Release 1.4.8

- Do not use \r if output is not a terminal (should fix unexpected job output in proxmox)
- Fix rm/rm-data error return code, add --down-ok option to bypass the error
- Add EIO retry timeout and allow to disable these retries, rename up_wait_retry_interval to client_retry_interval
- Add ubuntu jammy build
- Wait for blockstore initialisation before starting OSD (prevent timeouts when init takes time)
- Fix a rare use-after-free in automatic sync after delete in blockstore

.gitea/workflows/test.yml

@@ -395,7 +395,7 @@ jobs:
     steps:
     - name: Run test
       id: test
-      timeout-minutes: 3
+      timeout-minutes: 6
       run: SCHEME=ec /root/vitastor/tests/test_snapshot_chain.sh
     - name: Print logs
       if: always() && steps.test.outcome == 'failure'
@@ -532,6 +532,24 @@ jobs:
           echo ""
         done
 
+  test_switch_primary:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 3
+      run: /root/vitastor/tests/test_switch_primary.sh
+    - name: Print logs
+      if: always() && steps.test.outcome == 'failure'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
   test_write:
     runs-on: ubuntu-latest
     needs: build

.gitea/workflows/tests-to-yaml.pl

@@ -39,6 +39,10 @@ for my $line (<>)
                 $test_name .= '_'.lc($1).'_'.$2;
             }
         }
+        if ($test_name eq 'test_snapshot_chain_ec')
+        {
+            $timeout = 6;
+        }
         $line =~ s!\./test_!/root/vitastor/tests/test_!;
         # Gitea CI doesn't support artifacts yet, lol
         #- name: Upload results

CLA-en.md

@@ -0,0 +1,115 @@
+## Contributor License Agreement
+
+> This Agreement is made in the Russian and English languages. **The English
+text of Agreement is for informational purposes only** and is not binding
+for the Parties.
+>
+> In the event of a conflict between the provisions of the Russian and
+English versions of this Agreement, the **Russian version shall prevail**.
+>
+> Russian version is published at https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-ru.md
+
+This document represents the offer of Filippov Vitaliy Vladimirovich
+("Author"), author and copyright holder of Vitastor software ("Program"),
+acknowledged by a certificate of Federal Service for Intellectual
+Property of Russian Federation (Rospatent) # 2021617829 dated 20 May 2021,
+to "Contributors" to conclude this license agreement as follows
+("Agreement" or "Offer").
+
+In accordance with Art. 435, Art. 438 of the Civil Code of the Russian
+Federation, this Agreement is an offer and in case of acceptance of the
+offer, an agreement is considered concluded on the conditions specified
+in the offer.
+
+1. Applicable Terms. \
+   1.1. "Official Repository" shall mean the computer storage, operated by
+        the Author, containing all prior and future versions of the Source
+        Code of the Program, at Internet addresses https://git.yourcmc.ru/vitalif/vitastor/
+        or https://github.com/vitalif/vitastor/. \
+   1.2. "Contributions" shall mean results of intellectual activity
+        (including, but not limited to, source code, libraries, components,
+        texts, documentation) which can be software or elements of the software
+        and which are provided by Contributors to the Author for inclusion
+        in the Program. \
+   1.3. "Contributor" shall mean a person who provides Contributions to
+        the Author and agrees with all provisions of this Agreement.
+        A Сontributor can be: 1) an individual; or 2) a legal entity or an
+        individual entrepreneur in case when an individual provides Contributions
+        on behalf of third parties, including on behalf of his employer.
+
+2. Subject of the Agreement. \
+   2.1. Subject of the Agreement shall be the Contributions sent to the Author by Contributors. \
+   2.2. The Contributor grants to the Author the right to use Contributions at his own
+        discretion and without any necessity to get a prior approval from Contributor or
+        any other third party in any way, under a simple (non-exclusive), royalty-free,
+        irrevocable license throughout the world by all means not contrary to law, in whole
+        or as a part of the Program, or other open-source or closed-source computer programs,
+        products or services (hereinafter -- the "License"), including, but not limited to: \
+        2.2.1. to execute Contributions and use them for any tasks; \
+        2.2.2. to publish and distribute Contributions in modified or unmodified form and/or to rent them; \
+        2.2.3. to modify Contributions, add comments, illustrations or any explanations to Contributions while using them; \
+        2.2.4. to create other results of intellectual activity based on Contributions, including derivative works and composite works; \
+        2.2.5. to translate Contributions into other languages, including other programming languages; \
+        2.2.6. to carry out rental and public display of Contributions; \
+        2.2.7. to use Contributions under the trade name and/or any trademark or any other label, or without it, as the Author thinks fit; \
+   2.3. The Contributor grants to the Author the right to sublicense any of the aforementioned
+        rights to third parties on any terms at the Author's discretion. \
+   2.4. The License is provided for the entire duration of Contributor's
+        exclusive intellectual property rights to the Contributions. \
+   2.5. The Contributor grants to the Author the right to decide how and where to mention,
+        or to not mention at all, the fact of his authorship, name, nickname and/or company
+        details when including Contributions into the Program or in any other computer
+        programs, products or services.
+
+3. Acceptance of the Offer \
+   3.1. The Contributor may provide Contributions to the Author in the form of
+        a "Pull Request" in an Official Repository of the Program or by any
+        other electronic means of communication, including, but not limited to,
+        E-mail or messenger applications. \
+   3.2. The acceptance of the Offer shall be the fact of provision of Contributions
+        to the Author by the Contributor by any means with the following remark:
+        “I accept Vitastor CLA agreement: https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-en.md”
+        or “Я принимаю соглашение Vitastor CLA: https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-ru.md”. \
+   3.3. Date of acceptance of the Offer shall be the date of such provision.
+
+4. Rights and obligations of the parties. \
+   4.1. The Contributor reserves the right to use Contributions by any lawful means
+        not contrary to this Agreement. \
+   4.2. The Author has the right to refuse to include Contributions into the Program
+        at any moment with no explanation to the Contributor.
+
+5. Representations and Warranties. \
+   5.1. The person providing Contributions for the purpose of their inclusion
+        in the Program represents and warrants that he is the Contributor
+        or legally acts on the Contributor's behalf. Name or company details
+        of the Contributor shall be provided with the Contribution at the moment
+        of their provision to the Author. \
+   5.2. The Contributor represents and warrants that he legally owns exclusive
+        intellectual property rights to the Contributions. \
+   5.3. The Contributor represents and warrants that any further use of
+        Contributions by the Author as provided by Contributor under the terms
+        of the Agreement does not infringe on intellectual and other rights and
+        legitimate interests of third parties. \
+   5.4. The Contributor represents and warrants that he has all rights and legal
+        capacity needed to accept this Offer; \
+   5.5. The Contributor represents and warrants that Contributions don't
+        contain malware or any information considered illegal under the law
+        of Russian Federation.
+
+6. Termination of the Agreement \
+   6.1. The Agreement may be terminated at will of both Author and Contributor,
+        formalised in the written form or if the Agreement is terminated on
+        reasons prescribed by the law of Russian Federation.
+
+7. Final Clauses \
+   7.1. The Contributor may optionally sign the Agreement in the written form. \
+   7.2. The Agreement is deemed to become effective from the Date of signing of
+        the Agreement and until the expiration of Contributor's exclusive
+        intellectual property rights to the Contributions. \
+   7.3. The Author may unilaterally alter the Agreement without informing Contributors.
+        The new version of the document shall come into effect 3 (three) days after
+        being published in the Official Repository of the Program at Internet address
+        [https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-en.md](https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-en.md).
+        Contributors should keep informed about the actual version of the Agreement themselves. \
+   7.4. If the Author and the Contributor fail to agree on disputable issues,
+        disputes shall be referred to the Moscow Arbitration court.

CLA-ru.md

@@ -0,0 +1,108 @@
+## Лицензионное соглашение с участником
+
+> Данная Оферта написана в Русской и Английской версиях. **Версия на английском
+языке предоставляется в информационных целях** и не связывает стороны договора.
+>
+> В случае несоответствий между положениями Русской и Английской версий Договора,
+**Русская версия имеет приоритет**.
+>
+> Английская версия опубликована по адресу https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-en.md
+
+Настоящий договор-оферта (далее по тексту – Оферта, Договор) адресована физическим
+и юридическим лицам (далее – Участникам) и является официальным публичным предложением
+Филиппова Виталия Владимировича (далее – Автора) программного обеспечения Vitastor,
+свидетельство Федеральной службы по интеллектуальной собственности (Роспатент) № 2021617829
+от 20 мая 2021 г. (далее – Программа) о нижеследующем:
+
+1. Термины и определения \
+   1.1. Репозиторий – электронное хранилище, содержащее исходный код Программы. \
+   1.2. Доработка – результат интеллектуальной деятельности Участника, включающий
+        в себя изменения или дополнения к исходному коду Программы, которые Участник
+        желает включить в состав Программы для дальнейшего использования и распространения
+        Автором и для этого направляет их Автору. \
+   1.3. Участник – физическое или юридическое лицо, вносящее Доработки в код Программы. \
+   1.4. ГК РФ – Гражданский кодекс Российской Федерации.
+
+2. Предмет оферты \
+   2.1. Предметом настоящей оферты являются Доработки, отправляемые Участником Автору. \
+   2.2. Участник предоставляет Автору право использовать Доработки по собственному усмотрению
+        и без необходимости предварительного согласования с Участником или иным третьим лицом
+        на условиях простой (неисключительной) безвозмездной безотзывной лицензии, полностью
+        или фрагментарно, в составе Программы или других программ, продуктов или сервисов
+        как с открытым, так и с закрытым исходным кодом, любыми способами, не противоречащими
+        закону, включая, но не ограничиваясь следующими: \
+        2.2.1. Запускать и использовать Доработки для выполнения любых задач; \
+        2.2.2. Распространять, импортировать и доводить Доработки до всеобщего сведения; \
+        2.2.3. Вносить в Доработки изменения, сокращения и дополнения, снабжать Доработки
+               при их использовании комментариями, иллюстрациями или пояснениями; \
+        2.2.4. Создавать на основе Доработок иные результаты интеллектуальной деятельности,
+               в том числе производные и составные произведения; \
+        2.2.5. Переводить Доработки на другие языки, в том числе на другие языки программирования; \
+        2.2.6. Осуществлять прокат и публичный показ Доработок; \
+        2.2.7. Использовать Доработки под любым фирменным наименованием, товарным знаком
+               (знаком обслуживания) или иным обозначением, или без такового. \
+   2.3. Участник предоставляет Автору право сублицензировать полученные права на Доработки
+        третьим лицам на любых условиях на усмотрение Автора. \
+   2.4. Участник предоставляет Автору права на Доработки на территории всего мира. \
+   2.5. Участник предоставляет Автору права на весь срок действия исключительного права
+        Участника на Доработки. \
+   2.6. Участник предоставляет Автору права на Доработки на безвозмездной основе. \
+   2.7. Участник разрешает Автору самостоятельно определять порядок, способ и
+        место указания его имени, реквизитов и/или псевдонима при включении
+        Доработок в состав Программы или других программ, продуктов или сервисов.
+
+3. Акцепт Оферты \
+   3.1. Участник может передавать Доработки в адрес Автора через зеркала официального
+        Репозитория Программы по адресам https://git.yourcmc.ru/vitalif/vitastor/ или
+        https://github.com/vitalif/vitastor/ в виде “запроса на слияние” (pull request),
+        либо в письменном виде или с помощью любых других электронных средств коммуникации,
+        например, электронной почты или мессенджеров. \
+   3.2. Факт передачи Участником Доработок в адрес Автора любым способом с одной из пометок
+        “I accept Vitastor CLA agreement: https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-en.md”
+        или “Я принимаю соглашение Vitastor CLA: https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-ru.md”
+        является полным и безоговорочным акцептом (принятием) Участником условий настоящей
+        Оферты, т.е. Участник считается ознакомившимся с настоящим публичным договором и
+        в соответствии с ГК РФ признается лицом, вступившим с Автором в договорные отношения
+        на основании настоящей Оферты. \
+   3.3. Датой акцептирования настоящей Оферты считается дата такой передачи.
+
+4. Права и обязанности Сторон \
+   4.1. Участник сохраняет за собой право использовать Доработки любым законным
+        способом, не противоречащим настоящему Договору. \
+   4.2. Автор вправе отказать Участнику во включении Доработок в состав
+        Программы без объяснения причин в любой момент по своему усмотрению.
+
+5. Гарантии и заверения \
+   5.1. Лицо, направляющее Доработки для целей их включения в состав Программы,
+        гарантирует, что является Участником или представителем Участника. Имя или реквизиты
+        Участника должны быть указаны при их передаче в адрес Автора Программы. \
+   5.2. Участник гарантирует, что является законным обладателем исключительных прав
+        на Доработки. \
+   5.3. Участник гарантирует, что на момент акцептирования настоящей Оферты ему
+        ничего не известно (и не могло быть известно) о правах третьих лиц на
+        передаваемые Автору Доработки или их часть, которые могут быть нарушены
+        в связи с передачей Доработок по настоящему Договору. \
+   5.4. Участник гарантирует, что является дееспособным лицом и обладает всеми
+        необходимыми правами для заключения Договора. \
+   5.5. Участник гарантирует, что Доработки не содержат вредоносного ПО, а также
+        любой другой информации, запрещённой к распространению по законам Российской
+        Федерации.
+
+6. Прекращение действия оферты \
+   6.1. Действие настоящего договора может быть прекращено по соглашению сторон,
+        оформленному в письменном виде, а также вследствие его расторжения по основаниям,
+        предусмотренным законом.
+
+7. Заключительные положения \
+   7.1. Участник вправе по желанию подписать настоящий Договор в письменном виде. \
+   7.2. Настоящий договор действует с момента его заключения и до истечения срока
+        действия исключительных прав Участника на Доработки. \
+   7.3. Автор имеет право в одностороннем порядке вносить изменения и дополнения в договор
+        без специального уведомления об этом Участников. Новая редакция документа вступает
+        в силу через 3 (Три) календарных дня со дня опубликования в официальном Репозитории
+        Программы по адресу в сети Интернет
+        [https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-ru.md](https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-ru.md).
+        Участники самостоятельно отслеживают действующие условия Оферты. \
+   7.4. Все споры, возникающие между сторонами в процессе их взаимодействия по настоящему
+        договору, решаются путём переговоров. В случае невозможности урегулирования споров
+        переговорным порядком стороны разрешают их в Арбитражном суде г.Москвы.

CMakeLists.txt

@@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8.12)
 
 project(vitastor)
 
-set(VERSION "1.3.1")
+set(VERSION "1.4.8")
 
 add_subdirectory(src)

csi/Makefile

@@ -1,4 +1,4 @@
-VERSION ?= v1.3.1
+VERSION ?= v1.4.8
 
 all: build push
 

csi/deploy/004-csi-nodeplugin.yaml

@@ -49,7 +49,7 @@ spec:
             capabilities:
               add: ["SYS_ADMIN"]
             allowPrivilegeEscalation: true
-          image: vitalif/vitastor-csi:v1.3.1
+          image: vitalif/vitastor-csi:v1.4.8
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/deploy/007-csi-provisioner.yaml

@@ -121,7 +121,7 @@ spec:
             privileged: true
             capabilities:
               add: ["SYS_ADMIN"]
-          image: vitalif/vitastor-csi:v1.3.1
+          image: vitalif/vitastor-csi:v1.4.8
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/src/config.go

@@ -5,7 +5,7 @@ package vitastor
 
 const (
     vitastorCSIDriverName    = "csi.vitastor.io"
-    vitastorCSIDriverVersion = "1.3.1"
+    vitastorCSIDriverVersion = "1.4.8"
 )
 
 // Config struct fills the parameters of request or user input

csi/src/nodeserver.go

@@ -14,6 +14,7 @@ import (
     "strconv"
     "strings"
     "syscall"
+    "time"
 
     "google.golang.org/grpc/codes"
     "google.golang.org/grpc/status"
@@ -32,6 +33,7 @@ type NodeServer struct
     useVduse bool
     stateDir string
     mounter mount.Interface
+    restartInterval time.Duration
 }
 
 type DeviceState struct
@@ -65,6 +67,16 @@ func NewNodeServer(driver *Driver) *NodeServer
     if (ns.useVduse)
     {
         ns.restoreVduseDaemons()
+        dur, err := time.ParseDuration(os.Getenv("RESTART_INTERVAL"))
+        if (err != nil)
+        {
+            dur = 10 * time.Second
+        }
+        ns.restartInterval = dur
+        if (ns.restartInterval != time.Duration(0))
+        {
+            go ns.restarter()
+        }
     }
     return ns
 }
@@ -176,7 +188,6 @@ func (ns *NodeServer) unmapNbd(devicePath string)
 
 func findByPidFile(pidFile string) (*os.Process, error)
 {
-    klog.Infof("killing process with PID from file %s", pidFile)
     pidBuf, err := os.ReadFile(pidFile)
     if (err != nil)
     {
@@ -197,6 +208,7 @@ func findByPidFile(pidFile string) (*os.Process, error)
 
 func killByPidFile(pidFile string) error
 {
+    klog.Infof("killing process with PID from file %s", pidFile)
     proc, err := findByPidFile(pidFile)
     if (err != nil)
     {
@@ -364,6 +376,21 @@ func (ns *NodeServer) unmapVduseById(vdpaId string)
     }
 }
 
+func (ns *NodeServer) restarter()
+{
+    // Restart dead VDUSE daemons at regular intervals
+    // Otherwise volume I/O may hang in case of a qemu-storage-daemon crash
+    // Moreover, it may lead to a kernel panic of the kernel is configured to
+    // panic on hung tasks
+    ticker := time.NewTicker(ns.restartInterval)
+    defer ticker.Stop()
+    for
+    {
+        <-ticker.C
+        ns.restoreVduseDaemons()
+    }
+}
+
 func (ns *NodeServer) restoreVduseDaemons()
 {
     pattern := ns.stateDir+"vitastor-vduse-*.json"

debian/build-vitastor-bookworm.sh

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

debian/build-vitastor-bullseye.sh

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

debian/build-vitastor-buster.sh

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

debian/build-vitastor-ubuntu-jammy.sh

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

debian/changelog

@@ -1,4 +1,4 @@
-vitastor (1.3.1-1) unstable; urgency=medium
+vitastor (1.4.8-1) unstable; urgency=medium
 
   * Bugfixes
 

debian/libvirt.Dockerfile

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

debian/vitastor.Dockerfile

@@ -1,8 +1,10 @@
 # Build Vitastor packages for Debian inside a container
-# cd ..; podman build --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/vitastor.Dockerfile .
+# cd ..; podman build --build-arg DISTRO=debian --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/vitastor.Dockerfile .
 
+ARG DISTRO=debian
 ARG REL=
-FROM debian:$REL
+FROM $DISTRO:$REL
+ARG DISTRO=debian
 ARG REL=
 
 WORKDIR /root
@@ -35,8 +37,8 @@ RUN set -e -x; \
     mkdir -p /root/packages/vitastor-$REL; \
     rm -rf /root/packages/vitastor-$REL/*; \
     cd /root/packages/vitastor-$REL; \
-    cp -r /root/vitastor vitastor-1.3.1; \
-    cd vitastor-1.3.1; \
+    cp -r /root/vitastor vitastor-1.4.8; \
+    cd vitastor-1.4.8; \
     ln -s /root/fio-build/fio-*/ ./fio; \
     FIO=$(head -n1 fio/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
     ls /usr/include/linux/raw.h || cp ./debian/raw.h /usr/include/linux/raw.h; \
@@ -49,8 +51,8 @@ RUN set -e -x; \
     rm -rf a b; \
     echo "dep:fio=$FIO" > debian/fio_version; \
     cd /root/packages/vitastor-$REL; \
-    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_1.3.1.orig.tar.xz vitastor-1.3.1; \
-    cd vitastor-1.3.1; \
+    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_1.4.8.orig.tar.xz vitastor-1.4.8; \
+    cd vitastor-1.4.8; \
     V=$(head -n1 debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
     DEBFULLNAME="Vitaliy Filippov <vitalif@yourcmc.ru>" dch -D $REL -v "$V""$REL" "Rebuild for $REL"; \
     DEB_BUILD_OPTIONS=nocheck dpkg-buildpackage --jobs=auto -sa; \

docs/config/client.en.md

@@ -6,9 +6,11 @@
 
 # Client Parameters
 
-These parameters apply only to clients and affect their interaction with
-the cluster.
+These parameters apply only to Vitastor clients (QEMU, fio, NBD and so on) and
+affect their interaction with the cluster.
 
+- [client_retry_interval](#client_retry_interval)
+- [client_eio_retry_interval](#client_eio_retry_interval)
 - [client_max_dirty_bytes](#client_max_dirty_bytes)
 - [client_max_dirty_ops](#client_max_dirty_ops)
 - [client_enable_writeback](#client_enable_writeback)
@@ -19,6 +21,26 @@ the cluster.
 - [nbd_max_devices](#nbd_max_devices)
 - [nbd_max_part](#nbd_max_part)
 
+## client_retry_interval
+
+- Type: milliseconds
+- Default: 50
+- Minimum: 10
+- Can be changed online: yes
+
+Retry time for I/O requests failed due to inactive PGs or network
+connectivity errors.
+
+## client_eio_retry_interval
+
+- Type: milliseconds
+- Default: 1000
+- Can be changed online: yes
+
+Retry time for I/O requests failed due to data corruption or unfinished
+EC object deletions (has_incomplete PG state). 0 disables such retries
+and clients are not blocked and just get EIO error code instead.
+
 ## client_max_dirty_bytes
 
 - Type: integer

docs/config/client.ru.md

@@ -6,9 +6,11 @@
 
 # Параметры клиентского кода
 
-Данные параметры применяются только к клиентам Vitastor (QEMU, fio, NBD) и
+Данные параметры применяются только к клиентам Vitastor (QEMU, fio, NBD и т.п.) и
 затрагивают логику их работы с кластером.
 
+- [client_retry_interval](#client_retry_interval)
+- [client_eio_retry_interval](#client_eio_retry_interval)
 - [client_max_dirty_bytes](#client_max_dirty_bytes)
 - [client_max_dirty_ops](#client_max_dirty_ops)
 - [client_enable_writeback](#client_enable_writeback)
@@ -19,6 +21,27 @@
 - [nbd_max_devices](#nbd_max_devices)
 - [nbd_max_part](#nbd_max_part)
 
+## client_retry_interval
+
+- Тип: миллисекунды
+- Значение по умолчанию: 50
+- Минимальное значение: 10
+- Можно менять на лету: да
+
+Время повтора запросов ввода-вывода, неудачных из-за неактивных PG или
+ошибок сети.
+
+## client_eio_retry_interval
+
+- Тип: миллисекунды
+- Значение по умолчанию: 1000
+- Можно менять на лету: да
+
+Время повтора запросов ввода-вывода, неудачных из-за повреждения данных
+или незавершённых удалений EC-объектов (состояния PG has_incomplete).
+0 отключает повторы таких запросов и клиенты не блокируются, а вместо
+этого просто получают код ошибки EIO.
+
 ## client_max_dirty_bytes
 
 - Тип: целое число

docs/config/monitor.en.md

@@ -19,8 +19,8 @@ These parameters only apply to Monitors.
 ## etcd_mon_ttl
 
 - Type: seconds
-- Default: 30
-- Minimum: 10
+- Default: 1
+- Minimum: 5
 
 Monitor etcd lease refresh interval in seconds
 

docs/config/monitor.ru.md

@@ -19,8 +19,8 @@
 ## etcd_mon_ttl
 
 - Тип: секунды
-- Значение по умолчанию: 30
-- Минимальное значение: 10
+- Значение по умолчанию: 1
+- Минимальное значение: 5
 
 Интервал обновления etcd резервации (lease) монитором
 

docs/config/network.en.md

@@ -25,7 +25,6 @@ between clients, OSDs and etcd.
 - [peer_connect_timeout](#peer_connect_timeout)
 - [osd_idle_timeout](#osd_idle_timeout)
 - [osd_ping_timeout](#osd_ping_timeout)
-- [up_wait_retry_interval](#up_wait_retry_interval)
 - [max_etcd_attempts](#max_etcd_attempts)
 - [etcd_quick_timeout](#etcd_quick_timeout)
 - [etcd_slow_timeout](#etcd_slow_timeout)
@@ -212,17 +211,6 @@ Maximum time to wait for OSD keepalive responses. If an OSD doesn't respond
 within this time, the connection to it is dropped and a reconnection attempt
 is scheduled.
 
-## up_wait_retry_interval
-
-- Type: milliseconds
-- Default: 500
-- Minimum: 50
-- Can be changed online: yes
-
-OSDs respond to clients with a special error code when they receive I/O
-requests for a PG that's not synchronized and started. This parameter sets
-the time for the clients to wait before re-attempting such I/O requests.
-
 ## max_etcd_attempts
 
 - Type: integer

docs/config/network.ru.md

@@ -25,7 +25,6 @@
 - [peer_connect_timeout](#peer_connect_timeout)
 - [osd_idle_timeout](#osd_idle_timeout)
 - [osd_ping_timeout](#osd_ping_timeout)
-- [up_wait_retry_interval](#up_wait_retry_interval)
 - [max_etcd_attempts](#max_etcd_attempts)
 - [etcd_quick_timeout](#etcd_quick_timeout)
 - [etcd_slow_timeout](#etcd_slow_timeout)
@@ -221,19 +220,6 @@ OSD в любом случае согласовывают реальное зн
 Если OSD не отвечает за это время, соединение отключается и производится
 повторная попытка соединения.
 
-## up_wait_retry_interval
-
-- Тип: миллисекунды
-- Значение по умолчанию: 500
-- Минимальное значение: 50
-- Можно менять на лету: да
-
-Когда OSD получают от клиентов запросы ввода-вывода, относящиеся к не
-поднятым на данный момент на них PG, либо к PG в процессе синхронизации,
-они отвечают клиентам специальным кодом ошибки, означающим, что клиент
-должен некоторое время подождать перед повторением запроса. Именно это время
-ожидания задаёт данный параметр.
-
 ## max_etcd_attempts
 
 - Тип: целое число

docs/config/osd.en.md

@@ -19,6 +19,7 @@ them, even without restarting by updating configuration in etcd.
 - [autosync_interval](#autosync_interval)
 - [autosync_writes](#autosync_writes)
 - [recovery_queue_depth](#recovery_queue_depth)
+- [recovery_sleep_us](#recovery_sleep_us)
 - [recovery_pg_switch](#recovery_pg_switch)
 - [recovery_sync_batch](#recovery_sync_batch)
 - [readonly](#readonly)
@@ -51,6 +52,14 @@ them, even without restarting by updating configuration in etcd.
 - [scrub_list_limit](#scrub_list_limit)
 - [scrub_find_best](#scrub_find_best)
 - [scrub_ec_max_bruteforce](#scrub_ec_max_bruteforce)
+- [recovery_tune_interval](#recovery_tune_interval)
+- [recovery_tune_util_low](#recovery_tune_util_low)
+- [recovery_tune_util_high](#recovery_tune_util_high)
+- [recovery_tune_client_util_low](#recovery_tune_client_util_low)
+- [recovery_tune_client_util_high](#recovery_tune_client_util_high)
+- [recovery_tune_agg_interval](#recovery_tune_agg_interval)
+- [recovery_tune_sleep_min_us](#recovery_tune_sleep_min_us)
+- [recovery_tune_sleep_cutoff_us](#recovery_tune_sleep_cutoff_us)
 
 ## etcd_report_interval
 
@@ -135,12 +144,24 @@ operations before issuing an fsync operation internally.
 ## recovery_queue_depth
 
 - Type: integer
-- Default: 4
+- Default: 1
 - Can be changed online: yes
 
-Maximum recovery operations per one primary OSD at any given moment of time.
-Currently it's the only parameter available to tune the speed or recovery
-and rebalancing, but it's planned to implement more.
+Maximum recovery and rebalance operations initiated by each OSD in parallel.
+Note that each OSD talks to a lot of other OSDs so actual number of parallel
+recovery operations per each OSD is greater than just recovery_queue_depth.
+Increasing this parameter can speedup recovery if [auto-tuning](#recovery_tune_interval)
+allows it or if it is disabled.
+
+## recovery_sleep_us
+
+- Type: microseconds
+- Default: 0
+- Can be changed online: yes
+
+Delay for all recovery- and rebalance- related operations. If non-zero,
+such operations are artificially slowed down to reduce the impact on
+client I/O.
 
 ## recovery_pg_switch
 
@@ -508,3 +529,90 @@ the variant with most available equal copies is correct. For example, if
 you have 3 replicas and 1 of them differs, this one is considered to be
 corrupted. But if there is no "best" version with more copies than all
 others have then the object is also marked as inconsistent.
+
+## recovery_tune_interval
+
+- Type: seconds
+- Default: 1
+- Can be changed online: yes
+
+Interval at which OSD re-considers client and recovery load and automatically
+adjusts [recovery_sleep_us](#recovery_sleep_us). Recovery auto-tuning is
+disabled if recovery_tune_interval is set to 0.
+
+Auto-tuning targets utilization. Utilization is a measure of load and is
+equal to the product of iops and average latency (so it may be greater
+than 1). You set "low" and "high" client utilization thresholds and two
+corresponding target recovery utilization levels. OSD calculates desired
+recovery utilization from client utilization using linear interpolation
+and auto-tunes recovery operation delay to make actual recovery utilization
+match desired.
+
+This allows to reduce recovery/rebalance impact on client operations. It is
+of course impossible to remove it completely, but it should become adequate.
+In some tests rebalance could earlier drop client write speed from 1.5 GB/s
+to 50-100 MB/s, with default auto-tuning settings it now only reduces
+to ~1 GB/s.
+
+## recovery_tune_util_low
+
+- Type: number
+- Default: 0.1
+- Can be changed online: yes
+
+Desired recovery/rebalance utilization when client load is high, i.e. when
+it is at or above recovery_tune_client_util_high.
+
+## recovery_tune_util_high
+
+- Type: number
+- Default: 1
+- Can be changed online: yes
+
+Desired recovery/rebalance utilization when client load is low, i.e. when
+it is at or below recovery_tune_client_util_low.
+
+## recovery_tune_client_util_low
+
+- Type: number
+- Default: 0
+- Can be changed online: yes
+
+Client utilization considered "low".
+
+## recovery_tune_client_util_high
+
+- Type: number
+- Default: 0.5
+- Can be changed online: yes
+
+Client utilization considered "high".
+
+## recovery_tune_agg_interval
+
+- Type: integer
+- Default: 10
+- Can be changed online: yes
+
+The number of last auto-tuning iterations to use for calculating the
+delay as average. Lower values result in quicker response to client
+load change, higher values result in more stable delay. Default value of 10
+is usually fine.
+
+## recovery_tune_sleep_min_us
+
+- Type: microseconds
+- Default: 10
+- Can be changed online: yes
+
+Minimum possible value for auto-tuned recovery_sleep_us. Lower values
+are changed to 0.
+
+## recovery_tune_sleep_cutoff_us
+
+- Type: microseconds
+- Default: 10000000
+- Can be changed online: yes
+
+Maximum possible value for auto-tuned recovery_sleep_us. Higher values
+are treated as outliers and ignored in aggregation.

docs/config/osd.ru.md

@@ -20,6 +20,7 @@
 - [autosync_interval](#autosync_interval)
 - [autosync_writes](#autosync_writes)
 - [recovery_queue_depth](#recovery_queue_depth)
+- [recovery_sleep_us](#recovery_sleep_us)
 - [recovery_pg_switch](#recovery_pg_switch)
 - [recovery_sync_batch](#recovery_sync_batch)
 - [readonly](#readonly)
@@ -52,6 +53,14 @@
 - [scrub_list_limit](#scrub_list_limit)
 - [scrub_find_best](#scrub_find_best)
 - [scrub_ec_max_bruteforce](#scrub_ec_max_bruteforce)
+- [recovery_tune_interval](#recovery_tune_interval)
+- [recovery_tune_util_low](#recovery_tune_util_low)
+- [recovery_tune_util_high](#recovery_tune_util_high)
+- [recovery_tune_client_util_low](#recovery_tune_client_util_low)
+- [recovery_tune_client_util_high](#recovery_tune_client_util_high)
+- [recovery_tune_agg_interval](#recovery_tune_agg_interval)
+- [recovery_tune_sleep_min_us](#recovery_tune_sleep_min_us)
+- [recovery_tune_sleep_cutoff_us](#recovery_tune_sleep_cutoff_us)
 
 ## etcd_report_interval
 
@@ -138,13 +147,25 @@ OSD, чтобы успевать очищать журнал - без них OSD
 ## recovery_queue_depth
 
 - Тип: целое число
-- Значение по умолчанию: 4
+- Значение по умолчанию: 1
 - Можно менять на лету: да
 
-Максимальное число операций восстановления на одном первичном OSD в любой
-момент времени. На данный момент единственный параметр, который можно менять
-для ускорения или замедления восстановления и перебалансировки данных, но
-в планах реализация других параметров.
+Максимальное число параллельных операций восстановления, инициируемых одним
+OSD в любой момент времени. Имейте в виду, что каждый OSD обычно работает с
+многими другими OSD, так что на практике параллелизм восстановления больше,
+чем просто recovery_queue_depth. Увеличение значения этого параметра может
+ускорить восстановление если [автотюнинг скорости](#recovery_tune_interval)
+разрешает это или если он отключён.
+
+## recovery_sleep_us
+
+- Тип: микросекунды
+- Значение по умолчанию: 0
+- Можно менять на лету: да
+
+Delay for all recovery- and rebalance- related operations. If non-zero,
+such operations are artificially slowed down to reduce the impact on
+client I/O.
 
