Destroy qemu driver under lock (may fix crashes after attach/detach?)

New features:

- Support containerized Vitastor installations: http://vitastor.io/docs/installation/docker.html
- Add new functions to the node.js binding: delete(), get_immediate_commit(), on_ready(),
  get_min_io_size(), get_max_atomic_write_size()
- S3 (Zenko Cloudserver with Vitastor support) is coming shortly and will be released separately

Bug fixes:

- Use IP-derived etcd node names in make-etcd
- Set short name of the OSD process to display in `top`
- Fix snap-create without pool_id failing when there are multiple pools
- Several bugs are fixed in the write-back cache, it should now be stable:
  - Fix incorrect snapshot reads from dirty write-back cache
  - Do not try to repeat pending writebacks on OSD reconnections
  - Fix client hangs with multiple SYNCs in the writeback queue
  - Fix client hangs do to incorrect calculation of the writeback queue size
- Several improvements for NBD mapping/unmapping:
  - Add a workaround for race condition in the Linux kernel NBD driver leading
    to vitastor-nbd sometimes breaking a previously mapped device instead of
    setting up a new one
  - Check if the device is actually mapped in vitastor-nbd unmap
  - Fix device name/number validation in vitastor-nbd
- Fix OSD crashes after starting with corrupted metadata - from now it will skip
  corrupted metadata entries and heal itself
- Fix scrubbing of misplaced objects and object state recalculation after
  vitastor-cli fix - previously, an OSD restart could be required to fix object states
- Make primary OSD distribution more stable by using murmur3 hash instead of the old pseudo-rng
- Fix monitor sometimes racing with itself - do not touch /pool/stats from stats
  aggregation if PG recheck is active
- Sort vitastor-cli ls output by name by default
- Update antietcd to 1.1.2

CMakeLists.txt

@@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8.12)
 
 project(vitastor)
 
-set(VITASTOR_VERSION "1.10.1")
+set(VITASTOR_VERSION "1.11.0")
 
 add_subdirectory(src)

README-ru.md

@@ -41,6 +41,7 @@ Vitastor поддерживает QEMU-драйвер, протоколы NBD и
   - [Автор и лицензия](docs/intro/author.ru.md)
 - Установка
   - [Пакеты](docs/installation/packages.ru.md)
+  - [Docker](docs/installation/docker.ru.md)
   - [Proxmox](docs/installation/proxmox.ru.md)
   - [OpenNebula](docs/installation/opennebula.ru.md)
   - [OpenStack](docs/installation/openstack.ru.md)

README.md

@@ -41,6 +41,7 @@ Read more details in the documentation. You can start from here: [Quick Start](d
   - [Author and license](docs/intro/author.en.md)
 - Installation
   - [Packages](docs/installation/packages.en.md)
+  - [Docker](docs/installation/docker.en.md)
   - [Proxmox](docs/installation/proxmox.en.md)
   - [OpenNebula](docs/installation/opennebula.en.md)
   - [OpenStack](docs/installation/openstack.en.md)

csi/Makefile

@@ -1,4 +1,4 @@
-VITASTOR_VERSION ?= v1.10.1
+VITASTOR_VERSION ?= v1.11.0
 
 all: build push
 

csi/deploy/004-csi-nodeplugin.yaml

@@ -49,7 +49,7 @@ spec:
             capabilities:
               add: ["SYS_ADMIN"]
             allowPrivilegeEscalation: true
-          image: vitalif/vitastor-csi:v1.10.1
+          image: vitalif/vitastor-csi:v1.11.0
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/deploy/007-csi-provisioner.yaml

@@ -121,7 +121,7 @@ spec:
             privileged: true
             capabilities:
               add: ["SYS_ADMIN"]
-          image: vitalif/vitastor-csi:v1.10.1
+          image: vitalif/vitastor-csi:v1.11.0
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/src/config.go

@@ -5,7 +5,7 @@ package vitastor
 
 const (
     vitastorCSIDriverName    = "csi.vitastor.io"
-    vitastorCSIDriverVersion = "1.10.1"
+    vitastorCSIDriverVersion = "1.11.0"
 )
 
 // Config struct fills the parameters of request or user input

debian/changelog

@@ -1,4 +1,4 @@
-vitastor (1.10.1-1) unstable; urgency=medium
+vitastor (1.11.0-1) unstable; urgency=medium
 
   * Bugfixes
 

debian/control

@@ -2,7 +2,10 @@ Source: vitastor
 Section: admin
 Priority: optional
 Maintainer: Vitaliy Filippov <vitalif@yourcmc.ru>
-Build-Depends: debhelper, liburing-dev (>= 0.6), g++ (>= 8), libstdc++6 (>= 8), linux-libc-dev, libgoogle-perftools-dev, libjerasure-dev, libgf-complete-dev, libibverbs-dev, libisal-dev, cmake, pkg-config, libnl-3-dev, libnl-genl-3-dev
+Build-Depends: debhelper, liburing-dev (>= 0.6), g++ (>= 8), libstdc++6 (>= 8),
+  linux-libc-dev, libgoogle-perftools-dev, libjerasure-dev, libgf-complete-dev,
+  libibverbs-dev, libisal-dev, cmake, pkg-config, libnl-3-dev, libnl-genl-3-dev,
+  node-bindings <!nocheck>, node-gyp, node-nan
 Standards-Version: 4.5.0
 Homepage: https://vitastor.io/
 Rules-Requires-Root: no
@@ -59,3 +62,9 @@ Architecture: amd64
 Depends: ${shlibs:Depends}, ${misc:Depends}, vitastor-client, patch, python3, jq
 Description: Vitastor OpenNebula storage plugin
  Vitastor storage plugin for OpenNebula.
+
+Package: node-vitastor
+Architecture: amd64
+Depends: ${shlibs:Depends}, ${misc:Depends}, node-bindings
+Description: Node.js bindings for Vitastor client
+ Node.js native bindings for the Vitastor client library (vitastor-client).

debian/node-vitastor.install

@@ -0,0 +1 @@
+usr/lib/x86_64-linux-gnu/nodejs/vitastor

debian/patched-qemu.Dockerfile

@@ -1,8 +1,10 @@
 # Build patched QEMU for Debian inside a container
 # cd ..; podman build --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/patched-qemu.Dockerfile .
 
+ARG DISTRO=debian
 ARG REL=
-FROM debian:$REL
+FROM $DISTRO:$REL
+ARG DISTRO=debian
 ARG REL=
 
 WORKDIR /root
@@ -20,8 +22,8 @@ RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" -o "$REL" = "bookworm" ]; then
     echo 'APT::Install-Suggests false;' >> /etc/apt/apt.conf
 
 RUN apt-get update
-RUN apt-get -y install fio liburing-dev libgoogle-perftools-dev devscripts
+RUN DEBIAN_FRONTEND=noninteractive TZ=Europe/Moscow apt-get -y install fio liburing-dev libgoogle-perftools-dev devscripts
-RUN apt-get -y build-dep qemu
+RUN DEBIAN_FRONTEND=noninteractive TZ=Europe/Moscow apt-get -y build-dep qemu
 # To build a custom version
 #RUN cp /root/packages/qemu-orig/* /root
 RUN apt-get --download-only source qemu
@@ -38,9 +40,9 @@ ADD src/client/qemu_driver.c /root/qemu_driver.c
 #    apt-get install -y vitastor-client vitastor-client-dev quilt
 
 RUN set -e; \
-    dpkg -i /root/packages/vitastor-$REL/vitastor-client_*.deb /root/packages/vitastor-$REL/vitastor-client-dev_*.deb; \
+    DEBIAN_FRONTEND=noninteractive TZ=Europe/Moscow apt-get -y install /root/packages/vitastor-$REL/vitastor-client_*.deb /root/packages/vitastor-$REL/vitastor-client-dev_*.deb; \
     apt-get update; \
-    apt-get install -y quilt; \
+    DEBIAN_FRONTEND=noninteractive TZ=Europe/Moscow apt-get -y install quilt; \
     mkdir -p /root/packages/qemu-$REL; \
     rm -rf /root/packages/qemu-$REL/*; \
     cd /root/packages/qemu-$REL; \

debian/rules

@@ -4,6 +4,14 @@ export DH_VERBOSE = 1
 %:
 	dh $@
 
+override_dh_install:
+	perl -pe 's!prefix=/usr!prefix='`pwd`'/debian/tmp/usr!' < obj-x86_64-linux-gnu/src/client/vitastor.pc > node-binding/vitastor.pc
+	cd node-binding && PKG_CONFIG_PATH=./ PKG_CONFIG_ALLOW_SYSTEM_CFLAGS=1 npm install --unsafe-perm || exit 1
+	mkdir -p debian/tmp/usr/lib/x86_64-linux-gnu/nodejs/vitastor/build/Release
+	cp -v node-binding/package.json node-binding/index.js node-binding/addon.cc node-binding/addon.h node-binding/client.cc node-binding/client.h debian/tmp/usr/lib/x86_64-linux-gnu/nodejs/vitastor
+	cp -v node-binding/build/Release/addon.node debian/tmp/usr/lib/x86_64-linux-gnu/nodejs/vitastor/build/Release
+	dh_install
+
 override_dh_installdeb:
 	cat debian/fio_version >> debian/vitastor-fio.substvars
 	[ -f debian/qemu_version ] && (cat debian/qemu_version >> debian/vitastor-qemu.substvars) || true

debian/vitastor.Dockerfile

@@ -22,7 +22,8 @@ RUN set -e -x; \
     echo 'APT::Install-Suggests false;' >> /etc/apt/apt.conf
 
 RUN apt-get update && \
-    apt-get -y install fio liburing-dev libgoogle-perftools-dev devscripts libjerasure-dev cmake libibverbs-dev librdmacm-dev libisal-dev libnl-3-dev libnl-genl-3-dev curl && \
+    apt-get -y install fio liburing-dev libgoogle-perftools-dev devscripts libjerasure-dev cmake \
+        libibverbs-dev librdmacm-dev libisal-dev libnl-3-dev libnl-genl-3-dev curl nodejs npm node-nan node-bindings && \
     apt-get -y build-dep fio && \
     apt-get --download-only source fio
 

docker/Dockerfile

@@ -1,9 +1,11 @@
 # Build Docker image with Vitastor packages
 
-FROM debian:bullseye
+FROM debian:bookworm
 
-ADD vitastor.list /etc/apt/sources.list.d
+ADD etc/apt /etc/apt/
-ADD vitastor.gpg /etc/apt/trusted.gpg.d
+RUN apt-get update && apt-get -y install vitastor qemu-system-x86 qemu-system-common qemu-block-extra qemu-utils jq nfs-common && apt-get clean
-ADD vitastor.pref /etc/apt/preferences.d
+ADD sleep.sh /usr/bin/
-ADD apt.conf /etc/apt/
+ADD install.sh /usr/bin/
-RUN apt-get update && apt-get -y install vitastor qemu-system-x86 qemu-system-common && apt-get clean
+ADD scripts /opt/scripts/
+ADD etc /etc/
+RUN ln -s /usr/lib/vitastor/mon/make-etcd /usr/bin/make-etcd

docker/Makefile

@@ -0,0 +1,9 @@
+VITASTOR_VERSION ?= v1.11.0
+
+all: build push
+
+build:
+	@docker build --rm -t vitalif/vitastor:$(VITASTOR_VERSION) .
+
+push:
+	@docker push vitalif/vitastor:$(VITASTOR_VERSION)

docker/etc/apt/sources.list.d/vitastor.list

@@ -0,0 +1 @@
+deb http://vitastor.io/debian bookworm main

docker/etc/systemd/system/vitastor-etcd.service

@@ -0,0 +1,27 @@
+[Unit]
+Description=Containerized etcd for Vitastor
+After=network-online.target local-fs.target time-sync.target docker.service vitastor-host.service
+Wants=network-online.target local-fs.target time-sync.target docker.service vitastor-host.service
+PartOf=vitastor.target
+
+[Service]
+Restart=always
+Environment=GOGC=50
+EnvironmentFile=/etc/vitastor/docker.conf
+EnvironmentFile=/etc/vitastor/etcd.conf
+SyslogIdentifier=etcd
+ExecStart=bash -c 'docker run --rm -i -v /var/lib/vitastor/etcd:/data \
+    --log-driver none --network host $CONTAINER_OPTIONS --name vitastor-etcd \
+    $ETCD_IMAGE /usr/local/bin/etcd --name "$ETCD_NAME" --data-dir /data \
+    --snapshot-count 10000 --advertise-client-urls http://$ETCD_IP:2379 --listen-client-urls http://$ETCD_IP:2379 \
+    --initial-advertise-peer-urls http://$ETCD_IP:2380 --listen-peer-urls http://$ETCD_IP:2380 \
+    --initial-cluster-token vitastor-etcd-1 --initial-cluster "$ETCD_INITIAL_CLUSTER" \
+    --initial-cluster-state new --max-txn-ops=100000 --max-request-bytes=104857600 \
+    --auto-compaction-retention=10 --auto-compaction-mode=revision'
+ExecStop=docker stop vitastor-etcd
+Restart=always
+StartLimitInterval=0
+RestartSec=10
+
+[Install]
+WantedBy=multi-user.target

docker/etc/systemd/system/vitastor-host.service

@@ -0,0 +1,23 @@
+[Unit]
+Description=Empty container for running Vitastor commands
+After=network-online.target local-fs.target time-sync.target docker.service
+Wants=network-online.target local-fs.target time-sync.target docker.service
+PartOf=vitastor.target
+
+[Service]
+Restart=always
+EnvironmentFile=/etc/vitastor/docker.conf
+ExecStart=bash -c 'docker run --rm -i -v /etc/vitastor:/etc/vitastor -v /dev:/dev \
+    --privileged --log-driver none --network host --name vitastor vitastor:$VITASTOR_VERSION \
+    sleep.sh'
+ExecStartPost=udevadm trigger
+ExecStop=docker stop vitastor
+WorkingDirectory=/
+PrivateTmp=false
+TasksMax=infinity
+Restart=always
+StartLimitInterval=0
+RestartSec=10
+
+[Install]
+WantedBy=multi-user.target

docker/etc/systemd/system/vitastor-mon.service

@@ -0,0 +1,23 @@
+[Unit]
+Description=Containerized Vitastor monitor
+After=network-online.target local-fs.target time-sync.target docker.service
+Wants=network-online.target local-fs.target time-sync.target docker.service
+PartOf=vitastor.target
+
+[Service]
+Restart=always
+EnvironmentFile=/etc/vitastor/docker.conf
+SyslogIdentifier=vitastor-mon
+ExecStart=bash -c 'docker run --rm -i -v /etc/vitastor:/etc/vitastor -v /var/lib/vitastor:/var/lib/vitastor -v /dev:/dev \
+    --log-driver none --network host $CONTAINER_OPTIONS --name vitastor-mon vitastor:$VITASTOR_VERSION \
+    node /usr/lib/vitastor/mon/mon-main.js'
+ExecStop=docker stop vitastor-mon
+WorkingDirectory=/
+PrivateTmp=false
+TasksMax=infinity
+Restart=always
+StartLimitInterval=0
+RestartSec=10
+
+[Install]
+WantedBy=multi-user.target

docker/etc/systemd/system/vitastor-osd@.service

@@ -0,0 +1,27 @@
+[Unit]
+Description=Containerized Vitastor object storage daemon osd.%i
+After=network-online.target local-fs.target time-sync.target docker.service vitastor-host.service
+Wants=network-online.target local-fs.target time-sync.target docker.service vitastor-host.service
+PartOf=vitastor.target
+
+[Service]
+LimitNOFILE=1048576
+LimitNPROC=1048576
+LimitMEMLOCK=infinity
+EnvironmentFile=/etc/vitastor/docker.conf
+SyslogIdentifier=vitastor-osd%i
+ExecStart=bash -c 'docker run --rm -i -v /etc/vitastor:/etc/vitastor -v /dev:/dev \
+    $(for i in $(ls /dev/vitastor/osd%i-*); do echo --device $i:$i; done) \
+    --log-driver none --network host --ulimit nofile=1048576 --ulimit memlock=-1 $CONTAINER_OPTIONS --name vitastor-osd%i \
+    vitastor:$VITASTOR_VERSION vitastor-disk exec-osd /dev/vitastor/osd%i-data'
+ExecStartPre=+docker exec vitastor vitastor-disk pre-exec /dev/vitastor/osd%i-data
+ExecStop=docker stop vitastor-etcd%i
+WorkingDirectory=/
+PrivateTmp=false
+TasksMax=infinity
+Restart=always
+StartLimitInterval=0
+RestartSec=10
+
+[Install]
+WantedBy=vitastor.target

docker/etc/systemd/system/vitastor.target

@@ -0,0 +1,4 @@
+[Unit]
+Description=vitastor target
+[Install]
+WantedBy=multi-user.target

docker/etc/udev/rules.d/90-vitastor.rules

@@ -0,0 +1,7 @@
+SUBSYSTEM=="block", ENV{ID_PART_ENTRY_TYPE}=="e7009fac-a5a1-4d72-af72-53de13059903", \
+    OWNER="vitastor", GROUP="vitastor", \
+    IMPORT{program}="/usr/bin/docker exec vitastor vitastor-disk udev $devnode", \
+    SYMLINK+="vitastor/$env{VITASTOR_ALIAS}"
+
+ENV{VITASTOR_OSD_NUM}!="", ACTION=="add", RUN{program}+="/usr/bin/systemctl enable --now --no-block vitastor-osd@$env{VITASTOR_OSD_NUM}"
+ENV{VITASTOR_OSD_NUM}!="", ACTION=="remove", RUN{program}+="/usr/bin/systemctl disable --now --no-block vitastor-osd@$env{VITASTOR_OSD_NUM}"

docker/etc/vitastor/docker.conf

@@ -0,0 +1,11 @@
+#
+# Configuration file for containerized Vitastor installation
+# (non-Kubernetes, with systemd and udev-based orchestration)
+#
+
+# Desired Vitastor version
+VITASTOR_VERSION=1.11.0
+
+# Additional arguments for all containers
+# For example, you may want to specify a custom logging driver here
+CONTAINER_OPTIONS=""

docker/etc/vitastor/etcd.conf

@@ -0,0 +1,4 @@
+ETCD_IMAGE=quay.io/coreos/etcd:v3.5.18
+ETCD_NAME=""
+ETCD_IP=""
+ETCD_INITIAL_CLUSTER=""

docker/etc/vitastor/vitastor.conf

@@ -0,0 +1,2 @@
+{
+}

docker/install.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+
+set -e
+
+cp -urv /etc/default /host-etc/
+cp -urv /etc/systemd /host-etc/
+cp -urv /etc/udev /host-etc/
+cp -urnv /etc/vitastor /host-etc/
+cp -urnv /opt/scripts/* /host-bin/

docker/scripts/vitastor-cli

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+docker exec -it vitastor vitastor-cli "$@"

docker/scripts/vitastor-disk

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+docker exec -it vitastor vitastor-disk "$@"

docker/scripts/vitastor-fio

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+docker exec -it vitastor fio "$@"

docker/scripts/vitastor-nbd

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+docker exec -it vitastor vitastor-nbd "$@"

docker/sleep.sh

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+while :; do sleep infinity; done

docker/vitastor.list

@@ -1 +0,0 @@
-deb http://vitastor.io/debian bullseye main

docs/config.en.md

@@ -13,7 +13,7 @@ Vitastor configuration consists of:
 - [Separate OSD settings](config/pool.en.md#osd-settings)
 - [Inode configuration](config/inode.en.md) i.e. image metadata like name, size and parent reference
 
-Configuration parameters can be set in 3 places:
+Configuration parameters can be set in 4 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.

docs/config.ru.md

@@ -14,7 +14,7 @@
 - [Настроек инодов](config/inode.ru.md), т.е. метаданных образов, таких, как имя, размер и ссылки на
   родительский образ
 
-Параметры конфигурации могут задаваться в 3 местах:
+Параметры конфигурации могут задаваться в 4 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,

docs/config/client.en.md

@@ -13,6 +13,7 @@ affect their interaction with the cluster.
 - [client_retry_interval](#client_retry_interval)
 - [client_eio_retry_interval](#client_eio_retry_interval)
 - [client_retry_enospc](#client_retry_enospc)
+- [client_wait_up_timeout](#client_wait_up_timeout)
 - [client_max_dirty_bytes](#client_max_dirty_bytes)
 - [client_max_dirty_ops](#client_max_dirty_ops)
 - [client_enable_writeback](#client_enable_writeback)
@@ -70,6 +71,19 @@ and clients are not blocked and just get EIO error code instead.
 Retry writes on out of space errors to wait until some space is freed on
 OSDs.
 
+## client_wait_up_timeout
+
+- Type: seconds
+- Default: 16
+- Can be changed online: yes
+
+Wait for this number of seconds until PGs are up when doing operations
+which require all PGs to be up. Currently only used by object listings
+in delete and merge-based commands ([vitastor-cli rm](../usage/cli.en.md#rm), merge and so on).
+
+The default value is calculated as `1 + OSD lease timeout`, which is
+`1 + etcd_report_interval + max_etcd_attempts*2*etcd_quick_timeout`.
+
 ## client_max_dirty_bytes
 
 - Type: integer

docs/config/client.ru.md

@@ -13,6 +13,7 @@
 - [client_retry_interval](#client_retry_interval)
 - [client_eio_retry_interval](#client_eio_retry_interval)
 - [client_retry_enospc](#client_retry_enospc)
+- [client_wait_up_timeout](#client_wait_up_timeout)
 - [client_max_dirty_bytes](#client_max_dirty_bytes)
 - [client_max_dirty_ops](#client_max_dirty_ops)
 - [client_enable_writeback](#client_enable_writeback)
@@ -72,6 +73,19 @@ RDMA и хотите повысить пиковую производитель
 Повторять запросы записи, завершившиеся с ошибками нехватки места, т.е.
 ожидать, пока на OSD не освободится место.
 
+## client_wait_up_timeout
+
+- Тип: секунды
+- Значение по умолчанию: 16
+- Можно менять на лету: да
+
+Время ожидания поднятия PG при операциях, требующих активности всех PG.
+В данный момент используется листингами объектов в командах, использующих
+удаление и слияние ([vitastor-cli rm](../usage/cli.ru.md#rm), merge и подобные).
+
+Значение по умолчанию вычисляется как `1 + время lease OSD`, равное
+`1 + etcd_report_interval + max_etcd_attempts*2*etcd_quick_timeout`.
+
 ## client_max_dirty_bytes
 
 - Тип: целое число

docs/config/osd.en.md

@@ -316,7 +316,7 @@ for hot data and slower disks - HDDs and maybe SATA SSDs - but will slightly
 decrease write performance for fast disks because page cache is an overhead
 itself.
 
-Choose "directsync" to use [immediate_commit](layout-cluster.ru.md#immediate_commit)
+Choose "directsync" to use [immediate_commit](layout-cluster.en.md#immediate_commit)
 (which requires disable_data_fsync) with drives having write-back cache
 which can't be turned off, for example, Intel Optane. Also note that *some*
 desktop SSDs (for example, HP EX950) may ignore O_SYNC thus making

docs/config/pool.en.md

@@ -43,7 +43,7 @@ Parameters:
 - [osd_tags](#osd_tags)
 - [primary_affinity_tags](#primary_affinity_tags)
 - [scrub_interval](#scrub_interval)
-- [used_for_fs](#used_for_fs)
+- [used_for_app](#used_for_app)
 
 Examples:
 
@@ -377,24 +377,37 @@ of the OSDs containing a data chunk for a PG.
 Automatic scrubbing interval for this pool. Overrides
 [global scrub_interval setting](osd.en.md#scrub_interval).
 
-## used_for_fs
+## used_for_app
 
 - Type: string
 
-If non-empty, the pool is marked as used for VitastorFS with metadata stored
+If non-empty, the pool is marked as used for a separate application, for example,
-in block image (regular Vitastor volume) named as the value of this pool parameter.
+VitastorFS or S3, which allocates Vitastor volume IDs by itself and does not use
+image/inode metadata in etcd.
 
-When a pool is marked as used for VitastorFS, regular block volume creation in it
+When a pool is marked as used for such app, regular block volume creation in it
 is disabled (vitastor-cli refuses to create images without --force) to protect
-the user from block volume and FS file ID collisions and data loss.
+the user from block volume and FS/S3 volume ID collisions and data loss.
 
