Release 1.4.6

Unwavering stabilization of 1.4.x, continued :-)

- Include the accidentally lost part of 1.4.5 journal trimming fix
- Fix a possible OSD crash with "BUG: Attempt to overwrite used offset"
  which was probably present for long time, but became apparent after
  fixing flapping tests in CI
- Fix remaining flapping tests in CI. It was the first time when tests
  actually passed without retries :-)

.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 "1.4.6")
 
 add_subdirectory(src)

csi/Dockerfile

@@ -35,9 +35,9 @@ RUN (echo deb http://vitastor.io/debian bookworm main > /etc/apt/sources.list.d/
     wget -q -O /etc/apt/trusted.gpg.d/vitastor.gpg https://vitastor.io/debian/pubkey.gpg && \
     apt-get update && \
     apt-get install -y vitastor-client && \
-    apt-get download qemu-system-common && \
-    apt-get download qemu-block-extra && \
-    dpkg -x qemu-system-common*.deb tmp1 && \
+    wget https://vitastor.io/archive/qemu/qemu-bookworm-8.1.2%2Bds-1%2Bvitastor1/qemu-utils_8.1.2%2Bds-1%2Bvitastor1_amd64.deb && \
+    wget https://vitastor.io/archive/qemu/qemu-bookworm-8.1.2%2Bds-1%2Bvitastor1/qemu-block-extra_8.1.2%2Bds-1%2Bvitastor1_amd64.deb && \
+    dpkg -x qemu-utils*.deb tmp1 && \
     dpkg -x qemu-block-extra*.deb tmp1 && \
     cp -a tmp1/usr/bin/qemu-storage-daemon /usr/bin/ && \
     mkdir -p /usr/lib/x86_64-linux-gnu/qemu && \

csi/Makefile

@@ -1,4 +1,4 @@
-VERSION ?= v1.3.1
+VERSION ?= v1.4.6
 
 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:v1.4.6
           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:v1.4.6
           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 = "1.4.6"
 )
 
 // Config struct fills the parameters of request or user input

csi/src/controllerserver.go

@@ -97,6 +97,15 @@ func GetConnectionParams(params map[string]string) (map[string]string, error)
         }
     case []string:
         etcdUrl = config["etcd_address"].([]string)
+    case []interface{}:
+        for _, url := range config["etcd_address"].([]interface{})
+        {
+            s, ok := url.(string)
+            if (ok)
+            {
+                etcdUrl = append(etcdUrl, s)
+            }
+        }
     }
     if (len(etcdUrl) == 0)
     {
@@ -105,8 +114,9 @@ func GetConnectionParams(params map[string]string) (map[string]string, error)
     return ctxVars, nil
 }
 
-func system(program string, args ...string) ([]byte, error)
+func system(program string, args ...string) ([]byte, []byte, error)
 {
+    klog.Infof("Running "+program+" "+strings.Join(args, " "))
     c := exec.Command(program, args...)
     var stdout, stderr bytes.Buffer
     c.Stdout, c.Stderr = &stdout, &stderr
@@ -115,9 +125,9 @@ func system(program string, args ...string) ([]byte, error)
     {
         stdoutStr, stderrStr := string(stdout.Bytes()), string(stderr.Bytes())
         klog.Errorf(program+" "+strings.Join(args, " ")+" failed: %s, status %s\n", stdoutStr+stderrStr, err)
-        return nil, status.Error(codes.Internal, stdoutStr+stderrStr+" (status "+err.Error()+")")
+        return nil, nil, status.Error(codes.Internal, stdoutStr+stderrStr+" (status "+err.Error()+")")
     }
-    return stdout.Bytes(), nil
+    return stdout.Bytes(), stderr.Bytes(), nil
 }
 
 func invokeCLI(ctxVars map[string]string, args []string) ([]byte, error)
@@ -126,7 +136,8 @@ func invokeCLI(ctxVars map[string]string, args []string) ([]byte, error)
     {
         args = append(args, "--config_path", ctxVars["configPath"])
     }
-    return system("/usr/bin/vitastor-cli", args...)
+    stdout, _, err := system("/usr/bin/vitastor-cli", args...)
+    return stdout, err
 }
 
 // Create the volume

csi/src/nodeserver.go

@@ -7,12 +7,14 @@ import (
     "context"
     "errors"
     "encoding/json"
+    "fmt"
     "os"
     "os/exec"
     "path/filepath"
     "strconv"
     "strings"
     "syscall"
+    "time"
 
     "google.golang.org/grpc/codes"
     "google.golang.org/grpc/status"
@@ -31,6 +33,7 @@ type NodeServer struct
     useVduse bool
     stateDir string
     mounter mount.Interface
+    restartInterval time.Duration
 }
 
 type DeviceState struct
@@ -64,6 +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
 }
@@ -154,8 +167,13 @@ func (ns *NodeServer) mapNbd(volName string, ctxVars map[string]string, readonly
     {
         args = append(args, "--readonly", "1")
     }
-    dev, err := system("/usr/bin/vitastor-nbd", args...)
-    return strings.TrimSpace(string(dev)), err
+    stdout, stderr, err := system("/usr/bin/vitastor-nbd", args...)
+    dev := strings.TrimSpace(string(stdout))
+    if (dev == "")
+    {
+        return "", fmt.Errorf("vitastor-nbd did not return the name of NBD device. output: %s", stderr)
+    }
+    return dev, err
 }
 