 ## recovery_pg_switch
 
@@ -535,3 +556,93 @@ EC (кодов коррекции ошибок) с более, чем 1 диск
 считается некорректной. Однако, если "лучшую" версию с числом доступных
 копий большим, чем у всех других версий, найти невозможно, то объект тоже
 маркируется неконсистентным.
+
+## recovery_tune_interval
+
+- Тип: секунды
+- Значение по умолчанию: 1
+- Можно менять на лету: да
+
+Интервал, с которым OSD пересматривает клиентскую нагрузку и нагрузку
+восстановления и автоматически подстраивает [recovery_sleep_us](#recovery_sleep_us).
+Автотюнинг (автоподстройка) отключается, если recovery_tune_interval
+устанавливается в значение 0.
+
+Автотюнинг регулирует утилизацию. Утилизация является мерой нагрузки
+и равна произведению числа операций в секунду и средней задержки
+(то есть, она может быть выше 1). Вы задаёте два уровня клиентской
+утилизации - "низкий" и "высокий" (low и high) и два соответствующих
+целевых уровня утилизации операциями восстановления. OSD рассчитывает
+желаемый уровень утилизации восстановления линейной интерполяцией от
+клиентской утилизации и подстраивает задержку операций восстановления
+так, чтобы фактическая утилизация восстановления совпадала с желаемой.
+
+Это позволяет снизить влияние восстановления и ребаланса на клиентские
+операции. Конечно, невозможно исключить такое влияние полностью, но оно
+должно становиться адекватнее. В некоторых тестах перебалансировка могла
+снижать клиентскую скорость записи с 1.5 ГБ/с до 50-100 МБ/с, а теперь, с
+настройками автотюнинга по умолчанию, она снижается только до ~1 ГБ/с.
+
+## recovery_tune_util_low
+
+- Тип: число
+- Значение по умолчанию: 0.1
+- Можно менять на лету: да
+
+Желаемая утилизация восстановления в моменты, когда клиентская нагрузка
+высокая, то есть, находится на уровне или выше recovery_tune_client_util_high.
+
+## recovery_tune_util_high
+
+- Тип: число
+- Значение по умолчанию: 1
+- Можно менять на лету: да
+
+Желаемая утилизация восстановления в моменты, когда клиентская нагрузка
+низкая, то есть, находится на уровне или ниже recovery_tune_client_util_low.
+
+## recovery_tune_client_util_low
+
+- Тип: число
+- Значение по умолчанию: 0
+- Можно менять на лету: да
+
+Клиентская утилизация, которая считается "низкой".
+
+## recovery_tune_client_util_high
+
+- Тип: число
+- Значение по умолчанию: 0.5
+- Можно менять на лету: да
+
+Клиентская утилизация, которая считается "высокой".
+
+## recovery_tune_agg_interval
+
+- Тип: целое число
+- Значение по умолчанию: 10
+- Можно менять на лету: да
+
+Число последних итераций автоподстройки для расчёта задержки как среднего
+значения. Меньшие значения параметра ускоряют отклик на изменение нагрузки,
+большие значения делают задержку стабильнее. Значение по умолчанию 10
+обычно нормальное и не требует изменений.
+
+## recovery_tune_sleep_min_us
+
+- Тип: микросекунды
+- Значение по умолчанию: 10
+- Можно менять на лету: да
+
+Минимальное возможное значение авто-подстроенного recovery_sleep_us.
+Меньшие значения заменяются на 0.
+
+## recovery_tune_sleep_cutoff_us
+
+- Тип: микросекунды
+- Значение по умолчанию: 10000000
+- Можно менять на лету: да
+
+Максимальное возможное значение авто-подстроенного recovery_sleep_us.
+Большие значения считаются случайными выбросами и игнорируются в
+усреднении.

docs/config/pool.en.md

@@ -154,6 +154,9 @@ That is, if it becomes impossible to place PG data on at least (pg_minsize)
 OSDs, PG is deactivated for both read and write. So you know that a fresh
 write always goes to at least (pg_minsize) OSDs (disks).
 
+That is, pg_size minus pg_minsize sets the number of disk failures to tolerate
+without temporary downtime (for [osd_out_time](monitor.en.md#osd_out_time)).
+
 FIXME: pg_minsize behaviour may be changed in the future to only make PGs
 read-only instead of deactivating them.
 

docs/config/pool.ru.md

@@ -157,6 +157,10 @@
 OSD, PG деактивируется на чтение и запись. Иными словами, всегда известно,
 что новые блоки данных всегда записываются как минимум на pg_minsize дисков.
 
+По сути, разница pg_size и pg_minsize задаёт число отказов дисков, которые пул
+может пережить без временной (на [osd_out_time](monitor.ru.md#osd_out_time))
+остановки обслуживания.
+
 FIXME: Поведение pg_minsize может быть изменено в будущем с полной деактивации
 PG на перевод их в режим только для чтения.
 

docs/config/src/client.yml

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

docs/config/src/make.js

@@ -38,6 +38,7 @@ const types = {
         bool: 'boolean',
         int: 'integer',
         sec: 'seconds',
+        float: 'number',
         ms: 'milliseconds',
         us: 'microseconds',
     },
@@ -46,6 +47,7 @@ const types = {
         bool: 'булево (да/нет)',
         int: 'целое число',
         sec: 'секунды',
+        float: 'число',
         ms: 'миллисекунды',
         us: 'микросекунды',
     },

docs/config/src/monitor.yml

@@ -1,7 +1,7 @@
 - name: etcd_mon_ttl
   type: sec
-  min: 10
-  default: 30
+  min: 5
+  default: 1
   info: Monitor etcd lease refresh interval in seconds
   info_ru: Интервал обновления etcd резервации (lease) монитором
 - name: etcd_mon_timeout

docs/config/src/network.yml

@@ -243,21 +243,6 @@
     Максимальное время ожидания ответа на запрос проверки состояния соединения.
     Если OSD не отвечает за это время, соединение отключается и производится
     повторная попытка соединения.
-- name: up_wait_retry_interval
-  type: ms
-  min: 50
-  default: 500
-  online: true
-  info: |
-    OSDs respond to clients with a special error code when they receive I/O
-    requests for a PG that's not synchronized and started. This parameter sets
-    the time for the clients to wait before re-attempting such I/O requests.
-  info_ru: |
-    Когда OSD получают от клиентов запросы ввода-вывода, относящиеся к не
-    поднятым на данный момент на них PG, либо к PG в процессе синхронизации,
-    они отвечают клиентам специальным кодом ошибки, означающим, что клиент
-    должен некоторое время подождать перед повторением запроса. Именно это время
-    ожидания задаёт данный параметр.
 - name: max_etcd_attempts
   type: int
   default: 5

docs/config/src/osd.yml

@@ -107,17 +107,29 @@
     принудительной отправкой fsync-а.
 - name: recovery_queue_depth
   type: int
-  default: 4
+  default: 1
   online: true
   info: |
-    Maximum recovery operations per one primary OSD at any given moment of time.
-    Currently it's the only parameter available to tune the speed or recovery
-    and rebalancing, but it's planned to implement more.
+    Maximum recovery and rebalance operations initiated by each OSD in parallel.
+    Note that each OSD talks to a lot of other OSDs so actual number of parallel
+    recovery operations per each OSD is greater than just recovery_queue_depth.
+    Increasing this parameter can speedup recovery if [auto-tuning](#recovery_tune_interval)
+    allows it or if it is disabled.
   info_ru: |
-    Максимальное число операций восстановления на одном первичном OSD в любой
-    момент времени. На данный момент единственный параметр, который можно менять
-    для ускорения или замедления восстановления и перебалансировки данных, но
-    в планах реализация других параметров.
+    Максимальное число параллельных операций восстановления, инициируемых одним
+    OSD в любой момент времени. Имейте в виду, что каждый OSD обычно работает с
+    многими другими OSD, так что на практике параллелизм восстановления больше,
+    чем просто recovery_queue_depth. Увеличение значения этого параметра может
+    ускорить восстановление если [автотюнинг скорости](#recovery_tune_interval)
+    разрешает это или если он отключён.
+- name: recovery_sleep_us
+  type: us
+  default: 0
+  online: true
+  info: |
+    Delay for all recovery- and rebalance- related operations. If non-zero,
+    such operations are artificially slowed down to reduce the impact on
+    client I/O.
 - name: recovery_pg_switch
   type: int
   default: 128
@@ -626,3 +638,112 @@
     считается некорректной. Однако, если "лучшую" версию с числом доступных
     копий большим, чем у всех других версий, найти невозможно, то объект тоже
     маркируется неконсистентным.
+- name: recovery_tune_interval
+  type: sec
+  default: 1
+  online: true
+  info: |
+    Interval at which OSD re-considers client and recovery load and automatically
+    adjusts [recovery_sleep_us](#recovery_sleep_us). Recovery auto-tuning is
+    disabled if recovery_tune_interval is set to 0.
+
+    Auto-tuning targets utilization. Utilization is a measure of load and is
+    equal to the product of iops and average latency (so it may be greater
+    than 1). You set "low" and "high" client utilization thresholds and two
+    corresponding target recovery utilization levels. OSD calculates desired
+    recovery utilization from client utilization using linear interpolation
+    and auto-tunes recovery operation delay to make actual recovery utilization
+    match desired.
+
+    This allows to reduce recovery/rebalance impact on client operations. It is
+    of course impossible to remove it completely, but it should become adequate.
+    In some tests rebalance could earlier drop client write speed from 1.5 GB/s
+    to 50-100 MB/s, with default auto-tuning settings it now only reduces
+    to ~1 GB/s.
+  info_ru: |
+    Интервал, с которым OSD пересматривает клиентскую нагрузку и нагрузку
+    восстановления и автоматически подстраивает [recovery_sleep_us](#recovery_sleep_us).
+    Автотюнинг (автоподстройка) отключается, если recovery_tune_interval
+    устанавливается в значение 0.
+
+    Автотюнинг регулирует утилизацию. Утилизация является мерой нагрузки
+    и равна произведению числа операций в секунду и средней задержки
+    (то есть, она может быть выше 1). Вы задаёте два уровня клиентской
+    утилизации - "низкий" и "высокий" (low и high) и два соответствующих
+    целевых уровня утилизации операциями восстановления. OSD рассчитывает
+    желаемый уровень утилизации восстановления линейной интерполяцией от
+    клиентской утилизации и подстраивает задержку операций восстановления
+    так, чтобы фактическая утилизация восстановления совпадала с желаемой.
+
+    Это позволяет снизить влияние восстановления и ребаланса на клиентские
+    операции. Конечно, невозможно исключить такое влияние полностью, но оно
+    должно становиться адекватнее. В некоторых тестах перебалансировка могла
+    снижать клиентскую скорость записи с 1.5 ГБ/с до 50-100 МБ/с, а теперь, с
+    настройками автотюнинга по умолчанию, она снижается только до ~1 ГБ/с.
+- name: recovery_tune_util_low
+  type: float
+  default: 0.1
+  online: true
+  info: |
+    Desired recovery/rebalance utilization when client load is high, i.e. when
+    it is at or above recovery_tune_client_util_high.
+  info_ru: |
+    Желаемая утилизация восстановления в моменты, когда клиентская нагрузка
+    высокая, то есть, находится на уровне или выше recovery_tune_client_util_high.
+- name: recovery_tune_util_high
+  type: float
+  default: 1
+  online: true
+  info: |
+    Desired recovery/rebalance utilization when client load is low, i.e. when
+    it is at or below recovery_tune_client_util_low.
+  info_ru: |
+    Желаемая утилизация восстановления в моменты, когда клиентская нагрузка
+    низкая, то есть, находится на уровне или ниже recovery_tune_client_util_low.
+- name: recovery_tune_client_util_low
+  type: float
+  default: 0
+  online: true
+  info: Client utilization considered "low".
+  info_ru: Клиентская утилизация, которая считается "низкой".
+- name: recovery_tune_client_util_high
+  type: float
+  default: 0.5
+  online: true
+  info: Client utilization considered "high".
+  info_ru: Клиентская утилизация, которая считается "высокой".
+- name: recovery_tune_agg_interval
+  type: int
+  default: 10
+  online: true
+  info: |
+    The number of last auto-tuning iterations to use for calculating the
+    delay as average. Lower values result in quicker response to client
+    load change, higher values result in more stable delay. Default value of 10
+    is usually fine.
+  info_ru: |
+    Число последних итераций автоподстройки для расчёта задержки как среднего
+    значения. Меньшие значения параметра ускоряют отклик на изменение нагрузки,
+    большие значения делают задержку стабильнее. Значение по умолчанию 10
+    обычно нормальное и не требует изменений.
+- name: recovery_tune_sleep_min_us
+  type: us
+  default: 10
+  online: true
+  info: |
+    Minimum possible value for auto-tuned recovery_sleep_us. Lower values
+    are changed to 0.
+  info_ru: |
+    Минимальное возможное значение авто-подстроенного recovery_sleep_us.
+    Меньшие значения заменяются на 0.
+- name: recovery_tune_sleep_cutoff_us
+  type: us
+  default: 10000000
+  online: true
+  info: |
+    Maximum possible value for auto-tuned recovery_sleep_us. Higher values
+    are treated as outliers and ignored in aggregation.
+  info_ru: |
+    Максимальное возможное значение авто-подстроенного recovery_sleep_us.
+    Большие значения считаются случайными выбросами и игнорируются в
+    усреднении.

docs/installation/kubernetes.en.md

@@ -37,6 +37,7 @@ Vitastor CSI supports:
 - Volume snapshots. Example: [snapshot class](../../csi/deploy/example-snapshot-class.yaml), [snapshot](../../csi/deploy/example-snapshot.yaml), [clone](../../csi/deploy/example-snapshot-clone.yaml)
 - [VDUSE](../usage/qemu.en.md#vduse) (preferred) and [NBD](../usage/nbd.en.md) device mapping methods
 - Upgrades with VDUSE - new handler processes are restarted when CSI pods are restarted themselves
+- VDUSE daemon auto-restart - handler processes are automatically restarted if they crash due to a bug in Vitastor client code
 - Multiple clusters by using multiple configuration files in ConfigMap.
 
 Remember that to use snapshots with CSI you also have to install [Snapshot Controller and CRDs](https://kubernetes-csi.github.io/docs/snapshot-controller.html#deployment).

docs/installation/kubernetes.ru.md

@@ -37,6 +37,7 @@ CSI-плагин Vitastor поддерживает:
 - Снимки томов. Пример: [класс снимков](../../csi/deploy/example-snapshot-class.yaml), [снимок](../../csi/deploy/example-snapshot.yaml), [клон снимка](../../csi/deploy/example-snapshot-clone.yaml)
 - Способы подключения устройств [VDUSE](../usage/qemu.ru.md#vduse) (предпочитаемый) и [NBD](../usage/nbd.ru.md)
 - Обновление при использовании VDUSE - новые процессы-обработчики устройств успешно перезапускаются вместе с самими подами CSI
+- Автоперезауск демонов VDUSE - процесс-обработчик автоматически перезапустится, если он внезапно упадёт из-за бага в коде клиента Vitastor
 - Несколько кластеров через задание нескольких файлов конфигурации в ConfigMap.
 
 Не забывайте, что для использования снимков нужно сначала установить [контроллер снимков и CRD](https://kubernetes-csi.github.io/docs/snapshot-controller.html#deployment).

docs/installation/proxmox.en.md

@@ -25,7 +25,7 @@ vitastor: vitastor
     vitastor_pool testpool
     # path to the configuration file
     vitastor_config_path /etc/vitastor/vitastor.conf
-    # etcd address(es), required only if missing in the configuration file
+    # etcd address(es), OPTIONAL, required only if missing in the configuration file
     vitastor_etcd_address 192.168.7.2:2379/v3
     # prefix for keys in etcd
     vitastor_etcd_prefix /vitastor

docs/installation/proxmox.ru.md

@@ -24,7 +24,7 @@ vitastor: vitastor
     vitastor_pool testpool
     # Путь к файлу конфигурации
     vitastor_config_path /etc/vitastor/vitastor.conf
-    # Адрес(а) etcd, нужны, только если не указаны в vitastor.conf
+    # Адрес(а) etcd, ОПЦИОНАЛЬНЫ, нужны, только если не указаны в vitastor.conf
     vitastor_etcd_address 192.168.7.2:2379/v3
     # Префикс ключей метаданных в etcd
     vitastor_etcd_prefix /vitastor

docs/intro/features.en.md

@@ -32,6 +32,7 @@
 - [Scrubbing](../config/osd.en.md#auto_scrub) (verification of copies)
 - [Checksums](../config/layout-osd.en.md#data_csum_type)
 - [Client write-back cache](../config/client.en.md#client_enable_writeback)
+- [Intelligent recovery auto-tuning](../config/osd.en.md#recovery_tune_interval)
 
 ## Plugins and tools
 

docs/intro/features.ru.md

@@ -34,6 +34,7 @@
 - [Фоновая проверка целостности](../config/osd.ru.md#auto_scrub) (сверка копий)
 - [Контрольные суммы](../config/layout-osd.ru.md#data_csum_type)
 - [Буферизация записи на стороне клиента](../config/client.ru.md#client_enable_writeback)
+- [Интеллектуальная автоподстройка скорости восстановления](../config/osd.ru.md#recovery_tune_interval)
 
 ## Драйверы и инструменты
 

docs/performance/theoretical.en.md

@@ -11,19 +11,26 @@ Replicated setups:
 - Single-threaded write+fsync latency:
   - With immediate commit: 2 network roundtrips + 1 disk write.
   - With lazy commit: 4 network roundtrips + 1 disk write + 1 disk flush.
-- Saturated parallel read iops: min(network bandwidth, sum(disk read iops)).
-- Saturated parallel write iops: min(network bandwidth, sum(disk write iops / number of replicas / write amplification)).
+- Linear read: `min(total network bandwidth, sum(disk read MB/s))`.
+- Linear write: `min(total network bandwidth, sum(disk write MB/s / number of replicas))`.
+- Saturated parallel read iops: `min(total network bandwidth, sum(disk read iops))`.
+- Saturated parallel write iops: `min(total network bandwidth / number of replicas, sum(disk write iops / number of replicas / (write amplification = 4)))`.
 
-EC/XOR setups:
+EC/XOR setups (EC N+K):
 - Single-threaded (T1Q1) read latency: 1.5 network roundtrips + 1 disk read.
 - Single-threaded write+fsync latency:
   - With immediate commit: 3.5 network roundtrips + 1 disk read + 2 disk writes.
   - With lazy commit: 5.5 network roundtrips + 1 disk read + 2 disk writes + 2 disk fsyncs.
-  - 0.5 in actually (k-1)/k which means that an additional roundtrip doesn't happen when
+  - 0.5 in actually `(N-1)/N` which means that an additional roundtrip doesn't happen when
     the read sub-operation can be served locally.
-- Saturated parallel read iops: min(network bandwidth, sum(disk read iops)).
-- Saturated parallel write iops: min(network bandwidth, sum(disk write iops * number of data drives / (number of data + parity drives) / write amplification)).
-  In fact, you should put disk write iops under the condition of ~10% reads / ~90% writes in this formula.
+- Linear read: `min(total network bandwidth, sum(disk read MB/s))`.
+- Linear write: `min(total network bandwidth, sum(disk write MB/s * N/(N+K)))`.
+- Saturated parallel read iops: `min(total network bandwidth, sum(disk read iops))`.
+- Saturated parallel write iops: roughly `total iops / (N+K) / WA`. More exactly,
+  `min(total network bandwidth * N/(N+K), sum(disk randrw iops / (N*4 + K*5 + 1)))` with
+  random read/write mix corresponding to `(N-1)/(N*4 + K*5 + 1)*100 % reads`.
+  - For example, with EC 2+1 it is: `(7% randrw iops) / 14`.
+  - With EC 6+3 it is: `(12.5% randrw iops) / 40`.
 
 Write amplification for 4 KB blocks is usually 3-5 in Vitastor:
 1. Journal block write

docs/performance/theoretical.ru.md

@@ -11,20 +11,27 @@
 - Запись+fsync в 1 поток:
   - С мгновенным сбросом: 2 RTT + 1 запись.
   - С отложенным ("ленивым") сбросом: 4 RTT + 1 запись + 1 fsync.
-- Параллельное чтение: сумма IOPS всех дисков либо производительность сети, если в сеть упрётся раньше.
-- Параллельная запись: сумма IOPS всех дисков / число реплик / WA либо производительность сети, если в сеть упрётся раньше.
+- Линейное чтение: сумма МБ/с чтения всех дисков, либо общая производительность сети (сумма пропускной способности сети всех нод), если в сеть упрётся раньше.
+- Линейная запись: сумма МБ/с записи всех дисков / число реплик, либо производительность сети / число реплик, если в сеть упрётся раньше.
+- Параллельное случайное мелкое чтение: сумма IOPS чтения всех дисков, либо производительность сети, если в сеть упрётся раньше.
+- Параллельная случайная мелкая запись: сумма IOPS записи всех дисков / число реплик / WA, либо производительность сети / число реплик, если в сеть упрётся раньше.
 
-При использовании кодов коррекции ошибок (EC):
+При использовании кодов коррекции ошибок (EC N+K):
 - Задержка чтения в 1 поток (T1Q1): 1.5 RTT + 1 чтение.
 - Запись+fsync в 1 поток:
   - С мгновенным сбросом: 3.5 RTT + 1 чтение + 2 записи.
   - С отложенным ("ленивым") сбросом: 5.5 RTT + 1 чтение + 2 записи + 2 fsync.
-- Под 0.5 на самом деле подразумевается (k-1)/k, где k - число дисков данных,
+- Под 0.5 на самом деле подразумевается (N-1)/N, где N - число дисков данных,
   что означает, что дополнительное обращение по сети не нужно, когда операция
   чтения обслуживается локально.
-- Параллельное чтение: сумма IOPS всех дисков либо производительность сети, если в сеть упрётся раньше.
-- Параллельная запись: сумма IOPS всех дисков / общее число дисков данных и чётности / WA либо производительность сети, если в сеть упрётся раньше.
-  Примечание: IOPS дисков в данном случае надо брать в смешанном режиме чтения/записи в пропорции, аналогичной формулам выше.
+- Линейное чтение: сумма МБ/с чтения всех дисков, либо общая производительность сети, если в сеть упрётся раньше.
+- Линейная запись: сумма МБ/с записи всех дисков * N/(N+K), либо производительность сети * N / (N+K), если в сеть упрётся раньше.
+- Параллельное случайное мелкое чтение: сумма IOPS чтения всех дисков либо производительность сети, если в сеть упрётся раньше.
+- Параллельная случайная мелкая запись: грубо `(сумма IOPS / (N+K) / WA)`. Если точнее, то:
+  сумма смешанного IOPS всех дисков при `(N-1)/(N*4 + K*5 + 1)*100 %` чтения, делённая на `(N*4 + K*5 + 1)`.
+  Либо, производительность сети * N/(N+K), если в сеть упрётся раньше.
+  - Например, при EC 2+1 это: `(сумма IOPS при 7% чтения) / 14`.
+  - При EC 6+3 это: `(сумма IOPS при 12.5% чтения) / 40`.
 
 WA (мультипликатор записи) для 4 КБ блоков в Vitastor обычно составляет 3-5:
 1. Запись метаданных в журнал

docs/usage/cli.en.md

@@ -131,19 +131,18 @@ See also about [how to export snapshots](qemu.en.md#exporting-snapshots).
 
 ## modify
 
-`vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force]`
+`vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force] [--down-ok]`
 
 Rename, resize image or change its readonly status. Images with children can't be made read-write.
 If the new size is smaller than the old size, extra data will be purged.
 You should resize file system in the image, if present, before shrinking it.
 
-```
--f|--force  Proceed with shrinking or setting readwrite flag even if the image has children.
-```
+| `-f|--force` | Proceed with shrinking or setting readwrite flag even if the image has children. |
+| `--down-ok`  | Proceed with shrinking even if some data will be left on unavailable OSDs.       |
 
 ## rm
 
-`vitastor-cli rm <from> [<to>] [--writers-stopped]`
+`vitastor-cli rm <from> [<to>] [--writers-stopped] [--down-ok]`
 
 Remove `<from>` or all layers between `<from>` and `<to>` (`<to>` must be a child of `<from>`),
 rebasing all their children accordingly. --writers-stopped allows merging to be a bit
@@ -151,6 +150,10 @@ more effective in case of a single 'slim' read-write child and 'fat' removed par
 the child is merged into parent and parent is renamed to child in that case.
 In other cases parent layers are always merged into children.
 
+Other options:
+
+| `--down-ok` | Continue deletion/merging even if some data will be left on unavailable OSDs. |
+
 ## flatten
 
 `vitastor-cli flatten <layer>`

docs/usage/cli.ru.md

@@ -132,7 +132,7 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
 
 ## modify
 
-`vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force]`
+`vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force] [--down-ok]`
 
 Изменить размер, имя образа или флаг "только для чтения". Снимать флаг "только для чтения"
 и уменьшать размер образов, у которых есть дочерние клоны, без `--force` нельзя.
@@ -140,13 +140,12 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
 Если новый размер меньше старого, "лишние" данные будут удалены, поэтому перед уменьшением
 образа сначала уменьшите файловую систему в нём.
 
-```
--f|--force  Разрешить уменьшение или перевод в чтение-запись образа, у которого есть клоны.
-```
+| -f|--force | Разрешить уменьшение или перевод в чтение-запись образа, у которого есть клоны.        |
+| --down-ok  | Разрешить уменьшение, даже если часть данных останется неудалённой на недоступных OSD. |
 
 ## rm
 
-`vitastor-cli rm <from> [<to>] [--writers-stopped]`
+`vitastor-cli rm <from> [<to>] [--writers-stopped] [--down-ok]`
 
 Удалить образ `<from>` или все слои от `<from>` до `<to>` (`<to>` должен быть дочерним
 образом `<from>`), одновременно меняя родительские образы их клонов (если таковые есть).
@@ -158,6 +157,10 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
 
 В других случаях родительские слои вливаются в дочерние.
 
+Другие опции:
+
+| `--down-ok` | Продолжать удаление/слияние, даже если часть данных останется неудалённой на недоступных OSD. |
+
 ## flatten
 
 `vitastor-cli flatten <layer>`

docs/usage/disk.en.md

@@ -261,7 +261,7 @@ Options (see also [Cluster-Wide Disk Layout Parameters](../config/layout-cluster
 ```
 --object_size 128k       Set blockstore block size
 --bitmap_granularity 4k  Set bitmap granularity
---journal_size 16M       Set journal size
+--journal_size 32M       Set journal size
 --data_csum_type none    Set data checksum type (crc32c or none)
 --csum_block_size 4k     Set data checksum block size
 --device_block_size 4k   Set device block size

docs/usage/disk.ru.md

@@ -267,7 +267,7 @@ OSD отключены fsync-и.
 ```
 --object_size 128k       Размер блока хранилища
 --bitmap_granularity 4k  Гранулярность битовых карт
---journal_size 16M       Размер журнала
+--journal_size 32M       Размер журнала
 --data_csum_type none    Задать тип контрольных сумм (crc32c или none)
 --csum_block_size 4k     Задать размер блока расчёта контрольных сумм
 --device_block_size 4k   Размер блока устройства

docs/usage/fio.en.md

@@ -14,10 +14,13 @@ Vitastor has a fio driver which can be installed from the package vitastor-fio.
 Use the following command as an example to run tests with fio against a Vitastor cluster:
 
 ```
-fio -thread -ioengine=libfio_vitastor.so -name=test -bs=4M -direct=1 -iodepth=16 -rw=write -etcd=10.115.0.10:2379/v3 -image=testimg
+fio -thread -ioengine=libfio_vitastor.so -name=test -bs=4M -direct=1 -iodepth=16 -rw=write -image=testimg
 ```
 
 If you don't want to access your image by name, you can specify pool number, inode number and size
 (`-pool=1 -inode=1 -size=400G`) instead of the image name (`-image=testimg`).
 
-See exact fio commands to use for benchmarking [here](../performance/understanding.en.md#команды-fio).
+You can also specify etcd address(es) explicitly by adding `-etcd=10.115.0.10:2379/v3`, or you
+can override configuration file path by adding `-conf=/etc/vitastor/vitastor.conf`.
+
+See exact fio commands to use for benchmarking [here](../performance/understanding.en.md#fio-commands).

docs/usage/fio.ru.md

@@ -14,10 +14,13 @@
 Используйте следующую команду как пример для запуска тестов кластера Vitastor через fio:
 
 ```
-fio -thread -ioengine=libfio_vitastor.so -name=test -bs=4M -direct=1 -iodepth=16 -rw=write -etcd=10.115.0.10:2379/v3 -image=testimg
+fio -thread -ioengine=libfio_vitastor.so -name=test -bs=4M -direct=1 -iodepth=16 -rw=write -image=testimg
 ```
 
 Вместо обращения к образу по имени (`-image=testimg`) можно указать номер пула, номер инода и размер:
 `-pool=1 -inode=1 -size=400G`.
 
+Вы также можете задать адрес(а) подключения к etcd явно, добавив `-etcd=10.115.0.10:2379/v3`,
+или переопределить путь к файлу конфигурации, добавив `-conf=/etc/vitastor/vitastor.conf`.
+
 Конкретные команды fio для тестирования производительности можно посмотреть [здесь](../performance/understanding.ru.md#команды-fio).

docs/usage/nfs.en.md

@@ -34,7 +34,7 @@ vitastor-nfs [STANDARD OPTIONS] [OTHER OPTIONS]
 --foreground 1    stay in foreground, do not daemonize
 ```
 
-Example start and mount commands:
+Example start and mount commands (etcd_address is optional):
 
 ```
 vitastor-nfs --etcd_address 192.168.5.10:2379 --portmap 0 --port 2050 --pool testpool

docs/usage/nfs.ru.md

@@ -33,7 +33,7 @@ vitastor-nfs [СТАНДАРТНЫЕ ОПЦИИ] [ДРУГИЕ ОПЦИИ]
 --foreground 1    не уходить в фон после запуска
 ```
 
-Пример монтирования Vitastor через NFS:
+Пример монтирования Vitastor через NFS (etcd_address необязателен):
 
 ```
 vitastor-nfs --etcd_address 192.168.5.10:2379 --portmap 0 --port 2050 --pool testpool

docs/usage/qemu.en.md

@@ -16,13 +16,16 @@ Old syntax (-drive):
 
 ```
 qemu-system-x86_64 -enable-kvm -m 1024 \
-    -drive 'file=vitastor:etcd_host=192.168.7.2\:2379/v3:image=debian9',
+    -drive 'file=vitastor:image=debian9',
         format=raw,if=none,id=drive-virtio-disk0,cache=none \
     -device 'virtio-blk-pci,scsi=off,bus=pci.0,addr=0x5,drive=drive-virtio-disk0,
         id=virtio-disk0,bootindex=1,write-cache=off' \
     -vnc 0.0.0.0:0
 ```
 
+Etcd address may be specified explicitly by adding `:etcd_host=192.168.7.2\:2379/v3` to `file=`.
+Configuration file path may be overriden by adding `:config_path=/etc/vitastor/vitastor.conf`.
+
 New syntax (-blockdev):
 
 ```
@@ -50,12 +53,12 @@ You can also specify inode ID, pool and size manually instead of `:image=<IMAGE>
 
 ## qemu-img
 
-For qemu-img, you should use `vitastor:etcd_host=<HOST>:image=<IMAGE>` as filename.
+For qemu-img, you should use `vitastor:image=<IMAGE>[:etcd_host=<HOST>]` as filename.
 
 For example, to upload a VM image into Vitastor, run:
 
 ```
-qemu-img convert -f qcow2 debian10.qcow2 -p -O raw 'vitastor:etcd_host=192.168.7.2\:2379/v3:image=debian10'
+qemu-img convert -f qcow2 debian10.qcow2 -p -O raw 'vitastor:image=debian10'
 ```
 
 You can also specify `:pool=<POOL>:inode=<INODE>:size=<SIZE>` instead of `:image=<IMAGE>`
@@ -72,10 +75,10 @@ the snapshot separately using the following commands (key points are using `skip
 `-B backing_file` option):
 
 ```
-qemu-img convert -f raw 'vitastor:etcd_host=192.168.7.2\:2379/v3:image=testimg@0' \
+qemu-img convert -f raw 'vitastor:image=testimg@0' \
     -O qcow2 testimg_0.qcow2
 
-qemu-img convert -f raw 'vitastor:etcd_host=192.168.7.2\:2379/v3:image=testimg:skip-parents=1' \
+qemu-img convert -f raw 'vitastor:image=testimg:skip-parents=1' \
     -O qcow2 -o 'cluster_size=4k' -B testimg_0.qcow2 testimg.qcow2
 ```
 

docs/usage/qemu.ru.md

@@ -18,13 +18,16 @@
 
 ```
 qemu-system-x86_64 -enable-kvm -m 1024 \
-    -drive 'file=vitastor:etcd_host=192.168.7.2\:2379/v3:image=debian9',
+    -drive 'file=vitastor:image=debian9',
         format=raw,if=none,id=drive-virtio-disk0,cache=none \
     -device 'virtio-blk-pci,scsi=off,bus=pci.0,addr=0x5,drive=drive-virtio-disk0,
         id=virtio-disk0,bootindex=1,write-cache=off' \
     -vnc 0.0.0.0:0
 ```
 
+Адрес подключения etcd можно задать явно, если добавить `:etcd_host=192.168.7.2\:2379/v3` к `file=`.
+Путь к файлу конфигурации можно переопределить, добавив `:config_path=/etc/vitastor/vitastor.conf`.
+
 Новый синтаксис (-blockdev):
 
 ```
@@ -52,12 +55,12 @@ qemu-system-x86_64 -enable-kvm -m 1024 \
 
 ## qemu-img
 
-Для qemu-img используйте строку `vitastor:etcd_host=<HOST>:image=<IMAGE>` в качестве имени файла диска.
+Для qemu-img используйте строку `vitastor:image=<IMAGE>[:etcd_host=<HOST>]` в качестве имени файла диска.
 