-[vitastor-nfs](../usage/nfs.ru.md), in its turn, refuses to use pools not marked
+Also such pools do not calculate per-inode space usage statistics in etcd because
+using it for an external application implies that it may contain a very large
+number of volumes and their statistics may take too much space in etcd.
+
+Setting used_for_app to `fs:<name>` tells Vitastor that the pool is used for VitastorFS
+with VitastorKV metadata base stored in a block image (regular Vitastor volume) named
+`<name>`.
+
+[vitastor-nfs](../usage/nfs.en.md), in its turn, refuses to use pools not marked
 for the corresponding FS when starting. This also implies that you can use one
 pool only for one VitastorFS.
 
-The second thing that is disabled for VitastorFS pools is reporting per-inode space
+If you plan to use the pool for S3, set its used_for_app to `s3:<name>`. `<name>` may
-usage statistics in etcd because a FS pool may store a very large number of files
+be basically anything you want (for example, `s3:standard`) - it's not validated
-and statistics for them all would take a lot of space in etcd.
+by Vitastor S3 components in any way.
+
+All other values except prefixed with `fs:` or `s3:` may be used freely and don't
+mean anything special for Vitastor core components. For now, you can use them as
+you wish.
 
 # Examples
 

docs/config/pool.ru.md

@@ -42,7 +42,7 @@
 - [osd_tags](#osd_tags)
 - [primary_affinity_tags](#primary_affinity_tags)
 - [scrub_interval](#scrub_interval)
-- [used_for_fs](#used_for_fs)
+- [used_for_app](#used_for_app)
 
 Примеры:
 
@@ -256,7 +256,7 @@ PG в Vitastor эферемерны, то есть вы можете менят
 
 ## raw_placement
 
-- Type: string
+- Тип: строка
 
 Низкоуровневые правила генерации PG в форме DSL (доменно-специфичного языка).
 Используйте, только если действительно знаете, зачем вам это надо :)
@@ -383,26 +383,39 @@ OSD с "all".
 Интервал скраба, то есть, автоматической фоновой проверки данных для данного пула.
 Переопределяет [глобальную настройку scrub_interval](osd.ru.md#scrub_interval).
 
-## used_for_fs
+## used_for_app
 
-- Type: string
+- Тип: строка
 
-Если непусто, пул помечается как используемый для файловой системы VitastorFS с
+Если непусто, пул помечается как используемый для отдельного приложения, например,
-метаданными, хранимыми в блочном образе Vitastor с именем, равным значению
+для VitastorFS или S3, которое распределяет ID образов в пуле само и не использует
-этого параметра.
+метаданные образов/инодов в etcd.
 
-Когда пул помечается как используемый для VitastorFS, создание обычных блочных
+Когда пул помечается используемым для такого приложения, создание обычных блочных
-образов в нём отключается (vitastor-cli отказывается создавать образы без --force),
+образов в нём запрещается (vitastor-cli отказывается создавать образы без --force),
-чтобы защитить пользователя от коллизий ID файлов и блочных образов и, таким
+чтобы защитить пользователя от коллизий ID блочных образов и томов ФС/S3, и,
-образом, от потери данных.
+таким образом, от потери данных.
+
+Также для таких пулов отключается передача статистики в etcd по отдельным инодам,
+так как использование для внешнего приложения подразумевает, что пул может содержать
+очень много томов и их статистика может занять слишком много места в etcd.
+
+Установка used_for_app в значение `fs:<name>` сообщает о том, что пул используется
+для VitastorFS с базой метаданных VitastorKV, хранимой в блочном образе с именем
+`<name>`.
 
 [vitastor-nfs](../usage/nfs.ru.md), в свою очередь, при запуске отказывается
-использовать для ФС пулы, не выделенные для неё. Это также означает, что один
+использовать для ФС пулы, не помеченные, как используемые для неё. Это также
-пул может использоваться только для одной VitastorFS.
+означает, что один пул может использоваться только для одной VitastorFS.
 
-Также для ФС-пулов отключается передача статистики в etcd по отдельным инодам,
+Если же вы планируете использовать пул для данных S3, установите его used_for_app
-так как ФС-пул может содержать очень много файлов и статистика по ним всем
+в значение `s3:<name>`, где `<name>` - любое название по вашему усмотрению
-заняла бы очень много места в etcd.
+(например, `s3:standard`) - конкретное содержимое `<name>` пока никак не проверяется
+компонентами Vitastor S3.
+
+Все остальные значения used_for_app, кроме начинающихся на `fs:` или `s3:`, не
+означают ничего особенного для основных компонентов Vitastor. Поэтому сейчас вы
+можете использовать их свободно любым желаемым способом.
 
 # Примеры
 

docs/config/src/included.en.md

@@ -14,8 +14,12 @@
 
 {{../../installation/packages.en.md}}
 
+{{../../installation/docker.en.md}}
+
 {{../../installation/proxmox.en.md}}
 
+{{../../installation/opennebula.en.md}}
+
 {{../../installation/openstack.en.md}}
 
 {{../../installation/kubernetes.en.md}}

docs/config/src/included.ru.md

@@ -14,8 +14,12 @@
 
 {{../../installation/packages.ru.md}}
 
+{{../../installation/docker.ru.md}}
+
 {{../../installation/proxmox.ru.md}}
 
+{{../../installation/opennebula.ru.md}}
+
 {{../../installation/openstack.ru.md}}
 
 {{../../installation/kubernetes.ru.md}}

docs/config/src/osd.yml

@@ -315,7 +315,7 @@
     decrease write performance for fast disks because page cache is an overhead
     itself.
 
-    Choose "directsync" to use [immediate_commit](layout-cluster.ru.md#immediate_commit)
+    Choose "directsync" to use [immediate_commit](layout-cluster.en.md#immediate_commit)
     (which requires disable_data_fsync) with drives having write-back cache
     which can't be turned off, for example, Intel Optane. Also note that *some*
     desktop SSDs (for example, HP EX950) may ignore O_SYNC thus making

docs/installation/docker.en.md

@@ -0,0 +1,60 @@
+[Documentation](../../README.md#documentation) → Installation → Dockerized Installation
+
+-----
+
+[Читать на русском](docker.ru.md)
+
+# Dockerized Installation
+
+Vitastor may be installed in Docker/Podman. In such setups etcd, monitors and OSD
+all run in containers, but everything else looks as close as possible to a usual
+setup with packages:
+- host network is used
+- auto-start is implemented through udev and systemd
+- logs are written to journald (not docker json log files)
+- command-line wrapper scripts are installed to the host system to call vitastor-disk,
+  vitastor-cli and others through the container
+
+Such installations may be useful when it's impossible or inconvenient to install
+Vitastor from packages, for example, in exotic Linux distributions.
+
+If you don't want just a simple containerized installation, you can also take a look
+at Vitastor Kubernetes operator: https://github.com/Antilles7227/vitastor-operator
+
+## Installing Containers
+
+The instruction is very simple.
+
+1. Download a Docker image of the desired version: \
+   `docker pull vitastor:1.10.2`
+2. Install scripts to the host system: \
+   `docker run --rm -it -v /etc:/host-etc -v /usr/bin:/host-bin vitastor:1.10.2 install.sh`
+3. Reload udev rules: \
+   `udevadm control --reload-rules`
+
+And you can return to [Quick Start](../intro/quickstart.en.md).
+
+## Upgrading Containers
+
+First make sure to check the topic [Upgrading Vitastor](../usage/admin.en.md#upgrading-vitastor)
+to figure out if you need any additional steps.
+
+Then, to upgrade a containerized installation, you just need to change the `VITASTOR_VERSION`
+option in `/etc/vitastor/docker.conf` and restart all Vitastor services:
+
+`systemctl restart vitastor.target`
+
+## QEMU
+
+Vitastor Docker image also contains QEMU, qemu-img and qemu-storage-daemon built with Vitastor support.
+
+However, running QEMU in Docker is harder to setup and it depends on the used virtualization UI
+(OpenNebula, Proxmox and so on). Some of them also required patched Libvirt.
+
+That's why containerized installation of Vitastor doesn't contain a ready-made QEMU setup and it's
+recommended to install QEMU from packages or build it manually.
+
+## fio
+
+Vitastor Docker image also contains fio and installs a wrapper called `vitastor-fio` to use it from
+the host system.

docs/installation/docker.ru.md

@@ -0,0 +1,60 @@
+[Документация](../../README-ru.md#документация) → Установка → Установка в Docker
+
+-----
+
+[Read in English](docker.en.md)
+
+# Установка в Docker
+
+Vitastor можно установить в Docker/Podman. При этом etcd, мониторы и OSD запускаются
+в контейнерах, но всё остальное выглядит максимально приближенно к установке из пакетов:
+- используется сеть хост-системы
+- для автозапуска используются udev и systemd
+- журналы записываются в journald (не в json-файлы журналов docker)
+- в хост-систему устанавливаются обёртки для вызова консольных инструментов vitastor-disk,
+  vitastor-cli и других через контейнер
+
+Такая установка полезна тогда, когда установка из пакетов невозможна или неудобна,
+например, в нестандартных Linux-дистрибутивах.
+
+Если вам нужна не просто контейнеризованная инсталляция, вы также можете обратить внимание
+на Vitastor Kubernetes-оператор: https://github.com/Antilles7227/vitastor-operator
+
+## Установка контейнеров
+
+Инструкция по установке максимально простая.
+
+1. Скачайте Docker-образ желаемой версии: \
+   `docker pull vitastor:1.10.2`
+2. Установите скрипты в хост-систему командой: \
+   `docker run --rm -it -v /etc:/host-etc -v /usr/bin:/host-bin vitastor:1.10.2 install.sh`
+3. Перезагрузите правила udev: \
+   `udevadm control --reload-rules`
+
+После этого вы можете возвращаться к разделу [Быстрый старт](../intro/quickstart.ru.md).
+
+## Обновление контейнеров
+
+Сначала обязательно проверьте раздел [Обновление Vitastor](../usage/admin.ru.md#обновление-vitastor),
+чтобы понять, не требуются ли вам какие-то дополнительные действия.
+
+После этого для обновления Docker-инсталляции вам нужно просто поменять опцию `VITASTOR_VERSION`
+в файле `/etc/vitastor/docker.conf` и перезапустить все сервисы Vitastor командой:
+
+`systemctl restart vitastor.target`
+
+## QEMU
+
+В Docker-образ также входят QEMU, qemu-img и qemu-storage-daemon, собранные с поддержкой Vitastor.
+
+Однако настроить запуск QEMU в Docker сложнее и способ запуска зависит от используемого интерфейса
+виртуализации (OpenNebula, Proxmox и т.п.). Также для OpenNebula, например, требуется патченый
+Libvirt.
+
+Поэтому по умолчанию Docker-сборка пока что не включает в себя готового способа запуска QEMU
+и QEMU рекомендуется устанавливать из пакетов или собирать самостоятельно.
+
+## fio
+
+fio также входит в Docker-контейнер vitastor, и в хост-систему устанавливается обёртка `vitastor-fio`
+для запуска fio в контейнер.

docs/installation/packages.en.md

@@ -14,6 +14,7 @@
   - Debian 12 (Bookworm/Sid): `deb https://vitastor.io/debian bookworm main`
   - Debian 11 (Bullseye): `deb https://vitastor.io/debian bullseye main`
   - Debian 10 (Buster): `deb https://vitastor.io/debian buster main`
+  - Ubuntu 22.04 (Jammy): `deb https://vitastor.io/debian jammy main`
   - Add `-oldstable` to bookworm/bullseye/buster in this line to install the last
     stable version from 0.9.x branch instead of 1.x
 - Install packages: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu-system-x86`

docs/installation/packages.ru.md

@@ -14,6 +14,7 @@
   - Debian 12 (Bookworm/Sid): `deb https://vitastor.io/debian bookworm main`
   - Debian 11 (Bullseye): `deb https://vitastor.io/debian bullseye main`
   - Debian 10 (Buster): `deb https://vitastor.io/debian buster main`
+  - Ubuntu 22.04 (Jammy): `deb https://vitastor.io/debian jammy main`
   - Добавьте `-oldstable` к слову bookworm/bullseye/buster в этой строке, чтобы
     установить последнюю стабильную версию из ветки 0.9.x вместо 1.x
 - Установите пакеты: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu-system-x86`

docs/intro/quickstart.en.md

@@ -26,13 +26,13 @@
   you also need small SSDs for journal and metadata (even 2 GB per 1 TB of HDD space is enough).
 - 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](../installation/packages.en.md).
+- Either [install Vitastor packages](../installation/packages.en.md) or [install Vitastor in Docker](../installation/docker.en.md).
 
 ## Recommended drives
 
 - SATA SSD: Micron 5100/5200/5300/5400, Samsung PM863/PM883/PM893, Intel D3-S4510/4520/4610/4620, Kingston DC500M
 - NVMe: Micron 9100/9200/9300/9400, Micron 7300/7450, Samsung PM983/PM9A3, Samsung PM1723/1735/1743,
-  Intel DC-P3700/P4500/P4600, Intel D5-P4320, Intel D7-P5500/P5600, Intel Optane, Kingston DC1000B/DC1500M
+  Intel DC-P3700/P4500/P4600, Intel D5-P4320/P5530, Intel D7-P5500/P5600, Intel Optane, Kingston DC1000B/DC1500M
 - HDD: HGST Ultrastar, Toshiba MG, Seagate EXOS
 
 ## Configure monitors
@@ -45,7 +45,8 @@ On the monitor hosts:
   }
   ```
 - Create systemd units for etcd by running: `/usr/lib/vitastor/mon/make-etcd`
-- Start etcd and monitors: `systemctl enable --now etcd vitastor-mon`
+  Or, if you installed Vitastor in Docker, run `systemctl start vitastor-host; docker exec vitastor make-etcd`.
+- Start etcd and monitors: `systemctl enable --now vitastor-etcd vitastor-mon`
 
 ## Configure OSDs
 

docs/intro/quickstart.ru.md

@@ -26,13 +26,13 @@
   обязательно возьмите SSD под метаданные и журнал (маленькие, буквально 2 ГБ на 1 ТБ HDD-места).
 - Возьмите быструю сеть, минимум 10 гбит/с. Идеал - что-то вроде Mellanox ConnectX-4 с RoCEv2.
 - Для лучшей производительности отключите энергосбережение CPU: `cpupower idle-set -D 0 && cpupower frequency-set -g performance`.
-- [Установите пакеты Vitastor](../installation/packages.ru.md).
+- Либо [установите пакеты Vitastor](../installation/packages.ru.md), либо [установите Vitastor в Docker](../installation/docker.ru.md).
 
 ## Рекомендуемые диски
 
 - SATA SSD: Micron 5100/5200/5300/5400, Samsung PM863/PM883/PM893, Intel D3-S4510/4520/4610/4620, Kingston DC500M
 - NVMe: Micron 9100/9200/9300/9400, Micron 7300/7450, Samsung PM983/PM9A3, Samsung PM1723/1735/1743,
-  Intel DC-P3700/P4500/P4600, Intel D5-P4320, Intel D7-P5500/P5600, Intel Optane, Kingston DC1000B/DC1500M
+  Intel DC-P3700/P4500/P4600, Intel D5-P4320/P5530, Intel D7-P5500/P5600, Intel Optane, Kingston DC1000B/DC1500M
 - HDD: HGST Ultrastar, Toshiba MG, Seagate EXOS
 
 ## Настройте мониторы
@@ -44,8 +44,9 @@
     "etcd_address": ["10.200.1.10:2379","10.200.1.11:2379","10.200.1.12:2379"]
   }
   ```
-- Инициализируйте сервисы etcd, запустив `/usr/lib/vitastor/mon/make-etcd`
+- Инициализируйте сервисы etcd, запустив `/usr/lib/vitastor/mon/make-etcd`.\
-- Запустите etcd и мониторы: `systemctl enable --now etcd vitastor-mon`
+  Либо, если вы установили Vitastor в Docker, запустите `systemctl start vitastor-host; docker exec vitastor make-etcd`.
+- Запустите etcd и мониторы: `systemctl enable --now vitastor-etcd vitastor-mon`
 
 ## Настройте OSD
 

docs/usage/cli.en.md

@@ -37,7 +37,7 @@ It supports the following commands:
 Global options:
 
 ```
---config_file FILE   Path to Vitastor configuration file
+--config_path FILE   Path to Vitastor configuration file
 --etcd_address URL   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)
@@ -398,7 +398,8 @@ Optional parameters:
 | `--raw_placement <rules>`      | Specify raw PG generation rules ([details](../config/pool.en.md#raw_placement)) |
 | `--primary_affinity_tags tags` | Prefer to put primary copies on OSDs with all specified tags               |
 | `--scrub_interval <time>`      | Enable regular scrubbing for this pool. Format: number + unit s/m/h/d/M/y  |
-| `--used_for_fs <name>`         | Mark pool as used for VitastorFS with metadata in image <name>             |
+| `--used_for_app fs:<name>`     | Mark pool as used for VitastorFS with metadata in image `<name>`           |
+| `--used_for_app s3:<name>`     | Mark pool as used for S3 location with name `<name>`                       |
 | `--pg_stripe_size <number>`    | Increase object grouping stripe                                            |
 | `--max_osd_combinations 10000` | Maximum number of random combinations for LP solver input                  |
 | `--wait`                       | Wait for the new pool to come online                                       |

docs/usage/cli.ru.md

@@ -36,7 +36,7 @@ vitastor-cli - интерфейс командной строки для адм
 Глобальные опции:
 
 ```
---config_file FILE   Путь к файлу конфигурации Vitastor
+--config_path FILE   Путь к файлу конфигурации Vitastor
 --etcd_address URL   Адрес соединения с etcd
 --iodepth N          Отправлять параллельно N операций на каждый OSD (по умолчанию 32)
 --parallel_osds M    Работать параллельно с M OSD (по умолчанию 4)

docs/usage/nbd.en.md

@@ -36,7 +36,7 @@ It will output a block device name like /dev/nbd0 which you can then use as a no
 
 You can also use `--pool <POOL> --inode <INODE> --size <SIZE>` instead of `--image <IMAGE>` if you want.
 
-vitastor-nbd supports all usual Vitastor configuration options like `--config_file <path_to_config>` plus NBD-specific:
+vitastor-nbd supports all usual Vitastor configuration options like `--config_path <path_to_config>` plus NBD-specific:
 
 * `--nbd_timeout 0` \
   Timeout for I/O operations in seconds after exceeding which the kernel stops the device.
@@ -54,16 +54,18 @@ vitastor-nbd supports all usual Vitastor configuration options like `--config_fi
   Stay in foreground, do not daemonize.
 
 Note that `nbd_timeout`, `nbd_max_devices` and `nbd_max_part` options may also be specified
-in `/etc/vitastor/vitastor.conf` or in other configuration file specified with `--config_file`.
+in `/etc/vitastor/vitastor.conf` or in other configuration file specified with `--config_path`.
 
 ## unmap
 
 To unmap the device run:
 
 ```
-vitastor-nbd unmap /dev/nbd0
+vitastor-nbd unmap [--force] /dev/nbd0
 ```
 
+If `--force` is specified, `vitastor-nbd` doesn't check if the device is actually mapped.
+
 ## ls
 
 ```

docs/usage/nbd.ru.md

@@ -41,7 +41,7 @@ vitastor-nbd map [/dev/nbdN] --image testimg
 Для обращения по номеру инода, аналогично другим командам, можно использовать опции
 `--pool <POOL> --inode <INODE> --size <SIZE>` вместо `--image testimg`.
 
-vitastor-nbd поддерживает все обычные опции Vitastor, например, `--config_file <path_to_config>`,
+vitastor-nbd поддерживает все обычные опции Vitastor, например, `--config_path <path_to_config>`,
 плюс специфичные для NBD:
 
 * `--nbd_timeout 0` \
@@ -62,16 +62,19 @@ vitastor-nbd поддерживает все обычные опции Vitastor,
 
 Обратите внимание, что опции `nbd_timeout`, `nbd_max_devices` и `nbd_max_part` можно
 также задавать в `/etc/vitastor/vitastor.conf` или в другом файле конфигурации,
-заданном опцией `--config_file`.
+заданном опцией `--config_path`.
 
 ## unmap
 
 Для отключения устройства выполните:
 
 ```
-vitastor-nbd unmap /dev/nbd0
+vitastor-nbd unmap [--force] /dev/nbd0
 ```
 
+Если задана опция `--force`, `vitastor-nbd` не проверяет, подключено ли устройство,
+перед попыткой его отключить.
+
 ## ls
 
 ```

docs/usage/nfs.en.md

@@ -58,7 +58,7 @@ To use VitastorFS:
 2. Create an image for FS metadata, preferably in a faster (SSD or replica-HDD) pool,
    but you can create it in the data pool too if you want (image size doesn't matter):
    `vitastor-cli create -s 10G -p fastpool testfs`
-3. Mark data pool as an FS pool: `vitastor-cli modify-pool --used-for-fs testfs data-pool`
+3. Mark data pool as an FS pool: `vitastor-cli modify-pool --used-for-app fs:testfs data-pool`
 4. Either mount the FS: `vitastor-nfs mount --fs testfs --pool data-pool /mnt/vita`
 5. Or start the NFS server: `vitastor-nfs start --fs testfs --pool data-pool`
 

docs/usage/nfs.ru.md

@@ -60,7 +60,7 @@ JSON-формате :-). Для инспекции содержимого БД
    или по крайней мере на HDD, но без EC), но можно и в том же пуле, что данные
    (размер образа значения не имеет):
    `vitastor-cli create -s 10G -p fastpool testfs`
-3. Пометьте пул данных как ФС-пул: `vitastor-cli modify-pool --used-for-fs testfs data-pool`
+3. Пометьте пул данных как ФС-пул: `vitastor-cli modify-pool --used-for-app fs:testfs data-pool`
 4. Либо примонтируйте ФС: `vitastor-nfs mount --fs testfs --pool data-pool /mnt/vita`
 5. Либо запустите сетевой NFS-сервер: `vitastor-nfs start --fs testfs --pool data-pool`
 

mon/mon.js

@@ -773,23 +773,27 @@ class Mon
                 }
             }
         }
-        for (const pool_id in this.state.pool.stats)
+        if (!this.recheck_pgs_active)
         {
-            if (!seen_pools[pool_id])
+            // PG recheck also modifies /pool/stats, so don't touch it here if it's active
+            for (const pool_id in this.state.pool.stats)
             {
-                txn.push({ requestDeleteRange: {
+                if (!seen_pools[pool_id])
-                    key: b64(this.config.etcd_prefix+'/pool/stats/'+pool_id),
+                {
-                } });
+                    txn.push({ requestDeleteRange: {
-                delete this.state.pool.stats[pool_id];
+                        key: b64(this.config.etcd_prefix+'/pool/stats/'+pool_id),
-            }
+                    } });
-            else
+                    delete this.state.pool.stats[pool_id];
-            {
+                }
-                const pool_stats = { ...this.state.pool.stats[pool_id] };
+                else
-                serialize_bigints(pool_stats);
+                {
-                txn.push({ requestPut: {
+                    const pool_stats = { ...this.state.pool.stats[pool_id] };
-                    key: b64(this.config.etcd_prefix+'/pool/stats/'+pool_id),
+                    serialize_bigints(pool_stats);
-                    value: b64(JSON.stringify(pool_stats)),
+                    txn.push({ requestPut: {
-                } });
+                        key: b64(this.config.etcd_prefix+'/pool/stats/'+pool_id),
+                        value: b64(JSON.stringify(pool_stats)),
+                    } });
+                }
             }
         }
         if (txn.length)

mon/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vitastor-mon",
-  "version": "1.10.1",
+  "version": "1.11.0",
   "description": "Vitastor SDS monitor service",
   "main": "mon-main.js",
   "scripts": {
@@ -9,7 +9,7 @@
   "author": "Vitaliy Filippov",
   "license": "UNLICENSED",
   "dependencies": {
-    "antietcd": "^1.1.0",
+    "antietcd": "^1.1.2",
     "sprintf-js": "^1.1.2",
     "ws": "^7.2.5"
   },

mon/pg_gen.js

@@ -8,23 +8,9 @@ const LPOptimizer = require('./lp_optimizer/lp_optimizer.js');
 const { scale_pg_count } = require('./pg_utils.js');
 const { make_hier_tree, filter_osds_by_root_node,
     filter_osds_by_tags, filter_osds_by_block_layout, get_affinity_osds } = require('./osd_tree.js');
+const { select_murmur3 } = require('./lp_optimizer/murmur3.js');
 