 func (ns *NodeServer) unmapNbd(devicePath string)
@@ -190,6 +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)
     {
@@ -221,7 +240,7 @@ func startStorageDaemon(vdpaId, volName, pidFile, configPath string, readonly bo
     {
         writable = "false"
     }
-    _, err := system(
+    _, _, err := system(
         "/usr/bin/qemu-storage-daemon", "--daemonize", "--pidfile", pidFile, "--blockdev", string(blockSpecJson),
         "--export", "vduse-blk,id="+vdpaId+",node-name=disk1,name="+vdpaId+",num-queues=16,queue-size=128,writable="+writable,
     )
@@ -234,7 +253,7 @@ func (ns *NodeServer) mapVduse(volName string, ctxVars map[string]string, readon
     stateFd, err := os.CreateTemp(ns.stateDir, "vitastor-vduse-*.json")
     if (err != nil)
     {
-        return "", "", status.Error(codes.Internal, err.Error())
+        return "", "", err
     }
     stateFile := stateFd.Name()
     stateFd.Close()
@@ -246,11 +265,12 @@ func (ns *NodeServer) mapVduse(volName string, ctxVars map[string]string, readon
     if (err == nil)
     {
         // Add device to VDPA bus
-        _, err = system("/sbin/vdpa", "-j", "dev", "add", "name", vdpaId, "mgmtdev", "vduse")
+        _, _, err = system("/sbin/vdpa", "-j", "dev", "add", "name", vdpaId, "mgmtdev", "vduse")
         if (err == nil)
         {
             // Find block device name
-            matches, err := filepath.Glob("/sys/bus/vdpa/devices/"+vdpaId+"/virtio*/block/*")
+            var matches []string
+            matches, err = filepath.Glob("/sys/bus/vdpa/devices/"+vdpaId+"/virtio*/block/*")
             if (err == nil && len(matches) == 0)
             {
                 err = errors.New("/sys/bus/vdpa/devices/"+vdpaId+"/virtio*/block/* is not found")
@@ -277,21 +297,14 @@ func (ns *NodeServer) mapVduse(volName string, ctxVars map[string]string, readon
                     }
                 }
             }
-            if (err != nil)
-            {
-                err = status.Error(codes.Internal, err.Error())
-            }
         }
-        if (err != nil)
+        killErr := killByPidFile(pidFile)
+        if (killErr != nil)
         {
-            killErr := killByPidFile(pidFile)
-            if (killErr != nil)
-            {
-                klog.Errorf("Failed to kill started qemu-storage-daemon: %v", killErr)
-            }
-            os.Remove(stateFile)
-            os.Remove(pidFile)
+            klog.Errorf("Failed to kill started qemu-storage-daemon: %v", killErr)
         }
+        os.Remove(stateFile)
+        os.Remove(pidFile)
     }
     return "", "", err
 }
@@ -337,7 +350,7 @@ func (ns *NodeServer) unmapVduseById(vdpaId string)
     }
     else
     {
-        _, _ = system("/sbin/vdpa", "-j", "dev", "del", vdpaId)
+        _, _, _ = system("/sbin/vdpa", "-j", "dev", "del", vdpaId)
     }
     stateFile := ns.stateDir + vdpaId + ".json"
     os.Remove(stateFile)
@@ -363,6 +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"
@@ -377,7 +405,7 @@ func (ns *NodeServer) restoreVduseDaemons()
     }
     devList := make(map[string]interface{})
     // example output: {"dev":{"test1":{"type":"block","mgmtdev":"vduse","vendor_id":0,"max_vqs":16,"max_vq_size":128}}}
-    devListJSON, err := system("/sbin/vdpa", "-j", "dev", "list")
+    devListJSON, _, err := system("/sbin/vdpa", "-j", "dev", "list")
     if (err != nil)
     {
         return
@@ -456,13 +484,13 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
                 if (err != nil)
                 {
                     klog.Errorf("failed to create block device mount target %s with error: %v", targetPath, err)
-                    return nil, status.Error(codes.Internal, err.Error())
+                    return nil, err
                 }
                 err = pathFile.Close()
                 if (err != nil)
                 {
                     klog.Errorf("failed to close %s with error: %v", targetPath, err)
-                    return nil, status.Error(codes.Internal, err.Error())
+                    return nil, err
                 }
             }
             else
@@ -471,13 +499,13 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
                 if (err != nil)
                 {
                     klog.Errorf("failed to create fs mount target %s with error: %v", targetPath, err)
-                    return nil, status.Error(codes.Internal, err.Error())
+                    return nil, err
                 }
             }
         }
         else
         {
-            return nil, status.Error(codes.Internal, err.Error())
+            return nil, err
         }
     }
 
@@ -597,7 +625,7 @@ unmap:
     {
         ns.unmapVduseById(vdpaId)
     }
-    return nil, status.Error(codes.Internal, err.Error())
+    return nil, err
 }
 
