+};
+const params_files = fs.readdirSync(__dirname+'/params')
+    .filter(f => f.substr(-4) == '.yml')
+    .map(f => f.substr(0, f.length-4));
+
+for (const file of params_files)
+{
+    const cfg = yaml.parse(fs.readFileSync(__dirname+'/params/'+file+'.yml', { encoding: 'utf-8' }));
+    for (const lang in types)
+    {
+        let out = '\n\n{{< toc >}}';
+        for (const c of cfg)
+        {
+            out += `\n\n## ${c.name}\n\n`;
+            out += `- ${L[lang]['Type'] || 'Type'}: ${c["type_"+lang] || types[lang][c.type] || c.type}\n`;
+            if (c.default !== undefined)
+                out += `- ${L[lang]['Default'] || 'Default'}: ${c.default}\n`;
+            if (c.min !== undefined)
+                out += `- ${L[lang]['Minimum'] || 'Minimum'}: ${c.min}\n`;
+            out += `\n`+(c["info_"+lang] || c["info"]).replace(/\s+$/, '');
+        }
+        const head = fs.readFileSync(__dirname+'/params/head/'+file+'.'+lang+'.md', { encoding: 'utf-8' });
+        fs.writeFileSync(__dirname+'/hugo/content/config/'+file+'.'+lang+'.md', head.replace(/\s+$/, '')+out+"\n");
+    }
+}

docs/hugo/archetypes/default.md

@@ -0,0 +1,6 @@
+---
+title: "{{ replace .Name "-" " " | title }}"
+date: {{ .Date }}
+draft: true
+---
+

docs/hugo/config.yaml

@@ -0,0 +1,35 @@
+baseURL: http://localhost
+title: Vitastor
+theme: hugo-geekdoc
+#languageCode: en-us
+
+pluralizeListTitles: false
+
+# Geekdoc required configuration
+pygmentsUseClasses: true
+pygmentsCodeFences: true
+disablePathToLower: true
+
+# Required if you want to render robots.txt template
+enableRobotsTXT: true
+
+defaultContentLanguage: en
+languages:
+  en:
+    weight: 1
+    languageName: English
+  ru:
+    weight: 1
+    languageName: Русский
+
+markup:
+  goldmark:
+    renderer:
+      # Needed for mermaid shortcode
+      unsafe: true
+  tableOfContents:
+    startLevel: 1
+    endLevel: 9
+
+taxonomies:
+  tag: tags

docs/hugo/content/_index.md

@@ -0,0 +1,6 @@
+## The Idea
+
+Vitastor is a small, simple and fast clustered block storage (storage for VM drives),
+architecturally similar to Ceph which means strong consistency, primary-replication,
+symmetric clustering and automatic data distribution over any number of drives
+of any size with configurable redundancy (replication or erasure codes/XOR).

docs/hugo/content/config/_index.en.md

@@ -0,0 +1,61 @@
+---
+title: Parameter Reference
+weight: 1
+---
+
+Vitastor configuration consists of:
+- Configuration parameters (key-value), described here
+- [Pool configuration]({{< ref "config/pool" >}})
+- OSD placement tree configuration
+- Inode configuration i.e. image metadata like name, size and parent reference
+
+Configuration parameters can be set in 3 places:
+- Configuration file (`/etc/vitastor/vitastor.conf` or other path)
+- etcd key `/vitastor/config/global`. Most variables can be set there, but etcd
+  connection parameters should obviously be set in the configuration file.
+- Command line of Vitastor components: OSD, mon, fio and QEMU options,
+  OpenStack/Proxmox/etc configuration. The latter doesn't allow to set all
+  variables directly, but it allows to override the configuration file and
+  set everything you need inside it.
+
+In the future, additional configuration methods may be added:
+- OSD superblock which will, by design, contain parameters related to the disk
+  layout and to one specific OSD.
+- OSD-specific keys in etcd like `/vitastor/config/osd/<number>`.
+
+## Common Parameters
+
+These are the most common parameters which apply to all components of Vitastor.
+
+[See the list]({{< ref "common" >}})
+
+## Cluster-Wide Disk Layout Parameters
+
+These parameters apply to clients and OSDs and can't be changed after OSD
+initialization.
+
+[See the list]({{< ref "layout-cluster" >}})
+
+## OSD Disk Layout Parameters
+
+These parameters apply to OSDs and can't be changed after OSD initialization.
+
+[See the list]({{< ref "layout-osd" >}})
+
+## Network Protocol Parameters
+
+These parameters apply to clients and OSDs and can be changed with a restart.
+
+[See the list]({{< ref "network" >}})
+
+## Runtime OSD Parameters
+
+These parameters apply to OSDs and can be changed with an OSD restart.
+
+[See the list]({{< ref "osd" >}})
+
+## Monitor Parameters
+
+These parameters only apply to Monitors.
+
+[See the list]({{< ref "monitor" >}})

docs/hugo/content/config/_index.ru.md

@@ -0,0 +1,63 @@
+---
+title: Перечень настроек
+weight: 1
+---
+
+Конфигурация Vitastor состоит из:
+- Параметров (ключ-значение), описанных на данной странице
+- Настроек пулов
+- Настроек дерева OSD
+- Настроек инодов, т.е. метаданных образов, таких, как имя, размер и ссылки на
+  родительский образ
+
+Параметры конфигурации могут задаваться в 3 местах:
+- Файле конфигурации (`/etc/vitastor/vitastor.conf` или по другому пути)
+- Ключе в etcd `/vitastor/config/global`. Большая часть параметров может
+  задаваться там, кроме, естественно, самих параметров соединения с etcd,
+  которые должны задаваться в файле конфигурации
+- В командной строке компонентов Vitastor: OSD, монитора, опциях fio и QEMU,
+  настроек OpenStack, Proxmox и т.п. Последние, как правило, не включают полный
+  набор параметров напрямую, но разрешают определить путь к файлу конфигурации
+  и задать любые параметры в нём.
+
+В будущем также могут быть добавлены другие способы конфигурации:
+- Суперблок OSD, в котором будут храниться параметры OSD, связанные с дисковым
+  форматом и с этим конкретным OSD.
+- OSD-специфичные ключи в etcd типа `/vitastor/config/osd/<номер>`.
+
+## Общие параметры
+
+Это наиболее общие параметры, используемые всеми компонентами Vitastor.
+
+[Посмотреть список]({{< ref "common" >}})
+
+## Дисковые параметры уровня кластера
+
+Эти параметры используются клиентами и OSD и не могут быть изменены после
+инициализации OSD.
+
+[Посмотреть список]({{< ref "layout-cluster" >}})
+
+## Дисковые параметры OSD
+
+Эти параметры используются OSD и не могут быть изменены после инициализации OSD.
+
+[Посмотреть список]({{< ref "layout-osd" >}})
+
+## Параметры сетевого протокола
+
+Эти параметры используются клиентами и OSD и могут быть изменены с перезапуском.
+
+[Посмотреть список]({{< ref "network" >}})
+
+## Изменяемые параметры OSD
+
+Эти параметры используются OSD и могут быть изменены с перезапуском.
+
+[Посмотреть список]({{< ref "osd" >}})
+
+## Параметры мониторов
+
+Данные параметры используются только мониторами Vitastor.
+
+[Посмотреть список]({{< ref "monitor" >}})

docs/hugo/content/config/pool.en.md

@@ -0,0 +1,178 @@
+---
+title: Pool configuration
+weight: 100
+---
+
+Pool configuration is set in etcd key `/vitastor/config/pools` in the following
+JSON format:
+
+```
+{
+  "<Numeric ID>": {
+    "name": "<name>",
+    ...other parameters...
+  }
+}
+```
+
+{{< toc >}}
+
+# Parameters
+
+## name
+
+- Type: string
+- Required
+
+Pool name.
+
+## scheme
+
+- Type: string
+- Required
+- One of: "replicated", "xor" or "jerasure"
+
+Redundancy scheme used for data in this pool.
+
+## pg_size
+
+- Type: integer
+- Required
+
+Total number of disks for PGs of this pool - i.e., number of replicas for
+replicated pools and number of data plus parity disks for EC/XOR pools.
+
+## parity_chunks
+
+- Type: integer
+
+Number of parity chunks for EC/XOR pools. For such pools, data will be lost
+if you lose more than parity_chunks disks at once, so this parameter can be
+equally described as FTT (number of failures to tolerate).
+
+Required for EC/XOR pools, ignored for replicated pools.
+
+## pg_minsize
+
+- Type: integer
+- Required
+
+Number of available live disks for PGs of this pool to remain active.
+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).
+
+FIXME: pg_minsize behaviour may be changed in the future to only make PGs
+read-only instead of deactivating them.
+
+## pg_count
+
+- Type: integer
+- Required
+
+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,
+because it makes it easier to reduce or increase PG count later by dividing or
+multiplying it by 2.
+
+In Vitastor, PGs are ephemeral, so you can change pool PG count anytime just
+by overwriting pool configuration in etcd. Amount of the data affected by
+rebalance will be smaller if the new PG count is a multiple of the old PG count
+or vice versa.
+
+## failure_domain
+
+- Type: string
+- Default: host
+
+Failure domain specification. Must be "host" or "osd" or refer to one of the
+placement tree levels, defined in [placement_levels]({{< ref "config/monitor#placement_levels" >}}).
+
+Two replicas, or two parts in case of EC/XOR, of the same block of data are
+never put on OSDs in the same failure domain (for example, on the same host).
+So failure domain specifies the unit which failure you are protecting yourself
+from.
+
+## max_osd_combinations
+
+- Type: integer
+- Default: 10000
+
+Vitastor data placement algorithm is based on the LP solver and OSD combinations
+which are fed to it are generated ramdonly. This parameter specifies the maximum
+number of combinations to generate when optimising PG placement.
+
+This parameter usually doesn't require to be changed.
+
+## pg_stripe_size
+
+- Type: integer
+- Default: 0
+
+Specifies the stripe size for this pool according to which images are split into
+different PGs. Stripe size can't be smaller than [block_size]({{< ref "config/layout-cluster#block_size" >}})
+multiplied by (pg_size - parity_chunks) for EC/XOR pools, or 1 for replicated pools,
+and the same value is used by default.
+
+This means first `pg_stripe_size = (block_size * (pg_size-parity_chunks))` bytes
+of an image go to one PG, next `pg_stripe_size` bytes go to another PG and so on.
+
+Usually doesn't require to be changed separately from the block size.
+
+## root_node
+
+- Type: string
+
+Specifies the root node of the OSD tree to restrict this pool OSDs to.
+Referenced root node must exist in /vitastor/config/node_placement.
+
+## osd_tags
+
+- Type: string or array of strings
+
+Specifies OSD tags to restrict this pool to. If multiple tags are specified,
+only OSDs having all of these tags will be used for this pool.
+
+## primary_affinity_tags
+
+- Type: string or array of strings
+
+Specifies OSD tags to prefer putting primary OSDs in this pool to.
+Note that for EC/XOR pools Vitastor always prefers to put primary OSD on one
+of the OSDs containing a data chunk for a PG.
+
+# Examples
+
+## Replicated pool
+
+```
+{
+  "1": {
+    "name":"testpool",
+    "scheme":"replicated",
+    "pg_size":2,
+    "pg_minsize":1,
+    "pg_count":256,
+    "failure_domain":"host"
+  }
+}
+```
+
+## Erasure-coded pool
+
+```
+{
+  "2": {
+    "name":"ecpool",
+    "scheme":"jerasure",
+    "pg_size":3,
+    "parity_chunks":1,
+    "pg_minsize":2,
+    "pg_count":256,
+    "failure_domain":"host"
+  }
+}
+```

docs/hugo/content/installation/packages.md

@@ -0,0 +1,41 @@
+---
+title: Packages
+weight: 2
+---
+
+## Debian
+
+- Trust Vitastor package signing key:
+  `wget -q -O - https://vitastor.io/debian/pubkey | sudo apt-key add -`
+- Add Vitastor package repository to your /etc/apt/sources.list:
+  - Debian 11 (Bullseye/Sid): `deb https://vitastor.io/debian bullseye main`
+  - Debian 10 (Buster): `deb https://vitastor.io/debian buster main`
+- For Debian 10 (Buster) also enable backports repository:
+  `deb http://deb.debian.org/debian buster-backports main`
+- Install packages: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu`
+
+## CentOS
+
+- Add Vitastor package repository:
+  - CentOS 7: `yum install https://vitastor.io/rpms/centos/7/vitastor-release-1.0-1.el7.noarch.rpm`
+  - CentOS 8: `dnf install https://vitastor.io/rpms/centos/8/vitastor-release-1.0-1.el8.noarch.rpm`
+- Enable EPEL: `yum/dnf install epel-release`
+- Enable additional CentOS repositories:
+  - CentOS 7: `yum install centos-release-scl`
+  - CentOS 8: `dnf install centos-release-advanced-virtualization`
+- Enable elrepo-kernel:
+  - CentOS 7: `yum install https://www.elrepo.org/elrepo-release-7.el7.elrepo.noarch.rpm`
+  - CentOS 8: `dnf install https://www.elrepo.org/elrepo-release-8.el8.elrepo.noarch.rpm`
+- Install packages: `yum/dnf install vitastor lpsolve etcd kernel-ml qemu-kvm`
+
+## Installation requirements
+
+- Linux kernel 5.4 or newer, for io_uring support. 5.8 or later is highly
+  recommended because io_uring is a relatively new technology and there is
+  at least one bug which reproduces with io_uring and HP SmartArray
+  controllers in 5.4
+- liburing 0.4 or newer
+- lp_solve
+- etcd 3.4.15 or newer. Earlier versions won't work because of various bugs,
+  for example [#12402](https://github.com/etcd-io/etcd/pull/12402).
+- node.js 10 or newer

docs/hugo/content/installation/quickstart.md

@@ -0,0 +1,72 @@
+---
+title: Quick Start
+weight: 1
+---
+
+Prepare:
+
+- Get some SATA or NVMe SSDs with capacitors (server-grade drives). You can use desktop SSDs
+  with lazy fsync, but prepare for inferior single-thread latency. Read more about capacitors
+  [here]({{< ref "config/layout-cluster#immediate_commit" >}}).
+- Get a fast network (at least 10 Gbit/s). Something like Mellanox ConnectX-4 with RoCEv2 is ideal.
+- Disable CPU powersaving: `cpupower idle-set -D 0 && cpupower frequency-set -g performance`.
+- [Install Vitastor packages]({{< ref "installation/packages" >}}).
+
+## Configure monitors
+
+On the monitor hosts:
+- Edit variables at the top of `/usr/lib/vitastor/mon/make-units.sh` to desired values.
+- Create systemd units for the monitor and etcd: `/usr/lib/vitastor/mon/make-units.sh`
+- Start etcd and monitors: `systemctl start etcd vitastor-mon`
+
+## Configure OSDs
+
+- Put etcd_address and osd_network into `/etc/vitastor/vitastor.conf`. Example:
+  ```
+  {
+    "etcd_address": ["10.200.1.10:2379","10.200.1.11:2379","10.200.1.12:2379"],
+    "osd_network": "10.200.1.0/24"
+  }
+  ```
+- Initialize OSDs:
+  - Simplest, SSD-only: `/usr/lib/vitastor/mon/make-osd.sh /dev/disk/by-partuuid/XXX [/dev/disk/by-partuuid/YYY ...]`
+  - Hybrid, HDD+SSD: `/usr/lib/vitastor/mon/make-osd-hybrid.js /dev/sda /dev/sdb ...` &mdash; pass all your
+    devices (HDD and SSD) to this script &mdash; it will partition disks and initialize journals on its own.
+    This script skips HDDs which are already partitioned so if you want to use non-empty disks for
+    Vitastor you should first wipe them with `wipefs -a`. SSDs with GPT partition table are not skipped,
+    but some free unpartitioned space must be available because the script creates new partitions for journals.
+- You can change OSD configuration in units or in `vitastor.conf`.
+  Check [Configuration Reference]({{< ref "config" >}}) for parameter descriptions.
+- `systemctl start vitastor.target` everywhere.
+- If all your drives have capacitors, create global configuration in etcd: \
+  `etcdctl --endpoints=... put /vitastor/config/global '{"immediate_commit":"all"}'`
+
+## Create a pool
+
+Create pool configuration in etcd:
+
+```
+etcdctl --endpoints=... put /vitastor/config/pools '{"1":{"name":"testpool",
+  "scheme":"replicated","pg_size":2,"pg_minsize":1,"pg_count":256,"failure_domain":"host"}}'
+```
+
+For jerasure pools the configuration should look like the following:
+
+```
+etcdctl --endpoints=... put /vitastor/config/pools '{"2":{"name":"ecpool",
+  "scheme":"jerasure","pg_size":4,"parity_chunks":2,"pg_minsize":2,"pg_count":256,"failure_domain":"host"}`
+```
+
+After you do this, one of the monitors will configure PGs and OSDs will start them.
+
+You can check PG states with `etcdctl --endpoints=... get --prefix /vitastor/pg/state`. All PGs should become 'active'.
+
+## Create an image
+
+Use vitastor-cli ([read CLI documentation here]({{< ref "usage/cli" >}})):
+
+```
+vitastor-cli create -s 10G testimg
+```
+
+After that, you can run benchmarks or start QEMU manually with this image.

docs/hugo/content/installation/source.md

@@ -0,0 +1,54 @@
+---
+title: Building from Source
+weight: 3
+---
+
+## Requirements
+
+- gcc and g++ 8 or newer, clang 10 or newer, or other compiler with C++11 plus
+  designated initializers support from C++20
+- CMake
+- liburing, jerasure headers
+
+## Basic instructions
+
+Download source, for example using git: `git clone --recurse-submodules https://yourcmc.ru/git/vitalif/vitastor/`
+
+Get `fio` source and symlink it into `<vitastor>/fio`. If you don't want to build fio engine,
+you can disable it by passing `-DWITH_FIO=no` to cmake.
+
+Build and install Vitastor:
+
+```
+cd vitastor
+mkdir build
+cd build
+cmake .. && make -j8 install
+```
+
+## QEMU Driver
+
+It's recommended to build the QEMU driver (qemu_driver.c) in-tree, as a part of
+QEMU build process. To do that:
+- Install vitastor client library headers (from source or from vitastor-client-dev package)
+- Take a corresponding patch from `patches/qemu-*-vitastor.patch` and apply it to QEMU source
+- Copy `src/qemu_driver.c` to QEMU source directory as `block/block-vitastor.c`
+- Build QEMU as usual
+
+But it is also possible to build it out-of-tree. To do that:
+- Get QEMU source, begin to build it, stop the build and copy headers:
+   - `<qemu>/include` &rarr; `<vitastor>/qemu/include`
+   - Debian:
+      * Use qemu packages from the main repository
+      * `<qemu>/b/qemu/config-host.h` &rarr; `<vitastor>/qemu/b/qemu/config-host.h`
+      * `<qemu>/b/qemu/qapi` &rarr; `<vitastor>/qemu/b/qemu/qapi`
+   - CentOS 8:
+      * Use qemu packages from the Advanced-Virtualization repository. To enable it, run
+        `yum install centos-release-advanced-virtualization.noarch` and then `yum install qemu`
+      * `<qemu>/config-host.h` &rarr; `<vitastor>/qemu/b/qemu/config-host.h`
+      * For QEMU 3.0+: `<qemu>/qapi` &rarr; `<vitastor>/qemu/b/qemu/qapi`
+      * For QEMU 2.0+: `<qemu>/qapi-types.h` &rarr; `<vitastor>/qemu/b/qemu/qapi-types.h`
+   - `config-host.h` and `qapi` are required because they contain generated headers
+- Configure Vitastor with `WITH_QEMU=yes` and, if you're on RHEL, also with `QEMU_PLUGINDIR=qemu-kvm`:
+  `cmake .. -DWITH_QEMU=yes`.
+- After that, Vitastor will build `block-vitastor.so` during its build process.

docs/hugo/content/introduction/_index.md

@@ -0,0 +1,4 @@
+---
+title: Introduction
+weight: -1
+---

docs/hugo/content/introduction/architecture.md

@@ -0,0 +1,73 @@
+---
+title: Architecture
+weight: 3
+---
+
+For people familiar with Ceph, Vitastor is quite similar:
+
+- Vitastor also has Pools, PGs, OSDs, Monitors, Failure Domains, Placement Tree:
+  - OSD (Object Storage Daemon) is a process that stores data and serves read/write requests.
+  - PG (Placement Group) is a container for data that (normally) shares the same replicas.
+  - Pool is a container for data that has the same redundancy scheme and placement rules.
+  - Monitor is a separate daemon that watches cluster state and controls data distribution.
+  - Failure Domain is a group of OSDs that you allow to fail. It's "host" by default.
+  - Placement Tree groups OSDs in a hierarchy to later split them into Failure Domains.
+- Vitastor also distributes every image data across the whole cluster.
+- Vitastor is also transactional (every write to the cluster is atomic).
+- OSDs also have journal and metadata and they can also be put on separate drives.
+- Just like in Ceph, client library attempts to recover from any cluster failure so
+  you can basically reboot the whole cluster and only pause, but not crash, your clients
+  (please report a bug if the client crashes in that case).
+
+However, there are also differences:
+
+- Vitastor's main focus is on SSDs. Hybrid SSD+HDD setups are also possible.
+- Vitastor OSD is (and will always be) single-threaded. If you want to dedicate more than 1 core
+  per drive you should run multiple OSDs each on a different partition of the drive.
+  Vitastor isn't CPU-hungry though (as opposed to Ceph), so 1 core is sufficient in a lot of cases.
+- Metadata and journal are always kept in memory. Metadata size depends linearly on drive capacity
+  and data store block size which is 128 KB by default. With 128 KB blocks metadata should occupy
+  around 512 MB per 1 TB (which is still less than Ceph wants). Journal doesn't have to be big,
+  the example test below was conducted with only 16 MB journal. A big journal is probably even
+  harmful as dirty write metadata also take some memory.
+- Vitastor storage layer doesn't have internal copy-on-write or redirect-write. I know that maybe
+  it's possible to create a good copy-on-write storage, but it's much harder and makes performance
+  less deterministic, so CoW isn't used in Vitastor.
+- The basic layer of Vitastor is block storage with fixed-size blocks, not object storage with
+  rich semantics like in Ceph (RADOS).
+- There's a "lazy fsync" mode which allows to batch writes before flushing them to the disk.
+  This allows to use Vitastor with desktop SSDs, but still lowers performance due to additional
+  network roundtrips, so use server SSDs with capacitor-based power loss protection
+  ("Advanced Power Loss Protection") for best performance.
+- PGs are ephemeral. This means that they aren't stored on data disks and only exist in memory
+  while OSDs are running.
+- Recovery process is per-object (per-block), not per-PG. Also there are no PGLOGs.
+- Monitors don't store data. Cluster configuration and state is stored in etcd in simple human-readable
+  JSON structures. Monitors only watch cluster state and handle data movement.
+  Thus Vitastor's Monitor isn't a critical component of the system and is more similar to Ceph's Manager.
+  Vitastor's Monitor is implemented in node.js.
+- PG distribution isn't based on consistent hashes. All PG mappings are stored in etcd.
+  Rebalancing PGs between OSDs is done by mathematical optimization - data distribution problem
+  is reduced to a linear programming problem and solved by lp_solve. This allows for almost
+  perfect (96-99% uniformity compared to Ceph's 80-90%) data distribution in most cases, ability
+  to map PGs by hand without breaking rebalancing logic, reduced OSD peer-to-peer communication
+  (on average, OSDs have fewer peers) and less data movement. It also probably has a drawback -
+  this method may fail in very large clusters, but up to several hundreds of OSDs it's perfectly fine.
+  It's also easy to add consistent hashes in the future if something proves their necessity.
+- There's no separate CRUSH layer. You select pool redundancy scheme, placement root, failure domain
+  and so on directly in pool configuration.
+- Images are global i.e. you can't create multiple images with the same name in different pools.
+
+## Implementation Principles
+
+- I like architecturally simple solutions. Vitastor is and will always be designed
+  exactly like that.
+- I also like reinventing the wheel to some extent, like writing my own HTTP client
+  for etcd interaction instead of using prebuilt libraries, because in this case
+  I'm confident about what my code does and what it doesn't do.
+- I don't care about C++ "best practices" like RAII or proper inheritance or usage of
+  smart pointers or whatever and I don't intend to change my mind, so if you're here
+  looking for ideal reference C++ code, this probably isn't the right place.
+- I like node.js better than any other dynamically-typed language interpreter
+  because it's faster than any other interpreter in the world, has neutral C-like
+  syntax and built-in event loop. That's why Monitor is implemented in node.js.

docs/hugo/content/introduction/author.md

@@ -0,0 +1,34 @@
+---
+title: Author and License
+weight: 3
+---
+
+Copyright (c) Vitaliy Filippov (vitalif [at] yourcmc.ru), 2019+
+
+Join Vitastor Telegram Chat: https://t.me/vitastor
+
+All server-side code (OSD, Monitor and so on) is licensed under the terms of
+Vitastor Network Public License 1.1 (VNPL 1.1), a copyleft license based on
+GNU GPLv3.0 with the additional "Network Interaction" clause which requires
+opensourcing all programs directly or indirectly interacting with Vitastor
+through a computer network and expressly designed to be used in conjunction
+with it ("Proxy Programs"). Proxy Programs may be made public not only under
+the terms of the same license, but also under the terms of any GPL-Compatible
+Free Software License, as listed by the Free Software Foundation.
+This is a stricter copyleft license than the Affero GPL.
+
+Please note that VNPL doesn't require you to open the code of proprietary
+software running inside a VM if it's not specially designed to be used with
+Vitastor.
+
+Basically, you can't use the software in a proprietary environment to provide
+its functionality to users without opensourcing all intermediary components
+standing between the user and Vitastor or purchasing a commercial license
+from the author 😀.
+
+Client libraries (cluster_client and so on) are dual-licensed under the same
+VNPL 1.1 and also GNU GPL 2.0 or later to allow for compatibility with GPLed
+software like QEMU and fio.
+
+You can find the full text of VNPL-1.1 in the file [VNPL-1.1.txt](VNPL-1.1.txt).
+GPL 2.0 is also included in this repository as [GPL-2.0.txt](GPL-2.0.txt).

docs/hugo/content/introduction/features.md

@@ -0,0 +1,60 @@
+---
+title: Features
+weight: 1
+---
+
+Vitastor is currently a pre-release and it still misses some important features.
+However, the following is implemented:
+
+- Basic part: highly-available block storage with symmetric clustering and no SPOF
+- Performance ;-D
+- Multiple redundancy schemes: Replication, XOR n+1, Reed-Solomon erasure codes
+  based on jerasure library with any number of data and parity drives in a group
+- Configuration via simple JSON data structures in etcd (parameters, pools and images)
+- Automatic data distribution over OSDs, with support for:
+  - Mathematical optimization for better uniformity and less data movement
+  - Multiple pools
+  - Placement tree, OSD selection by tags (device classes) and placement root
+  - Configurable failure domains
+- Recovery of degraded blocks
+- Rebalancing (data movement between OSDs)
+- Lazy fsync support
+- Per-OSD and per-image I/O and space usage statistics in etcd
+- Snapshots and copy-on-write image clones
+- Write throttling to smooth random write workloads in SSD+HDD configurations
+- RDMA/RoCEv2 support via libibverbs
+
+CLI (vitastor-cli):
+- Pool listing and space stats (df)
+- Image listing, space and I/O stats (ls)
+- Image and snapshot creation (create, modify)
+- Image removal and snapshot merge (rm, flatten, merge, rm-data)
+
+Plugins and packaging:
+- Debian and CentOS packages
+- Generic user-space client library
+- Native QEMU driver
+- Loadable fio engine for benchmarks
+- NBD proxy for kernel mounts
+- CSI plugin for Kubernetes
+- OpenStack support: Cinder driver, Nova and libvirt patches
+- Proxmox storage plugin and packages
+
+## Roadmap
+
+The following features are planned for the future:
+
+- Better OSD creation and auto-start tools
+- Other administrative tools
+- Web GUI
+- OpenNebula plugin
+- iSCSI proxy
+- Simplified NFS proxy
+- Multi-threaded client
+- Faster failover
+- Scrubbing without checksums (verification of replicas)
+- Checksums
+- Tiered storage (SSD caching)
+- NVDIMM support
+- Compression (possibly)
+- Read caching using system page cache (possibly)

docs/hugo/content/performance/comparison1.md

@@ -0,0 +1,93 @@
+---
+title: Example Comparison with Ceph
+weight: 4
+---
+
+Hardware configuration: 4 nodes, each with:
+- 6x SATA SSD Intel D3-S4510 3.84 TB
+- 2x Xeon Gold 6242 (16 cores @ 2.8 GHz)
+- 384 GB RAM
+- 1x 25 GbE network interface (Mellanox ConnectX-4 LX), connected to a Juniper QFX5200 switch
+
+CPU powersaving was disabled. Both Vitastor and Ceph were configured with 2 OSDs per 1 SSD.
+
+All of the results below apply to 4 KB blocks and random access (unless indicated otherwise).
+
+T8Q64 tests were conducted over 8 400GB RBD images from all hosts (every host was running 2 instances of fio).
+This is because Ceph has performance penalties related to running multiple clients over a single RBD image.
+
+cephx_sign_messages was set to false during tests, RocksDB and Bluestore settings were left at defaults.
+
+T8Q64 read test was conducted over 1 larger inode (3.2T) from all hosts (every host was running 2 instances of fio).
+Vitastor has no performance penalties related to running multiple clients over a single inode.
+If conducted from one node with all primary OSDs moved to other nodes the result was slightly lower (689000 iops),
+this is because all operations resulted in network roundtrips between the client and the primary OSD.
+When fio was colocated with OSDs (like in Ceph benchmarks above), 1/4 of the read workload actually
+used the loopback network.
+
+Vitastor was configured with: `--disable_data_fsync true --immediate_commit all --flusher_count 8
+  --disk_alignment 4096 --journal_block_size 4096 --meta_block_size 4096
+  --journal_no_same_sector_overwrites true --journal_sector_buffer_count 1024
+  --journal_size 16777216`.
+
+## Raw drive performance
+
+- T1Q1 write ~27000 iops (~0.037ms latency)
+- T1Q1 read ~9800 iops (~0.101ms latency)
+- T1Q32 write ~60000 iops
+- T1Q32 read ~81700 iops
+
+## 2 replicas
+
+### Ceph 15.2.4 (Bluestore)
+
+- T1Q1 write ~1000 iops (~1ms latency)
+- T1Q1 read ~1750 iops (~0.57ms latency)
+- T8Q64 write ~100000 iops, total CPU usage by OSDs about 40 virtual cores on each node
+- T8Q64 read ~480000 iops, total CPU usage by OSDs about 40 virtual cores on each node
+
+In fact, not that bad for Ceph. These servers are an example of well-balanced Ceph nodes.
+However, CPU usage and I/O latency were through the roof, as usual.
+
+### Vitastor 0.4.0 (native)
+
+- T1Q1 write: 7087 iops (0.14ms latency)
+- T1Q1 read: 6838 iops (0.145ms latency)
+- T2Q64 write: 162000 iops, total CPU usage by OSDs about 3 virtual cores on each node
+- T8Q64 read: 895000 iops, total CPU usage by OSDs about 4 virtual cores on each node
+- Linear write (4M T1Q32): 2800 MB/s
+- Linear read (4M T1Q32): 1500 MB/s
+
+### Vitastor 0.4.0 (NBD)
+
+NBD is currently required to mount Vitastor via kernel, but it imposes additional overhead
+due to additional copying between the kernel and userspace. This mostly hurts linear
+bandwidth, not iops.
+
+Vitastor with single-threaded NBD on the same hardware:
+- T1Q1 write: 6000 iops (0.166ms latency)
+- T1Q1 read: 5518 iops (0.18ms latency)
+- T1Q128 write: 94400 iops
+- T1Q128 read: 103000 iops
+- Linear write (4M T1Q128): 1266 MB/s (compared to 2800 MB/s via fio)
+- Linear read (4M T1Q128): 975 MB/s (compared to 1500 MB/s via fio)
+
+## EC/XOR 2+1
+
+### Ceph 15.2.4
+
+- T1Q1 write: 730 iops (~1.37ms latency)
+- T1Q1 read: 1500 iops with cold cache (~0.66ms latency), 2300 iops after 2 minute metadata cache warmup (~0.435ms latency)
+- T4Q128 write (4 RBD images): 45300 iops, total CPU usage by OSDs about 30 virtual cores on each node
+- T8Q64 read (4 RBD images): 278600 iops, total CPU usage by OSDs about 40 virtual cores on each node
+- Linear write (4M T1Q32): 1950 MB/s before preallocation, 2500 MB/s after preallocation
+- Linear read (4M T1Q32): 2400 MB/s
+
+### Vitastor 0.4.0
+
+- T1Q1 write: 2808 iops (~0.355ms latency)
+- T1Q1 read: 6190 iops (~0.16ms latency)
+- T2Q64 write: 85500 iops, total CPU usage by OSDs about 3.4 virtual cores on each node
+- T8Q64 read: 812000 iops, total CPU usage by OSDs about 4.7 virtual cores on each node
+- Linear write (4M T1Q32): 3200 MB/s
+- Linear read (4M T1Q32): 1800 MB/s

docs/hugo/content/performance/theoretical.md

@@ -0,0 +1,46 @@
+---
+title: Vitastor's Theoretical Maximum Performance
+weight: 3
+---
+
+Replicated setups:
+- Single-threaded (T1Q1) read latency: 1 network roundtrip + 1 disk read.
+- Single-threaded write+fsync latency:
+  - With immediate commit: 2 network roundtrips + 1 disk write.
+  - With lazy commit: 4 network roundtrips + 1 disk write + 1 disk flush.
+- Saturated parallel read iops: min(network bandwidth, sum(disk read iops)).
+- Saturated parallel write iops: min(network bandwidth, sum(disk write iops / number of replicas / write amplification)).
+
+EC/XOR setups:
+- Single-threaded (T1Q1) read latency: 1.5 network roundtrips + 1 disk read.
+- Single-threaded write+fsync latency:
+  - With immediate commit: 3.5 network roundtrips + 1 disk read + 2 disk writes.
+  - With lazy commit: 5.5 network roundtrips + 1 disk read + 2 disk writes + 2 disk fsyncs.
+  - 0.5 in actually (k-1)/k which means that an additional roundtrip doesn't happen when
+    the read sub-operation can be served locally.
+- Saturated parallel read iops: min(network bandwidth, sum(disk read iops)).
+- Saturated parallel write iops: min(network bandwidth, sum(disk write iops * number of data drives / (number of data + parity drives) / write amplification)).
+  In fact, you should put disk write iops under the condition of ~10% reads / ~90% writes in this formula.
+
+Write amplification for 4 KB blocks is usually 3-5 in Vitastor:
+1. Journal block write
+2. Journal data write
+3. Metadata block write
+4. Another journal block write for EC/XOR setups
+5. Data block write
+
+If you manage to get an SSD which handles 512 byte blocks well (Optane?) you may
+lower 1, 3 and 4 to 512 bytes (1/8 of data size) and get WA as low as 2.375.
+
+Lazy fsync also reduces WA for parallel workloads because journal blocks are only
+written when they fill up or fsync is requested.
+
+## In Practice
+
+In practice, using tests from [Understanding Performance]({{< ref "performance/understanding" >}})
+and good server-grade SSD/NVMe drives, you should head for:
+- At least 5000 T1Q1 replicated read and write iops (maximum 0.2ms latency)
+- At least ~80k parallel read iops or ~30k write iops per 1 core (1 OSD)
+- Disk-speed or wire-speed linear reads and writes, whichever is the bottleneck in your case
+
+If your results are lower, that may mean you have bad drives, bad network or some kind of misconfiguration.

docs/hugo/content/performance/tuning.md

@@ -0,0 +1,6 @@
+---
+title: Tuning
+weight: 2
+---
+
+- Disable CPU powersaving

docs/hugo/content/performance/understanding.md

@@ -0,0 +1,52 @@
+---
+title: Understanding Storage Performance
+weight: 1
+---
+
+The most important thing for fast storage is latency, not parallel iops.
+
+The best possible latency is achieved with one thread and queue depth of 1 which basically means
+"client load as low as possible". In this case IOPS = 1/latency, and this number doesn't
+scale with number of servers, drives, server processes or threads and so on.
+Single-threaded IOPS and latency numbers only depend on *how fast a single daemon is*.
+
+Why is it important? It's important because some of the applications *can't* use
+queue depth greater than 1 because their task isn't parallelizable. A notable example
+is any ACID DBMS because all of them write their WALs sequentially with fsync()s.
+
+fsync, by the way, is another important thing often missing in benchmarks. The point is
+that drives have cache buffers and don't guarantee that your data is actually persisted
+until you call fsync() which is translated to a FLUSH CACHE command by the OS.
+
+Desktop SSDs are very fast without fsync - NVMes, for example, can process ~80000 write
+operations per second with queue depth of 1 without fsync - but they're really slow with
+fsync because they have to actually write data to flash chips when you call fsync. Typical
+number is around 1000-2000 iops with fsync.
+
+Server SSDs often have supercapacitors that act as a built-in UPS and allow the drive
+to flush its DRAM cache to the persistent flash storage when a power loss occurs.
+This makes them perform equally well with and without fsync. This feature is called
+"Advanced Power Loss Protection" by Intel; other vendors either call it similarly
+or directly as "Full Capacitor-Based Power Loss Protection".
+
+All software-defined storages that I currently know are slow in terms of latency.
+Notable examples are Ceph and internal SDSes used by cloud providers like Amazon, Google,
+Yandex and so on. They're all slow and can only reach ~0.3ms read and ~0.6ms 4 KB write latency
+with best-in-slot hardware.
+
+And that's in the SSD era when you can buy an SSD that has ~0.04ms latency for 100 $.
+
+I use the following 6 commands with small variations to benchmark any storage:
+
+- Linear write:
+  `fio -ioengine=libaio -direct=1 -invalidate=1 -name=test -bs=4M -iodepth=32 -rw=write -runtime=60 -filename=/dev/sdX`
+- Linear read:
+  `fio -ioengine=libaio -direct=1 -invalidate=1 -name=test -bs=4M -iodepth=32 -rw=read -runtime=60 -filename=/dev/sdX`
+- Random write latency (T1Q1, this hurts storages the most):
+  `fio -ioengine=libaio -direct=1 -invalidate=1 -name=test -bs=4k -iodepth=1 -fsync=1 -rw=randwrite -runtime=60 -filename=/dev/sdX`
+- Random read latency (T1Q1):
+  `fio -ioengine=libaio -direct=1 -invalidate=1 -name=test -bs=4k -iodepth=1 -rw=randread -runtime=60 -filename=/dev/sdX`
+- Parallel write iops (use numjobs if a single CPU core is insufficient to saturate the load):
+  `fio -ioengine=libaio -direct=1 -invalidate=1 -name=test -bs=4k -iodepth=128 [-numjobs=4 -group_reporting] -rw=randwrite -runtime=60 -filename=/dev/sdX`
+- Parallel read iops (use numjobs if a single CPU core is insufficient to saturate the load):
+  `fio -ioengine=libaio -direct=1 -invalidate=1 -name=test -bs=4k -iodepth=128 [-numjobs=4 -group_reporting] -rw=randread -runtime=60 -filename=/dev/sdX`

docs/hugo/content/usage/cli.md

@@ -0,0 +1,183 @@
+---
+title: Vitastor CLI
+weight: 1
+---
+
+vitastor-cli is a command-line tool for administrative tasks like image management.
+
+It supports the following commands:
+
+{{< toc >}}
+
+Global options:
+
+```
+--etcd_address ADDR  Etcd connection address
+--iodepth N          Send N operations in parallel to each OSD when possible (default 32)
+--parallel_osds M    Work with M osds in parallel when possible (default 4)
+--progress 1|0       Report progress (default 1)
+--cas 1|0            Use online CAS writes when possible (default auto)
+--no-color           Disable colored output
+--json               JSON output
+```
+
+## status
+
+`vitastor-cli status`
+
+Show cluster status.
+
+Example output:
+
+```
+  cluster:
+    etcd: 1 / 1 up, 1.8 M database size
+    mon:  1 up, master stump
+    osd:  8 / 12 up
+
+  data:
+    raw:   498.5 G used, 301.2 G / 799.7 G available, 399.8 G down
+    state: 156.6 G clean, 97.6 G misplaced
+    pools: 2 / 3 active
+    pgs:   30 active
+           34 active+has_misplaced
+           32 offline
+
+  io:
+    client:    0 B/s rd, 0 op/s rd, 0 B/s wr, 0 op/s wr
+    rebalance: 989.8 M/s, 7.9 K op/s
+```
+
+## df
+
+`vitastor-cli df`
+
+Show pool space statistics.
+
+Example output:
+
+```
+NAME      SCHEME  PGS  TOTAL    USED    AVAILABLE  USED%   EFFICIENCY
+testpool  2/1     32   100 G    34.2 G  60.7 G     39.23%  100%
+size1     1/1     32   199.9 G  10 G    121.5 G    39.23%  100%
+kaveri    2/1     32   0 B      10 G    0 B        100%    0%
+```
+
+In the example above, "kaveri" pool has "zero" efficiency because all its OSD are down.
+
+## ls
+
+`vitastor-cli ls [-l] [-p POOL] [--sort FIELD] [-r] [-n N] [<glob> ...]`
+
+List images (only matching `<glob>` pattern(s) if passed).
+
+Options:
+
+```
+-p|--pool POOL  Filter images by pool ID or name
+-l|--long       Also report allocated size and I/O statistics
+--del           Also include delete operation statistics
+--sort FIELD    Sort by specified field (name, size, used_size, <read|write|delete>_<iops|bps|lat|queue>)
+-r|--reverse    Sort in descending order
+-n|--count N    Only list first N items
+```
+
+Example output:
+
+```
+NAME                 POOL      SIZE  USED    READ   IOPS  QUEUE  LAT   WRITE  IOPS  QUEUE  LAT   FLAGS  PARENT
+debian9              testpool  20 G  12.3 G  0 B/s  0     0      0 us  0 B/s  0     0      0 us     RO
+pve/vm-100-disk-0    testpool  20 G  0 B     0 B/s  0     0      0 us  0 B/s  0     0      0 us      -  debian9
+pve/base-101-disk-0  testpool  20 G  0 B     0 B/s  0     0      0 us  0 B/s  0     0      0 us     RO  debian9
+pve/vm-102-disk-0    testpool  32 G  36.4 M  0 B/s  0     0      0 us  0 B/s  0     0      0 us      -  pve/base-101-disk-0
+debian9-test         testpool  20 G  36.6 M  0 B/s  0     0      0 us  0 B/s  0     0      0 us      -  debian9
+bench                testpool  10 G  10 G    0 B/s  0     0      0 us  0 B/s  0     0      0 us      -
+bench-kaveri         kaveri    10 G  10 G    0 B/s  0     0      0 us  0 B/s  0     0      0 us      -
+```
+
+## create
+
+`vitastor-cli create -s|--size <size> [-p|--pool <id|name>] [--parent <parent_name>[@<snapshot>]] <name>`
+
+Create an image. You may use K/M/G/T suffixes for `<size>`. If `--parent` is specified,
+a copy-on-write image clone is created. Parent must be a snapshot (readonly image).
+Pool must be specified if there is more than one pool.
+
+```
+vitastor-cli create --snapshot <snapshot> [-p|--pool <id|name>] <image>
+vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
+```
+
+Create a snapshot of image `<name>` (either form can be used). May be used live if only a single writer is active.
+
+## modify
+
+`vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force]`
+
+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.
+```
+
+## rm
+
+`vitastor-cli rm <from> [<to>] [--writers-stopped]`
+
+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
+more effective in case of a single 'slim' read-write child and 'fat' removed parent:
+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.
+
+## flatten
+
+`vitastor-cli flatten <layer>`
+
+Flatten a layer, i.e. merge data and detach it from parents.
+
+## rm-data
+
+`vitastor-cli rm-data --pool <pool> --inode <inode> [--wait-list] [--min-offset <offset>]`
+
+Remove inode data without changing metadata.
+
+```
+--wait-list   Retrieve full objects listings before starting to remove objects.
+              Requires more memory, but allows to show correct removal progress.
+--min-offset  Purge only data starting with specified offset.
+```
+
+## merge-data
+
+`vitastor-cli merge-data <from> <to> [--target <target>]`
+
+Merge layer data without changing metadata. Merge `<from>`..`<to>` to `<target>`.
+`<to>` must be a child of `<from>` and `<target>` may be one of the layers between
+`<from>` and `<to>`, including `<from>` and `<to>`.
+
+## alloc-osd
+
+`vitastor-cli alloc-osd`
+
+Allocate a new OSD number and reserve it by creating empty `/osd/stats/<n>` key.
+
+## simple-offsets
+
+`vitastor-cli simple-offsets <device>`
+
+Calculate offsets for simple&stupid (no superblock) OSD deployment.
+
+Options:
+
+```
+--object_size 128k       Set blockstore block size
+--bitmap_granularity 4k  Set bitmap granularity
+--journal_size 16M       Set journal size
+--device_block_size 4k   Set device block size
+--journal_offset 0       Set journal offset
+--device_size 0          Set device size
+--format text            Result format: json, options, env, or text
+```

docs/hugo/content/usage/nbd.md

@@ -0,0 +1,20 @@
+---
+title: NBD
+weight: 6
+---
+
+To create a local block device for a Vitastor image, use NBD. For example:
+
+```
+vitastor-nbd map --etcd_address 10.115.0.10:2379/v3 --image testimg
+```
+
+It will output the device name, like /dev/nbd0 which you can then format and mount as a normal block device.
+
+You can also use `--pool <POOL> --inode <INODE> --size <SIZE>` instead of `--image <IMAGE>` if you want.
+
+To unmap the device run:
+
+```
+vitastor-nbd unmap /dev/nbd0
+```

docs/hugo/content/usage/qemu.md

@@ -0,0 +1,39 @@
+---
+title: QEMU and qemu-img
+weight: 2
+---
+
+You need patched QEMU version to use Vitastor driver.
+
+To start a VM using plain QEMU command-line with Vitastor disk, use the following commands:
+
+Old syntax (-drive):
+
+```
+qemu-system-x86_64 -enable-kvm -m 1024 \
+    -drive 'file=vitastor:etcd_host=192.168.7.2\:2379/v3:image=debian9',
+        format=raw,if=none,id=drive-virtio-disk0,cache=none \
+    -device 'virtio-blk-pci,scsi=off,bus=pci.0,addr=0x5,drive=drive-virtio-disk0,
+        id=virtio-disk0,bootindex=1,write-cache=off' \
+    -vnc 0.0.0.0:0
+```
+
+New syntax (-blockdev):
+
+```
+qemu-system-x86_64 -enable-kvm -m 1024 \
+    -blockdev '{"node-name":"drive-virtio-disk0","driver":"vitastor","image":"debian9",
+        "cache":{"direct":true,"no-flush":false},"auto-read-only":true,"discard":"unmap"}' \
+    -device 'virtio-blk-pci,scsi=off,bus=pci.0,addr=0x5,drive=drive-virtio-disk0,
+        id=virtio-disk0,bootindex=1,write-cache=off' \
+    -vnc 0.0.0.0:0
+```
+
+For qemu-img, you should use `vitastor:etcd_host=<HOST>:image=<IMAGE>` as filename. For example:
+
+```
+qemu-img convert -f qcow2 debian10.qcow2 -p -O raw 'vitastor:etcd_host=192.168.7.2\:2379/v3:image=debian10'
+```
+
+You can also specify `:pool=<POOL>:inode=<INODE>:size=<SIZE>` instead of `:image=<IMAGE>`
+if you don't want to use inode metadata.