-let seed;
+function pick_primary(pool_id, pg_num, pool_config, osd_set, up_osds, aff_osds)
-
-function reset_rng()
-{
-    seed = 0x5f020e43;
-}
-
-function rng()
-{
-    seed ^= seed << 13;
-    seed ^= seed >> 17;
-    seed ^= seed << 5;
-    return seed + 2147483648;
-}
-
-function pick_primary(pool_config, osd_set, up_osds, aff_osds)
 {
     let alive_set;
     if (pool_config.scheme === 'replicated')
@@ -52,7 +38,7 @@ function pick_primary(pool_config, osd_set, up_osds, aff_osds)
     {
         return 0;
     }
-    return alive_set[rng() % alive_set.length];
+    return alive_set[select_murmur3(alive_set.length, osd_num => pool_id+'/'+pg_num+'/'+osd_num)];
 }
 
 function recheck_primary(state, global_config, up_osds, osd_tree)
@@ -66,7 +52,6 @@ function recheck_primary(state, global_config, up_osds, osd_tree)
             continue;
         }
         const aff_osds = get_affinity_osds(pool_cfg, up_osds, osd_tree);
-        reset_rng();
         for (let pg_num = 1; pg_num <= pool_cfg.pg_count; pg_num++)
         {
             if (!state.pg.config.items[pool_id])
@@ -76,7 +61,7 @@ function recheck_primary(state, global_config, up_osds, osd_tree)
             const pg_cfg = state.pg.config.items[pool_id][pg_num];
             if (pg_cfg)
             {
-                const new_primary = pick_primary(state.config.pools[pool_id], pg_cfg.osd_set, up_osds, aff_osds);
+                const new_primary = pick_primary(pool_id, pg_num, state.config.pools[pool_id], pg_cfg.osd_set, up_osds, aff_osds);
                 if (pg_cfg.primary != new_primary)
                 {
                     if (!new_pg_config)
@@ -99,13 +84,12 @@ function save_new_pgs_txn(save_to, request, state, etcd_prefix, etcd_watch_revis
 {
     const aff_osds = get_affinity_osds(state.config.pools[pool_id] || {}, up_osds, osd_tree);
     const pg_items = {};
-    reset_rng();
     new_pgs.map((osd_set, i) =>
     {
         osd_set = osd_set.map(osd_num => osd_num === LPOptimizer.NO_OSD ? 0 : osd_num);
         pg_items[i+1] = {
             osd_set,
-            primary: pick_primary(state.config.pools[pool_id], osd_set, up_osds, aff_osds),
+            primary: pick_primary(pool_id, i+1, state.config.pools[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)

mon/scripts/make-etcd

@@ -33,9 +33,11 @@ async function run()
         console.log(config_path+' is missing');
         process.exit(1);
     }
-    if (fs.existsSync("/etc/systemd/system/etcd.service"))
+    const in_docker = fs.existsSync("/etc/vitastor/etcd.conf") &&
+        fs.existsSync("/etc/vitastor/docker.conf");
+    if (!in_docker && fs.existsSync("/etc/systemd/system/vitastor-etcd.service"))
     {
-        console.log("/etc/systemd/system/etcd.service already exists");
+        console.log("/etc/systemd/system/vitastor-etcd.service already exists");
         process.exit(1);
     }
     const config = JSON.parse(fs.readFileSync(config_path, { encoding: 'utf-8' }));
@@ -52,10 +54,21 @@ async function run()
         console.log('No matching IPs in etcd_address from '+config_path);
         process.exit(0);
     }
-    const etcd_cluster = etcds.map((e, i) => `etcd${i}=http://${e}:2380`).join(',');
+    const etcd_name = 'etcd'+etcds[num].replace(/[^0-9a-z_]/ig, '_');
-    await system(`mkdir -p /var/lib/etcd${num}.etcd`);
+    const etcd_cluster = etcds.map(e => `etcd${e.replace(/[^0-9a-z_]/ig, '_')}=http://${e}:2380`).join(',');
+    if (in_docker)
+    {
+        let etcd_conf = fs.readFileSync("/etc/vitastor/etcd.conf", { encoding: 'utf-8' });
+        etcd_conf = replace_env(etcd_conf, 'ETCD_NAME', etcd_name);
+        etcd_conf = replace_env(etcd_conf, 'ETCD_IP', etcds[num]);
+        etcd_conf = replace_env(etcd_conf, 'ETCD_INITIAL_CLUSTER', etcd_cluster);
+        fs.writeFileSync("/etc/vitastor/etcd.conf", etcd_conf);
+        console.log('etcd for Vitastor configured. Run `systemctl enable --now vitastor-etcd` to start etcd');
+        process.exit(0);
+    }
+    await system(`mkdir -p /var/lib/etcd`);
     fs.writeFileSync(
-        "/etc/systemd/system/etcd.service",
+        "/etc/systemd/system/vitastor-etcd.service",
 `[Unit]
 Description=etcd for vitastor
 After=network-online.target local-fs.target time-sync.target
@@ -64,14 +77,14 @@ Wants=network-online.target local-fs.target time-sync.target
 [Service]
 Restart=always
 Environment=GOGC=50
-ExecStart=etcd -name etcd${num} --data-dir /var/lib/etcd${num}.etcd \\
+ExecStart=etcd --name ${etcd_name} --data-dir /var/lib/etcd \\
     --snapshot-count 10000 --advertise-client-urls http://${etcds[num]}:2379 --listen-client-urls http://${etcds[num]}:2379 \\
     --initial-advertise-peer-urls http://${etcds[num]}:2380 --listen-peer-urls http://${etcds[num]}:2380 \\
     --initial-cluster-token vitastor-etcd-1 --initial-cluster ${etcd_cluster} \\
     --initial-cluster-state new --max-txn-ops=100000 --max-request-bytes=104857600 \\
     --auto-compaction-retention=10 --auto-compaction-mode=revision
-WorkingDirectory=/var/lib/etcd${num}.etcd
+WorkingDirectory=/var/lib/etcd
-ExecStartPre=+chown -R etcd /var/lib/etcd${num}.etcd
+ExecStartPre=+chown -R etcd /var/lib/etcd
 User=etcd
 PrivateTmp=false
 TasksMax=infinity
@@ -89,6 +102,13 @@ WantedBy=multi-user.target
     process.exit(0);
 }
 
+function replace_env(text, key, value)
+{
+    let found = false;
+    text = text.replace(new RegExp('^'+key+'\\s*=.*', 'm'), () => { found = true; return key+'='+value; });
+    return found ? text : text.replace(/\s*$/, '\n')+key+'='+value+'\n';
+}
+
 function select_local_etcd(etcds)
 {
     const ifaces = os.networkInterfaces();

mon/scripts/vitastor-mon.service

@@ -5,6 +5,7 @@ Wants=network-online.target local-fs.target time-sync.target
 
 [Service]
 Restart=always
+SyslogIdentifier=vitastor-mon
 ExecStart=node /usr/lib/vitastor/mon/mon-main.js
 WorkingDirectory=/
 User=vitastor

mon/scripts/vitastor-osd@.service

@@ -8,6 +8,7 @@ PartOf=vitastor.target
 LimitNOFILE=1048576
 LimitNPROC=1048576
 LimitMEMLOCK=infinity
+SyslogIdentifier=vitastor-osd%i
 # Use the following for direct logs to files
 #ExecStart=bash -c 'exec vitastor-disk exec-osd /dev/vitastor/osd%i-data >>/var/log/vitastor/osd%i.log 2>&1'
 ExecStart=vitastor-disk exec-osd /dev/vitastor/osd%i-data

node-binding/addon.cc

@@ -14,8 +14,13 @@ NAN_MODULE_INIT(InitAddon)
 
     Nan::SetPrototypeMethod(tpl, "read", NodeVitastor::Read);
     Nan::SetPrototypeMethod(tpl, "write", NodeVitastor::Write);
+    Nan::SetPrototypeMethod(tpl, "delete", NodeVitastor::Delete);
     Nan::SetPrototypeMethod(tpl, "sync", NodeVitastor::Sync);
     Nan::SetPrototypeMethod(tpl, "read_bitmap", NodeVitastor::ReadBitmap);
+    Nan::SetPrototypeMethod(tpl, "on_ready", NodeVitastor::OnReady);
+    Nan::SetPrototypeMethod(tpl, "get_min_io_size", NodeVitastor::GetMinIoSize);
+    Nan::SetPrototypeMethod(tpl, "get_max_atomic_write_size", NodeVitastor::GetMaxAtomicWriteSize);
+    Nan::SetPrototypeMethod(tpl, "get_immediate_commit", NodeVitastor::GetImmediateCommit);
     //Nan::SetPrototypeMethod(tpl, "destroy", NodeVitastor::Destroy);
 
     Nan::Set(target, Nan::New("Client").ToLocalChecked(), Nan::GetFunction(tpl).ToLocalChecked());
@@ -63,6 +68,10 @@ NAN_MODULE_INIT(InitAddon)
     Nan::Set(target, Nan::New("ENOSYS").ToLocalChecked(), Nan::New<v8::Int32>(-ENOSYS));
     Nan::Set(target, Nan::New("EAGAIN").ToLocalChecked(), Nan::New<v8::Int32>(-EAGAIN));
 
+    Nan::Set(target, Nan::New("IMMEDIATE_NONE").ToLocalChecked(), Nan::New<v8::Int32>(IMMEDIATE_NONE));
+    Nan::Set(target, Nan::New("IMMEDIATE_SMALL").ToLocalChecked(), Nan::New<v8::Int32>(IMMEDIATE_SMALL));
+    Nan::Set(target, Nan::New("IMMEDIATE_ALL").ToLocalChecked(), Nan::New<v8::Int32>(IMMEDIATE_ALL));
+
     // Listing handle
 
     tpl = Nan::New<v8::FunctionTemplate>(NodeVitastorKVListing::Create);

node-binding/client.cc

@@ -5,9 +5,10 @@
 
 #define NODE_VITASTOR_READ 1
 #define NODE_VITASTOR_WRITE 2
-#define NODE_VITASTOR_SYNC 3
+#define NODE_VITASTOR_DELETE 3
-#define NODE_VITASTOR_READ_BITMAP 4
+#define NODE_VITASTOR_SYNC 4
-#define NODE_VITASTOR_GET_INFO 5
+#define NODE_VITASTOR_READ_BITMAP 5
+#define NODE_VITASTOR_GET_INFO 6
 
 #ifndef INODE_POOL
 #define INODE_POOL(inode) (uint32_t)((inode) >> (64 - POOL_ID_BITS))
@@ -80,6 +81,11 @@ NAN_METHOD(NodeVitastor::Create)
     NodeVitastor* cli = new NodeVitastor();
     cli->c = vitastor_c_create_uring_json(c_cfg, cfg.size());
     delete[] c_cfg;
+    if (!cli->c)
+    {
+        Nan::ThrowError("failed to initialize io_uring (old kernel or insufficient ulimit -l?)");
+        return;
+    }
 
     int res = vitastor_c_uring_register_eventfd(cli->c);
     if (res >= 0)
@@ -133,12 +139,12 @@ NodeVitastorRequest* NodeVitastor::get_read_request(const Nan::FunctionCallbackI
     return req;
 }
 
-// read(pool, inode, offset, len, callback(err, buffer, version))
+// read(pool, inode, offset, length, callback(err, buffer, version))
 NAN_METHOD(NodeVitastor::Read)
 {
     TRACE("NodeVitastor::Read");
     if (info.Length() < 5)
-        Nan::ThrowError("Not enough arguments to read(pool, inode, offset, len, callback(err, buffer, version))");
+        Nan::ThrowError("Not enough arguments to read(pool, inode, offset, length, callback(err, buffer, version))");
 
     NodeVitastor* self = Nan::ObjectWrap::Unwrap<NodeVitastor>(info.This());
 
@@ -149,6 +155,9 @@ NAN_METHOD(NodeVitastor::Read)
 
     self->Ref();
     vitastor_c_read(self->c, ((pool << (64-POOL_ID_BITS)) | inode), req->offset, req->len, &req->iov, 1, on_read_finish, req);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+    vitastor_c_uring_handle_events(self->c);
+#endif
 }
 
 NodeVitastorRequest* NodeVitastor::get_write_request(const Nan::FunctionCallbackInfo<v8::Value> & info, int argpos)
@@ -217,6 +226,58 @@ NAN_METHOD(NodeVitastor::Write)
         req->iov_list.size() ? req->iov_list.data() : &req->iov,
         req->iov_list.size() ? req->iov_list.size() : 1,
         on_write_finish, req);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+    vitastor_c_uring_handle_events(self->c);
+#endif
+}
+
+NodeVitastorRequest* NodeVitastor::get_delete_request(const Nan::FunctionCallbackInfo<v8::Value> & info, int argpos)
+{
+    uint64_t offset = get_ui64(info[argpos+0]);
+    uint64_t len = get_ui64(info[argpos+1]);
+    uint64_t version = 0;
+    if (!info[argpos+2].IsEmpty() &&
+        !info[argpos+2]->IsFunction() &&
+        info[argpos+2]->IsObject())
+    {
+        auto key = Nan::New<v8::String>("version").ToLocalChecked();
+        auto params = info[argpos+2].As<v8::Object>();
+        auto versionObj = Nan::Get(params, key).ToLocalChecked();
+        if (!versionObj.IsEmpty())
+            version = get_ui64(versionObj);
+        argpos++;
+    }
+
+    v8::Local<v8::Function> callback = info[argpos+2].As<v8::Function>();
+    auto req = new NodeVitastorRequest(this, callback);
+
+    req->offset = offset;
+    req->len = len;
+    req->version = version;
+
+    return req;
+}
+
+// delete(pool, inode, offset, length, { version }?, callback(err))
+NAN_METHOD(NodeVitastor::Delete)
+{
+    TRACE("NodeVitastor::Delete");
+    if (info.Length() < 5)
+        Nan::ThrowError("Not enough arguments to delete(pool, inode, offset, length, { version }?, callback(err))");
+
+    NodeVitastor* self = Nan::ObjectWrap::Unwrap<NodeVitastor>(info.This());
+
+    uint64_t pool = get_ui64(info[0]);
+    uint64_t inode = get_ui64(info[1]);
+
+    auto req = self->get_delete_request(info, 2);
+
+    self->Ref();
+    vitastor_c_delete(self->c, ((pool << (64-POOL_ID_BITS)) | inode), req->offset, req->len, req->version,
+        on_write_finish, req);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+    vitastor_c_uring_handle_events(self->c);
+#endif
 }
 
 // sync(callback(err))
@@ -233,14 +294,17 @@ NAN_METHOD(NodeVitastor::Sync)
 
     self->Ref();
     vitastor_c_sync(self->c, on_write_finish, req);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+    vitastor_c_uring_handle_events(self->c);
+#endif
 }
 
-// read_bitmap(pool, inode, offset, len, with_parents, callback(err, bitmap_buffer))
+// read_bitmap(pool, inode, offset, length, with_parents, callback(err, bitmap_buffer))
 NAN_METHOD(NodeVitastor::ReadBitmap)
 {
     TRACE("NodeVitastor::ReadBitmap");
     if (info.Length() < 6)
-        Nan::ThrowError("Not enough arguments to read_bitmap(pool, inode, offset, len, with_parents, callback(err, bitmap_buffer))");
+        Nan::ThrowError("Not enough arguments to read_bitmap(pool, inode, offset, length, with_parents, callback(err, bitmap_buffer))");
 
     NodeVitastor* self = Nan::ObjectWrap::Unwrap<NodeVitastor>(info.This());
 
@@ -254,6 +318,9 @@ NAN_METHOD(NodeVitastor::ReadBitmap)
     auto req = new NodeVitastorRequest(self, callback);
     self->Ref();
     vitastor_c_read_bitmap(self->c, ((pool << (64-POOL_ID_BITS)) | inode), offset, len, with_parents, on_read_bitmap_finish, req);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+    vitastor_c_uring_handle_events(self->c);
+#endif
 }
 
 static void on_error(NodeVitastorRequest *req, Nan::Callback & nanCallback, long retval)
@@ -267,6 +334,67 @@ static void on_error(NodeVitastorRequest *req, Nan::Callback & nanCallback, long
     nanCallback.Call(1, args, req);
 }
 
+// on_ready(callback(err))
+NAN_METHOD(NodeVitastor::OnReady)
+{
+    TRACE("NodeVitastor::OnReady");
+    if (info.Length() < 1)
+        Nan::ThrowError("Not enough arguments to on_ready(callback(err))");
+    NodeVitastor* self = Nan::ObjectWrap::Unwrap<NodeVitastor>(info.This());
+    v8::Local<v8::Function> callback = info[0].As<v8::Function>();
+    auto req = new NodeVitastorRequest(self, callback);
+    self->Ref();
+    vitastor_c_on_ready(self->c, on_ready_finish, req);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+    vitastor_c_uring_handle_events(self->c);
+#endif
+}
+
+void NodeVitastor::on_ready_finish(void *opaque, long retval)
+{
+    TRACE("NodeVitastor::on_ready_finish");
+    auto req = (NodeVitastorRequest*)opaque;
+    auto self = req->cli;
+    Nan::HandleScope scope;
+    Nan::Callback nanCallback(Nan::New(req->callback));
+    nanCallback.Call(0, NULL, req);
+    self->Unref();
+    delete req;
+}
+
+// get_min_io_size(pool_id)
+NAN_METHOD(NodeVitastor::GetMinIoSize)
+{
+    TRACE("NodeVitastor::GetMinIoSize");
+    if (info.Length() < 1)
+        Nan::ThrowError("Not enough arguments to get_min_io_size(pool_id)");
+    NodeVitastor* self = Nan::ObjectWrap::Unwrap<NodeVitastor>(info.This());
+    uint64_t pool = get_ui64(info[0]);
+    info.GetReturnValue().Set(Nan::New<v8::Number>(vitastor_c_inode_get_bitmap_granularity(self->c, INODE_WITH_POOL(pool, 1))));
+}
+
+// get_max_atomic_write_size(pool_id)
+NAN_METHOD(NodeVitastor::GetMaxAtomicWriteSize)
+{
+    TRACE("NodeVitastor::GetMaxAtomicWriteSize");
+    if (info.Length() < 1)
+        Nan::ThrowError("Not enough arguments to get_max_atomic_write_size(pool_id)");
+    NodeVitastor* self = Nan::ObjectWrap::Unwrap<NodeVitastor>(info.This());
+    uint64_t pool = get_ui64(info[0]);
+    info.GetReturnValue().Set(Nan::New<v8::Number>(vitastor_c_inode_get_block_size(self->c, INODE_WITH_POOL(pool, 1))));
+}
+
+// get_immediate_commit(pool_id)
+NAN_METHOD(NodeVitastor::GetImmediateCommit)
+{
+    TRACE("NodeVitastor::GetImmediateCommit");
+    if (info.Length() < 1)
+        Nan::ThrowError("Not enough arguments to get_immediate_commit(pool_id)");
+    NodeVitastor* self = Nan::ObjectWrap::Unwrap<NodeVitastor>(info.This());
+    uint64_t pool = get_ui64(info[0]);
+    info.GetReturnValue().Set(Nan::New<v8::Number>(vitastor_c_inode_get_immediate_commit(self->c, INODE_WITH_POOL(pool, 1))));
+}
+
 void NodeVitastor::on_read_finish(void *opaque, long retval, uint64_t version)
 {
     TRACE("NodeVitastor::on_read_finish");
@@ -364,6 +492,9 @@ NAN_METHOD(NodeVitastorImage::Create)
     img->Ref();
     cli->Ref();
     vitastor_c_watch_inode(cli->c, (char*)img->name.c_str(), on_watch_start, img);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+    vitastor_c_uring_handle_events(cli->c);
+#endif
 
     info.GetReturnValue().Set(info.This());
 }
@@ -378,12 +509,12 @@ NodeVitastorImage::~NodeVitastorImage()
     cli->Unref();
 }
 
-// read(offset, len, callback(err, buffer, version))
+// read(offset, length, callback(err, buffer, version))
 NAN_METHOD(NodeVitastorImage::Read)
 {
     TRACE("NodeVitastorImage::Read");
     if (info.Length() < 3)
-        Nan::ThrowError("Not enough arguments to read(offset, len, callback(err, buffer, version))");
+        Nan::ThrowError("Not enough arguments to read(offset, length, callback(err, buffer, version))");
 
     NodeVitastorImage* img = Nan::ObjectWrap::Unwrap<NodeVitastorImage>(info.This());
 
@@ -394,12 +525,12 @@ NAN_METHOD(NodeVitastorImage::Read)
     img->exec_or_wait(req);
 }
 
-// write(offset, buffer, { version }?, callback(err))
+// write(offset, buf: Buffer | Buffer[], { version }?, callback(err))
 NAN_METHOD(NodeVitastorImage::Write)
 {
     TRACE("NodeVitastorImage::Write");
     if (info.Length() < 3)
-        Nan::ThrowError("Not enough arguments to write(offset, buffer, { version }?, callback(err))");
+        Nan::ThrowError("Not enough arguments to write(offset, buf: Buffer | Buffer[], { version }?, callback(err))");
 
     NodeVitastorImage* img = Nan::ObjectWrap::Unwrap<NodeVitastorImage>(info.This());
 
@@ -410,6 +541,22 @@ NAN_METHOD(NodeVitastorImage::Write)
     img->exec_or_wait(req);
 }
 
+// delete(offset, length, { version }?, callback(err))
+NAN_METHOD(NodeVitastorImage::Delete)
+{
+    TRACE("NodeVitastorImage::Delete");
+    if (info.Length() < 3)
+        Nan::ThrowError("Not enough arguments to delete(offset, length, { version }?, callback(err))");
+
+    NodeVitastorImage* img = Nan::ObjectWrap::Unwrap<NodeVitastorImage>(info.This());
+
+    auto req = img->cli->get_delete_request(info, 0);
+    req->img = img;
+    req->op = NODE_VITASTOR_DELETE;
+
+    img->exec_or_wait(req);
+}
+
 // sync(callback(err))
 NAN_METHOD(NodeVitastorImage::Sync)
 {
@@ -427,12 +574,12 @@ NAN_METHOD(NodeVitastorImage::Sync)
     img->exec_or_wait(req);
 }
 
-// read_bitmap(offset, len, with_parents, callback(err, bitmap_buffer))
+// read_bitmap(offset, length, with_parents, callback(err, bitmap_buffer))
 NAN_METHOD(NodeVitastorImage::ReadBitmap)
 {
     TRACE("NodeVitastorImage::ReadBitmap");
     if (info.Length() < 4)
-        Nan::ThrowError("Not enough arguments to read_bitmap(offset, len, with_parents, callback(err, bitmap_buffer))");
+        Nan::ThrowError("Not enough arguments to read_bitmap(offset, length, with_parents, callback(err, bitmap_buffer))");
 
     NodeVitastorImage* img = Nan::ObjectWrap::Unwrap<NodeVitastorImage>(info.This());
 