 // NodeUnpublishVolume unmounts the volume from the target path
@@ -612,7 +640,7 @@ func (ns *NodeServer) NodeUnpublishVolume(ctx context.Context, req *csi.NodeUnpu
         {
             return nil, status.Error(codes.NotFound, "Target path not found")
         }
-        return nil, status.Error(codes.Internal, err.Error())
+        return nil, err
     }
     if (devicePath == "")
     {
@@ -625,7 +653,7 @@ func (ns *NodeServer) NodeUnpublishVolume(ctx context.Context, req *csi.NodeUnpu
     err = mount.CleanupMountPoint(targetPath, ns.mounter, false)
     if (err != nil)
     {
-        return nil, status.Error(codes.Internal, err.Error())
+        return nil, err
     }
     // unmap NBD device
     if (refCount == 1)

debian/changelog

@@ -1,4 +1,4 @@
-vitastor (1.3.1-1) unstable; urgency=medium
+vitastor (1.4.6-1) unstable; urgency=medium
 
   * Bugfixes
 

debian/patched-qemu.Dockerfile

@@ -7,7 +7,7 @@ ARG REL=
 
 WORKDIR /root
 
-RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" ]; then \
+RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" -o "$REL" = "bookworm" ]; then \
         echo "deb http://deb.debian.org/debian $REL-backports main" >> /etc/apt/sources.list; \
         echo >> /etc/apt/preferences; \
         echo 'Package: *' >> /etc/apt/preferences; \
@@ -45,7 +45,7 @@ RUN set -e; \
     rm -rf /root/packages/qemu-$REL/*; \
     cd /root/packages/qemu-$REL; \
     dpkg-source -x /root/qemu*.dsc; \
-    QEMU_VER=$(ls -d qemu*/ | perl -pe 's!^.*(\d+\.\d+).*!$1!'); \
+    QEMU_VER=$(ls -d qemu*/ | perl -pe 's!^.*?(\d+\.\d+).*!$1!'); \
     D=$(ls -d qemu*/); \
     cp /root/vitastor/patches/qemu-$QEMU_VER-vitastor.patch ./qemu-*/debian/patches; \
     echo qemu-$QEMU_VER-vitastor.patch >> $D/debian/patches/series; \

debian/vitastor.Dockerfile

@@ -35,8 +35,8 @@ RUN set -e -x; \
     mkdir -p /root/packages/vitastor-$REL; \
     rm -rf /root/packages/vitastor-$REL/*; \
     cd /root/packages/vitastor-$REL; \
-    cp -r /root/vitastor vitastor-1.3.1; \
-    cd vitastor-1.3.1; \
+    cp -r /root/vitastor vitastor-1.4.6; \
+    cd vitastor-1.4.6; \
     ln -s /root/fio-build/fio-*/ ./fio; \
     FIO=$(head -n1 fio/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
     ls /usr/include/linux/raw.h || cp ./debian/raw.h /usr/include/linux/raw.h; \
@@ -49,8 +49,8 @@ RUN set -e -x; \
     rm -rf a b; \
     echo "dep:fio=$FIO" > debian/fio_version; \
     cd /root/packages/vitastor-$REL; \
-    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_1.3.1.orig.tar.xz vitastor-1.3.1; \
-    cd vitastor-1.3.1; \
+    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_1.4.6.orig.tar.xz vitastor-1.4.6; \
+    cd vitastor-1.4.6; \
     V=$(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

@@ -6,8 +6,8 @@
 
 # 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_max_dirty_bytes](#client_max_dirty_bytes)
 - [client_max_dirty_ops](#client_max_dirty_ops)

docs/config/client.ru.md

@@ -6,7 +6,7 @@
 
 # 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_max_dirty_bytes](#client_max_dirty_bytes)

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

@@ -215,8 +215,8 @@ is scheduled.
 ## up_wait_retry_interval
 
 - Type: milliseconds
-- Default: 500
-- Minimum: 50
+- Default: 50
+- Minimum: 10
 - Can be changed online: yes
 
 OSDs respond to clients with a special error code when they receive I/O

docs/config/network.ru.md

@@ -224,8 +224,8 @@ OSD в любом случае согласовывают реальное зн
 ## up_wait_retry_interval
 
 - Тип: миллисекунды
-- Значение по умолчанию: 500
-- Минимальное значение: 50
+- Значение по умолчанию: 50
+- Минимальное значение: 10
 - Можно менять на лету: да
 
 Когда OSD получают от клиентов запросы ввода-вывода, относящиеся к не

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/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

@@ -245,8 +245,8 @@
     повторная попытка соединения.
 - name: up_wait_retry_interval
   type: ms
-  min: 50
-  default: 500
+  min: 10
+  default: 50
   online: true
   info: |
     OSDs respond to clients with a special error code when they receive I/O

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/packages.en.md

@@ -18,7 +18,7 @@
     stable version from 0.9.x branch instead of 1.x
 - For Debian 10 (Buster) also enable backports repository:
   `deb http://deb.debian.org/debian buster-backports main`
-- Install packages: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu`
+- Install packages: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu-system-x86`
 
 ## CentOS
 

docs/installation/packages.ru.md

@@ -18,7 +18,7 @@
     установить последнюю стабильную версию из ветки 0.9.x вместо 1.x
 - Для Debian 10 (Buster) также включите репозиторий backports:
   `deb http://deb.debian.org/debian buster-backports main`
-- Установите пакеты: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu`
+- Установите пакеты: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu-system-x86`
 
 ## CentOS
 

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/disk.en.md

@@ -17,6 +17,7 @@ It supports the following commands:
 - [purge](#purge)
 - [read-sb](#read-sb)
 - [write-sb](#write-sb)
+- [update-sb](#update-sb)
 - [udev](#udev)
 - [exec-osd](#exec-osd)
 - [pre-exec](#pre-exec)
@@ -182,6 +183,14 @@ Try to read Vitastor OSD superblock from `<device>` and print it in JSON format.
 