 Например, чтобы загрузить образ диска в Vitastor:
 
 ```
-qemu-img convert -f qcow2 debian10.qcow2 -p -O raw 'vitastor:etcd_host=10.115.0.10\:2379/v3:image=testimg'
+qemu-img convert -f qcow2 debian10.qcow2 -p -O raw 'vitastor:image=testimg'
 ```
 
 Если вы не хотите обращаться к образу по имени, вместо `:image=<IMAGE>` можно указать номер пула, номер инода и размер:
@@ -73,10 +76,10 @@ qemu-img convert -f qcow2 debian10.qcow2 -p -O raw 'vitastor:etcd_host=10.115.0.
 с помощью следующих команд (ключевые моменты - использование `skip-parents=1` и опции `-B backing_file.qcow2`):
 
 ```
-qemu-img convert -f raw 'vitastor:etcd_host=192.168.7.2\:2379/v3:image=testimg@0' \
+qemu-img convert -f raw 'vitastor:image=testimg@0' \
     -O qcow2 testimg_0.qcow2
 
-qemu-img convert -f raw 'vitastor:etcd_host=192.168.7.2\:2379/v3:image=testimg:skip-parents=1' \
+qemu-img convert -f raw 'vitastor:image=testimg:skip-parents=1' \
     -O qcow2 -o 'cluster_size=4k' -B testimg_0.qcow2 testimg.qcow2
 ```
 

mon/PGUtil.js

@@ -3,6 +3,7 @@
 
 module.exports = {
     scale_pg_count,
+    scale_pg_history,
 };
 
 function add_pg_history(new_pg_history, new_pg, prev_pgs, prev_pg_history, old_pg)
@@ -43,16 +44,18 @@ function finish_pg_history(merged_history)
     merged_history.all_peers = Object.values(merged_history.all_peers);
 }
 
-function scale_pg_count(prev_pgs, real_prev_pgs, prev_pg_history, new_pg_history, new_pg_count)
+function scale_pg_history(prev_pg_history, prev_pgs, new_pgs)
 {
-    const old_pg_count = real_prev_pgs.length;
+    const new_pg_history = [];
+    const old_pg_count = prev_pgs.length;
+    const new_pg_count = new_pgs.length;
     // Add all possibly intersecting PGs to the history of new PGs
     if (!(new_pg_count % old_pg_count))
     {
         // New PG count is a multiple of old PG count
         for (let i = 0; i < new_pg_count; i++)
         {
-            add_pg_history(new_pg_history, i, real_prev_pgs, prev_pg_history, i % old_pg_count);
+            add_pg_history(new_pg_history, i, prev_pgs, prev_pg_history, i % old_pg_count);
             finish_pg_history(new_pg_history[i]);
         }
     }
@@ -64,7 +67,7 @@ function scale_pg_count(prev_pgs, real_prev_pgs, prev_pg_history, new_pg_history
         {
             for (let j = 0; j < mul; j++)
             {
-                add_pg_history(new_pg_history, i, real_prev_pgs, prev_pg_history, i+j*new_pg_count);
+                add_pg_history(new_pg_history, i, prev_pgs, prev_pg_history, i+j*new_pg_count);
             }
             finish_pg_history(new_pg_history[i]);
         }
@@ -76,7 +79,7 @@ function scale_pg_count(prev_pgs, real_prev_pgs, prev_pg_history, new_pg_history
         let merged_history = {};
         for (let i = 0; i < old_pg_count; i++)
         {
-            add_pg_history(merged_history, 1, real_prev_pgs, prev_pg_history, i);
+            add_pg_history(merged_history, 1, prev_pgs, prev_pg_history, i);
         }
         finish_pg_history(merged_history[1]);
         for (let i = 0; i < new_pg_count; i++)
@@ -89,6 +92,12 @@ function scale_pg_count(prev_pgs, real_prev_pgs, prev_pg_history, new_pg_history
     {
         new_pg_history[i] = null;
     }
+    return new_pg_history;
+}
+
+function scale_pg_count(prev_pgs, new_pg_count)
+{
+    const old_pg_count = prev_pgs.length;
     // Just for the lp_solve optimizer - pick a "previous" PG for each "new" one
     if (prev_pgs.length < new_pg_count)
     {

mon/mon.js

@@ -55,10 +55,11 @@ const etcd_tree = {
             // etcd connection - configurable online
             etcd_address: "10.0.115.10:2379/v3",
             // mon
-            etcd_mon_ttl: 30, // min: 10
+            etcd_mon_ttl: 5, // min: 1
             etcd_mon_timeout: 1000, // ms. min: 0
             etcd_mon_retries: 5, // min: 0
             mon_change_timeout: 1000, // ms. min: 100
+            mon_retry_change_timeout: 50, // ms. min: 10
             mon_stats_timeout: 1000, // ms. min: 100
             osd_out_time: 600, // seconds. min: 0
             placement_levels: { datacenter: 1, rack: 2, host: 3, osd: 4, ... },
@@ -85,13 +86,14 @@ const etcd_tree = {
             client_max_buffered_bytes: 33554432,
             client_max_buffered_ops: 1024,
             client_max_writeback_iodepth: 256,
+            client_retry_interval: 50, // ms. min: 10
+            client_eio_retry_interval: 1000, // ms
             // client and osd - configurable online
             log_level: 0,
             peer_connect_interval: 5, // seconds. min: 1
             peer_connect_timeout: 5, // seconds. min: 1
             osd_idle_timeout: 5, // seconds. min: 1
             osd_ping_timeout: 5, // seconds. min: 1
-            up_wait_retry_interval: 500, // ms. min: 50
             max_etcd_attempts: 5,
             etcd_quick_timeout: 1000, // ms
             etcd_slow_timeout: 5000, // ms
@@ -110,7 +112,15 @@ const etcd_tree = {
             autosync_interval: 5,
             autosync_writes: 128,
             client_queue_depth: 128, // unused
-            recovery_queue_depth: 4,
+            recovery_queue_depth: 1,
+            recovery_sleep_us: 0,
+            recovery_tune_util_low: 0.1,
+            recovery_tune_client_util_low: 0,
+            recovery_tune_util_high: 1.0,
+            recovery_tune_client_util_high: 0.5,
+            recovery_tune_interval: 1,
+            recovery_tune_agg_interval: 10, // 10 times recovery_tune_interval
+            recovery_tune_sleep_min_us: 10, // 10 microseconds
             recovery_pg_switch: 128,
             recovery_sync_batch: 16,
             no_recovery: false,
@@ -381,7 +391,8 @@ class Mon
 {
     constructor(config)
     {
-        this.die = (e) => this._die(e);
+        this.failconnect = (e) => this._die(e, 2);
+        this.die = (e) => this._die(e, 1);
         if (fs.existsSync(config.config_path||'/etc/vitastor/vitastor.conf'))
         {
             config = {
@@ -392,7 +403,7 @@ class Mon
         this.parse_etcd_addresses(config.etcd_address||config.etcd_url);
         this.verbose = config.verbose || 0;
         this.initConfig = config;
-        this.config = {};
+        this.config = { ...config };
         this.etcd_prefix = config.etcd_prefix || '/vitastor';
         this.etcd_prefix = this.etcd_prefix.replace(/\/\/+/g, '/').replace(/^\/?(.*[^\/])\/?$/, '/$1');
         this.etcd_start_timeout = (config.etcd_start_timeout || 5) * 1000;
@@ -470,10 +481,10 @@ class Mon
 
     check_config()
     {
-        this.config.etcd_mon_ttl = Number(this.config.etcd_mon_ttl) || 30;
-        if (this.config.etcd_mon_ttl < 10)
+        this.config.etcd_mon_ttl = Number(this.config.etcd_mon_ttl) || 5;
+        if (this.config.etcd_mon_ttl < 1)
         {
-            this.config.etcd_mon_ttl = 10;
+            this.config.etcd_mon_ttl = 1;
         }
         this.config.etcd_mon_timeout = Number(this.config.etcd_mon_timeout) || 0;
         if (this.config.etcd_mon_timeout <= 0)
@@ -490,6 +501,11 @@ class Mon
         {
             this.config.mon_change_timeout = 100;
         }
+        this.config.mon_retry_change_timeout = Number(this.config.mon_retry_change_timeout) || 50;
+        if (this.config.mon_retry_change_timeout < 50)
+        {
+            this.config.mon_retry_change_timeout = 50;
+        }
         this.config.mon_stats_timeout = Number(this.config.mon_stats_timeout) || 1000;
         if (this.config.mon_stats_timeout < 100)
         {
@@ -590,7 +606,7 @@ class Mon
         }
         if (!this.ws)
         {
-            this.die('Failed to open etcd watch websocket');
+            this.failconnect('Failed to open etcd watch websocket');
         }
         const cur_addr = this.selected_etcd_url;
         this.ws_alive = true;
@@ -606,7 +622,7 @@ class Mon
                 console.log('etcd websocket timed out, restarting it');
                 this.restart_watcher(cur_addr);
             }
-        }, (Number(this.config.etcd_keepalive_interval) || 30)*1000);
+        }, (Number(this.config.etcd_ws_keepalive_interval) || 30)*1000);
         this.ws.on('error', () => this.restart_watcher(cur_addr));
         this.ws.send(JSON.stringify({
             create_request: {
@@ -660,7 +676,12 @@ class Mon
                 {
                     this.parse_kv(e.kv);
                     const key = e.kv.key.substr(this.etcd_prefix.length);
-                    if (key.substr(0, 11) == '/osd/stats/' || key.substr(0, 10) == '/pg/stats/' || key.substr(0, 16) == '/osd/inodestats/')
+                    if (key.substr(0, 11) == '/osd/state/')
+                    {
+                        stats_changed = true;
+                        changed = true;
+                    }
+                    else if (key.substr(0, 11) == '/osd/stats/' || key.substr(0, 10) == '/pg/stats/' || key.substr(0, 16) == '/osd/inodestats/')
                     {
                         stats_changed = true;
                     }
@@ -777,9 +798,9 @@ class Mon
             const res = await this.etcd_call('/lease/keepalive', { ID: this.etcd_lease_id }, this.config.etcd_mon_timeout, this.config.etcd_mon_retries);
             if (!res.result.TTL)
             {
-                this.die('Lease expired');
+                this.failconnect('Lease expired');
             }
-        }, this.config.etcd_mon_timeout);
+        }, this.config.etcd_mon_ttl*1000);
         if (!this.signals_set)
         {
             process.on('SIGINT', this.on_stop_cb);
@@ -1222,6 +1243,89 @@ class Mon
         return aff_osds;
     }
 
+    async generate_pool_pgs(pool_id, osd_tree, levels)
+    {
+        const pool_cfg = this.state.config.pools[pool_id];
+        if (!this.validate_pool_cfg(pool_id, pool_cfg, false))
+        {
+            return null;
+        }
+        let pool_tree = osd_tree[pool_cfg.root_node || ''];
+        pool_tree = pool_tree ? pool_tree.children : [];
+        pool_tree = LPOptimizer.flatten_tree(pool_tree, levels, pool_cfg.failure_domain, 'osd');
+        this.filter_osds_by_tags(osd_tree, pool_tree, pool_cfg.osd_tags);
+        this.filter_osds_by_block_layout(
+            pool_tree,
+            pool_cfg.block_size || this.config.block_size || 131072,
+            pool_cfg.bitmap_granularity || this.config.bitmap_granularity || 4096,
+            pool_cfg.immediate_commit || this.config.immediate_commit || 'none'
+        );
+        // First try last_clean_pgs to minimize data movement
+        let prev_pgs = [];
+        for (const pg in ((this.state.history.last_clean_pgs.items||{})[pool_id]||{}))
+        {
+            prev_pgs[pg-1] = [ ...this.state.history.last_clean_pgs.items[pool_id][pg].osd_set ];
+        }
+        if (!prev_pgs.length)
+        {
+            // Fall back to config/pgs if it's empty
+            for (const pg in ((this.state.config.pgs.items||{})[pool_id]||{}))
+            {
+                prev_pgs[pg-1] = [ ...this.state.config.pgs.items[pool_id][pg].osd_set ];
+            }
+        }
+        const old_pg_count = prev_pgs.length;
+        const optimize_cfg = {
+            osd_tree: pool_tree,
+            pg_count: pool_cfg.pg_count,
+            pg_size: pool_cfg.pg_size,
+            pg_minsize: pool_cfg.pg_minsize,
+            max_combinations: pool_cfg.max_osd_combinations,
+            ordered: pool_cfg.scheme != 'replicated',
+        };
+        let optimize_result;
+        // Re-shuffle PGs if config/pgs.hash is empty
+        if (old_pg_count > 0 && this.state.config.pgs.hash)
+        {
+            if (prev_pgs.length != pool_cfg.pg_count)
+            {
+                // Scale PG count
+                // Do it even if old_pg_count is already equal to pool_cfg.pg_count,
+                // because last_clean_pgs may still contain the old number of PGs
+                PGUtil.scale_pg_count(prev_pgs, pool_cfg.pg_count);
+            }
+            for (const pg of prev_pgs)
+            {
+                while (pg.length < pool_cfg.pg_size)
+                {
+                    pg.push(0);
+                }
+            }
+            optimize_result = await LPOptimizer.optimize_change({
+                prev_pgs,
+                ...optimize_cfg,
+            });
+        }
+        else
+        {
+            optimize_result = await LPOptimizer.optimize_initial(optimize_cfg);
+        }
+        console.log(`Pool ${pool_id} (${pool_cfg.name || 'unnamed'}):`);
+        LPOptimizer.print_change_stats(optimize_result);
+        const pg_effsize = Math.min(pool_cfg.pg_size, Object.keys(pool_tree).length);
+        return {
+            pool_id,
+            pgs: optimize_result.int_pgs,
+            stats: {
+                total_raw_tb: optimize_result.space,
+                pg_real_size: pg_effsize || pool_cfg.pg_size,
+                raw_to_usable: (pg_effsize || pool_cfg.pg_size) / (pool_cfg.scheme === 'replicated'
+                    ? 1 : (pool_cfg.pg_size - (pool_cfg.parity_chunks||0))),
+                space_efficiency: optimize_result.space/(optimize_result.total_space||1),
+            },
+        };
+    }
+
     async recheck_pgs()
     {
         if (this.recheck_pgs_active)
@@ -1236,158 +1340,47 @@ class Mon
         const { up_osds, levels, osd_tree } = this.get_osd_tree();
         const tree_cfg = {
             osd_tree,
+            levels,
             pools: this.state.config.pools,
         };
         const tree_hash = sha1hex(stableStringify(tree_cfg));
         if (this.state.config.pgs.hash != tree_hash)
         {
             // Something has changed
-            const new_config_pgs = JSON.parse(JSON.stringify(this.state.config.pgs));
-            const etcd_request = { compare: [], success: [] };
-            for (const pool_id in (this.state.config.pgs||{}).items||{})
+            console.log('Pool configuration or OSD tree changed, re-optimizing');
+            // First re-optimize PGs, but don't look at history yet
+            const optimize_results = await Promise.all(Object.keys(this.state.config.pools)
+                .map(pool_id => this.generate_pool_pgs(pool_id, osd_tree, levels)));
+            // Then apply the modification in the form of an optimistic transaction,
+            // each time considering new pg/history modifications (OSDs modify it during rebalance)
+            while (!await this.apply_pool_pgs(optimize_results, up_osds, osd_tree, tree_hash))
             {
-                if (!this.state.config.pools[pool_id])
-                {
-                    // Pool deleted. Delete all PGs, but first stop them.
-                    if (!await this.stop_all_pgs(pool_id))
-                    {
-                        this.recheck_pgs_active = false;
-                        this.schedule_recheck();
-                        return;
-                    }
-                    const prev_pgs = [];
-                    for (const pg in this.state.config.pgs.items[pool_id]||{})
-                    {
-                        prev_pgs[pg-1] = this.state.config.pgs.items[pool_id][pg].osd_set;
-                    }
-                    // Also delete pool statistics
-                    etcd_request.success.push({ requestDeleteRange: {
-                        key: b64(this.etcd_prefix+'/pool/stats/'+pool_id),
-                    } });
-                    this.save_new_pgs_txn(new_config_pgs, etcd_request, pool_id, up_osds, osd_tree, prev_pgs, [], []);
-                }
-            }
-            for (const pool_id in this.state.config.pools)
-            {
-                const pool_cfg = this.state.config.pools[pool_id];
-                if (!this.validate_pool_cfg(pool_id, pool_cfg, false))
-                {
-                    continue;
-                }
-                let pool_tree = osd_tree[pool_cfg.root_node || ''];
-                pool_tree = pool_tree ? pool_tree.children : [];
-                pool_tree = LPOptimizer.flatten_tree(pool_tree, levels, pool_cfg.failure_domain, 'osd');
-                this.filter_osds_by_tags(osd_tree, pool_tree, pool_cfg.osd_tags);
-                this.filter_osds_by_block_layout(
-                    pool_tree,
-                    pool_cfg.block_size || this.config.block_size || 131072,
-                    pool_cfg.bitmap_granularity || this.config.bitmap_granularity || 4096,
-                    pool_cfg.immediate_commit || this.config.immediate_commit || 'none'
+                console.log(
+                    'Someone changed PG configuration while we also tried to change it.'+
+                    ' Retrying in '+this.config.mon_retry_change_timeout+' ms'
                 );
-                // These are for the purpose of building history.osd_sets
-                const real_prev_pgs = [];
-                let pg_history = [];
-                for (const pg in ((this.state.config.pgs.items||{})[pool_id]||{}))
+                // Failed to apply - parallel change detected. Wait a bit and retry
+                const old_rev = this.etcd_watch_revision;
+                while (this.etcd_watch_revision === old_rev)
                 {
-                    real_prev_pgs[pg-1] = this.state.config.pgs.items[pool_id][pg].osd_set;
-                    if (this.state.pg.history[pool_id] &&
-                        this.state.pg.history[pool_id][pg])
-                    {
-                        pg_history[pg-1] = this.state.pg.history[pool_id][pg];
-                    }
+                    await new Promise(ok => setTimeout(ok, this.config.mon_retry_change_timeout));
                 }
-                // And these are for the purpose of minimizing data movement
-                let prev_pgs = [];
-                for (const pg in ((this.state.history.last_clean_pgs.items||{})[pool_id]||{}))
-                {
-                    prev_pgs[pg-1] = this.state.history.last_clean_pgs.items[pool_id][pg].osd_set;
-                }
-                prev_pgs = JSON.parse(JSON.stringify(prev_pgs.length ? prev_pgs : real_prev_pgs));
-                const old_pg_count = real_prev_pgs.length;
-                const optimize_cfg = {
-                    osd_tree: pool_tree,
-                    pg_count: pool_cfg.pg_count,
-                    pg_size: pool_cfg.pg_size,
-                    pg_minsize: pool_cfg.pg_minsize,
-                    max_combinations: pool_cfg.max_osd_combinations,
-                    ordered: pool_cfg.scheme != 'replicated',
+                const new_ot = this.get_osd_tree();
+                const new_tcfg = {
+                    osd_tree: new_ot.osd_tree,
+                    levels: new_ot.levels,
+                    pools: this.state.config.pools,
                 };
-                let optimize_result;
-                if (old_pg_count > 0)
+                if (sha1hex(stableStringify(new_tcfg)) !== tree_hash)
                 {
-                    if (old_pg_count != pool_cfg.pg_count)
-                    {
-                        // PG count changed. Need to bring all PGs down.
-                        if (!await this.stop_all_pgs(pool_id))
-                        {
-                            this.recheck_pgs_active = false;
-                            this.schedule_recheck();
-                            return;
-                        }
-                    }
-                    if (prev_pgs.length != pool_cfg.pg_count)
-                    {
-                        // Scale PG count
-                        // Do it even if old_pg_count is already equal to pool_cfg.pg_count,
-                        // because last_clean_pgs may still contain the old number of PGs
-                        const new_pg_history = [];
-                        PGUtil.scale_pg_count(prev_pgs, real_prev_pgs, pg_history, new_pg_history, pool_cfg.pg_count);
-                        pg_history = new_pg_history;
-                    }
-                    for (const pg of prev_pgs)
-                    {
-                        while (pg.length < pool_cfg.pg_size)
-                        {
-                            pg.push(0);
-                        }
-                    }
-                    if (!this.state.config.pgs.hash)
-                    {
-                        // Re-shuffle PGs
-                        optimize_result = await LPOptimizer.optimize_initial(optimize_cfg);
-                    }
-                    else
-                    {
-                        optimize_result = await LPOptimizer.optimize_change({
-                            prev_pgs,
-                            ...optimize_cfg,
-                        });
-                    }
+                    // Configuration actually changed, restart from the beginning
+                    this.recheck_pgs_active = false;
+                    setImmediate(() => this.recheck_pgs().catch(this.die));
+                    return;
                 }
-                else
-                {
-                    optimize_result = await LPOptimizer.optimize_initial(optimize_cfg);
-                }
-                if (old_pg_count != optimize_result.int_pgs.length)
-                {
-                    console.log(
-                        `PG count for pool ${pool_id} (${pool_cfg.name || 'unnamed'})`+
-                        ` changed from: ${old_pg_count} to ${optimize_result.int_pgs.length}`
-                    );
-                    // Drop stats
-                    etcd_request.success.push({ requestDeleteRange: {
-                        key: b64(this.etcd_prefix+'/pg/stats/'+pool_id+'/'),
-                        range_end: b64(this.etcd_prefix+'/pg/stats/'+pool_id+'0'),
-                    } });
-                }
-                LPOptimizer.print_change_stats(optimize_result);
-                const pg_effsize = Math.min(pool_cfg.pg_size, Object.keys(pool_tree).length);
-                this.state.pool.stats[pool_id] = {
-                    used_raw_tb: (this.state.pool.stats[pool_id]||{}).used_raw_tb || 0,
-                    total_raw_tb: optimize_result.space,
-                    pg_real_size: pg_effsize || pool_cfg.pg_size,
-                    raw_to_usable: (pg_effsize || pool_cfg.pg_size) / (pool_cfg.scheme === 'replicated'
-                        ? 1 : (pool_cfg.pg_size - (pool_cfg.parity_chunks||0))),
-                    space_efficiency: optimize_result.space/(optimize_result.total_space||1),
-                };
-                etcd_request.success.push({ requestPut: {
-                    key: b64(this.etcd_prefix+'/pool/stats/'+pool_id),
-                    value: b64(JSON.stringify(this.state.pool.stats[pool_id])),
-                } });
-                this.save_new_pgs_txn(new_config_pgs, etcd_request, pool_id, up_osds, osd_tree, real_prev_pgs, optimize_result.int_pgs, pg_history);
+                // Configuration didn't change, PG history probably changed, so just retry
             }
-            new_config_pgs.hash = tree_hash;
-            await this.save_pg_config(new_config_pgs, etcd_request);
+            console.log('PG configuration successfully changed');
         }
         else
         {
@@ -1428,12 +1421,97 @@ class Mon
             }
             if (changed)
             {
-                await this.save_pg_config(new_config_pgs);
+                const ok = await this.save_pg_config(new_config_pgs);
+                if (ok)
+                    console.log('PG configuration successfully changed');
+                else
+                {
+                    console.log('Someone changed PG configuration while we also tried to change it. Retrying in '+this.config.mon_change_timeout+' ms');
+                    this.schedule_recheck();
+                }
             }
         }
         this.recheck_pgs_active = false;
     }
 
+    async apply_pool_pgs(results, up_osds, osd_tree, tree_hash)
+    {
+        for (const pool_id in (this.state.config.pgs||{}).items||{})
+        {
+            // We should stop all PGs when deleting a pool or changing its PG count
+            if (!this.state.config.pools[pool_id] ||
+                this.state.config.pgs.items[pool_id] && this.state.config.pools[pool_id].pg_count !=
+                Object.keys(this.state.config.pgs.items[pool_id]).reduce((a, c) => (a < (0|c) ? (0|c) : a), 0))
+            {
+                if (!await this.stop_all_pgs(pool_id))
+                {
+                    return false;
+                }
+            }
+        }
+        const new_config_pgs = JSON.parse(JSON.stringify(this.state.config.pgs));
+        const etcd_request = { compare: [], success: [] };
+        for (const pool_id in (new_config_pgs||{}).items||{})
+        {
+            if (!this.state.config.pools[pool_id])
+            {
+                const prev_pgs = [];
+                for (const pg in new_config_pgs.items[pool_id]||{})
+                {
+                    prev_pgs[pg-1] = new_config_pgs.items[pool_id][pg].osd_set;
+                }
+                // Also delete pool statistics
+                etcd_request.success.push({ requestDeleteRange: {
+                    key: b64(this.etcd_prefix+'/pool/stats/'+pool_id),
+                } });
+                this.save_new_pgs_txn(new_config_pgs, etcd_request, pool_id, up_osds, osd_tree, prev_pgs, [], []);
+            }
+        }
+        for (const pool_res of results)
+        {
+            const pool_id = pool_res.pool_id;
+            const pool_cfg = this.state.config.pools[pool_id];
+            let pg_history = [];
+            for (const pg in ((this.state.config.pgs.items||{})[pool_id]||{}))
+            {
+                if (this.state.pg.history[pool_id] &&
+                    this.state.pg.history[pool_id][pg])
+                {
+                    pg_history[pg-1] = this.state.pg.history[pool_id][pg];
+                }
+            }
+            const real_prev_pgs = [];
+            for (const pg in ((this.state.config.pgs.items||{})[pool_id]||{}))
+            {
+                real_prev_pgs[pg-1] = [ ...this.state.config.pgs.items[pool_id][pg].osd_set ];
+            }
+            if (real_prev_pgs.length > 0 && real_prev_pgs.length != pool_res.pgs.length)
+            {
+                console.log(
+                    `Changing PG count for pool ${pool_id} (${pool_cfg.name || 'unnamed'})`+
+                    ` from: ${real_prev_pgs.length} to ${pool_res.pgs.length}`
+                );
+                pg_history = PGUtil.scale_pg_history(pg_history, real_prev_pgs, pool_res.pgs);
+                // Drop stats
+                etcd_request.success.push({ requestDeleteRange: {
+                    key: b64(this.etcd_prefix+'/pg/stats/'+pool_id+'/'),
+                    range_end: b64(this.etcd_prefix+'/pg/stats/'+pool_id+'0'),
+                } });
+            }
+            const stats = {
+                used_raw_tb: (this.state.pool.stats[pool_id]||{}).used_raw_tb || 0,
+                ...pool_res.stats,
+            };
+            etcd_request.success.push({ requestPut: {
+                key: b64(this.etcd_prefix+'/pool/stats/'+pool_id),
+                value: b64(JSON.stringify(stats)),
+            } });
+            this.save_new_pgs_txn(new_config_pgs, etcd_request, pool_id, up_osds, osd_tree, real_prev_pgs, pool_res.pgs, pg_history);
+        }
+        new_config_pgs.hash = tree_hash;
+        return await this.save_pg_config(new_config_pgs, etcd_request);
+    }
+
     async save_pg_config(new_config_pgs, etcd_request = { compare: [], success: [] })
     {
         etcd_request.compare.push(
@@ -1443,14 +1521,8 @@ class Mon
         etcd_request.success.push(
             { requestPut: { key: b64(this.etcd_prefix+'/config/pgs'), value: b64(JSON.stringify(new_config_pgs)) } },
         );
-        const res = await this.etcd_call('/kv/txn', etcd_request, this.config.etcd_mon_timeout, 0);
-        if (!res.succeeded)
-        {
-            console.log('Someone changed PG configuration while we also tried to change it. Retrying in '+this.config.mon_change_timeout+' ms');
-            this.schedule_recheck();
-            return;
-        }
-        console.log('PG configuration successfully changed');
+        const txn_res = await this.etcd_call('/kv/txn', etcd_request, this.config.etcd_mon_timeout, 0);
+        return txn_res.succeeded;
     }
 
     // Schedule next recheck at least at <unixtime>
@@ -1569,9 +1641,13 @@ class Mon
         }
         const sum_diff = { op_stats: {}, subop_stats: {}, recovery_stats: {} };
         // Sum derived values instead of deriving summed
-        for (const osd in this.state.osd.stats)
+        for (const osd in this.state.osd.state)
         {
             const derived = this.prev_stats.osd_diff[osd];
+            if (!this.state.osd.state[osd] || !derived)
+            {
+                continue;
+            }
             for (const type in sum_diff)
             {
                 for (const op in derived[type]||{})
@@ -1672,9 +1748,13 @@ class Mon
             const used = this.state.pool.stats[pool_id].used_raw_tb;
             this.state.pool.stats[pool_id].used_raw_tb = Number(used)/1024/1024/1024/1024;
         }
-        for (const osd_num in this.state.osd.inodestats)
+        for (const osd_num in this.state.osd.state)
         {
             const ist = this.state.osd.inodestats[osd_num];
+            if (!ist || !this.state.osd.state[osd_num])
+            {
+                continue;
+            }
             for (const pool_id in ist)
             {
                 inode_stats[pool_id] = inode_stats[pool_id] || {};
@@ -1690,9 +1770,14 @@ class Mon
                 }
             }
         }
-        for (const osd in this.prev_stats.osd_diff)
+        for (const osd in this.state.osd.state)
         {
-            for (const pool_id in this.prev_stats.osd_diff[osd].inode_stats)
+            const osd_diff = this.prev_stats.osd_diff[osd];
+            if (!osd_diff || !this.state.osd.state[osd])
+            {
+                continue;
+            }
+            for (const pool_id in osd_diff.inode_stats)
             {
                 for (const inode_num in this.prev_stats.osd_diff[osd].inode_stats[pool_id])
                 {
@@ -1932,14 +2017,14 @@ class Mon
                 return res.json;
             }
         }
-        this.die();
+        this.failconnect();
     }
 
-    _die(err)
+    _die(err, code)
     {
         // In fact we can just try to rejoin
         console.error(new Error(err || 'Cluster connection failed'));
-        process.exit(1);
+        process.exit(code || 2);
     }
 
     local_ips(all)

mon/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vitastor-mon",
-  "version": "1.3.1",
+  "version": "1.4.8",
   "description": "Vitastor SDS monitor service",
   "main": "mon-main.js",
   "scripts": {

mon/vitastor-osd@.service

@@ -8,7 +8,9 @@ PartOf=vitastor.target
 LimitNOFILE=1048576
 LimitNPROC=1048576
 LimitMEMLOCK=infinity
-ExecStart=bash -c 'exec vitastor-disk exec-osd /dev/vitastor/osd%i-data >>/var/log/vitastor/osd%i.log 2>&1'
+# 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
 ExecStartPre=+vitastor-disk pre-exec /dev/vitastor/osd%i-data
 WorkingDirectory=/
 User=vitastor

patches/VitastorPlugin.pm

@@ -110,7 +110,6 @@ sub properties
         vitastor_etcd_address => {
             description => 'IP address(es) of etcd.',
             type => 'string',
-            format => 'pve-storage-portal-dns-list',
         },
         vitastor_etcd_prefix => {
             description => 'Prefix for Vitastor etcd metadata',

patches/cinder-vitastor.py

@@ -50,7 +50,7 @@ from cinder.volume import configuration
 from cinder.volume import driver
 from cinder.volume import volume_utils
 
-VERSION = '1.3.1'
+VERSION = '1.4.8'
 