@@ -488,6 +635,9 @@ void NodeVitastorImage::exec_request(NodeVitastorRequest *req)
         uint64_t ino = vitastor_c_inode_get_num(watch);
         cli->Ref();
         vitastor_c_read(cli->c, ino, req->offset, req->len, &req->iov, 1, NodeVitastor::on_read_finish, req);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+        vitastor_c_uring_handle_events(cli->c);
+#endif
     }
     else if (req->op == NODE_VITASTOR_WRITE)
     {
@@ -497,6 +647,19 @@ void NodeVitastorImage::exec_request(NodeVitastorRequest *req)
             req->iov_list.size() ? req->iov_list.data() : &req->iov,
             req->iov_list.size() ? req->iov_list.size() : 1,
             NodeVitastor::on_write_finish, req);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+        vitastor_c_uring_handle_events(cli->c);
+#endif
+    }
+    else if (req->op == NODE_VITASTOR_DELETE)
+    {
+        uint64_t ino = vitastor_c_inode_get_num(watch);
+        cli->Ref();
+        vitastor_c_delete(cli->c, ino, req->offset, req->len, req->version,
+            NodeVitastor::on_write_finish, req);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+        vitastor_c_uring_handle_events(cli->c);
+#endif
     }
     else if (req->op == NODE_VITASTOR_SYNC)
     {
@@ -506,6 +669,9 @@ void NodeVitastorImage::exec_request(NodeVitastorRequest *req)
         if (imm != IMMEDIATE_ALL)
         {
             vitastor_c_sync(cli->c, NodeVitastor::on_write_finish, req);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+            vitastor_c_uring_handle_events(cli->c);
+#endif
         }
         else
         {
@@ -517,6 +683,9 @@ void NodeVitastorImage::exec_request(NodeVitastorRequest *req)
         uint64_t ino = vitastor_c_inode_get_num(watch);
         cli->Ref();
         vitastor_c_read_bitmap(cli->c, ino, req->offset, req->len, req->with_parents, NodeVitastor::on_read_bitmap_finish, req);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+        vitastor_c_uring_handle_events(cli->c);
+#endif
     }
     else if (req->op == NODE_VITASTOR_GET_INFO)
     {
@@ -648,6 +817,9 @@ NAN_METHOD(NodeVitastorKV::Open)
         delete req;
         kv->Unref();
     });
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+    vitastor_c_uring_handle_events(kv->cli->c);
+#endif
 }
 
 // close(callback(err))
@@ -671,6 +843,9 @@ NAN_METHOD(NodeVitastorKV::Close)
         delete req;
         kv->Unref();
     });
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+    vitastor_c_uring_handle_events(kv->cli->c);
+#endif
 }
 
 // set_config({ ...config })
@@ -729,6 +904,9 @@ void NodeVitastorKV::get_impl(const Nan::FunctionCallbackInfo<v8::Value> & info,
         delete req;
         kv->Unref();
     }, allow_cache);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+    vitastor_c_uring_handle_events(kv->cli->c);
+#endif
 }
 
 // get(key, callback(err, value))
@@ -801,6 +979,9 @@ NAN_METHOD(NodeVitastorKV::Set)
             delete cas_req;
         kv->Unref();
     }, cas_cb);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+    vitastor_c_uring_handle_events(kv->cli->c);
+#endif
 }
 
 // del(key, callback(err), cas_compare(old_value)?)
@@ -839,6 +1020,9 @@ NAN_METHOD(NodeVitastorKV::Del)
             delete cas_req;
         kv->Unref();
     }, cas_cb);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+    vitastor_c_uring_handle_events(kv->cli->c);
+#endif
 }
 
 // list(start_key?)
@@ -909,7 +1093,7 @@ NodeVitastorKVListing::~NodeVitastorKVListing()
     kv->Unref();
 }
 
-// next(callback(err, value)?)
+// next(callback(err, key, value)?)
 NAN_METHOD(NodeVitastorKVListing::Next)
 {
     TRACE("NodeVitastorKVListing::Next");
@@ -959,6 +1143,9 @@ NAN_METHOD(NodeVitastorKVListing::Next)
             list->iter = req;
         list->kv->Unref();
     });
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
+    vitastor_c_uring_handle_events(list->kv->cli->c);
+#endif
 }
 
 // close()

node-binding/client.h

@@ -15,14 +15,24 @@ class NodeVitastor: public Nan::ObjectWrap
 public:
     // constructor({ ...config })
     static NAN_METHOD(Create);
-    // read(pool, inode, offset, len, callback(err, buffer, version))
+    // read(pool_id, inode, offset, length, callback(err, buffer, version))
     static NAN_METHOD(Read);
-    // write(pool, inode, offset, buf: Buffer | Buffer[], { version }?, callback(err))
+    // write(pool_id, inode, offset, buf: Buffer | Buffer[], { version }?, callback(err))
     static NAN_METHOD(Write);
+    // delete(pool_id, inode, offset, length, { version }?, callback(err))
+    static NAN_METHOD(Delete);
     // sync(callback(err))
     static NAN_METHOD(Sync);
-    // read_bitmap(pool, inode, offset, len, with_parents, callback(err, bitmap_buffer))
+    // read_bitmap(pool_id, inode, offset, length, with_parents, callback(err, bitmap_buffer))
     static NAN_METHOD(ReadBitmap);
+    // on_ready(callback(err))
+    static NAN_METHOD(OnReady);
+    // get_min_io_size(pool_id)
+    static NAN_METHOD(GetMinIoSize);
+    // get_max_atomic_write_size(pool_id)
+    static NAN_METHOD(GetMaxAtomicWriteSize);
+    // get_immediate_commit(pool_id)
+    static NAN_METHOD(GetImmediateCommit);
 //    // destroy()
 //    static NAN_METHOD(Destroy);
 
@@ -37,11 +47,13 @@ private:
 
     static void on_io_readable(uv_poll_t* handle, int status, int revents);
     static void on_read_finish(void *opaque, long retval, uint64_t version);
+    static void on_ready_finish(void *opaque, long retval);
     static void on_write_finish(void *opaque, long retval);
     static void on_read_bitmap_finish(void *opaque, long retval, uint8_t *bitmap);
 
     NodeVitastorRequest* get_read_request(const Nan::FunctionCallbackInfo<v8::Value> & info, int argpos);
     NodeVitastorRequest* get_write_request(const Nan::FunctionCallbackInfo<v8::Value> & info, int argpos);
+    NodeVitastorRequest* get_delete_request(const Nan::FunctionCallbackInfo<v8::Value> & info, int argpos);
 
     friend class NodeVitastorImage;
     friend class NodeVitastorKV;
@@ -53,13 +65,15 @@ class NodeVitastorImage: public Nan::ObjectWrap
 public:
     // constructor(node_vitastor, name)
     static NAN_METHOD(Create);
-    // read(offset, len, callback(err, buffer, version))
+    // read(offset, length, callback(err, buffer, version))
     static NAN_METHOD(Read);
     // write(offset, buf: Buffer | Buffer[], { version }?, callback(err))
     static NAN_METHOD(Write);
+    // delete(offset, length, { version }?, callback(err))
+    static NAN_METHOD(Delete);
     // sync(callback(err))
     static NAN_METHOD(Sync);
-    // read_bitmap(offset, len, with_parents, callback(err, bitmap_buffer))
+    // read_bitmap(offset, length, with_parents, callback(err, bitmap_buffer))
     static NAN_METHOD(ReadBitmap);
     // get_info(callback({ num, name, size, parent_id?, readonly?, meta?, mod_revision, block_size, bitmap_granularity, immediate_commit }))
     static NAN_METHOD(GetInfo);
@@ -120,7 +134,7 @@ class NodeVitastorKVListing: public Nan::ObjectWrap
 public:
     // constructor(node_vitastor_kv, start_key?)
     static NAN_METHOD(Create);
-    // next(callback(err, value)?)
+    // next(callback(err, key, value)?)
     static NAN_METHOD(Next);
     // close()
     static NAN_METHOD(Close);

node-binding/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vitastor",
-  "version": "1.7.0",
+  "version": "1.11.0",
   "description": "Low-level native bindings to Vitastor client library",
   "main": "index.js",
   "keywords": [

patches/cinder-vitastor.py

@@ -50,7 +50,7 @@ from cinder.volume import configuration
 from cinder.volume import driver
 from cinder.volume import volume_utils
 
-VITASTOR_VERSION = '1.10.1'
+VITASTOR_VERSION = '1.11.0'
 
 LOG = logging.getLogger(__name__)
 

rpm/vitastor-el7.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        1.10.1
+Version:        1.11.0
 Release:        1%{?dist}
 Summary:        Vitastor, a fast software-defined clustered block storage
 
 License:        Vitastor Network Public License 1.1
 URL:            https://vitastor.io/
-Source0:        vitastor-1.10.1.el7.tar.gz
+Source0:        vitastor-1.11.0.el7.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

rpm/vitastor-el8.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        1.10.1
+Version:        1.11.0
 Release:        1%{?dist}
 Summary:        Vitastor, a fast software-defined clustered block storage
 
 License:        Vitastor Network Public License 1.1
 URL:            https://vitastor.io/
-Source0:        vitastor-1.10.1.el8.tar.gz
+Source0:        vitastor-1.11.0.el8.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

rpm/vitastor-el9.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        1.10.1
+Version:        1.11.0
 Release:        1%{?dist}
 Summary:        Vitastor, a fast software-defined clustered block storage
 
 License:        Vitastor Network Public License 1.1
 URL:            https://vitastor.io/
-Source0:        vitastor-1.10.1.el9.tar.gz
+Source0:        vitastor-1.11.0.el9.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

src/CMakeLists.txt

@@ -19,7 +19,7 @@ if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
 	set(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
 endif()
 
-add_definitions(-DVITASTOR_VERSION="1.10.1")
+add_definitions(-DVITASTOR_VERSION="1.11.0")
 add_definitions(-D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -Wall -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith -fdiagnostics-color=always -fno-omit-frame-pointer -I ${CMAKE_SOURCE_DIR}/src)
 add_link_options(-fno-omit-frame-pointer)
 if (${WITH_ASAN})

src/blockstore/blockstore_init.cpp

@@ -256,6 +256,7 @@ resume_2:
     }
     if (entries_to_zero.size() && !bs->inmemory_meta && !bs->readonly)
     {
+        std::sort(entries_to_zero.begin(), entries_to_zero.end());
         // we have to zero out additional entries
         for (i = 0; i < entries_to_zero.size(); )
         {
@@ -338,6 +339,15 @@ bool blockstore_init_meta::handle_meta_block(uint8_t *buf, uint64_t entries_per_
                 if (*entry_csum != crc32c(0, entry, bs->dsk.clean_entry_size - 4))
                 {
                     printf("Metadata entry %ju is corrupt (checksum mismatch), skipping\n", done_cnt+i);
+                    // zero out the invalid entry, otherwise we'll hit "tried to overwrite non-zero metadata entry" later
+                    if (bs->inmemory_meta)
+                    {
+                        memset(entry, 0, bs->dsk.clean_entry_size);
+                    }
+                    else
+                    {
+                        entries_to_zero.push_back(done_cnt+i);
+                    }
                     continue;
                 }
             }

src/client/cluster_client.cpp

@@ -63,6 +63,10 @@ cluster_client_t::cluster_client_t(ring_loop_t *ringloop, timerfd_manager_t *tfd
 
     st_cli.parse_config(config);
     st_cli.infinite_start = false;
+    if (!config["client_infinite_start"].is_null())
+    {
+        st_cli.infinite_start = config["client_infinite_start"].bool_value();
+    }
     st_cli.load_global_config();
 
     scrap_buffer_size = SCRAP_BUFFER_SIZE;
@@ -309,16 +313,17 @@ void cluster_client_t::erase_op(cluster_op_t *op)
     }
     if (flags & OP_FLUSH_BUFFER)
     {
+        auto overflow = std::move(wb->writeback_overflow);
         int i = 0;
-        while (i < wb->writeback_overflow.size() && wb->writebacks_active < client_max_writeback_iodepth)
+        while (i < overflow.size() && wb->writebacks_active < client_max_writeback_iodepth)
         {
-            execute_internal(wb->writeback_overflow[i]);
+            execute_internal(overflow[i]);
             i++;
         }
         if (i > 0)
-        {
+            overflow.erase(overflow.begin(), overflow.begin()+i);
-            wb->writeback_overflow.erase(wb->writeback_overflow.begin(), wb->writeback_overflow.begin()+i);
+        assert(!wb->writeback_overflow.size());
-        }
+        wb->writeback_overflow.swap(overflow);
     }
 }
 
@@ -673,7 +678,7 @@ void cluster_client_t::execute_internal(cluster_op_t *op)
         }
         // Just copy and acknowledge the operation
         wb->copy_write(op, CACHE_DIRTY);
-        while (wb->writeback_bytes + op->len > client_max_buffered_bytes || wb->writeback_queue_size > client_max_buffered_ops)
+        while (wb->writeback_bytes > client_max_buffered_bytes || wb->writeback_queue_size > client_max_buffered_ops)
         {
             // Initiate some writeback (asynchronously)
             wb->start_writebacks(this, 1);
@@ -791,6 +796,36 @@ bool cluster_client_t::check_rw(cluster_op_t *op)
             return false;
         }
     }
+    op->deoptimise_snapshot = false;
+    if (enable_writeback && (op->opcode == OSD_OP_READ || op->opcode == OSD_OP_READ_BITMAP || op->opcode == OSD_OP_READ_CHAIN_BITMAP))
+    {
+        auto ino_it = st_cli.inode_config.find(op->inode);
+        if (ino_it != st_cli.inode_config.end())
+        {
+            int chain_size = 0;
+            while (ino_it != st_cli.inode_config.end() && ino_it->second.parent_id)
+            {
+                // Check for loops - FIXME check it in etcd_state_client
+                if (ino_it->second.parent_id == op->inode ||
+                    chain_size > st_cli.inode_config.size())
+                {
+                    op->retval = -EINVAL;
+                    auto cb = std::move(op->callback);
+                    cb(op);
+                    return false;
+                }
+                if (INODE_POOL(ino_it->second.parent_id) == INODE_POOL(ino_it->first) &&
+                    wb->has_inode(ino_it->second.parent_id))
+                {
+                    // Deoptimise reads - we have dirty data for one of the parent layer(s).
+                    op->deoptimise_snapshot = true;
+                    break;
+                }
+                chain_size++;
+                ino_it = st_cli.inode_config.find(ino_it->second.parent_id);
+            }
+        }
+    }
     return true;
 }
 
@@ -922,12 +957,21 @@ resume_2:
         {
             // Check parent inode
             auto ino_it = st_cli.inode_config.find(op->cur_inode);
-            while (ino_it != st_cli.inode_config.end() && ino_it->second.parent_id &&
+            // Skip parents from the same pool
-                INODE_POOL(ino_it->second.parent_id) == INODE_POOL(op->cur_inode) &&
+            int skipped = 0;
-                // Check for loops
+            while (!op->deoptimise_snapshot &&
-                ino_it->second.parent_id != op->inode)
+                ino_it != st_cli.inode_config.end() && ino_it->second.parent_id &&
+                INODE_POOL(ino_it->second.parent_id) == INODE_POOL(op->cur_inode))
             {
-                // Skip parents from the same pool
+                // Check for loops - FIXME check it in etcd_state_client
+                if (ino_it->second.parent_id == op->inode ||
+                    skipped > st_cli.inode_config.size())
+                {
+                    op->retval = -EINVAL;
+                    erase_op(op);
+                    return 1;
+                }
+                skipped++;
                 ino_it = st_cli.inode_config.find(ino_it->second.parent_id);
             }
             if (ino_it != st_cli.inode_config.end() &&
@@ -1106,7 +1150,7 @@ void cluster_client_t::slice_rw(cluster_op_t *op)
             if (end == begin)
             {
                 op->done_count++;
-                op->parts[i].flags = PART_DONE;
+                op->parts[i].flags = PART_SENT|PART_DONE;
             }
         }
         else if (op->opcode != OSD_OP_READ_BITMAP && op->opcode != OSD_OP_READ_CHAIN_BITMAP && op->opcode != OSD_OP_DELETE)
@@ -1189,7 +1233,7 @@ int cluster_client_t::try_send(cluster_op_t *op, int i)
                 pool_cfg.scheme == POOL_SCHEME_REPLICATED ? 1 : pool_cfg.pg_size-pool_cfg.parity_chunks
             );
             uint64_t meta_rev = 0;
-            if (op->opcode != OSD_OP_READ_BITMAP && op->opcode != OSD_OP_DELETE)
+            if (op->opcode != OSD_OP_READ_BITMAP && op->opcode != OSD_OP_DELETE && !op->deoptimise_snapshot)
             {
                 auto ino_it = st_cli.inode_config.find(op->cur_inode);
                 if (ino_it != st_cli.inode_config.end())

src/client/cluster_client.h

@@ -60,7 +60,8 @@ struct cluster_op_t
 protected:
     int state = 0;
     uint64_t cur_inode; // for snapshot reads
-    bool needs_reslice = false;
+    bool needs_reslice: 1;
+    bool deoptimise_snapshot: 1;
     int retry_after = 0;
     int inflight_count = 0, done_count = 0;
     timespec wait_up_until = {};

src/client/cluster_client_impl.h

@@ -42,10 +42,10 @@ public:
     std::multimap<uint64_t, uint64_t*> flushed_buffers; // flush_id => refcnt
 
     ~writeback_cache_t();
+    bool has_inode(uint64_t inode);
     dirty_buf_it_t find_dirty(uint64_t inode, uint64_t offset);
     bool is_left_merged(dirty_buf_it_t dirty_it);
     bool is_right_merged(dirty_buf_it_t dirty_it);
-    bool is_merged(const dirty_buf_it_t & dirty_it);
     void copy_write(cluster_op_t *op, int state, uint64_t new_flush_id = 0);
     int repeat_ops_for(cluster_client_t *cli, osd_num_t peer_osd, pool_id_t pool_id, pg_num_t pg_num);
     void start_writebacks(cluster_client_t *cli, int count);

src/client/cluster_client_wb.cpp

@@ -9,7 +9,7 @@ writeback_cache_t::~writeback_cache_t()
 {
     for (auto & bp: dirty_buffers)
     {
-        if (!--(*bp.second.refcnt))
+        if (bp.second.buf && !--(*bp.second.refcnt))
         {
             free(bp.second.refcnt); // refcnt is allocated with the buffer
         }
@@ -17,6 +17,15 @@ writeback_cache_t::~writeback_cache_t()
     dirty_buffers.clear();
 }
 
+bool writeback_cache_t::has_inode(uint64_t inode)
+{
+    auto dirty_it = dirty_buffers.lower_bound((object_id){
+        .inode = inode,
+        .stripe = 0,
+    });
+    return dirty_it != dirty_buffers.end() && dirty_it->first.inode == inode;
+}
+
 dirty_buf_it_t writeback_cache_t::find_dirty(uint64_t inode, uint64_t offset)
 {
     auto dirty_it = dirty_buffers.lower_bound((object_id){
@@ -33,7 +42,11 @@ dirty_buf_it_t writeback_cache_t::find_dirty(uint64_t inode, uint64_t offset)
             break;
         }
     }
-    return dirty_it;
+    if (dirty_it != dirty_buffers.end() && dirty_it->first.inode == inode)
+    {
+        return dirty_it;
+    }
+    return dirty_buffers.end();
 }
 
 bool writeback_cache_t::is_left_merged(dirty_buf_it_t dirty_it)
@@ -68,11 +81,6 @@ bool writeback_cache_t::is_right_merged(dirty_buf_it_t dirty_it)
     return false;
 }
 
-bool writeback_cache_t::is_merged(const dirty_buf_it_t & dirty_it)
-{
-    return is_left_merged(dirty_it) || is_right_merged(dirty_it);
-}
-
 void writeback_cache_t::copy_write(cluster_op_t *op, int state, uint64_t new_flush_id)
 {
     // Save operation for replay when one of PGs goes out of sync
@@ -107,10 +115,16 @@ void writeback_cache_t::copy_write(cluster_op_t *op, int state, uint64_t new_flu
                     .flush_id = dirty_it->second.flush_id,
                     .refcnt = dirty_it->second.refcnt,
                 });
-                (*dirty_it->second.refcnt)++;
+                if (dirty_it->second.buf)
+                {
+                    (*dirty_it->second.refcnt)++;
+                }
                 if (dirty_it->second.state == CACHE_DIRTY)
                 {
-                    writeback_bytes -= op->len;
+                    if (dirty_it->second.buf)
+                    {
+                        writeback_bytes -= op->len;
+                    }
                     writeback_queue_size++;
                 }
                 break;
@@ -120,8 +134,11 @@ void writeback_cache_t::copy_write(cluster_op_t *op, int state, uint64_t new_flu
                 // Only leave the beginning
                 if (dirty_it->second.state == CACHE_DIRTY)
                 {
-                    writeback_bytes -= old_end - op->offset;
+                    if (dirty_it->second.buf)
-                    if (is_left_merged(dirty_it) && !is_right_merged(dirty_it))
+                    {
+                        writeback_bytes -= old_end - op->offset;
+                    }
+                    if (is_right_merged(dirty_it))
                     {
                         writeback_queue_size++;
                     }
@@ -135,8 +152,11 @@ void writeback_cache_t::copy_write(cluster_op_t *op, int state, uint64_t new_flu
             // Only leave the end
             if (dirty_it->second.state == CACHE_DIRTY)
             {
-                writeback_bytes -= new_end - dirty_it->first.stripe;
+                if (dirty_it->second.buf)
-                if (!is_left_merged(dirty_it) && is_right_merged(dirty_it))
+                {
+                    writeback_bytes -= new_end - dirty_it->first.stripe;
+                }
+                if (is_left_merged(dirty_it))
                 {
                     writeback_queue_size++;
                 }
@@ -158,13 +178,25 @@ void writeback_cache_t::copy_write(cluster_op_t *op, int state, uint64_t new_flu
         else
         {
             // Remove the whole buffer
-            if (dirty_it->second.state == CACHE_DIRTY && !is_merged(dirty_it))
+            if (dirty_it->second.state == CACHE_DIRTY)
             {
-                writeback_bytes -= dirty_it->second.len;
+                if (dirty_it->second.buf)
-                assert(writeback_queue_size > 0);
+                {
-                writeback_queue_size--;
+                    writeback_bytes -= dirty_it->second.len;
+                }
+                bool lm = is_left_merged(dirty_it);
+                bool rm = is_right_merged(dirty_it);
+                if (!lm && !rm)
+                {
+                    assert(writeback_queue_size > 0);
+                    writeback_queue_size--;
+                }
+                else if (lm && rm)
+                {
+                    writeback_queue_size++;
+                }
             }
-            if (!--(*dirty_it->second.refcnt))
+            if (dirty_it->second.buf && !--(*dirty_it->second.refcnt))
             {
                 free(dirty_it->second.refcnt);
             }
@@ -175,7 +207,10 @@ void writeback_cache_t::copy_write(cluster_op_t *op, int state, uint64_t new_flu
     bool is_del = op->opcode == OSD_OP_DELETE;
     uint64_t *refcnt = is_del ? NULL : (uint64_t*)malloc_or_die(sizeof(uint64_t) + op->len);
     uint8_t *buf = is_del ? NULL : ((uint8_t*)refcnt + sizeof(uint64_t));
-    *refcnt = 1;
+    if (!is_del)
+    {
+        *refcnt = 1;
+    }
     dirty_it = dirty_buffers.emplace_hint(dirty_it, (object_id){
         .inode = op->inode,
         .stripe = op->offset,
@@ -190,7 +225,9 @@ void writeback_cache_t::copy_write(cluster_op_t *op, int state, uint64_t new_flu
     {
         writeback_bytes += is_del ? 0 : op->len;
         // Track consecutive write-back operations
-        if (!is_merged(dirty_it))
+        bool lm = is_left_merged(dirty_it);
+        bool rm = is_right_merged(dirty_it);
+        if (!lm && !rm)
         {
             // <writeback_queue> is OK to contain more than actual number of consecutive
             // requests as long as it doesn't miss anything. But <writeback_queue_size>
@@ -201,6 +238,11 @@ void writeback_cache_t::copy_write(cluster_op_t *op, int state, uint64_t new_flu
                 .stripe = op->offset,
             });
         }
+        else if (lm && rm)
+        {
+            assert(writeback_queue_size > 0);
+            writeback_queue_size--;
+        }
     }
     if (!is_del)
     {
@@ -225,7 +267,7 @@ int writeback_cache_t::repeat_ops_for(cluster_client_t *cli, osd_num_t peer_osd,
         for (auto wr_it = dirty_buffers.begin(), flush_it = wr_it, last_it = wr_it; ; )
         {
             bool end = wr_it == dirty_buffers.end();
-            bool flush_this = !end && wr_it->second.state != CACHE_REPEATING;
+            bool flush_this = !end && wr_it->second.state != CACHE_REPEATING && wr_it->second.state != CACHE_DIRTY;
             if (peer_osd)
                 flush_this = flush_this && cli->affects_osd(wr_it->first.inode, wr_it->first.stripe, wr_it->second.len, peer_osd);
             if (pool_id && pg_num)
@@ -376,6 +418,7 @@ void writeback_cache_t::start_writebacks(cluster_client_t *cli, int count)
         assert(writeback_queue_size > 0);
         writeback_queue_size--;
         writeback_bytes -= off - from_it->first.stripe;
+        assert(writeback_queue_size > 0 || !writeback_bytes);
         flush_buffers(cli, from_it, to_it);
     }
     queue_copy.erase(queue_copy.begin(), queue_copy.begin()+i);
@@ -523,8 +566,10 @@ void writeback_cache_t::fsync_ok()
     {
         if (uw_it->second.state == CACHE_FLUSHING)
         {
-            if (!--(*uw_it->second.refcnt))
+            if (uw_it->second.buf && !--(*uw_it->second.refcnt))
+            {
                 free(uw_it->second.refcnt);
+            }
             dirty_buffers.erase(uw_it++);
         }
         else