 Read JSON from STDIN and write it into Vitastor OSD superblock on `<device>`.
 
+## update-sb
+
+`vitastor-disk update-sb <device> [--force] [--<parameter> <value>] [...]`
+
+Read Vitastor OSD superblock from <device>, update parameters in it and write it back.
+
+`--force` allows to ignore validation errors.
+
 ## udev
 
 `vitastor-disk udev <device>`

docs/usage/disk.ru.md

@@ -17,6 +17,7 @@ vitastor-disk - инструмент командной строки для уп
 - [purge](#purge)
 - [read-sb](#read-sb)
 - [write-sb](#write-sb)
+- [update-sb](#update-sb)
 - [udev](#udev)
 - [exec-osd](#exec-osd)
 - [pre-exec](#pre-exec)
@@ -187,6 +188,15 @@ throttle_target_mbs, throttle_target_parallelism, throttle_threshold_us.
 
 Прочитать JSON со стандартного ввода и записать его в суперблок OSD на диск `<device>`.
 
+## update-sb
+
+`vitastor-disk update-sb <device> [--force] [--<параметр> <значение>] [...]`
+
+Прочитать суперблок OSD с диска `<device>`, изменить в нём заданные параметры и записать обратно.
+
+Опция `--force` позволяет читать суперблок, даже если он считается некорректным
+из-за ошибок валидации.
+
 ## udev
 
 `vitastor-disk udev <device>`

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
 ```
 
@@ -146,7 +149,7 @@ Example performance comparison:
 | 4k random read Q1    | 9600 iops   | 7640 iops   | 7780 iops   |
 
 To try VDUSE you need at least Linux 5.15, built with VDUSE support
-(CONFIG_VIRTIO_VDPA=m, CONFIG_VDPA_USER=m, CONFIG_VIRTIO_VDPA=m).
+(CONFIG_VDPA=m, CONFIG_VDPA_USER=m, CONFIG_VIRTIO_VDPA=m).
 
 Debian Linux kernels have these options disabled by now, so if you want to try it on Debian,
 use a kernel from Ubuntu [kernel-ppa/mainline](https://kernel.ubuntu.com/~kernel-ppa/mainline/), Proxmox,

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
 ```
 
@@ -149,7 +152,7 @@ VDUSE - на данный момент лучший интерфейс для п
 | 4k случайное чтение Q1   | 9600 iops   | 7640 iops   | 7780 iops   |
 
 Чтобы попробовать VDUSE, вам нужно ядро Linux как минимум версии 5.15, собранное с поддержкой
-VDUSE (CONFIG_VIRTIO_VDPA=m, CONFIG_VDPA_USER=m, CONFIG_VIRTIO_VDPA=m).
+VDUSE (CONFIG_VDPA=m, CONFIG_VDPA_USER=m, CONFIG_VIRTIO_VDPA=m).
 
 В ядрах в Debian Linux поддержка пока отключена по умолчанию, так что чтобы попробовать VDUSE
 на Debian, поставьте ядро из Ubuntu [kernel-ppa/mainline](https://kernel.ubuntu.com/~kernel-ppa/mainline/),

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, ... },
@@ -91,7 +92,7 @@ const etcd_tree = {
             peer_connect_timeout: 5, // seconds. min: 1
             osd_idle_timeout: 5, // seconds. min: 1
             osd_ping_timeout: 5, // seconds. min: 1
-            up_wait_retry_interval: 500, // ms. min: 50
+            up_wait_retry_interval: 50, // ms. min: 10
             max_etcd_attempts: 5,
             etcd_quick_timeout: 1000, // ms
             etcd_slow_timeout: 5000, // ms
@@ -110,7 +111,15 @@ 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 +390,8 @@ 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 +402,7 @@ 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 +480,10 @@ 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 +500,11 @@ 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 +605,7 @@ 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 +621,7 @@ 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 +675,12 @@ 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 +797,9 @@ 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 +1242,89 @@ 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 +1339,47 @@ 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 +1420,97 @@ 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 +1520,8 @@ 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 +1640,13 @@ 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 +1747,13 @@ 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 +1769,14 @@ 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 +2016,14 @@ 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": "1.4.6",
   "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 = '1.4.6'
 
 LOG = logging.getLogger(__name__)
 

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-1.4.6/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-1.4.6$(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-1.4.6.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:        1.4.6
 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-1.4.6.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-1.4.6.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:        1.4.6
 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-1.4.6.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-1.4.6.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:        1.4.6
 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-1.4.6.el9.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

src/CMakeLists.txt

@@ -16,7 +16,7 @@ if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
 	set(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
 endif()
 
-add_definitions(-DVERSION="1.3.1")
+add_definitions(-DVERSION="1.4.6")
 add_definitions(-Wall -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith -fdiagnostics-color=always -fno-omit-frame-pointer -I ${CMAKE_SOURCE_DIR}/src)
 add_link_options(-fno-omit-frame-pointer)
 if (${WITH_ASAN})