docs/hugo/i18n/ru.yaml

@@ -0,0 +1,37 @@
+---
+nav_navigation: Навигация
+nav_tags: Теги
+nav_more: Подробнее
+nav_top: К началу
+
+form_placeholder_search: Поиск
+
+error_page_title: Открыта несуществующая страница
+error_message_title: Потерялись?
+error_message_code: Ошибка 404
+error_message_text: >
+  Похоже, страница, которую вы открыли, не существует. Попробуйте найти
+  нужную информацию с <a class="gdoc-error__link" href="{{ . }}">главной страницы</a>.
+
+button_toggle_dark: Переключить тёмный/светлый/авто режим
+button_nav_open: Показать навигацию
+button_nav_close: Скрыть навигацию
+button_menu_open: Открыть меню
+button_menu_close: Закрыть меню
+button_homepage: На главную
+
+title_anchor_prefix: "Ссылка на:"
+
+posts_read_more: Читать подробнее
+posts_read_time:
+  one: "Одна минута на чтение"
+  other: "{{ . }} минут(ы) на чтение"
+posts_update_prefix: Обновлено
+
+footer_build_with: >
+  Сделано на <a href="https://gohugo.io/" class="gdoc-footer__link">Hugo</a> с
+  <svg class="icon gdoc_heart"><use xlink:href="#gdoc_heart"></use></svg>
+footer_legal_notice: Правовая информация
+footer_privacy_policy: Приватность
+
+language_switch_no_tranlation_prefix: "Страница не переведена:"

docs/hugo/layouts/partials/site-footer.html

@@ -0,0 +1,34 @@
+<footer class="gdoc-footer">
+    <div class="container flex">
+        <div class="flex flex-wrap" style="flex: 1">
+            <span class="gdoc-footer__item gdoc-footer__item--row">
+                &copy; Vitaliy Filippov, 2021+
+            </span>
+        </div>
+        <div class="flex flex-wrap">
+            {{ with .Site.Params.GeekdocLegalNotice }}
+            <span class="gdoc-footer__item gdoc-footer__item--row">
+                <a href="{{ . | relURL }}" class="gdoc-footer__link">{{ i18n "footer_legal_notice" }}</a>
+            </span>
+            {{ end }}
+            {{ with .Site.Params.GeekdocPrivacyPolicy }}
+            <span class="gdoc-footer__item gdoc-footer__item--row">
+                <a href="{{ . | relURL }}" class="gdoc-footer__link">{{ i18n "footer_privacy_policy" }}</a>
+            </span>
+            {{ end }}
+        </div>
+        {{ if (default true .Site.Params.GeekdocBackToTop) }}
+        <div class="flex flex-25 justify-end">
+            <span class="gdoc-footer__item gdoc-footer__item--row" style="margin-right: 50px">
+                {{ i18n "footer_build_with" | safeHTML }}
+            </span>
+            <span class="gdoc-footer__item">
+                <a class="gdoc-footer__link fake-link" href="#" aria-label="{{ i18n "nav_top" }}">
+                    <svg class="icon gdoc_keyboard_arrow_up"><use xlink:href="#gdoc_keyboard_arrow_up"></use></svg>
+                    <span class="hidden-mobile">{{ i18n "nav_top" }}</span>
+                </a>
+            </span>
+        </div>
+        {{ end }}
+    </div>
+</footer>

docs/hugo/static/brand.svg

@@ -0,0 +1,215 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   xmlns:osb="http://www.openswatchbook.org/uri/2009/osb"
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:xlink="http://www.w3.org/1999/xlink"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   sodipodi:docname="logo_only2.svg"
+   inkscape:version="1.0.2 (e86c870879, 2021-01-15)"
+   id="svg1340"
+   version="1.1"
+   viewBox="0 0 100 86.80192"
+   height="86.801918mm"
+   width="100mm"
+   inkscape:export-filename="/var/home/vitali/SVN/vitastor/presentation/logos/logo_only.png"
+   inkscape:export-xdpi="92.889999"
+   inkscape:export-ydpi="92.889999">
+  <defs
+     id="defs1334">
+    <linearGradient
+       osb:paint="gradient"
+       id="linearGradient866">
+      <stop
+         id="stop862"
+         offset="0"
+         style="stop-color:#c0c0c0;stop-opacity:1" />
+      <stop
+         id="stop864"
+         offset="1"
+         style="stop-color:#000000;stop-opacity:0" />
+    </linearGradient>
+    <linearGradient
+       id="linearGradient846"
+       osb:paint="gradient">
+      <stop
+         style="stop-color:#ffd42a;stop-opacity:1"
+         offset="0"
+         id="stop842" />
+      <stop
+         style="stop-color:#ffa200;stop-opacity:1"
+         offset="1"
+         id="stop844" />
+    </linearGradient>
+    <radialGradient
+       r="50"
+       fy="159.11139"
+       fx="202.36813"
+       cy="159.11139"
+       cx="202.36813"
+       gradientTransform="matrix(1.2462942,-1.2279529,0.77712408,0.78873143,-190.96813,230.1331)"
+       gradientUnits="userSpaceOnUse"
+       id="radialGradient1530"
+       xlink:href="#linearGradient1352"
+       inkscape:collect="always" />
+    <linearGradient
+       inkscape:collect="always"
+       id="linearGradient1352">
+      <stop
+         style="stop-color:#00c9e6;stop-opacity:1"
+         offset="0"
+         id="stop1348" />
+      <stop
+         style="stop-color:#5240d3;stop-opacity:1"
+         offset="1"
+         id="stop1350" />
+    </linearGradient>
+    <linearGradient
+       y2="62.555599"
+       x2="51.484566"
+       y1="62.555599"
+       x1="38.105473"
+       gradientTransform="rotate(-16.930773,271.11609,-412.42594)"
+       gradientUnits="userSpaceOnUse"
+       id="linearGradient1508"
+       xlink:href="#linearGradient1323"
+       inkscape:collect="always" />
+    <linearGradient
+       inkscape:collect="always"
+       id="linearGradient1323">
+      <stop
+         style="stop-color:#000000;stop-opacity:0.47178105"
+         offset="0"
+         id="stop1319" />
+      <stop
+         style="stop-color:#eeaaff;stop-opacity:0;"
+         offset="1"
+         id="stop1321" />
+    </linearGradient>
+    <radialGradient
+       r="21.541935"
+       fy="24.614815"
+       fx="45.312912"
+       cy="24.614815"
+       cx="45.312912"
+       gradientTransform="matrix(1.0933447,0.13113705,-0.12664108,1.0558599,-1.082187,93.974708)"
+       gradientUnits="userSpaceOnUse"
+       id="radialGradient1504"
+       xlink:href="#linearGradient846"
+       inkscape:collect="always" />
+    <filter
+       style="color-interpolation-filters:sRGB"
+       inkscape:label="Drop Shadow"
+       id="filter1497"
+       width="2"
+       height="2"
+       x="-0.5"
+       y="-0.5">
+      <feFlood
+         flood-opacity="0.498039"
+         flood-color="rgb(0,0,0)"
+         result="flood"
+         id="feFlood1487" />
+      <feComposite
+         in="flood"
+         in2="SourceGraphic"
+         operator="in"
+         result="composite1"
+         id="feComposite1489" />
+      <feGaussianBlur
+         in="composite1"
+         stdDeviation="6"
+         result="blur"
+         id="feGaussianBlur1491" />
+      <feOffset
+         dx="0"
+         dy="6"
+         result="offset"
+         id="feOffset1493" />
+      <feComposite
+         in="offset"
+         in2="offset"
+         operator="atop"
+         result="composite2"
+         id="feComposite1495" />
+    </filter>
+    <radialGradient
+       r="21.541935"
+       fy="24.614815"
+       fx="45.312912"
+       cy="24.614815"
+       cx="45.312912"
+       gradientTransform="matrix(1.0933447,0.13113705,-0.12664108,1.0558599,-1.082187,93.974708)"
+       gradientUnits="userSpaceOnUse"
+       id="radialGradient1506"
+       xlink:href="#linearGradient846"
+       inkscape:collect="always" />
+  </defs>
+  <sodipodi:namedview
+     inkscape:window-maximized="1"
+     inkscape:window-y="0"
+     inkscape:window-x="0"
+     inkscape:window-height="992"
+     inkscape:window-width="1920"
+     fit-margin-bottom="0"
+     fit-margin-right="0"
+     fit-margin-left="0"
+     fit-margin-top="-30"
+     showgrid="false"
+     inkscape:document-rotation="0"
+     inkscape:current-layer="layer1"
+     inkscape:document-units="mm"
+     inkscape:cy="47.914558"
+     inkscape:cx="-103.69646"
+     inkscape:zoom="0.7"
+     inkscape:pageshadow="2"
+     inkscape:pageopacity="1"
+     borderopacity="1.0"
+     bordercolor="#666666"
+     pagecolor="#000000"
+     id="base" />
+  <metadata
+     id="metadata1337">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title></dc:title>
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     transform="translate(-133.26969,-52.101187)"
+     id="layer1"
+     inkscape:groupmode="layer"
+     inkscape:label="Слой 1">
+    <path
+       style="fill:url(#radialGradient1530);fill-opacity:1;fill-rule:evenodd;stroke:#000000;stroke-width:0;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1"
+       d="m 133.26969,59.089473 50,75.000087 50,-75.000087 z"
+       id="path1528"
+       sodipodi:nodetypes="cccc" />
+    <path
+       d="m 194.29572,89.403603 -8.41706,2.562119 -2.50682,7.49308 7.17785,23.579008 9.60097,-14.40173 z"
+       style="fill:url(#linearGradient1508);fill-opacity:1;stroke-width:0;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:0.501961"
+       id="path1459" />
+    <g
+       transform="translate(135.70225,-49.385894)"
+       id="g1465">
+      <path
+         id="path1461"
+         style="fill:url(#radialGradient1504);fill-opacity:1;fill-rule:evenodd;stroke:#000000;stroke-width:0;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1;filter:url(#filter1497)"
+         d="m 28.817436,101.36529 c 3.112699,10.74423 6.225077,21.48892 9.333984,32.23438 2.519532,0 5.039063,0 7.558594,0 -0.985406,8.09729 -2.085815,16.18202 -2.951172,24.29297 -0.06053,0.88723 1.098131,1.61652 1.76,0.9155 1.007514,-1.05482 1.676008,-2.3829 2.528566,-3.56053 7.51538,-11.37722 14.987447,-22.78299 22.482919,-34.17333 -3.239584,0 -6.479167,0 -9.71875,0 2.887267,-6.79562 5.775365,-13.59088 8.662109,-20.38672 -13.284505,0 -26.56901,0 -39.853516,0 0.06576,0.22591 0.131511,0.45182 0.197266,0.67773 z" />
+      <path
+         sodipodi:nodetypes="cccccccc"
+         id="path1463"
+         d="m 30.735882,102.2764 h 35.342242 l -8.662729,20.3854 h 9.173783 l -22.106472,33.62346 3.027029,-24.27377 H 39.34604 Z"
+         style="fill:url(#radialGradient1506);fill-opacity:1;fill-rule:evenodd;stroke:#000000;stroke-width:0;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1" />
+    </g>
+  </g>
+</svg>

docs/hugo/static/custom.css

@@ -0,0 +1,138 @@
+/* Global customization */
+
+:root {
+  --code-max-height: 60rem;
+}
+
+/* Light mode theming */
+:root,
+:root[color-mode="light"] {
+  --header-background: #404050;
+  --header-font-color: #ffffff;
+
+  --body-background: #ffffff;
+  --body-font-color: #343a40;
+
+  --button-background: #62cb97;
+  --button-border-color: #4ec58a;
+
+  --link-color: #c54e8a;
+  --link-color-visited: #c54e8a;
+
+  --code-background: #f5f6f8;
+  --code-accent-color: #e3e7eb;
+  --code-accent-color-lite: #eff1f3;
+
+  --accent-color: #e9ecef;
+  --accent-color-lite: #f8f9fa;
+
+  --control-icons: #b2bac1;
+
+  --footer-background: #606070;
+  --footer-font-color: #ffffff;
+  --footer-link-color: #ffcc5c;
+  --footer-link-color-visited: #ffcc5c;
+}
+@media (prefers-color-scheme: light) {
+  :root {
+    --header-background: #404050;
+    --header-font-color: #ffffff;
+
+    --body-background: #ffffff;
+    --body-font-color: #343a40;
+
+    --button-background: #62cb97;
+    --button-border-color: #4ec58a;
+
+    --link-color: #c54e8a;
+    --link-color-visited: #c54e8a;
+
+    --code-background: #f5f6f8;
+    --code-accent-color: #e3e7eb;
+    --code-accent-color-lite: #eff1f3;
+
+    --accent-color: #e9ecef;
+    --accent-color-lite: #f8f9fa;
+
+    --control-icons: #b2bac1;
+
+    --footer-background: #606070;
+    --footer-font-color: #ffffff;
+    --footer-link-color: #ffcc5c;
+    --footer-link-color-visited: #ffcc5c;
+  }
+}
+
+/* Dark mode theming */
+:root[color-mode="dark"] {
+  --header-background: #202830;
+  --header-font-color: #ffffff;
+
+  --body-background: #343a44;
+  --body-font-color: #ced3d8;
+
+  --button-background: #62cb97;
+  --button-border-color: #4ec58a;
+
+  --link-color: #7ac29e;
+  --link-color-visited: #7ac29e;
+
+  --code-background: #2f353a;
+  --code-accent-color: #262b2f;
+  --code-accent-color-lite: #2b3035;
+
+  --accent-color: #2b3035;
+  --accent-color-lite: #2f353a;
+
+  --control-icons: #b2bac1;
+
+  --footer-background: #2f333e;
+  --footer-font-color: #cccccc;
+  --footer-link-color: #7ac29e;
+  --footer-link-color-visited: #7ac29e;
+}
+@media (prefers-color-scheme: dark) {
+  :root {
+    --header-background: #404070;
+    --header-font-color: #ffffff;
+
+    --body-background: #343a40;
+    --body-font-color: #ced3d8;
+
+    --button-background: #62cb97;
+    --button-border-color: #4ec58a;
+
+    --link-color: #7ac29e;
+    --link-color-visited: #7ac29e;
+
+    --code-background: #2f353a;
+    --code-accent-color: #262b2f;
+    --code-accent-color-lite: #2b3035;
+
+    --accent-color: #2b3035;
+    --accent-color-lite: #2f353a;
+
+    --control-icons: #b2bac1;
+
+    --footer-background: #2f333e;
+    --footer-font-color: #cccccc;
+    --footer-link-color: #7ac29e;
+    --footer-link-color-visited: #7ac29e;
+  }
+}
+
+.gdoc-brand__img {
+  width: 48px;
+  height: auto;
+  margin-top: -4px;
+  margin-bottom: -4px;
+}
+
+.gdoc-menu-header > span {
+  display: flex;
+  flex-direction: row-reverse;
+}
+
+span.gdoc-language {
+  margin-right: 20px;
+}

docs/hugo/static/favicon/favicon.svg

@@ -0,0 +1,196 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   xmlns:osb="http://www.openswatchbook.org/uri/2009/osb"
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:xlink="http://www.w3.org/1999/xlink"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   sodipodi:docname="favicon.svg"
+   inkscape:version="1.0.2 (e86c870879, 2021-01-15)"
+   id="svg1340"
+   version="1.1"
+   viewBox="0 0 100 100"
+   height="100mm"
+   width="100mm"
+   inkscape:export-filename="/var/home/vitali/SVN/vitastor/docs/static/favicon/favicon-64x64.png"
+   inkscape:export-xdpi="16.26"
+   inkscape:export-ydpi="16.26">
+  <defs
+     id="defs1334">
+    <linearGradient
+       osb:paint="gradient"
+       id="linearGradient866">
+      <stop
+         id="stop862"
+         offset="0"
+         style="stop-color:#c0c0c0;stop-opacity:1" />
+      <stop
+         id="stop864"
+         offset="1"
+         style="stop-color:#000000;stop-opacity:0" />
+    </linearGradient>
+    <linearGradient
+       id="linearGradient846"
+       osb:paint="gradient">
+      <stop
+         style="stop-color:#ffd42a;stop-opacity:1"
+         offset="0"
+         id="stop842" />
+      <stop
+         style="stop-color:#ffa200;stop-opacity:1"
+         offset="1"
+         id="stop844" />
+    </linearGradient>
+    <radialGradient
+       r="50"
+       fy="159.11139"
+       fx="202.36813"
+       cy="159.11139"
+       cx="202.36813"
+       gradientTransform="matrix(1.2462942,-1.2279529,0.77712408,0.78873143,-190.96813,230.1331)"
+       gradientUnits="userSpaceOnUse"
+       id="radialGradient1530"
+       xlink:href="#linearGradient1352"
+       inkscape:collect="always" />
+    <linearGradient
+       inkscape:collect="always"
+       id="linearGradient1352">
+      <stop
+         style="stop-color:#00c9e6;stop-opacity:1"
+         offset="0"
+         id="stop1348" />
+      <stop
+         style="stop-color:#5240d3;stop-opacity:1"
+         offset="1"
+         id="stop1350" />
+    </linearGradient>
+    <linearGradient
+       y2="62.555599"
+       x2="51.484566"
+       y1="62.555599"
+       x1="38.105473"
+       gradientTransform="rotate(-16.930773,271.11609,-412.42594)"
+       gradientUnits="userSpaceOnUse"
+       id="linearGradient1508"
+       xlink:href="#linearGradient1323"
+       inkscape:collect="always" />
+    <linearGradient
+       inkscape:collect="always"
+       id="linearGradient1323">
+      <stop
+         style="stop-color:#000000;stop-opacity:0.47178105"
+         offset="0"
+         id="stop1319" />
+      <stop
+         style="stop-color:#eeaaff;stop-opacity:0;"
+         offset="1"
+         id="stop1321" />
+    </linearGradient>
+    <filter
+       style="color-interpolation-filters:sRGB"
+       inkscape:label="Drop Shadow"
+       id="filter1497"
+       width="2"
+       height="2"
+       x="-0.5"
+       y="-0.5">
+      <feFlood
+         flood-opacity="0.498039"
+         flood-color="rgb(0,0,0)"
+         result="flood"
+         id="feFlood1487" />
+      <feComposite
+         in="flood"
+         in2="SourceGraphic"
+         operator="in"
+         result="composite1"
+         id="feComposite1489" />
+      <feGaussianBlur
+         in="composite1"
+         stdDeviation="6"
+         result="blur"
+         id="feGaussianBlur1491" />
+      <feOffset
+         dx="0"
+         dy="6"
+         result="offset"
+         id="feOffset1493" />
+      <feComposite
+         in="offset"
+         in2="offset"
+         operator="atop"
+         result="composite2"
+         id="feComposite1495" />
+    </filter>
+    <radialGradient
+       r="21.541935"
+       fy="24.614815"
+       fx="45.312912"
+       cy="24.614815"
+       cx="45.312912"
+       gradientTransform="matrix(1.6678615,0.20004527,-0.19318681,1.6106796,108.48083,22.966962)"
+       gradientUnits="userSpaceOnUse"
+       id="radialGradient1506"
+       xlink:href="#linearGradient846"
+       inkscape:collect="always" />
+  </defs>
+  <sodipodi:namedview
+     inkscape:window-maximized="1"
+     inkscape:window-y="0"
+     inkscape:window-x="0"
+     inkscape:window-height="992"
+     inkscape:window-width="1920"
+     fit-margin-bottom="0"
+     fit-margin-right="0"
+     fit-margin-left="0"
+     fit-margin-top="0"
+     showgrid="false"
+     inkscape:document-rotation="0"
+     inkscape:current-layer="layer1"
+     inkscape:document-units="mm"
+     inkscape:cy="83.752268"
+     inkscape:cx="-103.69645"
+     inkscape:zoom="0.7"
+     inkscape:pageshadow="2"
+     inkscape:pageopacity="0"
+     borderopacity="1.0"
+     bordercolor="#666666"
+     pagecolor="#000000"
+     id="base" />
+  <metadata
+     id="metadata1337">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title></dc:title>
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     transform="translate(-133.26969,-35.630924)"
+     id="layer1"
+     inkscape:groupmode="layer"
+     inkscape:label="Слой 1">
+    <path
+       style="fill:url(#radialGradient1530);fill-opacity:1;fill-rule:evenodd;stroke:#000000;stroke-width:0;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1"
+       d="m 133.26969,59.089473 50,75.000087 50,-75.000087 z"
+       id="path1528"
+       sodipodi:nodetypes="cccc" />
+    <path
+       d="m 194.29572,89.403603 -8.41706,2.562119 -2.50682,7.49308 7.17785,23.579008 9.60097,-14.40173 z"
+       style="fill:url(#linearGradient1508);fill-opacity:1;stroke-width:0;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:0.501961"
+       id="path1459" />
+    <path
+       sodipodi:nodetypes="cccccccc"
+       id="path1463"
+       d="m 157.01826,35.630924 h 53.91343 l -13.21471,31.09726 h 13.99432 l -33.7227,51.291496 4.61762,-37.02885 h -12.45344 z"
+       style="fill:url(#radialGradient1506);fill-opacity:1;fill-rule:evenodd;stroke:#000000;stroke-width:0;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1" />
+  </g>
+</svg>

docs/params/common.yml

@@ -0,0 +1,35 @@
+- name: config_path
+  type: string
+  default: "/etc/vitastor/vitastor.conf"
+  info: |
+    Path to the JSON configuration file. Configuration file is optional,
+    a non-existing configuration file does not prevent Vitastor from
+    running if required parameters are specified.
+  info_ru: |
+    Путь к файлу конфигурации в формате JSON. Файл конфигурации необязателен,
+    без него Vitastor тоже будет работать, если переданы необходимые параметры.
+- name: etcd_address
+  type: string or array of strings
+  type_ru: строка или массив строк
+  info: |
+    etcd connection endpoint(s). Multiple endpoints may be delimited by "," or
+    specified in a JSON array `["10.0.115.10:2379/v3","10.0.115.11:2379/v3"]`.
+    Note that https is not supported for etcd connections yet.
+  info_ru: |
+    Адрес(а) подключения к etcd. Несколько адресов могут разделяться запятой
+    или указываться в виде JSON-массива `["10.0.115.10:2379/v3","10.0.115.11:2379/v3"]`.
+- name: etcd_prefix
+  type: string
+  default: "/vitastor"
+  info: |
+    Prefix for all keys in etcd used by Vitastor. You can change prefix and, for
+    example, use a single etcd cluster for multiple Vitastor clusters.
+  info_ru: |
+    Префикс для ключей etcd, которые использует Vitastor. Вы можете задать другой
+    префикс, например, чтобы запустить несколько кластеров Vitastor с одним
+    кластером etcd.
+- name: log_level
+  type: int
+  default: 0
+  info: Log level. Raise if you want more verbose output.
+  info_ru: Уровень логгирования. Повысьте, если хотите более подробный вывод.

docs/params/head/common.en.md

@@ -0,0 +1,6 @@
+---
+title: Common Parameters
+weight: 1
+---
+
+These are the most common parameters which apply to all components of Vitastor.

docs/params/head/common.ru.md

@@ -0,0 +1,6 @@
+---
+title: Общие параметры
+weight: 1
+---
+
+Это наиболее общие параметры, используемые всеми компонентами Vitastor.

docs/params/head/layout-cluster.en.md

@@ -0,0 +1,7 @@
+---
+title: Cluster-Wide Disk Layout Parameters
+weight: 2
+---
+
+These parameters apply to clients and OSDs, are fixed at the moment of OSD drive
+initialization and can't be changed after it without losing data.

docs/params/head/layout-cluster.ru.md

@@ -0,0 +1,7 @@
+---
+title: Дисковые параметры уровня кластера
+weight: 2
+---
+
+Данные параметры используются клиентами и OSD, задаются в момент инициализации
+диска OSD и не могут быть изменены после этого без потери данных.

docs/params/head/layout-osd.en.md

@@ -0,0 +1,7 @@
+---
+title: OSD Disk Layout Parameters
+weight: 3
+---
+
+These parameters apply to OSDs, are fixed at the moment of OSD drive
+initialization and can't be changed after it without losing data.

docs/params/head/layout-osd.ru.md

@@ -0,0 +1,8 @@
+---
+title: Дисковые параметры OSD
+weight: 3
+---
+
+Данные параметры используются только OSD и, также как и общекластерные
+дисковые параметры, задаются в момент инициализации дисков OSD и не могут быть
+изменены после этого без потери данных.

docs/params/head/monitor.en.md

@@ -0,0 +1,6 @@
+---
+title: Monitor Parameters
+weight: 6
+---
+
+These parameters only apply to Monitors.

docs/params/head/monitor.ru.md

@@ -0,0 +1,6 @@
+---
+title: Параметры мониторов
+weight: 6
+---
+
+Данные параметры используются только мониторами Vitastor.

docs/params/head/network.en.md

@@ -0,0 +1,7 @@
+---
+title: Network Protocol Parameters
+weight: 4
+---
+
+These parameters apply to clients and OSDs and affect network connection logic
+between clients, OSDs and etcd.

docs/params/head/network.ru.md

@@ -0,0 +1,7 @@
+---
+title: Параметры сетевого протокола
+weight: 4
+---
+
+Данные параметры используются клиентами и OSD и влияют на логику сетевого
+взаимодействия между клиентами, OSD, а также etcd.

docs/params/head/osd.en.md

@@ -0,0 +1,7 @@
+---
+title: Runtime OSD Parameters
+weight: 5
+---
+
+These parameters only apply to OSDs, are not fixed at the moment of OSD drive
+initialization and can be changed with an OSD restart.

docs/params/head/osd.ru.md

@@ -0,0 +1,8 @@
+---
+title: Изменяемые параметры OSD
+weight: 5
+---
+
+Данные параметры используются только OSD, но, в отличие от дисковых параметров,
+не фиксируются в момент инициализации дисков OSD и могут быть изменены в любой
+момент с перезапуском OSD.

docs/params/layout-cluster.yml

@@ -0,0 +1,200 @@
+- name: block_size
+  type: int
+  default: 131072
+  info: |
+    Size of objects (data blocks) into which all physical and virtual drives are
+    subdivided in Vitastor. One of current main settings in Vitastor, affects
+    memory usage, write amplification and I/O load distribution effectiveness.
+
+    Recommended default block size is 128 KB for SSD and 4 MB for HDD. In fact,
+    it's possible to use 4 MB for SSD too - it will lower memory usage, but
+    may increase average WA and reduce linear performance.
+
+    OSDs with different block sizes (for example, SSD and SSD+HDD OSDs) can
+    currently coexist in one etcd instance only within separate Vitastor
+    clusters with different etcd_prefix'es.
+
+    Also block size can't be changed after OSD initialization without losing
+    data.
+
+    You must always specify block_size in etcd in /vitastor/config/global if
+    you change it so all clients can know about it.
+
+    OSD memory usage is roughly (SIZE / BLOCK * 68 bytes) which is roughly
+    544 MB per 1 TB of used disk space with the default 128 KB block size.
+  info_ru: |
+    Размер объектов (блоков данных), на которые делятся физические и виртуальные
+    диски в Vitastor. Одна из ключевых на данный момент настроек, влияет на
+    потребление памяти, объём избыточной записи (write amplification) и
+    эффективность распределения нагрузки по OSD.
+
+    Рекомендуемые по умолчанию размеры блока - 128 килобайт для SSD и 4
+    мегабайта для HDD. В принципе, для SSD можно тоже использовать 4 мегабайта,
+    это понизит использование памяти, но ухудшит распределение нагрузки и в
+    среднем увеличит WA.
+
+    OSD с разными размерами блока (например, SSD и SSD+HDD OSD) на данный
+    момент могут сосуществовать в рамках одного etcd только в виде двух независимых
+    кластеров Vitastor с разными etcd_prefix.
+
+    Также размер блока нельзя менять после инициализации OSD без потери данных.
+
+    Если вы меняете размер блока, обязательно прописывайте его в etcd в
+    /vitastor/config/global, дабы все клиенты его знали.
+
+    Потребление памяти OSD составляет примерно (РАЗМЕР / БЛОК * 68 байт),
+    т.е. примерно 544 МБ памяти на 1 ТБ занятого места на диске при
+    стандартном 128 КБ блоке.
+- name: bitmap_granularity
+  type: int
+  default: 4096
+  info: |
+    Required virtual disk write alignment ("sector size"). Must be a multiple
+    of disk_alignment. It's called bitmap granularity because Vitastor tracks
+    an allocation bitmap for each object containing 2 bits per each
+    (bitmap_granularity) bytes.
+
+    This parameter can't be changed after OSD initialization without losing
+    data. Also it's fixed for the whole Vitastor cluster i.e. two different
+    values can't be used in a single Vitastor cluster.
+
+    Clients MUST be aware of this parameter value, so put it into etcd key
+    /vitastor/config/global if you change it for any reason.
+  info_ru: |
+    Требуемое выравнивание записи на виртуальные диски (размер их "сектора").
+    Должен быть кратен disk_alignment. Называется гранулярностью битовой карты
+    потому, что Vitastor хранит битовую карту для каждого объекта, содержащую
+    по 2 бита на каждые (bitmap_granularity) байт.
+
+    Данный параметр нельзя менять после инициализации OSD без потери данных.
+    Также он фиксирован для всего кластера Vitastor, т.е. разные значения
+    не могут сосуществовать в одном кластере.
+
+    Клиенты ДОЛЖНЫ знать правильное значение этого параметра, так что если вы
+    его меняете, обязательно прописывайте изменённое значение в etcd в ключ
+    /vitastor/config/global.
+- name: immediate_commit
+  type: string
+  default: false
+  info: |
+    Another parameter which is really important for performance.
+
+    Desktop SSDs are very fast (100000+ iops) for simple random writes
+    without cache flush. However, they are really slow (only around 1000 iops)
+    if you try to fsync() each write, that is, when you want to guarantee that
+    each change gets immediately persisted to the physical media.
+
+    Server-grade SSDs with "Advanced/Enhanced Power Loss Protection" or with
+    "Supercapacitor-based Power Loss Protection", on the other hand, are equally
+    fast with and without fsync because their cache is protected from sudden
+    power loss by a built-in supercapacitor-based "UPS".
+
+    Some software-defined storage systems always fsync each write and thus are
+    really slow when used with desktop SSDs. Vitastor, however, can also
+    efficiently utilize desktop SSDs by postponing fsync until the client calls
+    it explicitly.
+
+    This is what this parameter regulates. When it's set to "all" the whole
+    Vitastor cluster commits each change to disks immediately and clients just
+    ignore fsyncs because they know for sure that they're unneeded. This reduces
+    the amount of network roundtrips performed by clients and improves
+    performance. So it's always better to use server grade SSDs with
+    supercapacitors even with Vitastor, especially given that they cost only
+    a bit more than desktop models.
+
+    There is also a common SATA SSD (and HDD too!) firmware bug (or feature)
+    that makes server SSDs which have supercapacitors slow with fsync. To check
+    if your SSDs are affected, compare benchmark results from `fio -name=test
+    -ioengine=libaio -direct=1 -bs=4k -rw=randwrite -iodepth=1` with and without
+    `-fsync=1`. Results should be the same. If fsync=1 result is worse you can
+    try to work around this bug by "disabling" drive write-back cache by running
+    `hdparm -W 0 /dev/sdXX` or `echo write through > /sys/block/sdXX/device/scsi_disk/*/cache_type`
+    (IMPORTANT: don't mistake it with `/sys/block/sdXX/queue/write_cache` - it's
+    unsafe to change by hand). The same may apply to newer HDDs with internal
+    SSD cache or "media-cache" - for example, a lot of Seagate EXOS drives have
+    it (they have internal SSD cache even though it's not stated in datasheets).
+
+    This parameter must be set both in etcd in /vitastor/config/global and in
+    OSD command line or configuration. Setting it to "all" or "small" requires
+    enabling disable_journal_fsync and disable_meta_fsync, setting it to "all"
+    also requires enabling disable_data_fsync.
+
+    TLDR: For optimal performance, set immediate_commit to "all" if you only use
+    SSDs with supercapacitor-based power loss protection (nonvolatile
+    write-through cache) for both data and journals in the whole Vitastor
+    cluster. Set it to "small" if you only use such SSDs for journals. Leave
+    empty if your drives have write-back cache.
+  info_ru: |
+    Ещё один важный для производительности параметр.
+
+    Модели SSD для настольных компьютеров очень быстрые (100000+ операций в
+    секунду) при простой случайной записи без сбросов кэша. Однако они очень
+    медленные (всего порядка 1000 iops), если вы пытаетесь сбрасывать кэш после
+    каждой записи, то есть, если вы пытаетесь гарантировать, что каждое
+    изменение физически записывается в энергонезависимую память.
+
+    С другой стороны, серверные SSD с конденсаторами - функцией, называемой
+    "Advanced/Enhanced Power Loss Protection" или просто "Supercapacitor-based
+    Power Loss Protection" - одинаково быстрые и со сбросом кэша, и без
+    него, потому что их кэш защищён от потери питания встроенным "источником
+    бесперебойного питания" на основе суперконденсаторов и на самом деле они
+    его никогда не сбрасывают.
+
+    Некоторые программные СХД всегда сбрасывают кэши дисков при каждой записи
+    и поэтому работают очень медленно с настольными SSD. Vitastor, однако, может
+    откладывать fsync до явного его вызова со стороны клиента и таким образом
+    эффективно утилизировать настольные SSD.
+
+    Данный параметр влияет как раз на это. Когда он установлен в значение "all",
+    весь кластер Vitastor мгновенно фиксирует каждое изменение на физические
+    носители и клиенты могут просто игнорировать запросы fsync, т.к. они точно
+    знают, что fsync-и не нужны. Это уменьшает число необходимых обращений к OSD
+    по сети и улучшает производительность. Поэтому даже с Vitastor лучше всегда
+    использовать только серверные модели SSD с суперконденсаторами, особенно
+    учитывая то, что стоят они ненамного дороже настольных.
+
+    Также в прошивках SATA SSD (и даже HDD!) очень часто встречается либо баг,
+    либо просто особенность логики, из-за которой серверные SSD, имеющие
+    конденсаторы и защиту от потери питания, всё равно медленно работают с
+    fsync. Чтобы понять, подвержены ли этой проблеме ваши SSD, сравните
+    результаты тестов `fio -name=test -ioengine=libaio -direct=1 -bs=4k
+    -rw=randwrite -iodepth=1` без и с опцией `-fsync=1`. Результаты должны
+    быть одинаковые. Если результат с `fsync=1` хуже, вы можете попробовать
+    обойти проблему, "отключив" кэш записи диска командой `hdparm -W 0 /dev/sdXX`
+    либо `echo write through > /sys/block/sdXX/device/scsi_disk/*/cache_type`
+    (ВАЖНО: не перепутайте с `/sys/block/sdXX/queue/write_cache` - этот параметр
+    менять руками небезопасно). Такая же проблема может встречаться и в новых
+    HDD-дисках с внутренним SSD или "медиа" кэшем - например, она встречается во
+    многих дисках Seagate EXOS (у них есть внутренний SSD-кэш, хотя это и не
+    указано в спецификациях).
+
+    Данный параметр нужно указывать и в etcd в /vitastor/config/global, и в
+    командной строке или конфигурации OSD. Значения "all" и "small" требуют
+    включения disable_journal_fsync и disable_meta_fsync, значение "all" также
+    требует включения disable_data_fsync.
+
+    Итого, вкратце: для оптимальной производительности установите
+    immediate_commit в значение "all", если вы используете в кластере только SSD
+    с суперконденсаторами и для данных, и для журналов. Если вы используете
+    такие SSD для всех журналов, но не для данных - можете установить параметр
+    в "small". Если и какие-то из дисков журналов имеют волатильный кэш записи -
+    оставьте параметр пустым.
+- name: client_dirty_limit
+  type: int
+  default: 33554432
+  info: |
+    Without immediate_commit=all this parameter sets the limit of "dirty"
+    (not committed by fsync) data allowed by the client before forcing an
+    additional fsync and committing the data. Also note that the client always
+    holds a copy of uncommitted data in memory so this setting also affects
+    RAM usage of clients.
+
+    This parameter doesn't affect OSDs themselves.
+  info_ru: |
+    При работе без immediate_commit=all - это лимит объёма "грязных" (не
+    зафиксированных fsync-ом) данных, при достижении которого клиент будет
+    принудительно вызывать fsync и фиксировать данные. Также стоит иметь в виду,
+    что в этом случае до момента fsync клиент хранит копию незафиксированных
+    данных в памяти, то есть, настройка влияет на потребление памяти клиентами.
+
+    Параметр не влияет на сами OSD.