src/client/etcd_state_client.cpp

@@ -889,7 +889,11 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
             if (!pc.scrub_interval)
                 pc.scrub_interval = 0;
             // Mark pool as VitastorFS pool (disable per-inode stats and block volume creation)
-            pc.used_for_fs = pool_item.second["used_for_fs"].as_string();
+            pc.used_for_app = pool_item.second["used_for_fs"].as_string();
+            if (pc.used_for_app != "")
+                pc.used_for_app = "fs:"+pc.used_for_app;
+            else
+                pc.used_for_app = pool_item.second["used_for_app"].as_string();
             // Immediate Commit Mode
             pc.immediate_commit = pool_item.second["immediate_commit"].is_string()
                 ? parse_immediate_commit(pool_item.second["immediate_commit"].string_value(), IMMEDIATE_ALL)

src/client/etcd_state_client.h

@@ -61,7 +61,7 @@ struct pool_config_t
     uint64_t pg_stripe_size;
     std::map<pg_num_t, pg_config_t> pg_config;
     uint64_t scrub_interval;
-    std::string used_for_fs;
+    std::string used_for_app;
     int backfillfull;
 };
 

src/client/nbd_proxy.cpp

@@ -275,8 +275,8 @@ const char *help_text =
     "  --foreground 1\n"
     "    Stay in foreground, do not daemonize.\n"
     "\n"
-    "vitastor-nbd unmap /dev/nbdN\n"
+    "vitastor-nbd unmap [--force] /dev/nbdN\n"
-    "  Unmap an ioctl-mapped NBD device.\n"
+    "  Unmap an ioctl-mapped NBD device. Do not check if it's actually mapped if --force is specified.\n"
     "\n"
     "vitastor-nbd ls [--json]\n"
     "  List ioctl-mapped Vitastor NBD devices, optionally in JSON format.\n"
@@ -313,7 +313,7 @@ const char *help_text =
 #endif
     "Use vitastor-nbd --help <command> for command details or vitastor-nbd --help --all for all details.\n"
     "\n"
-    "All usual Vitastor config options like --config_file <path_to_config> may also be specified in CLI.\n"
+    "All usual Vitastor config options like --config_path <path_to_config> may also be specified in CLI.\n"
 ;
 
 class nbd_proxy
@@ -372,7 +372,8 @@ public:
             else if (args[i][0] == '-' && args[i][1] == '-')
             {
                 const char *opt = args[i]+2;
-                cfg[opt] = !strcmp(opt, "json") || !strcmp(opt, "all") || i == narg-1 ? "1" : args[++i];
+                cfg[opt] = !strcmp(opt, "json") || !strcmp(opt, "all") ||
+                    !strcmp(opt, "force") || i == narg-1 ? "1" : args[++i];
             }
             else if (pos == 0)
             {
@@ -381,8 +382,9 @@ public:
             }
             else if (pos == 1)
             {
+                char c = 0;
                 int n = 0;
-                if (sscanf(args[i], "/dev/nbd%d", &n) > 0)
+                if (sscanf(args[i], "/dev/nbd%d%c", &n, &c) == 1)
                     cfg["dev_num"] = n;
                 else
                     cfg["dev_num"] = args[i];
@@ -404,18 +406,14 @@ public:
         }
         else if (cfg["command"] == "unmap")
         {
-            if (cfg["dev_num"].is_null())
+            if (!cfg["dev_num"].is_number() &&
+                cfg["dev_num"].string_value() != "0" &&
+                !cfg["dev_num"].uint64_value())
             {
                 fprintf(stderr, "device name or number is missing\n");
                 exit(1);
             }
-            if (cfg["netlink"].is_null())
+            ioctl_unmap(cfg["dev_num"].uint64_value(), cfg["force"].bool_value());
-            {
-                ioctl_unmap(cfg["dev_num"].uint64_value());
-            }
-            else
-            {
-            }
         }
 #ifdef HAVE_NBD_NETLINK_H
         else if (cfg["command"] == "netlink-map")
@@ -444,9 +442,18 @@ help:
         }
     }
 
-    void ioctl_unmap(int dev_num)
+    void ioctl_unmap(int dev_num, bool force)
     {
         char path[64] = { 0 };
+        // Check if mapped
+        sprintf(path, "/sys/block/nbd%d/pid", dev_num);
+        if (access(path, F_OK) != 0)
+        {
+            fprintf(stderr, "/dev/nbd%d is not mapped: /sys/block/nbd%d/pid does not exist\n", dev_num, dev_num);
+            if (!force)
+                exit(1);
+        }
+        // Run unmap
         sprintf(path, "/dev/nbd%d", dev_num);
         int r, nbd = open(path, O_RDWR);
         if (nbd < 0)
@@ -610,36 +617,43 @@ help:
         {
             if (!cfg["dev_num"].is_null())
             {
-                if (run_nbd(sockfd, cfg["dev_num"].int64_value(), device_size, NBD_FLAG_SEND_FLUSH, nbd_timeout, bg) < 0)
+                int r;
+                if ((r = run_nbd(sockfd, cfg["dev_num"].int64_value(), device_size, NBD_FLAG_SEND_FLUSH, nbd_timeout, bg)) != 0)
                 {
-                    perror("run_nbd");
+                    fprintf(stderr, "run_nbd: %s\n", strerror(-r));
                     exit(1);
                 }
             }
             else
             {
                 // Find an unused device
+                auto mapped = list_mapped();
                 int i = 0;
                 while (true)
                 {
+                    if (mapped.find("/dev/nbd"+std::to_string(i)) != mapped.end())
+                    {
+                        i++;
+                        continue;
+                    }
                     int r = run_nbd(sockfd, i, device_size, NBD_FLAG_SEND_FLUSH, nbd_timeout, bg);
                     if (r == 0)
                     {
                         printf("/dev/nbd%d\n", i);
                         break;
                     }
-                    else if (r == -1 && errno == ENOENT)
+                    else if (r == -ENOENT)
                     {
                         fprintf(stderr, "No free NBD devices found\n");
                         exit(1);
                     }
-                    else if (r == -2 && errno == EBUSY)
+                    else if (r == -EBUSY)
                     {
                         i++;
                     }
                     else
                     {
-                        perror("run_nbd");
+                        fprintf(stderr, "run_nbd: %s\n", strerror(-r));
                         exit(1);
                     }
                 }
@@ -869,81 +883,114 @@ protected:
         // Check handle size
         assert(sizeof(cur_req.handle) == 8);
         char path[64] = { 0 };
-        sprintf(path, "/dev/nbd%d", dev_num);
+        int notifyfd[2] = { 0 };
-        int r, nbd = open(path, O_RDWR), qd_fd;
+        if (socketpair(AF_UNIX, SOCK_STREAM, 0, notifyfd) < 0)
-        if (nbd < 0)
         {
-            return -1;
+            return -errno;
         }
-        r = ioctl(nbd, NBD_SET_SOCK, sockfd[1]);
+        if (!fork())
-        if (r < 0)
         {
-            goto end_close;
+            // Do all NBD configuration in the child process, after the last fork.
-        }
+            // Why? It's needed because there is a race condition in the Linux kernel nbd driver
-        r = ioctl(nbd, NBD_SET_BLKSIZE, 4096);
+            // in nbd_add_socket() - it saves `current` task pointer as `nbd->task_setup` and
-        if (r < 0)
+            // then rechecks if the new `current` is the same. Problem is that if that process
-        {
+            // is already dead, `current` may be freed and then replaced by another process
-            goto end_unmap;
+            // with the same pointer value. So the check passes and NBD allows a different process
-        }
+            // to set up a device which is already set up. Proper fix would have to be done in the
-        r = ioctl(nbd, NBD_SET_SIZE, size);
+            // kernel code, but the workaround is obviously to perform NBD setup from the process
-        if (r < 0)
+            // which will then actually call NBD_DO_IT. That process stays alive during the whole
-        {
+            // time of NBD device execution and the (nbd->task_setup != current) check always
-            goto end_unmap;
+            // works correctly, and we don't accidentally break previous NBD devices while setting
-        }
+            // up a new device. Forking to check every device is of course rather slow, so we also
-        ioctl(nbd, NBD_SET_FLAGS, flags);
+            // do an additional check by calling list_mapped() before searching for a free NBD device.
-        if (timeout > 0)
+            if (bg)
-        {
+            {
-            r = ioctl(nbd, NBD_SET_TIMEOUT, (unsigned long)timeout);
+                daemonize_fork();
+            }
+            close(notifyfd[0]);
+            sprintf(path, "/dev/nbd%d", dev_num);
+            int r, nbd = open(path, O_RDWR), qd_fd;
+            if (nbd < 0)
+            {
+                write(notifyfd[1], &errno, sizeof(errno));
+                exit(1);
+            }
+            r = ioctl(nbd, NBD_SET_SOCK, sockfd[1]);
+            if (r < 0)
+            {
+                goto end_close;
+            }
+            r = ioctl(nbd, NBD_SET_BLKSIZE, 4096);
             if (r < 0)
             {
                 goto end_unmap;
             }
-        }
+            r = ioctl(nbd, NBD_SET_SIZE, size);
-        // Configure request size
+            if (r < 0)
-        sprintf(path, "/sys/block/nbd%d/queue/max_sectors_kb", dev_num);
+            {
-        qd_fd = open(path, O_WRONLY);
+                goto end_unmap;
-        if (qd_fd < 0)
+            }
-        {
+            ioctl(nbd, NBD_SET_FLAGS, flags);
-            goto end_unmap;
+            if (timeout > 0)
-        }
+            {
-        r = write(qd_fd, "32768", 5);
+                r = ioctl(nbd, NBD_SET_TIMEOUT, (unsigned long)timeout);
-        if (r != 5)
+                if (r < 0)
-        {
+                {
-            fprintf(stderr, "Warning: Failed to configure max_sectors_kb\n");
+                    goto end_unmap;
-        }
+                }
-        close(qd_fd);
+            }
-        if (!fork())
+            // Configure request size
-        {
+            sprintf(path, "/sys/block/nbd%d/queue/max_sectors_kb", dev_num);
-            // Run in child
+            qd_fd = open(path, O_WRONLY);
+            if (qd_fd < 0)
+            {
+                goto end_unmap;
+            }
+            r = write(qd_fd, "32768", 5);
+            if (r != 5)
+            {
+                fprintf(stderr, "Warning: Failed to configure max_sectors_kb\n");
+            }
+            close(qd_fd);
+            // Notify parent
+            errno = 0;
+            write(notifyfd[1], &errno, sizeof(errno));
+            close(notifyfd[1]);
             close(sockfd[0]);
             if (bg)
             {
-                daemonize();
+                daemonize_reopen_stdio();
             }
             r = ioctl(nbd, NBD_DO_IT);
             if (r < 0)
             {
-                fprintf(stderr, "NBD device terminated with error: %s\n", strerror(errno));
+                fprintf(stderr, "NBD device /dev/nbd%d terminated with error: %s\n", dev_num, strerror(errno));
             }
             close(sockfd[1]);
             ioctl(nbd, NBD_CLEAR_QUE);
             ioctl(nbd, NBD_CLEAR_SOCK);
             exit(0);
-        }
-        close(sockfd[1]);
-        close(nbd);
-        return 0;
     end_close:
-        r = errno;
+            write(notifyfd[1], &errno, sizeof(errno));
-        close(nbd);
+            close(nbd);
-        errno = r;
+            exit(2);
-        return -2;
     end_unmap:
-        r = errno;
+            write(notifyfd[1], &errno, sizeof(errno));
-        ioctl(nbd, NBD_CLEAR_SOCK);
+            ioctl(nbd, NBD_CLEAR_SOCK);
-        close(nbd);
+            close(nbd);
-        errno = r;
+            exit(3);
-        return -3;
+        }
+        // Parent - check status
+        close(notifyfd[1]);
+        int child_errno = 0;
+        int ok = read(notifyfd[0], &child_errno, sizeof(child_errno));
+        close(notifyfd[0]);
+        if (ok && !child_errno)
+        {
+            close(sockfd[1]);
+            return 0;
+        }
+        return -child_errno;
     }
 
     void submit_send()

src/client/qemu_driver.c

@@ -294,7 +294,9 @@ static void coroutine_fn vitastor_co_get_metadata(VitastorRPC *task)
 
     qemu_mutex_lock(&client->mutex);
     vitastor_c_watch_inode(client->proxy, client->image, vitastor_co_generic_cb, task);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
     vitastor_schedule_uring_handler(client);
+#endif
     qemu_mutex_unlock(&client->mutex);
 
     while (!task->complete)
@@ -566,6 +568,7 @@ static int vitastor_file_open(BlockDriverState *bs, QDict *options, int flags, E
 static void vitastor_close(BlockDriverState *bs)
 {
     VitastorClient *client = bs->opaque;
+    qemu_mutex_lock(&client->mutex);
     vitastor_c_destroy(client->proxy);
     if (client->fds)
     {
@@ -573,7 +576,6 @@ static void vitastor_close(BlockDriverState *bs)
         client->fds = NULL;
         client->fd_alloc = client->fd_count = 0;
     }
-    qemu_mutex_destroy(&client->mutex);
     if (client->config_path)
         g_free(client->config_path);
     if (client->etcd_host)
@@ -584,6 +586,8 @@ static void vitastor_close(BlockDriverState *bs)
         g_free(client->image);
     free(client->last_bitmap);
     client->last_bitmap = NULL;
+    qemu_mutex_unlock(&client->mutex);
+    qemu_mutex_destroy(&client->mutex);
 }
 
 #if QEMU_VERSION_MAJOR >= 3 || QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR > 2
@@ -749,7 +753,9 @@ static int coroutine_fn vitastor_co_preadv(BlockDriverState *bs,
     uint64_t inode = client->watch ? vitastor_c_inode_get_num(client->watch) : client->inode;
     qemu_mutex_lock(&client->mutex);
     vitastor_c_read(client->proxy, inode, offset, bytes, iov->iov, iov->niov, vitastor_co_read_cb, &task);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
     vitastor_schedule_uring_handler(client);
+#endif
     qemu_mutex_unlock(&client->mutex);
 
     while (!task.complete)
@@ -783,7 +789,9 @@ static int coroutine_fn vitastor_co_pwritev(BlockDriverState *bs,
     uint64_t inode = client->watch ? vitastor_c_inode_get_num(client->watch) : client->inode;
     qemu_mutex_lock(&client->mutex);
     vitastor_c_write(client->proxy, inode, offset, bytes, 0, iov->iov, iov->niov, vitastor_co_generic_cb, &task);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
     vitastor_schedule_uring_handler(client);
+#endif
     qemu_mutex_unlock(&client->mutex);
 
     while (!task.complete)
@@ -863,7 +871,9 @@ static int coroutine_fn vitastor_co_block_status(
         task.bitmap = client->last_bitmap = NULL;
         qemu_mutex_lock(&client->mutex);
         vitastor_c_read_bitmap(client->proxy, task.inode, task.offset, task.len, !client->skip_parents, vitastor_co_read_bitmap_cb, &task);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
         vitastor_schedule_uring_handler(client);
+#endif
         qemu_mutex_unlock(&client->mutex);
         while (!task.complete)
         {
@@ -950,7 +960,9 @@ static int coroutine_fn vitastor_co_flush(BlockDriverState *bs)
 
     qemu_mutex_lock(&client->mutex);
     vitastor_c_sync(client->proxy, vitastor_co_generic_cb, &task);
+#if !defined VITASTOR_C_API_VERSION || VITASTOR_C_API_VERSION < 5
     vitastor_schedule_uring_handler(client);
+#endif
     qemu_mutex_unlock(&client->mutex);
 
     while (!task.complete)

src/client/vitastor.pc.in

@@ -6,7 +6,7 @@ includedir=${prefix}/@CMAKE_INSTALL_INCLUDEDIR@
 
 Name: Vitastor
 Description: Vitastor client library
-Version: 1.10.1
+Version: 1.11.0
 Libs: -L${libdir} -lvitastor_client
 Cflags: -I${includedir}
 

src/client/vitastor_c.cpp

@@ -127,6 +127,7 @@ vitastor_c *vitastor_c_create_qemu_uring(QEMUSetFDHandler *aio_set_fd_handler, v
     auto self = vitastor_c_create_qemu_common(aio_set_fd_handler, aio_context);
     self->ringloop = ringloop;
     self->cli = new cluster_client_t(self->ringloop, self->tfd, cfg_json);
+    ringloop->loop();
     return self;
 }
 
@@ -150,6 +151,7 @@ vitastor_c *vitastor_c_create_uring(const char *config_path, const char *etcd_ho
     self->ringloop = ringloop;
     self->epmgr = new epoll_manager_t(self->ringloop);
     self->cli = new cluster_client_t(self->ringloop, self->epmgr->tfd, cfg_json);
+    ringloop->loop();
     return self;
 }
 
@@ -183,6 +185,7 @@ vitastor_c *vitastor_c_create_uring_json(const char **options, int options_len)
     self->ringloop = ringloop;
     self->epmgr = new epoll_manager_t(self->ringloop);
     self->cli = new cluster_client_t(self->ringloop, self->epmgr->tfd, cfg_json);
+    ringloop->loop();
     return self;
 }
 
@@ -222,6 +225,18 @@ int vitastor_c_is_ready(vitastor_c *client)
     return client->cli->is_ready();
 }
 
+void vitastor_c_on_ready(vitastor_c *client, VitastorIOHandler cb, void *opaque)
+{
+    client->cli->on_ready([=]()
+    {
+        cb(opaque, 0);
+    });
+    if (client->ringloop)
+    {
+        client->ringloop->loop();
+    }
+}
+
 void vitastor_c_uring_wait_ready(vitastor_c *client)
 {
     while (!client->cli->is_ready())
@@ -276,6 +291,10 @@ void vitastor_c_read(vitastor_c *client, uint64_t inode, uint64_t offset, uint64
         delete op;
     };
     client->cli->execute(op);
+    if (client->ringloop)
+    {
+        client->ringloop->loop();
+    }
 }
 
 void vitastor_c_write(vitastor_c *client, uint64_t inode, uint64_t offset, uint64_t len, uint64_t check_version,
@@ -297,6 +316,31 @@ void vitastor_c_write(vitastor_c *client, uint64_t inode, uint64_t offset, uint6
         delete op;
     };
     client->cli->execute(op);
+    if (client->ringloop)
+    {
+        client->ringloop->loop();
+    }
+}
+
+void vitastor_c_delete(vitastor_c *client, uint64_t inode, uint64_t offset, uint64_t len, uint64_t check_version,
+    VitastorIOHandler cb, void *opaque)
+{
+    cluster_op_t *op = new cluster_op_t;
+    op->opcode = OSD_OP_DELETE;
+    op->inode = inode;
+    op->offset = offset;
+    op->len = len;
+    op->version = check_version;
+    op->callback = [cb, opaque](cluster_op_t *op)
+    {
+        cb(opaque, op->retval);
+        delete op;
+    };
+    client->cli->execute(op);
+    if (client->ringloop)
+    {
+        client->ringloop->loop();
+    }
 }
 
 void vitastor_c_read_bitmap(vitastor_c *client, uint64_t inode, uint64_t offset, uint64_t len,
@@ -319,6 +363,10 @@ void vitastor_c_read_bitmap(vitastor_c *client, uint64_t inode, uint64_t offset,
         delete op;
     };
     client->cli->execute(op);
+    if (client->ringloop)
+    {
+        client->ringloop->loop();
+    }
 }
 
 void vitastor_c_sync(vitastor_c *client, VitastorIOHandler cb, void *opaque)
@@ -331,6 +379,10 @@ void vitastor_c_sync(vitastor_c *client, VitastorIOHandler cb, void *opaque)
         delete op;
     };
     client->cli->execute(op);
+    if (client->ringloop)
+    {
+        client->ringloop->loop();
+    }
 }
 
 void vitastor_c_watch_inode(vitastor_c *client, char *image, VitastorIOHandler cb, void *opaque)
@@ -340,6 +392,10 @@ void vitastor_c_watch_inode(vitastor_c *client, char *image, VitastorIOHandler c
         auto watch = client->cli->st_cli.watch_inode(std::string(image));
         cb(opaque, (long)watch);
     });
+    if (client->ringloop)
+    {
+        client->ringloop->loop();
+    }
 }
 
 void vitastor_c_close_watch(vitastor_c *client, void *handle)

src/client/vitastor_c.h

@@ -7,7 +7,7 @@
 #define VITASTOR_QEMU_PROXY_H
 
 // C API wrapper version
-#define VITASTOR_C_API_VERSION 4
+#define VITASTOR_C_API_VERSION 5
 