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_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);
@@ -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();
     }
 }
@@ -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;
         }
@@ -416,6 +415,7 @@ stop_flusher:
                 flusher->sync_to_repeat.erase(cur.oid);
                 if (!flusher->try_find_other(dirty_end, cur))
                 {
+                    cur.oid = {};
                     goto stop_flusher;
                 }
             }
@@ -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:
@@ -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)
     {
@@ -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)
@@ -283,7 +277,8 @@ 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
@@ -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

@@ -376,6 +376,7 @@ 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
@@ -732,8 +733,9 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
     resume:
         while (pos < bs->journal.block_size)
         {
-            journal_entry *je = (journal_entry*)((uint8_t*)buf + proc_pos - done_pos + pos);
-            if (je->magic != JOURNAL_MAGIC || je_crc32(je) != je->crc32 ||
+            auto buf_pos = proc_pos - done_pos + pos;
+            journal_entry *je = (journal_entry*)((uint8_t*)buf + buf_pos);
+            if (je->magic != JOURNAL_MAGIC || buf_pos+je->size > len || je_crc32(je) != je->crc32 ||
                 je->type < JE_MIN || je->type > JE_MAX || started && je->crc32_prev != crc32_last)
             {
                 if (pos == 0)
@@ -1180,6 +1182,7 @@ 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_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

@@ -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;
@@ -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

@@ -215,7 +215,7 @@ void blockstore_impl_t::erase_dirty(blockstore_dirty_db_t::iterator dirty_start,
 #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,
@@ -225,6 +225,11 @@ void blockstore_impl_t::erase_dirty(blockstore_dirty_db_t::iterator dirty_start,
         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

@@ -412,11 +412,40 @@ 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 +474,7 @@ 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 +485,7 @@ 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++;
                 }
             }

src/blockstore_sync.cpp

@@ -76,6 +76,7 @@ int blockstore_impl_t::continue_sync(blockstore_op_t *op)
         // 2nd step: Data device is synced, prepare & write journal entries
         // Check space in the journal and journal memory buffers
         blockstore_journal_check_t space_check(this);
+        auto reservation = (unstable_writes.size()+unstable_unsynced+PRIV(op)->sync_big_writes.size())*journal.block_size;
         if (dsk.csum_block_size)
         {
             // More complex check because all journal entries have different lengths
@@ -85,16 +86,14 @@ 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, left ? 0 : reservation))
                 {
                     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, reservation))
         {
             return 0;
         }
@@ -117,7 +116,10 @@ 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(

src/blockstore_write.cpp

@@ -129,7 +129,7 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
     }
     bool imm = (op->len < dsk.data_block_size ? (immediate_commit != IMMEDIATE_NONE) : (immediate_commit == IMMEDIATE_ALL));
     if (wait_big && !is_del && !deleted && op->len < dsk.data_block_size && !imm ||
-        !imm && 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;
@@ -320,7 +320,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
         blockstore_journal_check_t space_check(this);
         if (!space_check.check_available(op, unsynced_big_write_count + 1,
             sizeof(journal_entry_big_write) + dsk.clean_dyn_size,
-            (unstable_writes.size()+unstable_unsynced)*journal.block_size))
+            (unstable_writes.size()+unstable_unsynced+((dirty_it->second.state & BS_ST_INSTANT) ? 0 : 1))*journal.block_size))
         {
             return 0;
         }
@@ -412,7 +412,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
                 sizeof(journal_entry_big_write) + dsk.clean_dyn_size, 0)
             || !space_check.check_available(op, 1,
                 sizeof(journal_entry_small_write) + dyn_size,
-                op->len + (unstable_writes.size()+unstable_unsynced)*journal.block_size))
+                op->len + (unstable_writes.size()+unstable_unsynced+((dirty_it->second.state & BS_ST_INSTANT) ? 0 : 1))*journal.block_size))
         {
             return 0;
         }
@@ -436,7 +436,19 @@ 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 %08lx is used by %lx:%lx v%lu (%lu refs) BUT used_start=%lx next_free=%lx\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(
@@ -549,7 +561,7 @@ 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;
         }
@@ -558,7 +570,19 @@ 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 %08lx is used by %lx:%lx v%lu (%lu refs) BUT used_start=%lx next_free=%lx\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(
@@ -593,7 +617,7 @@ resume_4:
 #endif
         bool is_big = (dirty_it->second.state & BS_ST_TYPE_MASK) == BS_ST_BIG_WRITE;
         bool imm = is_big ? (immediate_commit == IMMEDIATE_ALL) : (immediate_commit != IMMEDIATE_NONE);
-        bool is_instant = ((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];

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
@@ -48,6 +49,7 @@ struct rm_inode_t
                 .objects = objects,
                 .obj_count = objects.size(),
                 .obj_done = 0,
+                .synced = parent->cli->get_immediate_commit(inode),
             });
             if (min_offset == 0)
             {
@@ -151,6 +153,37 @@ 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 %lu (retval=%ld)\n",
+                        cur_list->rm_osd_num, op->reply.hdr.retval);
+                    error_count++;
+                }
+                delete op;
+                continue_delete();
+            };
+            cur_list->in_flight++;
+            parent->cli->msgr.outbox_push(op);
+        }
     }
 
     void continue_delete()
@@ -161,7 +194,8 @@ 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);
@@ -187,7 +221,7 @@ struct rm_inode_t
             {
                 fprintf(stderr, "\n");
             }
-            if (parent->progress && (total_done < total_count || inactive_osds.size() > 0))
+            if (parent->progress && (total_done < total_count || inactive_osds.size() > 0 || error_count > 0))
             {
                 fprintf(
                     stderr, "Warning: Pool:%u,ID:%lu inode data may not have been fully removed.\n"