docs/params/layout-osd.yml

@@ -0,0 +1,205 @@
+- name: data_device
+  type: string
+  info: |
+    Path to the block device to use for data. It's highly recommendded to use
+    stable paths for all device names: `/dev/disk/by-partuuid/xxx...` instead
+    of just `/dev/sda` or `/dev/nvme0n1` to not mess up after server restart.
+    Files can also be used instead of block devices, but this is implemented
+    only for testing purposes and not for production.
+  info_ru: |
+    Путь к диску (блочному устройству) для хранения данных. Крайне рекомендуется
+    использовать стабильные пути: `/dev/disk/by-partuuid/xxx...` вместо простых
+    `/dev/sda` или `/dev/nvme0n1`, чтобы пути не могли спутаться после
+    перезагрузки сервера. Также вместо блочных устройств можно указывать файлы,
+    но это реализовано только для тестирования, а не для боевой среды.
+- name: meta_device
+  type: string
+  info: |
+    Path to the block device to use for the metadata. Metadata must be on a fast
+    SSD or performance will suffer. If this option is skipped, `data_device` is
+    used for the metadata.
+  info_ru: |
+    Путь к диску метаданных. Метаданные должны располагаться на быстром
+    SSD-диске, иначе производительность пострадает. Если эта опция не указана,
+    для метаданных используется `data_device`.
+- name: journal_device
+  type: string
+  info: |
+    Path to the block device to use for the journal. Journal must be on a fast
+    SSD or performance will suffer. If this option is skipped, `meta_device` is
+    used for the journal, and if it's also empty, journal is put on
+    `data_device`. It's almost always fine to put metadata and journal on the
+    same device, in this case you only need to set `meta_device`.
+  info_ru: |
+    Путь к диску журнала. Журнал должен располагаться на быстром SSD-диске,
+    иначе производительность пострадает. Если эта опция не указана,
+    для журнала используется `meta_device`, если же пуста и она, журнал
+    располагается на `data_device`. Нормально располагать журнал и метаданные
+    на одном устройстве, в этом случае достаточно указать только `meta_device`.
+- name: journal_offset
+  type: int
+  default: 0
+  info: Offset on the device in bytes where the journal is stored.
+  info_ru: Смещение на устройстве в байтах, по которому располагается журнал.
+- name: journal_size
+  type: int
+  info: |
+    Journal size in bytes. Doesn't have to be large, 16-32 MB is usually fine.
+    By default, the whole journal device will be used for the journal. You must
+    set it to some value manually (or use make-osd.sh) if you colocate the
+    journal with data or metadata.
+  info_ru: |
+    Размер журнала в байтах. Большим быть не обязан, 16-32 МБ обычно достаточно.
+    По умолчанию для журнала используется всё устройство журнала. Если же вы
+    размещаете журнал на устройстве данных или метаданных, то вы должны
+    установить эту опцию в какое-то значение сами (или использовать скрипт
+    make-osd.sh).
+- name: meta_offset
+  type: int
+  default: 0
+  info: |
+    Offset on the device in bytes where the metadata area is stored.
+    Again, set it to something if you colocate metadata with journal or data.
+  info_ru: |
+    Смещение на устройстве в байтах, по которому располагаются метаданные.
+    Эту опцию нужно задать, если метаданные у вас хранятся на том же
+    устройстве, что данные или журнал.
+- name: data_offset
+  type: int
+  default: 0
+  info: |
+    Offset on the device in bytes where the data area is stored.
+    Again, set it to something if you colocate data with journal or metadata.
+  info_ru: |
+    Смещение на устройстве в байтах, по которому располагаются данные.
+    Эту опцию нужно задать, если данные у вас хранятся на том же
+    устройстве, что метаданные или журнал.
+- name: data_size
+  type: int
+  info: |
+    Data area size in bytes. By default, the whole data device up to the end
+    will be used for the data area, but you can restrict it if you want to use
+    a smaller part. Note that there is no option to set metadata area size -
+    it's derived from the data area size.
+  info_ru: |
+    Размер области данных в байтах. По умолчанию под данные будет использована
+    вся доступная область устройства данных до конца устройства, но вы можете
+    использовать эту опцию, чтобы ограничить её меньшим размером. Заметьте, что
+    опции размера области метаданных нет - она вычисляется из размера области
+    данных автоматически.
+- name: meta_block_size
+  type: int
+  default: 4096
+  info: |
+    Physical block size of the metadata device. 4096 for most current
+    HDDs and SSDs.
+  info_ru: |
+    Размер физического блока устройства метаданных. 4096 для большинства
+    современных SSD и HDD.
+- name: journal_block_size
+  type: int
+  default: 4096
+  info: |
+    Physical block size of the journal device. Must be a multiple of
+    `disk_alignment`. 4096 for most current HDDs and SSDs.
+  info_ru: |
+    Размер физического блока устройства журнала. Должен быть кратен
+    `disk_alignment`. 4096 для большинства современных SSD и HDD.
+- name: disable_data_fsync
+  type: bool
+  default: false
+  info: |
+    Do not issue fsyncs to the data device, i.e. do not flush its cache.
+    Safe ONLY if your data device has write-through cache. If you disable
+    the cache yourself using `hdparm` or `scsi_disk/cache_type` then make sure
+    that the cache disable command is run every time before starting Vitastor
+    OSD, for example, in the systemd unit. See also `immediate_commit` option
+    for the instructions to disable cache and how to benefit from it.
+  info_ru: |
+    Не отправлять fsync-и устройству данных, т.е. не сбрасывать его кэш.
+    Безопасно, ТОЛЬКО если ваше устройство данных имеет кэш со сквозной
+    записью (write-through). Если вы отключаете кэш через `hdparm` или
+    `scsi_disk/cache_type`, то удостоверьтесь, что команда отключения кэша
+    выполняется перед каждым запуском Vitastor OSD, например, в systemd unit-е.
+    Смотрите также опцию `immediate_commit` для инструкций по отключению кэша
+    и о том, как из этого извлечь выгоду.
+- name: disable_meta_fsync
+  type: bool
+  default: false
+  info: |
+    Same as disable_data_fsync, but for the metadata device. If the metadata
+    device is not set or if the data device is used for the metadata the option
+    is ignored and disable_data_fsync value is used instead of it.
+  info_ru: |
+    То же, что disable_data_fsync, но для устройства метаданных. Если устройство
+    метаданных не задано или если оно равно устройству данных, значение опции
+    игнорируется и вместо него используется значение опции disable_data_fsync.
+- name: disable_journal_fsync
+  type: bool
+  default: false
+  info: |
+    Same as disable_data_fsync, but for the journal device. If the journal
+    device is not set or if the metadata device is used for the journal the
+    option is ignored and disable_meta_fsync value is used instead of it. If
+    the same device is used for data, metadata and journal the option is also
+    ignored and disable_data_fsync value is used instead of it.
+  info_ru: |
+    То же, что disable_data_fsync, но для устройства журнала. Если устройство
+    журнала не задано или если оно равно устройству метаданных, значение опции
+    игнорируется и вместо него используется значение опции disable_meta_fsync.
+    Если одно и то же устройство используется и под данные, и под журнал, и под
+    метаданные - значение опции также игнорируется и вместо него используется
+    значение опции disable_data_fsync.
+- name: disable_device_lock
+  type: bool
+  default: false
+  info: |
+    Do not lock data, metadata and journal block devices exclusively with
+    flock(). Though it's not recommended, but you can use it you want to run
+    multiple OSD with a single device and different offsets, without using
+    partitions.
+  info_ru: |
+    Не блокировать устройства данных, метаданных и журнала от открытия их
+    другими OSD с помощью flock(). Так делать не рекомендуется, но теоретически
+    вы можете это использовать, чтобы запускать несколько OSD на одном
+    устройстве с разными смещениями и без использования разделов.
+- name: disk_alignment
+  type: int
+  default: 4096
+  info: |
+    Required physical disk write alignment. Most current SSD and HDD drives
+    use 4 KB physical sectors even if they report 512 byte logical sector
+    size, so 4 KB is a good default setting.
+
+    Note, however, that physical sector size also affects WA, because with block
+    devices it's impossible to write anything smaller than a block. So, when
+    Vitastor has to write a single metadata entry that's only about 32 bytes in
+    size, it actually has to write the whole 4 KB sector.
+
+    Because of this it can actually be beneficial to use SSDs which work well
+    with 512 byte sectors and use 512 byte disk_alignment, journal_block_size
+    and meta_block_size. But the only SSD that may fit into this category is
+    Intel Optane (probably, not tested yet).
+
+    Clients don't need to be aware of disk_alignment, so it's not required to
+    put a modified value into etcd key /vitastor/config/global.
+  info_ru: |
+    Требуемое выравнивание записи на физические диски. Почти все современные
+    SSD и HDD диски используют 4 КБ физические секторы, даже если показывают
+    логический размер сектора 512 байт, поэтому 4 КБ - хорошее значение по
+    умолчанию.
+
+    Однако стоит понимать, что физический размер сектора тоже влияет на
+    избыточную запись (WA), потому что ничего меньше блока (сектора) на блочное
+    устройство записать невозможно. Таким образом, когда Vitastor-у нужно
+    записать на диск всего лишь одну 32-байтную запись метаданных, фактически
+    приходится перезаписывать 4 КБ сектор целиком.
+
+    Поэтому, на самом деле, может быть выгодно найти SSD, хорошо работающие с
+    меньшими, 512-байтными, блоками и использовать 512-байтные disk_alignment,
+    journal_block_size и meta_block_size. Однако единственные SSD, которые
+    теоретически могут попасть в эту категорию - это Intel Optane (но и это
+    пока не проверялось автором).
+
+    Клиентам не обязательно знать про disk_alignment, так что помещать значение
+    этого параметра в etcd в /vitastor/config/global не нужно.

docs/params/monitor.yml

@@ -0,0 +1,65 @@
+- name: etcd_mon_ttl
+  type: sec
+  min: 10
+  default: 30
+  info: Monitor etcd lease refresh interval in seconds
+  info_ru: Интервал обновления etcd резервации (lease) монитором
+- name: etcd_mon_timeout
+  type: ms
+  default: 1000
+  info: etcd request timeout used by monitor
+  info_ru: Таймаут выполнения запросов к etcd от монитора
+- name: etcd_mon_retries
+  type: int
+  default: 5
+  info: Maximum number of attempts for one monitor etcd request
+  info_ru: Максимальное число попыток выполнения запросов к etcd монитором
+- name: mon_change_timeout
+  type: ms
+  min: 100
+  default: 1000
+  info: Optimistic retry interval for monitor etcd modification requests
+  info_ru: Время повтора при коллизиях при запросах модификации в etcd, производимых монитором
+- name: mon_stats_timeout
+  type: ms
+  min: 100
+  default: 1000
+  info: |
+    Interval for monitor to wait before updating aggregated statistics in
+    etcd after receiving OSD statistics updates
+  info_ru: |
+    Интервал, который монитор ожидает при изменении статистики по отдельным
+    OSD перед обновлением агрегированной статистики в etcd
+- name: osd_out_time
+  type: sec
+  default: 600
+  info: |
+    Time after which a failed OSD is removed from the data distribution.
+    I.e. time which the monitor waits before attempting to restore data
+    redundancy using other OSDs.
+  info_ru: |
+    Время, через которое отключенный OSD исключается из распределения данных.
+    То есть, время, которое монитор ожидает перед попыткой переместить данные
+    на другие OSD и таким образом восстановить избыточность хранения.
+- name: placement_levels
+  type: json
+  default: '`{"host":100,"osd":101}`'
+  info: |
+    Levels for the placement tree. You can define arbitrary tree levels by
+    defining them in this parameter. The configuration parameter value should
+    contain a JSON object with level names as keys and integer priorities as
+    values.  Smaller priority means higher level in tree. For example,
+    "datacenter" should have smaller priority than "osd". "host" and "osd"
+    levels are always predefined and can't be removed. If one of them is not
+    present in the configuration, then it is defined with the default priority
+    (100 for "host", 101 for "osd").
+  info_ru: |
+    Определения уровней для дерева размещения OSD. Вы можете определять
+    произвольные уровни, помещая их в данный параметр конфигурации. Значение
+    параметра должно содержать JSON-объект, ключи которого будут являться
+    названиями уровней, а значения - целочисленными приоритетами. Меньшие
+    приоритеты соответствуют верхним уровням дерева. Например, уровень
+    "датацентр" должен иметь меньший приоритет, чем "OSD". Уровни с названиями
+    "host" и "osd" являются предопределёнными и не могут быть удалены. Если
+    один из них отсутствует в конфигурации, он доопределяется с приоритетом по
+    умолчанию (100 для уровня "host", 101 для "osd").

docs/params/network.yml

@@ -0,0 +1,225 @@
+- name: tcp_header_buffer_size
+  type: int
+  default: 65536
+  info: |
+    Size of the buffer used to read data using an additional copy. Vitastor
+    packet headers are 128 bytes, payload is always at least 4 KB, so it is
+    usually beneficial to try to read multiple packets at once even though
+    it requires to copy the data an additional time. The rest of each packet
+    is received without an additional copy. You can try to play with this
+    parameter and see how it affects random iops and linear bandwidth if you
+    want.
+  info_ru: |
+    Размер буфера для чтения данных с дополнительным копированием. Пакеты
+    Vitastor содержат 128-байтные заголовки, за которыми следуют данные размером
+    от 4 КБ и для мелких операций ввода-вывода обычно выгодно за 1 вызов читать
+    сразу несколько пакетов, даже не смотря на то, что это требует лишний раз
+    скопировать данные. Часть каждого пакета за пределами значения данного
+    параметра читается без дополнительного копирования. Вы можете попробовать
+    поменять этот параметр и посмотреть, как он влияет на производительность
+    случайного и линейного доступа.
+- name: use_sync_send_recv
+  type: bool
+  default: false
+  info: |
+    If true, synchronous send/recv syscalls are used instead of io_uring for
+    socket communication. Useless for OSDs because they require io_uring anyway,
+    but may be required for clients with old kernel versions.
+  info_ru: |
+    Если установлено в истину, то вместо io_uring для передачи данных по сети
+    будут использоваться обычные синхронные системные вызовы send/recv. Для OSD
+    это бессмысленно, так как OSD в любом случае нуждается в io_uring, но, в
+    принципе, это может применяться для клиентов со старыми версиями ядра.
+- name: use_rdma
+  type: bool
+  default: true
+  info: |
+    Try to use RDMA for communication if it's available. Disable if you don't
+    want Vitastor to use RDMA. RDMA increases the performance, but TCP-only
+    clients can still talk to an RDMA-enabled cluster, so you don't need to
+    make sure that all clients support RDMA when enabling it.
+  info_ru: |
+    Пытаться использовать RDMA для связи при наличии доступных устройств.
+    Отключите, если вы не хотите, чтобы Vitastor использовал RDMA.
+    RDMA улучшает производительность, но 
+    Клиенты и клиентов and TCP-only clients in the cluster at the
+    same time - TCP-only clients are still able to use an RDMA-enabled cluster.
+- name: rdma_device
+  type: string
+  info: |
+    RDMA device name to use for Vitastor OSD communications (for example,
+    "rocep5s0f0"). Please note that Vitastor RDMA requires Implicit On-Demand
+    Paging (Implicit ODP) and Scatter/Gather (SG) support from the RDMA device
+    to work. For example, Mellanox ConnectX-3 and older adapters don't have
+    Implicit ODP, so they're unsupported by Vitastor. Run `ibv_devinfo -v` as
+    root to list available RDMA devices and their features.
+  info_ru: |
+    Название RDMA-устройства для связи с Vitastor OSD (например, "rocep5s0f0").
+    Имейте в виду, что поддержка RDMA в Vitastor требует функций устройства
+    Implicit On-Demand Paging (Implicit ODP) и Scatter/Gather (SG). Например,
+    адаптеры Mellanox ConnectX-3 и более старые не поддерживают Implicit ODP и
+    потому не поддерживаются в Vitastor. Запустите `ibv_devinfo -v` от имени
+    суперпользователя, чтобы посмотреть список доступных RDMA-устройств, их
+    параметры и возможности.
+- name: rdma_port_num
+  type: int
+  default: 1
+  info: |
+    RDMA device port number to use. Only for devices that have more than 1 port.
+    See `phys_port_cnt` in `ibv_devinfo -v` output to determine how many ports
+    your device has.
+  info_ru: |
+    Номер порта RDMA-устройства, который следует использовать. Имеет смысл
+    только для устройств, у которых более 1 порта. Чтобы узнать, сколько портов
+    у вашего адаптера, посмотрите `phys_port_cnt` в выводе команды
+    `ibv_devinfo -v`.
+- name: rdma_gid_index
+  type: int
+  default: 0
+  info: |
+    Global address identifier index of the RDMA device to use. Different GID
+    indexes may correspond to different protocols like RoCEv1, RoCEv2 and iWARP.
+    Search for "GID" in `ibv_devinfo -v` output to determine which GID index
+    you need.
+
+    **IMPORTANT:** If you want to use RoCEv2 (as recommended) then the correct
+    rdma_gid_index is usually 1 (IPv6) or 3 (IPv4).
+  info_ru: |
+    Номер глобального идентификатора адреса RDMA-устройства, который следует
+    использовать. Разным gid_index могут соответствовать разные протоколы связи:
+    RoCEv1, RoCEv2, iWARP. Чтобы понять, какой нужен вам - смотрите строчки со
+    словом "GID" в выводе команды `ibv_devinfo -v`.
+
+    **ВАЖНО:** Если вы хотите использовать RoCEv2 (как мы и рекомендуем), то
+    правильный rdma_gid_index, как правило, 1 (IPv6) или 3 (IPv4).
+- name: rdma_mtu
+  type: int
+  default: 4096
+  info: |
+    RDMA Path MTU to use. Must be 1024, 2048 or 4096. There is usually no
+    sense to change it from the default 4096.
+  info_ru: |
+    Максимальная единица передачи (Path MTU) для RDMA. Должно быть равно 1024,
+    2048 или 4096. Обычно нет смысла менять значение по умолчанию, равное 4096.
+- name: rdma_max_sge
+  type: int
+  default: 128
+  info: |
+    Maximum number of scatter/gather entries to use for RDMA. OSDs negotiate
+    the actual value when establishing connection anyway, so it's usually not
+    required to change this parameter.
+  info_ru: |
+    Максимальное число записей разделения/сборки (scatter/gather) для RDMA.
+    OSD в любом случае согласовывают реальное значение при установке соединения,
+    так что менять этот параметр обычно не нужно.
+- name: rdma_max_msg
+  type: int
+  default: 1048576
+  info: Maximum size of a single RDMA send or receive operation in bytes.
+  info_ru: Максимальный размер одной RDMA-операции отправки или приёма.
+- name: rdma_max_recv
+  type: int
+  default: 8
+  info: |
+    Maximum number of parallel RDMA receive operations. Note that this number
+    of receive buffers `rdma_max_msg` in size are allocated for each client,
+    so this setting actually affects memory usage. This is because RDMA receive
+    operations are (sadly) still not zero-copy in Vitastor. It may be fixed in
+    later versions.
+  info_ru: |
+    Максимальное число параллельных RDMA-операций получения данных. Следует
+    иметь в виду, что данное число буферов размером `rdma_max_msg` выделяется
+    для каждого подключённого клиентского соединения, так что данная настройка
+    влияет на потребление памяти. Это так потому, что RDMA-приём данных в
+    Vitastor, увы, всё равно не является zero-copy, т.е. всё равно 1 раз
+    копирует данные в памяти. Данная особенность, возможно, будет исправлена в
+    более новых версиях Vitastor.
+- name: peer_connect_interval
+  type: sec
+  min: 1
+  default: 5
+  info: Interval before attempting to reconnect to an unavailable OSD.
+  info_ru: Время ожидания перед повторной попыткой соединиться с недоступным OSD.
+- name: peer_connect_timeout
+  type: sec
+  min: 1
+  default: 5
+  info: Timeout for OSD connection attempts.
+  info_ru: Максимальное время ожидания попытки соединения с OSD.
+- name: osd_idle_timeout
+  type: sec
+  min: 1
+  default: 5
+  info: |
+    OSD connection inactivity time after which clients and other OSDs send
+    keepalive requests to check state of the connection.
+  info_ru: |
+    Время неактивности соединения с OSD, после которого клиенты или другие OSD
+    посылают запрос проверки состояния соединения.
+- name: osd_ping_timeout
+  type: sec
+  min: 1
+  default: 5
+  info: |
+    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.
+  info_ru: |
+    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: 50
+  default: 500
+  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
+  info: |
+    Maximum number of attempts for etcd requests which can't be retried
+    indefinitely.
+  info_ru: |
+    Максимальное число попыток выполнения запросов к etcd для тех запросов,
+    которые нельзя повторять бесконечно.
+- name: etcd_quick_timeout
+  type: ms
+  default: 1000
+  info: |
+    Timeout for etcd requests which should complete quickly, like lease refresh.
+  info_ru: |
+    Максимальное время выполнения запросов к etcd, которые должны завершаться
+    быстро, таких, как обновление резервации (lease).
+- name: etcd_slow_timeout
+  type: ms
+  default: 5000
+  info: Timeout for etcd requests which are allowed to wait for some time.
+  info_ru: |
+    Максимальное время выполнения запросов к etcd, для которых не обязательно
+    гарантировать быстрое выполнение.
+- name: etcd_keepalive_timeout
+  type: sec
+  default: max(30, etcd_report_interval*2)
+  info: |
+    Timeout for etcd connection HTTP Keep-Alive. Should be higher than
+    etcd_report_interval to guarantee that keepalive actually works.
+  info_ru: |
+    Таймаут для HTTP Keep-Alive в соединениях к etcd. Должен быть больше, чем
+    etcd_report_interval, чтобы keepalive гарантированно работал.
+- name: etcd_ws_keepalive_timeout
+  type: sec
+  default: 30
+  info: |
+    etcd websocket ping interval required to keep the connection alive and
+    detect disconnections quickly.
+  info_ru: |
+    Интервал проверки живости вебсокет-подключений к etcd.

docs/params/osd.yml

@@ -0,0 +1,345 @@
+- name: etcd_report_interval
+  type: sec
+  default: 5
+  info: |
+    Interval at which OSDs report their state to etcd. Affects OSD lease time
+    and thus the failover speed. Lease time is equal to this parameter value
+    plus max_etcd_attempts * etcd_quick_timeout because it should be guaranteed
+    that every OSD always refreshes its lease in time.
+  info_ru: |
+    Интервал, с которым OSD обновляет своё состояние в etcd. Значение параметра
+    влияет на время резервации (lease) OSD и поэтому на скорость переключения
+    при падении OSD. Время lease равняется значению этого параметра плюс
+    max_etcd_attempts * etcd_quick_timeout.
+- name: run_primary
+  type: bool
+  default: true
+  info: |
+    Start primary OSD logic on this OSD. As of now, can be turned off only for
+    debugging purposes. It's possible to implement additional feature for the
+    monitor which may allow to separate primary and secondary OSDs, but it's
+    unclear why anyone could need it, so it's not implemented.
+  info_ru: |
+    Запускать логику первичного OSD на данном OSD. На данный момент отключать
+    эту опцию может иметь смысл только в целях отладки. В теории, можно
+    реализовать дополнительный режим для монитора, который позволит отделять
+    первичные OSD от вторичных, но пока не понятно, зачем это может кому-то
+    понадобиться, поэтому это не реализовано.
+- name: osd_network
+  type: string or array of strings
+  type_ru: строка или массив строк
+  info: |
+    Network mask of the network (IPv4 or IPv6) to use for OSDs. Note that
+    although it's possible to specify multiple networks here, this does not
+    mean that OSDs will create multiple listening sockets - they'll only
+    pick the first matching address of an UP + RUNNING interface. Separate
+    networks for cluster and client connections are also not implemented, but
+    they are mostly useless anyway, so it's not a big deal.
+  info_ru: |
+    Маска подсети (IPv4 или IPv6) для использования для соединений с OSD.
+    Имейте в виду, что хотя сейчас и можно передать в этот параметр несколько
+    подсетей, это не означает, что OSD будут создавать несколько слушающих
+    сокетов - они лишь будут выбирать адрес первого поднятого (состояние UP +
+    RUNNING), подходящий под заданную маску. Также не реализовано разделение
+    кластерной и публичной сетей OSD. Правда, от него обычно всё равно довольно
+    мало толку, так что особенной проблемы в этом нет.
+- name: bind_address
+  type: string
+  default: "0.0.0.0"
+  info: |
+    Instead of the network mask, you can also set OSD listen address explicitly
+    using this parameter. May be useful if you want to start OSDs on interfaces
+    that are not UP + RUNNING.
+  info_ru: |
+    Этим параметром можно явным образом задать адрес, на котором будет ожидать
+    соединений OSD (вместо использования маски подсети). Может быть полезно,
+    например, чтобы запускать OSD на неподнятых интерфейсах (не UP + RUNNING).
+- name: bind_port
+  type: int
+  info: |
+    By default, OSDs pick random ports to use for incoming connections
+    automatically. With this option you can set a specific port for a specific
+    OSD by hand.
+  info_ru: |
+    По умолчанию OSD сами выбирают случайные порты для входящих подключений.
+    С помощью данной опции вы можете задать порт для отдельного OSD вручную.
+- name: autosync_interval
+  type: sec
+  default: 5
+  info: |
+    Time interval at which automatic fsyncs/flushes are issued by each OSD when
+    the immediate_commit mode if disabled. fsyncs are required because without
+    them OSDs quickly fill their journals, become unable to clear them and
+    stall. Also this option limits the amount of recent uncommitted changes
+    which OSDs may lose in case of a power outage in case when clients don't
+    issue fsyncs at all.
+  info_ru: |
+    Временной интервал отправки автоматических fsync-ов (операций очистки кэша)
+    каждым OSD для случая, когда режим immediate_commit отключён. fsync-и нужны
+    OSD, чтобы успевать очищать журнал - без них OSD быстро заполняют журналы и
+    перестают обрабатывать операции записи. Также эта опция ограничивает объём
+    недавних незафиксированных изменений, которые OSD могут терять при
+    отключении питания, если клиенты вообще не отправляют fsync.
+- name: autosync_writes
+  type: int
+  default: 128
+  info: |
+    Same as autosync_interval, but sets the maximum number of uncommitted write
+    operations before issuing an fsync operation internally.
+  info_ru: |
+    Аналогично autosync_interval, но задаёт не временной интервал, а
+    максимальное количество незафиксированных операций записи перед
+    принудительной отправкой fsync-а.
+- name: recovery_queue_depth
+  type: int
+  default: 4
+  info: |
+    Maximum recovery operations per one primary OSD at any given moment of time.
+    Currently it's the only parameter available to tune the speed or recovery
+    and rebalancing, but it's planned to implement more.
+  info_ru: |
+    Максимальное число операций восстановления на одном первичном OSD в любой
+    момент времени. На данный момент единственный параметр, который можно менять
+    для ускорения или замедления восстановления и перебалансировки данных, но
+    в планах реализация других параметров.
+- name: recovery_sync_batch
+  type: int
+  default: 16
+  info: Maximum number of recovery operations before issuing an additional fsync.
+  info_ru: Максимальное число операций восстановления перед дополнительным fsync.
+- name: readonly
+  type: bool
+  default: false
+  info: |
+    Read-only mode. If this is enabled, an OSD will never issue any writes to
+    the underlying device. This may be useful for recovery purposes.
+  info_ru: |
+    Режим "только чтение". Если включить этот режим, OSD не будет писать ничего
+    на диск. Может быть полезно в целях восстановления.
+- name: no_recovery
+  type: bool
+  default: false
+  info: |
+    Disable automatic background recovery of objects. Note that it doesn't
+    affect implicit recovery of objects happening during writes - a write is
+    always made to a full set of at least pg_minsize OSDs.
+  info_ru: |
+    Отключить автоматическое фоновое восстановление объектов. Обратите внимание,
+    что эта опция не отключает восстановление объектов, происходящее при
+    записи - запись всегда производится в полный набор из как минимум pg_minsize
+    OSD.
+- name: no_rebalance
+  type: bool
+  default: false
+  info: |
+    Disable background movement of data between different OSDs. Disabling it
+    means that PGs in the `has_misplaced` state will be left in it indefinitely.
+  info_ru: |
+    Отключить фоновое перемещение объектов между разными OSD. Отключение
+    означает, что PG, находящиеся в состоянии `has_misplaced`, будут оставлены
+    в нём на неопределённый срок.
+- name: print_stats_interval
+  type: sec
+  default: 3
+  info: |
+    Time interval at which OSDs print simple human-readable operation
+    statistics on stdout.
+  info_ru: |
+    Временной интервал, с которым OSD печатают простую человекочитаемую
+    статистику выполнения операций в стандартный вывод.
+- name: slow_log_interval
+  type: sec
+  default: 10
+  info: |
+    Time interval at which OSDs dump slow or stuck operations on stdout, if
+    they're any. Also it's the time after which an operation is considered
+    "slow".
+  info_ru: |
+    Временной интервал, с которым OSD выводят в стандартный вывод список
+    медленных или зависших операций, если таковые имеются. Также время, при
+    превышении которого операция считается "медленной".
+- name: max_write_iodepth
+  type: int
+  default: 128
+  info: |
+    Parallel client write operation limit per one OSD. Operations that exceed
+    this limit are pushed to a temporary queue instead of being executed
+    immediately.
+  info_ru: |
+    Максимальное число одновременных клиентских операций записи на один OSD.
+    Операции, превышающие этот лимит, не исполняются сразу, а сохраняются во
+    временной очереди.
+- name: min_flusher_count
+  type: int
+  default: 1
+  info: |
+    Flusher is a micro-thread that moves data from the journal to the data
+    area of the device. Their number is auto-tuned between minimum and maximum.
+    Minimum number is set by this parameter.
+  info_ru: |
+    Flusher - это микро-поток (корутина), которая копирует данные из журнала в
+    основную область устройства данных. Их число настраивается динамически между
+    минимальным и максимальным значением. Этот параметр задаёт минимальное число.
+- name: max_flusher_count
+  type: int
+  default: 256
+  info: |
+    Maximum number of journal flushers (see above min_flusher_count).
+  info_ru: |
+    Максимальное число микро-потоков очистки журнала (см. выше min_flusher_count).
+- name: inmemory_metadata
+  type: bool
+  default: true
+  info: |
+    This parameter makes Vitastor always keep metadata area of the block device
+    in memory. It's required for good performance because it allows to avoid
+    additional read-modify-write cycles during metadata modifications. Metadata
+    area size is currently roughly 224 MB per 1 TB of data. You can turn it off
+    to reduce memory usage by this value, but it will hurt performance. This
+    restriction is likely to be removed in the future along with the upgrade
+    of the metadata storage scheme.
+  info_ru: |
+    Данный параметр заставляет Vitastor всегда держать область метаданных диска
+    в памяти. Это нужно, чтобы избегать дополнительных операций чтения с диска
+    при записи. Размер области метаданных на данный момент составляет примерно
+    224 МБ на 1 ТБ данных. При включении потребление памяти снизится примерно
+    на эту величину, но при этом также снизится и производительность. В будущем,
+    после обновления схемы хранения метаданных, это ограничение, скорее всего,
+    будет ликвидировано.
+- name: inmemory_journal
+  type: bool
+  default: true
+  info: |
+    This parameter make Vitastor always keep journal area of the block
+    device in memory. Turning it off will, again, reduce memory usage, but
+    hurt performance because flusher coroutines will have to read data from
+    the disk back before copying it into the main area. The memory usage benefit
+    is typically very small because it's sufficient to have 16-32 MB journal
+    for SSD OSDs. However, in theory it's possible that you'll want to turn it
+    off for hybrid (HDD+SSD) OSDs with large journals on quick devices.
+  info_ru: |
+    Данный параметр заставляет Vitastor всегда держать в памяти журналы OSD.
+    Отключение параметра, опять же, снижает потребление памяти, но ухудшает
+    производительность, так как для копирования данных из журнала в основную
+    область устройства OSD будут вынуждены читать их обратно с диска. Выигрыш
+    по памяти при этом обычно крайне низкий, так как для SSD OSD обычно
+    достаточно 16- или 32-мегабайтного журнала. Однако в теории отключение
+    параметра может оказаться полезным для гибридных OSD (HDD+SSD) с большими
+    журналами, расположенными на быстром по сравнению с HDD устройстве.
+- name: journal_sector_buffer_count
+  type: int
+  default: 32
+  info: |
+    Maximum number of buffers that can be used for writing journal metadata
+    blocks. The only situation when you should increase it to a larger value
+    is when you enable journal_no_same_sector_overwrites. In this case set
+    it to, for example, 1024.
+  info_ru: |
+    Максимальное число буферов, разрешённых для использования под записываемые
+    в журнал блоки метаданных. Единственная ситуация, в которой этот параметр
+    нужно менять - это если вы включаете journal_no_same_sector_overwrites. В
+    этом случае установите данный параметр, например, в 1024.
+- name: journal_no_same_sector_overwrites
+  type: bool
+  default: false
+  info: |
+    Enable this option for SSDs like Intel D3-S4510 and D3-S4610 which REALLY
+    don't like when a program overwrites the same sector multiple times in a
+    row and slow down significantly (from 25000+ iops to ~3000 iops). When
+    this option is set, Vitastor will always move to the next sector of the
+    journal after writing it instead of possibly overwriting it the second time.
+
+    Most (99%) other SSDs don't need this option.
+  info_ru: |
+    Включайте данную опцию для SSD вроде Intel D3-S4510 и D3-S4610, которые
+    ОЧЕНЬ не любят, когда ПО перезаписывает один и тот же сектор несколько раз
+    подряд. Такие SSD при многократной перезаписи одного и того же сектора
+    сильно замедляются - условно, с 25000 и более iops до 3000 iops. Когда
+    данная опция установлена, Vitastor всегда переходит к следующему сектору
+    журнала после записи вместо потенциально повторной перезаписи того же
+    самого сектора.
+
+    Почти все другие SSD (99% моделей) не требуют данной опции.
+- name: throttle_small_writes
+  type: bool
+  default: false
+  info: |
+    Enable soft throttling of small journaled writes. Useful for hybrid OSDs
+    with fast journal/metadata devices and slow data devices. The idea is that
+    small writes complete very quickly because they're first written to the
+    journal device, but moving them to the main device is slow. So if an OSD
+    allows clients to issue a lot of small writes it will perform very good
+    for several seconds and then the journal will fill up and the performance
+    will drop to almost zero. Throttling is meant to prevent this problem by
+    artifically slowing quick writes down based on the amount of free space in
+    the journal. When throttling is used, the performance of small writes will
+    decrease smoothly instead of abrupt drop at the moment when the journal
+    fills up.
+  info_ru: |
+    Разрешить мягкое ограничение скорости журналируемой записи. Полезно для
+    гибридных OSD с быстрыми устройствами метаданных и медленными устройствами
+    данных. Идея заключается в том, что мелкие записи в этой ситуации могут
+    завершаться очень быстро, так как они изначально записываются на быстрое
+    журнальное устройство (SSD). Но перемещать их потом на основное медленное
+    устройство долго. Поэтому если OSD быстро примет от клиентов очень много
+    мелких операций записи, он быстро заполнит свой журнал, после чего
+    производительность записи резко упадёт практически до нуля. Ограничение
+    скорости записи призвано решить эту проблему с помощью искусственного
+    замедления операций записи на основании объёма свободного места в журнале.
+    Когда эта опция включена, производительность мелких операций записи будет
+    снижаться плавно, а не резко в момент окончательного заполнения журнала.
+- name: throttle_target_iops
+  type: int
+  default: 100
+  info: |
+    Target maximum number of throttled operations per second under the condition
+    of full journal. Set it to approximate random write iops of your data devices
+    (HDDs).
+  info_ru: |
+    Расчётное максимальное число ограничиваемых операций в секунду при условии
+    отсутствия свободного места в журнале. Устанавливайте приблизительно равным
+    максимальной производительности случайной записи ваших устройств данных
+    (HDD) в операциях в секунду.
+- name: throttle_target_mbs
+  type: int
+  default: 100
+  info: |
+    Target maximum bandwidth in MB/s of throttled operations per second under
+    the condition of full journal. Set it to approximate linear write
+    performance of your data devices (HDDs).
+  info_ru: |
+    Расчётный максимальный размер в МБ/с ограничиваемых операций в секунду при
+    условии отсутствия свободного места в журнале. Устанавливайте приблизительно
+    равным максимальной производительности линейной записи ваших устройств
+    данных (HDD).
+- name: throttle_target_parallelism
+  type: int
+  default: 1
+  info: |
+    Target maximum parallelism of throttled operations under the condition of
+    full journal. Set it to approximate internal parallelism of your data
+    devices (1 for HDDs, 4-8 for SSDs).
+  info_ru: |
+    Расчётный максимальный параллелизм ограничиваемых операций в секунду при
+    условии отсутствия свободного места в журнале. Устанавливайте приблизительно
+    равным внутреннему параллелизму ваших устройств данных (1 для HDD, 4-8
+    для SSD).
+- name: throttle_threshold_us
+  type: us
+  default: 50
+  info: |
+    Minimal computed delay to be applied to throttled operations. Usually
+    doesn't need to be changed.
+  info_ru: |
+    Минимальная применимая к ограничиваемым операциям задержка. Обычно не
+    требует изменений.
+- name: osd_memlock
+  type: bool
+  default: false
+  info: >
+    Lock all OSD memory to prevent it from being unloaded into swap with
+    mlockall(). Requires sufficient ulimit -l (max locked memory).
+  info_ru: >
+    Блокировать всю память OSD с помощью mlockall, чтобы запретить её выгрузку
+    в пространство подкачки. Требует достаточного значения ulimit -l (лимита
+    заблокированной памяти).

mon/lp-optimizer.js

@@ -50,7 +50,7 @@ async function lp_solve(text)
     return { score, vars };
 }
 
-async function optimize_initial({ osd_tree, pg_count, pg_size = 3, pg_minsize = 2, max_combinations = 10000, parity_space = 1 })
+async function optimize_initial({ osd_tree, pg_count, pg_size = 3, pg_minsize = 2, max_combinations = 10000, parity_space = 1, ordered = false })
 {
     if (!pg_count || !osd_tree)
     {
@@ -92,7 +92,7 @@ async function optimize_initial({ osd_tree, pg_count, pg_size = 3, pg_minsize =
         console.log(lp);
         throw new Error('Problem is infeasible or unbounded - is it a bug?');
     }
-    const int_pgs = make_int_pgs(lp_result.vars, pg_count);
+    const int_pgs = make_int_pgs(lp_result.vars, pg_count, ordered);
     const eff = pg_list_space_efficiency(int_pgs, all_weights, pg_minsize, parity_space);
     const res = {
         score: lp_result.score,
@@ -115,7 +115,7 @@ function shuffle(array)
     }
 }
 
-function make_int_pgs(weights, pg_count)
+function make_int_pgs(weights, pg_count, round_robin)
 {
     const total_weight = Object.values(weights).reduce((a, c) => Number(a) + Number(c), 0);
     let int_pgs = [];
@@ -123,10 +123,15 @@ function make_int_pgs(weights, pg_count)
     let weight_left = total_weight;
     for (const pg_name in weights)
     {
+        let cur_pg = pg_name.substr(3).split('_');
         let n = Math.round(weights[pg_name] / weight_left * pg_left);
         for (let i = 0; i < n; i++)
         {
-            int_pgs.push(pg_name.substr(3).split('_'));
+            int_pgs.push([ ...cur_pg ]);
+            if (round_robin)
+            {
+                cur_pg.push(cur_pg.shift());
+            }
         }
         weight_left -= weights[pg_name];
         pg_left -= n;
@@ -135,20 +140,20 @@ function make_int_pgs(weights, pg_count)
     return int_pgs;
 }
 
-function calc_intersect_weights(pg_size, pg_count, prev_weights, all_pgs)
+function calc_intersect_weights(old_pg_size, pg_size, pg_count, prev_weights, all_pgs, ordered)
 {
     const move_weights = {};
-    if ((1 << pg_size) < pg_count)
+    if ((1 << old_pg_size) < pg_count)
     {
         const intersect = {};
         for (const pg_name in prev_weights)
         {
             const pg = pg_name.substr(3).split(/_/);
-            for (let omit = 1; omit < (1 << pg_size); omit++)
+            for (let omit = 1; omit < (1 << old_pg_size); omit++)
             {
                 let pg_omit = [ ...pg ];
-                let intersect_count = pg_size;
-                for (let i = 0; i < pg_size; i++)
+                let intersect_count = old_pg_size;
+                for (let i = 0; i < old_pg_size; i++)
                 {
                     if (omit & (1 << i))
                     {
@@ -156,6 +161,8 @@ function calc_intersect_weights(pg_size, pg_count, prev_weights, all_pgs)
                         intersect_count--;
                     }
                 }
+                if (!ordered)
+                    pg_omit = pg_omit.filter(n => n).sort();
                 pg_omit = pg_omit.join(':');
                 intersect[pg_omit] = Math.max(intersect[pg_omit] || 0, intersect_count);
             }
@@ -169,10 +176,10 @@ function calc_intersect_weights(pg_size, pg_count, prev_weights, all_pgs)
                 for (let i = 0; i < pg_size; i++)
                 {
                     if (omit & (1 << i))
-                    {
                         pg_omit[i] = '';
-                    }
                 }
+                if (!ordered)
+                    pg_omit = pg_omit.filter(n => n).sort();
                 pg_omit = pg_omit.join(':');
                 max_int = Math.max(max_int, intersect[pg_omit] || 0);
             }
@@ -181,15 +188,18 @@ function calc_intersect_weights(pg_size, pg_count, prev_weights, all_pgs)
     }
     else
     {
-        const prev_pg_hashed = Object.keys(prev_weights).map(pg_name => pg_name.substr(3).split(/_/).reduce((a, c) => { a[c] = 1; return a; }, {}));
+        const prev_pg_hashed = Object.keys(prev_weights).map(pg_name => pg_name
+            .substr(3).split(/_/).reduce((a, c, i) => { a[c] = i+1; return a; }, {}));
         for (const pg of all_pgs)
         {
             if (!prev_weights['pg_'+pg.join('_')])
             {
                 let max_int = 0;
-                for (const prev_hash in prev_pg_hashed)
+                for (const prev_hash of prev_pg_hashed)
                 {
-                    const intersect_count = pg.reduce((a, osd) => a + (prev_hash[osd] ? 1 : 0), 0);
+                    const intersect_count = ordered
+                        ? pg.reduce((a, osd, i) => a + (prev_hash[osd] == 1+i ? 1 : 0), 0)
+                        : pg.reduce((a, osd, i) => a + (prev_hash[osd] ? 1 : 0), 0);
                     if (max_int < intersect_count)
                     {
                         max_int = intersect_count;
@@ -238,7 +248,7 @@ function add_valid_previous(osd_tree, prev_weights, all_pgs)
 }
 