 LOG = logging.getLogger(__name__)
 

patches/libvirt-8.0-vitastor.diff

@@ -0,0 +1,692 @@
+commit d85024bd803b3b91f15578ed22de4ce31856626f
+Author: Vitaliy Filippov <vitalif@yourcmc.ru>
+Date:   Wed Jan 24 18:07:43 2024 +0300
+
+    Add Vitastor support
+
+diff --git a/docs/schemas/domaincommon.rng b/docs/schemas/domaincommon.rng
+index 7fa5c2b8b5..2d77f391e7 100644
+--- a/docs/schemas/domaincommon.rng
++++ b/docs/schemas/domaincommon.rng
+@@ -1898,6 +1898,35 @@
+     </element>
+   </define>
+ 
++  <define name="diskSourceNetworkProtocolVitastor">
++    <element name="source">
++      <interleave>
++        <attribute name="protocol">
++          <value>vitastor</value>
++        </attribute>
++        <ref name="diskSourceCommon"/>
++        <optional>
++          <attribute name="name"/>
++        </optional>
++        <optional>
++          <attribute name="query"/>
++        </optional>
++        <zeroOrMore>
++          <ref name="diskSourceNetworkHost"/>
++        </zeroOrMore>
++        <optional>
++          <element name="config">
++            <attribute name="file">
++              <ref name="absFilePath"/>
++            </attribute>
++            <empty/>
++          </element>
++        </optional>
++        <empty/>
++      </interleave>
++    </element>
++  </define>
++
+   <define name="diskSourceNetworkProtocolISCSI">
+     <element name="source">
+       <attribute name="protocol">
+@@ -2154,6 +2183,7 @@
+       <ref name="diskSourceNetworkProtocolSimple"/>
+       <ref name="diskSourceNetworkProtocolVxHS"/>
+       <ref name="diskSourceNetworkProtocolNFS"/>
++      <ref name="diskSourceNetworkProtocolVitastor"/>
+     </choice>
+   </define>
+ 
+diff --git a/include/libvirt/libvirt-storage.h b/include/libvirt/libvirt-storage.h
+index f89856b93e..a8cb9387e2 100644
+--- a/include/libvirt/libvirt-storage.h
++++ b/include/libvirt/libvirt-storage.h
+@@ -246,6 +246,7 @@ typedef enum {
+     VIR_CONNECT_LIST_STORAGE_POOLS_ZFS           = 1 << 17,
+     VIR_CONNECT_LIST_STORAGE_POOLS_VSTORAGE      = 1 << 18,
+     VIR_CONNECT_LIST_STORAGE_POOLS_ISCSI_DIRECT  = 1 << 19,
++    VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR      = 1 << 20,
+ } virConnectListAllStoragePoolsFlags;
+ 
+ int                     virConnectListAllStoragePools(virConnectPtr conn,
+diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c
+index 5691b8d2d5..6669e8451d 100644
+--- a/src/conf/domain_conf.c
++++ b/src/conf/domain_conf.c
+@@ -8293,7 +8293,8 @@ virDomainDiskSourceNetworkParse(xmlNodePtr node,
+     src->configFile = virXPathString("string(./config/@file)", ctxt);
+ 
+     if (src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTP ||
+-        src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTPS)
++        src->protocol == VIR_STORAGE_NET_PROTOCOL_HTTPS ||
++        src->protocol == VIR_STORAGE_NET_PROTOCOL_VITASTOR)
+         src->query = virXMLPropString(node, "query");
+ 
+     if (virDomainStorageNetworkParseHosts(node, ctxt, &src->hosts, &src->nhosts) < 0)
+@@ -31267,6 +31268,7 @@ virDomainStorageSourceTranslateSourcePool(virStorageSource *src,
+ 
+     case VIR_STORAGE_POOL_MPATH:
+     case VIR_STORAGE_POOL_RBD:
++    case VIR_STORAGE_POOL_VITASTOR:
+     case VIR_STORAGE_POOL_SHEEPDOG:
+     case VIR_STORAGE_POOL_GLUSTER:
+     case VIR_STORAGE_POOL_LAST:
+diff --git a/src/conf/domain_validate.c b/src/conf/domain_validate.c
+index a4271f1247..621c1b7b31 100644
+--- a/src/conf/domain_validate.c
++++ b/src/conf/domain_validate.c
+@@ -508,7 +508,7 @@ virDomainDiskDefValidateSourceChainOne(const virStorageSource *src)
+         }
+     }
+ 
+-    /* internal snapshots and config files are currently supported only with rbd: */
++    /* internal snapshots are currently supported only with rbd: */
+     if (virStorageSourceGetActualType(src) != VIR_STORAGE_TYPE_NETWORK &&
+         src->protocol != VIR_STORAGE_NET_PROTOCOL_RBD) {
+         if (src->snapshot) {
+@@ -517,11 +517,15 @@ virDomainDiskDefValidateSourceChainOne(const virStorageSource *src)
+                              "only with 'rbd' disks"));
+             return -1;
+         }
+-
++    }
++    /* config files are currently supported only with rbd and vitastor: */
++    if (virStorageSourceGetActualType(src) != VIR_STORAGE_TYPE_NETWORK &&
++        src->protocol != VIR_STORAGE_NET_PROTOCOL_RBD &&
++        src->protocol != VIR_STORAGE_NET_PROTOCOL_VITASTOR) {
+         if (src->configFile) {
+             virReportError(VIR_ERR_XML_ERROR, "%s",
+                            _("<config> element is currently supported "
+-                             "only with 'rbd' disks"));
++                             "only with 'rbd' and 'vitastor' disks"));
+             return -1;
+         }
+     }
+diff --git a/src/conf/storage_conf.c b/src/conf/storage_conf.c
+index 6690d26ffd..2255df9d28 100644
+--- a/src/conf/storage_conf.c
++++ b/src/conf/storage_conf.c
+@@ -60,7 +60,7 @@ VIR_ENUM_IMPL(virStoragePool,
+               "logical", "disk", "iscsi",
+               "iscsi-direct", "scsi", "mpath",
+               "rbd", "sheepdog", "gluster",
+-              "zfs", "vstorage",
++              "zfs", "vstorage", "vitastor",
+ );
+ 
+ VIR_ENUM_IMPL(virStoragePoolFormatFileSystem,
+@@ -246,6 +246,18 @@ static virStoragePoolTypeInfo poolTypeInfo[] = {
+           .formatToString = virStorageFileFormatTypeToString,
+       }
+     },
++    {.poolType = VIR_STORAGE_POOL_VITASTOR,
++     .poolOptions = {
++         .flags = (VIR_STORAGE_POOL_SOURCE_HOST |
++                   VIR_STORAGE_POOL_SOURCE_NETWORK |
++                   VIR_STORAGE_POOL_SOURCE_NAME),
++      },
++      .volOptions = {
++          .defaultFormat = VIR_STORAGE_FILE_RAW,
++          .formatFromString = virStorageVolumeFormatFromString,
++          .formatToString = virStorageFileFormatTypeToString,
++      }
++    },
+     {.poolType = VIR_STORAGE_POOL_SHEEPDOG,
+      .poolOptions = {
+          .flags = (VIR_STORAGE_POOL_SOURCE_HOST |
+@@ -546,6 +558,11 @@ virStoragePoolDefParseSource(xmlXPathContextPtr ctxt,
+                        _("element 'name' is mandatory for RBD pool"));
+         return -1;
+     }
++    if (pool_type == VIR_STORAGE_POOL_VITASTOR && source->name == NULL) {
++        virReportError(VIR_ERR_XML_ERROR, "%s",
++                       _("element 'name' is mandatory for Vitastor pool"));
++        return -1;
++    }
+ 
+     if (options->formatFromString) {
+         g_autofree char *format = NULL;
+@@ -1176,6 +1193,7 @@ virStoragePoolDefFormatBuf(virBuffer *buf,
+     /* RBD, Sheepdog, Gluster and Iscsi-direct devices are not local block devs nor
+      * files, so they don't have a target */
+     if (def->type != VIR_STORAGE_POOL_RBD &&
++        def->type != VIR_STORAGE_POOL_VITASTOR &&
+         def->type != VIR_STORAGE_POOL_SHEEPDOG &&
+         def->type != VIR_STORAGE_POOL_GLUSTER &&
+         def->type != VIR_STORAGE_POOL_ISCSI_DIRECT) {
+diff --git a/src/conf/storage_conf.h b/src/conf/storage_conf.h
+index aaecf138d6..97172db38b 100644
+--- a/src/conf/storage_conf.h
++++ b/src/conf/storage_conf.h
+@@ -106,6 +106,7 @@ typedef enum {
+     VIR_STORAGE_POOL_GLUSTER,  /* Gluster device */
+     VIR_STORAGE_POOL_ZFS,      /* ZFS */
+     VIR_STORAGE_POOL_VSTORAGE, /* Virtuozzo Storage */
++    VIR_STORAGE_POOL_VITASTOR, /* Vitastor */
+ 
+     VIR_STORAGE_POOL_LAST,
+ } virStoragePoolType;
+@@ -466,6 +467,7 @@ VIR_ENUM_DECL(virStoragePartedFs);
+                  VIR_CONNECT_LIST_STORAGE_POOLS_SCSI     | \
+                  VIR_CONNECT_LIST_STORAGE_POOLS_MPATH    | \
+                  VIR_CONNECT_LIST_STORAGE_POOLS_RBD      | \
++                 VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR | \
+                  VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG | \
+                  VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER  | \
+                  VIR_CONNECT_LIST_STORAGE_POOLS_ZFS      | \
+diff --git a/src/conf/storage_source_conf.c b/src/conf/storage_source_conf.c
+index d42f715f26..29d8da3d10 100644
+--- a/src/conf/storage_source_conf.c
++++ b/src/conf/storage_source_conf.c
+@@ -86,6 +86,7 @@ VIR_ENUM_IMPL(virStorageNetProtocol,
+               "ssh",
+               "vxhs",
+               "nfs",
++              "vitastor",
+ );
+ 
+ 
+@@ -1265,6 +1266,7 @@ virStorageSourceNetworkDefaultPort(virStorageNetProtocol protocol)
+         case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
+             return 24007;
+ 
++        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
+         case VIR_STORAGE_NET_PROTOCOL_RBD:
+             /* we don't provide a default for RBD */
+             return 0;
+diff --git a/src/conf/storage_source_conf.h b/src/conf/storage_source_conf.h
+index c4a026881c..67568e9181 100644
+--- a/src/conf/storage_source_conf.h
++++ b/src/conf/storage_source_conf.h
+@@ -128,6 +128,7 @@ typedef enum {
+     VIR_STORAGE_NET_PROTOCOL_SSH,
+     VIR_STORAGE_NET_PROTOCOL_VXHS,
+     VIR_STORAGE_NET_PROTOCOL_NFS,
++    VIR_STORAGE_NET_PROTOCOL_VITASTOR,
+ 
+     VIR_STORAGE_NET_PROTOCOL_LAST
+ } virStorageNetProtocol;
+diff --git a/src/conf/virstorageobj.c b/src/conf/virstorageobj.c
+index 02903ac487..504df599fb 100644
+--- a/src/conf/virstorageobj.c
++++ b/src/conf/virstorageobj.c
+@@ -1481,6 +1481,7 @@ virStoragePoolObjSourceFindDuplicateCb(const void *payload,
+             return 1;
+         break;
+ 
++    case VIR_STORAGE_POOL_VITASTOR:
+     case VIR_STORAGE_POOL_RBD:
+     case VIR_STORAGE_POOL_LAST:
+         break;
+@@ -1978,6 +1979,8 @@ virStoragePoolObjMatch(virStoragePoolObj *obj,
+                (obj->def->type == VIR_STORAGE_POOL_MPATH))   ||
+               (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_RBD) &&
+                (obj->def->type == VIR_STORAGE_POOL_RBD))     ||
++              (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR) &&
++               (obj->def->type == VIR_STORAGE_POOL_VITASTOR)) ||
+               (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG) &&
+                (obj->def->type == VIR_STORAGE_POOL_SHEEPDOG)) ||
+               (MATCH(VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER) &&
+diff --git a/src/libvirt-storage.c b/src/libvirt-storage.c
+index cbc522b300..b4760fa58d 100644
+--- a/src/libvirt-storage.c
++++ b/src/libvirt-storage.c
+@@ -92,6 +92,7 @@ virStoragePoolGetConnect(virStoragePoolPtr pool)
+  * VIR_CONNECT_LIST_STORAGE_POOLS_SCSI
+  * VIR_CONNECT_LIST_STORAGE_POOLS_MPATH
+  * VIR_CONNECT_LIST_STORAGE_POOLS_RBD
++ * VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR
+  * VIR_CONNECT_LIST_STORAGE_POOLS_SHEEPDOG
+  * VIR_CONNECT_LIST_STORAGE_POOLS_GLUSTER
+  * VIR_CONNECT_LIST_STORAGE_POOLS_ZFS
+diff --git a/src/libxl/libxl_conf.c b/src/libxl/libxl_conf.c
+index 1ac6253ad7..abe4587f94 100644
+--- a/src/libxl/libxl_conf.c
++++ b/src/libxl/libxl_conf.c
+@@ -962,6 +962,7 @@ libxlMakeNetworkDiskSrcStr(virStorageSource *src,
+     case VIR_STORAGE_NET_PROTOCOL_SSH:
+     case VIR_STORAGE_NET_PROTOCOL_VXHS:
+     case VIR_STORAGE_NET_PROTOCOL_NFS:
++    case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
+     case VIR_STORAGE_NET_PROTOCOL_LAST:
+     case VIR_STORAGE_NET_PROTOCOL_NONE:
+         virReportError(VIR_ERR_NO_SUPPORT,
+diff --git a/src/libxl/xen_xl.c b/src/libxl/xen_xl.c
+index 7604e3d534..6453bb9776 100644
+--- a/src/libxl/xen_xl.c
++++ b/src/libxl/xen_xl.c
+@@ -1506,6 +1506,7 @@ xenFormatXLDiskSrcNet(virStorageSource *src)
+     case VIR_STORAGE_NET_PROTOCOL_SSH:
+     case VIR_STORAGE_NET_PROTOCOL_VXHS:
+     case VIR_STORAGE_NET_PROTOCOL_NFS:
++    case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
+     case VIR_STORAGE_NET_PROTOCOL_LAST:
+     case VIR_STORAGE_NET_PROTOCOL_NONE:
+         virReportError(VIR_ERR_NO_SUPPORT,
+diff --git a/src/qemu/qemu_block.c b/src/qemu/qemu_block.c
+index e5ff653a60..884ecc79ea 100644
+--- a/src/qemu/qemu_block.c
++++ b/src/qemu/qemu_block.c
+@@ -943,6 +943,38 @@ qemuBlockStorageSourceGetRBDProps(virStorageSource *src,
+ }
+ 
+ 
++static virJSONValue *
++qemuBlockStorageSourceGetVitastorProps(virStorageSource *src)
++{
++    virJSONValue *ret = NULL;
++    virStorageNetHostDef *host;
++    size_t i;
++    g_auto(virBuffer) buf = VIR_BUFFER_INITIALIZER;
++    g_autofree char *etcd = NULL;
++
++    for (i = 0; i < src->nhosts; i++) {
++        host = src->hosts + i;
++        if ((virStorageNetHostTransport)host->transport != VIR_STORAGE_NET_HOST_TRANS_TCP) {
++            return NULL;
++        }
++        virBufferAsprintf(&buf, i > 0 ? ",%s:%u" : "%s:%u", host->name, host->port);
++    }
++    if (src->nhosts > 0) {
++        etcd = virBufferContentAndReset(&buf);
++    }
++
++    if (virJSONValueObjectCreate(&ret,
++                                 "S:etcd-host", etcd,
++                                 "S:etcd-prefix", src->query,
++                                 "S:config-path", src->configFile,
++                                 "s:image", src->path,
++                                 NULL) < 0)
++        return NULL;
++
++    return ret;
++}
++
++
+ static virJSONValue *
+ qemuBlockStorageSourceGetSheepdogProps(virStorageSource *src)
+ {
+@@ -1233,6 +1265,12 @@ qemuBlockStorageSourceGetBackendProps(virStorageSource *src,
+                 return NULL;
+             break;
+ 
++        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
++            driver = "vitastor";
++            if (!(fileprops = qemuBlockStorageSourceGetVitastorProps(src)))
++                return NULL;
++            break;
++
+         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
+             driver = "sheepdog";
+             if (!(fileprops = qemuBlockStorageSourceGetSheepdogProps(src)))
+@@ -2244,6 +2282,7 @@ qemuBlockGetBackingStoreString(virStorageSource *src,
+ 
+             case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
+             case VIR_STORAGE_NET_PROTOCOL_RBD:
++            case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
+             case VIR_STORAGE_NET_PROTOCOL_VXHS:
+             case VIR_STORAGE_NET_PROTOCOL_NFS:
+             case VIR_STORAGE_NET_PROTOCOL_SSH:
+@@ -2626,6 +2665,12 @@ qemuBlockStorageSourceCreateGetStorageProps(virStorageSource *src,
+                 return -1;
+             break;
+ 
++        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
++            driver = "vitastor";
++            if (!(location = qemuBlockStorageSourceGetVitastorProps(src)))
++                return -1;
++            break;
++
+         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
+             driver = "sheepdog";
+             if (!(location = qemuBlockStorageSourceGetSheepdogProps(src)))
+diff --git a/src/qemu/qemu_command.c b/src/qemu/qemu_command.c
+index d822533ccb..afe2087303 100644
+--- a/src/qemu/qemu_command.c
++++ b/src/qemu/qemu_command.c
+@@ -1723,6 +1723,43 @@ qemuBuildNetworkDriveStr(virStorageSource *src,
+             ret = virBufferContentAndReset(&buf);
+             break;
+ 
++        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
++            if (strchr(src->path, ':')) {
++                virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
++                               _("':' not allowed in Vitastor source volume name '%s'"),
++                               src->path);
++                return NULL;
++            }
++
++            virBufferStrcat(&buf, "vitastor:image=", src->path, NULL);
++
++            if (src->nhosts > 0) {
++                virBufferAddLit(&buf, ":etcd-host=");
++                for (i = 0; i < src->nhosts; i++) {
++                    if (i)
++                        virBufferAddLit(&buf, ",");
++
++                    /* assume host containing : is ipv6 */
++                    if (strchr(src->hosts[i].name, ':'))
++                        virBufferEscape(&buf, '\\', ":", "[%s]",
++                                        src->hosts[i].name);
++                    else
++                        virBufferAsprintf(&buf, "%s", src->hosts[i].name);
++
++                    if (src->hosts[i].port)
++                        virBufferAsprintf(&buf, "\\:%u", src->hosts[i].port);
++                }
++            }
++
++            if (src->configFile)
++                virBufferEscape(&buf, '\\', ":", ":config-path=%s", src->configFile);
++
++            if (src->query)
++                virBufferEscape(&buf, '\\', ":", ":etcd-prefix=%s", src->query);
++
++            ret = virBufferContentAndReset(&buf);
++            break;
++
+         case VIR_STORAGE_NET_PROTOCOL_VXHS:
+             virReportError(VIR_ERR_INTERNAL_ERROR, "%s",
+                            _("VxHS protocol does not support URI syntax"));
+diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c
+index a8401bac30..3dc1fe6db0 100644
+--- a/src/qemu/qemu_domain.c
++++ b/src/qemu/qemu_domain.c
+@@ -4731,7 +4731,8 @@ qemuDomainValidateStorageSource(virStorageSource *src,
+     if (src->query &&
+         (actualType != VIR_STORAGE_TYPE_NETWORK ||
+          (src->protocol != VIR_STORAGE_NET_PROTOCOL_HTTPS &&
+-          src->protocol != VIR_STORAGE_NET_PROTOCOL_HTTP))) {
++          src->protocol != VIR_STORAGE_NET_PROTOCOL_HTTP &&
++          src->protocol != VIR_STORAGE_NET_PROTOCOL_VITASTOR))) {
+         virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s",
+                        _("query is supported only with HTTP(S) protocols"));
+         return -1;
+@@ -9919,6 +9920,7 @@ qemuDomainPrepareStorageSourceTLS(virStorageSource *src,
+         break;
+ 
+     case VIR_STORAGE_NET_PROTOCOL_RBD:
++    case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
+     case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
+     case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
+     case VIR_STORAGE_NET_PROTOCOL_ISCSI:
+diff --git a/src/qemu/qemu_snapshot.c b/src/qemu/qemu_snapshot.c
+index f92e00f9c0..854a3fbc90 100644
+--- a/src/qemu/qemu_snapshot.c
++++ b/src/qemu/qemu_snapshot.c
+@@ -393,6 +393,7 @@ qemuSnapshotPrepareDiskExternalInactive(virDomainSnapshotDiskDef *snapdisk,
+         case VIR_STORAGE_NET_PROTOCOL_NONE:
+         case VIR_STORAGE_NET_PROTOCOL_NBD:
+         case VIR_STORAGE_NET_PROTOCOL_RBD:
++        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
+         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
+         case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
+         case VIR_STORAGE_NET_PROTOCOL_ISCSI:
+@@ -485,6 +486,7 @@ qemuSnapshotPrepareDiskExternalActive(virDomainObj *vm,
+         case VIR_STORAGE_NET_PROTOCOL_NONE:
+         case VIR_STORAGE_NET_PROTOCOL_NBD:
+         case VIR_STORAGE_NET_PROTOCOL_RBD:
++        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
+         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
+         case VIR_STORAGE_NET_PROTOCOL_ISCSI:
+         case VIR_STORAGE_NET_PROTOCOL_HTTP:
+@@ -638,6 +640,7 @@ qemuSnapshotPrepareDiskInternal(virDomainDiskDef *disk,
+         case VIR_STORAGE_NET_PROTOCOL_NONE:
+         case VIR_STORAGE_NET_PROTOCOL_NBD:
+         case VIR_STORAGE_NET_PROTOCOL_RBD:
++        case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
+         case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
+         case VIR_STORAGE_NET_PROTOCOL_GLUSTER:
+         case VIR_STORAGE_NET_PROTOCOL_ISCSI:
+diff --git a/src/storage/storage_driver.c b/src/storage/storage_driver.c
+index 4df2c75a2b..5a5e48ef71 100644
+--- a/src/storage/storage_driver.c
++++ b/src/storage/storage_driver.c
+@@ -1643,6 +1643,7 @@ storageVolLookupByPathCallback(virStoragePoolObj *obj,
+ 
+         case VIR_STORAGE_POOL_GLUSTER:
+         case VIR_STORAGE_POOL_RBD:
++        case VIR_STORAGE_POOL_VITASTOR:
+         case VIR_STORAGE_POOL_SHEEPDOG:
+         case VIR_STORAGE_POOL_ZFS:
+         case VIR_STORAGE_POOL_LAST:
+diff --git a/src/storage_file/storage_source_backingstore.c b/src/storage_file/storage_source_backingstore.c
+index e48ae725ab..2017ccc88c 100644
+--- a/src/storage_file/storage_source_backingstore.c
++++ b/src/storage_file/storage_source_backingstore.c
+@@ -284,6 +284,75 @@ virStorageSourceParseRBDColonString(const char *rbdstr,
+ }
+ 
+ 
++static int
++virStorageSourceParseVitastorColonString(const char *colonstr,
++                                         virStorageSource *src)
++{
++    char *p, *e, *next;
++    g_autofree char *options = NULL;
++
++    /* optionally skip the "vitastor:" prefix if provided */
++    if (STRPREFIX(colonstr, "vitastor:"))
++        colonstr += strlen("vitastor:");
++
++    options = g_strdup(colonstr);
++
++    p = options;
++    while (*p) {
++        /* find : delimiter or end of string */
++        for (e = p; *e && *e != ':'; ++e) {
++            if (*e == '\\') {
++                e++;
++                if (*e == '\0')
++                    break;
++            }
++        }
++        if (*e == '\0') {
++            next = e;    /* last kv pair */
++        } else {
++            next = e + 1;
++            *e = '\0';
++        }
++
++        if (STRPREFIX(p, "image=")) {
++            src->path = g_strdup(p + strlen("image="));
++        } else if (STRPREFIX(p, "etcd-prefix=")) {
++            src->query = g_strdup(p + strlen("etcd-prefix="));
++        } else if (STRPREFIX(p, "config-path=")) {
++            src->configFile = g_strdup(p + strlen("config-path="));
++        } else if (STRPREFIX(p, "etcd-host=")) {
++            char *h, *sep;
++
++            h = p + strlen("etcd-host=");
++            while (h < e) {
++                for (sep = h; sep < e; ++sep) {
++                    if (*sep == '\\' && (sep[1] == ',' ||
++                                         sep[1] == ';' ||
++                                         sep[1] == ' ')) {
++                        *sep = '\0';
++                        sep += 2;
++                        break;
++                    }
++                }
++
++                if (virStorageSourceRBDAddHost(src, h) < 0)
++                    return -1;
++
++                h = sep;
++            }
++        }
++
++        p = next;
++    }
++
++    if (!src->path) {
++        return -1;
++    }
++
++    return 0;
++}
++
++
+ static int
+ virStorageSourceParseNBDColonString(const char *nbdstr,
+                                     virStorageSource *src)
+@@ -396,6 +465,11 @@ virStorageSourceParseBackingColon(virStorageSource *src,
+             return -1;
+         break;
+ 
++    case VIR_STORAGE_NET_PROTOCOL_VITASTOR:
++        if (virStorageSourceParseVitastorColonString(path, src) < 0)
++            return -1;
++        break;
++
+     case VIR_STORAGE_NET_PROTOCOL_SHEEPDOG:
+     case VIR_STORAGE_NET_PROTOCOL_LAST:
+     case VIR_STORAGE_NET_PROTOCOL_NONE:
+@@ -984,6 +1058,54 @@ virStorageSourceParseBackingJSONRBD(virStorageSource *src,
+     return 0;
+ }
+ 
++static int
++virStorageSourceParseBackingJSONVitastor(virStorageSource *src,
++                                         virJSONValue *json,
++                                         const char *jsonstr G_GNUC_UNUSED,
++                                         int opaque G_GNUC_UNUSED)
++{
++    const char *filename;
++    const char *image = virJSONValueObjectGetString(json, "image");
++    const char *conf = virJSONValueObjectGetString(json, "config-path");
++    const char *etcd_prefix = virJSONValueObjectGetString(json, "etcd-prefix");
++    virJSONValue *servers = virJSONValueObjectGetArray(json, "server");
++    size_t nservers;
++    size_t i;
++
++    src->type = VIR_STORAGE_TYPE_NETWORK;
++    src->protocol = VIR_STORAGE_NET_PROTOCOL_VITASTOR;
++
++    /* legacy syntax passed via 'filename' option */
++    if ((filename = virJSONValueObjectGetString(json, "filename")))
++        return virStorageSourceParseVitastorColonString(filename, src);
++
++    if (!image) {
++        virReportError(VIR_ERR_INVALID_ARG, "%s",
++                       _("missing image name in Vitastor backing volume "
++                         "JSON specification"));
++        return -1;
++    }
++
++    src->path = g_strdup(image);
++    src->configFile = g_strdup(conf);
++    src->query = g_strdup(etcd_prefix);
++
++    if (servers) {
++        nservers = virJSONValueArraySize(servers);
++
++        src->hosts = g_new0(virStorageNetHostDef, nservers);
++        src->nhosts = nservers;
++
++        for (i = 0; i < nservers; i++) {
++            if (virStorageSourceParseBackingJSONInetSocketAddress(src->hosts + i,
++                                                                  virJSONValueArrayGet(servers, i)) < 0)
++                return -1;
++        }
++    }
++
++    return 0;
++}
++
+ static int
+ virStorageSourceParseBackingJSONRaw(virStorageSource *src,
+                                     virJSONValue *json,
+@@ -1162,6 +1284,7 @@ static const struct virStorageSourceJSONDriverParser jsonParsers[] = {
+     {"sheepdog", false, virStorageSourceParseBackingJSONSheepdog, 0},
+     {"ssh", false, virStorageSourceParseBackingJSONSSH, 0},
+     {"rbd", false, virStorageSourceParseBackingJSONRBD, 0},
++    {"vitastor", false, virStorageSourceParseBackingJSONVitastor, 0},
+     {"raw", true, virStorageSourceParseBackingJSONRaw, 0},
+     {"nfs", false, virStorageSourceParseBackingJSONNFS, 0},
+     {"vxhs", false, virStorageSourceParseBackingJSONVxHS, 0},
+diff --git a/src/test/test_driver.c b/src/test/test_driver.c
+index 0e93b79922..b4d33f5f56 100644
+--- a/src/test/test_driver.c
++++ b/src/test/test_driver.c
+@@ -7367,6 +7367,7 @@ testStorageVolumeTypeForPool(int pooltype)
+     case VIR_STORAGE_POOL_ISCSI_DIRECT:
+     case VIR_STORAGE_POOL_GLUSTER:
+     case VIR_STORAGE_POOL_RBD:
++    case VIR_STORAGE_POOL_VITASTOR:
+         return VIR_STORAGE_VOL_NETWORK;
+     case VIR_STORAGE_POOL_LOGICAL:
+     case VIR_STORAGE_POOL_DISK:
+diff --git a/tests/storagepoolcapsschemadata/poolcaps-fs.xml b/tests/storagepoolcapsschemadata/poolcaps-fs.xml
+index eee75af746..8bd0a57bdd 100644
+--- a/tests/storagepoolcapsschemadata/poolcaps-fs.xml
++++ b/tests/storagepoolcapsschemadata/poolcaps-fs.xml
+@@ -204,4 +204,11 @@
+       </enum>
+     </volOptions>
+   </pool>
++  <pool type='vitastor' supported='no'>
++    <volOptions>
++      <defaultFormat type='raw'/>
++      <enum name='targetFormatType'>
++      </enum>
++    </volOptions>
++  </pool>
+ </storagepoolCapabilities>
+diff --git a/tests/storagepoolcapsschemadata/poolcaps-full.xml b/tests/storagepoolcapsschemadata/poolcaps-full.xml
+index 805950a937..852df0de16 100644
+--- a/tests/storagepoolcapsschemadata/poolcaps-full.xml
++++ b/tests/storagepoolcapsschemadata/poolcaps-full.xml
+@@ -204,4 +204,11 @@
+       </enum>
+     </volOptions>
+   </pool>
++  <pool type='vitastor' supported='yes'>
++    <volOptions>
++      <defaultFormat type='raw'/>
++      <enum name='targetFormatType'>
++      </enum>
++    </volOptions>
++  </pool>
+ </storagepoolCapabilities>
+diff --git a/tests/storagepoolxml2argvtest.c b/tests/storagepoolxml2argvtest.c
+index 449b745519..7f95cc8e08 100644
+--- a/tests/storagepoolxml2argvtest.c
++++ b/tests/storagepoolxml2argvtest.c
+@@ -68,6 +68,7 @@ testCompareXMLToArgvFiles(bool shouldFail,
+     case VIR_STORAGE_POOL_GLUSTER:
+     case VIR_STORAGE_POOL_ZFS:
+     case VIR_STORAGE_POOL_VSTORAGE:
++    case VIR_STORAGE_POOL_VITASTOR:
+     case VIR_STORAGE_POOL_LAST:
+     default:
+         VIR_TEST_DEBUG("pool type '%s' has no xml2argv test", defTypeStr);
+diff --git a/tools/virsh-pool.c b/tools/virsh-pool.c
+index d391257f6e..46799c4a90 100644
+--- a/tools/virsh-pool.c
++++ b/tools/virsh-pool.c
+@@ -1213,6 +1213,9 @@ cmdPoolList(vshControl *ctl, const vshCmd *cmd G_GNUC_UNUSED)
+             case VIR_STORAGE_POOL_VSTORAGE:
+                 flags |= VIR_CONNECT_LIST_STORAGE_POOLS_VSTORAGE;
+                 break;
++            case VIR_STORAGE_POOL_VITASTOR:
++                flags |= VIR_CONNECT_LIST_STORAGE_POOLS_VITASTOR;
++                break;
+             case VIR_STORAGE_POOL_LAST:
+                 break;
+             }

patches/libvirt-9.10-vitastor.diff

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

pull_request_template.yml

@@ -0,0 +1,28 @@
+name: Pull Request
+about: Submit a pull request
+body:
+  - type: textarea
+    id: description
+    attributes:
+      label: Description
+      description: Describe your pull request
+      placeholder: ""
+      value: ""
+    validations:
+      required: true
+  - type: input
+    id: author
+    attributes:
+      label: Contributor Name
+      description: Contributor Name or Company Details if the Contributor is a company
+      placeholder: ""
+    validations:
+      required: false
+  - type: checkboxes
+    id: terms
+    attributes:
+      label: CLA
+      description: By submitting this pull request, I accept [Vitastor CLA](https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-en.md)
+      options:
+        - label: "I accept Vitastor CLA agreement: https://git.yourcmc.ru/vitalif/vitastor/src/branch/master/CLA-en.md"
+          required: true

rpm/build-tarball.sh

@@ -24,4 +24,4 @@ rm fio
 mv fio-copy fio
 FIO=`rpm -qi fio | perl -e 'while(<>) { /^Epoch[\s:]+(\S+)/ && print "$1:"; /^Version[\s:]+(\S+)/ && print $1; /^Release[\s:]+(\S+)/ && print "-$1"; }'`
 perl -i -pe 's/(Requires:\s*fio)([^\n]+)?/$1 = '$FIO'/' $VITASTOR/rpm/vitastor-el$EL.spec
-tar --transform 's#^#vitastor-1.3.1/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-1.3.1$(rpm --eval '%dist').tar.gz *
+tar --transform 's#^#vitastor-1.4.8/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-1.4.8$(rpm --eval '%dist').tar.gz *

rpm/vitastor-el7.Dockerfile

@@ -36,7 +36,7 @@ ADD . /root/vitastor
 RUN set -e; \
     cd /root/vitastor/rpm; \
     sh build-tarball.sh; \
-    cp /root/vitastor-1.3.1.el7.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-1.4.8.el7.tar.gz ~/rpmbuild/SOURCES; \
     cp vitastor-el7.spec ~/rpmbuild/SPECS/vitastor.spec; \
     cd ~/rpmbuild/SPECS/; \
     rpmbuild -ba vitastor.spec; \

rpm/vitastor-el7.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        1.3.1
+Version:        1.4.8
 Release:        1%{?dist}
 Summary:        Vitastor, a fast software-defined clustered block storage
 