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;

src/cluster_client.cpp

@@ -352,13 +352,15 @@ void cluster_client_t::on_load_config_hook(json11::Json::object & etcd_global_co
     // up_wait_retry_interval
     up_wait_retry_interval = config["up_wait_retry_interval"].uint64_value();
     if (!up_wait_retry_interval)
-    {
-        up_wait_retry_interval = 500;
-    }
-    else if (up_wait_retry_interval < 50)
     {
         up_wait_retry_interval = 50;
     }
+    else if (up_wait_retry_interval < 10)
+    {
+        up_wait_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 +705,8 @@ 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))
@@ -726,8 +730,10 @@ resume_1:
             }
         }
     }
+    op->inflight_count--;
     if (op->state == 1)
     {
+        // Some suboperations have to be resent
         return 0;
     }
 resume_2:
@@ -1147,10 +1153,13 @@ 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 %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
+                );
+            }
         }
         else
         {

src/cluster_client.h

@@ -91,7 +91,7 @@ class cluster_client_t
     uint64_t client_max_buffered_ops = 0;
     uint64_t client_max_writeback_iodepth = 0;
 
-    int log_level;
+    int log_level = 0;
     int up_wait_retry_interval = 500; // ms
 
     int retry_timeout_id = 0;

src/disk_tool.cpp

@@ -127,6 +127,10 @@ static const char *help_text =
     "vitastor-disk write-sb <device>\n"
     "  Read JSON from STDIN and write it into Vitastor OSD superblock on <device>.\n"
     "\n"
+    "vitastor-disk update-sb <device> [--force] [--<parameter> <value>] [...]\n"
+    "  Read Vitastor OSD superblock from <device>, update parameters in it and write it back.\n"
+    "  --force allows to ignore validation errors.\n"
+    "\n"
     "vitastor-disk udev <device>\n"
     "  Try to read Vitastor OSD superblock from <device> and print variables for udev.\n"
     "\n"
@@ -363,6 +367,15 @@ int main(int argc, char *argv[])
         }
         return self.write_sb(cmd[1]);
     }
+    else if (!strcmp(cmd[0], "update-sb"))
+    {
+        if (cmd.size() != 2)
+        {
+            fprintf(stderr, "Exactly 1 device path argument is required\n");
+            return 1;
+        }
+        return self.update_sb(cmd[1]);
+    }
     else if (!strcmp(cmd[0], "start") || !strcmp(cmd[0], "stop") ||
         !strcmp(cmd[0], "restart") || !strcmp(cmd[0], "enable") || !strcmp(cmd[0], "disable"))
     {

src/disk_tool.h

@@ -109,6 +109,7 @@ struct disk_tool_t
     int udev_import(std::string device);
     int read_sb(std::string device);
     int write_sb(std::string device);
+    int update_sb(std::string device);
     int exec_osd(std::string device);
     int systemd_start_stop_osds(const std::vector<std::string> & cmd, const std::vector<std::string> & devices);
     int pre_exec_osd(std::string device);