 // Try to minimize data movement
-async function optimize_change({ prev_pgs: prev_int_pgs, osd_tree, pg_size = 3, pg_minsize = 2, max_combinations = 10000, parity_space = 1 })
+async function optimize_change({ prev_pgs: prev_int_pgs, osd_tree, pg_size = 3, pg_minsize = 2, max_combinations = 10000, parity_space = 1, ordered = false })
 {
     if (!osd_tree)
     {
@@ -261,9 +271,13 @@ async function optimize_change({ prev_pgs: prev_int_pgs, osd_tree, pg_size = 3,
             prev_pg_per_osd[osd].push([ pg_name, (i >= pg_minsize ? parity_space : 1) ]);
         }
     }
+    const old_pg_size = prev_int_pgs[0].length;
     // Get all combinations
     let all_pgs = random_combinations(osd_tree, pg_size, max_combinations, parity_space > 1);
-    add_valid_previous(osd_tree, prev_weights, all_pgs);
+    if (old_pg_size == pg_size)
+    {
+        add_valid_previous(osd_tree, prev_weights, all_pgs);
+    }
     all_pgs = Object.values(all_pgs);
     const pg_per_osd = {};
     for (const pg of all_pgs)
@@ -277,7 +291,7 @@ async function optimize_change({ prev_pgs: prev_int_pgs, osd_tree, pg_size = 3,
         }
     }
     // Penalize PGs based on their similarity to old PGs
-    const move_weights = calc_intersect_weights(pg_size, pg_count, prev_weights, all_pgs);
+    const move_weights = calc_intersect_weights(old_pg_size, pg_size, pg_count, prev_weights, all_pgs, ordered);
     // Calculate total weight - old PG weights
     const all_pg_names = all_pgs.map(pg => 'pg_'+pg.join('_'));
     const all_pgs_hash = all_pg_names.reduce((a, c) => { a[c] = true; return a; }, {});
@@ -288,11 +302,6 @@ async function optimize_change({ prev_pgs: prev_int_pgs, osd_tree, pg_size = 3,
     lp += 'max: '+all_pg_names.map(pg_name => (
         prev_weights[pg_name] ? `${pg_size+1}*add_${pg_name} - ${pg_size+1}*del_${pg_name}` : `${pg_size+1-move_weights[pg_name]}*${pg_name}`
     )).join(' + ')+';\n';
-    lp += all_pg_names
-        .map(pg_name => (prev_weights[pg_name] ? `add_${pg_name} - del_${pg_name}` : `${pg_name}`))
-        .join(' + ')+' = '+(pg_count
-            - Object.keys(prev_weights).reduce((a, old_pg_name) => (a + (all_pgs_hash[old_pg_name] ? prev_weights[old_pg_name] : 0)), 0)
-        )+';\n';
     for (const osd in pg_per_osd)
     {
         if (osd !== NO_OSD)
@@ -373,11 +382,35 @@ async function optimize_change({ prev_pgs: prev_int_pgs, osd_tree, pg_size = 3,
         {
             differs++;
         }
-        for (let j = 0; j < pg_size; j++)
+    }
+    if (ordered)
+    {
+        for (let i = 0; i < pg_count; i++)
         {
-            if (new_pgs[i][j] != prev_int_pgs[i][j])
+            for (let j = 0; j < pg_size; j++)
             {
-                osd_differs++;
+                if (new_pgs[i][j] != prev_int_pgs[i][j])
+                {
+                    osd_differs++;
+                }
+            }
+        }
+    }
+    else
+    {
+        for (let i = 0; i < pg_count; i++)
+        {
+            const old_map = prev_int_pgs[i].reduce((a, c) => { a[c] = (a[c]|0) + 1; return a; }, {});
+            for (let j = 0; j < pg_size; j++)
+            {
+                if ((0|old_map[new_pgs[i][j]]) > 0)
+                {
+                    old_map[new_pgs[i][j]]--;
+                }
+                else
+                {
+                    osd_differs++;
+                }
             }
         }
     }

mon/make-osd-hybrid.js

@@ -0,0 +1,414 @@
+#!/usr/bin/nodejs
+// systemd unit generator for hybrid (HDD+SSD) vitastor OSDs
+// Copyright (c) Vitaliy Filippov, 2019+
+// License: VNPL-1.1
+
+// USAGE: nodejs make-osd-hybrid.js [--disable_ssd_cache 0] [--disable_hdd_cache 0] /dev/sda /dev/sdb /dev/sdc /dev/sdd ...
+// I.e. - just pass all HDDs and SSDs mixed, the script will decide where
+// to put journals on its own
+
+const fs = require('fs');
+const fsp = fs.promises;
+const child_process = require('child_process');
+
+const options = {
+    debug: 1,
+    journal_size: 1024*1024*1024,
+    min_meta_size: 1024*1024*1024,
+    object_size: 1024*1024,
+    bitmap_granularity: 4096,
+    device_block_size: 4096,
+    disable_ssd_cache: 1,
+    disable_hdd_cache: 1,
+};
+
+run().catch(console.fatal);
+
+async function run()
+{
+    const device_list = parse_options();
+    await system_or_die("mkdir -p /var/log/vitastor; chown vitastor /var/log/vitastor");
+    // Collect devices
+    const all_devices = await collect_devices(device_list);
+    const ssds = all_devices.filter(d => d.ssd);
+    const hdds = all_devices.filter(d => !d.ssd);
+    // Collect existing OSD units
+    const osd_units = await collect_osd_units();
+    // Count assigned HDD journals and unallocated space for each SSD
+    await check_journal_count(ssds, osd_units);
+    // Create new OSDs
+    await create_new_hybrid_osds(hdds, ssds, osd_units);
+    process.exit(0);
+}
+
+function parse_options()
+{
+    const devices = [];
+    const opt = {};
+    for (let i = 2; i < process.argv.length; i++)
+    {
+        const arg = process.argv[i];
+        if (arg == '--help' || arg == '-h')
+        {
+            opt.help = true;
+            break;
+        }
+        else if (arg.substr(0, 2) == '--')
+            opt[arg.substr(2)] = process.argv[++i];
+        else
+            devices.push(arg);
+    }
+    if (opt.help || !devices.length)
+    {
+        console.log(
+            'Prepare hybrid (HDD+SSD) Vitastor OSDs\n'+
+            '(c) Vitaliy Filippov, 2019+, license: VNPL-1.1\n\n'+
+            'USAGE: nodejs make-osd-hybrid.js [OPTIONS] /dev/sda /dev/sdb /dev/sdc ...\n'+
+            'Just pass all your SSDs and HDDs in any order, the script will distribute OSDs for you.\n\n'+
+            'OPTIONS (with defaults):\n'+
+            Object.keys(options).map(k => `  --${k} ${options[k]}`).join('\n')
+        );
+        process.exit(0);
+    }
+    for (const k in opt)
+        options[k] = opt[k];
+    return devices;
+}
+
+// Collect devices
+async function collect_devices(devices_to_check)
+{
+    const devices = [];
+    for (const dev of devices_to_check)
+    {
+        if (dev.substr(0, 5) != '/dev/')
+        {
+            console.log(`${dev} does not start with /dev/, skipping`);
+            continue;
+        }
+        if (!await file_exists('/sys/block/'+dev.substr(5)))
+        {
+            console.log(`${dev} is a partition, skipping`);
+            continue;
+        }
+        // Check if the device is an SSD
+        const rot = '/sys/block/'+dev.substr(5)+'/queue/rotational';
+        if (!await file_exists(rot))
+        {
+            console.log(`${dev} does not have ${rot} to check whether it's an SSD, skipping`);
+            continue;
+        }
+        const ssd = !parseInt(await fsp.readFile(rot, { encoding: 'utf-8' }));
+        // Check if the device has partition table
+        let [ has_partition_table, parts ] = await system(`sfdisk --dump ${dev} --json`);
+        if (has_partition_table != 0)
+        {
+            // Check if the device has any data
+            const [ has_data, out ] = await system(`blkid ${dev}`);
+            if (has_data == 0)
+            {
+                console.log(`${dev} contains data, skipping:\n  ${out.trim().replace(/\n/g, '\n  ')}`);
+                continue;
+            }
+        }
+        parts = parts ? JSON.parse(parts).partitiontable : null;
+        if (parts && parts.label != 'gpt')
+        {
+            console.log(`${dev} contains "${parts.label}" partition table, only GPT is supported, skipping`);
+            continue;
+        }
+        devices.push({
+            path: dev,
+            ssd,
+            parts,
+        });
+    }
+    return devices;
+}
+
+// Collect existing OSD units
+async function collect_osd_units()
+{
+    const units = [];
+    for (const unit of (await system("ls /etc/systemd/system/vitastor-osd*.service"))[1].trim().split('\n'))
+    {
+        if (!unit)
+        {
+            continue;
+        }
+        let cmd = /^ExecStart\s*=\s*(([^\n]*\\\n)*[^\n]*)/.exec(await fsp.readFile(unit, { encoding: 'utf-8' }));
+        if (!cmd)
+        {
+            console.log('ExecStart= not found in '+unit+', skipping')
+            continue;
+        }
+        let kv = {}, key;
+        cmd = cmd[1].replace(/^bash\s+-c\s+'/, '')
+            .replace(/>>\s*\S+2>\s*&1\s*'$/, '')
+            .replace(/\s*\\\n\s*/g, ' ')
+            .replace(/([^\s']+)|'([^']+)'/g, (m, m1, m2) =>
+            {
+                m1 = m1||m2;
+                if (key == null)
+                {
+                    if (m1.substr(0, 2) != '--')
+                    {
+                        console.log('Strange command line in '+unit+', stopping');
+                        process.exit(1);
+                    }
+                    key = m1.substr(2);
+                }
+                else
+                {
+                    kv[key] = m1;
+                    key = null;
+                }
+            });
+        units.push(kv);
+    }
+    return units;
+}
+
+// Count assigned HDD journals and unallocated space for each SSD
+async function check_journal_count(ssds, osd_units)
+{
+    const units_by_journal = osd_units.reduce((a, c) =>
+    {
+        if (c.journal_device)
+            a[c.journal_device] = c;
+        return a;
+    }, {});
+    for (const dev of ssds)
+    {
+        dev.journals = 0;
+        if (dev.parts)
+        {
+            for (const part of dev.parts.partitions)
+            {
+                if (part.uuid && units_by_journal['/dev/disk/by-partuuid/'+part.uuid.toLowerCase()])
+                {
+                    dev.journals++;
+                }
+            }
+            dev.free = free_from_parttable(dev.parts);
+        }
+        else
+        {
+            dev.free = parseInt(await system_or_die("blockdev --getsize64 "+dev.path));
+        }
+    }
+}
+
+async function create_new_hybrid_osds(hdds, ssds, osd_units)
+{
+    const units_by_disk = osd_units.reduce((a, c) => { a[c.data_device] = c; return a; }, {});
+    for (const dev of hdds)
+    {
+        if (!dev.parts)
+        {
+            // HDD is not partitioned yet, create a single partition
+            // + is the "default value" for sfdisk
+            await system_or_die('sfdisk '+dev.path, 'label: gpt\n\n+ +\n');
+            dev.parts = JSON.parse(await system_or_die('sfdisk --dump '+dev.path+' --json')).partitiontable;
+        }
+        if (dev.parts.partitions.length != 1)
+        {
+            console.log(dev.path+' has more than 1 partition, skipping');
+        }
+        else if ((dev.parts.partitions[0].start + dev.parts.partitions[0].size) != (1 + dev.parts.lastlba))
+        {
+            console.log(dev.path+'1 is not a whole-disk partition, skipping');
+        }
+        else if (!dev.parts.partitions[0].uuid)
+        {
+            console.log(dev.parts.partitions[0].node+' does not have UUID. Please repartition '+dev.path+' with GPT');
+        }
+        else if (!units_by_disk['/dev/disk/by-partuuid/'+dev.parts.partitions[0].uuid.toLowerCase()])
+        {
+            await create_hybrid_osd(dev, ssds);
+        }
+    }
+}
+
+async function create_hybrid_osd(dev, ssds)
+{
+    // Create a new OSD
+    // Calculate metadata size
+    const data_device = '/dev/disk/by-partuuid/'+dev.parts.partitions[0].uuid.toLowerCase();
+    const data_size = dev.parts.partitions[0].size * dev.parts.sectorsize;
+    const meta_entry_size = 24 + 2*options.object_size/options.bitmap_granularity/8;
+    const entries_per_block = Math.floor(options.device_block_size / meta_entry_size);
+    const object_count = Math.floor(data_size / options.object_size);
+    let meta_size = Math.ceil(1 + object_count / entries_per_block) * options.device_block_size;
+    // Leave some extra space for future metadata formats and round metadata area size to multiples of 1 MB
+    meta_size = 2*meta_size;
+    meta_size = Math.ceil(meta_size/1024/1024) * 1024*1024;
+    if (meta_size < options.min_meta_size)
+        meta_size = options.min_meta_size;
+    let journal_size = Math.ceil(options.journal_size/1024/1024) * 1024*1024;
+    // Pick an SSD for journal, balancing the number of journals across SSDs
+    let selected_ssd;
+    for (const ssd of ssds)
+        if (ssd.free >= (meta_size+journal_size) && (!selected_ssd || selected_ssd.journals > ssd.journals))
+            selected_ssd = ssd;
+    if (!selected_ssd)
+    {
+        console.error('Could not find free space for SSD journal and metadata for '+dev.path);
+        process.exit(1);
+    }
+    // Allocate an OSD number
+    const osd_num = (await system_or_die("vitastor-cli alloc-osd")).trim();
+    if (!osd_num)
+    {
+        console.error('Failed to run vitastor-cli alloc-osd');
+        process.exit(1);
+    }
+    console.log('Creating OSD '+osd_num+' on '+dev.path+' (HDD) with journal and metadata on '+selected_ssd.path+' (SSD)');
+    // Add two partitions: journal and metadata
+    const new_parts = await add_partitions(selected_ssd, [ journal_size, meta_size ]);
+    selected_ssd.journals++;
+    const journal_device = '/dev/disk/by-partuuid/'+new_parts[0].uuid.toLowerCase();
+    const meta_device = '/dev/disk/by-partuuid/'+new_parts[1].uuid.toLowerCase();
+    // Wait until the device symlinks appear
+    while (!await file_exists(journal_device))
+    {
+        await new Promise(ok => setTimeout(ok, 100));
+    }
+    while (!await file_exists(meta_device))
+    {
+        await new Promise(ok => setTimeout(ok, 100));
+    }
+    // Zero out metadata and journal
+    await system_or_die("dd if=/dev/zero of="+journal_device+" bs=1M count="+(journal_size/1024/1024)+" oflag=direct");
+    await system_or_die("dd if=/dev/zero of="+meta_device+" bs=1M count="+(meta_size/1024/1024)+" oflag=direct");
+    // Create unit file for the OSD
+    const has_scsi_cache_type = options.disable_ssd_cache &&
+        (await system("ls /sys/block/"+selected_ssd.path.substr(5)+"/device/scsi_disk/*/cache_type"))[0] == 0;
+    const write_through = options.disable_ssd_cache && (
+        has_scsi_cache_type || selected_ssd.path.substr(5, 4) == 'nvme'
+        && (await system_or_die("/sys/block/"+selected_ssd.path.substr(5)+"/queue/write_cache")).trim() == "write through");
+    await fsp.writeFile('/etc/systemd/system/vitastor-osd'+osd_num+'.service',
+`[Unit]
+Description=Vitastor object storage daemon osd.${osd_num}
+After=network-online.target local-fs.target time-sync.target
+Wants=network-online.target local-fs.target time-sync.target
+PartOf=vitastor.target
+
+[Service]
+LimitNOFILE=1048576
+LimitNPROC=1048576
+LimitMEMLOCK=infinity
+ExecStart=bash -c '/usr/bin/vitastor-osd \\
+    --osd_num ${osd_num} ${write_through
+        ? "--disable_meta_fsync 1 --disable_journal_fsync 1 --immediate_commit "+(options.disable_hdd_cache ? "all" : "small")
+        : ""} \\
+    --throttle_small_writes 1 \\
+    --disk_alignment ${options.device_block_size} \\
+    --journal_block_size ${options.device_block_size} \\
+    --meta_block_size ${options.device_block_size} \\
+    --journal_no_same_sector_overwrites true \\
+    --journal_sector_buffer_count 1024 \\
+    --block_size ${options.object_size} \\
+    --data_device ${data_device} \\
+    --journal_device ${journal_device} \\
+    --meta_device ${meta_device} >>/var/log/vitastor/osd${osd_num}.log 2>&1'
+WorkingDirectory=/
+ExecStartPre=+chown vitastor:vitastor ${data_device}
+ExecStartPre=+chown vitastor:vitastor ${journal_device}
+ExecStartPre=+chown vitastor:vitastor ${meta_device}${
+    has_scsi_cache_type
+    ? "\nExecStartPre=+bash -c 'D=$$$(readlink "+journal_device+"); echo write through > $$$(dirname /sys/block/*/$$\${D##*/})/device/scsi_disk/*/cache_type'"
+    : ""}${
+    options.disable_hdd_cache
+    ? "\nExecStartPre=+bash -c 'D=$$$(readlink "+data_device+"); echo write through > $$$(dirname /sys/block/*/$$\${D##*/})/device/scsi_disk/*/cache_type'"
+    : ""}
+User=vitastor
+PrivateTmp=false
+TasksMax=infinity
+Restart=always
+StartLimitInterval=0
+RestartSec=10
+
+[Install]
+WantedBy=vitastor.target
+`);
+    await system_or_die("systemctl enable vitastor-osd"+osd_num);
+}
+
+async function add_partitions(dev, sizes)
+{
+    let script = 'label: gpt\n\n';
+    if (dev.parts)
+    {
+        // Old partitions
+        for (const part of dev.parts.partitions)
+        {
+            script += part.node+': '+Object.keys(part).map(k => k == 'node' ? '' : k+'='+part[k]).filter(k => k).join(', ')+'\n';
+        }
+    }
+    // New partitions
+    for (const size of sizes)
+    {
+        script += '+ '+Math.ceil(size/1024)+'KiB\n';
+    }
+    await system_or_die('sfdisk '+dev.path, script);
+    // Get new partition table and find the new partition
+    const newpt = JSON.parse(await system_or_die('sfdisk --dump '+dev.path+' --json')).partitiontable;
+    const old_nodes = dev.parts ? dev.parts.partitions.reduce((a, c) => { a[c.uuid] = true; return a; }, {}) : {};
+    const new_nodes = newpt.partitions.filter(part => !old_nodes[part.uuid]);
+    if (new_nodes.length != sizes.length)
+    {
+        console.error('Failed to partition '+dev.path+': new partitions not found in table');
+        process.exit(1);
+    }
+    dev.parts = newpt;
+    dev.free = free_from_parttable(newpt);
+    return new_nodes;
+}
+
+function free_from_parttable(pt)
+{
+    let free = pt.lastlba + 1 - pt.firstlba;
+    for (const part of pt.partitions)
+    {
+        free -= part.size;
+    }
+    free *= pt.sectorsize;
+    return free;
+}
+
+async function system_or_die(cmd, input = '')
+{
+    let [ exitcode, stdout, stderr ] = await system(cmd, input);
+    if (exitcode != 0)
+    {
+        console.error(cmd+' failed: '+stderr);
+        process.exit(1);
+    }
+    return stdout;
+}
+
+async function system(cmd, input = '')
+{
+    if (options.debug)
+    {
+        process.stderr.write('+ '+cmd+(input ? " <<EOF\n"+input.replace(/\s*$/, '\n')+"EOF" : '')+'\n');
+    }
+    const cp = child_process.spawn(cmd, { shell: true });
+    let stdout = '', stderr = '', finish_cb;
+    cp.stdout.on('data', buf => stdout += buf.toString());
+    cp.stderr.on('data', buf => stderr += buf.toString());
+    cp.on('exit', () => finish_cb && finish_cb());
+    cp.stdin.write(input);
+    cp.stdin.end();
+    if (cp.exitCode == null)
+    {
+        await new Promise(ok => finish_cb = ok);
+    }
+    return [ cp.exitCode, stdout, stderr ];
+}
+
+async function file_exists(filename)
+{
+    return new Promise((ok, no) => fs.access(filename, fs.constants.R_OK, err => ok(!err)));
+}

mon/make-osd.sh

@@ -4,38 +4,31 @@
 # Copyright (c) Vitaliy Filippov, 2019+
 # License: MIT
 
-# USAGE: ./make-osd.sh /dev/disk/by-partuuid/xxx [ /dev/disk/by-partuuid/yyy]...
-
-IP_SUBSTR="10.200.1."
-ETCD_HOSTS="etcd0=http://10.200.1.10:2380,etcd1=http://10.200.1.11:2380,etcd2=http://10.200.1.12:2380"
+# USAGE:
+# 1) Put etcd_address and osd_network into /etc/vitastor/vitastor.conf. Example:
+#    {
+#        "etcd_address":["http://10.200.1.10:2379/v3","http://10.200.1.11:2379/v3","http://10.200.1.12:2379/v3"],
+#        "osd_network":"10.200.1.0/24"
+#    }
+# 2) Run ./make-osd.sh /dev/disk/by-partuuid/xxx [ /dev/disk/by-partuuid/yyy]...
 
 set -e -x
 
-IP=`ip -json a s | jq -r '.[].addr_info[] | select(.local | startswith("'$IP_SUBSTR'")) | .local'`
-[ "$IP" != "" ] || exit 1
-ETCD_MON=$(echo $ETCD_HOSTS | perl -pe 's/:2380/:2379/g; s/etcd\d*=//g;')
-D=`dirname $0`
-
 # Create OSDs on all passed devices
-OSD_NUM=1
 for DEV in $*; do
 
-# Ugly :) -> node.js rework pending
-while true; do
-    ST=$(etcdctl --endpoints="$ETCD_MON" get --print-value-only /vitastor/osd/stats/$OSD_NUM)
-    if [ "$ST" = "" ]; then
-        break
-    fi
-    OSD_NUM=$((OSD_NUM+1))
-done
-etcdctl --endpoints="$ETCD_MON" put /vitastor/osd/stats/$OSD_NUM '{}'
+OSD_NUM=$(vitastor-cli alloc-osd)
 
 echo Creating OSD $OSD_NUM on $DEV
 
-OPT=`node $D/simple-offsets.js --device $DEV --format options | tr '\n' ' '`
-META=`echo $OPT | grep -Po '(?<=data_offset )\d+'`
+OPT=$(vitastor-cli simple-offsets --format options $DEV | tr '\n' ' ')
+META=$(vitastor-cli simple-offsets --format json $DEV | jq .data_offset)
 dd if=/dev/zero of=$DEV bs=1048576 count=$(((META+1048575)/1048576)) oflag=direct
 
+mkdir -p /var/log/vitastor
+id vitastor &>/dev/null || useradd vitastor
+chown vitastor /var/log/vitastor
+
 cat >/etc/systemd/system/vitastor-osd$OSD_NUM.service <<EOF
 [Unit]
 Description=Vitastor object storage daemon osd.$OSD_NUM
@@ -47,16 +40,14 @@ PartOf=vitastor.target
 LimitNOFILE=1048576
 LimitNPROC=1048576
 LimitMEMLOCK=infinity
-ExecStart=/usr/bin/vitastor-osd \\
-    --etcd_address $IP:2379/v3 \\
-    --bind_address $IP \\
+ExecStart=bash -c '/usr/bin/vitastor-osd \\
     --osd_num $OSD_NUM \\
     --disable_data_fsync 1 \\
     --immediate_commit all \\
     --disk_alignment 4096 --journal_block_size 4096 --meta_block_size 4096 \\
     --journal_no_same_sector_overwrites true \\
     --journal_sector_buffer_count 1024 \\
-    $OPT
+    $OPT >>/var/log/vitastor/osd$OSD_NUM.log 2>&1'
 WorkingDirectory=/
 ExecStartPre=+chown vitastor:vitastor $DEV
 User=vitastor

mon/mon-main.js

@@ -9,17 +9,18 @@ const options = {};
 
 for (let i = 2; i < process.argv.length; i++)
 {
-    if (process.argv[i].substr(0, 2) == '--')
+    if (process.argv[i] === '-h' || process.argv[i] === '--help')
+    {
+        console.error('USAGE: '+process.argv[0]+' '+process.argv[1]+' [--verbose 1]'+
+            ' [--etcd_address "http://127.0.0.1:2379,..."] [--config_file /etc/vitastor/vitastor.conf]'+
+            ' [--etcd_prefix "/vitastor"] [--etcd_start_timeout 5]');
+        process.exit();
+    }
+    else if (process.argv[i].substr(0, 2) == '--')
     {
         options[process.argv[i].substr(2)] = process.argv[i+1];
         i++;
     }
 }
 
-if (!options.etcd_url)
-{
-    console.error('USAGE: '+process.argv[0]+' '+process.argv[1]+' --etcd_url "http://127.0.0.1:2379,..." --etcd_prefix "/vitastor" --etcd_start_timeout 5 [--verbose 1]');
-    process.exit();
-}
-
-new Mon(options).start().catch(e => { console.error(e); process.exit(); });
+new Mon(options).start().catch(e => { console.error(e); process.exit(1); });

mon/mon.js

@@ -1,6 +1,7 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 (see README.md for details)
 
+const fs = require('fs');
 const http = require('http');
 const crypto = require('crypto');
 const os = require('os');
@@ -30,6 +31,7 @@ const etcd_allow = new RegExp('^'+[
     'osd/inodestats/[1-9]\\d*',
     'osd/space/[1-9]\\d*',
     'mon/master',
+    'mon/member/[a-f0-9]+',
     'pg/state/[1-9]\\d*/[1-9]\\d*',
     'pg/stats/[1-9]\\d*/[1-9]\\d*',
     'pg/history/[1-9]\\d*/[1-9]\\d*',
@@ -82,9 +84,15 @@ const etcd_tree = {
             osd_idle_timeout: 5, // seconds. min: 1
             osd_ping_timeout: 5, // seconds. min: 1
             up_wait_retry_interval: 500, // ms. min: 50
+            max_etcd_attempts: 5,
+            etcd_quick_timeout: 1000, // ms
+            etcd_slow_timeout: 5000, // ms
+            etcd_keepalive_timeout: 30, // seconds, default is max(30, etcd_report_interval*2)
+            etcd_ws_keepalive_interval: 30, // seconds
             // osd
-            etcd_report_interval: 5,
+            etcd_report_interval: 5, // seconds
             run_primary: true,
+            osd_network: null, // "192.168.7.0/24" or an array of masks
             bind_address: "0.0.0.0",
             bind_port: 0,
             autosync_interval: 5,
@@ -97,6 +105,7 @@ const etcd_tree = {
             no_rebalance: false,
             print_stats_interval: 3,
             slow_log_interval: 10,
+            osd_memlock: false,
             // blockstore - fixed in superblock
             block_size,
             disk_alignment,
@@ -123,6 +132,11 @@ const etcd_tree = {
             inmemory_journal,
             journal_sector_buffer_count,
             journal_no_same_sector_overwrites,
+            throttle_small_writes: false,
+            throttle_target_iops: 100,
+            throttle_target_mbs: 100,
+            throttle_target_parallelism: 1,
+            throttle_threshold_us: 50,
         }, */
         global: {},
         /* node_placement: {
@@ -146,6 +160,8 @@ const etcd_tree = {
                 root_node?: 'rack1',
                 // restrict pool to OSDs having all of these tags
                 osd_tags?: 'nvme' | [ 'nvme', ... ],
+                // prefer to put primary on OSD with these tags
+                primary_affinity_tags?: 'nvme' | [ 'nvme', ... ],
             },
             ...
         }, */
@@ -210,21 +226,28 @@ const etcd_tree = {
             }, */
         },
         inodestats: {
-            /* <inode_t>: {
-                read: { count: uint64_t, usec: uint64_t, bytes: uint64_t },
-                write: { count: uint64_t, usec: uint64_t, bytes: uint64_t },
-                delete: { count: uint64_t, usec: uint64_t, bytes: uint64_t },
+            /* <pool_id>: {
+                <inode_t>: {
+                    read: { count: uint64_t, usec: uint64_t, bytes: uint64_t },
+                    write: { count: uint64_t, usec: uint64_t, bytes: uint64_t },
+                    delete: { count: uint64_t, usec: uint64_t, bytes: uint64_t },
+                },
             }, */
         },
         space: {
             /* <osd_num_t>: {
-                <inode_t>: uint64_t, // bytes
+                <pool_id>: {
+                    <inode_t>: uint64_t, // bytes
+                },
             }, */
         },
     },
     mon: {
         master: {
-            /* ip: [ string ], */
+            /* ip: [ string ], id: uint64_t */
+        },
+        standby: {
+            /* <uint64_t>: { ip: [ string ] }, */
         },
     },
     pg: {
@@ -255,7 +278,7 @@ const etcd_tree = {
                 <pg_id>: {
                     osd_sets: osd_num_t[][],
                     all_peers: osd_num_t[],
-                    epoch: uint32_t,
+                    epoch: uint64_t,
                 },
             }, */
         },
@@ -322,24 +345,56 @@ class Mon
 {
     constructor(config)
     {
-        // FIXME: Maybe prefer local etcd
-        this.etcd_urls = [];
-        for (let url of config.etcd_url.split(/,/))
+        this.die = (e) => this._die(e);
+        if (fs.existsSync(config.config_path||'/etc/vitastor/vitastor.conf'))
         {
-            let scheme = 'http';
-            url = url.trim().replace(/^(https?):\/\//, (m, m1) => { scheme = m1; return ''; });
-            if (!/\/[^\/]/.exec(url))
-                url += '/v3';
-            this.etcd_urls.push(scheme+'://'+url);
+            config = {
+                ...JSON.parse(fs.readFileSync(config.config_path||'/etc/vitastor/vitastor.conf', { encoding: 'utf-8' })),
+                ...config,
+            };
         }
+        this.parse_etcd_addresses(config.etcd_address||config.etcd_url);
         this.verbose = config.verbose || 0;
+        this.initConfig = config;
         this.config = {};
         this.etcd_prefix = config.etcd_prefix || '/vitastor';
         this.etcd_prefix = this.etcd_prefix.replace(/\/\/+/g, '/').replace(/^\/?(.*[^\/])\/?$/, '/$1');
         this.etcd_start_timeout = (config.etcd_start_timeout || 5) * 1000;
         this.state = JSON.parse(JSON.stringify(this.constructor.etcd_tree));
         this.signals_set = false;
-        this.on_stop_cb = () => this.on_stop().catch(console.error);
+        this.ws = null;
+        this.ws_alive = false;
+        this.ws_keepalive_timer = null;
+        this.on_stop_cb = () => this.on_stop(0).catch(console.error);
+    }
+
+    parse_etcd_addresses(addrs)
+    {
+        const is_local_ip = this.local_ips(true).reduce((a, c) => { a[c] = true; return a; }, {});
+        this.etcd_local = [];
+        this.etcd_urls = [];
+        this.selected_etcd_url = null;
+        this.etcd_urls_to_try = [];
+        if (!(addrs instanceof Array))
+            addrs = addrs ? (''+(addrs||'')).split(/,/) : [];
+        if (!addrs.length)
+        {
+            console.error('Vitastor etcd address(es) not specified. Please set on the command line or in the config file');
+            process.exit(1);
+        }
+        for (let url of addrs)
+        {
+            let scheme = 'http';
+            url = url.trim().replace(/^(https?):\/\//, (m, m1) => { scheme = m1; return ''; });
+            const slash = url.indexOf('/');
+            const colon = url.indexOf(':');
+            const is_local = is_local_ip[colon >= 0 ? url.substr(0, colon) : (slash >= 0 ? url.substr(0, slash) : url)];
+            url = scheme+'://'+(slash >= 0 ? url : url+'/v3');
+            if (is_local)
+                this.etcd_local.push(url);
+            else
+                this.etcd_urls.push(url);
+        }
     }
 
     async start()
@@ -352,7 +407,7 @@ class Mon
         for (const pool_id in this.state.config.pools)
         {
             if (!this.state.pool.stats[pool_id] ||
-                !this.state.pool.stats[pool_id].pg_real_size)
+                !Number(this.state.pool.stats[pool_id].pg_real_size))
             {
                 // Generate missing data in etcd
                 this.state.config.pgs.hash = null;
@@ -410,6 +465,43 @@ class Mon
         }
     }
 
+    pick_next_etcd()
+    {
+        if (this.selected_etcd_url)
+            return this.selected_etcd_url;
+        if (!this.etcd_urls_to_try || !this.etcd_urls_to_try.length)
+        {
+            this.etcd_urls_to_try = [ ...this.etcd_local ];
+            const others = [ ...this.etcd_urls ];
+            while (others.length)
+            {
+                const url = others.splice(0|(others.length*Math.random()), 1);
+                this.etcd_urls_to_try.push(url[0]);
+            }
+        }
+        this.selected_etcd_url = this.etcd_urls_to_try.shift();
+        return this.selected_etcd_url;
+    }
+
+    restart_watcher(cur_addr)
+    {
+        if (this.ws)
+        {
+            this.ws.close();
+            this.ws = null;
+        }
+        if (this.ws_keepalive_timer)
+        {
+            clearInterval(this.ws_keepalive_timer);
+            this.ws_keepalive_timer = null;
+        }
+        if (this.selected_etcd_url == cur_addr)
+        {
+            this.selected_etcd_url = null;
+        }
+        this.start_watcher(this.config.etcd_mon_retries).catch(this.die);
+    }
+
     async start_watcher(retries)
     {
         let retry = 0;
@@ -419,12 +511,14 @@ class Mon
         }
         while (retries < 0 || retry < retries)
         {
-            const base = 'ws'+this.etcd_urls[Math.floor(Math.random()*this.etcd_urls.length)].substr(4);
+            const cur_addr = this.pick_next_etcd();
+            const base = 'ws'+cur_addr.substr(4);
             const ok = await new Promise((ok, no) =>
             {
                 const timer_id = setTimeout(() =>
                 {
                     this.ws.close();
+                    this.ws = null;
                     ok(false);
                 }, this.config.etcd_mon_timeout);
                 this.ws = new WebSocket(base+'/watch');
@@ -442,9 +536,9 @@ class Mon
                 });
             });
             if (ok)
-            {
                 break;
-            }
+            if (this.selected_etcd_url == cur_addr)
+                this.selected_etcd_url = null;
             this.ws = null;
             retry++;
         }
@@ -452,6 +546,22 @@ class Mon
         {
             this.die('Failed to open etcd watch websocket');
         }
+        const cur_addr = this.selected_etcd_url;
+        this.ws_alive = true;
+        this.ws_keepalive_timer = setInterval(() =>
+        {
+            if (this.ws_alive)
+            {
+                this.ws_alive = false;
+                this.ws.send(JSON.stringify({ progress_request: {} }));
+            }
+            else
+            {
+                console.log('etcd websocket timed out, restarting it');
+                this.restart_watcher(cur_addr);
+            }
+        }, (Number(this.config.etcd_keepalive_interval) || 30)*1000);
+        this.ws.on('error', () => this.restart_watcher(cur_addr));
         this.ws.send(JSON.stringify({
             create_request: {
                 key: b64(this.etcd_prefix+'/'),
@@ -463,6 +573,7 @@ class Mon
         }));
         this.ws.on('message', (msg) =>
         {
+            this.ws_alive = true;
             let data;
             try
             {
@@ -471,12 +582,25 @@ class Mon
             catch (e)
             {
             }
-            if (!data || !data.result || !data.result.events)
+            if (!data || !data.result)
             {
-                if (!data || !data.result || !data.result.watch_id)
+                console.error('Unknown message received from watch websocket: '+msg);
+            }
+            else if (data.result.canceled)
+            {
+                // etcd watch canceled
+                if (data.result.compact_revision)
                 {
-                    console.error('Garbage received from watch websocket: '+msg);
+                    // we may miss events if we proceed
+                    console.error('Revisions before '+data.result.compact_revision+' were compacted by etcd, exiting');
+                    this.on_stop(1);
                 }
+                console.error('Watch canceled by etcd, reason: '+data.result.cancel_reason+', exiting');
+                this.on_stop(1);
+            }
+            else if (data.result.created)
+            {
+                // etcd watch created
             }
             else
             {
@@ -486,7 +610,7 @@ class Mon
                     console.log('Revision '+data.result.header.revision+' events: ');
                 }
                 this.etcd_watch_revision = BigInt(data.result.header.revision)+BigInt(1);
-                for (const e of data.result.events)
+                for (const e of data.result.events||[])
                 {
                     this.parse_kv(e.kv);
                     const key = e.kv.key.substr(this.etcd_prefix.length);
@@ -509,7 +633,7 @@ class Mon
                 }
                 if (pg_states_changed)
                 {
-                    this.save_last_clean().catch(console.error);
+                    this.save_last_clean().catch(this.die);
                 }
                 if (stats_changed)
                 {
@@ -559,11 +683,25 @@ class Mon
         }, this.etcd_start_timeout, 0);
     }
 
+    get_mon_state()
+    {
+        return { ip: this.local_ips(), hostname: os.hostname() };
+    }
+
     async get_lease()
     {
         const max_ttl = this.config.etcd_mon_ttl + this.config.etcd_mon_timeout/1000*this.config.etcd_mon_retries;
-        const res = await this.etcd_call('/lease/grant', { TTL: max_ttl }, this.config.etcd_mon_timeout, -1);
+        // Get lease
+        let res = await this.etcd_call('/lease/grant', { TTL: max_ttl }, this.config.etcd_mon_timeout, -1);
         this.etcd_lease_id = res.ID;
+        // Register in /mon/member, just for the information
+        const state = this.get_mon_state();
+        res = await this.etcd_call('/kv/put', {
+            key: b64(this.etcd_prefix+'/mon/member/'+this.etcd_lease_id),
+            value: b64(JSON.stringify(state)),
+            lease: ''+this.etcd_lease_id
+        }, this.etcd_start_timeout, 0);
+        // Set refresh timer
         this.lease_timer = setInterval(async () =>
         {
             const res = await this.etcd_call('/lease/keepalive', { ID: this.etcd_lease_id }, this.config.etcd_mon_timeout, this.config.etcd_mon_retries);
@@ -580,16 +718,16 @@ class Mon
         }
     }
 
-    async on_stop()
+    async on_stop(status)
     {
         clearInterval(this.lease_timer);
         await this.etcd_call('/lease/revoke', { ID: this.etcd_lease_id }, this.config.etcd_mon_timeout, this.config.etcd_mon_retries);
-        process.exit(0);
+        process.exit(status);
     }
 
     async become_master()
     {
-        const state = { ip: this.local_ips() };
+        const state = { ...this.get_mon_state(), id: ''+this.etcd_lease_id };
         while (1)
         {
             const res = await this.etcd_call('/kv/txn', {
@@ -637,10 +775,13 @@ class Mon
         for (const node_id in this.state.config.node_placement||{})
         {
             const node_cfg = this.state.config.node_placement[node_id];
-            if (!node_id || /^\d/.exec(node_id) ||
-                !node_cfg.level || !levels[node_cfg.level])
+            if (/^\d+$/.exec(node_id))
             {
-                // All nodes must have non-empty non-numeric IDs and valid levels
+                node_cfg.level = 'osd';
+            }
+            if (!node_id || !node_cfg.level || !levels[node_cfg.level])
+            {
+                // All nodes must have non-empty IDs and valid levels
                 continue;
             }
             tree[node_id] = { id: node_id, level: node_cfg.level, parent: node_cfg.parent, children: [] };
@@ -673,10 +814,10 @@ class Mon
                         .reduce((a, c) => { a[c] = true; return a; }, {});
                 }
                 delete tree[osd_num].children;
-                if (!tree[tree[osd_num].parent])
+                if (!tree[stat.host])
                 {
-                    tree[tree[osd_num].parent] = {
-                        id: tree[osd_num].parent,
+                    tree[stat.host] = {
+                        id: stat.host,
                         level: 'host',
                         parent: null,
                         children: [],
@@ -764,27 +905,39 @@ class Mon
         return this.seed + 2147483648;
     }
 
-    pick_primary(pool_id, osd_set, up_osds)
+    pick_primary(pool_id, osd_set, up_osds, aff_osds)
     {
         let alive_set;
         if (this.state.config.pools[pool_id].scheme === 'replicated')
-            alive_set = osd_set.filter(osd_num => osd_num && up_osds[osd_num]);
+        {
+            // Prefer "affinity" OSDs
+            alive_set = osd_set.filter(osd_num => osd_num && aff_osds[osd_num]);
+            if (!alive_set.length)
+                alive_set = osd_set.filter(osd_num => osd_num && up_osds[osd_num]);
+        }
         else
         {
             // Prefer data OSDs for EC because they can actually read something without an additional network hop
             const pg_data_size = (this.state.config.pools[pool_id].pg_size||0) -
                 (this.state.config.pools[pool_id].parity_chunks||0);
-            alive_set = osd_set.slice(0, pg_data_size).filter(osd_num => osd_num && up_osds[osd_num]);
+            alive_set = osd_set.slice(0, pg_data_size).filter(osd_num => osd_num && aff_osds[osd_num]);
             if (!alive_set.length)
-                alive_set = osd_set.filter(osd_num => osd_num && up_osds[osd_num]);
+                alive_set = osd_set.filter(osd_num => osd_num && aff_osds[osd_num]);
+            if (!alive_set.length)
+            {
+                alive_set = osd_set.slice(0, pg_data_size).filter(osd_num => osd_num && up_osds[osd_num]);
+                if (!alive_set.length)
+                    alive_set = osd_set.filter(osd_num => osd_num && up_osds[osd_num]);
+            }
         }
         if (!alive_set.length)
             return 0;
         return alive_set[this.rng() % alive_set.length];
     }
 