 License:        Vitastor Network Public License 1.1
 URL:            https://vitastor.io/
-Source0:        vitastor-1.3.1.el7.tar.gz
+Source0:        vitastor-1.4.8.el7.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

rpm/vitastor-el8.Dockerfile

@@ -35,7 +35,7 @@ ADD . /root/vitastor
 RUN set -e; \
     cd /root/vitastor/rpm; \
     sh build-tarball.sh; \
-    cp /root/vitastor-1.3.1.el8.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-1.4.8.el8.tar.gz ~/rpmbuild/SOURCES; \
     cp vitastor-el8.spec ~/rpmbuild/SPECS/vitastor.spec; \
     cd ~/rpmbuild/SPECS/; \
     rpmbuild -ba vitastor.spec; \

rpm/vitastor-el8.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        1.3.1
+Version:        1.4.8
 Release:        1%{?dist}
 Summary:        Vitastor, a fast software-defined clustered block storage
 
 License:        Vitastor Network Public License 1.1
 URL:            https://vitastor.io/
-Source0:        vitastor-1.3.1.el8.tar.gz
+Source0:        vitastor-1.4.8.el8.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

rpm/vitastor-el9.Dockerfile

@@ -18,7 +18,7 @@ ADD . /root/vitastor
 RUN set -e; \
     cd /root/vitastor/rpm; \
     sh build-tarball.sh; \
-    cp /root/vitastor-1.3.1.el9.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-1.4.8.el9.tar.gz ~/rpmbuild/SOURCES; \
     cp vitastor-el9.spec ~/rpmbuild/SPECS/vitastor.spec; \
     cd ~/rpmbuild/SPECS/; \
     rpmbuild -ba vitastor.spec; \

rpm/vitastor-el9.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        1.3.1
+Version:        1.4.8
 Release:        1%{?dist}
 Summary:        Vitastor, a fast software-defined clustered block storage
 
 License:        Vitastor Network Public License 1.1
 URL:            https://vitastor.io/
-Source0:        vitastor-1.3.1.el9.tar.gz
+Source0:        vitastor-1.4.8.el9.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

src/CMakeLists.txt

@@ -16,8 +16,8 @@ if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
 	set(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
 endif()
 
-add_definitions(-DVERSION="1.3.1")
-add_definitions(-Wall -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith -fdiagnostics-color=always -fno-omit-frame-pointer -I ${CMAKE_SOURCE_DIR}/src)
+add_definitions(-DVERSION="1.4.8")
+add_definitions(-D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -Wall -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith -fdiagnostics-color=always -fno-omit-frame-pointer -I ${CMAKE_SOURCE_DIR}/src)
 add_link_options(-fno-omit-frame-pointer)
 if (${WITH_ASAN})
 	add_definitions(-fsanitize=address)

src/addr_util.cpp

@@ -8,6 +8,7 @@
 #include <stdio.h>
 
 #include <stdexcept>
+#include <set>
 
 #include "addr_util.h"
 
@@ -135,7 +136,7 @@ std::vector<std::string> getifaddr_list(std::vector<std::string> mask_cfg, bool
             throw std::runtime_error((include_v6 ? "Invalid IPv4 address mask: " : "Invalid IP address mask: ") + mask);
         }
     }
-    std::vector<std::string> addresses;
+    std::set<std::string> addresses;
     ifaddrs *list, *ifa;
     if (getifaddrs(&list) == -1)
     {
@@ -149,7 +150,8 @@ std::vector<std::string> getifaddr_list(std::vector<std::string> mask_cfg, bool
         }
         int family = ifa->ifa_addr->sa_family;
         if ((family == AF_INET || family == AF_INET6 && include_v6) &&
-            (ifa->ifa_flags & (IFF_UP | IFF_RUNNING | IFF_LOOPBACK)) == (IFF_UP | IFF_RUNNING))
+            // Do not skip loopback addresses if the address filter is specified
+            (ifa->ifa_flags & (IFF_UP | IFF_RUNNING | (masks.size() ? 0 : IFF_LOOPBACK))) == (IFF_UP | IFF_RUNNING))
         {
             void *addr_ptr;
             if (family == AF_INET)
@@ -182,11 +184,11 @@ std::vector<std::string> getifaddr_list(std::vector<std::string> mask_cfg, bool
             {
                 throw std::runtime_error(std::string("inet_ntop: ") + strerror(errno));
             }
-            addresses.push_back(std::string(addr));
+            addresses.insert(std::string(addr));
         }
     }
     freeifaddrs(list);
-    return addresses;
+    return std::vector<std::string>(addresses.begin(), addresses.end());
 }
 
 int create_and_bind_socket(std::string bind_address, int bind_port, int listen_backlog, int *listening_port)

src/blockstore_disk.cpp

@@ -108,6 +108,10 @@ void blockstore_disk_t::parse_config(std::map<std::string, std::string> & config
     {
         throw std::runtime_error("journal_block_size must be a multiple of "+std::to_string(DIRECT_IO_ALIGNMENT));
     }
+    else if (journal_block_size > MAX_DATA_BLOCK_SIZE)
+    {
+        throw std::runtime_error("journal_block_size must not exceed "+std::to_string(MAX_DATA_BLOCK_SIZE));
+    }
     if (!meta_block_size)
     {
         meta_block_size = 4096;
@@ -116,6 +120,10 @@ void blockstore_disk_t::parse_config(std::map<std::string, std::string> & config
     {
         throw std::runtime_error("meta_block_size must be a multiple of "+std::to_string(DIRECT_IO_ALIGNMENT));
     }
+    else if (meta_block_size > MAX_DATA_BLOCK_SIZE)
+    {
+        throw std::runtime_error("meta_block_size must not exceed "+std::to_string(MAX_DATA_BLOCK_SIZE));
+    }
     if (data_offset % disk_alignment)
     {
         throw std::runtime_error("data_offset must be a multiple of disk_alignment = "+std::to_string(disk_alignment));

src/blockstore_flush.cpp

@@ -19,7 +19,6 @@ journal_flusher_t::journal_flusher_t(blockstore_impl_t *bs)
     syncing_flushers = 0;
     // FIXME: allow to configure flusher_start_threshold and journal_trim_interval
     flusher_start_threshold = bs->dsk.journal_block_size / sizeof(journal_entry_stable);
-    journal_trim_interval = 512;
     journal_trim_counter = bs->journal.flush_journal ? 1 : 0;
     trim_wanted = bs->journal.flush_journal ? 1 : 0;
     journal_superblock = bs->journal.inmemory ? bs->journal.buffer : memalign_or_die(MEM_ALIGNMENT, bs->dsk.journal_block_size);
@@ -94,7 +93,7 @@ void journal_flusher_t::loop()
 void journal_flusher_t::enqueue_flush(obj_ver_id ov)
 {
 #ifdef BLOCKSTORE_DEBUG
-    printf("enqueue_flush %lx:%lx v%lu\n", ov.oid.inode, ov.oid.stripe, ov.version);
+    printf("enqueue_flush %jx:%jx v%ju\n", ov.oid.inode, ov.oid.stripe, ov.version);
 #endif
     auto it = flush_versions.find(ov.oid);
     if (it != flush_versions.end())
@@ -117,7 +116,7 @@ void journal_flusher_t::enqueue_flush(obj_ver_id ov)
 void journal_flusher_t::unshift_flush(obj_ver_id ov, bool force)
 {
 #ifdef BLOCKSTORE_DEBUG
-    printf("unshift_flush %lx:%lx v%lu\n", ov.oid.inode, ov.oid.stripe, ov.version);
+    printf("unshift_flush %jx:%jx v%ju\n", ov.oid.inode, ov.oid.stripe, ov.version);
 #endif
     auto it = flush_versions.find(ov.oid);
     if (it != flush_versions.end())
@@ -143,7 +142,7 @@ void journal_flusher_t::unshift_flush(obj_ver_id ov, bool force)
 void journal_flusher_t::remove_flush(object_id oid)
 {
 #ifdef BLOCKSTORE_DEBUG
-    printf("undo_flush %lx:%lx\n", oid.inode, oid.stripe);
+    printf("undo_flush %jx:%jx\n", oid.inode, oid.stripe);
 #endif
     auto v_it = flush_versions.find(oid);
     if (v_it != flush_versions.end())
@@ -184,8 +183,7 @@ void journal_flusher_t::mark_trim_possible()
     if (trim_wanted > 0)
     {
         dequeuing = true;
-        if (!journal_trim_counter)
-            journal_trim_counter = journal_trim_interval;
+        journal_trim_counter = 0;
         bs->ringloop->wakeup();
     }
 }
@@ -235,7 +233,7 @@ void journal_flusher_t::dump_diagnostics()
         break;
     }
     printf(
-        "Flusher: queued=%ld first=%s%lx:%lx trim_wanted=%d dequeuing=%d trimming=%d cur=%d target=%d active=%d syncing=%d\n",
+        "Flusher: queued=%zd first=%s%jx:%jx trim_wanted=%d dequeuing=%d trimming=%d cur=%d target=%d active=%d syncing=%d\n",
         flush_queue.size(), unflushable_type, unflushable.oid.inode, unflushable.oid.stripe,
         trim_wanted, dequeuing, trimming, cur_flusher_count, target_flusher_count,
         active_flushers, syncing_flushers
@@ -268,7 +266,7 @@ bool journal_flusher_t::try_find_other(std::map<obj_ver_id, dirty_entry>::iterat
 {
     int search_left = flush_queue.size() - 1;
 #ifdef BLOCKSTORE_DEBUG
-    printf("Flusher overran writers (%lx:%lx v%lu, dirty_start=%08lx) - searching for older flushes (%d left)\n",
+    printf("Flusher overran writers (%jx:%jx v%ju, dirty_start=%08jx) - searching for older flushes (%d left)\n",
         cur.oid.inode, cur.oid.stripe, cur.version, bs->journal.dirty_start, search_left);
 #endif
     while (search_left > 0)
@@ -285,7 +283,7 @@ bool journal_flusher_t::try_find_other(std::map<obj_ver_id, dirty_entry>::iterat
                 dirty_end->second.journal_sector < bs->journal.used_start))
             {
 #ifdef BLOCKSTORE_DEBUG
-                printf("Write %lx:%lx v%lu is too new: offset=%08lx\n", cur.oid.inode, cur.oid.stripe, cur.version, dirty_end->second.journal_sector);
+                printf("Write %jx:%jx v%ju is too new: offset=%08jx\n", cur.oid.inode, cur.oid.stripe, cur.version, dirty_end->second.journal_sector);
 #endif
                 enqueue_flush(cur);
             }
@@ -366,9 +364,10 @@ resume_0:
         !flusher->flush_queue.size() || !flusher->dequeuing)
     {
 stop_flusher:
-        if (flusher->trim_wanted > 0 && flusher->journal_trim_counter > 0)
+        if (flusher->trim_wanted > 0 && cur.oid.inode != 0)
         {
             // Attempt forced trim
+            cur.oid = {};
             flusher->active_flushers++;
             goto trim_journal;
         }
@@ -387,7 +386,7 @@ stop_flusher:
         if (repeat_it != flusher->sync_to_repeat.end())
         {
 #ifdef BLOCKSTORE_DEBUG
-            printf("Postpone %lx:%lx v%lu\n", cur.oid.inode, cur.oid.stripe, cur.version);
+            printf("Postpone %jx:%jx v%ju\n", cur.oid.inode, cur.oid.stripe, cur.version);
 #endif
             // We don't flush different parts of history of the same object in parallel
             // So we check if someone is already flushing this object
@@ -416,12 +415,13 @@ stop_flusher:
                 flusher->sync_to_repeat.erase(cur.oid);
                 if (!flusher->try_find_other(dirty_end, cur))
                 {
+                    cur.oid = {};
                     goto stop_flusher;
                 }
             }
         }
 #ifdef BLOCKSTORE_DEBUG
-        printf("Flushing %lx:%lx v%lu\n", cur.oid.inode, cur.oid.stripe, cur.version);
+        printf("Flushing %jx:%jx v%ju\n", cur.oid.inode, cur.oid.stripe, cur.version);
 #endif
         flusher->active_flushers++;
         // Find it in clean_db
@@ -448,7 +448,7 @@ stop_flusher:
                 // Object not allocated. This is a bug.
                 char err[1024];
                 snprintf(
-                    err, 1024, "BUG: Object %lx:%lx v%lu that we are trying to flush is not allocated on the data device",
+                    err, 1024, "BUG: Object %jx:%jx v%ju that we are trying to flush is not allocated on the data device",
                     cur.oid.inode, cur.oid.stripe, cur.version
                 );
                 throw std::runtime_error(err);
@@ -538,7 +538,7 @@ resume_2:
                 clean_disk_entry *old_entry = (clean_disk_entry*)((uint8_t*)meta_old.buf + meta_old.pos*bs->dsk.clean_entry_size);
                 if (old_entry->oid.inode != 0 && old_entry->oid != cur.oid)
                 {
-                    printf("Fatal error (metadata corruption or bug): tried to wipe metadata entry %lu (%lx:%lx v%lu) as old location of %lx:%lx\n",
+                    printf("Fatal error (metadata corruption or bug): tried to wipe metadata entry %ju (%jx:%jx v%ju) as old location of %jx:%jx\n",
                         old_clean_loc >> bs->dsk.block_order, old_entry->oid.inode, old_entry->oid.stripe,
                         old_entry->version, cur.oid.inode, cur.oid.stripe);
                     exit(1);
@@ -571,7 +571,7 @@ resume_2:
         // Erase dirty_db entries
         bs->erase_dirty(dirty_start, std::next(dirty_end), clean_loc);
 #ifdef BLOCKSTORE_DEBUG
-        printf("Flushed %lx:%lx v%lu (%d copies, wr:%d, del:%d), %ld left\n", cur.oid.inode, cur.oid.stripe, cur.version,
+        printf("Flushed %jx:%jx v%ju (%d copies, wr:%d, del:%d), %jd left\n", cur.oid.inode, cur.oid.stripe, cur.version,
             copy_count, has_writes, has_delete, flusher->flush_queue.size());
 #endif
     release_oid:
@@ -584,7 +584,8 @@ resume_2:
         flusher->sync_to_repeat.erase(repeat_it);
     trim_journal:
         // Clear unused part of the journal every <journal_trim_interval> flushes
-        if (!((++flusher->journal_trim_counter) % flusher->journal_trim_interval) || flusher->trim_wanted > 0)
+        if (bs->journal_trim_interval && !((++flusher->journal_trim_counter) % bs->journal_trim_interval) ||
+            flusher->trim_wanted > 0)
         {
     resume_26:
     resume_27:
@@ -609,8 +610,8 @@ void journal_flusher_co::update_metadata_entry()
     {
         printf(
             has_delete
-                ? "Fatal error (metadata corruption or bug): tried to delete metadata entry %lu (%lx:%lx v%lu) while deleting %lx:%lx v%lu\n"
-                : "Fatal error (metadata corruption or bug): tried to overwrite non-zero metadata entry %lu (%lx:%lx v%lu) with %lx:%lx v%lu\n",
+                ? "Fatal error (metadata corruption or bug): tried to delete metadata entry %ju (%jx:%jx v%ju) while deleting %jx:%jx v%ju\n"
+                : "Fatal error (metadata corruption or bug): tried to overwrite non-zero metadata entry %ju (%jx:%jx v%ju) with %jx:%jx v%ju\n",
             clean_loc >> bs->dsk.block_order, new_entry->oid.inode, new_entry->oid.stripe,
             new_entry->version, cur.oid.inode, cur.oid.stripe, cur.version
         );
@@ -710,7 +711,7 @@ bool journal_flusher_co::write_meta_block(flusher_meta_write_t & meta_block, int
     if (wait_state == wait_base)
         goto resume_0;
     await_sqe(0);
-    data->iov = (struct iovec){ meta_block.buf, bs->dsk.meta_block_size };
+    data->iov = (struct iovec){ meta_block.buf, (size_t)bs->dsk.meta_block_size };
     data->callback = simple_callback_w;
     my_uring_prep_writev(
         sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + bs->dsk.meta_block_size + meta_block.sector
@@ -760,7 +761,7 @@ bool journal_flusher_co::clear_incomplete_csum_block_bits(int wait_base)
         {
             // If we encounter bad checksums during flush, we still update the bad block,
             // but intentionally mangle checksums to avoid hiding the corruption.
-            iovec iov = { .iov_base = v[i].buf, .iov_len = v[i].len };
+            iovec iov = { .iov_base = v[i].buf, .iov_len = (size_t)v[i].len };
             if (!(v[i].copy_flags & COPY_BUF_JOURNAL))
             {
                 assert(!(v[i].offset % bs->dsk.csum_block_size));
@@ -768,7 +769,7 @@ bool journal_flusher_co::clear_incomplete_csum_block_bits(int wait_base)
                 bs->verify_padded_checksums(new_clean_bitmap, new_clean_bitmap + 2*bs->dsk.clean_entry_bitmap_size,
                     v[i].offset, &iov, 1, [&](uint32_t bad_block, uint32_t calc_csum, uint32_t stored_csum)
                 {
-                    printf("Checksum mismatch in object %lx:%lx v%lu in data area at offset 0x%lx+0x%x: got %08x, expected %08x\n",
+                    printf("Checksum mismatch in object %jx:%jx v%ju in data area at offset 0x%jx+0x%x: got %08x, expected %08x\n",
                         cur.oid.inode, cur.oid.stripe, old_clean_ver, old_clean_loc, bad_block, calc_csum, stored_csum);
                     for (uint32_t j = 0; j < bs->dsk.csum_block_size; j += bs->dsk.bitmap_granularity)
                     {
@@ -781,7 +782,7 @@ bool journal_flusher_co::clear_incomplete_csum_block_bits(int wait_base)
             {
                 bs->verify_journal_checksums(v[i].csum_buf, v[i].offset, &iov, 1, [&](uint32_t bad_block, uint32_t calc_csum, uint32_t stored_csum)
                 {
-                    printf("Checksum mismatch in object %lx:%lx v%lu in journal at offset 0x%lx+0x%x (block offset 0x%lx): got %08x, expected %08x\n",
+                    printf("Checksum mismatch in object %jx:%jx v%ju in journal at offset 0x%jx+0x%x (block offset 0x%jx): got %08x, expected %08x\n",
                         cur.oid.inode, cur.oid.stripe, old_clean_ver,
                         v[i].disk_offset, bad_block, v[i].offset, calc_csum, stored_csum);
                     bad_block += (v[i].offset/bs->dsk.csum_block_size) * bs->dsk.csum_block_size;
@@ -805,7 +806,7 @@ bool journal_flusher_co::clear_incomplete_csum_block_bits(int wait_base)
             if (new_entry->oid != cur.oid)
             {
                 printf(
-                    "Fatal error (metadata corruption or bug): tried to make holes in %lu (%lx:%lx v%lu) with %lx:%lx v%lu\n",
+                    "Fatal error (metadata corruption or bug): tried to make holes in %ju (%jx:%jx v%ju) with %jx:%jx v%ju\n",
                     clean_loc >> bs->dsk.block_order, new_entry->oid.inode, new_entry->oid.stripe,
                     new_entry->version, cur.oid.inode, cur.oid.stripe, cur.version
                 );
@@ -925,7 +926,7 @@ void journal_flusher_co::scan_dirty()
         {
             char err[1024];
             snprintf(
-                err, 1024, "BUG: Unexpected dirty_entry %lx:%lx v%lu unstable state during flush: 0x%x",
+                err, 1024, "BUG: Unexpected dirty_entry %jx:%jx v%ju unstable state during flush: 0x%x",
                 dirty_it->first.oid.inode, dirty_it->first.oid.stripe, dirty_it->first.version, dirty_it->second.state
             );
             throw std::runtime_error(err);
@@ -1021,7 +1022,7 @@ void journal_flusher_co::scan_dirty()
             // May happen if the metadata entry is corrupt, but journal isn't
             // FIXME: Report corrupted object to the upper layer (OSD)
             printf(
-                "Warning: object %lx:%lx has overwrites, but doesn't have a clean version."
+                "Warning: object %jx:%jx has overwrites, but doesn't have a clean version."
                 " Metadata is likely corrupted. Dropping object from the DB.\n",
                 cur.oid.inode, cur.oid.stripe
             );
@@ -1056,7 +1057,7 @@ void journal_flusher_co::scan_dirty()
         flusher->enqueue_flush(cur);
         cur.version = dirty_end->first.version;
 #ifdef BLOCKSTORE_DEBUG
-        printf("Partial checksum block overwrites found - rewinding flush back to %lx:%lx v%lu\n", cur.oid.inode, cur.oid.stripe, cur.version);
+        printf("Partial checksum block overwrites found - rewinding flush back to %jx:%jx v%ju\n", cur.oid.inode, cur.oid.stripe, cur.version);
 #endif
         v.clear();
         copy_count = 0;
@@ -1084,7 +1085,7 @@ bool journal_flusher_co::read_dirty(int wait_base)
         auto & vi = v[v.size()-i];
         assert(vi.len != 0);
         vi.buf = memalign_or_die(MEM_ALIGNMENT, vi.len);
-        data->iov = (struct iovec){ vi.buf, vi.len };
+        data->iov = (struct iovec){ vi.buf, (size_t)vi.len };
         data->callback = simple_callback_r;
         my_uring_prep_readv(
             sqe, bs->dsk.data_fd, &data->iov, 1, bs->dsk.data_offset + old_clean_loc + vi.offset
@@ -1208,7 +1209,7 @@ bool journal_flusher_co::modify_meta_read(uint64_t meta_loc, flusher_meta_write_
             .usage_count = 1,
         }).first;
         await_sqe(0);
-        data->iov = (struct iovec){ wr.it->second.buf, bs->dsk.meta_block_size };
+        data->iov = (struct iovec){ wr.it->second.buf, (size_t)bs->dsk.meta_block_size };
         data->callback = simple_callback_r;
         wr.submitted = true;
         my_uring_prep_readv(
@@ -1247,7 +1248,7 @@ void journal_flusher_co::free_data_blocks()
         auto uo_it = bs->used_clean_objects.find(old_clean_loc);
         bool used = uo_it != bs->used_clean_objects.end();
 #ifdef BLOCKSTORE_DEBUG
-        printf("%s block %lu from %lx:%lx v%lu (new location is %lu)\n",
+        printf("%s block %ju from %jx:%jx v%ju (new location is %ju)\n",
             used ? "Postpone free" : "Free",
             old_clean_loc >> bs->dsk.block_order,
             cur.oid.inode, cur.oid.stripe, cur.version,
@@ -1264,7 +1265,7 @@ void journal_flusher_co::free_data_blocks()
         auto uo_it = bs->used_clean_objects.find(old_clean_loc);
         bool used = uo_it != bs->used_clean_objects.end();
 #ifdef BLOCKSTORE_DEBUG
-        printf("%s block %lu from %lx:%lx v%lu (delete)\n",
+        printf("%s block %ju from %jx:%jx v%ju (delete)\n",
             used ? "Postpone free" : "Free",
             old_clean_loc >> bs->dsk.block_order,
             cur.oid.inode, cur.oid.stripe, cur.version);
@@ -1346,7 +1347,6 @@ bool journal_flusher_co::trim_journal(int wait_base)
     else if (wait_state == wait_base+2) goto resume_2;
     else if (wait_state == wait_base+3) goto resume_3;
     else if (wait_state == wait_base+4) goto resume_4;
-    flusher->journal_trim_counter = 0;
     new_trim_pos = bs->journal.get_trim_pos();
     if (new_trim_pos != bs->journal.used_start)
     {
@@ -1378,7 +1378,7 @@ bool journal_flusher_co::trim_journal(int wait_base)
                 .csum_block_size = bs->dsk.csum_block_size,
             };
             ((journal_entry_start*)flusher->journal_superblock)->crc32 = je_crc32((journal_entry*)flusher->journal_superblock);
-            data->iov = (struct iovec){ flusher->journal_superblock, bs->dsk.journal_block_size };
+            data->iov = (struct iovec){ flusher->journal_superblock, (size_t)bs->dsk.journal_block_size };
             data->callback = simple_callback_w;
             my_uring_prep_writev(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset);
             wait_count++;
@@ -1410,7 +1410,7 @@ bool journal_flusher_co::trim_journal(int wait_base)
             }
             bs->journal.used_start = new_trim_pos;
 #ifdef BLOCKSTORE_DEBUG
-            printf("Journal trimmed to %08lx (next_free=%08lx dirty_start=%08lx)\n", bs->journal.used_start, bs->journal.next_free, bs->journal.dirty_start);
+            printf("Journal trimmed to %08jx (next_free=%08jx dirty_start=%08jx)\n", bs->journal.used_start, bs->journal.next_free, bs->journal.dirty_start);
 #endif
             if (bs->journal.flush_journal && !flusher->flush_queue.size())
             {
@@ -1419,6 +1419,7 @@ bool journal_flusher_co::trim_journal(int wait_base)
                 exit(0);
             }
         }
+        flusher->journal_trim_counter = 0;
         flusher->trimming = false;
     }
     return true;

src/blockstore_flush.h

@@ -107,7 +107,7 @@ class journal_flusher_t
     blockstore_impl_t *bs;
     friend class journal_flusher_co;
 
-    int journal_trim_counter, journal_trim_interval;
+    int journal_trim_counter;
     bool trimming;
     void* journal_superblock;
 

src/blockstore_impl.cpp

@@ -163,20 +163,10 @@ void blockstore_impl_t::loop()
             }
             else if (op->opcode == BS_OP_SYNC)
             {
-                // wait for all small writes to be submitted
-                // wait for all big writes to complete, submit data device fsync
+                // sync only completed writes?
                 // wait for the data device fsync to complete, then submit journal writes for big writes
                 // then submit an fsync operation
-                if (has_writes)
-                {
-                    // Can't submit SYNC before previous writes
-                    continue;
-                }
                 wr_st = continue_sync(op);
-                if (wr_st != 2)
-                {
-                    has_writes = wr_st > 0 ? 1 : 2;
-                }
             }
             else if (op->opcode == BS_OP_STABLE)
             {
@@ -205,6 +195,10 @@ void blockstore_impl_t::loop()
                     // ring is full, stop submission
                     break;
                 }
+                else if (PRIV(op)->wait_for == WAIT_JOURNAL)
+                {
+                    PRIV(op)->wait_detail2 = (unstable_writes.size()+unstable_unsynced);
+                }
             }
         }
         if (op_idx != new_idx)
@@ -275,7 +269,7 @@ void blockstore_impl_t::check_wait(blockstore_op_t *op)
         {
             // stop submission if there's still no free space
 #ifdef BLOCKSTORE_DEBUG
-            printf("Still waiting for %lu SQE(s)\n", PRIV(op)->wait_detail);
+            printf("Still waiting for %ju SQE(s)\n", PRIV(op)->wait_detail);
 #endif
             return;
         }
@@ -283,11 +277,12 @@ void blockstore_impl_t::check_wait(blockstore_op_t *op)
     }
     else if (PRIV(op)->wait_for == WAIT_JOURNAL)
     {
-        if (journal.used_start == PRIV(op)->wait_detail)
+        if (journal.used_start == PRIV(op)->wait_detail &&
+            (unstable_writes.size()+unstable_unsynced) == PRIV(op)->wait_detail2)
         {
             // do not submit
 #ifdef BLOCKSTORE_DEBUG
-            printf("Still waiting to flush journal offset %08lx\n", PRIV(op)->wait_detail);
+            printf("Still waiting to flush journal offset %08jx\n", PRIV(op)->wait_detail);
 #endif
             return;
         }
@@ -558,13 +553,14 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
             if (stable_count >= stable_alloc)
             {
                 stable_alloc *= 2;
-                stable = (obj_ver_id*)realloc(stable, sizeof(obj_ver_id) * stable_alloc);
-                if (!stable)
+                obj_ver_id* nst = (obj_ver_id*)realloc(stable, sizeof(obj_ver_id) * stable_alloc);
+                if (!nst)
                 {
                     op->retval = -ENOMEM;
                     FINISH_OP(op);
                     return;
                 }
+                stable = nst;
             }
             stable[stable_count++] = {
                 .oid = clean_it->first,
@@ -642,8 +638,8 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
                             if (stable_count >= stable_alloc)
                             {
                                 stable_alloc += 32768;
-                                stable = (obj_ver_id*)realloc(stable, sizeof(obj_ver_id) * stable_alloc);
-                                if (!stable)
+                                obj_ver_id *nst = (obj_ver_id*)realloc(stable, sizeof(obj_ver_id) * stable_alloc);
+                                if (!nst)
                                 {
                                     if (unstable)
                                         free(unstable);
@@ -651,6 +647,7 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
                                     FINISH_OP(op);
                                     return;
                                 }
+                                stable = nst;
                             }
                             stable[stable_count++] = dirty_it->first;
                         }
@@ -666,8 +663,8 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
                     if (unstable_count >= unstable_alloc)
                     {
                         unstable_alloc += 32768;
-                        unstable = (obj_ver_id*)realloc(unstable, sizeof(obj_ver_id) * unstable_alloc);
-                        if (!unstable)
+                        obj_ver_id *nst = (obj_ver_id*)realloc(unstable, sizeof(obj_ver_id) * unstable_alloc);
+                        if (!nst)
                         {
                             if (stable)
                                 free(stable);
@@ -675,6 +672,7 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
                             FINISH_OP(op);
                             return;
                         }
+                        unstable = nst;
                     }
                     unstable[unstable_count++] = dirty_it->first;
                 }
@@ -694,8 +692,8 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
     if (stable_count+unstable_count > stable_alloc)
     {
         stable_alloc = stable_count+unstable_count;
-        stable = (obj_ver_id*)realloc(stable, sizeof(obj_ver_id) * stable_alloc);
-        if (!stable)
+        obj_ver_id *nst = (obj_ver_id*)realloc(stable, sizeof(obj_ver_id) * stable_alloc);
+        if (!nst)
         {
             if (unstable)
                 free(unstable);
@@ -703,6 +701,7 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
             FINISH_OP(op);
             return;
         }
+        stable = nst;
     }
     // Copy unstable entries
     for (int i = 0; i < unstable_count; i++)

src/blockstore_impl.h

@@ -55,6 +55,7 @@
 #define IS_JOURNAL(st) (((st) & 0x0F) == BS_ST_SMALL_WRITE)
 #define IS_BIG_WRITE(st) (((st) & 0x0F) == BS_ST_BIG_WRITE)
 #define IS_DELETE(st) (((st) & 0x0F) == BS_ST_DELETE)
+#define IS_INSTANT(st) (((st) & BS_ST_TYPE_MASK) == BS_ST_DELETE || ((st) & BS_ST_INSTANT))
 
 #define BS_SUBMIT_CHECK_SQES(n) \
     if (ringloop->sqes_left() < (n))\
@@ -201,7 +202,7 @@ struct blockstore_op_private_t
 {
     // Wait status
     int wait_for;
-    uint64_t wait_detail;
+    uint64_t wait_detail, wait_detail2;
     int pending_ops;
     int op_state;
 