src/disk_tool_prepare.cpp

@@ -8,6 +8,7 @@
 int disk_tool_t::prepare_one(std::map<std::string, std::string> options, int is_hdd)
 {
     static const char *allow_additional_params[] = {
+        "autosync_writes",
         "data_io",
         "meta_io",
         "journal_io",
@@ -99,12 +100,9 @@ int disk_tool_t::prepare_one(std::map<std::string, std::string> options, int is_
         options["disable_journal_fsync"] = options["disable_data_fsync"];
     }
     // Calculate offsets if the same device is used for two or more of data, meta, and journal
-    if (options["journal_size"] == "")
+    if (options["journal_size"] == "" && (options["journal_device"] == "" || options["journal_device"] == options["data_device"]))
     {
-        if (options["journal_device"] == "")
-            options["journal_size"] = is_hdd ? "128M" : "32M";
-        else if (is_hdd)
-            options["journal_size"] = DEFAULT_HYBRID_JOURNAL;
+        options["journal_size"] = is_hdd || !json_is_true(options["disable_data_fsync"]) ? "128M" : "32M";
     }
     bool is_hybrid = is_hdd && options["journal_device"] != "" && options["journal_device"] != options["data_device"];
     if (is_hdd)
@@ -114,6 +112,15 @@ int disk_tool_t::prepare_one(std::map<std::string, std::string> options, int is_
         if (is_hybrid && options["throttle_small_writes"] == "")
             options["throttle_small_writes"] = "1";
     }
+    else if (!json_is_true(options["disable_data_fsync"]))
+    {
+        if (options.find("min_flusher_count") == options.end())
+            options["min_flusher_count"] = "32";
+        if (options.find("max_flusher_count") == options.end())
+            options["max_flusher_count"] = "256";
+        if (options.find("autosync_writes") == options.end())
+            options["autosync_writes"] = "512";
+    }
     json11::Json::object sb;
     blockstore_disk_t dsk;
     try
@@ -440,16 +447,25 @@ std::vector<std::string> disk_tool_t::get_new_data_parts(vitastor_dev_info_t & d
                 {
                     // Use this partition
                     use_parts.push_back(part["uuid"].string_value());
+                    osds_exist++;
                 }
                 else
                 {
+                    std::string part_path = "/dev/disk/by-partuuid/"+strtolower(part["uuid"].string_value());
+                    bool is_meta = sb["params"]["meta_device"].string_value() == part_path;
+                    bool is_journal = sb["params"]["journal_device"].string_value() == part_path;
+                    bool is_data = sb["params"]["data_device"].string_value() == part_path;
                     fprintf(
-                        stderr, "%s is already initialized for OSD %lu, skipping\n",
-                        part["node"].string_value().c_str(), sb["params"]["osd_num"].uint64_value()
+                        stderr, "%s is already initialized for OSD %lu%s, skipping\n",
+                        part["node"].string_value().c_str(), sb["params"]["osd_num"].uint64_value(),
+                        (is_data ? " data" : (is_meta ? " meta" : (is_journal ? " journal" : "")))
                     );
-                    osds_size += part["size"].uint64_value()*dev.pt["sectorsize"].uint64_value();
+                    if (is_data || sb["params"]["data_device"].string_value().substr(0, 22) != "/dev/disk/by-partuuid/")
+                    {
+                        osds_size += part["size"].uint64_value()*dev.pt["sectorsize"].uint64_value();
+                        osds_exist++;
+                    }
                 }
-                osds_exist++;
             }
         }
         // Still create OSD(s) if a disk has no more than (max_other_percent) other data
@@ -607,6 +623,7 @@ int disk_tool_t::prepare(std::vector<std::string> devices)
         options.erase("disable_meta_fsync");
         options.erase("disable_journal_fsync");
     }
+    auto journal_size = options["journal_size"];
     for (auto & dev: devinfo)
     {
         if (!hybrid || dev.is_hdd)
@@ -624,11 +641,13 @@ int disk_tool_t::prepare(std::vector<std::string> devices)
                     {
                         return 1;
                     }
+                    options.erase("journal_size");
                 }
                 // Treat all disks as SSDs if not in the hybrid mode
                 prepare_one(options, dev.is_hdd ? 1 : 0);
                 if (hybrid)
                 {
+                    options["journal_size"] = journal_size;
                     options.erase("journal_device");
                     options.erase("meta_device");
                 }

src/disk_tool_udev.cpp

@@ -86,6 +86,24 @@ int disk_tool_t::write_sb(std::string device)
     return !write_osd_superblock(device, params);
 }
 
+int disk_tool_t::update_sb(std::string device)
+{
+    json11::Json sb = read_osd_superblock(device, true, options.find("force") != options.end());
+    if (sb.is_null())
+    {
+        return 1;
+    }
+    auto sb_obj = sb["params"].object_items();
+    for (auto & kv: options)
+    {
+        if (kv.first != "force")
+        {
+            sb_obj[kv.first] = kv.second;
+        }
+    }
+    return !write_osd_superblock(device, sb_obj);
+}
+
 uint32_t disk_tool_t::write_osd_superblock(std::string device, json11::Json params)
 {
     std::string json_data = params.dump();