-    save_new_pgs_txn(request, pool_id, up_osds, prev_pgs, new_pgs, pg_history)
+    save_new_pgs_txn(request, pool_id, up_osds, osd_tree, prev_pgs, new_pgs, pg_history)
     {
+        const aff_osds = this.get_affinity_osds(this.state.config.pools[pool_id], up_osds, osd_tree);
         const pg_items = {};
         this.reset_rng();
         new_pgs.map((osd_set, i) =>
@@ -792,7 +945,7 @@ class Mon
             osd_set = osd_set.map(osd_num => osd_num === LPOptimizer.NO_OSD ? 0 : osd_num);
             pg_items[i+1] = {
                 osd_set,
-                primary: this.pick_primary(pool_id, osd_set, up_osds),
+                primary: this.pick_primary(pool_id, osd_set, up_osds, aff_osds),
             };
             if (prev_pgs[i] && prev_pgs[i].join(' ') != osd_set.join(' ') &&
                 prev_pgs[i].filter(osd_num => osd_num).length > 0)
@@ -923,6 +1076,13 @@ class Mon
                 console.log('Pool '+pool_id+' has invalid osd_tags (must be a string or array of strings)');
             return false;
         }
+        if (pool_cfg.primary_affinity_tags && typeof(pool_cfg.primary_affinity_tags) != 'string' &&
+            (!(pool_cfg.primary_affinity_tags instanceof Array) || pool_cfg.primary_affinity_tags.filter(t => typeof t != 'string').length > 0))
+        {
+            if (warn)
+                console.log('Pool '+pool_id+' has invalid primary_affinity_tags (must be a string or array of strings)');
+            return false;
+        }
         return true;
     }
 
@@ -952,6 +1112,17 @@ class Mon
         }
     }
 
+    get_affinity_osds(pool_cfg, up_osds, osd_tree)
+    {
+        let aff_osds = up_osds;
+        if (pool_cfg.primary_affinity_tags)
+        {
+            aff_osds = { ...up_osds };
+            this.filter_osds_by_tags(osd_tree, { x: aff_osds }, pool_cfg.primary_affinity_tags);
+        }
+        return aff_osds;
+    }
+
     async recheck_pgs()
     {
         // Take configuration and state, check it against the stored configuration hash
@@ -982,7 +1153,7 @@ class Mon
                     {
                         prev_pgs[pg-1] = this.state.config.pgs.items[pool_id][pg].osd_set;
                     }
-                    this.save_new_pgs_txn(etcd_request, pool_id, up_osds, prev_pgs, [], []);
+                    this.save_new_pgs_txn(etcd_request, pool_id, up_osds, osd_tree, prev_pgs, [], []);
                 }
             }
             for (const pool_id in this.state.config.pools)
@@ -1022,6 +1193,7 @@ class Mon
                     pg_size: pool_cfg.pg_size,
                     pg_minsize: pool_cfg.pg_minsize,
                     max_combinations: pool_cfg.max_osd_combinations,
+                    ordered: pool_cfg.scheme != 'replicated',
                 };
                 let optimize_result;
                 if (old_pg_count > 0)
@@ -1044,10 +1216,6 @@ class Mon
                         {
                             pg.push(0);
                         }
-                        while (pg.length > pool_cfg.pg_size)
-                        {
-                            pg.pop();
-                        }
                     }
                     if (!this.state.config.pgs.hash)
                     {
@@ -1083,8 +1251,8 @@ class Mon
                 this.state.pool.stats[pool_id] = {
                     used_raw_tb: (this.state.pool.stats[pool_id]||{}).used_raw_tb || 0,
                     total_raw_tb: optimize_result.space,
-                    pg_real_size: pg_effsize,
-                    raw_to_usable: pg_effsize / (pool_cfg.scheme === 'replicated'
+                    pg_real_size: pg_effsize || pool_cfg.pg_size,
+                    raw_to_usable: (pg_effsize || pool_cfg.pg_size) / (pool_cfg.scheme === 'replicated'
                         ? 1 : (pool_cfg.pg_size - (pool_cfg.parity_chunks||0))),
                     space_efficiency: optimize_result.space/(optimize_result.total_space||1),
                 };
@@ -1092,7 +1260,7 @@ class Mon
                     key: b64(this.etcd_prefix+'/pool/stats/'+pool_id),
                     value: b64(JSON.stringify(this.state.pool.stats[pool_id])),
                 } });
-                this.save_new_pgs_txn(etcd_request, pool_id, up_osds, real_prev_pgs, optimize_result.int_pgs, pg_history);
+                this.save_new_pgs_txn(etcd_request, pool_id, up_osds, osd_tree, real_prev_pgs, optimize_result.int_pgs, pg_history);
             }
             this.state.config.pgs.hash = tree_hash;
             await this.save_pg_config(etcd_request);
@@ -1109,13 +1277,14 @@ class Mon
                     continue;
                 }
                 const replicated = pool_cfg.scheme === 'replicated';
+                const aff_osds = this.get_affinity_osds(pool_cfg, up_osds, osd_tree);
                 this.reset_rng();
                 for (let pg_num = 1; pg_num <= pool_cfg.pg_count; pg_num++)
                 {
                     const pg_cfg = this.state.config.pgs.items[pool_id][pg_num];
                     if (pg_cfg)
                     {
-                        const new_primary = this.pick_primary(pool_id, pg_cfg.osd_set, up_osds);
+                        const new_primary = this.pick_primary(pool_id, pg_cfg.osd_set, up_osds, aff_osds);
                         if (pg_cfg.primary != new_primary)
                         {
                             console.log(
@@ -1194,7 +1363,7 @@ class Mon
         this.recheck_timer = setTimeout(() =>
         {
             this.recheck_timer = null;
-            this.recheck_pgs().catch(console.error);
+            this.recheck_pgs().catch(this.die);
         }, this.config.mon_change_timeout || 1000);
     }
 
@@ -1231,21 +1400,30 @@ class Mon
         const tm = prev_stats ? BigInt(timestamp - prev_stats.timestamp) : 0;
         for (const op in op_stats)
         {
-            op_stats[op].bps = prev_stats ? (op_stats[op].bytes - prev_stats.op_stats[op].bytes) * 1000n / tm : 0;
-            op_stats[op].iops = prev_stats ? (op_stats[op].count - prev_stats.op_stats[op].count) * 1000n / tm : 0;
-            op_stats[op].lat = prev_stats ? (op_stats[op].usec - prev_stats.op_stats[op].usec)
-                / ((op_stats[op].count - prev_stats.op_stats[op].count) || 1n) : 0;
+            if (prev_stats && prev_stats.op_stats && prev_stats.op_stats[op])
+            {
+                op_stats[op].bps = (op_stats[op].bytes - prev_stats.op_stats[op].bytes) * 1000n / tm;
+                op_stats[op].iops = (op_stats[op].count - prev_stats.op_stats[op].count) * 1000n / tm;
+                op_stats[op].lat = (op_stats[op].usec - prev_stats.op_stats[op].usec)
+                    / ((op_stats[op].count - prev_stats.op_stats[op].count) || 1n);
+            }
         }
         for (const op in subop_stats)
         {
-            subop_stats[op].iops = prev_stats ? (subop_stats[op].count - prev_stats.subop_stats[op].count) * 1000n / tm : 0;
-            subop_stats[op].lat = prev_stats ? (subop_stats[op].usec - prev_stats.subop_stats[op].usec)
-                / ((subop_stats[op].count - prev_stats.subop_stats[op].count) || 1n) : 0;
+            if (prev_stats && prev_stats.subop_stats && prev_stats.subop_stats[op])
+            {
+                subop_stats[op].iops = (subop_stats[op].count - prev_stats.subop_stats[op].count) * 1000n / tm;
+                subop_stats[op].lat = (subop_stats[op].usec - prev_stats.subop_stats[op].usec)
+                    / ((subop_stats[op].count - prev_stats.subop_stats[op].count) || 1n);
+            }
         }
         for (const op in recovery_stats)
         {
-            recovery_stats[op].bps = prev_stats ? (recovery_stats[op].bytes - prev_stats.recovery_stats[op].bytes) * 1000n / tm : 0;
-            recovery_stats[op].iops = prev_stats ? (recovery_stats[op].count - prev_stats.recovery_stats[op].count) * 1000n / tm : 0;
+            if (prev_stats && prev_stats.recovery_stats && prev_stats.recovery_stats[op])
+            {
+                recovery_stats[op].bps = (recovery_stats[op].bytes - prev_stats.recovery_stats[op].bytes) * 1000n / tm;
+                recovery_stats[op].iops = (recovery_stats[op].count - prev_stats.recovery_stats[op].count) * 1000n / tm;
+            }
         }
         return { op_stats, subop_stats, recovery_stats };
     }
@@ -1341,6 +1519,7 @@ class Mon
         {
             for (const inode_num in inode_stats[pool_id])
             {
+                let nonzero = inode_stats[pool_id][inode_num].raw_used > 0;
                 for (const op of [ 'read', 'write', 'delete' ])
                 {
                     const op_st = inode_stats[pool_id][inode_num][op];
@@ -1348,6 +1527,13 @@ class Mon
                     op_st.bps = prev_st ? (op_st.bytes - prev_st.bytes) * 1000n / tm : 0;
                     op_st.iops = prev_st ? (op_st.count - prev_st.count) * 1000n / tm : 0;
                     op_st.lat = prev_st ? (op_st.usec - prev_st.usec) / ((op_st.count - prev_st.count) || 1n) : 0;
+                    if (op_st.bps > 0 || op_st.iops > 0 || op_st.lat > 0)
+                        nonzero = true;
+                }
+                if (!nonzero && (!this.state.config.inode[pool_id] || !this.state.config.inode[pool_id][inode_num]))
+                {
+                    // Deleted inode (no data, no I/O, no config)
+                    delete inode_stats[pool_id][inode_num];
                 }
             }
         }
@@ -1396,6 +1582,18 @@ class Mon
                 } });
             }
         }
+        for (const pool_id in this.state.inode.stats)
+        {
+            for (const inode_num in this.state.inode.stats[pool_id])
+            {
+                if (!inode_stats[pool_id] || !inode_stats[pool_id][inode_num])
+                {
+                    txn.push({ requestDeleteRange: {
+                        key: b64(this.etcd_prefix+'/inode/stats/'+pool_id+'/'+inode_num),
+                    } });
+                }
+            }
+        }
         for (const pool_id in this.state.pool.stats)
         {
             const pool_stats = { ...this.state.pool.stats[pool_id] };
@@ -1461,7 +1659,7 @@ class Mon
         cur[key_parts[key_parts.length-1]] = kv.value;
         if (key === 'config/global')
         {
-            this.config = this.state.config.global;
+            this.config = { ...this.initConfig, ...this.state.config.global };
             this.check_config();
             for (const osd_num in this.state.osd.stats)
             {
@@ -1498,12 +1696,15 @@ class Mon
         }
         while (retries < 0 || retry < retries)
         {
-            const base = this.etcd_urls[Math.floor(Math.random()*this.etcd_urls.length)];
+            retry++;
+            const base = this.pick_next_etcd();
             const res = await POST(base+path, body, timeout);
             if (res.error)
             {
-                console.error('etcd returned error: '+res.error);
-                break;
+                if (this.selected_etcd_url == base)
+                    this.selected_etcd_url = null;
+                console.error('failed to query etcd: '+res.error);
+                continue;
             }
             if (res.json)
             {
@@ -1512,26 +1713,20 @@ class Mon
                     console.error('etcd returned error: '+res.json.error);
                     break;
                 }
-                if (this.etcd_urls.length > 1)
-                {
-                    // Stick to the same etcd for the rest of calls
-                    this.etcd_urls = [ base ];
-                }
                 return res.json;
             }
-            retry++;
         }
         this.die();
     }
 
-    die(err)
+    _die(err)
     {
         // In fact we can just try to rejoin
         console.error(new Error(err || 'Cluster connection failed'));
         process.exit(1);
     }
 
-    local_ips()
+    local_ips(all)
     {
         const ips = [];
         const ifaces = os.networkInterfaces();
@@ -1539,7 +1734,7 @@ class Mon
         {
             for (const iface of ifaces[ifname])
             {
-                if (iface.family == 'IPv4' && !iface.internal)
+                if (iface.family == 'IPv4' && !iface.internal || all)
                 {
                     ips.push(iface.address);
                 }

mon/simple-offsets.js

@@ -49,7 +49,8 @@ async function run()
     }
     options.journal_offset = Math.ceil(options.journal_offset/options.device_block_size)*options.device_block_size;
     const meta_offset = options.journal_offset + Math.ceil(options.journal_size/options.device_block_size)*options.device_block_size;
-    const entries_per_block = Math.floor(options.device_block_size / (24 + 2*options.object_size/options.bitmap_granularity/8));
+    const meta_entry_size = 24 + 2*options.object_size/options.bitmap_granularity/8;
+    const entries_per_block = Math.floor(options.device_block_size / meta_entry_size);
     const object_count = Math.floor((device_size-meta_offset)/options.object_size);
     const meta_size = Math.ceil(1 + object_count / entries_per_block) * options.device_block_size;
     const data_offset = meta_offset + meta_size;

mon/test-optimize-simple.js

@@ -5,21 +5,45 @@ const LPOptimizer = require('./lp-optimizer.js');
 
 async function run()
 {
-    const osd_tree = { a: { 1: 1 }, b: { 2: 1 }, c: { 3: 1 } };
+    const osd_tree = {
+        100: { 1: 1 },
+        200: { 2: 1 },
+        300: { 3: 1 },
+    };
+
     let res;
 
     console.log('16 PGs, size=3');
-    res = await LPOptimizer.optimize_initial({ osd_tree, pg_size: 3, pg_count: 16 });
+    res = await LPOptimizer.optimize_initial({ osd_tree, pg_size: 3, pg_count: 16, ordered: false });
     LPOptimizer.print_change_stats(res, false);
-
-    console.log('\nReduce PG size to 2');
-    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs.map(pg => pg.slice(0, 2)), osd_tree, pg_size: 2 });
+    assert(res.space == 3, 'Initial distribution');
+    console.log('\nChange size to 2');
+    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree, pg_size: 2, ordered: false });
     LPOptimizer.print_change_stats(res, false);
-
+    assert(res.space >= 3*14/16 && res.osd_differs == 0, 'Redistribution');
     console.log('\nRemove OSD 3');
-    delete osd_tree['c'];
-    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree, pg_size: 2 });
+    const no3_tree = { ...osd_tree };
+    delete no3_tree['300'];
+    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree: no3_tree, pg_size: 2, ordered: false });
     LPOptimizer.print_change_stats(res, false);
+    assert(res.space == 2, 'Redistribution after OSD removal');
+
+    console.log('\n16 PGs, size=3, ordered');
+    res = await LPOptimizer.optimize_initial({ osd_tree, pg_size: 3, pg_count: 16, ordered: true });
+    LPOptimizer.print_change_stats(res, false);
+    assert(res.space == 3, 'Initial distribution');
+    console.log('\nChange size to 2, ordered');
+    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree, pg_size: 2, ordered: true });
+    LPOptimizer.print_change_stats(res, false);
+    assert(res.space >= 3*14/16 && res.osd_differs < 8, 'Redistribution');
+}
+
+function assert(cond, txt)
+{
+    if (!cond)
+    {
+        throw new Error((txt||'test')+' failed');
+    }
 }
 
 run().catch(console.error);

mon/test-optimize-undersized.js

@@ -45,30 +45,45 @@ async function run()
     console.log('Empty tree:');
     let res = await LPOptimizer.optimize_initial({ osd_tree: cur_tree, pg_size: 3, pg_count: 256 });
     LPOptimizer.print_change_stats(res, false);
+    assert(res.space == 0);
     console.log('\nAdding 1st failure domain:');
     cur_tree['dom1'] = osd_tree['dom1'];
     res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree: cur_tree, pg_size: 3 });
     LPOptimizer.print_change_stats(res, false);
+    assert(res.space == 12 && res.total_space == 12);
     console.log('\nAdding 2nd failure domain:');
     cur_tree['dom2'] = osd_tree['dom2'];
     res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree: cur_tree, pg_size: 3 });
     LPOptimizer.print_change_stats(res, false);
+    assert(res.space == 24 && res.total_space == 24);
     console.log('\nAdding 3rd failure domain:');
     cur_tree['dom3'] = osd_tree['dom3'];
     res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree: cur_tree, pg_size: 3 });
     LPOptimizer.print_change_stats(res, false);
+    assert(res.space == 36 && res.total_space == 36);
     console.log('\nRemoving 3rd failure domain:');
     delete cur_tree['dom3'];
     res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree: cur_tree, pg_size: 3 });
     LPOptimizer.print_change_stats(res, false);
+    assert(res.space == 24 && res.total_space == 24);
     console.log('\nRemoving 2nd failure domain:');
     delete cur_tree['dom2'];
     res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree: cur_tree, pg_size: 3 });
     LPOptimizer.print_change_stats(res, false);
+    assert(res.space == 12 && res.total_space == 12);
     console.log('\nRemoving 1st failure domain:');
     delete cur_tree['dom1'];
     res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree: cur_tree, pg_size: 3 });
     LPOptimizer.print_change_stats(res, false);
+    assert(res.space == 0);
+}
+
+function assert(cond, txt)
+{
+    if (!cond)
+    {
+        throw new Error((txt||'test')+' failed');
+    }
 }
 
 run().catch(console.error);

mon/test-optimize-unfeasible.js

@@ -0,0 +1,33 @@
+// Copyright (c) Vitaliy Filippov, 2019+
+// License: VNPL-1.1 (see README.md for details)
+
+const LPOptimizer = require('./lp-optimizer.js');
+
+const osd_tree = {
+    100: {
+        1: 0.1,
+        2: 0.1,
+        3: 0.1,
+    },
+    200: {
+        4: 0.1,
+        5: 0.1,
+        6: 0.1,
+    },
+};
+
+async function run()
+{
+    let res;
+    console.log('256 PGs, 3+3 OSDs, size=2');
+    res = await LPOptimizer.optimize_initial({ osd_tree, pg_size: 2, pg_count: 256 });
+    LPOptimizer.print_change_stats(res, false);
+
+    // Should NOT fail with the "unfeasible or unbounded" exception
+    console.log('\nRemoving osd.2');
+    delete osd_tree[100][2];
+    res = await LPOptimizer.optimize_change({ prev_pgs: res.int_pgs, osd_tree, pg_size: 2 });
+    LPOptimizer.print_change_stats(res, false);
+}
+
+run().catch(console.error);

patches/PVE_VitastorPlugin.pm

@@ -0,0 +1,503 @@
+# Install as /usr/share/perl5/PVE/Storage/Custom/VitastorPlugin.pm
+
+# Proxmox Vitastor Driver
+# Copyright (c) Vitaliy Filippov, 2021+
+# License: VNPL-1.1 or GNU AGPLv3.0
+
+package PVE::Storage::Custom::VitastorPlugin;
+
+use strict;
+use warnings;
+
+use JSON;
+
+use PVE::Storage::Plugin;
+use PVE::Tools qw(run_command);
+
+use base qw(PVE::Storage::Plugin);
+
+sub api
+{
+    # Trick it :)
+    return PVE::Storage->APIVER;
+}
+
+sub run_cli
+{
+    my ($scfg, $cmd, %args) = @_;
+    my $retval;
+    my $stderr = '';
+    my $errmsg = $args{errmsg} ? $args{errmsg}.": " : "vitastor-cli error: ";
+    my $json = delete $args{json};
+    $json = 1 if !defined $json;
+    my $binary = delete $args{binary};
+    $binary = '/usr/bin/vitastor-cli' if !defined $binary;
+    if (!exists($args{errfunc}))
+    {
+        $args{errfunc} = sub
+        {
+            my $line = shift;
+            print STDERR $line;
+            *STDERR->flush();
+            $stderr .= $line;
+        };
+    }
+    if (!exists($args{outfunc}))
+    {
+        $retval = '';
+        $args{outfunc} = sub { $retval .= shift };
+        if ($json)
+        {
+            unshift @$cmd, '--json';
+        }
+    }
+    if ($scfg->{vitastor_etcd_address})
+    {
+        unshift @$cmd, '--etcd_address', $scfg->{vitastor_etcd_address};
+    }
+    if ($scfg->{vitastor_config_path})
+    {
+        unshift @$cmd, '--config_path', $scfg->{vitastor_config_path};
+    }
+    unshift @$cmd, $binary;
+    eval { run_command($cmd, %args); };
+    if (my $err = $@)
+    {
+        die "Error invoking vitastor-cli: $err";
+    }
+    if (defined $retval)
+    {
+        # untaint
+        $retval =~ /^(.*)$/s;
+        if ($json)
+        {
+            eval { $retval = JSON::decode_json($1); };
+            if ($@)
+            {
+                die "vitastor-cli returned bad JSON: $@";
+            }
+        }
+        else
+        {
+            $retval = $1;
+        }
+    }
+    return $retval;
+}
+
+# Configuration
+
+sub type
+{
+    return 'vitastor';
+}
+
+sub plugindata
+{
+    return {
+        content => [ { images => 1, rootdir => 1 }, { images => 1 } ],
+    };
+}
+
+sub properties
+{
+    return {
+        vitastor_etcd_address => {
+            description => 'IP address(es) of etcd.',
+            type => 'string',
+            format => 'pve-storage-portal-dns-list',
+        },
+        vitastor_etcd_prefix => {
+            description => 'Prefix for Vitastor etcd metadata',
+            type => 'string',
+        },
+        vitastor_config_path => {
+            description => 'Path to Vitastor configuration file',
+            type => 'string',
+        },
+        vitastor_prefix => {
+            description => 'Image name prefix',
+            type => 'string',
+        },
+        vitastor_pool => {
+            description => 'Default pool to use for images',
+            type => 'string',
+        },
+        vitastor_nbd => {
+            description => 'Use kernel NBD devices (slower)',
+            type => 'boolean',
+        },
+    };
+}
+
+sub options
+{
+    return {
+        nodes => { optional => 1 },
+        disable => { optional => 1 },
+        vitastor_etcd_address => { optional => 1},
+        vitastor_etcd_prefix => { optional => 1 },
+        vitastor_config_path => { optional => 1 },
+        vitastor_prefix => { optional => 1 },
+        vitastor_pool => {},
+        vitastor_nbd => { optional => 1 },
+    };
+}
+
+# Storage implementation
+
+sub parse_volname
+{
+    my ($class, $volname) = @_;
+    if ($volname =~ m/^((base-(\d+)-\S+)\/)?((?:(base)|(vm))-(\d+)-\S+)$/)
+    {
+        # ($vtype, $name, $vmid, $basename, $basevmid, $isBase, $format)
+        return ('images', $4, $7, $2, $3, $5, 'raw');
+    }
+    die "unable to parse vitastor volume name '$volname'\n";
+}
+
+sub _qemu_option
+{
+    my ($k, $v) = @_;
+    if (defined $v && $v ne "")
+    {
+        $v =~ s/:/\\:/gso;
+        return ":$k=$v";
+    }
+    return "";
+}
+
+sub path
+{
+    my ($class, $scfg, $volname, $storeid, $snapname) = @_;
+    my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
+    my ($vtype, $name, $vmid) = $class->parse_volname($volname);
+    $name .= '@'.$snapname if $snapname;
+    if ($scfg->{vitastor_nbd})
+    {
+        my $mapped = run_cli($scfg, [ 'ls' ], binary => '/usr/bin/vitastor-nbd');
+        my ($kerneldev) = grep { $mapped->{$_}->{image} eq $prefix.$name } keys %$mapped;
+        die "Image not mapped via NBD" if !$kerneldev;
+        return ($kerneldev, $vmid, $vtype);
+    }
+    my $path = "vitastor";
+    $path .= _qemu_option('config_path', $scfg->{vitastor_config_path});
+    # FIXME This is the only exception: etcd_address -> etcd_host for qemu
+    $path .= _qemu_option('etcd_host', $scfg->{vitastor_etcd_address});
+    $path .= _qemu_option('etcd_prefix', $scfg->{vitastor_etcd_prefix});
+    $path .= _qemu_option('image', $prefix.$name);
+    return ($path, $vmid, $vtype);
+}
+
+sub _find_free_diskname
+{
+    my ($class, $storeid, $scfg, $vmid, $fmt, $add_fmt_suffix) = @_;
+    my $list = _process_list($scfg, $storeid, run_cli($scfg, [ 'ls' ]));
+    $list = [ map { $_->{name} } @$list ];
+    return PVE::Storage::Plugin::get_next_vm_diskname($list, $storeid, $vmid, undef, $scfg);
+}
+
+# Used only in "Create Template" and, in fact, converts a VM into a template
+# As a consequence, this is always invoked with the VM powered off
+# So we just rename vm-xxx to base-xxx and make it a readonly base layer
+sub create_base
+{
+    my ($class, $storeid, $scfg, $volname) = @_;
+    my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
+
+    my ($vtype, $name, $vmid, $basename, $basevmid, $isBase) = $class->parse_volname($volname);
+    die "create_base not possible with base image\n" if $isBase;
+
+    my $info = _process_list($scfg, $storeid, run_cli($scfg, [ 'ls', $prefix.$name ]))->[0];
+    die "image $name does not exist\n" if !$info;
+
+    die "volname '$volname' contains wrong information about parent {$info->{parent}} $basename\n"
+        if $basename && (!$info->{parent} || $info->{parent} ne $basename);
+
+    my $newname = $name;
+    $newname =~ s/^vm-/base-/;
+
+    my $newvolname = $basename ? "$basename/$newname" : "$newname";
+    run_cli($scfg, [ 'modify', '--rename', $prefix.$newname, '--readonly', $prefix.$name ], json => 0);
+
+    return $newvolname;
+}
+
+sub clone_image
+{
+    my ($class, $scfg, $storeid, $volname, $vmid, $snapname) = @_;
+    my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
+
+    my $snap = '';
+    $snap = '@'.$snapname if length $snapname;
+
+    my ($vtype, $basename, $basevmid, undef, undef, $isBase) = $class->parse_volname($volname);
+    die "$volname is not a base image and snapname is not provided\n" if !$isBase && !length($snapname);
+
+    my $name = $class->find_free_diskname($storeid, $scfg, $vmid);
+
+    warn "clone $volname: $basename snapname $snap to $name\n";
+
+    my $newvol = "$basename/$name";
+    $newvol = $name if length($snapname);
+
+    run_cli($scfg, [ 'create', '--parent', $prefix.$basename.$snap, $prefix.$name ], json => 0);
+
+    return $newvol;
+}
+
+sub alloc_image
+{
+    # $size is in kb in this method
+    my ($class, $storeid, $scfg, $vmid, $fmt, $name, $size) = @_;
+    my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
+    die "illegal name '$name' - should be 'vm-$vmid-*'\n" if $name && $name !~ m/^vm-$vmid-/;
+    $name = $class->find_free_diskname($storeid, $scfg, $vmid) if !$name;
+    run_cli($scfg, [ 'create', '--size', (int(($size+3)/4)*4).'k', '--pool', $scfg->{vitastor_pool}, $prefix.$name ], json => 0);
+    return $name;
+}
+
+sub free_image
+{
+    my ($class, $storeid, $scfg, $volname, $isBase) = @_;
+    my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
+    my ($vtype, $name, $vmid, undef, undef, undef) = $class->parse_volname($volname);
+    $class->deactivate_volume($storeid, $scfg, $volname);
+    my $full_list = run_cli($scfg, [ 'ls', '-l' ]);
+    my $list = _process_list($scfg, $storeid, $full_list);
+    # Remove image and all its snapshots
+    my $rm_names = {
+        map { ($prefix.$_->{name} => 1) }
+        grep { $_->{name} eq $name || substr($_->{name}, 0, length($name)+1) eq ($name.'@') }
+        @$list
+    };
+    my $children = [ grep { $_->{parent_name} && $rm_names->{$_->{parent_name}} } @$full_list ];
+    die "Image has children: ".join(', ', map {
+        substr($_->{name}, 0, length $prefix) eq $prefix
+            ? substr($_->name, length $prefix)
+            : $_->{name}
+    } @$children)."\n" if @$children;
+    my $to_remove = [ grep { $rm_names->{$_->{name}} } @$full_list ];
+    for my $rmi (@$to_remove)
+    {
+        run_cli($scfg, [ 'rm-data', '--pool', $rmi->{pool_id}, '--inode', $rmi->{inode_num} ], json => 0);
+    }
+    for my $rmi (@$to_remove)
+    {
+        run_cli($scfg, [ 'rm', $rmi->{name} ], json => 0);
+    }
+    return undef;
+}
+
+sub _process_list
+{
+    my ($scfg, $storeid, $result) = @_;
+    my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
+    my $list = [];
+    foreach my $el (@$result)
+    {
+        next if !$el->{name} || length($prefix) && substr($el->{name}, 0, length $prefix) ne $prefix;
+        my $name = substr($el->{name}, length $prefix);
+        next if $name =~ /@/;
+        my ($owner) = $name =~ /^(?:vm|base)-(\d+)-/s;
+        next if !defined $owner;
+        my $parent = !defined $el->{parent_name}
+            ? undef
+            : ($prefix eq '' || substr($el->{parent_name}, 0, length $prefix) eq $prefix
+                ? substr($el->{parent_name}, length $prefix) : '');
+        my $volid = $parent && $parent =~ /^(base-\d+-\S+)$/s
+            ? "$storeid:$1/$name" : "$storeid:$name";
+        push @$list, {
+            format => 'raw',
+            volid => $volid,
+            name => $name,
+            size => $el->{size},
+            parent => $parent,
+            vmid => $owner,
+        };
+    }
+    return $list;
+}
+
+sub list_images
+{
+    my ($class, $storeid, $scfg, $vmid, $vollist, $cache) = @_;
+    my $list = _process_list($scfg, $storeid, run_cli($scfg, [ 'ls', '-l' ]));
+    if ($vollist)
+    {
+        my $h = { map { ($_ => 1) } @$vollist };
+        $list = [ grep { $h->{$_->{volid}} } @$list ]
+    }
+    elsif (defined $vmid)
+    {
+        $list = [ grep { $_->{vmid} eq $vmid } @$list ];
+    }
+    return $list;
+}
+
+sub status
+{
+    my ($class, $storeid, $scfg, $cache) = @_;
+    my $stats = [ grep { $_->{name} eq $scfg->{vitastor_pool} } @{ run_cli($scfg, [ 'df' ]) } ]->[0];
+    my $free = $stats ? $stats->{max_available} : 0;
+    my $used = $stats ? $stats->{used_raw}/($stats->{raw_to_usable}||1) : 0;
+    my $total = $free+$used;
+    my $active = $stats ? 1 : 0;
+    return ($total, $free, $used, $active);
+}
+
+sub activate_storage
+{
+    my ($class, $storeid, $scfg, $cache) = @_;
+    return 1;
+}
+
+sub deactivate_storage
+{
+    my ($class, $storeid, $scfg, $cache) = @_;
+    return 1;
+}
+
+sub map_volume
+{
+    my ($class, $storeid, $scfg, $volname, $snapname) = @_;
+    my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
+
+    my ($vtype, $img_name, $vmid) = $class->parse_volname($volname);
+    my $name = $img_name;
+    $name .= '@'.$snapname if $snapname;
+
+    my $mapped = run_cli($scfg, [ 'ls' ], binary => '/usr/bin/vitastor-nbd');
+    my ($kerneldev) = grep { $mapped->{$_}->{image} eq $prefix.$name } keys %$mapped;
+    return $kerneldev if $kerneldev && -b $kerneldev; # already mapped
+
+    $kerneldev = run_cli($scfg, [ 'map', '--image', $prefix.$name ], binary => '/usr/bin/vitastor-nbd', json => 0);
+    return $kerneldev;
+}
+
+sub unmap_volume
+{
+    my ($class, $storeid, $scfg, $volname, $snapname) = @_;
+    my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
+
+    return 1 if !$scfg->{vitastor_nbd};
+
+    my ($vtype, $name, $vmid) = $class->parse_volname($volname);
+    $name .= '@'.$snapname if $snapname;
+
+    my $mapped = run_cli($scfg, [ 'ls' ], binary => '/usr/bin/vitastor-nbd');
+    my ($kerneldev) = grep { $mapped->{$_}->{image} eq $prefix.$name } keys %$mapped;
+    if ($kerneldev && -b $kerneldev)
+    {
+        run_cli($scfg, [ 'unmap', $kerneldev ], binary => '/usr/bin/vitastor-nbd', json => 0);
+    }
+
+    return 1;
+}
+
+sub activate_volume
+{
+    my ($class, $storeid, $scfg, $volname, $snapname, $cache) = @_;
+    $class->map_volume($storeid, $scfg, $volname, $snapname) if $scfg->{vitastor_nbd};
+    return 1;
+}
+
+sub deactivate_volume
+{
+    my ($class, $storeid, $scfg, $volname, $snapname, $cache) = @_;
+    $class->unmap_volume($storeid, $scfg, $volname, $snapname);
+    return 1;
+}
+
+sub volume_size_info
+{
+    my ($class, $scfg, $storeid, $volname, $timeout) = @_;
+    my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
+    my ($vtype, $name, $vmid) = $class->parse_volname($volname);
+    my $info = _process_list($scfg, $storeid, run_cli($scfg, [ 'ls', $prefix.$name ]))->[0];
+    #return wantarray ? ($size, $format, $used, $parent, $st->ctime) : $size;
+    return $info->{size};
+}
+
+sub volume_resize
+{
+    my ($class, $scfg, $storeid, $volname, $size, $running) = @_;
+    my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
+    my ($vtype, $name, $vmid) = $class->parse_volname($volname);
+    # $size is in bytes in this method
+    run_cli($scfg, [ 'modify', '--resize', (int(($size+4095)/4096)*4).'k', $prefix.$name ], json => 0);
+    return undef;
+}
+
+sub volume_snapshot
+{
+    my ($class, $scfg, $storeid, $volname, $snap) = @_;
+    my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
+    my ($vtype, $name, $vmid) = $class->parse_volname($volname);
+    run_cli($scfg, [ 'create', '--snapshot', $snap, $prefix.$name ], json => 0);
+    return undef;
+}
+
+sub volume_snapshot_rollback
+{
+    my ($class, $scfg, $storeid, $volname, $snap) = @_;
+    my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
+    my ($vtype, $name, $vmid) = $class->parse_volname($volname);
+    run_cli($scfg, [ 'rm', $prefix.$name ], json => 0);
+    run_cli($scfg, [ 'create', '--parent', $prefix.$name.'@'.$snap, $prefix.$name ], json => 0);
+    return undef;
+}
+
+sub volume_snapshot_delete
+{
+    my ($class, $scfg, $storeid, $volname, $snap, $running) = @_;
+    my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
+    my ($vtype, $name, $vmid) = $class->parse_volname($volname);
+    run_cli($scfg, [ 'rm', $prefix.$name.'@'.$snap ], json => 0);
+    return undef;
+}
+
+sub volume_snapshot_needs_fsfreeze
+{
+    return 1;
+}
+
+sub volume_has_feature
+{
+    my ($class, $scfg, $feature, $storeid, $volname, $snapname, $running) = @_;
+    my $features = {
+        snapshot => { current => 1, snap => 1 },
+        clone => { base => 1, snap => 1 },
+        template => { current => 1 },
+        copy => { base => 1, current => 1, snap => 1 },
+        sparseinit => { base => 1, current => 1 },
+        rename => { current => 1 },
+    };
+    my ($vtype, $name, $vmid, $basename, $basevmid, $isBase) = $class->parse_volname($volname);
+    my $key = undef;
+    if ($snapname)
+    {
+        $key = 'snap';
+    }
+    else
+    {
+        $key = $isBase ? 'base' : 'current';
+    }
+    return 1 if $features->{$feature}->{$key};
+    return undef;
+}
+
+sub rename_volume
+{
+    my ($class, $scfg, $storeid, $source_volname, $target_vmid, $target_volname) = @_;
+    my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
+    my (undef, $source_image, $source_vmid, $base_name, $base_vmid, undef, $format) =
+        $class->parse_volname($source_volname);
+    $target_volname = $class->find_free_diskname($storeid, $scfg, $target_vmid, $format) if !$target_volname;
+    run_cli($scfg, [ 'modify', '--rename', $prefix.$target_volname, $prefix.$source_image ], json => 0);
+    $base_name = $base_name ? "${base_name}/" : '';
+    return "${storeid}:${base_name}${target_volname}";
+}
+
+1;

patches/cinder-vitastor.py

@@ -50,7 +50,7 @@ from cinder.volume import configuration
 from cinder.volume import driver
 from cinder.volume import volume_utils
 
-VERSION = '0.6.8'
+VERSION = '0.6.17'
 
 LOG = logging.getLogger(__name__)
 
@@ -355,7 +355,25 @@ class VitastorDriver(driver.CloneableImageVD,
     def revert_to_snapshot(self, context, volume, snapshot):
         """Revert a volume to a given snapshot."""
 