 #ifndef POOL_ID_BITS
 #define POOL_ID_BITS 16
@@ -51,6 +51,7 @@ vitastor_c *vitastor_c_create_epoll_json(const char **options, int options_len);
 void* vitastor_c_get_internal_client(vitastor_c *client);
 void vitastor_c_destroy(vitastor_c *client);
 int vitastor_c_is_ready(vitastor_c *client);
+void vitastor_c_on_ready(vitastor_c *client, VitastorIOHandler cb, void *opaque);
 int vitastor_c_uring_register_eventfd(vitastor_c *client);
 void vitastor_c_uring_wait_ready(vitastor_c *client);
 void vitastor_c_uring_handle_events(vitastor_c *client);
@@ -62,6 +63,8 @@ void vitastor_c_read(vitastor_c *client, uint64_t inode, uint64_t offset, uint64
     struct iovec *iov, int iovcnt, VitastorReadHandler cb, void *opaque);
 void vitastor_c_write(vitastor_c *client, uint64_t inode, uint64_t offset, uint64_t len, uint64_t check_version,
     struct iovec *iov, int iovcnt, VitastorIOHandler cb, void *opaque);
+void vitastor_c_delete(vitastor_c *client, uint64_t inode, uint64_t offset, uint64_t len, uint64_t check_version,
+    VitastorIOHandler cb, void *opaque);
 void vitastor_c_read_bitmap(vitastor_c *client, uint64_t inode, uint64_t offset, uint64_t len,
     int with_parents, VitastorReadBitmapHandler cb, void *opaque);
 void vitastor_c_sync(vitastor_c *client, VitastorIOHandler cb, void *opaque);

src/cmd/cli.cpp

@@ -186,7 +186,8 @@ static const char* help_text =
     "    --raw_placement <rules>       Specify raw PG generation rules (see documentation for details)\n"
     "    --primary_affinity_tags tags  Prefer to put primary copies on OSDs with all specified tags\n"
     "    --scrub_interval <time>       Enable regular scrubbing for this pool. Format: number + unit s/m/h/d/M/y\n"
-    "    --used_for_fs <name>          Mark pool as used for VitastorFS with metadata in image <name>\n"
+    "    --used_for_app fs:<name>      Mark pool as used for VitastorFS with metadata in image <name>\n"
+    "    --used_for_app s3:<name>      Mark pool as used for S3 location with name <name>\n"
     "    --pg_stripe_size <number>     Increase object grouping stripe\n"
     "    --max_osd_combinations 10000  Maximum number of random combinations for LP solver input\n"
     "    --wait                        Wait for the new pool to come online\n"
@@ -198,7 +199,7 @@ static const char* help_text =
     "vitastor-cli modify-pool|pool-modify <id|name> [--name <new_name>] [PARAMETERS...]\n"
     "  Modify an existing pool. Modifiable parameters:\n"
     "    [-s|--pg_size <number>] [--pg_minsize <number>] [-n|--pg_count <count>]\n"
-    "    [--failure_domain <level>] [--root_node <node>] [--osd_tags <tags>] [--used_for_fs <name>]\n"
+    "    [--failure_domain <level>] [--root_node <node>] [--osd_tags <tags>] [--used_for_app <type>:<name>]\n"
     "    [--max_osd_combinations <number>] [--primary_affinity_tags <tags>] [--scrub_interval <time>]\n"
     "    [--level_placement <rules>] [--raw_placement <rules>]\n"
     "  Non-modifiable parameters (changing them WILL lead to data loss):\n"
@@ -224,7 +225,7 @@ static const char* help_text =
     "Use vitastor-cli --help <command> for command details or vitastor-cli --help --all for all details.\n"
     "\n"
     "GLOBAL OPTIONS:\n"
-    "  --config_file FILE  Path to Vitastor configuration file\n"
+    "  --config_path FILE  Path to Vitastor configuration file\n"
     "  --etcd_address URL  Etcd connection address\n"
     "  --iodepth N         Send N operations in parallel to each OSD when possible (default 32)\n"
     "  --parallel_osds M   Work with M osds in parallel when possible (default 4)\n"

src/cmd/cli_create.cpp

@@ -92,12 +92,12 @@ struct image_creator_t
         {
             new_pool_id = pools.begin()->first;
         }
-        if (new_pool_id && !pools.at(new_pool_id).used_for_fs.empty() && !force)
+        if (new_pool_id && !pools.at(new_pool_id).used_for_app.empty() && !force)
         {
             result = (cli_result_t){
                 .err = EINVAL,
                 .text = "Pool "+pools.at(new_pool_id).name+
-                    " is used for VitastorFS "+pools.at(new_pool_id).used_for_fs+
+                    " is used for application "+pools.at(new_pool_id).used_for_app+
                     ". Use --force if you really know what you are doing",
             };
             state = 100;
@@ -215,6 +215,7 @@ resume_3:
             goto resume_3;
         else if (state == 4)
             goto resume_4;
+        // FIXME: take all info from etcd requests, not mixed with st_cli.inode_config
         for (auto & ic: parent->cli->st_cli.inode_config)
         {
             if (ic.second.name == image_name+"@"+new_snap)
@@ -286,6 +287,7 @@ resume_4:
 
     json11::Json::object get_next_id()
     {
+        assert(new_pool_id);
         return json11::Json::object {
             { "request_range", json11::Json::object {
                 { "key", base64_encode(
@@ -321,6 +323,17 @@ resume_4:
             goto resume_2;
         else if (state == 3)
             goto resume_3;
+        if (!new_pool_id)
+        {
+            for (auto & ic: parent->cli->st_cli.inode_config)
+            {
+                if (ic.second.name == image_name)
+                {
+                    new_pool_id = INODE_POOL(ic.first);
+                    break;
+                }
+            }
+        }
         parent->etcd_txn(json11::Json::object { { "success", json11::Json::array {
             get_next_id(),
             json11::Json::object {

src/cmd/cli_ls.cpp

@@ -546,7 +546,7 @@ std::function<bool(cli_result_t &)> cli_tool_t::start_ls(json11::Json cfg)
     lister->list_pool_name = lister->list_pool_id ? "" : cfg["pool"].as_string();
     lister->show_stats = cfg["long"].bool_value();
     lister->show_delete = cfg["del"].bool_value();
-    lister->sort_field = cfg["sort"].string_value();
+    lister->sort_field = cfg["sort"].string_value() != "" ? cfg["sort"].string_value() : "name";
     lister->reverse = cfg["reverse"].bool_value();
     lister->max_count = cfg["count"].uint64_value();
     for (auto & item: cfg["names"].array_items())

src/cmd/cli_pool_cfg.cpp

@@ -90,8 +90,8 @@ std::string validate_pool_config(json11::Json::object & new_cfg, json11::Json ol
             value = sz;
         }
         else if (key == "name" || key == "scheme" || key == "immediate_commit" ||
-            key == "failure_domain" || key == "root_node" || key == "scrub_interval" || key == "used_for_fs" ||
+            key == "failure_domain" || key == "root_node" || key == "scrub_interval" || key == "used_for_app" ||
-            key == "raw_placement")
+            key == "used_for_fs" || key == "raw_placement")
         {
             if (!value.is_string())
             {
@@ -156,8 +156,13 @@ std::string validate_pool_config(json11::Json::object & new_cfg, json11::Json ol
     {
         new_cfg.erase("parity_chunks");
     }
-    if (new_cfg.find("used_for_fs") != new_cfg.end() && new_cfg["used_for_fs"].string_value() == "")
+    if (new_cfg.find("used_for_app") != new_cfg.end() && new_cfg["used_for_app"].string_value() == "")
     {
+        new_cfg.erase("used_for_app");
+    }
+    if (new_cfg.find("used_for_app") == new_cfg.end() && new_cfg.find("used_for_fs") != new_cfg.end())
+    {
+        new_cfg["used_for_app"] = "fs:"+new_cfg["used_for_fs"].string_value();
         new_cfg.erase("used_for_fs");
     }
 

src/cmd/cli_pool_ls.cpp

@@ -199,7 +199,9 @@ resume_1:
             auto & st = pool_stats[pool_id];
             for (auto & kv: pp.second.object_items())
             {
-                if (st.find(kv.first) == st.end())
+                if (kv.first == "used_for_fs" && st.find("used_for_app") == st.end())
+                    st["used_for_app"] = "fs:"+kv.second.string_value();
+                else if (st.find(kv.first) == st.end())
                     st[kv.first] = kv.second;
             }
         }
@@ -493,7 +495,7 @@ resume_3:
                 { "name", "Name" },
                 { "id", "ID" },
                 { "scheme_name", "Scheme" },
-                { "used_for_fs", "Used for VitastorFS" },
+                { "used_for_app", "Used for app" },
                 { "status", "Status" },
                 { "backfillfull_fmt", "Backfillfull" },
                 { "pg_count_fmt", "PGs" },

src/cmd/cli_pool_modify.cpp

@@ -112,19 +112,21 @@ resume_1:
                 return;
             }
 
-            if (new_cfg.find("used_for_fs") != new_cfg.end() && !force)
+            if (new_cfg.find("used_for_app") != new_cfg.end() && !force)
             {
                 // Check that pool doesn't have images
                 auto img_it = parent->cli->st_cli.inode_config.lower_bound(INODE_WITH_POOL(pool_id, 0));
-                if (img_it != parent->cli->st_cli.inode_config.end() && INODE_POOL(img_it->first) == pool_id &&
+                if (img_it != parent->cli->st_cli.inode_config.end() &&
-                    img_it->second.name == new_cfg["used_for_fs"].string_value())
+                    INODE_POOL(img_it->first) == pool_id &&
+                    new_cfg["used_for_app"].string_value().substr(0, 3) == "fs:" &&
+                    img_it->second.name == new_cfg["used_for_app"].string_value().substr(3))
                 {
                     // Only allow metadata image to exist in the FS pool
                     img_it++;
                 }
                 if (img_it != parent->cli->st_cli.inode_config.end() && INODE_POOL(img_it->first) == pool_id)
                 {
-                    result = (cli_result_t){ .err = ENOENT, .text = "Pool "+pool_name+" has block images, delete them before using it for VitastorFS" };
+                    result = (cli_result_t){ .err = ENOENT, .text = "Pool "+pool_name+" has block images, delete them before using it for VitastorFS, S3 or another app" };
                     state = 100;
                     return;
                 }

src/nfs/nfs_kv.cpp

@@ -245,10 +245,10 @@ void kv_fs_state_t::init(nfs_proxy_t *proxy, json11::Json cfg)
     if (proxy->cli->st_cli.inode_config.find(fs_kv_inode) != proxy->cli->st_cli.inode_config.end())
     {
         auto & name = proxy->cli->st_cli.inode_config.at(fs_kv_inode).name;
-        if (pool_cfg.used_for_fs != name)
+        if (pool_cfg.used_for_app != "fs:"+name)
         {
-            fprintf(stderr, "Please mark pool as used for this file system with `vitastor-cli modify-pool --used-for-fs %s %s`\n",
+            fprintf(stderr, "Please mark pool as used for this file system with `vitastor-cli modify-pool --used-for-app fs:%s %s`\n",
-                name.c_str(), cfg["fs"].string_value().c_str());
+                name.c_str(), pool_cfg.name.c_str());
             exit(1);
         }
     }

src/osd/osd.h

@@ -281,6 +281,8 @@ class osd_t
     int pick_next_scrub(object_id & next_oid);
     void submit_scrub_op(object_id oid);
     bool continue_scrub();
+    void submit_scrub_subops(osd_op_t *cur_op);
+    void scrub_check_results(osd_op_t *cur_op);
     void plan_scrub(pg_t & pg, bool report_state = true);
     void schedule_scrub(pg_t & pg);
 
@@ -313,7 +315,7 @@ class osd_t
     pg_osd_set_state_t *mark_object(pg_t & pg, object_id oid, pg_osd_set_state_t *prev_object_state, bool ref,
         std::function<int(pg_osd_set_t & new_set)> calc_set);
     pg_osd_set_state_t *mark_object_corrupted(pg_t & pg, object_id oid, pg_osd_set_state_t *prev_object_state,
-        osd_rmw_stripe_t *stripes, bool ref, bool inconsistent);
+        osd_rmw_stripe_t *stripes, bool ref);
     pg_osd_set_state_t *mark_partial_write(pg_t & pg, object_id oid, pg_osd_set_state_t *prev_object_state,
         osd_rmw_stripe_t *stripes, bool ref);
     void deref_object_state(pg_t & pg, pg_osd_set_state_t **object_state, bool deref);
@@ -326,6 +328,8 @@ class osd_t
     void submit_primary_subops(int submit_type, uint64_t op_version, const uint64_t* osd_set, osd_op_t *cur_op);
     int submit_primary_subop_batch(int submit_type, inode_t inode, uint64_t op_version,
         osd_rmw_stripe_t *stripes, const uint64_t* osd_set, osd_op_t *cur_op, int subop_idx, int zero_read);
+    void submit_primary_subop(osd_op_t *cur_op, osd_op_t *subop,
+        osd_rmw_stripe_t *si, bool wr, inode_t inode, uint64_t op_version);
     void submit_primary_del_subops(osd_op_t *cur_op, uint64_t *cur_set, uint64_t set_size, pg_osd_set_t & loc_set);
     void submit_primary_del_batch(osd_op_t *cur_op, obj_ver_osd_t *chunks_to_delete, int chunks_to_delete_count);
     int submit_primary_sync_subops(osd_op_t *cur_op);

src/osd/osd_cluster.cpp

@@ -673,7 +673,7 @@ void osd_t::apply_no_inode_stats()
     std::vector<uint64_t> no_inode_stats;
     for (auto & pool_item: st_cli.pool_config)
     {
-        if (!pool_item.second.used_for_fs.empty())
+        if (!pool_item.second.used_for_app.empty())
         {
             no_inode_stats.push_back(pool_item.first);
         }

src/osd/osd_main.cpp

@@ -3,6 +3,7 @@
 
 #include "osd.h"
 
+#include <sys/prctl.h>
 #include <signal.h>
 
 static osd_t *osd = NULL;
@@ -56,6 +57,9 @@ int main(int narg, char *args[])
         printf("%s", help_text);
         return 1;
     }
+    char osdname[16] = { 0 };
+    snprintf(osdname, 16, "osd%lu", config["osd_num"].uint64_value());
+    prctl(PR_SET_NAME, (unsigned long)osdname, 0, 0, 0);
     signal(SIGINT, handle_sigint);
     signal(SIGTERM, handle_sigint);
     ring_loop_t *ringloop = new ring_loop_t(RINGLOOP_DEFAULT_SIZE);

src/osd/osd_primary.cpp

@@ -28,7 +28,6 @@ bool osd_t::prepare_primary_rw(osd_op_t *cur_op)
         return false;
     }
     auto & pool_cfg = pool_cfg_it->second;
-    // FIXME: op_data->pg_data_size can probably be removed (there's pg.pg_data_size)
     uint64_t pg_data_size = (pool_cfg.scheme == POOL_SCHEME_REPLICATED ? 1 : pool_cfg.pg_size-pool_cfg.parity_chunks);
     uint64_t pg_block_size = bs_block_size * pg_data_size;
     object_id oid = {
@@ -52,13 +51,13 @@ bool osd_t::prepare_primary_rw(osd_op_t *cur_op)
         finish_op(cur_op, -EINVAL);
         return false;
     }
-    // Scrub is similar to r/w, so it's also handled here
+    int stripe_count = (cur_op->req.hdr.opcode == OSD_OP_SCRUB ? 0 :
-    int stripe_count = (pool_cfg.scheme == POOL_SCHEME_REPLICATED
+        (pool_cfg.scheme == POOL_SCHEME_REPLICATED ? 1 : pg_it->second.pg_size));
-        && cur_op->req.hdr.opcode != OSD_OP_SCRUB ? 1 : pg_it->second.pg_size);
     int chain_size = 0;
     if (cur_op->req.hdr.opcode == OSD_OP_READ && cur_op->req.rw.meta_revision > 0)
     {
         // Chained read
+        // FIXME: Introduce an explicit opcode for chained reads
         auto inode_it = st_cli.inode_config.find(cur_op->req.rw.inode);
         if (inode_it->second.mod_revision != cur_op->req.rw.meta_revision)
         {
@@ -72,7 +71,7 @@ bool osd_t::prepare_primary_rw(osd_op_t *cur_op)
             inode_it->second.parent_id &&
             INODE_POOL(inode_it->second.parent_id) == pg_it->second.pool_id)
         {
-            // Check for loops
+            // Check for loops - FIXME check it in etcd_state_client
             if (inode_it->second.parent_id == cur_op->req.rw.inode ||
                 inode_it->second.parent_id == inode_it->second.num ||
                 chain_size > st_cli.inode_config.size())
@@ -110,20 +109,22 @@ bool osd_t::prepare_primary_rw(osd_op_t *cur_op)
     );
     void *data_buf = (uint8_t*)op_data + sizeof(osd_primary_op_data_t);
     op_data->pg_num = pg_num;
+    op_data->pg = &pg_it->second;
     op_data->oid = oid;
     op_data->stripes = (osd_rmw_stripe_t*)data_buf;
+    op_data->stripe_count = stripe_count;
     data_buf = (uint8_t*)data_buf + sizeof(osd_rmw_stripe_t) * stripe_count;
-    op_data->scheme = pool_cfg.scheme;
-    op_data->pg_data_size = pg_data_size;
-    op_data->pg_size = pg_it->second.pg_size;
     cur_op->op_data = op_data;
-    split_stripes(pg_data_size, bs_block_size, (uint32_t)(cur_op->req.rw.offset - oid.stripe), cur_op->req.rw.len, op_data->stripes);
+    if (cur_op->req.hdr.opcode != OSD_OP_SCRUB)
-    // Resulting bitmaps have to survive op_data and be freed with the op itself
-    assert(!cur_op->bitmap_buf);
-    cur_op->bitmap_buf = calloc_or_die(1, clean_entry_bitmap_size * stripe_count);
-    for (int i = 0; i < stripe_count; i++)
     {
-        op_data->stripes[i].bmp_buf = (uint8_t*)cur_op->bitmap_buf + clean_entry_bitmap_size * i;
+        split_stripes(pg_data_size, bs_block_size, (uint32_t)(cur_op->req.rw.offset - oid.stripe), cur_op->req.rw.len, op_data->stripes);
+        // Resulting bitmaps have to survive op_data and be freed with the op itself
+        assert(!cur_op->bitmap_buf);
+        cur_op->bitmap_buf = calloc_or_die(1, clean_entry_bitmap_size * stripe_count);
+        for (int i = 0; i < stripe_count; i++)
+        {
+            op_data->stripes[i].bmp_buf = (uint8_t*)cur_op->bitmap_buf + clean_entry_bitmap_size * i;
+        }
     }
     op_data->chain_size = chain_size;
     if (chain_size > 0)
@@ -205,11 +206,11 @@ void osd_t::continue_primary_read(osd_op_t *cur_op)
 resume_0:
     cur_op->reply.rw.bitmap_len = 0;
     {
-        auto & pg = pgs.at({ .pool_id = INODE_POOL(op_data->oid.inode), .pg_num = op_data->pg_num });
+        auto & pg = *op_data->pg;
         if (cur_op->req.rw.len == 0)
         {
             // len=0 => bitmap read
-            for (int role = 0; role < op_data->pg_data_size; role++)
+            for (int role = 0; role < pg.pg_data_size; role++)
             {
                 op_data->stripes[role].read_start = 0;
                 op_data->stripes[role].read_end = UINT32_MAX;
@@ -217,7 +218,7 @@ resume_0:
         }
         else
         {
-            for (int role = 0; role < op_data->pg_data_size; role++)
+            for (int role = 0; role < pg.pg_data_size; role++)
             {
                 op_data->stripes[role].read_start = op_data->stripes[role].req_start;
                 op_data->stripes[role].read_end = op_data->stripes[role].req_end;
@@ -228,29 +229,27 @@ resume_0:
         op_data->target_ver = vo_it != pg.ver_override.end() ? vo_it->second : UINT64_MAX;
         // PG may have degraded or misplaced objects
         op_data->prev_set = get_object_osd_set(pg, op_data->oid, &op_data->object_state);
-        if (pg.state == PG_ACTIVE || op_data->scheme == POOL_SCHEME_REPLICATED)
+        if (pg.state == PG_ACTIVE || pg.scheme == POOL_SCHEME_REPLICATED)
         {
             // Fast happy-path
-            if (op_data->scheme == POOL_SCHEME_REPLICATED &&
+            if (pg.scheme == POOL_SCHEME_REPLICATED &&
                 op_data->object_state && (op_data->object_state->state & OBJ_INCOMPLETE))
             {
                 finish_op(cur_op, -EIO);
                 return;
             }
-            cur_op->buf = alloc_read_buffer(op_data->stripes, op_data->pg_data_size, 0);
+            cur_op->buf = alloc_read_buffer(op_data->stripes, pg.pg_data_size, 0);
             submit_primary_subops(SUBMIT_RMW_READ, op_data->target_ver, op_data->prev_set, cur_op);
             op_data->st = 1;
         }
         else
         {
-            if (extend_missing_stripes(op_data->stripes, op_data->prev_set, op_data->pg_data_size, pg.pg_size) < 0)
+            if (extend_missing_stripes(op_data->stripes, op_data->prev_set, pg.pg_data_size, pg.pg_size) < 0)
             {
                 finish_op(cur_op, -EIO);
                 return;
             }
             // Submit reads
-            op_data->pg_size = pg.pg_size;
-            op_data->scheme = pg.scheme;
             op_data->degraded = 1;
             cur_op->buf = alloc_read_buffer(op_data->stripes, pg.pg_size, 0);
             submit_primary_subops(SUBMIT_RMW_READ, op_data->target_ver, op_data->prev_set, cur_op);
@@ -265,30 +264,29 @@ resume_2:
         if (op_data->errcode == -EIO || op_data->errcode == -EDOM)
         {
             // I/O or checksum error
-            auto & pg = pgs.at({ .pool_id = INODE_POOL(op_data->oid.inode), .pg_num = op_data->pg_num });
             // FIXME: ref = true ideally... because new_state != state is not necessarily true if it's freed and recreated
-            op_data->object_state = mark_object_corrupted(pg, op_data->oid, op_data->object_state, op_data->stripes, false, false);
+            op_data->object_state = mark_object_corrupted(*op_data->pg, op_data->oid, op_data->object_state, op_data->stripes, false);
             goto resume_0;
         }
         finish_op(cur_op, op_data->errcode);
         return;
     }
     cur_op->reply.rw.version = op_data->fact_ver;
-    cur_op->reply.rw.bitmap_len = op_data->pg_data_size * clean_entry_bitmap_size;
+    cur_op->reply.rw.bitmap_len = op_data->pg->pg_data_size * clean_entry_bitmap_size;
     if (op_data->degraded)
     {
         // Reconstruct missing stripes
         osd_rmw_stripe_t *stripes = op_data->stripes;
-        if (op_data->scheme == POOL_SCHEME_XOR)
+        if (op_data->pg->scheme == POOL_SCHEME_XOR)
         {
-            reconstruct_stripes_xor(stripes, op_data->pg_size, clean_entry_bitmap_size);
+            reconstruct_stripes_xor(stripes, op_data->pg->pg_size, clean_entry_bitmap_size);
         }
-        else if (op_data->scheme == POOL_SCHEME_EC)
+        else if (op_data->pg->scheme == POOL_SCHEME_EC)
         {
-            reconstruct_stripes_ec(stripes, op_data->pg_size, op_data->pg_data_size, clean_entry_bitmap_size);
+            reconstruct_stripes_ec(stripes, op_data->pg->pg_size, op_data->pg->pg_data_size, clean_entry_bitmap_size);
         }
         cur_op->iov.push_back(op_data->stripes[0].bmp_buf, cur_op->reply.rw.bitmap_len);
-        for (int role = 0; role < op_data->pg_size; role++)
+        for (int role = 0; role < op_data->pg->pg_size; role++)
         {
             if (stripes[role].req_end != 0)
             {
@@ -360,10 +358,10 @@ pg_osd_set_state_t *osd_t::mark_object(pg_t & pg, object_id oid, pg_osd_set_stat
     return object_state;
 }
 