@@ -252,6 +253,7 @@ class blockstore_impl_t
     bool inmemory_meta = false;
     // Maximum and minimum flusher count
     unsigned max_flusher_count, min_flusher_count;
+    unsigned journal_trim_interval;
     // Maximum queue depth
     unsigned max_write_iodepth = 128;
     // Enable small (journaled) write throttling, useful for the SSD+HDD case
@@ -277,6 +279,7 @@ class blockstore_impl_t
     int unsynced_big_write_count = 0, unstable_unsynced = 0;
     int unsynced_queued_ops = 0;
     allocator *data_alloc = NULL;
+    uint64_t used_blocks = 0;
     uint8_t *zero_object;
 
     void *metadata_buffer = NULL;
@@ -376,7 +379,7 @@ class blockstore_impl_t
     // Stabilize
     int dequeue_stable(blockstore_op_t *op);
     int continue_stable(blockstore_op_t *op);
-    void mark_stable(const obj_ver_id & ov, bool forget_dirty = false);
+    void mark_stable(obj_ver_id ov, bool forget_dirty = false);
     void stabilize_object(object_id oid, uint64_t max_ver);
     blockstore_op_t* selective_sync(blockstore_op_t *op);
     int split_stab_op(blockstore_op_t *op, std::function<int(obj_ver_id v)> decider);
@@ -430,7 +433,7 @@ public:
 
     inline uint32_t get_block_size() { return dsk.data_block_size; }
     inline uint64_t get_block_count() { return dsk.block_count; }
-    inline uint64_t get_free_block_count() { return data_alloc->get_free_count(); }
+    inline uint64_t get_free_block_count() { return dsk.block_count - used_blocks; }
     inline uint32_t get_bitmap_granularity() { return dsk.disk_alignment; }
     inline uint64_t get_journal_size() { return dsk.journal_len; }
 };

src/blockstore_init.cpp

@@ -63,7 +63,7 @@ int blockstore_init_meta::loop()
         throw std::runtime_error("Failed to allocate metadata read buffer");
     // Read superblock
     GET_SQE();
-    data->iov = { metadata_buffer, bs->dsk.meta_block_size };
+    data->iov = { metadata_buffer, (size_t)bs->dsk.meta_block_size };
     data->callback = [this](ring_data_t *data) { handle_event(data, -1); };
     my_uring_prep_readv(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset);
     bs->ringloop->submit();
@@ -100,7 +100,7 @@ resume_1:
         {
             printf("Initializing metadata area\n");
             GET_SQE();
-            data->iov = (struct iovec){ metadata_buffer, bs->dsk.meta_block_size };
+            data->iov = (struct iovec){ metadata_buffer, (size_t)bs->dsk.meta_block_size };
             data->callback = [this](ring_data_t *data) { handle_event(data, -1); };
             my_uring_prep_writev(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset);
             bs->ringloop->submit();
@@ -153,7 +153,7 @@ resume_1:
         else if (hdr->version > BLOCKSTORE_META_FORMAT_V2)
         {
             printf(
-                "Metadata format is too new for me (stored version is %lu, max supported %u).\n",
+                "Metadata format is too new for me (stored version is %ju, max supported %u).\n",
                 hdr->version, BLOCKSTORE_META_FORMAT_V2
             );
             exit(1);
@@ -167,7 +167,7 @@ resume_1:
             printf(
                 "Configuration stored in metadata superblock"
                 " (meta_block_size=%u, data_block_size=%u, bitmap_granularity=%u, data_csum_type=%u, csum_block_size=%u)"
-                " differs from OSD configuration (%lu/%u/%lu, %u/%u).\n",
+                " differs from OSD configuration (%ju/%u/%ju, %u/%u).\n",
                 hdr->meta_block_size, hdr->data_block_size, hdr->bitmap_granularity,
                 hdr->data_csum_type, hdr->csum_block_size,
                 bs->dsk.meta_block_size, bs->dsk.data_block_size, bs->dsk.bitmap_granularity,
@@ -199,7 +199,8 @@ resume_2:
                 submitted++;
                 next_offset += bufs[i].size;
                 GET_SQE();
-                data->iov = { bufs[i].buf, bufs[i].size };
+                assert(bufs[i].size <= 0x7fffffff);
+                data->iov = { bufs[i].buf, (size_t)bufs[i].size };
                 data->callback = [this, i](ring_data_t *data) { handle_event(data, i); };
                 if (!zero_on_init)
                     my_uring_prep_readv(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + bufs[i].offset);
@@ -231,7 +232,8 @@ resume_2:
             {
                 // write the modified buffer back
                 GET_SQE();
-                data->iov = { bufs[i].buf, bufs[i].size };
+                assert(bufs[i].size <= 0x7fffffff);
+                data->iov = { bufs[i].buf, (size_t)bufs[i].size };
                 data->callback = [this, i](ring_data_t *data) { handle_event(data, i); };
                 my_uring_prep_writev(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + bufs[i].offset);
                 bufs[i].state = INIT_META_WRITING;
@@ -257,7 +259,7 @@ resume_2:
             next_offset = entries_to_zero[i]/entries_per_block;
             for (j = i; j < entries_to_zero.size() && entries_to_zero[j]/entries_per_block == next_offset; j++) {}
             GET_SQE();
-            data->iov = { metadata_buffer, bs->dsk.meta_block_size };
+            data->iov = { metadata_buffer, (size_t)bs->dsk.meta_block_size };
             data->callback = [this](ring_data_t *data) { handle_event(data, -1); };
             my_uring_prep_readv(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + (1+next_offset)*bs->dsk.meta_block_size);
             submitted++;
@@ -273,7 +275,7 @@ resume_5:
                 memset((uint8_t*)metadata_buffer + pos*bs->dsk.clean_entry_size, 0, bs->dsk.clean_entry_size);
             }
             GET_SQE();
-            data->iov = { metadata_buffer, bs->dsk.meta_block_size };
+            data->iov = { metadata_buffer, (size_t)bs->dsk.meta_block_size };
             data->callback = [this](ring_data_t *data) { handle_event(data, -1); };
             my_uring_prep_writev(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + (1+next_offset)*bs->dsk.meta_block_size);
             submitted++;
@@ -287,7 +289,7 @@ resume_6:
         entries_to_zero.clear();
     }
     // metadata read finished
-    printf("Metadata entries loaded: %lu, free blocks: %lu / %lu\n", entries_loaded, bs->data_alloc->get_free_count(), bs->dsk.block_count);
+    printf("Metadata entries loaded: %ju, free blocks: %ju / %ju\n", entries_loaded, bs->data_alloc->get_free_count(), bs->dsk.block_count);
     if (!bs->inmemory_meta)
     {
         free(metadata_buffer);
@@ -328,7 +330,7 @@ bool blockstore_init_meta::handle_meta_block(uint8_t *buf, uint64_t entries_per_
                 uint32_t *entry_csum = (uint32_t*)((uint8_t*)entry + bs->dsk.clean_entry_size - 4);
                 if (*entry_csum != crc32c(0, entry, bs->dsk.clean_entry_size - 4))
                 {
-                    printf("Metadata entry %lu is corrupt (checksum mismatch), skipping\n", done_cnt+i);
+                    printf("Metadata entry %ju is corrupt (checksum mismatch), skipping\n", done_cnt+i);
                     continue;
                 }
             }
@@ -366,7 +368,7 @@ bool blockstore_init_meta::handle_meta_block(uint8_t *buf, uint64_t entries_per_
                         entries_to_zero.push_back(clean_it->second.location >> bs->dsk.block_order);
                     }
 #ifdef BLOCKSTORE_DEBUG
-                    printf("Free block %lu from %lx:%lx v%lu (new location is %lu)\n",
+                    printf("Free block %ju from %jx:%jx v%ju (new location is %ju)\n",
                         old_clean_loc,
                         clean_it->first.inode, clean_it->first.stripe, clean_it->second.version,
                         done_cnt+i);
@@ -376,10 +378,11 @@ bool blockstore_init_meta::handle_meta_block(uint8_t *buf, uint64_t entries_per_
                 else
                 {
                     bs->inode_space_stats[entry->oid.inode] += bs->dsk.data_block_size;
+                    bs->used_blocks++;
                 }
                 entries_loaded++;
 #ifdef BLOCKSTORE_DEBUG
-                printf("Allocate block (clean entry) %lu: %lx:%lx v%lu\n", done_cnt+i, entry->oid.inode, entry->oid.stripe, entry->version);
+                printf("Allocate block (clean entry) %ju: %jx:%jx v%ju\n", done_cnt+i, entry->oid.inode, entry->oid.stripe, entry->version);
 #endif
                 bs->data_alloc->set(done_cnt+i, true);
                 clean_db[entry->oid] = (struct clean_entry){
@@ -393,7 +396,7 @@ bool blockstore_init_meta::handle_meta_block(uint8_t *buf, uint64_t entries_per_
                 updated = true;
                 memset(entry, 0, bs->dsk.clean_entry_size);
 #ifdef BLOCKSTORE_DEBUG
-                printf("Old clean entry %lu: %lx:%lx v%lu\n", done_cnt+i, entry->oid.inode, entry->oid.stripe, entry->version);
+                printf("Old clean entry %ju: %jx:%jx v%ju\n", done_cnt+i, entry->oid.inode, entry->oid.stripe, entry->version);
 #endif
             }
         }
@@ -465,7 +468,7 @@ int blockstore_init_journal::loop()
     if (!sqe)
         throw std::runtime_error("io_uring is full while trying to read journal");
     data = ((ring_data_t*)sqe->user_data);
-    data->iov = { submitted_buf, bs->journal.block_size };
+    data->iov = { submitted_buf, (size_t)bs->journal.block_size };
     data->callback = simple_callback;
     my_uring_prep_readv(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset);
     bs->ringloop->submit();
@@ -506,7 +509,7 @@ resume_1:
             // FIXME: Randomize initial crc32. Track crc32 when trimming.
             printf("Resetting journal\n");
             GET_SQE();
-            data->iov = (struct iovec){ submitted_buf, 2*bs->journal.block_size };
+            data->iov = (struct iovec){ submitted_buf, (size_t)(2*bs->journal.block_size) };
             data->callback = simple_callback;
             my_uring_prep_writev(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset);
             wait_count++;
@@ -556,7 +559,7 @@ resume_1:
             (je_start->version != JOURNAL_VERSION_V2 || je_start->size != JE_START_V2_SIZE && je_start->size != JE_START_V1_SIZE))
         {
             fprintf(
-                stderr, "The code only supports journal versions 2 and 1, but it is %lu on disk."
+                stderr, "The code only supports journal versions 2 and 1, but it is %ju on disk."
                     " Please use vitastor-disk to rewrite the journal\n",
                 je_start->size == JE_START_V0_SIZE ? 0 : je_start->version
             );
@@ -605,7 +608,7 @@ resume_1:
                     submitted_buf = (uint8_t*)bs->journal.buffer + journal_pos;
                 data->iov = {
                     submitted_buf,
-                    end - journal_pos < JOURNAL_BUFFER_SIZE ? end - journal_pos : JOURNAL_BUFFER_SIZE,
+                    (size_t)(end - journal_pos < JOURNAL_BUFFER_SIZE ? end - journal_pos : JOURNAL_BUFFER_SIZE),
                 };
                 data->callback = [this](ring_data_t *data1) { handle_event(data1); };
                 my_uring_prep_readv(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset + journal_pos);
@@ -621,7 +624,7 @@ resume_1:
                     if (init_write_buf && !bs->readonly)
                     {
                         GET_SQE();
-                        data->iov = { init_write_buf, bs->journal.block_size };
+                        data->iov = { init_write_buf, (size_t)bs->journal.block_size };
                         data->callback = simple_callback;
                         my_uring_prep_writev(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset + init_write_sector);
                         wait_count++;
@@ -690,7 +693,7 @@ resume_1:
             IS_BIG_WRITE(dirty_it->second.state) &&
             dirty_it->second.location == UINT64_MAX)
         {
-            printf("Fatal error (bug): %lx:%lx v%lu big_write journal_entry was allocated over another object\n",
+            printf("Fatal error (bug): %jx:%jx v%ju big_write journal_entry was allocated over another object\n",
                 dirty_it->first.oid.inode, dirty_it->first.oid.stripe, dirty_it->first.version);
             exit(1);
         }
@@ -698,7 +701,7 @@ resume_1:
     bs->flusher->mark_trim_possible();
     bs->journal.dirty_start = bs->journal.next_free;
     printf(
-        "Journal entries loaded: %lu, free journal space: %lu bytes (%08lx..%08lx is used), free blocks: %lu / %lu\n",
+        "Journal entries loaded: %ju, free journal space: %ju bytes (%08jx..%08jx is used), free blocks: %ju / %ju\n",
         entries_loaded,
         (bs->journal.next_free >= bs->journal.used_start
             ? bs->journal.len-bs->journal.block_size - (bs->journal.next_free-bs->journal.used_start)
@@ -753,7 +756,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
             {
 #ifdef BLOCKSTORE_DEBUG
                 printf(
-                    "je_small_write%s oid=%lx:%lx ver=%lu offset=%u len=%u\n",
+                    "je_small_write%s oid=%jx:%jx ver=%ju offset=%u len=%u\n",
                     je->type == JE_SMALL_WRITE_INSTANT ? "_instant" : "",
                     je->small_write.oid.inode, je->small_write.oid.stripe, je->small_write.version,
                     je->small_write.offset, je->small_write.len
@@ -775,7 +778,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                 if (location != je->small_write.data_offset)
                 {
                     char err[1024];
-                    snprintf(err, 1024, "BUG: calculated journal data offset (%08lx) != stored journal data offset (%08lx)", location, je->small_write.data_offset);
+                    snprintf(err, 1024, "BUG: calculated journal data offset (%08jx) != stored journal data offset (%08jx)", location, je->small_write.data_offset);
                     throw std::runtime_error(err);
                 }
                 small_write_data.clear();
@@ -802,7 +805,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                             covered += part_end - part_begin;
                             small_write_data.push_back((iovec){
                                 .iov_base = (uint8_t*)done[i].buf + part_begin - done[i].pos,
-                                .iov_len = part_end - part_begin,
+                                .iov_len = (size_t)(part_end - part_begin),
                             });
                         }
                     }
@@ -825,7 +828,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                     if (!data_csum_valid)
                     {
                         printf(
-                            "Journal entry data is corrupt for small_write%s oid=%lx:%lx ver=%lu offset=%u len=%u - data crc32 %x != %x\n",
+                            "Journal entry data is corrupt for small_write%s oid=%jx:%jx ver=%ju offset=%u len=%u - data crc32 %x != %x\n",
                             je->type == JE_SMALL_WRITE_INSTANT ? "_instant" : "",
                             je->small_write.oid.inode, je->small_write.oid.stripe, je->small_write.version,
                             je->small_write.offset, je->small_write.len,
@@ -844,7 +847,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                     if (je->size != required_size)
                     {
                         printf(
-                            "Journal entry data has invalid size for small_write%s oid=%lx:%lx ver=%lu offset=%u len=%u - should be %u bytes but is %u bytes\n",
+                            "Journal entry data has invalid size for small_write%s oid=%jx:%jx ver=%ju offset=%u len=%u - should be %u bytes but is %u bytes\n",
                             je->type == JE_SMALL_WRITE_INSTANT ? "_instant" : "",
                             je->small_write.oid.inode, je->small_write.oid.stripe, je->small_write.version,
                             je->small_write.offset, je->small_write.len,
@@ -892,7 +895,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                             if (block_crc32 != *block_csums)
                             {
                                 printf(
-                                    "Journal entry data is corrupt for small_write%s oid=%lx:%lx ver=%lu offset=%u len=%u - block %u crc32 %x != %x\n",
+                                    "Journal entry data is corrupt for small_write%s oid=%jx:%jx ver=%ju offset=%u len=%u - block %u crc32 %x != %x\n",
                                     je->type == JE_SMALL_WRITE_INSTANT ? "_instant" : "",
                                     je->small_write.oid.inode, je->small_write.oid.stripe, je->small_write.version,
                                     je->small_write.offset, je->small_write.len,
@@ -955,7 +958,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                     bs->journal.used_sectors[proc_pos]++;
 #ifdef BLOCKSTORE_DEBUG
                     printf(
-                        "journal offset %08lx is used by %lx:%lx v%lu (%lu refs)\n",
+                        "journal offset %08jx is used by %jx:%jx v%ju (%ju refs)\n",
                         proc_pos, ov.oid.inode, ov.oid.stripe, ov.version, bs->journal.used_sectors[proc_pos]
                     );
 #endif
@@ -971,7 +974,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
             {
 #ifdef BLOCKSTORE_DEBUG
                 printf(
-                    "je_big_write%s oid=%lx:%lx ver=%lu loc=%lu\n",
+                    "je_big_write%s oid=%jx:%jx ver=%ju loc=%ju\n",
                     je->type == JE_BIG_WRITE_INSTANT ? "_instant" : "",
                     je->big_write.oid.inode, je->big_write.oid.stripe, je->big_write.version, je->big_write.location >> bs->dsk.block_order
                 );
@@ -1048,7 +1051,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                     {
 #ifdef BLOCKSTORE_DEBUG
                         printf(
-                            "Allocate block (journal) %lu: %lx:%lx v%lu\n",
+                            "Allocate block (journal) %ju: %jx:%jx v%ju\n",
                             je->big_write.location >> bs->dsk.block_order,
                             ov.oid.inode, ov.oid.stripe, ov.version
                         );
@@ -1058,7 +1061,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                     bs->journal.used_sectors[proc_pos]++;
 #ifdef BLOCKSTORE_DEBUG
                     printf(
-                        "journal offset %08lx is used by %lx:%lx v%lu (%lu refs)\n",
+                        "journal offset %08jx is used by %jx:%jx v%ju (%ju refs)\n",
                         proc_pos, ov.oid.inode, ov.oid.stripe, ov.version, bs->journal.used_sectors[proc_pos]
                     );
 #endif
@@ -1073,7 +1076,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
             else if (je->type == JE_STABLE)
             {
 #ifdef BLOCKSTORE_DEBUG
-                printf("je_stable oid=%lx:%lx ver=%lu\n", je->stable.oid.inode, je->stable.oid.stripe, je->stable.version);
+                printf("je_stable oid=%jx:%jx ver=%ju\n", je->stable.oid.inode, je->stable.oid.stripe, je->stable.version);
 #endif
                 // oid, version
                 obj_ver_id ov = {
@@ -1085,7 +1088,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
             else if (je->type == JE_ROLLBACK)
             {
 #ifdef BLOCKSTORE_DEBUG
-                printf("je_rollback oid=%lx:%lx ver=%lu\n", je->rollback.oid.inode, je->rollback.oid.stripe, je->rollback.version);
+                printf("je_rollback oid=%jx:%jx ver=%ju\n", je->rollback.oid.inode, je->rollback.oid.stripe, je->rollback.version);
 #endif
                 // rollback dirty writes of <oid> up to <version>
                 obj_ver_id ov = {
@@ -1097,7 +1100,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
             else if (je->type == JE_DELETE)
             {
 #ifdef BLOCKSTORE_DEBUG
-                printf("je_delete oid=%lx:%lx ver=%lu\n", je->del.oid.inode, je->del.oid.stripe, je->del.version);
+                printf("je_delete oid=%jx:%jx ver=%ju\n", je->del.oid.inode, je->del.oid.stripe, je->del.version);
 #endif
                 bool dirty_exists = false;
                 auto dirty_it = bs->dirty_db.upper_bound((obj_ver_id){
@@ -1181,6 +1184,7 @@ void blockstore_init_journal::erase_dirty_object(blockstore_dirty_db_t::iterator
             sp -= bs->dsk.data_block_size;
         else
             bs->inode_space_stats.erase(oid.inode);
+        bs->used_blocks--;
     }
     bs->erase_dirty(dirty_it, dirty_end, clean_loc);
     // Remove it from the flusher's queue, too

src/blockstore_journal.cpp

@@ -90,8 +90,8 @@ int blockstore_journal_check_t::check_available(blockstore_op_t *op, int entries
             }
             // In fact, it's even more rare than "ran out of journal space", so print a warning
             printf(
-                "Ran out of journal sector buffers: %d/%lu buffers used (%d dirty), next buffer (%ld)"
-                " is %s and flushed %lu times. Consider increasing \'journal_sector_buffer_count\'\n",
+                "Ran out of journal sector buffers: %d/%ju buffers used (%d dirty), next buffer (%jd)"
+                " is %s and flushed %ju times. Consider increasing \'journal_sector_buffer_count\'\n",
                 used, bs->journal.sector_count, dirty, next_sector,
                 bs->journal.sector_info[next_sector].dirty ? "dirty" : "not dirty",
                 bs->journal.sector_info[next_sector].flush_count
@@ -103,7 +103,7 @@ int blockstore_journal_check_t::check_available(blockstore_op_t *op, int entries
     if (data_after > 0)
     {
         next_pos = next_pos + data_after;
-        if (next_pos > bs->journal.len)
+        if (next_pos >= bs->journal.len)
         {
             if (right_dir)
                 next_pos = bs->journal.block_size + data_after;
@@ -114,7 +114,7 @@ int blockstore_journal_check_t::check_available(blockstore_op_t *op, int entries
     {
         // No space in the journal. Wait until used_start changes.
         printf(
-            "Ran out of journal space (used_start=%08lx, next_free=%08lx, dirty_start=%08lx)\n",
+            "Ran out of journal space (used_start=%08jx, next_free=%08jx, dirty_start=%08jx)\n",
             bs->journal.used_start, bs->journal.next_free, bs->journal.dirty_start
         );
         PRIV(op)->wait_for = WAIT_JOURNAL;
@@ -146,7 +146,7 @@ journal_entry* prefill_single_journal_entry(journal_t & journal, uint16_t type,
         journal.in_sector_pos = 0;
         auto next_next_free = (journal.next_free+journal.block_size) < journal.len ? journal.next_free + journal.block_size : journal.block_size;
         // double check that next_free doesn't cross used_start from the left
-        assert(journal.next_free >= journal.used_start || next_next_free < journal.used_start);
+        assert(journal.next_free >= journal.used_start && next_next_free >= journal.next_free || next_next_free < journal.used_start);
         journal.next_free = next_next_free;
         memset(journal.inmemory
             ? (uint8_t*)journal.buffer + journal.sector_info[journal.cur_sector].offset
@@ -183,7 +183,7 @@ void blockstore_impl_t::prepare_journal_sector_write(int cur_sector, blockstore_
             (journal.inmemory
                 ? (uint8_t*)journal.buffer + journal.sector_info[cur_sector].offset
                 : (uint8_t*)journal.sector_buf + journal.block_size*cur_sector),
-            journal.block_size
+            (size_t)journal.block_size
         };
         data->callback = [this, flush_id = journal.submit_id](ring_data_t *data) { handle_journal_write(data, flush_id); };
         my_uring_prep_writev(
@@ -263,7 +263,7 @@ uint64_t journal_t::get_trim_pos()
             // next_free does not need updating during trim
 #ifdef BLOCKSTORE_DEBUG
             printf(
-                "Trimming journal (used_start=%08lx, next_free=%08lx, dirty_start=%08lx, new_start=%08lx, new_refcount=%ld)\n",
+                "Trimming journal (used_start=%08jx, next_free=%08jx, dirty_start=%08jx, new_start=%08jx, new_refcount=%jd)\n",
                 used_start, next_free, dirty_start,
                 journal_used_it->first, journal_used_it->second
             );
@@ -276,7 +276,7 @@ uint64_t journal_t::get_trim_pos()
         // Journal is cleared up to <journal_used_it>
 #ifdef BLOCKSTORE_DEBUG
         printf(
-            "Trimming journal (used_start=%08lx, next_free=%08lx, dirty_start=%08lx, new_start=%08lx, new_refcount=%ld)\n",
+            "Trimming journal (used_start=%08jx, next_free=%08jx, dirty_start=%08jx, new_start=%08jx, new_refcount=%jd)\n",
             used_start, next_free, dirty_start,
             journal_used_it->first, journal_used_it->second
         );
@@ -296,7 +296,7 @@ void journal_t::dump_diagnostics()
         journal_used_it = used_sectors.begin();
     }
     printf(
-        "Journal: used_start=%08lx next_free=%08lx dirty_start=%08lx trim_to=%08lx trim_to_refs=%ld\n",
+        "Journal: used_start=%08jx next_free=%08jx dirty_start=%08jx trim_to=%08jx trim_to_refs=%jd\n",
         used_start, next_free, dirty_start,
         journal_used_it == used_sectors.end() ? 0 : journal_used_it->first,
         journal_used_it == used_sectors.end() ? 0 : journal_used_it->second

src/blockstore_open.cpp

@@ -13,13 +13,14 @@ void blockstore_impl_t::parse_config(blockstore_config_t & config, bool init)
         max_flusher_count = strtoull(config["flusher_count"].c_str(), NULL, 10);
     }
     min_flusher_count = strtoull(config["min_flusher_count"].c_str(), NULL, 10);
+    journal_trim_interval = strtoull(config["journal_trim_interval"].c_str(), NULL, 10);
     max_write_iodepth = strtoull(config["max_write_iodepth"].c_str(), NULL, 10);
     throttle_small_writes = config["throttle_small_writes"] == "true" || config["throttle_small_writes"] == "1" || config["throttle_small_writes"] == "yes";
     throttle_target_iops = strtoull(config["throttle_target_iops"].c_str(), NULL, 10);
     throttle_target_mbs = strtoull(config["throttle_target_mbs"].c_str(), NULL, 10);
     throttle_target_parallelism = strtoull(config["throttle_target_parallelism"].c_str(), NULL, 10);
     throttle_threshold_us = strtoull(config["throttle_threshold_us"].c_str(), NULL, 10);
-    if (config.find("autosync_writes") != config.end())
+    if (config["autosync_writes"] != "")
     {
         autosync_writes = strtoull(config["autosync_writes"].c_str(), NULL, 10);
     }
@@ -31,6 +32,10 @@ void blockstore_impl_t::parse_config(blockstore_config_t & config, bool init)
     {
         min_flusher_count = 1;
     }
+    if (!journal_trim_interval)
+    {
+        journal_trim_interval = 512;
+    }
     if (!max_write_iodepth)
     {
         max_write_iodepth = 128;

src/blockstore_read.cpp

@@ -25,7 +25,7 @@ int blockstore_impl_t::fulfill_read_push(blockstore_op_t *op, void *buf, uint64_
         return 1;
     }
     BS_SUBMIT_GET_SQE(sqe, data);
-    data->iov = (struct iovec){ buf, len };
+    data->iov = (struct iovec){ buf, (size_t)len };
     PRIV(op)->pending_ops++;
     my_uring_prep_readv(
         sqe,
@@ -505,7 +505,7 @@ int blockstore_impl_t::dequeue_read(blockstore_op_t *read_op)
         for (auto & rv: PRIV(read_op)->read_vec)
         {
             if (rv.journal_sector)
-                journal.used_sectors[rv.journal_sector-1]++;
+                journal.used_sectors.at(rv.journal_sector-1)++;
         }
     }
     read_op->retval = 0;
@@ -700,7 +700,7 @@ uint8_t* blockstore_impl_t::read_clean_meta_block(blockstore_op_t *op, uint64_t
         .buf = buf,
     });
     BS_SUBMIT_GET_SQE(sqe, data);
-    data->iov = (struct iovec){ buf, dsk.meta_block_size };
+    data->iov = (struct iovec){ buf, (size_t)dsk.meta_block_size };
     PRIV(op)->pending_ops++;
     my_uring_prep_readv(sqe, dsk.meta_fd, &data->iov, 1, dsk.meta_offset + dsk.meta_block_size + sector);
     data->callback = [this, op](ring_data_t *data) { handle_read_event(data, op); };
@@ -855,7 +855,7 @@ void blockstore_impl_t::handle_read_event(ring_data_t *data, blockstore_op_t *op
                             {
                                 ok = false;
                                 printf(
-                                    "Checksum mismatch in object %lx:%lx v%lu in journal at 0x%lx, checksum block #%u: got %08x, expected %08x\n",
+                                    "Checksum mismatch in object %jx:%jx v%ju in journal at 0x%jx, checksum block #%u: got %08x, expected %08x\n",
                                     op->oid.inode, op->oid.stripe, op->version,
                                     rv[i].disk_offset, bad_block / dsk.csum_block_size, calc_csum, stored_csum
                                 );
@@ -875,7 +875,7 @@ void blockstore_impl_t::handle_read_event(ring_data_t *data, blockstore_op_t *op
                                 {
                                     ok = false;
                                     printf(
-                                        "Checksum mismatch in object %lx:%lx v%lu in %s data at 0x%lx, checksum block #%u: got %08x, expected %08x\n",
+                                        "Checksum mismatch in object %jx:%jx v%ju in %s data at 0x%jx, checksum block #%u: got %08x, expected %08x\n",
                                         op->oid.inode, op->oid.stripe, op->version,
                                         (rv[i].copy_flags & COPY_BUF_JOURNALED_BIG ? "redirect-write" : "clean"),
                                         rv[i].disk_offset, bad_block / dsk.csum_block_size, calc_csum, stored_csum
@@ -918,7 +918,7 @@ void blockstore_impl_t::handle_read_event(ring_data_t *data, blockstore_op_t *op
                             {
                                 // checksum error
                                 printf(
-                                    "Checksum mismatch in object %lx:%lx v%lu in %s area at offset 0x%lx+0x%lx: %08x vs %08x\n",
+                                    "Checksum mismatch in object %jx:%jx v%ju in %s area at offset 0x%jx+0x%zx: %08x vs %08x\n",
                                     op->oid.inode, op->oid.stripe, op->version,
                                     (vec.copy_flags & COPY_BUF_JOURNAL) ? "journal" : "data", vec.disk_offset, p,
                                     crc32c(0, (uint8_t*)op->buf + vec.offset - op->offset + p, dsk.csum_block_size), *csum
@@ -966,7 +966,7 @@ void blockstore_impl_t::handle_read_event(ring_data_t *data, blockstore_op_t *op
             {
                 if (rv.journal_sector)
                 {
-                    auto used = --journal.used_sectors[rv.journal_sector-1];
+                    auto used = --journal.used_sectors.at(rv.journal_sector-1);
                     if (used == 0)
                     {
                         journal.used_sectors.erase(rv.journal_sector-1);

src/blockstore_rollback.cpp

@@ -179,7 +179,7 @@ void blockstore_impl_t::erase_dirty(blockstore_dirty_db_t::iterator dirty_start,
     {
         object_id oid = dirty_it->first.oid;
 #ifdef BLOCKSTORE_DEBUG
-        printf("Unblock writes-after-delete %lx:%lx v%lu\n", oid.inode, oid.stripe, dirty_it->first.version);
+        printf("Unblock writes-after-delete %jx:%jx v%ju\n", oid.inode, oid.stripe, dirty_it->first.version);
 #endif
         dirty_it = dirty_end;
         // Unblock operations blocked by delete flushing
@@ -210,21 +210,26 @@ void blockstore_impl_t::erase_dirty(blockstore_dirty_db_t::iterator dirty_start,
             dirty_it->second.location != UINT64_MAX)
         {
 #ifdef BLOCKSTORE_DEBUG
-            printf("Free block %lu from %lx:%lx v%lu\n", dirty_it->second.location >> dsk.block_order,
+            printf("Free block %ju from %jx:%jx v%ju\n", dirty_it->second.location >> dsk.block_order,
                 dirty_it->first.oid.inode, dirty_it->first.oid.stripe, dirty_it->first.version);
 #endif
             data_alloc->set(dirty_it->second.location >> dsk.block_order, false);
         }
-        auto used = --journal.used_sectors[dirty_it->second.journal_sector];
+        auto used = --journal.used_sectors.at(dirty_it->second.journal_sector);
 #ifdef BLOCKSTORE_DEBUG
         printf(
-            "remove usage of journal offset %08lx by %lx:%lx v%lu (%lu refs)\n", dirty_it->second.journal_sector,
+            "remove usage of journal offset %08jx by %jx:%jx v%ju (%ju refs)\n", dirty_it->second.journal_sector,
             dirty_it->first.oid.inode, dirty_it->first.oid.stripe, dirty_it->first.version, used
         );
 #endif
         if (used == 0)
         {
             journal.used_sectors.erase(dirty_it->second.journal_sector);
+            if (dirty_it->second.journal_sector == journal.sector_info[journal.cur_sector].offset)
+            {
+                // Mark current sector as "full" to select the new one
+                journal.in_sector_pos = dsk.journal_block_size;
+            }
             flusher->mark_trim_possible();
         }
         free_dirty_dyn_data(dirty_it->second);

src/blockstore_stable.cpp

@@ -298,7 +298,7 @@ int blockstore_impl_t::dequeue_stable(blockstore_op_t *op)
             if (clean_it == clean_db.end() || clean_it->second.version < ov.version)
             {
                 // No such object version
-                printf("Error: %lx:%lx v%lu not found while stabilizing\n", ov.oid.inode, ov.oid.stripe, ov.version);
+                printf("Error: %jx:%jx v%ju not found while stabilizing\n", ov.oid.inode, ov.oid.stripe, ov.version);
                 return -ENOENT;
             }
             else
@@ -307,35 +307,49 @@ int blockstore_impl_t::dequeue_stable(blockstore_op_t *op)
                 return STAB_SPLIT_DONE;
             }
         }
-        else if (IS_IN_FLIGHT(dirty_it->second.state))
-        {
-            // Object write is still in progress. Wait until the write request completes
-            return STAB_SPLIT_WAIT;
-        }
-        else if (!IS_SYNCED(dirty_it->second.state))
-        {
-            // Object not synced yet - sync it
-            // In previous versions we returned EBUSY here and required
-            // the caller (OSD) to issue a global sync first. But a global sync
-            // waits for all writes in the queue including inflight writes. And
-            // inflight writes may themselves be blocked by unstable writes being
-            // still present in the journal and not flushed away from it.
-            // So we must sync specific objects here.
-            //
-            // Even more, we have to process "stabilize" request in parts. That is,
-            // we must stabilize all objects which are already synced. Otherwise
-            // they may block objects which are NOT synced yet.
-            return STAB_SPLIT_SYNC;
-        }
         else if (IS_STABLE(dirty_it->second.state))
         {
             // Already stable
             return STAB_SPLIT_DONE;
         }
-        else
+        while (true)
         {
-            return STAB_SPLIT_TODO;
+            if (IS_IN_FLIGHT(dirty_it->second.state))
+            {
+                // Object write is still in progress. Wait until the write request completes
+                return STAB_SPLIT_WAIT;
+            }
+            else if (!IS_SYNCED(dirty_it->second.state))
+            {
+                // Object not synced yet - sync it
+                // In previous versions we returned EBUSY here and required
+                // the caller (OSD) to issue a global sync first. But a global sync
+                // waits for all writes in the queue including inflight writes. And
+                // inflight writes may themselves be blocked by unstable writes being
+                // still present in the journal and not flushed away from it.
+                // So we must sync specific objects here.
+                //
+                // Even more, we have to process "stabilize" request in parts. That is,
+                // we must stabilize all objects which are already synced. Otherwise
+                // they may block objects which are NOT synced yet.
+                return STAB_SPLIT_SYNC;
+            }
+            else if (IS_STABLE(dirty_it->second.state))
+            {
+                break;
+            }
+            // Check previous versions too
+            if (dirty_it == dirty_db.begin())
+            {
+                break;
+            }
+            dirty_it--;
+            if (dirty_it->first.oid != ov.oid)
+            {
+                break;
+            }
         }
+        return STAB_SPLIT_TODO;
     });
     if (r != 1)
     {
@@ -402,7 +416,7 @@ resume_4:
     {
         // Mark all dirty_db entries up to op->version as stable
 #ifdef BLOCKSTORE_DEBUG
-        printf("Stabilize %lx:%lx v%lu\n", v->oid.inode, v->oid.stripe, v->version);
+        printf("Stabilize %jx:%jx v%ju\n", v->oid.inode, v->oid.stripe, v->version);
 #endif
         mark_stable(*v);
     }
@@ -412,11 +426,40 @@ resume_4:
     return 2;
 }
 