-        # FIXME Delete the image, then recreate it from the snapshot
+        vol_name = utils.convert_str(snapshot.volume_name)
+        snap_name = utils.convert_str(snapshot.name)
+
+        # Delete the image and recreate it from the snapshot
+        args = [ 'vitastor-cli', 'rm', vol_name, *(self._vitastor_args()) ]
+        try:
+            self._execute(*args)
+        except processutils.ProcessExecutionError as exc:
+            LOG.error("Failed to delete image "+vol_name+": "+exc)
+            raise exception.VolumeBackendAPIException(data = exc.stderr)
+        args = [
+            'vitastor-cli', 'create', '--parent', vol_name+'@'+snap_name,
+            vol_name, *(self._vitastor_args())
+        ]
+        try:
+            self._execute(*args)
+        except processutils.ProcessExecutionError as exc:
+            LOG.error("Failed to recreate image "+vol_name+" from "+vol_name+"@"+snap_name+": "+exc)
+            raise exception.VolumeBackendAPIException(data = exc.stderr)
 
     def delete_snapshot(self, snapshot):
         """Deletes a snapshot."""
@@ -363,24 +381,15 @@ class VitastorDriver(driver.CloneableImageVD,
         vol_name = utils.convert_str(snapshot.volume_name)
         snap_name = utils.convert_str(snapshot.name)
 
-        # Find the snapshot
-        resp = self._etcd_txn({ 'success': [
-            { 'request_range': { 'key': 'index/image/'+vol_name+'@'+snap_name } },
-        ] })
-        if len(resp['responses'][0]['kvs']) == 0:
-            raise exception.SnapshotNotFound(snapshot_id = snap_name)
-        inode_id = int(resp['responses'][0]['kvs'][0]['value']['id'])
-        pool_id = int(resp['responses'][0]['kvs'][0]['value']['pool_id'])
-        parents = {}
-        parents[(pool_id << 48) | (inode_id & 0xffffffffffff)] = True
-
-        # Check if there are child volumes
-        children = self._child_count(parents)
-        if children > 0:
-            raise exception.SnapshotIsBusy(snapshot_name = snap_name)
-
-        # FIXME: We can't delete snapshots because we can't merge layers yet
-        raise exception.VolumeBackendAPIException(data = 'Snapshot delete (layer merge) is not implemented yet')
+        args = [
+            'vitastor-cli', 'rm', vol_name+'@'+snap_name,
+            *(self._vitastor_args())
+        ]
+        try:
+            self._execute(*args)
+        except processutils.ProcessExecutionError as exc:
+            LOG.error("Failed to remove snapshot "+vol_name+'@'+snap_name+": "+exc)
+            raise exception.VolumeBackendAPIException(data = exc.stderr)
 
     def _child_count(self, parents):
         children = 0
@@ -489,7 +498,7 @@ class VitastorDriver(driver.CloneableImageVD,
                 # FIXME use etcd_address in qemu driver
                 kk = 'etcd_host'
             if v:
-                args += ':'+kk+'='+v.replace(':', '\\:')
+                args += ':'+kk.replace('_', '-')+'='+v.replace(':', '\\:')
         return args
 
     def delete_volume(self, volume):
@@ -658,8 +667,8 @@ class VitastorDriver(driver.CloneableImageVD,
                 'etcd_address': self.configuration.vitastor_etcd_address,
                 'etcd_prefix': self.configuration.vitastor_etcd_prefix,
                 'name': volume.name,
-                'logical_block_size': 512,
-                'physical_block_size': 4096,
+                'logical_block_size': '512',
+                'physical_block_size': '4096',
             }
         }
         LOG.debug('connection data: %s', data)

patches/libvirt-5.0-vitastor.diff

@@ -1,4 +1,4 @@
-commit bd283191b3e7a4c6d1c100d3d96e348a1ebffe55
+commit 7f01510ef207940b07fac4f5fc8b9f1580b443aa
 Author: Vitaliy Filippov <vitalif@yourcmc.ru>
 Date:   Sun Jun 27 12:52:40 2021 +0300
 
@@ -65,10 +65,38 @@ index 4bf2b5f..dbc011b 100644
  
  int                     virConnectListAllStoragePools(virConnectPtr conn,
 diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c
-index 222bb8c..685d255 100644
+index 222bb8c..2c30c55 100644
 --- a/src/conf/domain_conf.c
 +++ b/src/conf/domain_conf.c
-@@ -8653,6 +8653,10 @@ virDomainDiskSourceNetworkParse(xmlNodePtr node,
+@@ -4667,8 +4667,7 @@ virDomainDeviceDefPostParseCommon(virDomainDeviceDefPtr dev,
+     if (dev->type == VIR_DOMAIN_DEVICE_DISK) {
+         virDomainDiskDefPtr disk = dev->data.disk;
+ 
+-        /* internal snapshots and config files are currently supported
+-         * only with rbd: */
++        /* internal snapshots are currently supported only with rbd: */
+         if (virStorageSourceGetActualType(disk->src) != VIR_STORAGE_TYPE_NETWORK &&
+             disk->src->protocol != VIR_STORAGE_NET_PROTOCOL_RBD) {
+             if (disk->src->snapshot) {
+@@ -4677,11 +4676,15 @@ virDomainDeviceDefPostParseCommon(virDomainDeviceDefPtr dev,
+                                  "only with 'rbd' disks"));
+                 return -1;
+             }
+-
++        }
++        /* config files are currently supported only with rbd and vitastor: */
++        if (virStorageSourceGetActualType(disk->src) != VIR_STORAGE_TYPE_NETWORK &&
++            disk->src->protocol != VIR_STORAGE_NET_PROTOCOL_RBD &&
++            disk->src->protocol != VIR_STORAGE_NET_PROTOCOL_VITASTOR) {
+             if (disk->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;
+             }
+         }
+@@ -8653,6 +8656,10 @@ virDomainDiskSourceNetworkParse(xmlNodePtr node,
          goto cleanup;
      }
  
@@ -79,7 +107,7 @@ index 222bb8c..685d255 100644
      if ((haveTLS = virXMLPropString(node, "tls")) &&
          (src->haveTLS = virTristateBoolTypeFromString(haveTLS)) <= 0) {
          virReportError(VIR_ERR_XML_ERROR,
-@@ -23849,6 +23853,10 @@ virDomainDiskSourceFormatNetwork(virBufferPtr attrBuf,
+@@ -23849,6 +23856,10 @@ virDomainDiskSourceFormatNetwork(virBufferPtr attrBuf,
  
      virBufferEscapeString(attrBuf, " name='%s'", path ? path : src->path);
  
@@ -90,7 +118,7 @@ index 222bb8c..685d255 100644
      VIR_FREE(path);
  
      if (src->haveTLS != VIR_TRISTATE_BOOL_ABSENT &&
-@@ -30930,6 +30938,7 @@ virDomainDiskTranslateSourcePool(virDomainDiskDefPtr def)
+@@ -30930,6 +30941,7 @@ virDomainDiskTranslateSourcePool(virDomainDiskDefPtr def)
  
      case VIR_STORAGE_POOL_MPATH:
      case VIR_STORAGE_POOL_RBD:
@@ -216,7 +244,7 @@ index 73e988a..ab7bb81 100644
      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 cbf0aa4..096700d 100644
+index cbf0aa4..f0ca9e7 100644
 --- a/src/qemu/qemu_block.c
 +++ b/src/qemu/qemu_block.c
 @@ -959,6 +959,42 @@ qemuBlockStorageSourceGetRBDProps(virStorageSourcePtr src)
@@ -245,9 +273,9 @@ index cbf0aa4..096700d 100644
 +
 +    if (virJSONValueObjectCreate(&ret,
 +                                 "s:driver", "vitastor",
-+                                 "S:etcd_host", etcd,
-+                                 "S:etcd_prefix", src->relPath,
-+                                 "S:config_path", src->configFile,
++                                 "S:etcd-host", etcd,
++                                 "S:etcd-prefix", src->relPath,
++                                 "S:config-path", src->configFile,
 +                                 "s:image", src->path,
 +                                 NULL) < 0)
 +        goto cleanup;
@@ -275,7 +303,7 @@ index cbf0aa4..096700d 100644
              if (!(fileprops = qemuBlockStorageSourceGetSheepdogProps(src)))
                  return NULL;
 diff --git a/src/qemu/qemu_command.c b/src/qemu/qemu_command.c
-index 822d5f8..e375cef 100644
+index 822d5f8..abec34e 100644
 --- a/src/qemu/qemu_command.c
 +++ b/src/qemu/qemu_command.c
 @@ -975,6 +975,43 @@ qemuBuildNetworkDriveStr(virStorageSourcePtr src,
@@ -293,7 +321,7 @@ index 822d5f8..e375cef 100644
 +            virBufferStrcat(&buf, "vitastor:image=", src->path, NULL);
 +
 +            if (src->nhosts > 0) {
-+                virBufferAddLit(&buf, ":etcd_host=");
++                virBufferAddLit(&buf, ":etcd-host=");
 +                for (i = 0; i < src->nhosts; i++) {
 +                    if (i)
 +                        virBufferAddLit(&buf, ",");
@@ -311,10 +339,10 @@ index 822d5f8..e375cef 100644
 +            }
 +
 +            if (src->configFile)
-+                virBufferEscape(&buf, '\\', ":", ":config_path=%s", src->configFile);
++                virBufferEscape(&buf, '\\', ":", ":config-path=%s", src->configFile);
 +
 +            if (src->relPath)
-+                virBufferEscape(&buf, '\\', ":", ":etcd_prefix=%s", src->relPath);
++                virBufferEscape(&buf, '\\', ":", ":etcd-prefix=%s", src->relPath);
 +
 +            ret = virBufferContentAndReset(&buf);
 +            break;
@@ -387,7 +415,7 @@ index 4a13e90..33301c7 100644
              ignore_value(VIR_STRDUP(stable_path, data->path));
              break;
 diff --git a/src/util/virstoragefile.c b/src/util/virstoragefile.c
-index bd4b027..b323cd6 100644
+index bd4b027..8454906 100644
 --- a/src/util/virstoragefile.c
 +++ b/src/util/virstoragefile.c
 @@ -84,7 +84,8 @@ VIR_ENUM_IMPL(virStorageNetProtocol, VIR_STORAGE_NET_PROTOCOL_LAST,
@@ -438,16 +466,16 @@ index bd4b027..b323cd6 100644
 +        if (STRPREFIX(p, "image=")) {
 +            if (VIR_STRDUP(src->path, p + strlen("image=")) < 0)
 +                return -1;
-+        } else if (STRPREFIX(p, "etcd_prefix=")) {
-+            if (VIR_STRDUP(src->relPath, p + strlen("etcd_prefix=")) < 0)
++        } else if (STRPREFIX(p, "etcd-prefix=")) {
++            if (VIR_STRDUP(src->relPath, p + strlen("etcd-prefix=")) < 0)
 +                return -1;
-+        } else if (STRPREFIX(p, "config_file=")) {
-+            if (VIR_STRDUP(src->configFile, p + strlen("config_file=")) < 0)
++        } else if (STRPREFIX(p, "config-path=")) {
++            if (VIR_STRDUP(src->configFile, p + strlen("config-path=")) < 0)
 +                return -1;
-+        } else if (STRPREFIX(p, "etcd_host=")) {
++        } else if (STRPREFIX(p, "etcd-host=")) {
 +            char *h, *sep;
 +
-+            h = p + strlen("etcd_host=");
++            h = p + strlen("etcd-host=");
 +            while (h < e) {
 +                for (sep = h; sep < e; ++sep) {
 +                    if (*sep == '\\' && (sep[1] == ',' ||
@@ -507,8 +535,8 @@ index bd4b027..b323cd6 100644
 +{
 +    const char *filename;
 +    const char *image = virJSONValueObjectGetString(json, "image");
-+    const char *conf = virJSONValueObjectGetString(json, "config_path");
-+    const char *etcd_prefix = virJSONValueObjectGetString(json, "etcd_prefix");
++    const char *conf = virJSONValueObjectGetString(json, "config-path");
++    const char *etcd_prefix = virJSONValueObjectGetString(json, "etcd-prefix");
 +    virJSONValuePtr servers = virJSONValueObjectGetArray(json, "server");
 +    size_t nservers;
 +    size_t i;

patches/libvirt-7.0-vitastor.diff

@@ -1,4 +1,4 @@
-commit 41cdfe8317d98f70aadedfdbb381effed2641bdd
+commit 4e74c622884e2585b2cfcdf322fbd2bff6de41ca
 Author: Vitaliy Filippov <vitalif@yourcmc.ru>
 Date:   Fri Jul 9 01:31:57 2021 +0300
 
@@ -65,10 +65,38 @@ index 089e1e0..d7e7ef4 100644
  
  int                     virConnectListAllStoragePools(virConnectPtr conn,
 diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c
-index 01b7187..c6e9702 100644
+index 01b7187..645c758 100644
 --- a/src/conf/domain_conf.c
 +++ b/src/conf/domain_conf.c
-@@ -8261,7 +8261,8 @@ virDomainDiskSourceNetworkParse(xmlNodePtr node,
+@@ -5230,8 +5230,7 @@ virDomainDiskDefPostParse(virDomainDiskDefPtr disk,
+                           const virDomainDef *def,
+                           virDomainXMLOptionPtr xmlopt)
+ {
+-    /* internal snapshots and config files are currently supported
+-     * only with rbd: */
++    /* internal snapshots are currently supported only with rbd: */
+     if (virStorageSourceGetActualType(disk->src) != VIR_STORAGE_TYPE_NETWORK &&
+         disk->src->protocol != VIR_STORAGE_NET_PROTOCOL_RBD) {
+         if (disk->src->snapshot) {
+@@ -5240,11 +5239,15 @@ virDomainDiskDefPostParse(virDomainDiskDefPtr disk,
+                              "only with 'rbd' disks"));
+             return -1;
+         }
+-
++    }
++    /* config files are currently supported only with rbd and vitastor: */
++    if (virStorageSourceGetActualType(disk->src) != VIR_STORAGE_TYPE_NETWORK &&
++        disk->src->protocol != VIR_STORAGE_NET_PROTOCOL_RBD &&
++        disk->src->protocol != VIR_STORAGE_NET_PROTOCOL_VITASTOR) {
+         if (disk->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;
+         }
+     }
+@@ -8261,7 +8264,8 @@ virDomainDiskSourceNetworkParse(xmlNodePtr node,
      src->configFile = virXPathString("string(./config/@file)", ctxt);
  
      if (src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTP ||
@@ -78,7 +106,7 @@ index 01b7187..c6e9702 100644
          src->query = virXMLPropString(node, "query");
  
      if (virDomainStorageNetworkParseHosts(node, ctxt, &src->hosts, &src->nhosts) < 0)
-@@ -31392,6 +31393,7 @@ virDomainStorageSourceTranslateSourcePool(virStorageSourcePtr src,
+@@ -31392,6 +31396,7 @@ virDomainStorageSourceTranslateSourcePool(virStorageSourcePtr src,
  
      case VIR_STORAGE_POOL_MPATH:
      case VIR_STORAGE_POOL_RBD:
@@ -216,7 +244,7 @@ index 17b93d0..c5a0084 100644
      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 f9c6da2..922dde5 100644
+index f9c6da2..d837a05 100644
 --- a/src/qemu/qemu_block.c
 +++ b/src/qemu/qemu_block.c
 @@ -938,6 +938,38 @@ qemuBlockStorageSourceGetRBDProps(virStorageSourcePtr src,
@@ -244,9 +272,9 @@ index f9c6da2..922dde5 100644
 +    }
 +
 +    if (virJSONValueObjectCreate(&ret,
-+                                 "S:etcd_host", etcd,
-+                                 "S:etcd_prefix", src->query,
-+                                 "S:config_path", src->configFile,
++                                 "S:etcd-host", etcd,
++                                 "S:etcd-prefix", src->query,
++                                 "S:config-path", src->configFile,
 +                                 "s:image", src->path,
 +                                 NULL) < 0)
 +        return NULL;
@@ -293,7 +321,7 @@ index f9c6da2..922dde5 100644
              driver = "sheepdog";
              if (!(location = qemuBlockStorageSourceGetSheepdogProps(src)))
 diff --git a/src/qemu/qemu_command.c b/src/qemu/qemu_command.c
-index 6f970a3..10b39ca 100644
+index 6f970a3..4c03fb8 100644
 --- a/src/qemu/qemu_command.c
 +++ b/src/qemu/qemu_command.c
 @@ -1034,6 +1034,43 @@ qemuBuildNetworkDriveStr(virStorageSourcePtr src,
@@ -311,7 +339,7 @@ index 6f970a3..10b39ca 100644
 +            virBufferStrcat(&buf, "vitastor:image=", src->path, NULL);
 +
 +            if (src->nhosts > 0) {
-+                virBufferAddLit(&buf, ":etcd_host=");
++                virBufferAddLit(&buf, ":etcd-host=");
 +                for (i = 0; i < src->nhosts; i++) {
 +                    if (i)
 +                        virBufferAddLit(&buf, ",");
@@ -329,10 +357,10 @@ index 6f970a3..10b39ca 100644
 +            }
 +
 +            if (src->configFile)
-+                virBufferEscape(&buf, '\\', ":", ":config_path=%s", src->configFile);
++                virBufferEscape(&buf, '\\', ":", ":config-path=%s", src->configFile);
 +
 +            if (src->query)
-+                virBufferEscape(&buf, '\\', ":", ":etcd_prefix=%s", src->query);
++                virBufferEscape(&buf, '\\', ":", ":etcd-prefix=%s", src->query);
 +
 +            ret = virBufferContentAndReset(&buf);
 +            break;
@@ -415,7 +443,7 @@ index 29c4c86..a27ad94 100644
      case VIR_STORAGE_POOL_LOGICAL:
      case VIR_STORAGE_POOL_DISK:
 diff --git a/src/util/virstoragefile.c b/src/util/virstoragefile.c
-index 0d3c2af..36e3afc 100644
+index 0d3c2af..edb7f9e 100644
 --- a/src/util/virstoragefile.c
 +++ b/src/util/virstoragefile.c
 @@ -91,6 +91,7 @@ VIR_ENUM_IMPL(virStorageNetProtocol,
@@ -462,14 +490,14 @@ index 0d3c2af..36e3afc 100644
 +
 +        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_file=")) {
-+            src->configFile = g_strdup(p + strlen("config_file="));
-+        } else if (STRPREFIX(p, "etcd_host=")) {
++        } 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=");
++            h = p + strlen("etcd-host=");
 +            while (h < e) {
 +                for (sep = h; sep < e; ++sep) {
 +                    if (*sep == '\\' && (sep[1] == ',' ||
@@ -526,8 +554,8 @@ index 0d3c2af..36e3afc 100644
 +{
 +    const char *filename;
 +    const char *image = virJSONValueObjectGetString(json, "image");
-+    const char *conf = virJSONValueObjectGetString(json, "config_path");
-+    const char *etcd_prefix = virJSONValueObjectGetString(json, "etcd_prefix");
++    const char *conf = virJSONValueObjectGetString(json, "config-path");
++    const char *etcd_prefix = virJSONValueObjectGetString(json, "etcd-prefix");
 +    virJSONValuePtr servers = virJSONValueObjectGetArray(json, "server");
 +    size_t nservers;
 +    size_t i;

patches/libvirt-7.5-vitastor.diff

@@ -1,4 +1,4 @@
-commit c6e1958a1b4974828e8e5852beb252ce6594e670
+commit c97d7f2bfb7798f0d68bdba2646245dcfb940efa
 Author: Vitaliy Filippov <vitalif@yourcmc.ru>
 Date:   Mon Jun 28 01:20:19 2021 +0300
 
@@ -86,6 +86,37 @@ index d78f846..f7222e3 100644
      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 2124d25..6acc6fa 100644
+--- a/src/conf/domain_validate.c
++++ b/src/conf/domain_validate.c
+@@ -470,7 +470,7 @@ 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) {
+@@ -479,11 +479,15 @@ 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 2aa9a3d..166ca1f 100644
 --- a/src/conf/storage_conf.c
@@ -248,7 +279,7 @@ index c0905b0..c172378 100644
      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 6627d04..c33f428 100644
+index 6627d04..f769d24 100644
 --- a/src/qemu/qemu_block.c
 +++ b/src/qemu/qemu_block.c
 @@ -928,6 +928,38 @@ qemuBlockStorageSourceGetRBDProps(virStorageSource *src,
@@ -276,9 +307,9 @@ index 6627d04..c33f428 100644
 +    }
 +
 +    if (virJSONValueObjectCreate(&ret,
-+                                 "S:etcd_host", etcd,
-+                                 "S:etcd_prefix", src->query,
-+                                 "S:config_path", src->configFile,
++                                 "S:etcd-host", etcd,
++                                 "S:etcd-prefix", src->query,
++                                 "S:config-path", src->configFile,
 +                                 "s:image", src->path,
 +                                 NULL) < 0)
 +        return NULL;
@@ -325,7 +356,7 @@ index 6627d04..c33f428 100644
              driver = "sheepdog";
              if (!(location = qemuBlockStorageSourceGetSheepdogProps(src)))
 diff --git a/src/qemu/qemu_command.c b/src/qemu/qemu_command.c
-index ea51369..8258632 100644
+index ea51369..d714597 100644
 --- a/src/qemu/qemu_command.c
 +++ b/src/qemu/qemu_command.c
 @@ -1074,6 +1074,43 @@ qemuBuildNetworkDriveStr(virStorageSource *src,
@@ -343,7 +374,7 @@ index ea51369..8258632 100644
 +            virBufferStrcat(&buf, "vitastor:image=", src->path, NULL);
 +
 +            if (src->nhosts > 0) {
-+                virBufferAddLit(&buf, ":etcd_host=");
++                virBufferAddLit(&buf, ":etcd-host=");
 +                for (i = 0; i < src->nhosts; i++) {
 +                    if (i)
 +                        virBufferAddLit(&buf, ",");
@@ -361,10 +392,10 @@ index ea51369..8258632 100644
 +            }
 +
 +            if (src->configFile)
-+                virBufferEscape(&buf, '\\', ":", ":config_path=%s", src->configFile);
++                virBufferEscape(&buf, '\\', ":", ":config-path=%s", src->configFile);
 +
 +            if (src->query)
-+                virBufferEscape(&buf, '\\', ":", ":etcd_prefix=%s", src->query);
++                virBufferEscape(&buf, '\\', ":", ":etcd-prefix=%s", src->query);
 +
 +            ret = virBufferContentAndReset(&buf);
 +            break;
@@ -435,7 +466,7 @@ index c2ff4b8..70d0689 100644
          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 e48ae72..d7a9b72 100644
+index e48ae72..2017ccc 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,
@@ -474,14 +505,14 @@ index e48ae72..d7a9b72 100644
 +
 +        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_file=")) {
-+            src->configFile = g_strdup(p + strlen("config_file="));
-+        } else if (STRPREFIX(p, "etcd_host=")) {
++        } 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=");
++            h = p + strlen("etcd-host=");
 +            while (h < e) {
 +                for (sep = h; sep < e; ++sep) {
 +                    if (*sep == '\\' && (sep[1] == ',' ||
@@ -538,8 +569,8 @@ index e48ae72..d7a9b72 100644
 +{
 +    const char *filename;
 +    const char *image = virJSONValueObjectGetString(json, "image");
-+    const char *conf = virJSONValueObjectGetString(json, "config_path");
-+    const char *etcd_prefix = virJSONValueObjectGetString(json, "etcd_prefix");
++    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;

patches/libvirt-7.6-vitastor.diff

@@ -0,0 +1,692 @@
+commit c97d7f2bfb7798f0d68bdba2646245dcfb940efa
+Author: Vitaliy Filippov <vitalif@yourcmc.ru>
+Date:   Mon Jun 28 01:20:19 2021 +0300
+
+    Add Vitastor support
+
+Index: libvirt-7.6.0/docs/schemas/domaincommon.rng
+===================================================================
+--- libvirt-7.6.0.orig/docs/schemas/domaincommon.rng
++++ libvirt-7.6.0/docs/schemas/domaincommon.rng
+@@ -1877,6 +1877,35 @@
+     </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">
+@@ -2133,6 +2162,7 @@
+       <ref name="diskSourceNetworkProtocolSimple"/>
+       <ref name="diskSourceNetworkProtocolVxHS"/>
+       <ref name="diskSourceNetworkProtocolNFS"/>
++      <ref name="diskSourceNetworkProtocolVitastor"/>
+     </choice>
+   </define>
+ 
+Index: libvirt-7.6.0/include/libvirt/libvirt-storage.h
+===================================================================
+--- libvirt-7.6.0.orig/include/libvirt/libvirt-storage.h
++++ libvirt-7.6.0/include/libvirt/libvirt-storage.h
+@@ -245,6 +245,7 @@ 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,
+Index: libvirt-7.6.0/src/conf/domain_conf.c
+===================================================================
+--- libvirt-7.6.0.orig/src/conf/domain_conf.c
++++ libvirt-7.6.0/src/conf/domain_conf.c
+@@ -8268,7 +8268,8 @@ virDomainDiskSourceNetworkParse(xmlNodeP
+     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)
+@@ -30831,6 +30832,7 @@ virDomainStorageSourceTranslateSourcePoo
+ 
+     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:
+Index: libvirt-7.6.0/src/conf/domain_validate.c
+===================================================================
+--- libvirt-7.6.0.orig/src/conf/domain_validate.c
++++ libvirt-7.6.0/src/conf/domain_validate.c
+@@ -470,7 +470,7 @@ virDomainDiskDefValidateSourceChainOne(c
+         }
+     }
+ 
+-    /* 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) {
+@@ -479,11 +479,15 @@ virDomainDiskDefValidateSourceChainOne(c
+                              "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;
+         }
+     }
+Index: libvirt-7.6.0/src/conf/storage_conf.c
+===================================================================
+--- libvirt-7.6.0.orig/src/conf/storage_conf.c
++++ libvirt-7.6.0/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 poolTypeIn
+           .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(xmlXPathCon
+                        _("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;
+@@ -1182,6 +1199,7 @@ virStoragePoolDefFormatBuf(virBuffer *bu
+     /* 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) {
+Index: libvirt-7.6.0/src/conf/storage_conf.h
+===================================================================
+--- libvirt-7.6.0.orig/src/conf/storage_conf.h
++++ libvirt-7.6.0/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;
+@@ -465,6 +466,7 @@ 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      | \
+Index: libvirt-7.6.0/src/conf/storage_source_conf.c
+===================================================================
+--- libvirt-7.6.0.orig/src/conf/storage_source_conf.c
++++ libvirt-7.6.0/src/conf/storage_source_conf.c
+@@ -85,6 +85,7 @@ VIR_ENUM_IMPL(virStorageNetProtocol,
+               "ssh",
+               "vxhs",
+               "nfs",
++              "vitastor",
+ );
+ 
+ 
+@@ -1262,6 +1263,7 @@ virStorageSourceNetworkDefaultPort(virSt
+         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;
+Index: libvirt-7.6.0/src/conf/storage_source_conf.h
+===================================================================
+--- libvirt-7.6.0.orig/src/conf/storage_source_conf.h
++++ libvirt-7.6.0/src/conf/storage_source_conf.h
+@@ -127,6 +127,7 @@ 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;
+Index: libvirt-7.6.0/src/conf/virstorageobj.c
+===================================================================
+--- libvirt-7.6.0.orig/src/conf/virstorageobj.c
++++ libvirt-7.6.0/src/conf/virstorageobj.c
+@@ -1481,6 +1481,7 @@ virStoragePoolObjSourceFindDuplicateCb(c
+             return 1;
+         break;
+ 
++    case VIR_STORAGE_POOL_VITASTOR:
+     case VIR_STORAGE_POOL_RBD:
+     case VIR_STORAGE_POOL_LAST:
+         break;
+@@ -1980,6 +1981,8 @@ virStoragePoolObjMatch(virStoragePoolObj
+                (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) &&
+Index: libvirt-7.6.0/src/libvirt-storage.c
+===================================================================
+--- libvirt-7.6.0.orig/src/libvirt-storage.c
++++ libvirt-7.6.0/src/libvirt-storage.c
+@@ -92,6 +92,7 @@ virStoragePoolGetConnect(virStoragePoolP
+  * 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
+Index: libvirt-7.6.0/src/libxl/libxl_conf.c
+===================================================================
+--- libvirt-7.6.0.orig/src/libxl/libxl_conf.c
++++ libvirt-7.6.0/src/libxl/libxl_conf.c
+@@ -972,6 +972,7 @@ libxlMakeNetworkDiskSrcStr(virStorageSou
+     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,
+Index: libvirt-7.6.0/src/libxl/xen_xl.c
+===================================================================
+--- libvirt-7.6.0.orig/src/libxl/xen_xl.c
++++ libvirt-7.6.0/src/libxl/xen_xl.c
+@@ -1540,6 +1540,7 @@ xenFormatXLDiskSrcNet(virStorageSource *
+     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,
+Index: libvirt-7.6.0/src/qemu/qemu_block.c
+===================================================================
+--- libvirt-7.6.0.orig/src/qemu/qemu_block.c
++++ libvirt-7.6.0/src/qemu/qemu_block.c
+@@ -916,6 +916,38 @@ qemuBlockStorageSourceGetRBDProps(virSto
+ 
+ 
+ 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)
+ {
+     g_autoptr(virJSONValue) serverprops = NULL;
+@@ -1205,6 +1237,12 @@ qemuBlockStorageSourceGetBackendProps(vi
+                 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)))
+@@ -2219,6 +2257,7 @@ qemuBlockGetBackingStoreString(virStorag
+ 
+             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:
+@@ -2596,6 +2635,12 @@ qemuBlockStorageSourceCreateGetStoragePr
+                 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)))
+Index: libvirt-7.6.0/src/qemu/qemu_command.c
+===================================================================
+--- libvirt-7.6.0.orig/src/qemu/qemu_command.c
++++ libvirt-7.6.0/src/qemu/qemu_command.c
+@@ -1074,6 +1074,43 @@ qemuBuildNetworkDriveStr(virStorageSourc
+             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"));
+Index: libvirt-7.6.0/src/qemu/qemu_domain.c
+===================================================================
+--- libvirt-7.6.0.orig/src/qemu/qemu_domain.c
++++ libvirt-7.6.0/src/qemu/qemu_domain.c
+@@ -4900,7 +4900,8 @@ qemuDomainValidateStorageSource(virStora
+     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;
+@@ -10102,6 +10103,7 @@ qemuDomainPrepareStorageSourceTLS(virSto
+         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:
+Index: libvirt-7.6.0/src/qemu/qemu_snapshot.c
+===================================================================
+--- libvirt-7.6.0.orig/src/qemu/qemu_snapshot.c
++++ libvirt-7.6.0/src/qemu/qemu_snapshot.c
+@@ -402,6 +402,7 @@ qemuSnapshotPrepareDiskExternalInactive(
+         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:
+@@ -494,6 +495,7 @@ qemuSnapshotPrepareDiskExternalActive(vi
+         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:
+@@ -647,6 +649,7 @@ qemuSnapshotPrepareDiskInternal(virDomai
+         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:
+Index: libvirt-7.6.0/src/storage/storage_driver.c
+===================================================================
+--- libvirt-7.6.0.orig/src/storage/storage_driver.c
++++ libvirt-7.6.0/src/storage/storage_driver.c
+@@ -1644,6 +1644,7 @@ storageVolLookupByPathCallback(virStorag
+ 
+         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:
+Index: libvirt-7.6.0/src/storage_file/storage_source_backingstore.c
+===================================================================
+--- libvirt-7.6.0.orig/src/storage_file/storage_source_backingstore.c
++++ libvirt-7.6.0/src/storage_file/storage_source_backingstore.c
+@@ -285,6 +285,75 @@ virStorageSourceParseRBDColonString(cons
+ 
+ 
+ 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(virSto
+             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:
+@@ -985,6 +1059,54 @@ virStorageSourceParseBackingJSONRBD(virS
+ }
+ 
+ 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,
+                                     const char *jsonstr,
+@@ -1162,6 +1284,7 @@ static const struct virStorageSourceJSON
+     {"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},
+Index: libvirt-7.6.0/src/test/test_driver.c
+===================================================================
+--- libvirt-7.6.0.orig/src/test/test_driver.c
++++ libvirt-7.6.0/src/test/test_driver.c
+@@ -7193,6 +7193,7 @@ testStorageVolumeTypeForPool(int pooltyp
+     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:
+Index: libvirt-7.6.0/tests/storagepoolcapsschemadata/poolcaps-fs.xml
+===================================================================
+--- libvirt-7.6.0.orig/tests/storagepoolcapsschemadata/poolcaps-fs.xml
++++ libvirt-7.6.0/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>
+Index: libvirt-7.6.0/tests/storagepoolcapsschemadata/poolcaps-full.xml
+===================================================================
+--- libvirt-7.6.0.orig/tests/storagepoolcapsschemadata/poolcaps-full.xml
++++ libvirt-7.6.0/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>
+Index: libvirt-7.6.0/tests/storagepoolxml2argvtest.c
+===================================================================
+--- libvirt-7.6.0.orig/tests/storagepoolxml2argvtest.c
++++ libvirt-7.6.0/tests/storagepoolxml2argvtest.c
+@@ -68,6 +68,7 @@ testCompareXMLToArgvFiles(bool shouldFai
+     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);
+Index: libvirt-7.6.0/tools/virsh-pool.c
+===================================================================
+--- libvirt-7.6.0.orig/tools/virsh-pool.c
++++ libvirt-7.6.0/tools/virsh-pool.c
+@@ -1231,6 +1231,9 @@ cmdPoolList(vshControl *ctl, const vshCm
+             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;
+             }

patches/libvirt-example.xml

@@ -15,9 +15,10 @@
       <target dev='vda' bus='virtio' />
       <driver name='qemu' type='raw' />
       <!-- name is Vitastor image name -->
-      <!-- config (optional) is the path to Vitastor's configuration file -->
       <!-- query (optional) is Vitastor's etcd_prefix -->
-      <source protocol='vitastor' name='debian9' query='/vitastor' config='/etc/vitastor/vitastor.conf'>
+      <source protocol='vitastor' name='debian9' query='/vitastor'>
+        <!-- config (optional) is the path to Vitastor's configuration file -->
+        <config file='/etc/vitastor/vitastor.conf' />
         <!-- hosts = etcd addresses -->
         <host name='192.168.7.2' port='2379' />
       </source>

patches/nova-21.diff

@@ -0,0 +1,288 @@
+diff --git a/nova/virt/image/model.py b/nova/virt/image/model.py
+index 971f7e9c07..ec3fca72cb 100644
+--- a/nova/virt/image/model.py
++++ b/nova/virt/image/model.py
+@@ -129,3 +129,22 @@ class RBDImage(Image):
+         self.user = user
+         self.password = password
+         self.servers = servers
++
++
++class VitastorImage(Image):
++    """Class for images in a remote Vitastor cluster"""
++
++    def __init__(self, name, etcd_address = None, etcd_prefix = None, config_path = None):
++        """Create a new Vitastor image object
++
++        :param name: name of the image
++        :param etcd_address: etcd URL(s) (optional)
++        :param etcd_prefix: etcd prefix (optional)
++        :param config_path: path to the configuration (optional)
++        """
++        super(VitastorImage, self).__init__(FORMAT_RAW)
++
++        self.name = name
++        self.etcd_address = etcd_address
++        self.etcd_prefix = etcd_prefix
++        self.config_path = config_path
+diff --git a/nova/virt/images.py b/nova/virt/images.py
+index 5358f3766a..ebe3d6effb 100644
+--- a/nova/virt/images.py
++++ b/nova/virt/images.py
+@@ -41,7 +41,7 @@ IMAGE_API = glance.API()
+ 
+ def qemu_img_info(path, format=None):
+     """Return an object containing the parsed output from qemu-img info."""
+-    if not os.path.exists(path) and not path.startswith('rbd:'):
++    if not os.path.exists(path) and not path.startswith('rbd:') and not path.startswith('vitastor:'):
+         raise exception.DiskNotFound(location=path)
+ 
+     info = nova.privsep.qemu.unprivileged_qemu_img_info(path, format=format)
+@@ -50,7 +50,7 @@ def qemu_img_info(path, format=None):
+ 
+ def privileged_qemu_img_info(path, format=None, output_format='json'):
+     """Return an object containing the parsed output from qemu-img info."""
+-    if not os.path.exists(path) and not path.startswith('rbd:'):
++    if not os.path.exists(path) and not path.startswith('rbd:') and not path.startswith('vitastor:'):
+         raise exception.DiskNotFound(location=path)
+ 
+     info = nova.privsep.qemu.privileged_qemu_img_info(path, format=format)
+diff --git a/nova/virt/libvirt/config.py b/nova/virt/libvirt/config.py
+index ea525648b3..d7aa798954 100644
+--- a/nova/virt/libvirt/config.py
++++ b/nova/virt/libvirt/config.py
+@@ -1005,6 +1005,8 @@ class LibvirtConfigGuestDisk(LibvirtConfigGuestDevice):
+         self.driver_iommu = False
+         self.source_path = None
+         self.source_protocol = None
++        self.source_query = None
++        self.source_config = None
+         self.source_name = None
+         self.source_hosts = []
+         self.source_ports = []
+@@ -1133,6 +1135,10 @@ class LibvirtConfigGuestDisk(LibvirtConfigGuestDevice):
+             source = etree.Element("source", protocol=self.source_protocol)
+             if self.source_name is not None:
+                 source.set('name', self.source_name)
++            if self.source_query is not None:
++                source.set('query', self.source_query)
++            if self.source_config is not None:
++                source.append(etree.Element('config', file=self.source_config))
+             hosts_info = zip(self.source_hosts, self.source_ports)
+             for name, port in hosts_info:
+                 host = etree.Element('host', name=name)
+diff --git a/nova/virt/libvirt/driver.py b/nova/virt/libvirt/driver.py
+index fbd033690a..74dc59ce87 100644
+--- a/nova/virt/libvirt/driver.py
++++ b/nova/virt/libvirt/driver.py
+@@ -180,6 +180,7 @@ libvirt_volume_drivers = [
+     'local=nova.virt.libvirt.volume.volume.LibvirtVolumeDriver',
+     'fake=nova.virt.libvirt.volume.volume.LibvirtFakeVolumeDriver',
+     'rbd=nova.virt.libvirt.volume.net.LibvirtNetVolumeDriver',
++    'vitastor=nova.virt.libvirt.volume.vitastor.LibvirtVitastorVolumeDriver',
+     'nfs=nova.virt.libvirt.volume.nfs.LibvirtNFSVolumeDriver',
+     'smbfs=nova.virt.libvirt.volume.smbfs.LibvirtSMBFSVolumeDriver',
+     'fibre_channel='
+@@ -287,10 +288,10 @@ class LibvirtDriver(driver.ComputeDriver):
+         # This prevents the risk of one test setting a capability
+         # which bleeds over into other tests.
+ 
+-        # LVM and RBD require raw images. If we are not configured to
++        # LVM, RBD, Vitastor require raw images. If we are not configured to
+         # force convert images into raw format, then we _require_ raw
+         # images only.
+-        raw_only = ('rbd', 'lvm')
++        raw_only = ('rbd', 'lvm', 'vitastor')
+         requires_raw_image = (CONF.libvirt.images_type in raw_only and
+                               not CONF.force_raw_images)
+         requires_ploop_image = CONF.libvirt.virt_type == 'parallels'
+@@ -703,12 +704,12 @@ class LibvirtDriver(driver.ComputeDriver):
+         # Some imagebackends are only able to import raw disk images,
+         # and will fail if given any other format. See the bug
+         # https://bugs.launchpad.net/nova/+bug/1816686 for more details.
+-        if CONF.libvirt.images_type in ('rbd',):
++        if CONF.libvirt.images_type in ('rbd', 'vitastor'):
+             if not CONF.force_raw_images:
+                 msg = _("'[DEFAULT]/force_raw_images = False' is not "
+-                        "allowed with '[libvirt]/images_type = rbd'. "
++                        "allowed with '[libvirt]/images_type = rbd' or 'vitastor'. "
+                         "Please check the two configs and if you really "
+-                        "do want to use rbd as images_type, set "
++                        "do want to use rbd or vitastor as images_type, set "
+                         "force_raw_images to True.")
+                 raise exception.InvalidConfiguration(msg)
+ 
+@@ -2165,6 +2166,16 @@ class LibvirtDriver(driver.ComputeDriver):
+                     if connection_info['data'].get('auth_enabled'):
+                         username = connection_info['data']['auth_username']
+                         path = f"rbd:{volume_name}:id={username}"
++                elif connection_info['driver_volume_type'] == 'vitastor':
++                    volume_name = connection_info['data']['name']
++                    path = 'vitastor:image='+volume_name.replace(':', '\\:')
++                    for k in [ 'config_path', 'etcd_address', 'etcd_prefix' ]:
++                        if k in connection_info['data']:
++                            kk = k
++                            if kk == 'etcd_address':
++                                # FIXME use etcd_address in qemu driver
++                                kk = 'etcd_host'
++                            path += ":"+kk.replace('_', '-')+"="+connection_info['data'][k].replace(':', '\\:')
+                 else:
+                     path = 'unknown'
+                     raise exception.DiskNotFound(location='unknown')
+@@ -2440,8 +2451,8 @@ class LibvirtDriver(driver.ComputeDriver):
+ 
+         image_format = CONF.libvirt.snapshot_image_format or source_type
+ 
+-        # NOTE(bfilippov): save lvm and rbd as raw
+-        if image_format == 'lvm' or image_format == 'rbd':
++        # NOTE(bfilippov): save lvm and rbd and vitastor as raw
++        if image_format == 'lvm' or image_format == 'rbd' or image_format == 'vitastor':
+             image_format = 'raw'
+ 
+         metadata = self._create_snapshot_metadata(instance.image_meta,
+@@ -2512,7 +2523,7 @@ class LibvirtDriver(driver.ComputeDriver):
+                               expected_state=task_states.IMAGE_UPLOADING)
+ 
+             # TODO(nic): possibly abstract this out to the root_disk
+-            if source_type == 'rbd' and live_snapshot:
++            if (source_type == 'rbd' or source_type == 'vitastor') and live_snapshot:
+                 # Standard snapshot uses qemu-img convert from RBD which is
+                 # not safe to run with live_snapshot.
+                 live_snapshot = False
+@@ -3715,7 +3726,7 @@ class LibvirtDriver(driver.ComputeDriver):
+         # cleanup rescue volume
+         lvm.remove_volumes([lvmdisk for lvmdisk in self._lvm_disks(instance)
+                                 if lvmdisk.endswith('.rescue')])
+-        if CONF.libvirt.images_type == 'rbd':
++        if CONF.libvirt.images_type == 'rbd' or CONF.libvirt.images_type == 'vitastor':
+             filter_fn = lambda disk: (disk.startswith(instance.uuid) and
+                                       disk.endswith('.rescue'))
+             rbd_utils.RBDDriver().cleanup_volumes(filter_fn)
+@@ -3972,6 +3983,8 @@ class LibvirtDriver(driver.ComputeDriver):
+         # TODO(mikal): there is a bug here if images_type has
+         # changed since creation of the instance, but I am pretty
+         # sure that this bug already exists.
++        if CONF.libvirt.images_type == 'vitastor':
++            return 'vitastor'
+         return 'rbd' if CONF.libvirt.images_type == 'rbd' else 'raw'
+ 
+     @staticmethod
+@@ -4370,10 +4383,10 @@ class LibvirtDriver(driver.ComputeDriver):
+                 finally:
+                     # NOTE(mikal): if the config drive was imported into RBD,
+                     # then we no longer need the local copy
+-                    if CONF.libvirt.images_type == 'rbd':
++                    if CONF.libvirt.images_type == 'rbd' or CONF.libvirt.images_type == 'vitastor':
+                         LOG.info('Deleting local config drive %(path)s '
+-                                 'because it was imported into RBD.',
+-                                 {'path': config_disk_local_path},
++                                 'because it was imported into %(type).',
++                                 {'path': config_disk_local_path, 'type': CONF.libvirt.images_type},
+                                  instance=instance)
+                         os.unlink(config_disk_local_path)
+ 
+diff --git a/nova/virt/libvirt/utils.py b/nova/virt/libvirt/utils.py
+index c1dc34daf4..263965912f 100644
+--- a/nova/virt/libvirt/utils.py
++++ b/nova/virt/libvirt/utils.py
+@@ -399,6 +399,10 @@ def find_disk(guest: libvirt_guest.Guest) -> ty.Tuple[str, ty.Optional[str]]:
+             disk_path = disk.source_name
+             if disk_path:
+                 disk_path = 'rbd:' + disk_path
++        elif not disk_path and disk.source_protocol == 'vitastor':
++            disk_path = disk.source_name
++            if disk_path:
++                disk_path = 'vitastor:' + disk_path
+ 
+     if not disk_path:
+         raise RuntimeError(_("Can't retrieve root device path "
+@@ -417,6 +421,8 @@ def get_disk_type_from_path(path: str) -> ty.Optional[str]:
+         return 'lvm'
+     elif path.startswith('rbd:'):
+         return 'rbd'
++    elif path.startswith('vitastor:'):
++        return 'vitastor'
+     elif (os.path.isdir(path) and
+           os.path.exists(os.path.join(path, "DiskDescriptor.xml"))):
+         return 'ploop'
+diff --git a/nova/virt/libvirt/volume/vitastor.py b/nova/virt/libvirt/volume/vitastor.py
+new file mode 100644
+index 0000000000..0256df62c1
+--- /dev/null
++++ b/nova/virt/libvirt/volume/vitastor.py
+@@ -0,0 +1,75 @@
++# Copyright (c) 2021+, Vitaliy Filippov <vitalif@yourcmc.ru>
++#
++#    Licensed under the Apache License, Version 2.0 (the "License"); you may
++#    not use this file except in compliance with the License. You may obtain
++#    a copy of the License at
++#
++#         http://www.apache.org/licenses/LICENSE-2.0
++#
++#    Unless required by applicable law or agreed to in writing, software
++#    distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
++#    WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
++#    License for the specific language governing permissions and limitations
++#    under the License.
++
++from os_brick import exception as os_brick_exception
++from os_brick import initiator
++from os_brick.initiator import connector
++from oslo_log import log as logging
++
++import nova.conf
++from nova import utils
++from nova.virt.libvirt.volume import volume as libvirt_volume
++
++
++CONF = nova.conf.CONF
++LOG = logging.getLogger(__name__)
++
++
++class LibvirtVitastorVolumeDriver(libvirt_volume.LibvirtBaseVolumeDriver):
++    """Driver to attach Vitastor volumes to libvirt."""
++    def __init__(self, host):
++        super(LibvirtVitastorVolumeDriver, self).__init__(host, is_block_dev=False)
++
++    def connect_volume(self, connection_info, instance):
++        pass
++
++    def disconnect_volume(self, connection_info, instance):
++        pass
++
++    def get_config(self, connection_info, disk_info):
++        """Returns xml for libvirt."""
++        conf = super(LibvirtVitastorVolumeDriver, self).get_config(connection_info, disk_info)
++        conf.source_type = 'network'
++        conf.source_protocol = 'vitastor'
++        conf.source_name = connection_info['data'].get('name')
++        conf.source_query = connection_info['data'].get('etcd_prefix') or None
++        conf.source_config = connection_info['data'].get('config_path') or None
++        conf.source_hosts = []
++        conf.source_ports = []
++        addresses = connection_info['data'].get('etcd_address', '')
++        if addresses:
++            if not isinstance(addresses, list):
++                addresses = addresses.split(',')
++            for addr in addresses:
++                if addr.startswith('https://'):
++                    raise NotImplementedError('Vitastor block driver does not support SSL for etcd communication yet')
++                if addr.startswith('http://'):
++                    addr = addr[7:]
++                addr = addr.rstrip('/')
++                if addr.endswith('/v3'):
++                    addr = addr[0:-3]
++                p = addr.find('/')
++                if p > 0:
++                    raise NotImplementedError('libvirt does not support custom URL paths for Vitastor etcd yet. Use /etc/vitastor/vitastor.conf')
++                p = addr.find(':')
++                port = '2379'
++                if p > 0:
++                    port = addr[p+1:]
++                    addr = addr[0:p]
++                conf.source_hosts.append(addr)
++                conf.source_ports.append(port)
++        return conf
++
++    def extend_volume(self, connection_info, instance, requested_size):
++        raise NotImplementedError