-pg_osd_set_state_t *osd_t::mark_object_corrupted(pg_t & pg, object_id oid, pg_osd_set_state_t *prev_object_state,
+pg_osd_set_state_t *osd_t::mark_object_corrupted(pg_t & pg, object_id oid,
-    osd_rmw_stripe_t *stripes, bool ref, bool inconsistent)
+    pg_osd_set_state_t *prev_object_state, osd_rmw_stripe_t *stripes, bool ref)
 {
-    return mark_object(pg, oid, prev_object_state, ref, [stripes, inconsistent](pg_osd_set_t & new_set)
+    return mark_object(pg, oid, prev_object_state, ref, [stripes](pg_osd_set_t & new_set)
     {
         // Mark object chunk(s) as corrupted
         int changes = 0;
@@ -390,16 +388,6 @@ pg_osd_set_state_t *osd_t::mark_object_corrupted(pg_t & pg, object_id oid, pg_os
                     chunk.loc_bad &= ~LOC_CORRUPTED;
                 }
             }
-            if (inconsistent && !chunk.loc_bad)
-            {
-                changes++;
-                chunk.loc_bad |= LOC_INCONSISTENT;
-            }
-            else if (!inconsistent && (chunk.loc_bad & LOC_INCONSISTENT))
-            {
-                changes++;
-                chunk.loc_bad &= ~LOC_INCONSISTENT;
-            }
             chunk_it++;
         }
         return changes;
@@ -695,7 +683,7 @@ void osd_t::continue_primary_del(osd_op_t *cur_op)
         return;
     }
     osd_primary_op_data_t *op_data = cur_op->op_data;
-    auto & pg = pgs.at({ .pool_id = INODE_POOL(op_data->oid.inode), .pg_num = op_data->pg_num });
+    auto & pg = *op_data->pg;
     if (op_data->st == 1)      goto resume_1;
     else if (op_data->st == 2) goto resume_2;
     else if (op_data->st == 3) goto resume_3;
@@ -734,54 +722,58 @@ resume_3:
         cur_op->reply.rw.version = op_data->fact_ver;
         goto continue_others;
     }
-    // Save version override for parallel reads
+    // If not already deleted:
-    pg.ver_override[op_data->oid] = op_data->fact_ver;
+    if (op_data->fact_ver)
-    // Submit deletes
+    {
-    op_data->fact_ver++;
+        // Save version override for parallel reads
-    submit_primary_del_subops(cur_op, NULL, 0, op_data->object_state ? op_data->object_state->osd_set : pg.cur_loc_set);
+        pg.ver_override[op_data->oid] = op_data->fact_ver;
+        // Submit deletes
+        op_data->fact_ver++;
+        submit_primary_del_subops(cur_op, NULL, 0, op_data->object_state ? op_data->object_state->osd_set : pg.cur_loc_set);
 resume_4:
-    op_data->st = 4;
+        op_data->st = 4;
-    return;
-resume_5:
-    if (op_data->errors > 0)
-    {
-        deref_object_state(pg, &op_data->object_state, true);
-        pg_cancel_write_queue(pg, cur_op, op_data->oid, op_data->errcode);
         return;
-    }
+resume_5:
-    // Remove version override
+        if (op_data->errors > 0)
-    pg.ver_override.erase(op_data->oid);
-    // Adjust PG stats after "instant stabilize", because we need object_state above
-    if (!op_data->object_state)
-    {
-        pg.clean_count--;
-    }
-    else
-    {
-        remove_object_from_state(op_data->oid, &op_data->object_state, pg);
-        deref_object_state(pg, &op_data->object_state, true);
-    }
-    // Mark PG and OSDs as dirty
-    for (auto & chunk: (op_data->object_state ? op_data->object_state->osd_set : pg.cur_loc_set))
-    {
-        this->dirty_osds.insert(chunk.osd_num);
-    }
-    for (auto cl_it = msgr.clients.find(cur_op->peer_fd); cl_it != msgr.clients.end(); )
-    {
-        cl_it->second->dirty_pgs.insert({ .pool_id = pg.pool_id, .pg_num = pg.pg_num });
-        break;
-    }
-    dirty_pgs.insert({ .pool_id = pg.pool_id, .pg_num = pg.pg_num });
-    if (immediate_commit == IMMEDIATE_NONE)
-    {
-        unstable_write_count++;
-        if (unstable_write_count >= autosync_writes)
         {
-            unstable_write_count = 0;
+            deref_object_state(pg, &op_data->object_state, true);
-            autosync();
+            pg_cancel_write_queue(pg, cur_op, op_data->oid, op_data->errcode);
+            return;
         }
+        // Remove version override
+        pg.ver_override.erase(op_data->oid);
+        // Adjust PG stats after "instant stabilize", because we need object_state above
+        if (!op_data->object_state)
+        {
+            pg.clean_count--;
+        }
+        else
+        {
+            remove_object_from_state(op_data->oid, &op_data->object_state, pg);
+            deref_object_state(pg, &op_data->object_state, true);
+        }
+        // Mark PG and OSDs as dirty
+        for (auto & chunk: (op_data->object_state ? op_data->object_state->osd_set : pg.cur_loc_set))
+        {
+            this->dirty_osds.insert(chunk.osd_num);
+        }
+        for (auto cl_it = msgr.clients.find(cur_op->peer_fd); cl_it != msgr.clients.end(); )
+        {
+            cl_it->second->dirty_pgs.insert({ .pool_id = pg.pool_id, .pg_num = pg.pg_num });
+            break;
+        }
+        dirty_pgs.insert({ .pool_id = pg.pool_id, .pg_num = pg.pg_num });
+        if (immediate_commit == IMMEDIATE_NONE)
+        {
+            unstable_write_count++;
+            if (unstable_write_count >= autosync_writes)
+            {
+                unstable_write_count = 0;
+                autosync();
+            }
+        }
+        pg.total_count--;
     }
-    pg.total_count--;
     cur_op->reply.hdr.retval = 0;
     // indicate possibly unfinished (left_on_dead) deletions
     cur_op->reply.del.flags = OSD_DEL_SUPPORT_LEFT_ON_DEAD;

src/osd/osd_primary.h

@@ -20,14 +20,15 @@ struct unstable_osd_num_t
 struct osd_primary_op_data_t
 {
     int st = 0;
-    pg_num_t pg_num;
+    pg_num_t pg_num = 0;
-    object_id oid;
+    object_id oid = {};
-    uint64_t target_ver;
+    uint64_t target_ver = 0;
     uint64_t orig_ver = 0, fact_ver = 0;
-    uint64_t scheme = 0;
     int n_subops = 0, done = 0, errors = 0, drops = 0, errcode = 0;
-    int degraded = 0, pg_size, pg_data_size;
+    int degraded = 0;
-    osd_rmw_stripe_t *stripes;
+    int stripe_count = 0;
+    osd_rmw_stripe_t *stripes = NULL;
+    pg_t *pg = NULL;
     osd_op_t *subops = NULL;
     uint64_t *prev_set = NULL;
     pg_osd_set_state_t *object_state = NULL;

src/osd/osd_primary_chain.cpp

@@ -7,7 +7,7 @@
 void osd_t::continue_chained_read(osd_op_t *cur_op)
 {
     osd_primary_op_data_t *op_data = cur_op->op_data;
-    auto & pg = pgs.at({ .pool_id = INODE_POOL(op_data->oid.inode), .pg_num = op_data->pg_num });
+    auto & pg = *op_data->pg;
     if (op_data->st == 1)
         goto resume_1;
     else if (op_data->st == 2)
@@ -17,7 +17,7 @@ void osd_t::continue_chained_read(osd_op_t *cur_op)
     else if (op_data->st == 4)
         goto resume_4;
     cur_op->reply.rw.bitmap_len = 0;
-    for (int role = 0; role < op_data->pg_data_size; role++)
+    for (int role = 0; role < pg.pg_data_size; role++)
     {
         op_data->stripes[role].read_start = op_data->stripes[role].req_start;
         op_data->stripes[role].read_end = op_data->stripes[role].req_end;
@@ -329,7 +329,7 @@ std::vector<osd_chain_read_t> osd_t::collect_chained_read_requests(osd_op_t *cur
 {
     osd_primary_op_data_t *op_data = cur_op->op_data;
     std::vector<osd_chain_read_t> chain_reads;
-    int stripe_count = (op_data->scheme == POOL_SCHEME_REPLICATED ? 1 : op_data->pg_size);
+    int stripe_count = (op_data->pg->scheme == POOL_SCHEME_REPLICATED ? 1 : op_data->pg->pg_size);
     memset(op_data->stripes[0].bmp_buf, 0, stripe_count * clean_entry_bitmap_size);
     uint8_t *global_bitmap = (uint8_t*)op_data->stripes[0].bmp_buf;
     // We always use at most 1 read request per layer
@@ -337,7 +337,7 @@ std::vector<osd_chain_read_t> osd_t::collect_chained_read_requests(osd_op_t *cur
     {
         uint8_t *part_bitmap = ((uint8_t*)op_data->snapshot_bitmaps) + chain_pos*stripe_count*clean_entry_bitmap_size;
         int start = !cur_op->req.rw.len ? 0 : (cur_op->req.rw.offset - op_data->oid.stripe)/bs_bitmap_granularity;
-        int end = !cur_op->req.rw.len ? op_data->pg_data_size*clean_entry_bitmap_size*8 : start + cur_op->req.rw.len/bs_bitmap_granularity;
+        int end = !cur_op->req.rw.len ? op_data->pg->pg_data_size*clean_entry_bitmap_size*8 : start + cur_op->req.rw.len/bs_bitmap_granularity;
         // Skip unneeded part in the beginning
         while (start < end && (
             ((global_bitmap[start>>3] >> (start&7)) & 1) ||
@@ -410,11 +410,11 @@ int osd_t::submit_chained_read_requests(pg_t & pg, osd_op_t *cur_op)
         // FIXME: maybe introduce split_read_stripes to shorten these lines and to remove read_start=req_start
         osd_rmw_stripe_t *stripes = chain_stripes + chain_reads[cri].chain_pos*stripe_count;
         split_stripes(pg.pg_data_size, bs_block_size, chain_reads[cri].offset, chain_reads[cri].len, stripes);
-        if (op_data->scheme == POOL_SCHEME_REPLICATED && !stripes[0].req_end)
+        if (pg.scheme == POOL_SCHEME_REPLICATED && !stripes[0].req_end)
         {
             continue;
         }
-        for (int role = 0; role < op_data->pg_data_size; role++)
+        for (int role = 0; role < pg.pg_data_size; role++)
         {
             stripes[role].read_start = stripes[role].req_start;
             stripes[role].read_end = stripes[role].req_end;
@@ -423,7 +423,7 @@ int osd_t::submit_chained_read_requests(pg_t & pg, osd_op_t *cur_op)
         if (pg.state != PG_ACTIVE)
         {
             cur_set = get_object_osd_set(pg, cur_oid, &op_data->chain_states[chain_reads[cri].chain_pos]);
-            if (op_data->scheme != POOL_SCHEME_REPLICATED)
+            if (pg.scheme != POOL_SCHEME_REPLICATED)
             {
                 if (extend_missing_stripes(stripes, cur_set, pg.pg_data_size, pg.pg_size) < 0)
                 {
@@ -446,7 +446,7 @@ int osd_t::submit_chained_read_requests(pg_t & pg, osd_op_t *cur_op)
                 }
             }
         }
-        if (op_data->scheme == POOL_SCHEME_REPLICATED)
+        if (pg.scheme == POOL_SCHEME_REPLICATED)
         {
             n_subops++;
             read_buffer_size += stripes[0].read_end - stripes[0].read_start;
@@ -491,7 +491,7 @@ int osd_t::submit_chained_read_requests(pg_t & pg, osd_op_t *cur_op)
     for (int cri = 0; cri < chain_reads.size(); cri++)
     {
         osd_rmw_stripe_t *stripes = chain_stripes + chain_reads[cri].chain_pos*stripe_count;
-        if (op_data->scheme == POOL_SCHEME_REPLICATED && !stripes[0].req_end)
+        if (pg.scheme == POOL_SCHEME_REPLICATED && !stripes[0].req_end)
         {
             continue;
         }
@@ -501,9 +501,9 @@ int osd_t::submit_chained_read_requests(pg_t & pg, osd_op_t *cur_op)
         auto cur_state = op_data->chain_states[chain_reads[cri].chain_pos];
         uint64_t *cur_set = (pg.state != PG_ACTIVE && cur_state ? cur_state->read_target.data() : pg.cur_set.data());
         int zero_read = -1;
-        if (op_data->scheme == POOL_SCHEME_REPLICATED)
+        if (pg.scheme == POOL_SCHEME_REPLICATED)
         {
-            for (int role = 0; role < op_data->pg_size; role++)
+            for (int role = 0; role < pg.pg_size; role++)
                 if (cur_set[role] == this->osd_num || zero_read == -1)
                     zero_read = role;
         }
@@ -535,7 +535,7 @@ void osd_t::check_corrupted_chained(pg_t & pg, osd_op_t *cur_op)
         }
         if (corrupted)
         {
-            mark_object_corrupted(pg, cur_oid, op_data->chain_states[op_data->chain_reads[cri].chain_pos], stripes, false, false);
+            mark_object_corrupted(pg, cur_oid, op_data->chain_states[op_data->chain_reads[cri].chain_pos], stripes, false);
         }
     }
 }
@@ -555,18 +555,18 @@ void osd_t::send_chained_read_results(pg_t & pg, osd_op_t *cur_op)
         {
             // Reconstruct missing stripes
             osd_rmw_stripe_t *stripes = chain_stripes + op_data->chain_reads[cri].chain_pos*stripe_count;
-            if (op_data->scheme == POOL_SCHEME_XOR)
+            if (pg.scheme == POOL_SCHEME_XOR)
             {
                 reconstruct_stripes_xor(stripes, pg.pg_size, clean_entry_bitmap_size);
             }
-            else if (op_data->scheme == POOL_SCHEME_EC)
+            else if (pg.scheme == POOL_SCHEME_EC)
             {
                 reconstruct_stripes_ec(stripes, pg.pg_size, pg.pg_data_size, clean_entry_bitmap_size);
             }
         }
     }
     // Send bitmap
-    cur_op->reply.rw.bitmap_len = op_data->pg_data_size * clean_entry_bitmap_size;
+    cur_op->reply.rw.bitmap_len = pg.pg_data_size * clean_entry_bitmap_size;
     cur_op->iov.push_back(op_data->stripes[0].bmp_buf, cur_op->reply.rw.bitmap_len);
     // And finally compose the result
     uint64_t sent = 0;

src/osd/osd_primary_subops.cpp

@@ -67,7 +67,7 @@ void osd_t::finish_op(osd_op_t *cur_op, int retval)
         if (cur_op->req.hdr.opcode == OSD_OP_DELETE)
         {
             if (cur_op->op_data)
-                inode_stats[cur_op->req.rw.inode].op_bytes[inode_st_op] += cur_op->op_data->pg_data_size * bs_block_size;
+                inode_stats[cur_op->req.rw.inode].op_bytes[inode_st_op] += cur_op->op_data->pg->pg_data_size * bs_block_size;
         }
         else
             inode_stats[cur_op->req.rw.inode].op_bytes[inode_st_op] += cur_op->req.rw.len;
@@ -76,7 +76,7 @@ void osd_t::finish_op(osd_op_t *cur_op, int retval)
     {
         if (cur_op->op_data->pg_num > 0)
         {
-            auto & pg = pgs.at({ .pool_id = INODE_POOL(cur_op->op_data->oid.inode), .pg_num = cur_op->op_data->pg_num });
+            auto & pg = *cur_op->op_data->pg;
             pg.inflight--;
             assert(pg.inflight >= 0);
             if ((pg.state & PG_STOPPING) && pg.inflight == 0 && !pg.flush_batch)
@@ -126,10 +126,10 @@ void osd_t::submit_primary_subops(int submit_type, uint64_t op_version, const ui
     bool wr = submit_type == SUBMIT_WRITE;
     osd_primary_op_data_t *op_data = cur_op->op_data;
     osd_rmw_stripe_t *stripes = op_data->stripes;
-    bool rep = op_data->scheme == POOL_SCHEME_REPLICATED;
+    bool rep = op_data->pg->scheme == POOL_SCHEME_REPLICATED;
     // Allocate subops
     int n_subops = 0, zero_read = -1;
-    for (int role = 0; role < op_data->pg_size; role++)
+    for (int role = 0; role < op_data->pg->pg_size; role++)
     {
         if (osd_set[role] == this->osd_num || osd_set[role] != 0 && zero_read == -1)
             zero_read = role;
@@ -152,11 +152,11 @@ void osd_t::submit_primary_subops(int submit_type, uint64_t op_version, const ui
 int osd_t::submit_primary_subop_batch(int submit_type, inode_t inode, uint64_t op_version,
     osd_rmw_stripe_t *stripes, const uint64_t* osd_set, osd_op_t *cur_op, int subop_idx, int zero_read)
 {
+    bool rep = cur_op->op_data->pg->scheme == POOL_SCHEME_REPLICATED;
     bool wr = submit_type == SUBMIT_WRITE;
     osd_primary_op_data_t *op_data = cur_op->op_data;
-    bool rep = op_data->scheme == POOL_SCHEME_REPLICATED;
     int i = subop_idx;
-    for (int role = 0; role < op_data->pg_size; role++)
+    for (int role = 0; role < op_data->pg->pg_size; role++)
     {
         // We always submit zero-length writes to all replicas, even if the stripe is not modified
         if (!(wr || !rep && stripes[role].read_end != 0 || zero_read == role || submit_type == SUBMIT_SCRUB_READ))
@@ -168,109 +168,9 @@ int osd_t::submit_primary_subop_batch(int submit_type, inode_t inode, uint64_t o
         osd_rmw_stripe_t *si = stripes + (submit_type == SUBMIT_SCRUB_READ ? role : stripe_num);
         if (role_osd_num != 0)
         {
-            osd_op_t *subop = op_data->subops + i;
-            uint32_t subop_len = wr
-                ? si->write_end - si->write_start
-                : si->read_end - si->read_start;
-            if (!wr && si->read_end == UINT32_MAX)
-            {
-                subop_len = 0;
-            }
             si->osd_num = role_osd_num;
-            si->read_error = false;
+            si->role = stripe_num;
-            subop->bitmap = si->bmp_buf;
+            submit_primary_subop(cur_op, &op_data->subops[i], si, wr, inode, op_version);
-            subop->bitmap_len = clean_entry_bitmap_size;
-            // Using rmw_buf to pass pointer to stripes. Dirty but should work
-            subop->rmw_buf = si;
-            if (role_osd_num == this->osd_num)
-            {
-                clock_gettime(CLOCK_REALTIME, &subop->tv_begin);
-                subop->op_type = (uint64_t)cur_op;
-                subop->bs_op = new blockstore_op_t((blockstore_op_t){
-                    .opcode = (uint64_t)(wr ? (rep ? BS_OP_WRITE_STABLE : BS_OP_WRITE) : BS_OP_READ),
-                    .callback = [subop, this](blockstore_op_t *bs_subop)
-                    {
-                        handle_primary_bs_subop(subop);
-                    },
-                    { {
-                        .oid = (object_id){
-                            .inode = inode,
-                            .stripe = op_data->oid.stripe | stripe_num,
-                        },
-                        .version = op_version,
-                        .offset = wr ? si->write_start : si->read_start,
-                        .len = subop_len,
-                    } },
-                    .buf = wr ? si->write_buf : si->read_buf,
-                    .bitmap = si->bmp_buf,
-                });
-#ifdef OSD_DEBUG
-                printf(
-                    "Submit %s to local: %jx:%jx v%ju %u-%u\n", wr ? "write" : "read",
-                    inode, op_data->oid.stripe | stripe_num, op_version,
-                    subop->bs_op->offset, subop->bs_op->len
-                );
-#endif
-                bs->enqueue_op(subop->bs_op);
-            }
-            else
-            {
-                subop->op_type = OSD_OP_OUT;
-                subop->req.sec_rw = {
-                    .header = {
-                        .magic = SECONDARY_OSD_OP_MAGIC,
-                        .id = msgr.next_subop_id++,
-                        .opcode = (uint64_t)(wr ? (rep ? OSD_OP_SEC_WRITE_STABLE : OSD_OP_SEC_WRITE) : OSD_OP_SEC_READ),
-                    },
-                    .oid = {
-                        .inode = inode,
-                        .stripe = op_data->oid.stripe | stripe_num,
-                    },
-                    .version = op_version,
-                    .offset = wr ? si->write_start : si->read_start,
-                    .len = subop_len,
-                    .attr_len = wr ? clean_entry_bitmap_size : 0,
-                    .flags = cur_op->peer_fd == SELF_FD && cur_op->req.hdr.opcode != OSD_OP_SCRUB ? OSD_OP_RECOVERY_RELATED : 0,
-                };
-#ifdef OSD_DEBUG
-                printf(
-                    "Submit %s to osd %ju: %jx:%jx v%ju %u-%u\n", wr ? "write" : "read", role_osd_num,
-                    inode, op_data->oid.stripe | stripe_num, op_version,
-                    subop->req.sec_rw.offset, subop->req.sec_rw.len
-                );
-#endif
-                if (wr)
-                {
-                    if (si->write_end > si->write_start)
-                    {
-                        subop->iov.push_back(si->write_buf, si->write_end - si->write_start);
-                    }
-                }
-                else
-                {
-                    if (subop_len > 0)
-                    {
-                        subop->iov.push_back(si->read_buf, subop_len);
-                    }
-                }
-                subop->callback = [cur_op, this](osd_op_t *subop)
-                {
-                    handle_primary_subop(subop, cur_op);
-                };
-                auto peer_fd_it = msgr.osd_peer_fds.find(role_osd_num);
-                if (peer_fd_it != msgr.osd_peer_fds.end())
-                {
-                    subop->peer_fd = peer_fd_it->second;
-                    msgr.outbox_push(subop);
-                }
-                else
-                {
-                    // Fail it immediately
-                    subop->peer_fd = -1;
-                    subop->reply.hdr.retval = -EPIPE;
-                    ringloop->set_immediate([subop]() { std::function<void(osd_op_t*)>(subop->callback)(subop); });
-                }
-            }
             i++;
         }
         else
@@ -281,6 +181,112 @@ int osd_t::submit_primary_subop_batch(int submit_type, inode_t inode, uint64_t o
     return i-subop_idx;
 }
 
+void osd_t::submit_primary_subop(osd_op_t *cur_op, osd_op_t *subop,
+    osd_rmw_stripe_t *si, bool wr, inode_t inode, uint64_t op_version)
+{
+    uint32_t subop_len = wr
+        ? si->write_end - si->write_start
+        : si->read_end - si->read_start;
+    if (!wr && si->read_end == UINT32_MAX)
+    {
+        subop_len = 0;
+    }
+    si->read_error = false;
+    subop->bitmap = si->bmp_buf;
+    subop->bitmap_len = clean_entry_bitmap_size;
+    // Using rmw_buf to pass pointer to stripes. Dirty but works
+    subop->rmw_buf = si;
+    if (si->osd_num == this->osd_num)
+    {
+        clock_gettime(CLOCK_REALTIME, &subop->tv_begin);
+        subop->op_type = (uint64_t)cur_op; // also dirty
+        subop->bs_op = new blockstore_op_t((blockstore_op_t){
+            .opcode = (uint64_t)(wr ? (cur_op->op_data->pg->scheme == POOL_SCHEME_REPLICATED ? BS_OP_WRITE_STABLE : BS_OP_WRITE) : BS_OP_READ),
+            .callback = [subop, this](blockstore_op_t *bs_subop)
+            {
+                handle_primary_bs_subop(subop);
+            },
+            { {
+                .oid = (object_id){
+                    .inode = inode,
+                    .stripe = cur_op->op_data->oid.stripe | si->role,
+                },
+                .version = op_version,
+                .offset = wr ? si->write_start : si->read_start,
+                .len = subop_len,
+            } },
+            .buf = wr ? si->write_buf : si->read_buf,
+            .bitmap = si->bmp_buf,
+        });
+#ifdef OSD_DEBUG
+         printf(
+             "Submit %s to local: %jx:%jx v%ju %u-%u\n", wr ? "write" : "read",
+             inode, op_data->oid.stripe | si->role, op_version,
+             subop->bs_op->offset, subop->bs_op->len
+         );
+#endif
+        bs->enqueue_op(subop->bs_op);
+    }
+    else
+    {
+        subop->op_type = OSD_OP_OUT;
+        subop->req.sec_rw = (osd_op_sec_rw_t){
+            .header = {
+                .magic = SECONDARY_OSD_OP_MAGIC,
+                .id = msgr.next_subop_id++,
+                .opcode = (uint64_t)(wr ? (cur_op->op_data->pg->scheme == POOL_SCHEME_REPLICATED ? OSD_OP_SEC_WRITE_STABLE : OSD_OP_SEC_WRITE) : OSD_OP_SEC_READ),
+            },
+            .oid = {
+                .inode = inode,
+                .stripe = cur_op->op_data->oid.stripe | si->role,
+            },
+            .version = op_version,
+            .offset = wr ? si->write_start : si->read_start,
+            .len = subop_len,
+            .attr_len = wr ? clean_entry_bitmap_size : 0,
+            .flags = cur_op->peer_fd == SELF_FD && cur_op->req.hdr.opcode != OSD_OP_SCRUB ? OSD_OP_RECOVERY_RELATED : 0,
+        };
+#ifdef OSD_DEBUG
+        printf(
+            "Submit %s to osd %ju: %jx:%jx v%ju %u-%u\n", wr ? "write" : "read", si->osd_num,
+            inode, op_data->oid.stripe | si->role, op_version,
+            subop->req.sec_rw.offset, subop->req.sec_rw.len
+        );
+#endif
+        if (wr)
+        {
+            if (si->write_end > si->write_start)
+            {
+                subop->iov.push_back(si->write_buf, si->write_end - si->write_start);
+            }
+        }
+        else
+        {
+            if (subop_len > 0)
+            {
+                subop->iov.push_back(si->read_buf, subop_len);
+            }
+        }
+        subop->callback = [cur_op, this](osd_op_t *subop)
+        {
+            handle_primary_subop(subop, cur_op);
+        };
+        auto peer_fd_it = msgr.osd_peer_fds.find(si->osd_num);
+        if (peer_fd_it != msgr.osd_peer_fds.end())
+        {
+            subop->peer_fd = peer_fd_it->second;
+            msgr.outbox_push(subop);
+        }
+        else
+        {
+            // Fail it immediately
+            subop->peer_fd = -1;
+            subop->reply.hdr.retval = -EPIPE;
+            ringloop->set_immediate([subop]() { std::function<void(osd_op_t*)>(subop->callback)(subop); });
+        }
+    }
+}
+
 static uint64_t bs_op_to_osd_op[] = {
     0,
     OSD_OP_SEC_READ,            // BS_OP_READ = 1
@@ -401,7 +407,7 @@ void osd_t::handle_primary_subop(osd_op_t *subop, osd_op_t *cur_op)
         printf("subop %s %jx:%jx from osd %jd: version = %ju\n", osd_op_names[opcode],
             subop->req.sec_rw.oid.inode, subop->req.sec_rw.oid.stripe, peer_osd, version);
 #endif
-        if (op_data->fact_ver != UINT64_MAX)
+        if (version != 0 && op_data->fact_ver != UINT64_MAX)
         {
             if (op_data->fact_ver != 0 && op_data->fact_ver != version)
             {
@@ -526,7 +532,7 @@ bool contains_osd(osd_num_t *osd_set, uint64_t size, osd_num_t osd_num)
 void osd_t::submit_primary_del_subops(osd_op_t *cur_op, osd_num_t *cur_set, uint64_t set_size, pg_osd_set_t & loc_set)
 {
     osd_primary_op_data_t *op_data = cur_op->op_data;
-    bool rep = op_data->scheme == POOL_SCHEME_REPLICATED;
+    bool rep = op_data->pg->scheme == POOL_SCHEME_REPLICATED;
     obj_ver_osd_t extra_chunks[loc_set.size()];
     int chunks_to_del = 0;
     for (auto & chunk: loc_set)
@@ -738,10 +744,10 @@ void osd_t::submit_primary_rollback_subops(osd_op_t *cur_op, const uint64_t* osd
 {
     osd_primary_op_data_t *op_data = cur_op->op_data;
     osd_rmw_stripe_t *stripes = op_data->stripes;
-    assert(op_data->scheme != POOL_SCHEME_REPLICATED);
+    assert(op_data->pg->scheme != POOL_SCHEME_REPLICATED);
     // Allocate subops
     int n_subops = 0;
-    for (int role = 0; role < op_data->pg_size; role++)
+    for (int role = 0; role < op_data->pg->pg_size; role++)
     {
         if (osd_set[role] != 0 && !stripes[role].read_error &&
             (osd_set[role] == this->osd_num || msgr.osd_peer_fds.find(osd_set[role]) != msgr.osd_peer_fds.end()))
@@ -758,7 +764,7 @@ void osd_t::submit_primary_rollback_subops(osd_op_t *cur_op, const uint64_t* osd
     op_data->subops = new osd_op_t[n_subops];
     op_data->unstable_writes = new obj_ver_id[n_subops];
     int i = 0;
-    for (int role = 0; role < op_data->pg_size; role++)
+    for (int role = 0; role < op_data->pg->pg_size; role++)
     {
         if (osd_set[role] != 0 && !stripes[role].read_error &&
             (osd_set[role] == this->osd_num || msgr.osd_peer_fds.find(osd_set[role]) != msgr.osd_peer_fds.end()))