-void blockstore_impl_t::mark_stable(const obj_ver_id & v, bool forget_dirty)
+void blockstore_impl_t::mark_stable(obj_ver_id v, bool forget_dirty)
 {
     auto dirty_it = dirty_db.find(v);
     if (dirty_it != dirty_db.end())
     {
+        if (IS_INSTANT(dirty_it->second.state))
+        {
+            // 'Instant' (non-EC) operations may complete and try to become stable out of order. Prevent it.
+            auto back_it = dirty_it;
+            while (back_it != dirty_db.begin())
+            {
+                back_it--;
+                if (back_it->first.oid != v.oid)
+                {
+                    break;
+                }
+                if (!IS_STABLE(back_it->second.state))
+                {
+                    // There are preceding unstable versions, can't flush <v>
+                    return;
+                }
+            }
+            while (true)
+            {
+                dirty_it++;
+                if (dirty_it == dirty_db.end() || dirty_it->first.oid != v.oid ||
+                    !IS_SYNCED(dirty_it->second.state))
+                {
+                    dirty_it--;
+                    break;
+                }
+                v.version = dirty_it->first.version;
+            }
+        }
         while (1)
         {
             bool was_stable = IS_STABLE(dirty_it->second.state);
@@ -445,6 +488,7 @@ void blockstore_impl_t::mark_stable(const obj_ver_id & v, bool forget_dirty)
                     if (!exists)
                     {
                         inode_space_stats[dirty_it->first.oid.inode] += dsk.data_block_size;
+                        used_blocks++;
                     }
                     big_to_flush++;
                 }
@@ -455,6 +499,7 @@ void blockstore_impl_t::mark_stable(const obj_ver_id & v, bool forget_dirty)
                         sp -= dsk.data_block_size;
                     else
                         inode_space_stats.erase(dirty_it->first.oid.inode);
+                    used_blocks--;
                     big_to_flush++;
                 }
             }
@@ -462,7 +507,7 @@ void blockstore_impl_t::mark_stable(const obj_ver_id & v, bool forget_dirty)
             {
                 // mark_stable should never be called for in-flight or submitted writes
                 printf(
-                    "BUG: Attempt to mark_stable object %lx:%lx v%lu state of which is %x\n",
+                    "BUG: Attempt to mark_stable object %jx:%jx v%ju state of which is %x\n",
                     dirty_it->first.oid.inode, dirty_it->first.oid.stripe, dirty_it->first.version,
                     dirty_it->second.state
                 );

src/blockstore_sync.cpp

@@ -85,16 +85,14 @@ int blockstore_impl_t::continue_sync(blockstore_op_t *op)
                 left--;
                 auto & dirty_entry = dirty_db.at(sbw);
                 uint64_t dyn_size = dsk.dirty_dyn_size(dirty_entry.offset, dirty_entry.len);
-                if (!space_check.check_available(op, 1, sizeof(journal_entry_big_write) + dyn_size,
-                    (unstable_writes.size()+unstable_unsynced)*journal.block_size))
+                if (!space_check.check_available(op, 1, sizeof(journal_entry_big_write) + dyn_size, 0))
                 {
                     return 0;
                 }
             }
         }
         else if (!space_check.check_available(op, PRIV(op)->sync_big_writes.size(),
-            sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size,
-            (unstable_writes.size()+unstable_unsynced)*journal.block_size))
+            sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size, 0))
         {
             return 0;
         }
@@ -117,11 +115,14 @@ int blockstore_impl_t::continue_sync(blockstore_op_t *op)
                 journal, (dirty_entry.state & BS_ST_INSTANT) ? JE_BIG_WRITE_INSTANT : JE_BIG_WRITE,
                 sizeof(journal_entry_big_write) + dyn_size
             );
-            dirty_entry.journal_sector = journal.sector_info[journal.cur_sector].offset;
+            auto jsec = dirty_entry.journal_sector = journal.sector_info[journal.cur_sector].offset;
+            assert(journal.next_free >= journal.used_start
+                ? (jsec >= journal.used_start && jsec < journal.next_free)
+                : (jsec >= journal.used_start || jsec < journal.next_free));
             journal.used_sectors[journal.sector_info[journal.cur_sector].offset]++;
 #ifdef BLOCKSTORE_DEBUG
             printf(
-                "journal offset %08lx is used by %lx:%lx v%lu (%lu refs)\n",
+                "journal offset %08jx is used by %jx:%jx v%ju (%ju refs)\n",
                 dirty_entry.journal_sector, it->oid.inode, it->oid.stripe, it->version,
                 journal.used_sectors[journal.sector_info[journal.cur_sector].offset]
             );
@@ -175,7 +176,7 @@ void blockstore_impl_t::ack_sync(blockstore_op_t *op)
     for (auto it = PRIV(op)->sync_big_writes.begin(); it != PRIV(op)->sync_big_writes.end(); it++)
     {
 #ifdef BLOCKSTORE_DEBUG
-        printf("Ack sync big %lx:%lx v%lu\n", it->oid.inode, it->oid.stripe, it->version);
+        printf("Ack sync big %jx:%jx v%ju\n", it->oid.inode, it->oid.stripe, it->version);
 #endif
         auto & unstab = unstable_writes[it->oid];
         unstab = unstab < it->version ? it->version : unstab;
@@ -203,7 +204,7 @@ void blockstore_impl_t::ack_sync(blockstore_op_t *op)
     for (auto it = PRIV(op)->sync_small_writes.begin(); it != PRIV(op)->sync_small_writes.end(); it++)
     {
 #ifdef BLOCKSTORE_DEBUG
-        printf("Ack sync small %lx:%lx v%lu\n", it->oid.inode, it->oid.stripe, it->version);
+        printf("Ack sync small %jx:%jx v%ju\n", it->oid.inode, it->oid.stripe, it->version);
 #endif
         auto & unstab = unstable_writes[it->oid];
         unstab = unstab < it->version ? it->version : unstab;

src/blockstore_write.cpp

@@ -85,7 +85,7 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
             // It's allowed to write versions with low numbers over deletes
             // However, we have to flush those deletes first as we use version number for ordering
 #ifdef BLOCKSTORE_DEBUG
-            printf("Write %lx:%lx v%lu over delete (real v%lu) offset=%u len=%u\n", op->oid.inode, op->oid.stripe, version, op->version, op->offset, op->len);
+            printf("Write %jx:%jx v%ju over delete (real v%ju) offset=%u len=%u\n", op->oid.inode, op->oid.stripe, version, op->version, op->offset, op->len);
 #endif
             wait_del = true;
             PRIV(op)->real_version = op->version;
@@ -95,11 +95,13 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
                 // Issue an additional sync so the delete reaches the journal
                 blockstore_op_t *sync_op = new blockstore_op_t;
                 sync_op->opcode = BS_OP_SYNC;
-                sync_op->callback = [this, op](blockstore_op_t *sync_op)
+                sync_op->oid = op->oid;
+                sync_op->version = op->version;
+                sync_op->callback = [this](blockstore_op_t *sync_op)
                 {
                     flusher->unshift_flush((obj_ver_id){
-                        .oid = op->oid,
-                        .version = op->version-1,
+                        .oid = sync_op->oid,
+                        .version = sync_op->version-1,
                     }, true);
                     delete sync_op;
                 };
@@ -117,7 +119,7 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
         {
             // Invalid version requested
 #ifdef BLOCKSTORE_DEBUG
-            printf("Write %lx:%lx v%lu requested, but we already have v%lu\n", op->oid.inode, op->oid.stripe, op->version, version);
+            printf("Write %jx:%jx v%ju requested, but we already have v%ju\n", op->oid.inode, op->oid.stripe, op->version, version);
 #endif
             op->retval = -EEXIST;
             if (!is_del && alloc_dyn_data)
@@ -129,7 +131,7 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
     }
     bool imm = (op->len < dsk.data_block_size ? (immediate_commit != IMMEDIATE_NONE) : (immediate_commit == IMMEDIATE_ALL));
     if (wait_big && !is_del && !deleted && op->len < dsk.data_block_size && !imm ||
-        !imm && unsynced_queued_ops >= autosync_writes)
+        !imm && autosync_writes && unsynced_queued_ops >= autosync_writes)
     {
         // Issue an additional sync so that the previous big write can reach the journal
         blockstore_op_t *sync_op = new blockstore_op_t;
@@ -144,9 +146,9 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
         unsynced_queued_ops++;
 #ifdef BLOCKSTORE_DEBUG
     if (is_del)
-        printf("Delete %lx:%lx v%lu\n", op->oid.inode, op->oid.stripe, op->version);
+        printf("Delete %jx:%jx v%ju\n", op->oid.inode, op->oid.stripe, op->version);
     else if (!wait_del)
-        printf("Write %lx:%lx v%lu offset=%u len=%u\n", op->oid.inode, op->oid.stripe, op->version, op->offset, op->len);
+        printf("Write %jx:%jx v%ju offset=%u len=%u\n", op->oid.inode, op->oid.stripe, op->version, op->offset, op->len);
 #endif
     // No strict need to add it into dirty_db here except maybe for listings to return
     // correct data when there are inflight operations in the queue
@@ -286,7 +288,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
         }
         // Restore original low version number for unblocked operations
 #ifdef BLOCKSTORE_DEBUG
-        printf("Restoring %lx:%lx version: v%lu -> v%lu\n", op->oid.inode, op->oid.stripe, op->version, PRIV(op)->real_version);
+        printf("Restoring %jx:%jx version: v%ju -> v%ju\n", op->oid.inode, op->oid.stripe, op->version, PRIV(op)->real_version);
 #endif
         auto prev_it = dirty_it;
         if (prev_it != dirty_db.begin())
@@ -296,7 +298,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
             {
                 // Original version is still invalid
                 // All subsequent writes to the same object must be canceled too
-                printf("Tried to write %lx:%lx v%lu after delete (old version v%lu), but already have v%lu\n",
+                printf("Tried to write %jx:%jx v%ju after delete (old version v%ju), but already have v%ju\n",
                     op->oid.inode, op->oid.stripe, PRIV(op)->real_version, op->version, prev_it->first.version);
                 cancel_all_writes(op, dirty_it, -EEXIST);
                 return 2;
@@ -320,7 +322,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
         blockstore_journal_check_t space_check(this);
         if (!space_check.check_available(op, unsynced_big_write_count + 1,
             sizeof(journal_entry_big_write) + dsk.clean_dyn_size,
-            (unstable_writes.size()+unstable_unsynced)*journal.block_size))
+            (unstable_writes.size()+unstable_unsynced+((dirty_it->second.state & BS_ST_INSTANT) ? 0 : 1))*journal.block_size))
         {
             return 0;
         }
@@ -348,8 +350,8 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
             if (entry->oid.inode || entry->oid.stripe || entry->version)
             {
                 printf(
-                    "Fatal error (metadata corruption or bug): tried to write object %lx:%lx v%lu"
-                    " over a non-zero metadata entry %lu with %lx:%lx v%lu\n", op->oid.inode,
+                    "Fatal error (metadata corruption or bug): tried to write object %jx:%jx v%ju"
+                    " over a non-zero metadata entry %ju with %jx:%jx v%ju\n", op->oid.inode,
                     op->oid.stripe, op->version, loc, entry->oid.inode, entry->oid.stripe, entry->version
                 );
                 exit(1);
@@ -361,7 +363,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
         dirty_it->second.state = (dirty_it->second.state & ~BS_ST_WORKFLOW_MASK) | BS_ST_SUBMITTED;
 #ifdef BLOCKSTORE_DEBUG
         printf(
-            "Allocate block %lu for %lx:%lx v%lu\n",
+            "Allocate block %ju for %jx:%jx v%ju\n",
             loc, op->oid.inode, op->oid.stripe, op->version
         );
 #endif
@@ -372,13 +374,13 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
         int vcnt = 0;
         if (stripe_offset)
         {
-            PRIV(op)->iov_zerofill[vcnt++] = (struct iovec){ zero_object, stripe_offset };
+            PRIV(op)->iov_zerofill[vcnt++] = (struct iovec){ zero_object, (size_t)stripe_offset };
         }
         PRIV(op)->iov_zerofill[vcnt++] = (struct iovec){ op->buf, op->len };
         if (stripe_end)
         {
             stripe_end = dsk.bitmap_granularity - stripe_end;
-            PRIV(op)->iov_zerofill[vcnt++] = (struct iovec){ zero_object, stripe_end };
+            PRIV(op)->iov_zerofill[vcnt++] = (struct iovec){ zero_object, (size_t)stripe_end };
         }
         data->iov.iov_len = op->len + stripe_offset + stripe_end; // to check it in the callback
         data->callback = [this, op](ring_data_t *data) { handle_write_event(data, op); };
@@ -412,7 +414,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
                 sizeof(journal_entry_big_write) + dsk.clean_dyn_size, 0)
             || !space_check.check_available(op, 1,
                 sizeof(journal_entry_small_write) + dyn_size,
-                op->len + (unstable_writes.size()+unstable_unsynced)*journal.block_size))
+                op->len + (unstable_writes.size()+unstable_unsynced+((dirty_it->second.state & BS_ST_INSTANT) ? 0 : 1))*journal.block_size))
         {
             return 0;
         }
@@ -436,11 +438,23 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
             journal, op->opcode == BS_OP_WRITE_STABLE ? JE_SMALL_WRITE_INSTANT : JE_SMALL_WRITE,
             sizeof(journal_entry_small_write) + dyn_size
         );
-        dirty_it->second.journal_sector = journal.sector_info[journal.cur_sector].offset;
+        auto jsec = dirty_it->second.journal_sector = journal.sector_info[journal.cur_sector].offset;
+        if (!(journal.next_free >= journal.used_start
+            ? (jsec >= journal.used_start && jsec < journal.next_free)
+            : (jsec >= journal.used_start || jsec < journal.next_free)))
+        {
+            printf(
+                "BUG: journal offset %08jx is used by %jx:%jx v%ju (%ju refs) BUT used_start=%jx next_free=%jx\n",
+                dirty_it->second.journal_sector, dirty_it->first.oid.inode, dirty_it->first.oid.stripe, dirty_it->first.version,
+                journal.used_sectors[journal.sector_info[journal.cur_sector].offset],
+                journal.used_start, journal.next_free
+            );
+            abort();
+        }
         journal.used_sectors[journal.sector_info[journal.cur_sector].offset]++;
 #ifdef BLOCKSTORE_DEBUG
         printf(
-            "journal offset %08lx is used by %lx:%lx v%lu (%lu refs)\n",
+            "journal offset %08jx is used by %jx:%jx v%ju (%ju refs)\n",
             dirty_it->second.journal_sector, dirty_it->first.oid.inode, dirty_it->first.oid.stripe, dirty_it->first.version,
             journal.used_sectors[journal.sector_info[journal.cur_sector].offset]
         );
@@ -454,8 +468,8 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
                 journal_used_it->first < next_next_free + op->len)
             {
                 printf(
-                    "BUG: Attempt to overwrite used offset (%lx, %lu refs) of the journal with the object %lx:%lx v%lu: data at %lx, len %x!"
-                    " Journal used_start=%08lx (%lu refs), next_free=%08lx, dirty_start=%08lx\n",
+                    "BUG: Attempt to overwrite used offset (%jx, %ju refs) of the journal with the object %jx:%jx v%ju: data at %jx, len %x!"
+                    " Journal used_start=%08jx (%ju refs), next_free=%08jx, dirty_start=%08jx\n",
                     journal_used_it->first, journal_used_it->second, op->oid.inode, op->oid.stripe, op->version, next_next_free, op->len,
                     journal.used_start, journal.used_sectors[journal.used_start], journal.next_free, journal.dirty_start
                 );
@@ -463,7 +477,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
             }
         }
         // double check that next_free doesn't cross used_start from the left
-        assert(journal.next_free >= journal.used_start || next_next_free < journal.used_start);
+        assert(journal.next_free >= journal.used_start && next_next_free >= journal.next_free || next_next_free < journal.used_start);
         journal.next_free = next_next_free;
         je->oid = op->oid;
         je->version = op->version;
@@ -505,7 +519,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
         if (next_next_free >= journal.len)
             next_next_free = dsk.journal_block_size;
         // double check that next_free doesn't cross used_start from the left
-        assert(journal.next_free >= journal.used_start || next_next_free < journal.used_start);
+        assert(journal.next_free >= journal.used_start && next_next_free >= journal.next_free || next_next_free < journal.used_start);
         journal.next_free = next_next_free;
         if (!(dirty_it->second.state & BS_ST_INSTANT))
         {
@@ -549,7 +563,7 @@ resume_2:
         uint64_t dyn_size = dsk.dirty_dyn_size(op->offset, op->len);
         blockstore_journal_check_t space_check(this);
         if (!space_check.check_available(op, 1, sizeof(journal_entry_big_write) + dyn_size,
-            (unstable_writes.size()+unstable_unsynced)*journal.block_size))
+            (unstable_writes.size()+unstable_unsynced+((dirty_it->second.state & BS_ST_INSTANT) ? 0 : 1))*journal.block_size))
         {
             return 0;
         }
@@ -558,11 +572,23 @@ resume_2:
             journal, op->opcode == BS_OP_WRITE_STABLE ? JE_BIG_WRITE_INSTANT : JE_BIG_WRITE,
             sizeof(journal_entry_big_write) + dyn_size
         );
-        dirty_it->second.journal_sector = journal.sector_info[journal.cur_sector].offset;
+        auto jsec = dirty_it->second.journal_sector = journal.sector_info[journal.cur_sector].offset;
+        if (!(journal.next_free >= journal.used_start
+            ? (jsec >= journal.used_start && jsec < journal.next_free)
+            : (jsec >= journal.used_start || jsec < journal.next_free)))
+        {
+            printf(
+                "BUG: journal offset %08jx is used by %jx:%jx v%ju (%ju refs) BUT used_start=%jx next_free=%jx\n",
+                dirty_it->second.journal_sector, dirty_it->first.oid.inode, dirty_it->first.oid.stripe, dirty_it->first.version,
+                journal.used_sectors[journal.sector_info[journal.cur_sector].offset],
+                journal.used_start, journal.next_free
+            );
+            abort();
+        }
         journal.used_sectors[journal.sector_info[journal.cur_sector].offset]++;
 #ifdef BLOCKSTORE_DEBUG
         printf(
-            "journal offset %08lx is used by %lx:%lx v%lu (%lu refs)\n",
+            "journal offset %08jx is used by %jx:%jx v%ju (%ju refs)\n",
             journal.sector_info[journal.cur_sector].offset, op->oid.inode, op->oid.stripe, op->version,
             journal.used_sectors[journal.sector_info[journal.cur_sector].offset]
         );
@@ -589,11 +615,11 @@ resume_4:
         });
         assert(dirty_it != dirty_db.end());
 #ifdef BLOCKSTORE_DEBUG
-        printf("Ack write %lx:%lx v%lu = state 0x%x\n", op->oid.inode, op->oid.stripe, op->version, dirty_it->second.state);
+        printf("Ack write %jx:%jx v%ju = state 0x%x\n", op->oid.inode, op->oid.stripe, op->version, dirty_it->second.state);
 #endif
         bool is_big = (dirty_it->second.state & BS_ST_TYPE_MASK) == BS_ST_BIG_WRITE;
         bool imm = is_big ? (immediate_commit == IMMEDIATE_ALL) : (immediate_commit != IMMEDIATE_NONE);
-        bool is_instant = ((dirty_it->second.state & BS_ST_TYPE_MASK) == BS_ST_DELETE || (dirty_it->second.state & BS_ST_INSTANT));
+        bool is_instant = IS_INSTANT(dirty_it->second.state);
         if (imm)
         {
             auto & unstab = unstable_writes[op->oid];
@@ -782,7 +808,7 @@ int blockstore_impl_t::dequeue_del(blockstore_op_t *op)
     journal.used_sectors[journal.sector_info[journal.cur_sector].offset]++;
 #ifdef BLOCKSTORE_DEBUG
     printf(
-        "journal offset %08lx is used by %lx:%lx v%lu (%lu refs)\n",
+        "journal offset %08jx is used by %jx:%jx v%ju (%ju refs)\n",
         dirty_it->second.journal_sector, dirty_it->first.oid.inode, dirty_it->first.oid.stripe, dirty_it->first.version,
         journal.used_sectors[journal.sector_info[journal.cur_sector].offset]
     );

src/cli.cpp

@@ -46,18 +46,21 @@ static const char* help_text =
     "vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>\n"
     "  Create a snapshot of image <name>. May be used live if only a single writer is active.\n"
     "\n"
-    "vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force]\n"
+    "vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force] [--down-ok]\n"
     "  Rename, resize image or change its readonly status. Images with children can't be made read-write.\n"
     "  If the new size is smaller than the old size, extra data will be purged.\n"
     "  You should resize file system in the image, if present, before shrinking it.\n"
     "  -f|--force  Proceed with shrinking or setting readwrite flag even if the image has children.\n"
+    "  --down-ok   Proceed with shrinking even if some data will be left on unavailable OSDs.\n"
     "\n"
-    "vitastor-cli rm <from> [<to>] [--writers-stopped]\n"
+    "vitastor-cli rm <from> [<to>] [--writers-stopped] [--down-ok]\n"
     "  Remove <from> or all layers between <from> and <to> (<to> must be a child of <from>),\n"
     "  rebasing all their children accordingly. --writers-stopped allows merging to be a bit\n"
     "  more effective in case of a single 'slim' read-write child and 'fat' removed parent:\n"
     "  the child is merged into parent and parent is renamed to child in that case.\n"
     "  In other cases parent layers are always merged into children.\n"
+    "  Other options:\n"
+    "  --down-ok  Continue deletion/merging even if some data will be left on unavailable OSDs.\n"
     "\n"
     "vitastor-cli flatten <layer>\n"
     "  Flatten a layer, i.e. merge data and detach it from parents.\n"
@@ -122,7 +125,7 @@ static const char* help_text =
     "  --parallel_osds M   Work with M osds in parallel when possible (default 4)\n"
     "  --progress 1|0      Report progress (default 1)\n"
     "  --cas 1|0           Use CAS writes for flatten, merge, rm (default is decide automatically)\n"
-    "  --no-color          Disable colored output\n"
+    "  --color 1|0         Enable/disable colored output and CR symbols (default 1 if stdout is a terminal)\n"
     "  --json              JSON output\n"
 ;
 
@@ -171,6 +174,7 @@ static json11::Json::object parse_args(int narg, const char *args[])
                 !strcmp(opt, "readonly") || !strcmp(opt, "readwrite") ||
                 !strcmp(opt, "force") || !strcmp(opt, "reverse") ||
                 !strcmp(opt, "allow-data-loss") || !strcmp(opt, "allow_data_loss") ||
+                !strcmp(opt, "down-ok") || !strcmp(opt, "down_ok") ||
                 !strcmp(opt, "dry-run") || !strcmp(opt, "dry_run") ||
                 !strcmp(opt, "help") || !strcmp(opt, "all") ||
                 (!strcmp(opt, "writers-stopped") || !strcmp(opt, "writers_stopped")) && strcmp("1", args[i+1]) != 0

src/cli_alloc_osd.cpp

@@ -77,7 +77,7 @@ struct alloc_osd_t
                     std::string key = base64_decode(kv["key"].string_value());
                     osd_num_t cur_osd;
                     char null_byte = 0;
-                    int scanned = sscanf(key.c_str() + parent->cli->st_cli.etcd_prefix.length(), "/osd/stats/%lu%c", &cur_osd, &null_byte);
+                    int scanned = sscanf(key.c_str() + parent->cli->st_cli.etcd_prefix.length(), "/osd/stats/%ju%c", &cur_osd, &null_byte);
                     if (scanned != 1 || !cur_osd)
                     {
                         fprintf(stderr, "Invalid key in etcd: %s\n", key.c_str());

src/cli_common.cpp

@@ -1,6 +1,7 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 (see README.md for details)
 
+#include <unistd.h>
 #include "str_util.h"
 #include "cluster_client.h"
 #include "cli.h"
@@ -11,7 +12,7 @@ void cli_tool_t::change_parent(inode_t cur, inode_t new_parent, cli_result_t *re
     if (cur_cfg_it == cli->st_cli.inode_config.end())
     {
         char buf[128];
-        snprintf(buf, 128, "Inode 0x%lx disappeared", cur);
+        snprintf(buf, 128, "Inode 0x%jx disappeared", cur);
         *result = (cli_result_t){ .err = EIO, .text = buf };
         return;
     }
@@ -113,7 +114,12 @@ void cli_tool_t::parse_config(json11::Json::object & cfg)
         else
             kv_it++;
     }
-    color = !cfg["no_color"].bool_value();
+    if (cfg.find("no_color") != cfg.end())
+        color = !cfg["no_color"].bool_value();
+    else if (cfg.find("color") != cfg.end())
+        color = cfg["color"].bool_value();
+    else
+        color = isatty(1);
     json_output = cfg["json"].bool_value();
     iodepth = cfg["iodepth"].uint64_value();
     if (!iodepth)

src/cli_describe.cpp

@@ -160,14 +160,14 @@ struct cli_describe_t
                 if (op->reply.hdr.retval < 0)
                 {
                     fprintf(
-                        stderr, "Failed to describe objects on OSD %lu (retval=%ld)\n",
+                        stderr, "Failed to describe objects on OSD %ju (retval=%jd)\n",
                         osd_num, op->reply.hdr.retval
                     );
                 }
                 else if (op->reply.describe.result_bytes != op->reply.hdr.retval * sizeof(osd_reply_describe_item_t))
                 {
                     fprintf(
-                        stderr, "Invalid response size from OSD %lu (expected %lu bytes, got %lu bytes)\n",
+                        stderr, "Invalid response size from OSD %ju (expected %ju bytes, got %ju bytes)\n",
                         osd_num, op->reply.hdr.retval * sizeof(osd_reply_describe_item_t), op->reply.describe.result_bytes
                     );
                 }
@@ -178,11 +178,11 @@ struct cli_describe_t
                     {
                         if (!parent->json_output || parent->is_command_line)
                         {
-#define FMT "{\"inode\":\"0x%lx\",\"stripe\":\"0x%lx\",\"part\":%u,\"osd_num\":%lu%s%s%s}"
+#define FMT "{\"inode\":\"0x%jx\",\"stripe\":\"0x%jx\",\"part\":%u,\"osd_num\":%ju%s%s%s}"
                             printf(
                                 (parent->json_output
                                     ? (count > 0 ? ",\n  " FMT : "  " FMT)
-                                    : "%lx:%lx part %u on OSD %lu%s%s%s\n"),
+                                    : "%jx:%jx part %u on OSD %ju%s%s%s\n"),
 #undef FMT
                                 items[i].inode, items[i].stripe,
                                 items[i].role, items[i].osd_num,

src/cli_df.cpp

@@ -82,7 +82,7 @@ resume_1:
             // osd ID
             osd_num_t osd_num;
             char null_byte = 0;
-            int scanned = sscanf(kv.key.substr(parent->cli->st_cli.etcd_prefix.length()).c_str(), "/osd/stats/%lu%c", &osd_num, &null_byte);
+            int scanned = sscanf(kv.key.substr(parent->cli->st_cli.etcd_prefix.length()).c_str(), "/osd/stats/%ju%c", &osd_num, &null_byte);
             if (scanned != 1 || !osd_num || osd_num >= POOL_ID_MAX)
             {
                 fprintf(stderr, "Invalid key in etcd: %s\n", kv.key.c_str());

src/cli_fix.cpp

@@ -136,7 +136,7 @@ struct cli_fix_t
             auto pool_cfg_it = parent->cli->st_cli.pool_config.find(INODE_POOL(obj.inode));
             if (pool_cfg_it == parent->cli->st_cli.pool_config.end())
             {
-                fprintf(stderr, "Object %lx:%lx is from unknown pool\n", obj.inode, obj.stripe);
+                fprintf(stderr, "Object %jx:%jx is from unknown pool\n", obj.inode, obj.stripe);
                 continue;
             }
             auto & pool_cfg = pool_cfg_it->second;
@@ -146,7 +146,7 @@ struct cli_fix_t
                 !pg_it->second.cur_primary || !(pg_it->second.cur_state & PG_ACTIVE))
             {
                 fprintf(
-                    stderr, "Object %lx:%lx is from PG %u/%u which is not currently active\n",
+                    stderr, "Object %jx:%jx is from PG %u/%u which is not currently active\n",
                     obj.inode, obj.stripe, pool_cfg_it->first, pg_num
                 );
                 continue;
@@ -171,7 +171,7 @@ struct cli_fix_t
             {
                 if (op->reply.hdr.retval < 0 || op->reply.describe.result_bytes != op->reply.hdr.retval * sizeof(osd_reply_describe_item_t))
                 {
-                    fprintf(stderr, "Failed to describe objects on OSD %lu (retval=%ld)\n", primary_osd, op->reply.hdr.retval);
+                    fprintf(stderr, "Failed to describe objects on OSD %ju (retval=%jd)\n", primary_osd, op->reply.hdr.retval);
                     parent->waiting--;
                     loop();
                 }
@@ -209,7 +209,7 @@ struct cli_fix_t
                                 if (rm_op->reply.hdr.retval < 0)
                                 {
                                     fprintf(
-                                        stderr, "Failed to remove object %lx:%lx from OSD %lu (retval=%ld)\n",
+                                        stderr, "Failed to remove object %jx:%jx from OSD %ju (retval=%jd)\n",
                                         rm_op->req.sec_del.oid.inode, rm_op->req.sec_del.oid.stripe,
                                         rm_osd_num, rm_op->reply.hdr.retval
                                     );
@@ -226,7 +226,7 @@ struct cli_fix_t
                                 else
                                 {
                                     printf(
-                                        "Removed %lx:%lx (part %lu) from OSD %lu\n",
+                                        "Removed %jx:%jx (part %ju) from OSD %ju\n",
                                         rm_op->req.sec_del.oid.inode, rm_op->req.sec_del.oid.stripe & ~STRIPE_MASK,
                                         rm_op->req.sec_del.oid.stripe & STRIPE_MASK, rm_osd_num
                                     );
@@ -254,7 +254,7 @@ struct cli_fix_t
                                         if (scrub_op->reply.hdr.retval < 0 && scrub_op->reply.hdr.retval != -ENOENT)
                                         {
                                             fprintf(
-                                                stderr, "Failed to scrub %lx:%lx on OSD %lu (retval=%ld)\n",
+                                                stderr, "Failed to scrub %jx:%jx on OSD %ju (retval=%jd)\n",
                                                 obj.inode, obj.stripe, primary_osd, scrub_op->reply.hdr.retval
                                             );
                                         }

src/cli_ls.cpp

@@ -150,7 +150,7 @@ resume_1:
             inode_t only_inode_num;
             char null_byte = 0;
             int scanned = sscanf(kv.key.substr(parent->cli->st_cli.etcd_prefix.length()).c_str(),
-                "/inode/stats/%u/%lu%c", &pool_id, &only_inode_num, &null_byte);
+                "/inode/stats/%u/%ju%c", &pool_id, &only_inode_num, &null_byte);
             if (scanned != 2 || !pool_id || pool_id >= POOL_ID_MAX || INODE_POOL(only_inode_num) != 0)
             {
                 fprintf(stderr, "Invalid key in etcd: %s\n", kv.key.c_str());
@@ -456,7 +456,7 @@ std::string format_lat(uint64_t lat)
     char buf[256];
     int l = 0;
     if (lat < 100)
-        l = snprintf(buf, sizeof(buf), "%lu us", lat);
+        l = snprintf(buf, sizeof(buf), "%ju us", lat);
     else if (lat < 500000)
         l = snprintf(buf, sizeof(buf), "%.2f ms", (double)lat/1000);
     else

src/cli_merge.cpp

@@ -202,7 +202,7 @@ struct snap_merger_t
         if (parent->progress)
         {
             printf(
-                "Merging %ld layer(s) into target %s%s (inode %lu in pool %u)\n",
+                "Merging %zd layer(s) into target %s%s (inode %ju in pool %u)\n",
                 sources.size(), target_cfg->name.c_str(),
                 use_cas ? " online (with CAS)" : "", INODE_NO_POOL(target), INODE_POOL(target)
             );
@@ -275,7 +275,9 @@ struct snap_merger_t
                 processed++;
                 if (parent->progress && !(processed % 128))
                 {
-                    printf("\rFiltering target blocks: %lu/%lu", processed, to_process);
+                    fprintf(stderr, parent->color
+                        ? "\rFiltering target blocks: %ju/%ju"
+                        : "Filtering target blocks: %ju/%ju\n", processed, to_process);
                 }
             }
             if (in_flight > 0 || oit != merge_offsets.end())
@@ -285,7 +287,9 @@ struct snap_merger_t
             }
             if (parent->progress)
             {
-                printf("\r%lu full blocks of target filtered out\n", to_process-merge_offsets.size());
+                fprintf(stderr, parent->color
+                    ? "\r%ju full blocks of target filtered out\n"
+                    : "%ju full blocks of target filtered out\n", to_process-merge_offsets.size());
             }
         }
         state = 3;
@@ -320,7 +324,9 @@ struct snap_merger_t
             processed++;
             if (parent->progress && !(processed % 128))
             {
-                printf("\rOverwriting blocks: %lu/%lu", processed, to_process);
+                fprintf(stderr, parent->color
+                    ? "\rOverwriting blocks: %ju/%ju"
+                    : "Overwriting blocks: %ju/%ju\n", processed, to_process);
             }
         }
         if (in_flight == 0 && rwo_error.size())
@@ -339,7 +345,9 @@ struct snap_merger_t
         }
         if (parent->progress)
         {
-            printf("\rOverwriting blocks: %lu/%lu\n", to_process, to_process);
+            fprintf(stderr, parent->color
+                ? "\rOverwriting blocks: %ju/%ju\n"
+                : "Overwriting blocks: %ju/%ju\n", to_process, to_process);
         }
         // Done
         result = (cli_result_t){ .text = "Done, layers from "+from_name+" to "+to_name+" merged into "+target_name };
@@ -384,7 +392,7 @@ struct snap_merger_t
                         auto & name = parent->cli->st_cli.inode_config.at(src).name;
                         if (parent->progress)
                         {
-                            printf("Got listing of layer %s (inode %lu in pool %u)\n", name.c_str(), INODE_NO_POOL(src), INODE_POOL(src));
+                            printf("Got listing of layer %s (inode %ju in pool %u)\n", name.c_str(), INODE_NO_POOL(src), INODE_POOL(src));
                         }
                         if (delete_source)
                         {
@@ -416,7 +424,7 @@ struct snap_merger_t
         {
             if (op->retval < 0)
             {
-                fprintf(stderr, "error reading target bitmap at offset %lx: %s\n", op->offset, strerror(-op->retval));
+                fprintf(stderr, "error reading target bitmap at offset %jx: %s\n", op->offset, strerror(-op->retval));
             }
             else
             {
@@ -571,7 +579,7 @@ struct snap_merger_t
         {
             if (subop->retval != 0)
             {
-                fprintf(stderr, "error deleting from layer 0x%lx at offset %lx: %s", subop->inode, subop->offset, strerror(-subop->retval));
+                fprintf(stderr, "error deleting from layer 0x%jx at offset %jx: %s", subop->inode, subop->offset, strerror(-subop->retval));
             }
             delete subop;
         };
@@ -620,7 +628,7 @@ struct snap_merger_t
             if (rwo->error_code)
             {
                 char buf[1024];
-                snprintf(buf, 1024, "Error %s target at offset %lx: %s",
+                snprintf(buf, 1024, "Error %s target at offset %jx: %s",
                     rwo->error_read ? "reading" : "writing", rwo->error_offset, strerror(rwo->error_code));
                 rwo_error = std::string(buf);
             }

src/cli_modify.cpp

@@ -15,6 +15,7 @@ struct image_changer_t
     uint64_t new_size = 0;
     bool force_size = false, inc_size = false;
     bool set_readonly = false, set_readwrite = false, force = false;
+    bool down_ok = false;
     // interval between fsyncs
     int fsync_interval = 128;
 