patches/nova-23.diff

@@ -1,5 +1,5 @@
 diff --git a/nova/virt/image/model.py b/nova/virt/image/model.py
-index 971f7e9c07..70ed70d5e2 100644
+index 971f7e9c07..ec3fca72cb 100644
 --- a/nova/virt/image/model.py
 +++ b/nova/virt/image/model.py
 @@ -129,3 +129,22 @@ class RBDImage(Image):
@@ -19,7 +19,7 @@ index 971f7e9c07..70ed70d5e2 100644
 +        :param etcd_prefix: etcd prefix (optional)
 +        :param config_path: path to the configuration (optional)
 +        """
-+        super(RBDImage, self).__init__(FORMAT_RAW)
++        super(VitastorImage, self).__init__(FORMAT_RAW)
 +
 +        self.name = name
 +        self.etcd_address = etcd_address
@@ -48,7 +48,7 @@ index 5358f3766a..ebe3d6effb 100644
  
      info = nova.privsep.qemu.privileged_qemu_img_info(path, format=format)
 diff --git a/nova/virt/libvirt/config.py b/nova/virt/libvirt/config.py
-index f9475776b3..51573fe41d 100644
+index f9475776b3..a2e18aab67 100644
 --- a/nova/virt/libvirt/config.py
 +++ b/nova/virt/libvirt/config.py
 @@ -1060,6 +1060,8 @@ class LibvirtConfigGuestDisk(LibvirtConfigGuestDevice):
@@ -60,18 +60,19 @@ index f9475776b3..51573fe41d 100644
          self.source_name = None
          self.source_hosts = []
          self.source_ports = []
-@@ -1186,7 +1188,8 @@ class LibvirtConfigGuestDisk(LibvirtConfigGuestDevice):
-         elif self.source_type == "mount":
-             dev.append(etree.Element("source", dir=self.source_path))
-         elif self.source_type == "network" and self.source_protocol:
--            source = etree.Element("source", protocol=self.source_protocol)
-+            source = etree.Element("source", protocol=self.source_protocol,
-+                query=self.source_query, config=self.source_config)
+@@ -1189,6 +1191,10 @@ class LibvirtConfigGuestDisk(LibvirtConfigGuestDevice):
+             source = etree.Element("source", protocol=self.source_protocol)
              if self.source_name is not None:
                  source.set('name', self.source_name)
++            if self.source_query is not None:
++                source.set('query', self.source_query)
++            if self.source_config is not None:
++                source.append(etree.Element('config', file=self.source_config))
              hosts_info = zip(self.source_hosts, self.source_ports)
+             for name, port in hosts_info:
+                 host = etree.Element('host', name=name)
 diff --git a/nova/virt/libvirt/driver.py b/nova/virt/libvirt/driver.py
-index 391231c527..34dc60dcdd 100644
+index 391231c527..f38faa1608 100644
 --- a/nova/virt/libvirt/driver.py
 +++ b/nova/virt/libvirt/driver.py
 @@ -179,6 +179,7 @@ VOLUME_DRIVERS = {
@@ -124,7 +125,7 @@ index 391231c527..34dc60dcdd 100644
 +                            if kk == 'etcd_address':
 +                                # FIXME use etcd_address in qemu driver
 +                                kk = 'etcd_host'
-+                            path += ":"+kk+"="+connection_info['data'][k].replace(':', '\\:')
++                            path += ":"+kk.replace('_', '-')+"="+connection_info['data'][k].replace(':', '\\:')
                  else:
                      path = 'unknown'
                      raise exception.DiskNotFound(location='unknown')

patches/pve-qemu-5.1-vitastor.patch

@@ -0,0 +1,175 @@
+Index: pve-qemu-kvm-5.1.0/qapi/block-core.json
+===================================================================
+--- pve-qemu-kvm-5.1.0.orig/qapi/block-core.json
++++ pve-qemu-kvm-5.1.0/qapi/block-core.json
+@@ -3041,7 +3041,7 @@
+             'luks', 'nbd', 'nfs', 'null-aio', 'null-co', 'nvme', 'parallels',
+             'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'rbd',
+             { 'name': 'replication', 'if': 'defined(CONFIG_REPLICATION)' },
+-            'sheepdog', 'pbs',
++            'sheepdog', 'pbs', 'vitastor',
+             'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat' ] }
+ 
+ ##
+@@ -3889,6 +3889,28 @@
+             '*tag': 'str' } }
+ 
+ ##
++# @BlockdevOptionsVitastor:
++#
++# Driver specific block device options for vitastor
++#
++# @image:       Image name
++# @inode:       Inode number
++# @pool:        Pool ID
++# @size:        Desired image size in bytes
++# @config-path: Path to Vitastor configuration
++# @etcd-host:   etcd connection address(es)
++# @etcd-prefix: etcd key/value prefix
++##
++{ 'struct': 'BlockdevOptionsVitastor',
++  'data': { '*inode': 'uint64',
++            '*pool': 'uint64',
++            '*size': 'uint64',
++            '*image': 'str',
++            '*config-path': 'str',
++            '*etcd-host': 'str',
++            '*etcd-prefix': 'str' } }
++
++##
+ # @ReplicationMode:
+ #
+ # An enumeration of replication modes.
+@@ -4234,6 +4256,7 @@
+       'replication': { 'type': 'BlockdevOptionsReplication',
+                        'if': 'defined(CONFIG_REPLICATION)' },
+       'sheepdog':   'BlockdevOptionsSheepdog',
++      'vitastor':   'BlockdevOptionsVitastor',
+       'ssh':        'BlockdevOptionsSsh',
+       'throttle':   'BlockdevOptionsThrottle',
+       'vdi':        'BlockdevOptionsGenericFormat',
+@@ -4623,6 +4646,17 @@
+             '*cluster-size' :   'size' } }
+ 
+ ##
++# @BlockdevCreateOptionsVitastor:
++#
++# Driver specific image creation options for Vitastor.
++#
++# @size: Size of the virtual disk in bytes
++##
++{ 'struct': 'BlockdevCreateOptionsVitastor',
++  'data': { 'location':         'BlockdevOptionsVitastor',
++            'size':             'size' } }
++
++##
+ # @BlockdevVmdkSubformat:
+ #
+ # Subformat options for VMDK images
+@@ -4884,6 +4918,7 @@
+       'qed':            'BlockdevCreateOptionsQed',
+       'rbd':            'BlockdevCreateOptionsRbd',
+       'sheepdog':       'BlockdevCreateOptionsSheepdog',
++      'vitastor':       'BlockdevCreateOptionsVitastor',
+       'ssh':            'BlockdevCreateOptionsSsh',
+       'vdi':            'BlockdevCreateOptionsVdi',
+       'vhdx':           'BlockdevCreateOptionsVhdx',
+Index: pve-qemu-kvm-5.1.0/configure
+===================================================================
+--- pve-qemu-kvm-5.1.0.orig/configure
++++ pve-qemu-kvm-5.1.0/configure
+@@ -446,6 +446,7 @@ trace_backends="log"
+ trace_file="trace"
+ spice=""
+ rbd=""
++vitastor=""
+ smartcard=""
+ libusb=""
+ usb_redir=""
+@@ -1383,6 +1384,10 @@ for opt do
+   ;;
+   --enable-rbd) rbd="yes"
+   ;;
++  --disable-vitastor) vitastor="no"
++  ;;
++  --enable-vitastor) vitastor="yes"
++  ;;
+   --disable-xfsctl) xfs="no"
+   ;;
+   --enable-xfsctl) xfs="yes"
+@@ -1901,6 +1906,7 @@ disabled with --disable-FEATURE, default
+   vhost-vdpa      vhost-vdpa kernel backend support
+   spice           spice
+   rbd             rados block device (rbd)
++  vitastor        vitastor block device
+   libiscsi        iscsi support
+   libnfs          nfs support
+   smartcard       smartcard support (libcacard)
+@@ -4234,6 +4240,27 @@ EOF
+ fi
+ 
+ ##########################################
++# vitastor probe
++if test "$vitastor" != "no" ; then
++  cat > $TMPC <<EOF
++#include <vitastor_c.h>
++int main(void) {
++  vitastor_c_create_qemu(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
++  return 0;
++}
++EOF
++  vitastor_libs="-lvitastor_client"
++  if compile_prog "" "$vitastor_libs" ; then
++    vitastor=yes
++  else
++    if test "$vitastor" = "yes" ; then
++      feature_not_found "vitastor block device" "Install vitastor-client-dev"
++    fi
++    vitastor=no
++  fi
++fi
++
++##########################################
+ # libssh probe
+ if test "$libssh" != "no" ; then
+   if $pkg_config --exists libssh; then
+@@ -6969,6 +6996,7 @@ echo "Trace output file $trace_file-<pid
+ fi
+ echo "spice support     $spice $(echo_version $spice $spice_protocol_version/$spice_server_version)"
+ echo "rbd support       $rbd"
++echo "vitastor support  $vitastor"
+ echo "xfsctl support    $xfs"
+ echo "smartcard support $smartcard"
+ echo "libusb            $libusb"
+@@ -7644,6 +7672,10 @@ if test "$rbd" = "yes" ; then
+   echo "RBD_CFLAGS=$rbd_cflags" >> $config_host_mak
+   echo "RBD_LIBS=$rbd_libs" >> $config_host_mak
+ fi
++if test "$vitastor" = "yes" ; then
++  echo "CONFIG_VITASTOR=y" >> $config_host_mak
++  echo "VITASTOR_LIBS=$vitastor_libs" >> $config_host_mak
++fi
+ 
+ echo "CONFIG_COROUTINE_BACKEND=$coroutine" >> $config_host_mak
+ if test "$coroutine_pool" = "yes" ; then
+Index: pve-qemu-kvm-5.1.0/block/Makefile.objs
+===================================================================
+--- pve-qemu-kvm-5.1.0.orig/block/Makefile.objs
++++ pve-qemu-kvm-5.1.0/block/Makefile.objs
+@@ -32,6 +32,7 @@ block-obj-$(if $(CONFIG_LIBISCSI),y,n) +
+ block-obj-$(CONFIG_LIBNFS) += nfs.o
+ block-obj-$(CONFIG_CURL) += curl.o
+ block-obj-$(CONFIG_RBD) += rbd.o
++block-obj-$(CONFIG_VITASTOR) += vitastor.o
+ block-obj-$(CONFIG_GLUSTERFS) += gluster.o
+ block-obj-$(CONFIG_LIBSSH) += ssh.o
+ block-obj-y += backup-dump.o
+@@ -61,6 +62,8 @@ curl.o-cflags      := $(CURL_CFLAGS)
+ curl.o-libs        := $(CURL_LIBS)
+ rbd.o-cflags       := $(RBD_CFLAGS)
+ rbd.o-libs         := $(RBD_LIBS)
++vitastor.o-cflags  := $(VITASTOR_CFLAGS)
++vitastor.o-libs    := $(VITASTOR_LIBS)
+ gluster.o-cflags   := $(GLUSTERFS_CFLAGS)
+ gluster.o-libs     := $(GLUSTERFS_LIBS)
+ ssh.o-cflags       := $(LIBSSH_CFLAGS)

patches/pve-qemu-5.2-vitastor.patch

@@ -0,0 +1,181 @@
+Index: pve-qemu-kvm-5.2.0/qapi/block-core.json
+===================================================================
+--- pve-qemu-kvm-5.2.0.orig/qapi/block-core.json
++++ pve-qemu-kvm-5.2.0/qapi/block-core.json
+@@ -3076,7 +3076,7 @@
+             'luks', 'nbd', 'nfs', 'null-aio', 'null-co', 'nvme', 'parallels',
+             'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'rbd',
+             { 'name': 'replication', 'if': 'defined(CONFIG_REPLICATION)' },
+-            'sheepdog', 'pbs',
++            'sheepdog', 'pbs', 'vitastor',
+             'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat' ] }
+ 
+ ##
+@@ -3924,6 +3924,28 @@
+             '*tag': 'str' } }
+ 
+ ##
++# @BlockdevOptionsVitastor:
++#
++# Driver specific block device options for vitastor
++#
++# @image:       Image name
++# @inode:       Inode number
++# @pool:        Pool ID
++# @size:        Desired image size in bytes
++# @config-path: Path to Vitastor configuration
++# @etcd-host:   etcd connection address(es)
++# @etcd-prefix: etcd key/value prefix
++##
++{ 'struct': 'BlockdevOptionsVitastor',
++  'data': { '*inode': 'uint64',
++            '*pool': 'uint64',
++            '*size': 'uint64',
++            '*image': 'str',
++            '*config-path': 'str',
++            '*etcd-host': 'str',
++            '*etcd-prefix': 'str' } }
++
++##
+ # @ReplicationMode:
+ #
+ # An enumeration of replication modes.
+@@ -4272,6 +4294,7 @@
+       'replication': { 'type': 'BlockdevOptionsReplication',
+                        'if': 'defined(CONFIG_REPLICATION)' },
+       'sheepdog':   'BlockdevOptionsSheepdog',
++      'vitastor':   'BlockdevOptionsVitastor',
+       'ssh':        'BlockdevOptionsSsh',
+       'throttle':   'BlockdevOptionsThrottle',
+       'vdi':        'BlockdevOptionsGenericFormat',
+@@ -4662,6 +4685,17 @@
+             '*cluster-size' :   'size' } }
+ 
+ ##
++# @BlockdevCreateOptionsVitastor:
++#
++# Driver specific image creation options for Vitastor.
++#
++# @size: Size of the virtual disk in bytes
++##
++{ 'struct': 'BlockdevCreateOptionsVitastor',
++  'data': { 'location':         'BlockdevOptionsVitastor',
++            'size':             'size' } }
++
++##
+ # @BlockdevVmdkSubformat:
+ #
+ # Subformat options for VMDK images
+@@ -4923,6 +4957,7 @@
+       'qed':            'BlockdevCreateOptionsQed',
+       'rbd':            'BlockdevCreateOptionsRbd',
+       'sheepdog':       'BlockdevCreateOptionsSheepdog',
++      'vitastor':       'BlockdevCreateOptionsVitastor',
+       'ssh':            'BlockdevCreateOptionsSsh',
+       'vdi':            'BlockdevCreateOptionsVdi',
+       'vhdx':           'BlockdevCreateOptionsVhdx',
+Index: pve-qemu-kvm-5.2.0/block/meson.build
+===================================================================
+--- pve-qemu-kvm-5.2.0.orig/block/meson.build
++++ pve-qemu-kvm-5.2.0/block/meson.build
+@@ -89,6 +89,7 @@ foreach m : [
+   ['CONFIG_LIBNFS', 'nfs', libnfs, 'nfs.c'],
+   ['CONFIG_LIBSSH', 'ssh', libssh, 'ssh.c'],
+   ['CONFIG_RBD', 'rbd', rbd, 'rbd.c'],
++  ['CONFIG_VITASTOR', 'vitastor', vitastor, 'vitastor.c'],
+ ]
+   if config_host.has_key(m[0])
+     if enable_modules
+Index: pve-qemu-kvm-5.2.0/configure
+===================================================================
+--- pve-qemu-kvm-5.2.0.orig/configure
++++ pve-qemu-kvm-5.2.0/configure
+@@ -372,6 +372,7 @@ trace_backends="log"
+ trace_file="trace"
+ spice=""
+ rbd=""
++vitastor=""
+ smartcard=""
+ u2f="auto"
+ libusb=""
+@@ -1264,6 +1265,10 @@ for opt do
+   ;;
+   --enable-rbd) rbd="yes"
+   ;;
++  --disable-vitastor) vitastor="no"
++  ;;
++  --enable-vitastor) vitastor="yes"
++  ;;
+   --disable-xfsctl) xfs="no"
+   ;;
+   --enable-xfsctl) xfs="yes"
+@@ -1807,6 +1812,7 @@ disabled with --disable-FEATURE, default
+   vhost-vdpa      vhost-vdpa kernel backend support
+   spice           spice
+   rbd             rados block device (rbd)
++  vitastor        vitastor block device
+   libiscsi        iscsi support
+   libnfs          nfs support
+   smartcard       smartcard support (libcacard)
+@@ -3700,6 +3706,27 @@ EOF
+ fi
+ 
+ ##########################################
++# vitastor probe
++if test "$vitastor" != "no" ; then
++  cat > $TMPC <<EOF
++#include <vitastor_c.h>
++int main(void) {
++  vitastor_c_create_qemu(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
++  return 0;
++}
++EOF
++  vitastor_libs="-lvitastor_client"
++  if compile_prog "" "$vitastor_libs" ; then
++    vitastor=yes
++  else
++    if test "$vitastor" = "yes" ; then
++      feature_not_found "vitastor block device" "Install vitastor-client-dev"
++    fi
++    vitastor=no
++  fi
++fi
++
++##########################################
+ # libssh probe
+ if test "$libssh" != "no" ; then
+   if $pkg_config --exists libssh; then
+@@ -6437,6 +6464,10 @@ if test "$rbd" = "yes" ; then
+   echo "CONFIG_RBD=y" >> $config_host_mak
+   echo "RBD_LIBS=$rbd_libs" >> $config_host_mak
+ fi
++if test "$vitastor" = "yes" ; then
++  echo "CONFIG_VITASTOR=y" >> $config_host_mak
++  echo "VITASTOR_LIBS=$vitastor_libs" >> $config_host_mak
++fi
+ 
+ echo "CONFIG_COROUTINE_BACKEND=$coroutine" >> $config_host_mak
+ if test "$coroutine_pool" = "yes" ; then
+Index: pve-qemu-kvm-5.2.0/meson.build
+===================================================================
+--- pve-qemu-kvm-5.2.0.orig/meson.build
++++ pve-qemu-kvm-5.2.0/meson.build
+@@ -596,6 +596,10 @@ rbd = not_found
+ if 'CONFIG_RBD' in config_host
+   rbd = declare_dependency(link_args: config_host['RBD_LIBS'].split())
+ endif
++vitastor = not_found
++if 'CONFIG_VITASTOR' in config_host
++  vitastor = declare_dependency(link_args: config_host['VITASTOR_LIBS'].split())
++endif
+ glusterfs = not_found
+ if 'CONFIG_GLUSTERFS' in config_host
+   glusterfs = declare_dependency(compile_args: config_host['GLUSTERFS_CFLAGS'].split(),
+@@ -2151,6 +2155,7 @@ endif
+ # TODO: add back protocol and server version
+ summary_info += {'spice support':     config_host.has_key('CONFIG_SPICE')}
+ summary_info += {'rbd support':       config_host.has_key('CONFIG_RBD')}
++summary_info += {'vitastor support':  config_host.has_key('CONFIG_VITASTOR')}
+ summary_info += {'xfsctl support':    config_host.has_key('CONFIG_XFS')}
+ summary_info += {'smartcard support': config_host.has_key('CONFIG_SMARTCARD')}
+ summary_info += {'U2F support':       u2f.found()}

patches/pve-qemu-6.1-vitastor.patch

@@ -0,0 +1,188 @@
+Index: pve-qemu-kvm-6.1.0/qapi/block-core.json
+===================================================================
+--- pve-qemu-kvm-6.1.0.orig/qapi/block-core.json
++++ pve-qemu-kvm-6.1.0/qapi/block-core.json
+@@ -3084,7 +3084,7 @@
+             'preallocate', 'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'rbd',
+             { 'name': 'replication', 'if': 'defined(CONFIG_REPLICATION)' },
+             'pbs',
+-            'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat' ] }
++            'ssh', 'throttle', 'vdi', 'vhdx', 'vitastor', 'vmdk', 'vpc', 'vvfat' ] }
+ 
+ ##
+ # @BlockdevOptionsFile:
+@@ -4020,6 +4020,28 @@
+             '*server': ['InetSocketAddressBase'] } }
+ 
+ ##
++# @BlockdevOptionsVitastor:
++#
++# Driver specific block device options for vitastor
++#
++# @image:       Image name
++# @inode:       Inode number
++# @pool:        Pool ID
++# @size:        Desired image size in bytes
++# @config-path: Path to Vitastor configuration
++# @etcd-host:   etcd connection address(es)
++# @etcd-prefix: etcd key/value prefix
++##
++{ 'struct': 'BlockdevOptionsVitastor',
++  'data': { '*inode': 'uint64',
++            '*pool': 'uint64',
++            '*size': 'uint64',
++            '*image': 'str',
++            '*config-path': 'str',
++            '*etcd-host': 'str',
++            '*etcd-prefix': 'str' } }
++
++##
+ # @ReplicationMode:
+ #
+ # An enumeration of replication modes.
+@@ -4392,6 +4414,7 @@
+       'throttle':   'BlockdevOptionsThrottle',
+       'vdi':        'BlockdevOptionsGenericFormat',
+       'vhdx':       'BlockdevOptionsGenericFormat',
++      'vitastor':   'BlockdevOptionsVitastor',
+       'vmdk':       'BlockdevOptionsGenericCOWFormat',
+       'vpc':        'BlockdevOptionsGenericFormat',
+       'vvfat':      'BlockdevOptionsVVFAT'
+@@ -4782,6 +4805,17 @@
+             '*encrypt' :        'RbdEncryptionCreateOptions' } }
+ 
+ ##
++# @BlockdevCreateOptionsVitastor:
++#
++# Driver specific image creation options for Vitastor.
++#
++# @size: Size of the virtual disk in bytes
++##
++{ 'struct': 'BlockdevCreateOptionsVitastor',
++  'data': { 'location':         'BlockdevOptionsVitastor',
++            'size':             'size' } }
++
++##
+ # @BlockdevVmdkSubformat:
+ #
+ # Subformat options for VMDK images
+@@ -4977,6 +5011,7 @@
+       'ssh':            'BlockdevCreateOptionsSsh',
+       'vdi':            'BlockdevCreateOptionsVdi',
+       'vhdx':           'BlockdevCreateOptionsVhdx',
++      'vitastor':       'BlockdevCreateOptionsVitastor',
+       'vmdk':           'BlockdevCreateOptionsVmdk',
+       'vpc':            'BlockdevCreateOptionsVpc'
+   } }
+Index: pve-qemu-kvm-6.1.0/block/meson.build
+===================================================================
+--- pve-qemu-kvm-6.1.0.orig/block/meson.build
++++ pve-qemu-kvm-6.1.0/block/meson.build
+@@ -91,6 +91,7 @@ foreach m : [
+   [libnfs, 'nfs', files('nfs.c')],
+   [libssh, 'ssh', files('ssh.c')],
+   [rbd, 'rbd', files('rbd.c')],
++  [vitastor, 'vitastor', files('vitastor.c')],
+ ]
+   if m[0].found()
+     module_ss = ss.source_set()
+Index: pve-qemu-kvm-6.1.0/configure
+===================================================================
+--- pve-qemu-kvm-6.1.0.orig/configure
++++ pve-qemu-kvm-6.1.0/configure
+@@ -375,6 +375,7 @@ trace_file="trace"
+ spice="$default_feature"
+ spice_protocol="auto"
+ rbd="auto"
++vitastor="auto"
+ smartcard="auto"
+ u2f="auto"
+ libusb="auto"
+@@ -1293,6 +1294,10 @@ for opt do
+   ;;
+   --enable-rbd) rbd="enabled"
+   ;;
++  --disable-vitastor) vitastor="disabled"
++  ;;
++  --enable-vitastor) vitastor="enabled"
++  ;;
+   --disable-xfsctl) xfs="no"
+   ;;
+   --enable-xfsctl) xfs="yes"
+@@ -1921,6 +1926,7 @@ disabled with --disable-FEATURE, default
+   spice           spice
+   spice-protocol  spice-protocol
+   rbd             rados block device (rbd)
++  vitastor        vitastor block device
+   libiscsi        iscsi support
+   libnfs          nfs support
+   smartcard       smartcard support (libcacard)
+@@ -5211,7 +5217,7 @@ if test "$skip_meson" = no; then
+         -Dcapstone=$capstone -Dslirp=$slirp -Dfdt=$fdt -Dbrlapi=$brlapi \
+         -Dcurl=$curl -Dglusterfs=$glusterfs -Dbzip2=$bzip2 -Dlibiscsi=$libiscsi \
+         -Dlibnfs=$libnfs -Diconv=$iconv -Dcurses=$curses -Dlibudev=$libudev\
+-        -Drbd=$rbd -Dlzo=$lzo -Dsnappy=$snappy -Dlzfse=$lzfse -Dlibxml2=$libxml2 \
++        -Drbd=$rbd -Dvitastor=$vitastor -Dlzo=$lzo -Dsnappy=$snappy -Dlzfse=$lzfse -Dlibxml2=$libxml2 \
+         -Dlibdaxctl=$libdaxctl -Dlibpmem=$libpmem -Dlinux_io_uring=$linux_io_uring \
+         -Dgnutls=$gnutls -Dnettle=$nettle -Dgcrypt=$gcrypt -Dauth_pam=$auth_pam \
+         -Dzstd=$zstd -Dseccomp=$seccomp -Dvirtfs=$virtfs -Dcap_ng=$cap_ng \
+Index: pve-qemu-kvm-6.1.0/meson.build
+===================================================================
+--- pve-qemu-kvm-6.1.0.orig/meson.build
++++ pve-qemu-kvm-6.1.0/meson.build
+@@ -729,6 +729,26 @@ if not get_option('rbd').auto() or have_
+   endif
+ endif
+ 
++vitastor = not_found
++if not get_option('vitastor').auto() or have_block
++  libvitastor_client = cc.find_library('vitastor_client', has_headers: ['vitastor_c.h'],
++    required: get_option('vitastor'), kwargs: static_kwargs)
++  if libvitastor_client.found()
++    if cc.links('''
++      #include <vitastor_c.h>
++      int main(void) {
++        vitastor_c_create_qemu(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
++        return 0;
++      }''', dependencies: libvitastor_client)
++      vitastor = declare_dependency(dependencies: libvitastor_client)
++    elif get_option('vitastor').enabled()
++      error('could not link libvitastor_client')
++    else
++      warning('could not link libvitastor_client, disabling')
++    endif
++  endif
++endif
++
+ glusterfs = not_found
+ glusterfs_ftruncate_has_stat = false
+ glusterfs_iocb_has_stat = false
+@@ -1268,6 +1288,7 @@ config_host_data.set('CONFIG_LIBNFS', li
+ config_host_data.set('CONFIG_LINUX_IO_URING', linux_io_uring.found())
+ config_host_data.set('CONFIG_LIBPMEM', libpmem.found())
+ config_host_data.set('CONFIG_RBD', rbd.found())
++config_host_data.set('CONFIG_VITASTOR', vitastor.found())
+ config_host_data.set('CONFIG_SDL', sdl.found())
+ config_host_data.set('CONFIG_SDL_IMAGE', sdl_image.found())
+ config_host_data.set('CONFIG_SECCOMP', seccomp.found())
+@@ -3087,6 +3108,7 @@ summary_info += {'bpf support': libbpf.f
+ # TODO: add back protocol and server version
+ summary_info += {'spice support':     config_host.has_key('CONFIG_SPICE')}
+ summary_info += {'rbd support':       rbd.found()}
++summary_info += {'vitastor support':  vitastor.found()}
+ summary_info += {'xfsctl support':    config_host.has_key('CONFIG_XFS')}
+ summary_info += {'smartcard support': cacard.found()}
+ summary_info += {'U2F support':       u2f.found()}
+Index: pve-qemu-kvm-6.1.0/meson_options.txt
+===================================================================
+--- pve-qemu-kvm-6.1.0.orig/meson_options.txt
++++ pve-qemu-kvm-6.1.0/meson_options.txt
+@@ -102,6 +102,8 @@ option('lzo', type : 'feature', value :
+        description: 'lzo compression support')
+ option('rbd', type : 'feature', value : 'auto',
+        description: 'Ceph block device driver')
++option('vitastor', type : 'feature', value : 'auto',
++       description: 'Vitastor block device driver')
+ option('gtk', type : 'feature', value : 'auto',
+        description: 'GTK+ user interface')
+ option('sdl', type : 'feature', value : 'auto',

patches/qemu-3.1-vitastor.patch

@@ -1,7 +1,107 @@
-Index: qemu-3.1+dfsg/qapi/block-core.json
-===================================================================
---- qemu-3.1+dfsg.orig/qapi/block-core.json
-+++ qemu-3.1+dfsg/qapi/block-core.json
+diff --git a/block/Makefile.objs b/block/Makefile.objs
+index 46d585cfd0..62222f25fe 100644
+--- a/block/Makefile.objs
++++ b/block/Makefile.objs
+@@ -29,6 +29,7 @@ block-obj-$(if $(CONFIG_LIBISCSI),y,n) += iscsi-opts.o
+ block-obj-$(CONFIG_LIBNFS) += nfs.o
+ block-obj-$(CONFIG_CURL) += curl.o
+ block-obj-$(CONFIG_RBD) += rbd.o
++block-obj-$(CONFIG_VITASTOR) += vitastor.o
+ block-obj-$(CONFIG_GLUSTERFS) += gluster.o
+ block-obj-$(CONFIG_VXHS) += vxhs.o
+ block-obj-$(CONFIG_LIBSSH2) += ssh.o
+@@ -49,6 +50,8 @@ curl.o-cflags      := $(CURL_CFLAGS)
+ curl.o-libs        := $(CURL_LIBS)
+ rbd.o-cflags       := $(RBD_CFLAGS)
+ rbd.o-libs         := $(RBD_LIBS)
++vitastor.o-cflags  := $(VITASTOR_CFLAGS)
++vitastor.o-libs    := $(VITASTOR_LIBS)
+ gluster.o-cflags   := $(GLUSTERFS_CFLAGS)
+ gluster.o-libs     := $(GLUSTERFS_LIBS)
+ vxhs.o-libs        := $(VXHS_LIBS)
+diff --git a/configure b/configure
+index 1c9f6090e8..25ef89c33a 100755
+--- a/configure
++++ b/configure
+@@ -422,6 +422,7 @@ trace_backends="log"
+ trace_file="trace"
+ spice=""
+ rbd=""
++vitastor=""
+ smartcard=""
+ libusb=""
+ usb_redir=""
+@@ -1282,6 +1283,10 @@ for opt do
+   ;;
+   --enable-rbd) rbd="yes"
+   ;;
++  --disable-vitastor) vitastor="no"
++  ;;
++  --enable-vitastor) vitastor="yes"
++  ;;
+   --disable-xfsctl) xfs="no"
+   ;;
+   --enable-xfsctl) xfs="yes"
+@@ -1737,6 +1742,7 @@ disabled with --disable-FEATURE, default is enabled if available:
+   vhost-crypto    vhost-crypto acceleration support
+   spice           spice
+   rbd             rados block device (rbd)
++  vitastor        vitastor block device
+   libiscsi        iscsi support
+   libnfs          nfs support
+   smartcard       smartcard support (libcacard)
+@@ -3722,6 +3728,27 @@ EOF
+   fi
+ fi
+ 
++##########################################
++# vitastor probe
++if test "$vitastor" != "no" ; then
++  cat > $TMPC <<EOF
++#include <vitastor_c.h>
++int main(void) {
++  vitastor_c_create_qemu(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
++  return 0;
++}
++EOF
++  vitastor_libs="-lvitastor_client"
++  if compile_prog "" "$vitastor_libs" ; then
++    vitastor=yes
++  else
++    if test "$vitastor" = "yes" ; then
++      feature_not_found "vitastor block device" "Install vitastor-client-dev"
++    fi
++    vitastor=no
++  fi
++fi
++
+ ##########################################
+ # libssh2 probe
+ min_libssh2_version=1.2.8
+@@ -6109,6 +6136,7 @@ echo "Trace output file $trace_file-<pid>"
+ fi
+ echo "spice support     $spice $(echo_version $spice $spice_protocol_version/$spice_server_version)"
+ echo "rbd support       $rbd"
++echo "vitastor support  $vitastor"
+ echo "xfsctl support    $xfs"
+ echo "smartcard support $smartcard"
+ echo "libusb            $libusb"
+@@ -6694,6 +6722,11 @@ if test "$rbd" = "yes" ; then
+   echo "RBD_CFLAGS=$rbd_cflags" >> $config_host_mak
+   echo "RBD_LIBS=$rbd_libs" >> $config_host_mak
+ fi
++if test "$vitastor" = "yes" ; then
++  echo "CONFIG_VITASTOR=m" >> $config_host_mak
++  echo "VITASTOR_CFLAGS=$vitastor_cflags" >> $config_host_mak
++  echo "VITASTOR_LIBS=$vitastor_libs" >> $config_host_mak
++fi
+ 
+ echo "CONFIG_COROUTINE_BACKEND=$coroutine" >> $config_host_mak
+ if test "$coroutine_pool" = "yes" ; then
+diff --git a/qapi/block-core.json b/qapi/block-core.json
+index d4fe710836..dbad3327b3 100644
+--- a/qapi/block-core.json
++++ b/qapi/block-core.json
 @@ -2617,7 +2617,7 @@
  ##
  { 'enum': 'BlockdevDriver',
@@ -11,10 +111,11 @@ Index: qemu-3.1+dfsg/qapi/block-core.json
              'host_cdrom', 'host_device', 'http', 'https', 'iscsi', 'luks',
              'nbd', 'nfs', 'null-aio', 'null-co', 'nvme', 'parallels', 'qcow',
              'qcow2', 'qed', 'quorum', 'raw', 'rbd', 'replication', 'sheepdog',
-@@ -3367,6 +3367,28 @@
+@@ -3366,6 +3366,28 @@
+             '*snap-id': 'uint32',
              '*tag': 'str' } }
  
- ##
++##
 +# @BlockdevOptionsVitastor:
 +#
 +# Driver specific block device options for vitastor
@@ -23,24 +124,23 @@ Index: qemu-3.1+dfsg/qapi/block-core.json
 +# @inode:       Inode number
 +# @pool:        Pool ID
 +# @size:        Desired image size in bytes
-+# @config_path: Path to Vitastor configuration
-+# @etcd_host:   etcd connection address(es)
-+# @etcd_prefix: etcd key/value prefix
++# @config-path: Path to Vitastor configuration
++# @etcd-host:   etcd connection address(es)
++# @etcd-prefix: etcd key/value prefix
 +##
 +{ 'struct': 'BlockdevOptionsVitastor',
 +  'data': { '*inode': 'uint64',
 +            '*pool': 'uint64',
 +            '*size': 'uint64',
 +            '*image': 'str',
-+            '*config_path': 'str',
-+            '*etcd_host': 'str',
-+            '*etcd_prefix': 'str' } }
++            '*config-path': 'str',
++            '*etcd-host': 'str',
++            '*etcd-prefix': 'str' } }
 +
-+##
+ ##
  # @ReplicationMode:
  #
- # An enumeration of replication modes.
-@@ -3713,6 +3731,7 @@
+@@ -3713,6 +3735,7 @@
        'rbd':        'BlockdevOptionsRbd',
        'replication':'BlockdevOptionsReplication',
        'sheepdog':   'BlockdevOptionsSheepdog',
@@ -48,10 +148,11 @@ Index: qemu-3.1+dfsg/qapi/block-core.json
        'ssh':        'BlockdevOptionsSsh',
        'throttle':   'BlockdevOptionsThrottle',
        'vdi':        'BlockdevOptionsGenericFormat',
-@@ -4158,6 +4177,17 @@
+@@ -4157,6 +4180,17 @@
+             '*subformat':           'BlockdevVhdxSubformat',
              '*block-state-zero':    'bool' } }
  
- ##
++##
 +# @BlockdevCreateOptionsVitastor:
 +#
 +# Driver specific image creation options for Vitastor.
@@ -62,11 +163,10 @@ Index: qemu-3.1+dfsg/qapi/block-core.json
 +  'data': { 'location':         'BlockdevOptionsVitastor',
 +            'size':             'size' } }
 +
-+##
+ ##
  # @BlockdevVpcSubformat:
  #
- # @dynamic: Growing image file
-@@ -4212,6 +4242,7 @@
+@@ -4212,6 +4246,7 @@
        'qed':            'BlockdevCreateOptionsQed',
        'rbd':            'BlockdevCreateOptionsRbd',
        'sheepdog':       'BlockdevCreateOptionsSheepdog',
@@ -74,15 +174,3 @@ Index: qemu-3.1+dfsg/qapi/block-core.json
        'ssh':            'BlockdevCreateOptionsSsh',
        'vdi':            'BlockdevCreateOptionsVdi',
        'vhdx':           'BlockdevCreateOptionsVhdx',
-Index: qemu-3.1+dfsg/scripts/modules/module_block.py
-===================================================================
---- qemu-3.1+dfsg.orig/scripts/modules/module_block.py
-+++ qemu-3.1+dfsg/scripts/modules/module_block.py
-@@ -88,6 +88,7 @@ def print_bottom(fheader):
- output_file = sys.argv[1]
- with open(output_file, 'w') as fheader:
-     print_top(fheader)
-+    add_module(fheader, "vitastor", "vitastor", "vitastor")
- 
-     for filename in sys.argv[2:]:
-         if os.path.isfile(filename):

patches/qemu-4.2-vitastor.patch

@@ -1,8 +1,105 @@
-Index: qemu/qapi/block-core.json
-===================================================================
---- qemu.orig/qapi/block-core.json	2020-11-07 22:57:38.932613674 +0000
-+++ qemu.orig/qapi/block-core.json	2020-11-07 22:59:49.890722862 +0000
-@@ -2907,7 +2907,7 @@
+diff -NaurpbB qemu-4.2.0/block/Makefile.objs qemu-4.2.0-vitastor/block/Makefile.objs
+--- qemu-4.2.0/block/Makefile.objs	2019-12-12 18:20:47.000000000 +0000
++++ qemu-4.2.0-vitastor/block/Makefile.objs	2021-12-01 21:28:47.342341760 +0000
+@@ -29,6 +29,7 @@ block-obj-$(if $(CONFIG_LIBISCSI),y,n) +
+ block-obj-$(CONFIG_LIBNFS) += nfs.o
+ block-obj-$(CONFIG_CURL) += curl.o
+ block-obj-$(CONFIG_RBD) += rbd.o
++block-obj-$(CONFIG_VITASTOR) += vitastor.o
+ block-obj-$(CONFIG_GLUSTERFS) += gluster.o
+ block-obj-$(CONFIG_VXHS) += vxhs.o
+ block-obj-$(CONFIG_LIBSSH) += ssh.o
+@@ -53,6 +54,8 @@ curl.o-cflags      := $(CURL_CFLAGS)
+ curl.o-libs        := $(CURL_LIBS)
+ rbd.o-cflags       := $(RBD_CFLAGS)
+ rbd.o-libs         := $(RBD_LIBS)
++vitastor.o-cflags  := $(VITASTOR_CFLAGS)
++vitastor.o-libs    := $(VITASTOR_LIBS)
+ gluster.o-cflags   := $(GLUSTERFS_CFLAGS)
+ gluster.o-libs     := $(GLUSTERFS_LIBS)
+ vxhs.o-libs        := $(VXHS_LIBS)
+diff -NaurpbB qemu-4.2.0/configure qemu-4.2.0-vitastor/configure
+--- qemu-4.2.0/configure	2019-12-12 18:20:47.000000000 +0000
++++ qemu-4.2.0-vitastor/configure	2021-12-01 21:30:24.605237562 +0000
+@@ -435,6 +435,7 @@ trace_backends="log"
+ trace_file="trace"
+ spice=""
+ rbd=""
++vitastor=""
+ smartcard=""
+ libusb=""
+ usb_redir=""
+@@ -1312,6 +1313,10 @@ for opt do
+   ;;
+   --enable-rbd) rbd="yes"
+   ;;
++  --disable-vitastor) vitastor="no"
++  ;;
++  --enable-vitastor) vitastor="yes"
++  ;;
+   --disable-xfsctl) xfs="no"
+   ;;
+   --enable-xfsctl) xfs="yes"
+@@ -1782,6 +1787,7 @@ disabled with --disable-FEATURE, default
+   vhost-user      vhost-user backend support
+   spice           spice
+   rbd             rados block device (rbd)
++  vitastor        vitastor block device
+   libiscsi        iscsi support
+   libnfs          nfs support
+   smartcard       smartcard support (libcacard)
+@@ -3980,6 +3986,27 @@ EOF
+ fi
+ 
+ ##########################################
++# vitastor probe
++if test "$vitastor" != "no" ; then
++  cat > $TMPC <<EOF
++#include <vitastor_c.h>
++int main(void) {
++  vitastor_c_create_qemu(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
++  return 0;
++}
++EOF
++  vitastor_libs="-lvitastor_client"
++  if compile_prog "" "$vitastor_libs" ; then
++    vitastor=yes
++  else
++    if test "$vitastor" = "yes" ; then
++      feature_not_found "vitastor block device" "Install vitastor-client-dev"
++    fi
++    vitastor=no
++  fi
++fi
++
++##########################################
+ # libssh probe
+ if test "$libssh" != "no" ; then
+   if $pkg_config --exists libssh; then
+@@ -6549,6 +6576,7 @@ echo "Trace output file $trace_file-<pid
+ fi
+ echo "spice support     $spice $(echo_version $spice $spice_protocol_version/$spice_server_version)"
+ echo "rbd support       $rbd"
++echo "vitastor support  $vitastor"
+ echo "xfsctl support    $xfs"
+ echo "smartcard support $smartcard"
+ echo "libusb            $libusb"
+@@ -7182,6 +7210,11 @@ if test "$rbd" = "yes" ; then
+   echo "RBD_CFLAGS=$rbd_cflags" >> $config_host_mak
+   echo "RBD_LIBS=$rbd_libs" >> $config_host_mak
+ fi
++if test "$vitastor" = "yes" ; then
++  echo "CONFIG_VITASTOR=m" >> $config_host_mak
++  echo "VITASTOR_CFLAGS=$vitastor_cflags" >> $config_host_mak
++  echo "VITASTOR_LIBS=$vitastor_libs" >> $config_host_mak
++fi
+ 
+ echo "CONFIG_COROUTINE_BACKEND=$coroutine" >> $config_host_mak
+ if test "$coroutine_pool" = "yes" ; then
+diff -NaurpbB qemu-4.2.0/qapi/block-core.json qemu-4.2.0-vitastor/qapi/block-core.json
+--- qemu-4.2.0/qapi/block-core.json	2019-12-12 18:20:48.000000000 +0000
++++ qemu-4.2.0-vitastor/qapi/block-core.json	2021-12-01 21:27:49.213574396 +0000
+@@ -2894,7 +2894,7 @@
              'nbd', 'nfs', 'null-aio', 'null-co', 'nvme', 'parallels', 'qcow',
              'qcow2', 'qed', 'quorum', 'raw', 'rbd',
              { 'name': 'replication', 'if': 'defined(CONFIG_REPLICATION)' },
@@ -11,7 +108,7 @@ Index: qemu/qapi/block-core.json
              'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat', 'vxhs' ] }
  