src/osd/osd_primary_write.cpp

@@ -44,7 +44,7 @@ void osd_t::continue_primary_write(osd_op_t *cur_op)
         return;
     }
     osd_primary_op_data_t *op_data = cur_op->op_data;
-    auto & pg = pgs.at({ .pool_id = INODE_POOL(op_data->oid.inode), .pg_num = op_data->pg_num });
+    auto & pg = *cur_op->op_data->pg;
     if (op_data->st == 1)      goto resume_1;
     else if (op_data->st == 2) goto resume_2;
     else if (op_data->st == 3) goto resume_3;
@@ -73,7 +73,7 @@ resume_1:
         op_data->object_state->ref_count++;
     }
 retry_1:
-    if (op_data->scheme == POOL_SCHEME_REPLICATED)
+    if (pg.scheme == POOL_SCHEME_REPLICATED)
     {
         // Simplified algorithm
         op_data->stripes[0].write_start = op_data->stripes[0].req_start;
@@ -99,7 +99,7 @@ retry_1:
     {
         assert(!cur_op->rmw_buf);
         cur_op->rmw_buf = calc_rmw(cur_op->buf, op_data->stripes, op_data->prev_set,
-            pg.pg_size, op_data->pg_data_size, pg.pg_cursize, pg.cur_set.data(), bs_block_size, clean_entry_bitmap_size);
+            pg.pg_size, pg.pg_data_size, pg.pg_cursize, pg.cur_set.data(), bs_block_size, clean_entry_bitmap_size);
         if (!cur_op->rmw_buf)
         {
             // Refuse partial overwrite of an incomplete object
@@ -114,7 +114,7 @@ retry_1:
             // Allow to read version number (just version number!) from corrupted chunks
             // to allow full overwrite of a corrupted object
             bool found = false;
-            for (int role = 0; role < op_data->pg_size; role++)
+            for (int role = 0; role < pg.pg_size; role++)
             {
                 if (op_data->prev_set[role] != 0 || op_data->stripes[role].read_end > op_data->stripes[role].read_start)
                 {
@@ -124,8 +124,8 @@ retry_1:
             }
             if (!found)
             {
-                osd_num_t corrupted_target[op_data->pg_size];
+                osd_num_t corrupted_target[pg.pg_size];
-                for (int role = 0; role < op_data->pg_size; role++)
+                for (int role = 0; role < pg.pg_size; role++)
                 {
                     corrupted_target[role] = 0;
                 }
@@ -151,7 +151,7 @@ resume_3:
         if (op_data->errcode == -EIO || op_data->errcode == -EDOM)
         {
             // Mark object corrupted and retry
-            op_data->object_state = mark_object_corrupted(pg, op_data->oid, op_data->object_state, op_data->stripes, true, false);
+            op_data->object_state = mark_object_corrupted(pg, op_data->oid, op_data->object_state, op_data->stripes, true);
             op_data->prev_set = op_data->object_state ? op_data->object_state->read_target.data() : pg.cur_set.data();
             if (cur_op->rmw_buf)
             {
@@ -165,6 +165,7 @@ resume_3:
         return;
     }
     // Check CAS version
+    // FIXME: Handle CAS writes as "immediate" in non-immediate_commit pools, otherwise CAS doesn't make sense
     if (cur_op->req.rw.version && op_data->fact_ver != (cur_op->req.rw.version-1))
     {
         deref_object_state(pg, &op_data->object_state, true);
@@ -172,7 +173,7 @@ resume_3:
         cur_op->reply.rw.version = op_data->fact_ver;
         goto continue_others;
     }
-    if (op_data->scheme == POOL_SCHEME_REPLICATED)
+    if (pg.scheme == POOL_SCHEME_REPLICATED)
     {
         // Set bitmap bits
         bitmap_set(op_data->stripes[0].bmp_buf, op_data->stripes[0].write_start,
@@ -203,7 +204,7 @@ resume_3:
         }
         else if (pg.scheme == POOL_SCHEME_EC)
         {
-            calc_rmw_parity_ec(op_data->stripes, pg.pg_size, op_data->pg_data_size, op_data->prev_set, pg.cur_set.data(), bs_block_size, clean_entry_bitmap_size);
+            calc_rmw_parity_ec(op_data->stripes, pg.pg_size, pg.pg_data_size, op_data->prev_set, pg.cur_set.data(), bs_block_size, clean_entry_bitmap_size);
         }
     }
     // Send writes
@@ -269,7 +270,7 @@ resume_5:
         // and rollback successful part updates in case of EC.
         if (op_data->done > 0 && !op_data->drops)
         {
-            if (op_data->scheme != POOL_SCHEME_REPLICATED)
+            if (pg.scheme != POOL_SCHEME_REPLICATED)
             {
                 submit_primary_rollback_subops(cur_op, pg.cur_set.data());
 resume_11:
@@ -293,7 +294,7 @@ resume_12:
         pg_cancel_write_queue(pg, cur_op, op_data->oid, op_data->errcode);
         return;
     }
-    if (op_data->scheme != POOL_SCHEME_REPLICATED)
+    if (pg.scheme != POOL_SCHEME_REPLICATED)
     {
         // Remove version override just after the write, but before stabilizing
         pg.ver_override.erase(op_data->oid);
@@ -329,7 +330,7 @@ resume_7:
                 memset(&recovery_stat[recovery_type], 0, sizeof(recovery_stat[recovery_type]));
                 recovery_stat[recovery_type].count++;
             }
-            for (int role = 0; role < (op_data->scheme == POOL_SCHEME_REPLICATED ? 1 : pg.pg_size); role++)
+            for (int role = 0; role < (pg.scheme == POOL_SCHEME_REPLICATED ? 1 : pg.pg_size); role++)
             {
                 recovery_stat[recovery_type].bytes += op_data->stripes[role].write_end - op_data->stripes[role].write_start;
             }
@@ -353,7 +354,7 @@ resume_7:
             for (auto & chunk: op_data->object_state->osd_set)
             {
                 // Check is the same as in submit_primary_del_subops()
-                if (op_data->scheme == POOL_SCHEME_REPLICATED
+                if (pg.scheme == POOL_SCHEME_REPLICATED
                     ? !contains_osd(pg.cur_set.data(), pg.pg_size, chunk.osd_num)
                     : (chunk.osd_num != pg.cur_set[chunk.role]))
                 {
@@ -361,7 +362,7 @@ resume_7:
                         .osd_num = chunk.osd_num,
                         .oid = {
                             .inode = op_data->oid.inode,
-                            .stripe = op_data->oid.stripe | (op_data->scheme == POOL_SCHEME_REPLICATED ? 0 : chunk.role),
+                            .stripe = op_data->oid.stripe | (pg.scheme == POOL_SCHEME_REPLICATED ? 0 : chunk.role),
                         },
                         .version = op_data->fact_ver,
                     });
@@ -472,7 +473,7 @@ bool osd_t::remember_unstable_write(osd_op_t *cur_op, pg_t & pg, pg_osd_set_t &
     if (immediate_commit == IMMEDIATE_ALL)
     {
 immediate:
-        if (op_data->scheme != POOL_SCHEME_REPLICATED)
+        if (pg.scheme != POOL_SCHEME_REPLICATED)
         {
             // Send STABILIZE ops immediately
             op_data->unstable_write_osds = new std::vector<unstable_osd_num_t>();
@@ -515,7 +516,7 @@ resume_7:
     }
     else if (immediate_commit == IMMEDIATE_SMALL)
     {
-        int stripe_count = (op_data->scheme == POOL_SCHEME_REPLICATED ? 1 : op_data->pg_size);
+        int stripe_count = (pg.scheme == POOL_SCHEME_REPLICATED ? 1 : pg.pg_size);
         for (int role = 0; role < stripe_count; role++)
         {
             if (op_data->stripes[role].write_start == 0 &&
@@ -531,7 +532,7 @@ resume_7:
     {
 lazy:
         unstable_write_count++;
-        if (op_data->scheme != POOL_SCHEME_REPLICATED)
+        if (pg.scheme != POOL_SCHEME_REPLICATED)
         {
             // Remember version as unstable for EC/XOR
             for (auto & chunk: loc_set)

src/osd/osd_rmw.cpp

@@ -1118,139 +1118,230 @@ static bool next_combination(int *subset, int k, int n)
     return true;
 }
 
-static int c_n_k(int n, int k)
+static uint64_t c_n_k(uint64_t n, uint64_t k)
 {
-    int c = 1;
+    uint64_t c = 1;
-    for (int i = n; i > k; i--)
+    for (uint64_t i = n; i > k; i--)
+    {
+        if ((c*i) < i)
+            return UINT64_MAX;
         c *= i;
-    for (int i = 2; i <= (n-k); i++)
+    }
+    for (uint64_t i = 2; i <= (n-k); i++)
         c /= i;
     return c;
 }
 
-std::vector<int> ec_find_good(osd_rmw_stripe_t *stripes, int pg_size, int pg_minsize, bool is_xor,
+static std::vector<int> ec_check_combination(osd_rmw_stripe_t *stripes, int stripe_count,
-    uint32_t chunk_size, uint32_t bitmap_size, int max_bruteforce)
+    int *subset, int pg_size, int pg_minsize, bool is_xor,
+    uint32_t chunk_size, uint32_t bitmap_size, uint8_t *tmp_buf)
+{
+    osd_num_t fake_osd_set[pg_size];
+    for (int i = 0; i < pg_size; i++)
+    {
+        fake_osd_set[i] = i+1;
+    }
+    osd_rmw_stripe_t brute_stripes[pg_size];
+    memset(brute_stripes, 0, sizeof(osd_rmw_stripe_t)*pg_size);
+    for (int i = 0; i < pg_size; i++)
+    {
+        auto & bs = brute_stripes[i];
+        bs.req_end = bs.read_end = chunk_size;
+    }
+    for (int i = 0; i < pg_minsize; i++)
+    {
+        auto & src = stripes[subset[i]];
+        auto & bs = brute_stripes[src.role];
+        bs.bmp_buf = src.bmp_buf;
+        bs.write_buf = bs.read_buf = src.read_buf;
+    }
+    for (int i = 0; i < pg_size; i++)
+    {
+        auto & bs = brute_stripes[i];
+        if (!bs.read_buf)
+        {
+            // missing chunks are recovered in read_bufs and write_bufs are used as source for parity
+            bs.missing = true;
+            bs.read_buf = bs.write_buf = tmp_buf+i*chunk_size;
+            bs.bmp_buf = tmp_buf + stripe_count*chunk_size + i*bitmap_size;
+        }
+        else if (i >= pg_minsize)
+        {
+            // parity chunks are regenerated in their write_bufs, so use a temporary buffer
+            bs.write_buf = tmp_buf+i*chunk_size;
+        }
+    }
+    if (is_xor)
+    {
+        assert(pg_size == pg_minsize+1);
+        reconstruct_stripes_xor(brute_stripes, pg_size, bitmap_size);
+    }
+    else
+    {
+        reconstruct_stripes_ec(brute_stripes, pg_size, pg_minsize, bitmap_size);
+        calc_rmw_parity_ec(brute_stripes, pg_size, pg_minsize, fake_osd_set, fake_osd_set, chunk_size, bitmap_size);
+    }
+    bool matched_other = false;
+    std::vector<int> good_set;
+    for (int i = 0; i < stripe_count; i++)
+    {
+        if (stripes[i].read_error || stripes[i].not_exists)
+        {
+            continue;
+        }
+        auto & bs = brute_stripes[stripes[i].role];
+        if (!bs.missing && bs.read_buf == stripes[i].read_buf)
+        {
+            // source chunk, mark OK
+            good_set.push_back(i);
+        }
+        else if (memcmp(stripes[i].role < pg_minsize ? bs.read_buf : bs.write_buf, stripes[i].read_buf, chunk_size) == 0)
+        {
+            // matching chunk, mark OK
+            good_set.push_back(i);
+            matched_other = true;
+        }
+    }
+    if (!matched_other)
+    {
+        good_set.clear();
+    }
+    return good_set;
+}
+
+static int count_roles(osd_rmw_stripe_t *stripes, std::vector<int> & valid_chunks, int pg_size)
+{
+    bool role_ok[pg_size];
+    for (int i = 0; i < pg_size; i++)
+    {
+        role_ok[i] = false;
+    }
+    for (int idx: valid_chunks)
+    {
+        role_ok[stripes[idx].role] = true;
+    }
+    int ok_count = 0;
+    for (int i = 0; i < pg_size; i++)
+    {
+        if (role_ok[i])
+            ok_count++;
+    }
+    return ok_count;
+}
+
+std::vector<int> ec_find_good(osd_rmw_stripe_t *stripes, int stripe_count, int pg_size, int pg_minsize, bool is_xor,
+    uint32_t chunk_size, uint32_t bitmap_size, uint64_t max_bruteforce, bool find_best)
 {
     std::vector<int> found_valid;
-    int cur_live[pg_size], live_count = 0, exists_count = 0;
+    std::vector<std::vector<int>> live_variants(pg_size);
-    osd_num_t fake_osd_set[pg_size];
+    int eq_to[stripe_count];
-    for (int role = 0; role < pg_size; role++)
+    int live_roles = 0, live_total = 0;
+    for (int i = 0; i < pg_size; i++)
     {
-        if (!stripes[role].missing)
+        eq_to[i] = i;
-        {
-            if (!stripes[role].not_exists)
-                exists_count++;
-            cur_live[live_count++] = role;
-            fake_osd_set[role] = role+1;
-        }
     }
-    if (live_count <= pg_minsize)
+    for (int i = 0; i < stripe_count; i++)
     {
-        return std::vector<int>();
+        if (!stripes[i].read_error && !stripes[i].not_exists)
-    }
-    if (exists_count <= pg_minsize)
-    {
-        // Special case: user manually deleted some chunks
-        for (int role = 0; role < pg_size; role++)
-            if (!stripes[role].missing && !stripes[role].not_exists)
-                found_valid.push_back(role);
-        return found_valid;
-    }
-    // Try to locate errors using brute force if there isn't too many combinations
-    osd_rmw_stripe_t brute_stripes[pg_size];
-    int out_count = live_count-pg_minsize;
-    bool brute_force = out_count > 1 && c_n_k(live_count-1, out_count-1) <= max_bruteforce;
-    int subset[pg_minsize], outset[out_count];
-    // Select all combinations with items except the last one (== anything to compare)
-    first_combination(subset, pg_minsize, live_count-1);
-    uint8_t *tmp_buf = (uint8_t*)malloc_or_die(pg_size*chunk_size);
-    do
-    {
-        memcpy(brute_stripes, stripes, sizeof(osd_rmw_stripe_t)*pg_size);
-        int i = 0, j = 0, k = 0;
-        for (; i < pg_minsize; i++, j++)
-            while (j < subset[i])
-                outset[k++] = j++;
-        while (j < pg_size)
-            outset[k++] = j++;
-        for (int i = 0; i < out_count; i++)
         {
-            brute_stripes[cur_live[outset[i]]].missing = true;
+            if (live_variants[stripes[i].role].size() > 0)
-            brute_stripes[cur_live[outset[i]]].read_buf = tmp_buf+cur_live[outset[i]]*chunk_size;
-        }
-        for (int i = 0; i < pg_minsize; i++)
-        {
-            brute_stripes[i].write_buf = brute_stripes[i].read_buf;
-            brute_stripes[i].req_start = 0;
-            brute_stripes[i].req_end = chunk_size;
-        }
-        for (int i = pg_minsize; i < pg_size; i++)
-        {
-            brute_stripes[i].write_buf = tmp_buf+i*chunk_size;
-        }
-        if (is_xor)
-        {
-            assert(pg_size == pg_minsize+1);
-            reconstruct_stripes_xor(brute_stripes, pg_size, bitmap_size);
-        }
-        else
-        {
-            reconstruct_stripes_ec(brute_stripes, pg_size, pg_minsize, bitmap_size);
-            calc_rmw_parity_ec(brute_stripes, pg_size, pg_minsize, fake_osd_set, fake_osd_set, chunk_size, bitmap_size);
-        }
-        for (int i = pg_minsize; i < pg_size; i++)
-        {
-            brute_stripes[i].read_buf = brute_stripes[i].write_buf;
-        }
-        int valid_count = 0;
-        for (int i = 0; i < out_count; i++)
-        {
-            if (memcmp(brute_stripes[cur_live[outset[i]]].read_buf,
-                    stripes[cur_live[outset[i]]].read_buf, chunk_size) == 0)
             {
-                brute_stripes[cur_live[outset[i]]].missing = false;
+                for (int j = 0; j < i; j++)
-                valid_count++;
-            }
-        }
-        if (valid_count > 0)
-        {
-            if (found_valid.size())
-            {
-                // Check if we found the same set from the different point of view,
-                // like 1 2 3 -> valid 4 5 and 1 3 4 -> valid 2 5
-                for (int i = 0, j = 0; i < pg_size; i++)
                 {
-                    if (!brute_stripes[i].missing)
+                    if (stripes[j].role == stripes[i].role &&
+                        memcmp(stripes[i].read_buf, stripes[j].read_buf, chunk_size) == 0)
                     {
-                        if (j >= found_valid.size() || found_valid[j] != i)
+                        eq_to[i] = eq_to[j];
-                        {
+                        break;
-                            // Ambiguity: we found multiple valid sets and don't know which one is correct
-                            found_valid.clear();
-                            break;
-                        }
-                        j++;
                     }
                 }
-                if (!found_valid.size())
-                {
-                    break;
-                }
             }
             else
             {
-                for (int i = 0; i < pg_size; i++)
+                live_roles++;
+            }
+            if (eq_to[i] == i)
+            {
+                live_variants[stripes[i].role].push_back(i);
+                live_total++;
+            }
+        }
+    }
+    if (live_roles == pg_minsize && live_total > pg_minsize)
+    {
+        // Nothing to validate and there are chunks with different data => object is inconsistent
+        return std::vector<int>();
+    }
+    if (live_roles <= pg_minsize)
+    {
+        // Nothing to validate, just return all live chunks
+        for (int i = 0; i < stripe_count; i++)
+            if (!stripes[i].read_error)
+                found_valid.push_back(i);
+        return found_valid;
+    }
+    // Try to locate errors using brute force if there isn't too many combinations
+    bool brute_force = c_n_k(live_roles, pg_minsize) <= max_bruteforce;
+    int combination[pg_minsize], subset[pg_minsize], subvar[pg_minsize];
+    // To translate 0..live_roles into 0..pg_size
+    int comb_to_subset[live_roles];
+    for (int i = 0, r = 0; i < pg_size; i++)
+    {
+        if (live_variants[i].size() > 0)
+            comb_to_subset[r++] = i;
+    }
+    // Select all combinations with items except the last one (== anything to compare)
+    first_combination(combination, pg_minsize, live_roles);
+    uint8_t *tmp_buf = (uint8_t*)malloc_or_die(stripe_count*(chunk_size+bitmap_size));
+    do
+    {
+        // Then loop over all subvariants (if some roles have multiple diverged variants of data)
+        for (int i = 0; i < pg_minsize; i++)
+        {
+            subvar[i] = 0;
+        }
+        while (true)
+        {
+            // Transform combination[] + subvar[] into subset[]
+            for (int i = 0; i < pg_minsize; i++)
+            {
+                subset[i] = live_variants[comb_to_subset[combination[i]]][subvar[i]];
+            }
+            // Check the combination
+            auto valid_chunks = ec_check_combination(stripes, stripe_count, subset, pg_size, pg_minsize, is_xor, chunk_size, bitmap_size, tmp_buf);
+            // The same set may be found from different points of view,
+            // like 1 2 3 -> valid 4 5 and 1 3 4 -> valid 2 5
+            if (valid_chunks.size() > 0)
+            {
+                if (found_valid.size() >= valid_chunks.size() && found_valid != valid_chunks)
                 {
-                    if (!brute_stripes[i].missing)
+                    // Ambiguity: we found multiple valid sets and don't know which one is correct
-                    {
+                    printf("Scrub found 2 different correct chunk subsets: OSD ");
-                        found_valid.push_back(i);
+                    for (int i = 0; i < found_valid.size(); i++)
-                    }
+                        printf(i > 0 ? ", %ju" : "%ju", stripes[found_valid[i]].osd_num);
+                    printf(" and OSD ");
+                    for (int i = 0; i < valid_chunks.size(); i++)
+                        printf(i > 0 ? ", %ju" : "%ju", stripes[valid_chunks[i]].osd_num);
+                    printf("\n");
+                    found_valid.clear();
+                    goto out;
+                }
+                else if (!found_valid.size() && (find_best || count_roles(stripes, valid_chunks, pg_size) >= pg_size))
+                {
+                    found_valid = valid_chunks;
                 }
             }
-            if (valid_count == out_count)
+            // Select next subvariant
+            int i = 0;
+            for (i = 0; i < pg_minsize; i++)
             {
-                // All chunks are good
+                subvar[i]++;
-                break;
+                if (subvar[i] < live_variants[combination[i]].size())
+                    break;
+                subvar[i] = 0;
             }
+            if (i >= pg_minsize)
+                break;
         }
         if (!brute_force)
         {
@@ -1258,7 +1349,8 @@ std::vector<int> ec_find_good(osd_rmw_stripe_t *stripes, int pg_size, int pg_min
             // if we find it we won't be able to check that it's the only good one
             break;
         }
-    } while (out_count > 1 && next_combination(subset, pg_minsize, live_count-1));
+    } while (next_combination(combination, pg_minsize, live_roles));
+out:
     free(tmp_buf);
     return found_valid;
 }