@@ -105,6 +106,7 @@ struct image_changer_t
                     { "pool", (uint64_t)INODE_POOL(inode_num) },
                     { "fsync-interval", fsync_interval },
                     { "min-offset", ((new_size+4095)/4096)*4096 },
+                    { "down-ok", down_ok },
                 });
 resume_1:
                 while (!cb(result))
@@ -240,6 +242,7 @@ std::function<bool(cli_result_t &)> cli_tool_t::start_modify(json11::Json cfg)
     changer->fsync_interval = cfg["fsync_interval"].uint64_value();
     if (!changer->fsync_interval)
         changer->fsync_interval = 128;
+    changer->down_ok = cfg["down_ok"].bool_value();
     // FIXME Check that the image doesn't have children when shrinking
     return [changer](cli_result_t & result)
     {

src/cli_rm.cpp

@@ -53,6 +53,8 @@ struct snap_remover_t
     int use_cas = 1;
     // interval between fsyncs
     int fsync_interval = 128;
+    // ignore deletion errors
+    bool down_ok = false;
 
     std::map<inode_t,int> sources;
     std::map<inode_t,uint64_t> inode_used;
@@ -291,7 +293,7 @@ resume_100:
             if (it == parent->cli->st_cli.inode_config.end())
             {
                 char buf[1024];
-                snprintf(buf, 1024, "Parent inode of layer %s (id 0x%lx) not found", cur->name.c_str(), cur->parent_id);
+                snprintf(buf, 1024, "Parent inode of layer %s (id 0x%jx) not found", cur->name.c_str(), cur->parent_id);
                 state = 100;
                 return;
             }
@@ -384,7 +386,7 @@ resume_100:
                 pool_id_t pool_id = 0;
                 inode_t inode = 0;
                 char null_byte = 0;
-                int scanned = sscanf(kv.key.c_str() + parent->cli->st_cli.etcd_prefix.length()+13, "%u/%lu%c", &pool_id, &inode, &null_byte);
+                int scanned = sscanf(kv.key.c_str() + parent->cli->st_cli.etcd_prefix.length()+13, "%u/%ju%c", &pool_id, &inode, &null_byte);
                 if (scanned != 2 || !inode)
                 {
                     result = (cli_result_t){ .err = EIO, .text = "Bad key returned from etcd: "+kv.key };
@@ -439,7 +441,7 @@ resume_100:
         if (child_it == parent->cli->st_cli.inode_config.end())
         {
             char buf[1024];
-            snprintf(buf, 1024, "Inode 0x%lx disappeared", inverse_child);
+            snprintf(buf, 1024, "Inode 0x%jx disappeared", inverse_child);
             result = (cli_result_t){ .err = EIO, .text = std::string(buf) };
             state = 100;
             return;
@@ -448,7 +450,7 @@ resume_100:
         if (target_it == parent->cli->st_cli.inode_config.end())
         {
             char buf[1024];
-            snprintf(buf, 1024, "Inode 0x%lx disappeared", inverse_parent);
+            snprintf(buf, 1024, "Inode 0x%jx disappeared", inverse_parent);
             result = (cli_result_t){ .err = EIO, .text = std::string(buf) };
             state = 100;
             return;
@@ -576,7 +578,7 @@ resume_100:
         if (cur_cfg_it == parent->cli->st_cli.inode_config.end())
         {
             char buf[1024];
-            snprintf(buf, 1024, "Inode 0x%lx disappeared", cur);
+            snprintf(buf, 1024, "Inode 0x%jx disappeared", cur);
             result = (cli_result_t){ .err = EIO, .text = std::string(buf) };
             state = 100;
             return;
@@ -640,7 +642,7 @@ resume_100:
         if (child_it == parent->cli->st_cli.inode_config.end())
         {
             char buf[1024];
-            snprintf(buf, 1024, "Inode 0x%lx disappeared", child_inode);
+            snprintf(buf, 1024, "Inode 0x%jx disappeared", child_inode);
             result = (cli_result_t){ .err = EIO, .text = std::string(buf) };
             state = 100;
             return;
@@ -649,7 +651,7 @@ resume_100:
         if (target_it == parent->cli->st_cli.inode_config.end())
         {
             char buf[1024];
-            snprintf(buf, 1024, "Inode 0x%lx disappeared", target_inode);
+            snprintf(buf, 1024, "Inode 0x%jx disappeared", target_inode);
             result = (cli_result_t){ .err = EIO, .text = std::string(buf) };
             state = 100;
             return;
@@ -670,7 +672,7 @@ resume_100:
         if (source == parent->cli->st_cli.inode_config.end())
         {
             char buf[1024];
-            snprintf(buf, 1024, "Inode 0x%lx disappeared", inode);
+            snprintf(buf, 1024, "Inode 0x%jx disappeared", inode);
             result = (cli_result_t){ .err = EIO, .text = std::string(buf) };
             state = 100;
             return;
@@ -679,6 +681,7 @@ resume_100:
             { "inode", inode },
             { "pool", (uint64_t)INODE_POOL(inode) },
             { "fsync-interval", fsync_interval },
+            { "down-ok", down_ok },
         });
     }
 };
@@ -690,6 +693,7 @@ std::function<bool(cli_result_t &)> cli_tool_t::start_rm(json11::Json cfg)
     snap_remover->from_name = cfg["from"].string_value();
     snap_remover->to_name = cfg["to"].string_value();
     snap_remover->fsync_interval = cfg["fsync_interval"].uint64_value();
+    snap_remover->down_ok = cfg["down_ok"].bool_value();
     if (!snap_remover->fsync_interval)
         snap_remover->fsync_interval = 128;
     if (!cfg["cas"].is_null())

src/cli_rm_data.cpp

@@ -17,6 +17,7 @@ struct rm_pg_t
     uint64_t obj_count = 0, obj_done = 0;
     int state = 0;
     int in_flight = 0;
+    bool synced = false;
 };
 
 struct rm_inode_t
@@ -24,6 +25,7 @@ struct rm_inode_t
     uint64_t inode = 0;
     pool_id_t pool_id = 0;
     uint64_t min_offset = 0;
+    bool down_ok = false;
 
     cli_tool_t *parent = NULL;
     inode_list_t *lister = NULL;
@@ -48,6 +50,7 @@ struct rm_inode_t
                 .objects = objects,
                 .obj_count = objects.size(),
                 .obj_done = 0,
+                .synced = parent->cli->get_immediate_commit(inode),
             });
             if (min_offset == 0)
             {
@@ -93,7 +96,7 @@ struct rm_inode_t
             fprintf(stderr, "Some data may remain after delete on OSDs which are currently down: ");
             for (int i = 0; i < inactive_osds.size(); i++)
             {
-                fprintf(stderr, i > 0 ? ", %lu" : "%lu", inactive_osds[i]);
+                fprintf(stderr, i > 0 ? ", %ju" : "%ju", inactive_osds[i]);
             }
             fprintf(stderr, "\n");
         }
@@ -136,7 +139,7 @@ struct rm_inode_t
                     cur_list->in_flight--;
                     if (op->reply.hdr.retval < 0)
                     {
-                        fprintf(stderr, "Failed to remove object %lx:%lx from PG %u (OSD %lu) (retval=%ld)\n",
+                        fprintf(stderr, "Failed to remove object %jx:%jx from PG %u (OSD %ju) (retval=%jd)\n",
                             op->req.rw.inode, op->req.rw.offset,
                             cur_list->pg_num, cur_list->rm_osd_num, op->reply.hdr.retval);
                         error_count++;
@@ -151,6 +154,37 @@ struct rm_inode_t
             }
             cur_list->obj_pos++;
         }
+        if (cur_list->in_flight == 0 && cur_list->obj_pos == cur_list->objects.end() &&
+            !cur_list->synced)
+        {
+            osd_op_t *op = new osd_op_t();
+            op->op_type = OSD_OP_OUT;
+            op->peer_fd = parent->cli->msgr.osd_peer_fds.at(cur_list->rm_osd_num);
+            op->req = (osd_any_op_t){
+                .sync = {
+                    .header = {
+                        .magic = SECONDARY_OSD_OP_MAGIC,
+                        .id = parent->cli->next_op_id(),
+                        .opcode = OSD_OP_SYNC,
+                    },
+                },
+            };
+            op->callback = [this, cur_list](osd_op_t *op)
+            {
+                cur_list->in_flight--;
+                cur_list->synced = true;
+                if (op->reply.hdr.retval < 0)
+                {
+                    fprintf(stderr, "Failed to sync OSD %ju (retval=%jd)\n",
+                        cur_list->rm_osd_num, op->reply.hdr.retval);
+                    error_count++;
+                }
+                delete op;
+                continue_delete();
+            };
+            cur_list->in_flight++;
+            parent->cli->msgr.outbox_push(op);
+        }
     }
 
     void continue_delete()
@@ -161,7 +195,8 @@ struct rm_inode_t
         }
         for (int i = 0; i < lists.size(); i++)
         {
-            if (!lists[i]->in_flight && lists[i]->obj_pos == lists[i]->objects.end())
+            if (!lists[i]->in_flight && lists[i]->obj_pos == lists[i]->objects.end() &&
+                lists[i]->synced)
             {
                 delete lists[i];
                 lists.erase(lists.begin()+i, lists.begin()+i+1);
@@ -178,7 +213,9 @@ struct rm_inode_t
         }
         if (parent->progress && total_count > 0 && total_done*1000/total_count != total_prev_pct)
         {
-            fprintf(stderr, "\rRemoved %lu/%lu objects, %lu more PGs to list...", total_done, total_count, pgs_to_list);
+            fprintf(stderr, parent->color
+                ? "\rRemoved %ju/%ju objects, %ju more PGs to list..."
+                : "Removed %ju/%ju objects, %ju more PGs to list...\n", total_done, total_count, pgs_to_list);
             total_prev_pct = total_done*1000/total_count;
         }
         if (lists_done && !lists.size())
@@ -187,17 +224,18 @@ struct rm_inode_t
             {
                 fprintf(stderr, "\n");
             }
-            if (parent->progress && (total_done < total_count || inactive_osds.size() > 0))
+            bool is_error = (total_done < total_count || inactive_osds.size() > 0 || error_count > 0);
+            if (parent->progress && is_error)
             {
                 fprintf(
-                    stderr, "Warning: Pool:%u,ID:%lu inode data may not have been fully removed.\n"
-                    " Use `vitastor-cli rm-data --pool %u --inode %lu` if you encounter it in listings.\n",
+                    stderr, "Warning: Pool:%u,ID:%ju inode data may not have been fully removed.\n"
+                    "Use `vitastor-cli rm-data --pool %u --inode %ju` if you encounter it in listings.\n",
                     pool_id, INODE_NO_POOL(inode), pool_id, INODE_NO_POOL(inode)
                 );
             }
             result = (cli_result_t){
-                .err = error_count > 0 ? EIO : 0,
-                .text = error_count > 0 ? "Some blocks were not removed" : (
+                .err = is_error && !down_ok ? EIO : 0,
+                .text = is_error ? "Some blocks were not removed" : (
                     "Done, inode "+std::to_string(INODE_NO_POOL(inode))+" from pool "+
                     std::to_string(pool_id)+" removed"),
                 .data = json11::Json::object {
@@ -246,6 +284,7 @@ std::function<bool(cli_result_t &)> cli_tool_t::start_rm_data(json11::Json cfg)
     {
         remover->inode = (remover->inode & (((uint64_t)1 << (64-POOL_ID_BITS)) - 1)) | (((uint64_t)remover->pool_id) << (64-POOL_ID_BITS));
     }
+    remover->down_ok = cfg["down_ok"].bool_value();
     remover->pool_id = INODE_POOL(remover->inode);
     remover->min_offset = cfg["min_offset"].uint64_value();
     return [remover](cli_result_t & result)

src/cli_status.cpp

@@ -106,7 +106,7 @@ resume_2:
             if (etcd_states[i]["error"].is_null())
             {
                 etcd_alive++;
-                etcd_db_size = etcd_states[i]["dbSizeInUse"].uint64_value();
+                etcd_db_size = etcd_states[i]["dbSize"].uint64_value();
             }
         }
         int mon_count = 0;
@@ -132,7 +132,7 @@ resume_2:
             auto kv = parent->cli->st_cli.parse_etcd_kv(osd_stats[i]);
             osd_num_t stat_osd_num = 0;
             char null_byte = 0;
-            int scanned = sscanf(kv.key.c_str() + parent->cli->st_cli.etcd_prefix.size(), "/osd/stats/%lu%c", &stat_osd_num, &null_byte);
+            int scanned = sscanf(kv.key.c_str() + parent->cli->st_cli.etcd_prefix.size(), "/osd/stats/%ju%c", &stat_osd_num, &null_byte);
             if (scanned != 1 || !stat_osd_num)
             {
                 fprintf(stderr, "Invalid key in etcd: %s\n", kv.key.c_str());
@@ -283,7 +283,7 @@ resume_2:
         }
         printf(
             "  cluster:\n"
-            "    etcd: %d / %ld up, %s database size\n"
+            "    etcd: %d / %zd up, %s database size\n"
             "    mon:  %d up%s\n"
             "    osd:  %d / %d up\n"
             "  \n"

src/cluster_client.cpp

@@ -265,7 +265,7 @@ void cluster_client_t::erase_op(cluster_op_t *op)
     }
 }
 
-void cluster_client_t::continue_ops(bool up_retry)
+void cluster_client_t::continue_ops(int time_passed)
 {
     if (!pgs_loaded)
     {
@@ -277,22 +277,27 @@ void cluster_client_t::continue_ops(bool up_retry)
         // Attempt to reenter the function
         return;
     }
+    int reset_duration = 0;
 restart:
     continuing_ops = 1;
     for (auto op = op_queue_head; op; )
     {
         cluster_op_t *next_op = op->next;
-        if (!op->up_wait || up_retry)
+        if (op->retry_after && time_passed)
         {
-            op->up_wait = false;
-            if (!op->prev_wait)
+            op->retry_after = op->retry_after > time_passed ? op->retry_after-time_passed : 0;
+            if (op->retry_after && (!reset_duration || op->retry_after < reset_duration))
             {
-                if (op->opcode == OSD_OP_SYNC)
-                    continue_sync(op);
-                else
-                    continue_rw(op);
+                reset_duration = op->retry_after;
             }
         }
+        if (!op->retry_after && !op->prev_wait)
+        {
+            if (op->opcode == OSD_OP_SYNC)
+                continue_sync(op);
+            else
+                continue_rw(op);
+        }
         op = next_op;
         if (continuing_ops == 2)
         {
@@ -300,6 +305,27 @@ restart:
         }
     }
     continuing_ops = 0;
+    reset_retry_timer(reset_duration);
+}
+
+void cluster_client_t::reset_retry_timer(int new_duration)
+{
+    if (retry_timeout_duration && retry_timeout_duration <= new_duration || !new_duration)
+    {
+        return;
+    }
+    if (retry_timeout_id)
+    {
+        tfd->clear_timer(retry_timeout_id);
+    }
+    retry_timeout_duration = new_duration;
+    retry_timeout_id = tfd->set_timer(retry_timeout_duration, false, [this](int)
+    {
+        int time_passed = retry_timeout_duration;
+        retry_timeout_id = 0;
+        retry_timeout_duration = 0;
+        continue_ops(time_passed);
+    });
 }
 
 void cluster_client_t::on_load_config_hook(json11::Json::object & etcd_global_config)
@@ -349,16 +375,28 @@ void cluster_client_t::on_load_config_hook(json11::Json::object & etcd_global_co
     {
         client_max_writeback_iodepth = DEFAULT_CLIENT_MAX_WRITEBACK_IODEPTH;
     }
-    // up_wait_retry_interval
-    up_wait_retry_interval = config["up_wait_retry_interval"].uint64_value();
-    if (!up_wait_retry_interval)
+    // client_retry_interval
+    client_retry_interval = config["client_retry_interval"].uint64_value();
+    if (!client_retry_interval)
     {
-        up_wait_retry_interval = 500;
+        client_retry_interval = 50;
     }
-    else if (up_wait_retry_interval < 50)
+    else if (client_retry_interval < 10)
     {
-        up_wait_retry_interval = 50;
+        client_retry_interval = 10;
     }
+    // client_eio_retry_interval
+    client_eio_retry_interval = 1000;
+    if (!config["client_eio_retry_interval"].is_null())
+    {
+        client_eio_retry_interval = config["client_eio_retry_interval"].uint64_value();
+        if (client_eio_retry_interval && client_eio_retry_interval < 10)
+        {
+            client_eio_retry_interval = 10;
+        }
+    }
+    // log_level
+    log_level = config["log_level"].uint64_value();
     msgr.parse_config(config);
     st_cli.parse_config(config);
     st_cli.load_pgs();
@@ -703,6 +741,8 @@ resume_1:
         }
         goto resume_2;
     }
+    // Protect from try_send completing the operation immediately
+    op->inflight_count++;
     for (int i = 0; i < op->parts.size(); i++)
     {
         if (!(op->parts[i].flags & PART_SENT))
@@ -712,22 +752,17 @@ resume_1:
                 // We'll need to retry again
                 if (op->parts[i].flags & PART_RETRY)
                 {
-                    op->up_wait = true;
-                    if (!retry_timeout_id)
-                    {
-                        retry_timeout_id = tfd->set_timer(up_wait_retry_interval, false, [this](int)
-                        {
-                            retry_timeout_id = 0;
-                            continue_ops(true);
-                        });
-                    }
+                    op->retry_after = client_retry_interval;
+                    reset_retry_timer(client_retry_interval);
                 }
                 op->state = 1;
             }
         }
     }
+    op->inflight_count--;
     if (op->state == 1)
     {
+        // Some suboperations have to be resent
         return 0;
     }
 resume_2:
@@ -774,10 +809,9 @@ resume_2:
         return 1;
     }
     else if (op->retval != 0 && !(op->flags & OP_FLUSH_BUFFER) &&
-        op->retval != -EPIPE && op->retval != -EIO && op->retval != -ENOSPC)
+        op->retval != -EPIPE && (op->retval != -EIO || !client_eio_retry_interval) && op->retval != -ENOSPC)
     {
         // Fatal error (neither -EPIPE, -EIO nor -ENOSPC)
-        // FIXME: Add a parameter to allow to not wait for EIOs (incomplete or corrupted objects) to heal
         erase_op(op);
         return 1;
     }
@@ -1147,31 +1181,30 @@ void cluster_client_t::handle_op_part(cluster_op_part_t *part)
         if (op->retval != -EINTR && op->retval != -EIO && op->retval != -ENOSPC)
         {
             stop_fd = part->op.peer_fd;
-            fprintf(
-                stderr, "%s operation failed on OSD %lu: retval=%ld (expected %d), dropping connection\n",
-                osd_op_names[part->op.req.hdr.opcode], part->osd_num, part->op.reply.hdr.retval, expected
-            );
+            if (op->retval != -EPIPE || log_level > 0)
+            {
+                fprintf(
+                    stderr, "%s operation failed on OSD %ju: retval=%jd (expected %d), dropping connection\n",
+                    osd_op_names[part->op.req.hdr.opcode], part->osd_num, part->op.reply.hdr.retval, expected
+                );
+            }
         }
         else
         {
             fprintf(
-                stderr, "%s operation failed on OSD %lu: retval=%ld (expected %d)\n",
+                stderr, "%s operation failed on OSD %ju: retval=%jd (expected %d)\n",
                 osd_op_names[part->op.req.hdr.opcode], part->osd_num, part->op.reply.hdr.retval, expected
             );
         }
         // All next things like timer, continue_sync/rw and stop_client may affect the operation again
         // So do all these things after modifying operation state, otherwise we may hit reenterability bugs
         // FIXME postpone such things to set_immediate here to avoid bugs
-        // Mark op->up_wait = true to retry operation after a short pause (not immediately)
-        op->up_wait = true;
-        if (!retry_timeout_id)
+        // Set op->retry_after to retry operation after a short pause (not immediately)
+        if (!op->retry_after)
         {
-            retry_timeout_id = tfd->set_timer(up_wait_retry_interval, false, [this](int)
-            {
-                retry_timeout_id = 0;
-                continue_ops(true);
-            });
+            op->retry_after = op->retval == -EIO ? client_eio_retry_interval : client_retry_interval;
         }
+        reset_retry_timer(op->retry_after);
         if (op->inflight_count == 0)
         {
             if (op->opcode == OSD_OP_SYNC)

src/cluster_client.h

@@ -59,7 +59,7 @@ protected:
     void *buf = NULL;
     cluster_op_t *orig_op = NULL;
     bool needs_reslice = false;
-    bool up_wait = false;
+    int retry_after = 0;
     int inflight_count = 0, done_count = 0;
     std::vector<cluster_op_part_t> parts;
     void *part_bitmaps = NULL;
@@ -91,10 +91,12 @@ class cluster_client_t
     uint64_t client_max_buffered_ops = 0;
     uint64_t client_max_writeback_iodepth = 0;
 
-    int log_level;
-    int up_wait_retry_interval = 500; // ms
+    int log_level = 0;
+    int client_retry_interval = 50; // ms
+    int client_eio_retry_interval = 1000; // ms
 
     int retry_timeout_id = 0;
+    int retry_timeout_duration = 0;
     std::vector<cluster_op_t*> offline_ops;
     cluster_op_t *op_queue_head = NULL, *op_queue_tail = NULL;
     writeback_cache_t *wb = NULL;
@@ -131,7 +133,7 @@ public:
 
     bool get_immediate_commit(uint64_t inode);
 
-    void continue_ops(bool up_retry = false);
+    void continue_ops(int time_passed = 0);
     inode_list_t *list_inode_start(inode_t inode,
         std::function<void(inode_list_t* lst, std::set<object_id>&& objects, pg_num_t pg_num, osd_num_t primary_osd, int status)> callback);
     int list_pg_count(inode_list_t *lst);
@@ -152,6 +154,7 @@ protected:
     int continue_rw(cluster_op_t *op);
     bool check_rw(cluster_op_t *op);
     void slice_rw(cluster_op_t *op);
+    void reset_retry_timer(int new_duration);
     bool try_send(cluster_op_t *op, int i);
     int continue_sync(cluster_op_t *op);
     void send_sync(cluster_op_t *op, cluster_op_part_t *part);

src/cluster_client_list.cpp

@@ -226,7 +226,7 @@ void cluster_client_t::send_list(inode_list_osd_t *cur_list)
     {
         if (op->reply.hdr.retval < 0)
         {
-            fprintf(stderr, "Failed to get PG %u/%u object list from OSD %lu (retval=%ld), skipping\n",
+            fprintf(stderr, "Failed to get PG %u/%u object list from OSD %ju (retval=%jd), skipping\n",
                 cur_list->pg->lst->pool_id, cur_list->pg->pg_num, cur_list->osd_num, op->reply.hdr.retval);
         }
         else
@@ -236,7 +236,7 @@ void cluster_client_t::send_list(inode_list_osd_t *cur_list)
                 // Unstable objects, if present, mean that someone still writes into the inode. Warn the user about it.
                 cur_list->pg->has_unstable = true;
                 fprintf(
-                    stderr, "[PG %u/%u] Inode still has %lu unstable object versions out of total %lu - is it still open?\n",
+                    stderr, "[PG %u/%u] Inode still has %ju unstable object versions out of total %ju - is it still open?\n",
                     cur_list->pg->lst->pool_id, cur_list->pg->pg_num, op->reply.hdr.retval - op->reply.sec_list.stable_count,
                     op->reply.hdr.retval
                 );
@@ -244,7 +244,7 @@ void cluster_client_t::send_list(inode_list_osd_t *cur_list)
             if (log_level > 0)
             {
                 fprintf(
-                    stderr, "[PG %u/%u] Got inode object list from OSD %lu: %ld object versions\n",
+                    stderr, "[PG %u/%u] Got inode object list from OSD %ju: %jd object versions\n",
                     cur_list->pg->lst->pool_id, cur_list->pg->pg_num, cur_list->osd_num, op->reply.hdr.retval
                 );
             }

src/disk_simple_offsets.cpp

@@ -47,7 +47,7 @@ void disk_tool_simple_offsets(json11::Json cfg, bool json_output)
     if (!bitmap_granularity)
         bitmap_granularity = DEFAULT_BITMAP_GRANULARITY;
     if (!journal_size)
-        journal_size = 16*1024*1024;
+        journal_size = 32*1024*1024;
     if (!device_block_size)
         device_block_size = 4096;
     if (!data_csum_type)
@@ -75,9 +75,9 @@ void disk_tool_simple_offsets(json11::Json cfg, bool json_output)
             if (st.st_blksize < device_block_size)
             {
                 fprintf(
-                    stderr, "Warning: %s reports %lu byte blocks, but we use %lu."
-                    " Set --device_block_size=%lu if you're sure it works well with %lu byte blocks.\n",
-                    device.c_str(), st.st_blksize, device_block_size, st.st_blksize, st.st_blksize
+                    stderr, "Warning: %s reports %ju byte blocks, but we use %ju."
+                    " Set --device_block_size=%ju if you're sure it works well with %ju byte blocks.\n",
+                    device.c_str(), (uint64_t)st.st_blksize, device_block_size, (uint64_t)st.st_blksize, (uint64_t)st.st_blksize
                 );
             }
         }
@@ -99,19 +99,19 @@ void disk_tool_simple_offsets(json11::Json cfg, bool json_output)
     if (device_block_size < 512 || device_block_size > 1048576 ||
         device_block_size & (device_block_size-1) != 0)
     {
-        fprintf(stderr, "Invalid device block size specified: %lu\n", device_block_size);
+        fprintf(stderr, "Invalid device block size specified: %ju\n", device_block_size);
         exit(1);
     }
     if (data_block_size < device_block_size || data_block_size > MAX_DATA_BLOCK_SIZE ||
         data_block_size & (data_block_size-1) != 0)
     {
-        fprintf(stderr, "Invalid object size specified: %lu\n", data_block_size);
+        fprintf(stderr, "Invalid object size specified: %ju\n", data_block_size);
         exit(1);
     }
     if (bitmap_granularity < device_block_size || bitmap_granularity > data_block_size ||
         bitmap_granularity & (bitmap_granularity-1) != 0)
     {
-        fprintf(stderr, "Invalid bitmap granularity specified: %lu\n", bitmap_granularity);
+        fprintf(stderr, "Invalid bitmap granularity specified: %ju\n", bitmap_granularity);
         exit(1);
     }
     if (csum_block_size && (data_block_size % csum_block_size))
@@ -145,8 +145,8 @@ void disk_tool_simple_offsets(json11::Json cfg, bool json_output)
     {
         // Env
         printf(
-            "meta_block_size=%lu\njournal_block_size=%lu\ndata_size=%lu\n"
-            "data_device=%s\njournal_offset=%lu\nmeta_offset=%lu\ndata_offset=%lu\n",
+            "meta_block_size=%ju\njournal_block_size=%ju\ndata_size=%ju\n"
+            "data_device=%s\njournal_offset=%ju\nmeta_offset=%ju\ndata_offset=%ju\n",
             device_block_size, device_block_size, device_size-data_offset,
             device.c_str(), journal_offset, meta_offset, data_offset
         );
@@ -160,14 +160,14 @@ void disk_tool_simple_offsets(json11::Json cfg, bool json_output)
         }
         if (device_block_size != 4096)
         {
-            printf("--meta_block_size %lu\n--journal_block_size %lu\n", device_block_size, device_block_size);
+            printf("--meta_block_size %ju\n--journal_block_size %ju\n", device_block_size, device_block_size);
         }
         if (orig_device_size)
         {
-            printf("--data_size %lu\n", device_size-data_offset);
+            printf("--data_size %ju\n", device_size-data_offset);
         }
         printf(
-            "--data_device %s\n--journal_offset %lu\n--meta_offset %lu\n--data_offset %lu\n",
+            "--data_device %s\n--journal_offset %ju\n--meta_offset %ju\n--data_offset %ju\n",
             device.c_str(), journal_offset, meta_offset, data_offset
         );
     }

src/disk_tool.cpp

@@ -167,7 +167,7 @@ static const char *help_text =
     "  Calculate offsets for old simple&stupid (no superblock) OSD deployment. Options:\n"
     "    --object_size 128k       Set blockstore block size\n"
     "    --bitmap_granularity 4k  Set bitmap granularity\n"
-    "    --journal_size 16M       Set journal size\n"
+    "    --journal_size 32M       Set journal size\n"
     "    --data_csum_type none    Set data checksum type (crc32c or none)\n"
     "    --csum_block_size 4k     Set data checksum block size\n"
     "    --device_block_size 4k   Set device block size\n"

src/disk_tool.h

@@ -4,7 +4,7 @@
 #pragma once
 
 #ifndef _LARGEFILE64_SOURCE
-#define _LARGEFILE64_SOURCE 1
+#define _LARGEFILE64_SOURCE
 #endif
 
 #include <map>