  ##
-@@ -3725,6 +3725,28 @@
+@@ -3712,6 +3712,28 @@
              '*tag': 'str' } }
  
  ##
@@ -23,24 +120,24 @@ Index: qemu/qapi/block-core.json
 +# @inode:       Inode number
 +# @pool:        Pool ID
 +# @size:        Desired image size in bytes
-+# @config_path: Path to Vitastor configuration
-+# @etcd_host:   etcd connection address(es)
-+# @etcd_prefix: etcd key/value prefix
++# @config-path: Path to Vitastor configuration
++# @etcd-host:   etcd connection address(es)
++# @etcd-prefix: etcd key/value prefix
 +##
 +{ 'struct': 'BlockdevOptionsVitastor',
 +  'data': { '*inode': 'uint64',
 +            '*pool': 'uint64',
 +            '*size': 'uint64',
 +            '*image': 'str',
-+            '*config_path': 'str',
-+            '*etcd_host': 'str',
-+            '*etcd_prefix': 'str' } }
++            '*config-path': 'str',
++            '*etcd-host': 'str',
++            '*etcd-prefix': 'str' } }
 +
 +##
  # @ReplicationMode:
  #
  # An enumeration of replication modes.
-@@ -4084,6 +4102,7 @@
+@@ -4071,6 +4093,7 @@
        'replication': { 'type': 'BlockdevOptionsReplication',
                         'if': 'defined(CONFIG_REPLICATION)' },
        'sheepdog':   'BlockdevOptionsSheepdog',
@@ -48,7 +145,7 @@ Index: qemu/qapi/block-core.json
        'ssh':        'BlockdevOptionsSsh',
        'throttle':   'BlockdevOptionsThrottle',
        'vdi':        'BlockdevOptionsGenericFormat',
-@@ -4461,6 +4480,17 @@
+@@ -4441,6 +4464,17 @@
              '*cluster-size' :   'size' } }
  
  ##
@@ -66,7 +163,7 @@ Index: qemu/qapi/block-core.json
  # @BlockdevVmdkSubformat:
  #
  # Subformat options for VMDK images
-@@ -4722,6 +4752,7 @@
+@@ -4702,6 +4736,7 @@
        'qed':            'BlockdevCreateOptionsQed',
        'rbd':            'BlockdevCreateOptionsRbd',
        'sheepdog':       'BlockdevCreateOptionsSheepdog',
@@ -74,15 +171,3 @@ Index: qemu/qapi/block-core.json
        'ssh':            'BlockdevCreateOptionsSsh',
        'vdi':            'BlockdevCreateOptionsVdi',
        'vhdx':           'BlockdevCreateOptionsVhdx',
-Index: qemu/scripts/modules/module_block.py
-===================================================================
---- qemu.orig/scripts/modules/module_block.py	2020-11-07 22:57:38.936613739 +0000
-+++ qemu/scripts/modules/module_block.py	2020-11-07 22:59:49.890722862 +0000
-@@ -86,6 +86,7 @@ def print_bottom(fheader):
- output_file = sys.argv[1]
- with open(output_file, 'w') as fheader:
-     print_top(fheader)
-+    add_module(fheader, "vitastor", "vitastor", "vitastor")
- 
-     for filename in sys.argv[2:]:
-         if os.path.isfile(filename):

patches/qemu-5.0-vitastor.patch

@@ -1,7 +1,107 @@
-Index: qemu/qapi/block-core.json
-===================================================================
---- qemu.orig/qapi/block-core.json
-+++ qemu/qapi/block-core.json
+diff --git a/block/Makefile.objs b/block/Makefile.objs
+index 3635b6b4c1..6cdf6df6ff 100644
+--- a/block/Makefile.objs
++++ b/block/Makefile.objs
+@@ -30,6 +30,7 @@ block-obj-$(if $(CONFIG_LIBISCSI),y,n) += iscsi-opts.o
+ block-obj-$(CONFIG_LIBNFS) += nfs.o
+ block-obj-$(CONFIG_CURL) += curl.o
+ block-obj-$(CONFIG_RBD) += rbd.o
++block-obj-$(CONFIG_VITASTOR) += vitastor.o
+ block-obj-$(CONFIG_GLUSTERFS) += gluster.o
+ block-obj-$(CONFIG_VXHS) += vxhs.o
+ block-obj-$(CONFIG_LIBSSH) += ssh.o
+@@ -58,6 +59,8 @@ curl.o-cflags      := $(CURL_CFLAGS)
+ curl.o-libs        := $(CURL_LIBS)
+ rbd.o-cflags       := $(RBD_CFLAGS)
+ rbd.o-libs         := $(RBD_LIBS)
++vitastor.o-cflags  := $(VITASTOR_CFLAGS)
++vitastor.o-libs    := $(VITASTOR_LIBS)
+ gluster.o-cflags   := $(GLUSTERFS_CFLAGS)
+ gluster.o-libs     := $(GLUSTERFS_LIBS)
+ vxhs.o-libs        := $(VXHS_LIBS)
+diff --git a/configure b/configure
+index 23b5e93752..7400cb9546 100755
+--- a/configure
++++ b/configure
+@@ -438,6 +438,7 @@ trace_backends="log"
+ trace_file="trace"
+ spice=""
+ rbd=""
++vitastor=""
+ smartcard=""
+ libusb=""
+ usb_redir=""
+@@ -1355,6 +1356,10 @@ for opt do
+   ;;
+   --enable-rbd) rbd="yes"
+   ;;
++  --disable-vitastor) vitastor="no"
++  ;;
++  --enable-vitastor) vitastor="yes"
++  ;;
+   --disable-xfsctl) xfs="no"
+   ;;
+   --enable-xfsctl) xfs="yes"
+@@ -1848,6 +1853,7 @@ disabled with --disable-FEATURE, default is enabled if available:
+   vhost-user      vhost-user backend support
+   spice           spice
+   rbd             rados block device (rbd)
++  vitastor        vitastor block device
+   libiscsi        iscsi support
+   libnfs          nfs support
+   smartcard       smartcard support (libcacard)
+@@ -4088,6 +4094,27 @@ EOF
+   fi
+ fi
+ 
++##########################################
++# vitastor probe
++if test "$vitastor" != "no" ; then
++  cat > $TMPC <<EOF
++#include <vitastor_c.h>
++int main(void) {
++  vitastor_c_create_qemu(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
++  return 0;
++}
++EOF
++  vitastor_libs="-lvitastor_client"
++  if compile_prog "" "$vitastor_libs" ; then
++    vitastor=yes
++  else
++    if test "$vitastor" = "yes" ; then
++      feature_not_found "vitastor block device" "Install vitastor-client-dev"
++    fi
++    vitastor=no
++  fi
++fi
++
+ ##########################################
+ # libssh probe
+ if test "$libssh" != "no" ; then
+@@ -6679,6 +6706,7 @@ echo "Trace output file $trace_file-<pid>"
+ fi
+ echo "spice support     $spice $(echo_version $spice $spice_protocol_version/$spice_server_version)"
+ echo "rbd support       $rbd"
++echo "vitastor support  $vitastor"
+ echo "xfsctl support    $xfs"
+ echo "smartcard support $smartcard"
+ echo "libusb            $libusb"
+@@ -7329,6 +7357,11 @@ if test "$rbd" = "yes" ; then
+   echo "RBD_CFLAGS=$rbd_cflags" >> $config_host_mak
+   echo "RBD_LIBS=$rbd_libs" >> $config_host_mak
+ fi
++if test "$vitastor" = "yes" ; then
++  echo "CONFIG_VITASTOR=m" >> $config_host_mak
++  echo "VITASTOR_CFLAGS=$vitastor_cflags" >> $config_host_mak
++  echo "VITASTOR_LIBS=$vitastor_libs" >> $config_host_mak
++fi
+ 
+ echo "CONFIG_COROUTINE_BACKEND=$coroutine" >> $config_host_mak
+ if test "$coroutine_pool" = "yes" ; then
+diff --git a/qapi/block-core.json b/qapi/block-core.json
+index 943df1926a..c4f23230a3 100644
+--- a/qapi/block-core.json
++++ b/qapi/block-core.json
 @@ -2798,7 +2798,7 @@
              'luks', 'nbd', 'nfs', 'null-aio', 'null-co', 'nvme', 'parallels',
              'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'rbd',
@@ -11,10 +111,11 @@ Index: qemu/qapi/block-core.json
              'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat', 'vxhs' ] }
  
  ##
-@@ -3635,6 +3635,28 @@
+@@ -3634,6 +3634,28 @@
+             '*snap-id': 'uint32',
              '*tag': 'str' } }
  
- ##
++##
 +# @BlockdevOptionsVitastor:
 +#
 +# Driver specific block device options for vitastor
@@ -23,24 +124,23 @@ Index: qemu/qapi/block-core.json
 +# @inode:       Inode number
 +# @pool:        Pool ID
 +# @size:        Desired image size in bytes
-+# @config_path: Path to Vitastor configuration
-+# @etcd_host:   etcd connection address(es)
-+# @etcd_prefix: etcd key/value prefix
++# @config-path: Path to Vitastor configuration
++# @etcd-host:   etcd connection address(es)
++# @etcd-prefix: etcd key/value prefix
 +##
 +{ 'struct': 'BlockdevOptionsVitastor',
 +  'data': { '*inode': 'uint64',
 +            '*pool': 'uint64',
 +            '*size': 'uint64',
 +            '*image': 'str',
-+            '*config_path': 'str',
-+            '*etcd_host': 'str',
-+            '*etcd_prefix': 'str' } }
++            '*config-path': 'str',
++            '*etcd-host': 'str',
++            '*etcd-prefix': 'str' } }
 +
-+##
+ ##
  # @ReplicationMode:
  #
- # An enumeration of replication modes.
-@@ -3995,6 +4013,7 @@
+@@ -3995,6 +4017,7 @@
        'replication': { 'type': 'BlockdevOptionsReplication',
                         'if': 'defined(CONFIG_REPLICATION)' },
        'sheepdog':   'BlockdevOptionsSheepdog',
@@ -48,10 +148,11 @@ Index: qemu/qapi/block-core.json
        'ssh':        'BlockdevOptionsSsh',
        'throttle':   'BlockdevOptionsThrottle',
        'vdi':        'BlockdevOptionsGenericFormat',
-@@ -4365,6 +4384,17 @@
+@@ -4364,6 +4387,17 @@
+             'size':             'size',
              '*cluster-size' :   'size' } }
  
- ##
++##
 +# @BlockdevCreateOptionsVitastor:
 +#
 +# Driver specific image creation options for Vitastor.
@@ -62,11 +163,10 @@ Index: qemu/qapi/block-core.json
 +  'data': { 'location':         'BlockdevOptionsVitastor',
 +            'size':             'size' } }
 +
-+##
+ ##
  # @BlockdevVmdkSubformat:
  #
- # Subformat options for VMDK images
-@@ -4626,6 +4656,7 @@
+@@ -4626,6 +4660,7 @@
        'qed':            'BlockdevCreateOptionsQed',
        'rbd':            'BlockdevCreateOptionsRbd',
        'sheepdog':       'BlockdevCreateOptionsSheepdog',
@@ -74,15 +174,3 @@ Index: qemu/qapi/block-core.json
        'ssh':            'BlockdevCreateOptionsSsh',
        'vdi':            'BlockdevCreateOptionsVdi',
        'vhdx':           'BlockdevCreateOptionsVhdx',
-Index: qemu/scripts/modules/module_block.py
-===================================================================
---- qemu.orig/scripts/modules/module_block.py
-+++ qemu/scripts/modules/module_block.py
-@@ -85,6 +85,7 @@ def print_bottom(fheader):
- output_file = sys.argv[1]
- with open(output_file, 'w') as fheader:
-     print_top(fheader)
-+    add_module(fheader, "vitastor", "vitastor", "vitastor")
- 
-     for filename in sys.argv[2:]:
-         if os.path.isfile(filename):

patches/qemu-5.1-vitastor.patch

@@ -1,8 +1,8 @@
-Index: qemu-5.1+dfsg/qapi/block-core.json
+Index: qemu-5.2+dfsg/qapi/block-core.json
 ===================================================================
---- qemu-5.1+dfsg.orig/qapi/block-core.json
-+++ qemu-5.1+dfsg/qapi/block-core.json
-@@ -2807,7 +2807,7 @@
+--- qemu-5.2+dfsg.orig/qapi/block-core.json
++++ qemu-5.2+dfsg/qapi/block-core.json
+@@ -2831,7 +2831,7 @@
              'luks', 'nbd', 'nfs', 'null-aio', 'null-co', 'nvme', 'parallels',
              'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'rbd',
              { 'name': 'replication', 'if': 'defined(CONFIG_REPLICATION)' },
@@ -11,7 +11,7 @@ Index: qemu-5.1+dfsg/qapi/block-core.json
              'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat' ] }
  
  ##
-@@ -3644,6 +3644,28 @@
+@@ -3668,6 +3668,28 @@
              '*tag': 'str' } }
  
  ##
@@ -23,24 +23,24 @@ Index: qemu-5.1+dfsg/qapi/block-core.json
 +# @inode:       Inode number
 +# @pool:        Pool ID
 +# @size:        Desired image size in bytes
-+# @config_path: Path to Vitastor configuration
-+# @etcd_host:   etcd connection address(es)
-+# @etcd_prefix: etcd key/value prefix
++# @config-path: Path to Vitastor configuration
++# @etcd-host:   etcd connection address(es)
++# @etcd-prefix: etcd key/value prefix
 +##
 +{ 'struct': 'BlockdevOptionsVitastor',
 +  'data': { '*inode': 'uint64',
 +            '*pool': 'uint64',
 +            '*size': 'uint64',
 +            '*image': 'str',
-+            '*config_path': 'str',
-+            '*etcd_host': 'str',
-+            '*etcd_prefix': 'str' } }
++            '*config-path': 'str',
++            '*etcd-host': 'str',
++            '*etcd-prefix': 'str' } }
 +
 +##
  # @ReplicationMode:
  #
  # An enumeration of replication modes.
-@@ -3988,6 +4006,7 @@
+@@ -4015,6 +4037,7 @@
        'replication': { 'type': 'BlockdevOptionsReplication',
                         'if': 'defined(CONFIG_REPLICATION)' },
        'sheepdog':   'BlockdevOptionsSheepdog',
@@ -48,7 +48,7 @@ Index: qemu-5.1+dfsg/qapi/block-core.json
        'ssh':        'BlockdevOptionsSsh',
        'throttle':   'BlockdevOptionsThrottle',
        'vdi':        'BlockdevOptionsGenericFormat',
-@@ -4376,6 +4395,17 @@
+@@ -4404,6 +4427,17 @@
              '*cluster-size' :   'size' } }
  
  ##
@@ -66,7 +66,7 @@ Index: qemu-5.1+dfsg/qapi/block-core.json
  # @BlockdevVmdkSubformat:
  #
  # Subformat options for VMDK images
-@@ -4637,6 +4667,7 @@
+@@ -4665,6 +4699,7 @@
        'qed':            'BlockdevCreateOptionsQed',
        'rbd':            'BlockdevCreateOptionsRbd',
        'sheepdog':       'BlockdevCreateOptionsSheepdog',
@@ -74,15 +74,108 @@ Index: qemu-5.1+dfsg/qapi/block-core.json
        'ssh':            'BlockdevCreateOptionsSsh',
        'vdi':            'BlockdevCreateOptionsVdi',
        'vhdx':           'BlockdevCreateOptionsVhdx',
-Index: qemu-5.1+dfsg/scripts/modules/module_block.py
+Index: qemu-5.2+dfsg/block/meson.build
 ===================================================================
---- qemu-5.1+dfsg.orig/scripts/modules/module_block.py
-+++ qemu-5.1+dfsg/scripts/modules/module_block.py
-@@ -86,6 +86,7 @@ if __name__ == '__main__':
-     output_file = sys.argv[1]
-     with open(output_file, 'w') as fheader:
-         print_top(fheader)
-+        add_module(fheader, "vitastor", "vitastor", "vitastor")
+--- qemu-5.2+dfsg.orig/block/meson.build
++++ qemu-5.2+dfsg/block/meson.build
+@@ -76,6 +76,7 @@ foreach m : [
+   ['CONFIG_LIBNFS', 'nfs', libnfs, 'nfs.c'],
+   ['CONFIG_LIBSSH', 'ssh', libssh, 'ssh.c'],
+   ['CONFIG_RBD', 'rbd', rbd, 'rbd.c'],
++  ['CONFIG_VITASTOR', 'vitastor', vitastor, 'vitastor.c'],
+ ]
+   if config_host.has_key(m[0])
+     if enable_modules
+Index: qemu-5.2+dfsg/configure
+===================================================================
+--- qemu-5.2+dfsg.orig/configure
++++ qemu-5.2+dfsg/configure
+@@ -372,6 +372,7 @@ trace_backends="log"
+ trace_file="trace"
+ spice=""
+ rbd=""
++vitastor=""
+ smartcard=""
+ u2f="auto"
+ libusb=""
+@@ -1263,6 +1264,10 @@ for opt do
+   ;;
+   --enable-rbd) rbd="yes"
+   ;;
++  --disable-vitastor) vitastor="no"
++  ;;
++  --enable-vitastor) vitastor="yes"
++  ;;
+   --disable-xfsctl) xfs="no"
+   ;;
+   --enable-xfsctl) xfs="yes"
+@@ -1827,6 +1832,7 @@ disabled with --disable-FEATURE, default
+   vhost-vdpa      vhost-vdpa kernel backend support
+   spice           spice
+   rbd             rados block device (rbd)
++  vitastor        vitastor block device
+   libiscsi        iscsi support
+   libnfs          nfs support
+   smartcard       smartcard support (libcacard)
+@@ -3719,6 +3725,27 @@ EOF
+ fi
  
-         for filename in sys.argv[2:]:
-             if os.path.isfile(filename):
+ ##########################################
++# vitastor probe
++if test "$vitastor" != "no" ; then
++  cat > $TMPC <<EOF
++#include <vitastor_c.h>
++int main(void) {
++  vitastor_c_create_qemu(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
++  return 0;
++}
++EOF
++  vitastor_libs="-lvitastor_client"
++  if compile_prog "" "$vitastor_libs" ; then
++    vitastor=yes
++  else
++    if test "$vitastor" = "yes" ; then
++      feature_not_found "vitastor block device" "Install vitastor-client-dev"
++    fi
++    vitastor=no
++  fi
++fi
++
++##########################################
+ # libssh probe
+ if test "$libssh" != "no" ; then
+   if $pkg_config --exists libssh; then
+@@ -6456,6 +6483,10 @@ if test "$rbd" = "yes" ; then
+   echo "CONFIG_RBD=y" >> $config_host_mak
+   echo "RBD_LIBS=$rbd_libs" >> $config_host_mak
+ fi
++if test "$vitastor" = "yes" ; then
++  echo "CONFIG_VITASTOR=y" >> $config_host_mak
++  echo "VITASTOR_LIBS=$vitastor_libs" >> $config_host_mak
++fi
+ 
+ echo "CONFIG_COROUTINE_BACKEND=$coroutine" >> $config_host_mak
+ if test "$coroutine_pool" = "yes" ; then
+Index: qemu-5.2+dfsg/meson.build
+===================================================================
+--- qemu-5.2+dfsg.orig/meson.build
++++ qemu-5.2+dfsg/meson.build
+@@ -596,6 +596,10 @@ rbd = not_found
+ if 'CONFIG_RBD' in config_host
+   rbd = declare_dependency(link_args: config_host['RBD_LIBS'].split())
+ endif
++vitastor = not_found
++if 'CONFIG_VITASTOR' in config_host
++  vitastor = declare_dependency(link_args: config_host['VITASTOR_LIBS'].split())
++endif
+ glusterfs = not_found
+ if 'CONFIG_GLUSTERFS' in config_host
+   glusterfs = declare_dependency(compile_args: config_host['GLUSTERFS_CFLAGS'].split(),
+@@ -2145,6 +2149,7 @@ endif
+ # TODO: add back protocol and server version
+ summary_info += {'spice support':     config_host.has_key('CONFIG_SPICE')}
+ summary_info += {'rbd support':       config_host.has_key('CONFIG_RBD')}
++summary_info += {'vitastor support':  config_host.has_key('CONFIG_VITASTOR')}
+ summary_info += {'xfsctl support':    config_host.has_key('CONFIG_XFS')}
+ summary_info += {'smartcard support': config_host.has_key('CONFIG_SMARTCARD')}
+ summary_info += {'U2F support':       u2f.found()}

patches/qemu-6.0-vitastor.patch

@@ -0,0 +1,188 @@
+diff --git a/block/meson.build b/block/meson.build
+index d21990ec95..385ac37732 100644
+--- a/block/meson.build
++++ b/block/meson.build
+@@ -78,6 +78,7 @@ foreach m : [
+   [libnfs, 'nfs', libnfs, 'nfs.c'],
+   [libssh, 'ssh', libssh, 'ssh.c'],
+   [rbd, 'rbd', rbd, 'rbd.c'],
++  [vitastor, 'vitastor', vitastor, 'vitastor.c'],
+ ]
+   if m[0].found()
+     if enable_modules
+diff --git a/configure b/configure
+index c77f7b1020..5f534e8484 100755
+--- a/configure
++++ b/configure
+@@ -389,6 +389,7 @@ trace_backends="log"
+ trace_file="trace"
+ spice="$default_feature"
+ rbd="auto"
++vitastor="auto"
+ smartcard="$default_feature"
+ u2f="auto"
+ libusb="$default_feature"
+@@ -1280,6 +1281,10 @@ for opt do
+   ;;
+   --enable-rbd) rbd="enabled"
+   ;;
++  --disable-vitastor) vitastor="disabled"
++  ;;
++  --enable-vitastor) vitastor="enabled"
++  ;;
+   --disable-xfsctl) xfs="no"
+   ;;
+   --enable-xfsctl) xfs="yes"
+@@ -1867,6 +1872,7 @@ disabled with --disable-FEATURE, default is enabled if available
+   vhost-vdpa      vhost-vdpa kernel backend support
+   spice           spice
+   rbd             rados block device (rbd)
++  vitastor        vitastor block device
+   libiscsi        iscsi support
+   libnfs          nfs support
+   smartcard       smartcard support (libcacard)
+@@ -6423,7 +6429,7 @@ NINJA=$ninja $meson setup \
+         -Dcapstone=$capstone -Dslirp=$slirp -Dfdt=$fdt -Dbrlapi=$brlapi \
+         -Dcurl=$curl -Dglusterfs=$glusterfs -Dbzip2=$bzip2 -Dlibiscsi=$libiscsi \
+         -Dlibnfs=$libnfs -Diconv=$iconv -Dcurses=$curses -Dlibudev=$libudev\
+-        -Drbd=$rbd -Dlzo=$lzo -Dsnappy=$snappy -Dlzfse=$lzfse \
++        -Drbd=$rbd -Dvitastor=$vitastor -Dlzo=$lzo -Dsnappy=$snappy -Dlzfse=$lzfse \
+         -Dzstd=$zstd -Dseccomp=$seccomp -Dvirtfs=$virtfs -Dcap_ng=$cap_ng \
+         -Dattr=$attr -Ddefault_devices=$default_devices \
+         -Ddocs=$docs -Dsphinx_build=$sphinx_build -Dinstall_blobs=$blobs \
+diff --git a/meson.build b/meson.build
+index c6f4b0cf5e..3dc7f7b463 100644
+--- a/meson.build
++++ b/meson.build
+@@ -720,6 +720,26 @@ if not get_option('rbd').auto() or have_block
+   endif
+ endif
+ 
++vitastor = not_found
++if not get_option('vitastor').auto() or have_block
++  libvitastor_client = cc.find_library('vitastor_client', has_headers: ['vitastor_c.h'],
++    required: get_option('vitastor'), kwargs: static_kwargs)
++  if libvitastor_client.found()
++    if cc.links('''
++      #include <vitastor_c.h>
++      int main(void) {
++        vitastor_c_create_qemu(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
++        return 0;
++      }''', dependencies: libvitastor_client)
++      vitastor = declare_dependency(dependencies: libvitastor_client)
++    elif get_option('vitastor').enabled()
++      error('could not link libvitastor_client')
++    else
++      warning('could not link libvitastor_client, disabling')
++    endif
++  endif
++endif
++
+ glusterfs = not_found
+ glusterfs_ftruncate_has_stat = false
+ glusterfs_iocb_has_stat = false
+@@ -1118,6 +1138,7 @@ config_host_data.set('CONFIG_LIBCAP_NG', libcap_ng.found())
+ config_host_data.set('CONFIG_LIBISCSI', libiscsi.found())
+ config_host_data.set('CONFIG_LIBNFS', libnfs.found())
+ config_host_data.set('CONFIG_RBD', rbd.found())
++config_host_data.set('CONFIG_VITASTOR', vitastor.found())
+ config_host_data.set('CONFIG_SDL', sdl.found())
+ config_host_data.set('CONFIG_SDL_IMAGE', sdl_image.found())
+ config_host_data.set('CONFIG_SECCOMP', seccomp.found())
+@@ -2683,6 +2704,7 @@ summary_info += {'libcap-ng support': libcap_ng.found()}
+ # TODO: add back protocol and server version
+ summary_info += {'spice support':     config_host.has_key('CONFIG_SPICE')}
+ summary_info += {'rbd support':       rbd.found()}
++summary_info += {'vitastor support':  vitastor.found()}
+ summary_info += {'xfsctl support':    config_host.has_key('CONFIG_XFS')}
+ summary_info += {'smartcard support': config_host.has_key('CONFIG_SMARTCARD')}
+ summary_info += {'U2F support':       u2f.found()}
+diff --git a/meson_options.txt b/meson_options.txt
+index 9734019995..bc93963b27 100644
+--- a/meson_options.txt
++++ b/meson_options.txt
+@@ -80,6 +80,8 @@ option('lzo', type : 'feature', value : 'auto',
+        description: 'lzo compression support')
+ option('rbd', type : 'feature', value : 'auto',
+        description: 'Ceph block device driver')
++option('vitastor', type : 'feature', value : 'auto',
++       description: 'Vitastor block device driver')
+ option('gtk', type : 'feature', value : 'auto',
+        description: 'GTK+ user interface')
+ option('sdl', type : 'feature', value : 'auto',
+diff --git a/qapi/block-core.json b/qapi/block-core.json
+index 6d227924d0..d14b29aa43 100644
+--- a/qapi/block-core.json
++++ b/qapi/block-core.json
+@@ -2819,7 +2819,7 @@
+             'preallocate', 'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'rbd',
+             { 'name': 'replication', 'if': 'defined(CONFIG_REPLICATION)' },
+             'sheepdog',
+-            'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat' ] }
++            'ssh', 'throttle', 'vdi', 'vhdx', 'vitastor', 'vmdk', 'vpc', 'vvfat' ] }
+ 
+ ##
+ # @BlockdevOptionsFile:
+@@ -3671,6 +3671,28 @@
+             '*snap-id': 'uint32',
+             '*tag': 'str' } }
+ 
++##
++# @BlockdevOptionsVitastor:
++#
++# Driver specific block device options for vitastor
++#
++# @image:       Image name
++# @inode:       Inode number
++# @pool:        Pool ID
++# @size:        Desired image size in bytes
++# @config-path: Path to Vitastor configuration
++# @etcd-host:   etcd connection address(es)
++# @etcd-prefix: etcd key/value prefix
++##
++{ 'struct': 'BlockdevOptionsVitastor',
++  'data': { '*inode': 'uint64',
++            '*pool': 'uint64',
++            '*size': 'uint64',
++            '*image': 'str',
++            '*config-path': 'str',
++            '*etcd-host': 'str',
++            '*etcd-prefix': 'str' } }
++
+ ##
+ # @ReplicationMode:
+ #
+@@ -4042,6 +4064,7 @@
+       'throttle':   'BlockdevOptionsThrottle',
+       'vdi':        'BlockdevOptionsGenericFormat',
+       'vhdx':       'BlockdevOptionsGenericFormat',
++      'vitastor':   'BlockdevOptionsVitastor',
+       'vmdk':       'BlockdevOptionsGenericCOWFormat',
+       'vpc':        'BlockdevOptionsGenericFormat',
+       'vvfat':      'BlockdevOptionsVVFAT'
+@@ -4426,6 +4449,17 @@
+             'size':             'size',
+             '*cluster-size' :   'size' } }
+ 
++##
++# @BlockdevCreateOptionsVitastor:
++#
++# Driver specific image creation options for Vitastor.
++#
++# @size: Size of the virtual disk in bytes
++##
++{ 'struct': 'BlockdevCreateOptionsVitastor',
++  'data': { 'location':         'BlockdevOptionsVitastor',
++            'size':             'size' } }
++
+ ##
+ # @BlockdevVmdkSubformat:
+ #
+@@ -4691,6 +4725,7 @@
+       'ssh':            'BlockdevCreateOptionsSsh',
+       'vdi':            'BlockdevCreateOptionsVdi',
+       'vhdx':           'BlockdevCreateOptionsVhdx',
++      'vitastor':       'BlockdevCreateOptionsVitastor',
+       'vmdk':           'BlockdevCreateOptionsVmdk',
+       'vpc':            'BlockdevCreateOptionsVpc'
+   } }

patches/qemu-6.1-vitastor.patch

@@ -0,0 +1,188 @@
+Index: qemu-6.1+dfsg/qapi/block-core.json
+===================================================================
+--- qemu-6.1+dfsg.orig/qapi/block-core.json
++++ qemu-6.1+dfsg/qapi/block-core.json
+@@ -2838,7 +2838,7 @@
+             'luks', 'nbd', 'nfs', 'null-aio', 'null-co', 'nvme', 'parallels',
+             'preallocate', 'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'rbd',
+             { 'name': 'replication', 'if': 'defined(CONFIG_REPLICATION)' },
+-            'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat' ] }
++            'ssh', 'throttle', 'vdi', 'vhdx', 'vitastor', 'vmdk', 'vpc', 'vvfat' ] }
+ 
+ ##
+ # @BlockdevOptionsFile:
+@@ -3763,6 +3763,28 @@
+             '*server': ['InetSocketAddressBase'] } }
+ 
+ ##
++# @BlockdevOptionsVitastor:
++#
++# Driver specific block device options for vitastor
++#
++# @image:       Image name
++# @inode:       Inode number
++# @pool:        Pool ID
++# @size:        Desired image size in bytes
++# @config-path: Path to Vitastor configuration
++# @etcd-host:   etcd connection address(es)
++# @etcd-prefix: etcd key/value prefix
++##
++{ 'struct': 'BlockdevOptionsVitastor',
++  'data': { '*inode': 'uint64',
++            '*pool': 'uint64',
++            '*size': 'uint64',
++            '*image': 'str',
++            '*config-path': 'str',
++            '*etcd-host': 'str',
++            '*etcd-prefix': 'str' } }
++
++##
+ # @ReplicationMode:
+ #
+ # An enumeration of replication modes.
+@@ -4134,6 +4156,7 @@
+       'throttle':   'BlockdevOptionsThrottle',
+       'vdi':        'BlockdevOptionsGenericFormat',
+       'vhdx':       'BlockdevOptionsGenericFormat',
++      'vitastor':   'BlockdevOptionsVitastor',
+       'vmdk':       'BlockdevOptionsGenericCOWFormat',
+       'vpc':        'BlockdevOptionsGenericFormat',
+       'vvfat':      'BlockdevOptionsVVFAT'
+@@ -4523,6 +4546,17 @@
+             '*encrypt' :        'RbdEncryptionCreateOptions' } }
+ 
+ ##
++# @BlockdevCreateOptionsVitastor:
++#
++# Driver specific image creation options for Vitastor.
++#
++# @size: Size of the virtual disk in bytes
++##
++{ 'struct': 'BlockdevCreateOptionsVitastor',
++  'data': { 'location':         'BlockdevOptionsVitastor',
++            'size':             'size' } }
++
++##
+ # @BlockdevVmdkSubformat:
+ #
+ # Subformat options for VMDK images
+@@ -4718,6 +4752,7 @@
+       'ssh':            'BlockdevCreateOptionsSsh',
+       'vdi':            'BlockdevCreateOptionsVdi',
+       'vhdx':           'BlockdevCreateOptionsVhdx',
++      'vitastor':       'BlockdevCreateOptionsVitastor',
+       'vmdk':           'BlockdevCreateOptionsVmdk',
+       'vpc':            'BlockdevCreateOptionsVpc'
+   } }
+Index: qemu-6.1+dfsg/block/meson.build
+===================================================================
+--- qemu-6.1+dfsg.orig/block/meson.build
++++ qemu-6.1+dfsg/block/meson.build
+@@ -78,6 +78,7 @@ foreach m : [
+   [libnfs, 'nfs', files('nfs.c')],
+   [libssh, 'ssh', files('ssh.c')],
+   [rbd, 'rbd', files('rbd.c')],
++  [vitastor, 'vitastor', files('vitastor.c')],
+ ]
+   if m[0].found()
+     module_ss = ss.source_set()
+Index: qemu-6.1+dfsg/configure
+===================================================================
+--- qemu-6.1+dfsg.orig/configure
++++ qemu-6.1+dfsg/configure
+@@ -375,6 +375,7 @@ trace_file="trace"
+ spice="$default_feature"
+ spice_protocol="auto"
+ rbd="auto"
++vitastor="auto"
+ smartcard="auto"
+ u2f="auto"
+ libusb="auto"
+@@ -1292,6 +1293,10 @@ for opt do
+   ;;
+   --enable-rbd) rbd="enabled"
+   ;;
++  --disable-vitastor) vitastor="disabled"
++  ;;
++  --enable-vitastor) vitastor="enabled"
++  ;;
+   --disable-xfsctl) xfs="no"
+   ;;
+   --enable-xfsctl) xfs="yes"
+@@ -1916,6 +1921,7 @@ disabled with --disable-FEATURE, default
+   spice           spice
+   spice-protocol  spice-protocol
+   rbd             rados block device (rbd)
++  vitastor        vitastor block device
+   libiscsi        iscsi support
+   libnfs          nfs support
+   smartcard       smartcard support (libcacard)
+@@ -5202,7 +5208,7 @@ if test "$skip_meson" = no; then
+         -Dcapstone=$capstone -Dslirp=$slirp -Dfdt=$fdt -Dbrlapi=$brlapi \
+         -Dcurl=$curl -Dglusterfs=$glusterfs -Dbzip2=$bzip2 -Dlibiscsi=$libiscsi \
+         -Dlibnfs=$libnfs -Diconv=$iconv -Dcurses=$curses -Dlibudev=$libudev\
+-        -Drbd=$rbd -Dlzo=$lzo -Dsnappy=$snappy -Dlzfse=$lzfse -Dlibxml2=$libxml2 \
++        -Drbd=$rbd -Dvitastor=$vitastor -Dlzo=$lzo -Dsnappy=$snappy -Dlzfse=$lzfse -Dlibxml2=$libxml2 \
+         -Dlibdaxctl=$libdaxctl -Dlibpmem=$libpmem -Dlinux_io_uring=$linux_io_uring \
+         -Dgnutls=$gnutls -Dnettle=$nettle -Dgcrypt=$gcrypt -Dauth_pam=$auth_pam \
+         -Dzstd=$zstd -Dseccomp=$seccomp -Dvirtfs=$virtfs -Dcap_ng=$cap_ng \
+Index: qemu-6.1+dfsg/meson.build
+===================================================================
+--- qemu-6.1+dfsg.orig/meson.build
++++ qemu-6.1+dfsg/meson.build
+@@ -729,6 +729,26 @@ if not get_option('rbd').auto() or have_
+   endif
+ endif
+ 
++vitastor = not_found
++if not get_option('vitastor').auto() or have_block
++  libvitastor_client = cc.find_library('vitastor_client', has_headers: ['vitastor_c.h'],
++    required: get_option('vitastor'), kwargs: static_kwargs)
++  if libvitastor_client.found()
++    if cc.links('''
++      #include <vitastor_c.h>
++      int main(void) {
++        vitastor_c_create_qemu(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
++        return 0;
++      }''', dependencies: libvitastor_client)
++      vitastor = declare_dependency(dependencies: libvitastor_client)
++    elif get_option('vitastor').enabled()
++      error('could not link libvitastor_client')
++    else
++      warning('could not link libvitastor_client, disabling')
++    endif
++  endif
++endif
++
+ glusterfs = not_found
+ glusterfs_ftruncate_has_stat = false
+ glusterfs_iocb_has_stat = false
+@@ -1264,6 +1284,7 @@ config_host_data.set('CONFIG_LIBNFS', li
+ config_host_data.set('CONFIG_LINUX_IO_URING', linux_io_uring.found())
+ config_host_data.set('CONFIG_LIBPMEM', libpmem.found())
+ config_host_data.set('CONFIG_RBD', rbd.found())
++config_host_data.set('CONFIG_VITASTOR', vitastor.found())
+ config_host_data.set('CONFIG_SDL', sdl.found())
+ config_host_data.set('CONFIG_SDL_IMAGE', sdl_image.found())
+ config_host_data.set('CONFIG_SECCOMP', seccomp.found())
+@@ -3075,6 +3096,7 @@ summary_info += {'bpf support': libbpf.f
+ # TODO: add back protocol and server version
+ summary_info += {'spice support':     config_host.has_key('CONFIG_SPICE')}
+ summary_info += {'rbd support':       rbd.found()}
++summary_info += {'vitastor support':  vitastor.found()}
+ summary_info += {'xfsctl support':    config_host.has_key('CONFIG_XFS')}
+ summary_info += {'smartcard support': cacard.found()}
+ summary_info += {'U2F support':       u2f.found()}
+Index: qemu-6.1+dfsg/meson_options.txt
+===================================================================
+--- qemu-6.1+dfsg.orig/meson_options.txt
++++ qemu-6.1+dfsg/meson_options.txt
+@@ -102,6 +102,8 @@ option('lzo', type : 'feature', value :
+        description: 'lzo compression support')
+ option('rbd', type : 'feature', value : 'auto',
+        description: 'Ceph block device driver')
++option('vitastor', type : 'feature', value : 'auto',
++       description: 'Vitastor block device driver')
+ option('gtk', type : 'feature', value : 'auto',
+        description: 'GTK+ user interface')
+ option('sdl', type : 'feature', value : 'auto',

patches/qemu-make-patches.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+# QEMU patches don't include the `block/vitastor.c` file to not duplicate it in sources
+# Run this script to append its creation to all QEMU patches
+
+DIR=$(dirname $0)
+for i in "$DIR"/qemu-*-vitastor.patch "$DIR"/pve-qemu-*-vitastor.patch; do
+    if ! grep -qP '^\+\+\+ .*block/vitastor\.c' $i; then
+        echo 'Index: a/block/vitastor.c' >> $i
+        echo '===================================================================' >> $i
+        echo '--- /dev/null' >> $i
+        echo '+++ a/block/vitastor.c' >> $i
+        echo '@@ -0,0 +1,'$(wc -l "$DIR"/../src/qemu_driver.c)' @@' >> $i
+        cat "$DIR"/../src/qemu_driver.c | sed 's/^/+/' >> $i
+    fi
+done

rpm/build-tarball.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
-# Vitastor depends on QEMU and FIO headers, but QEMU and FIO don't have -devel packages
+# Vitastor depends on QEMU and/or FIO headers, but QEMU and FIO don't have -devel packages
 # So we have to copy their headers into the source tarball
 
 set -e
@@ -18,34 +18,11 @@ else
 fi
 cd ~/rpmbuild/SPECS
 rpmbuild -bp fio.spec
-perl -i -pe 's/^make V=1/exit 0; make V=1/' qemu*.spec
-rpmbuild -bc qemu*.spec
-perl -i -pe 's/^exit 0; make V=1/make V=1/' qemu*.spec
-cd ~/rpmbuild/BUILD/qemu*/
-rm -rf $VITASTOR/qemu $VITASTOR/fio
-mkdir -p $VITASTOR/qemu/b/qemu
-make -j8 config-host.h
-cp config-host.h $VITASTOR/qemu/b/qemu
-cp -r include $VITASTOR/qemu
-if [ -f qapi-schema.json ]; then
-    # QEMU 2.0
-    make qapi-types.h
-    cp qapi-types.h $VITASTOR/qemu/b/qemu
-else
-    # QEMU 3.0+
-    make qapi
-    cp -r qapi $VITASTOR/qemu/b/qemu
-fi
 cd $VITASTOR
-sh copy-qemu-includes.sh
-rm -rf qemu
-mv qemu-copy qemu
 ln -s ~/rpmbuild/BUILD/fio*/ fio
 sh copy-fio-includes.sh
 rm fio
 mv fio-copy fio
 FIO=`rpm -qi fio | perl -e 'while(<>) { /^Epoch[\s:]+(\S+)/ && print "$1:"; /^Version[\s:]+(\S+)/ && print $1; /^Release[\s:]+(\S+)/ && print "-$1"; }'`
-QEMU=`rpm -qi qemu qemu-kvm | perl -e 'while(<>) { /^Epoch[\s:]+(\S+)/ && print "$1:"; /^Version[\s:]+(\S+)/ && print $1; /^Release[\s:]+(\S+)/ && print "-$1"; }'`
 perl -i -pe 's/(Requires:\s*fio)([^\n]+)?/$1 = '$FIO'/' $VITASTOR/rpm/vitastor-el$EL.spec
-perl -i -pe 's/(Requires:\s*qemu(?:-kvm)?)([^\n]+)?/$1 = '$QEMU'/' $VITASTOR/rpm/vitastor-el$EL.spec
-tar --transform 's#^#vitastor-0.6.8/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-0.6.8$(rpm --eval '%dist').tar.gz *
+tar --transform 's#^#vitastor-0.6.17/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-0.6.17$(rpm --eval '%dist').tar.gz *