src/etcd_state_client.cpp

@@ -135,8 +135,8 @@ void etcd_state_client_t::etcd_call(std::string api, json11::Json payload, int t
             {
                 if (this->log_level > 0)
                 {
-                    printf(
-                        "Warning: etcd request failed: %s, retrying %d more times\n",
+                    fprintf(
+                        stderr, "Warning: etcd request failed: %s, retrying %d more times\n",
                         err.c_str(), retries
                     );
                 }
@@ -333,7 +333,7 @@ void etcd_state_client_t::start_etcd_watcher()
         etcd_watch_ws = NULL;
     }
     if (this->log_level > 1)
-        printf("Trying to connect to etcd websocket at %s\n", etcd_address.c_str());
+        fprintf(stderr, "Trying to connect to etcd websocket at %s, watch from revision %lu\n", etcd_address.c_str(), etcd_watch_revision);
     etcd_watch_ws = open_websocket(tfd, etcd_address, etcd_api_path+"/watch", etcd_slow_timeout,
         [this, cur_addr = selected_etcd_address](const http_response_t *msg)
     {
@@ -356,8 +356,8 @@ void etcd_state_client_t::start_etcd_watcher()
                         watch_id == ETCD_PG_HISTORY_WATCH_ID ||
                         watch_id == ETCD_OSD_STATE_WATCH_ID)
                         etcd_watches_initialised++;
-                    if (etcd_watches_initialised == 4 && this->log_level > 0)
-                        fprintf(stderr, "Successfully subscribed to etcd at %s\n", cur_addr.c_str());
+                    if (etcd_watches_initialised == ETCD_TOTAL_WATCHES && this->log_level > 0)
+                        fprintf(stderr, "Successfully subscribed to etcd at %s, revision %lu\n", cur_addr.c_str(), etcd_watch_revision);
                 }
                 if (data["result"]["canceled"].bool_value())
                 {
@@ -393,9 +393,13 @@ void etcd_state_client_t::start_etcd_watcher()
                         exit(1);
                     }
                 }
-                if (etcd_watches_initialised == 4)
+                if (etcd_watches_initialised == ETCD_TOTAL_WATCHES && !data["result"]["header"]["revision"].is_null())
                 {
-                    etcd_watch_revision = data["result"]["header"]["revision"].uint64_value()+1;
+                    // Protect against a revision beign split into multiple messages and some
+                    // of them being lost. Even though I'm not sure if etcd actually splits them
+                    // Also sometimes etcd sends something without a header, like:
+                    // {"error": {"grpc_code": 14, "http_code": 503, "http_status": "Service Unavailable", "message": "error reading from server: EOF"}}
+                    etcd_watch_revision = data["result"]["header"]["revision"].uint64_value();
                     addresses_to_try.clear();
                 }
                 // First gather all changes into a hash to remove multiple overwrites
@@ -507,7 +511,7 @@ void etcd_state_client_t::start_ws_keepalive()
     {
         ws_keepalive_timer = tfd->set_timer(etcd_ws_keepalive_interval*1000, true, [this](int)
         {
-            if (!etcd_watch_ws)
+            if (!etcd_watch_ws || etcd_watches_initialised < ETCD_TOTAL_WATCHES)
             {
                 // Do nothing
             }
@@ -636,18 +640,28 @@ void etcd_state_client_t::load_pgs()
             on_load_pgs_hook(false);
             return;
         }
+        reset_pg_exists();
         if (!etcd_watch_revision)
         {
             etcd_watch_revision = data["header"]["revision"].uint64_value()+1;
+            if (this->log_level > 3)
+            {
+                fprintf(stderr, "Loaded revision %lu of PG configuration\n", etcd_watch_revision-1);
+            }
         }
         for (auto & res: data["responses"].array_items())
         {
             for (auto & kv_json: res["response_range"]["kvs"].array_items())
             {
                 auto kv = parse_etcd_kv(kv_json);
+                if (this->log_level > 3)
+                {
+                    fprintf(stderr, "Loaded key: %s -> %s\n", kv.key.c_str(), kv.value.dump().c_str());
+                }
                 parse_state(kv);
             }
         }
+        clean_nonexistent_pgs();
         on_load_pgs_hook(true);
         start_etcd_watcher();
     });
@@ -668,6 +682,73 @@ void etcd_state_client_t::load_pgs()
 }
 #endif
 
+void etcd_state_client_t::reset_pg_exists()
+{
+    for (auto & pool_item: pool_config)
+    {
+        for (auto & pg_item: pool_item.second.pg_config)
+        {
+            pg_item.second.state_exists = false;
+            pg_item.second.history_exists = false;
+        }
+    }
+    seen_peers.clear();
+}
+
+void etcd_state_client_t::clean_nonexistent_pgs()
+{
+    for (auto & pool_item: pool_config)
+    {
+        for (auto pg_it = pool_item.second.pg_config.begin(); pg_it != pool_item.second.pg_config.end(); )
+        {
+            auto & pg_cfg = pg_it->second;
+            if (!pg_cfg.config_exists && !pg_cfg.state_exists && !pg_cfg.history_exists)
+            {
+                if (this->log_level > 3)
+                {
+                    fprintf(stderr, "PG %u/%u disappeared after reload, forgetting it\n", pool_item.first, pg_it->first);
+                }
+                pool_item.second.pg_config.erase(pg_it++);
+            }
+            else
+            {
+                if (!pg_cfg.state_exists)
+                {
+                    if (this->log_level > 3)
+                    {
+                        fprintf(stderr, "PG %u/%u primary OSD disappeared after reload, forgetting it\n", pool_item.first, pg_it->first);
+                    }
+                    parse_state((etcd_kv_t){
+                        .key = etcd_prefix+"/pg/state/"+std::to_string(pool_item.first)+"/"+std::to_string(pg_it->first),
+                    });
+                }
+                if (!pg_cfg.history_exists)
+                {
+                    if (this->log_level > 3)
+                    {
+                        fprintf(stderr, "PG %u/%u history disappeared after reload, forgetting it\n", pool_item.first, pg_it->first);
+                    }
+                    parse_state((etcd_kv_t){
+                        .key = etcd_prefix+"/pg/history/"+std::to_string(pool_item.first)+"/"+std::to_string(pg_it->first),
+                    });
+                }
+                pg_it++;
+            }
+        }
+    }
+    for (auto & peer_item: peer_states)
+    {
+        if (seen_peers.find(peer_item.first) == seen_peers.end())
+        {
+            fprintf(stderr, "OSD %lu state disappeared after reload, forgetting it\n", peer_item.first);
+            parse_state((etcd_kv_t){
+                .key = etcd_prefix+"/osd/state/"+std::to_string(peer_item.first),
+            });
+        }
+    }
+    seen_peers.clear();
+}
+
 void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
 {
     const std::string & key = kv.key;
@@ -822,7 +903,7 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
         {
             for (auto & pg_item: pool_item.second.pg_config)
             {
-                pg_item.second.exists = false;
+                pg_item.second.config_exists = false;
             }
         }
         for (auto & pool_item: value["items"].object_items())
@@ -845,7 +926,7 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
                     continue;
                 }
                 auto & parsed_cfg = this->pool_config[pool_id].pg_config[pg_num];
-                parsed_cfg.exists = true;
+                parsed_cfg.config_exists = true;
                 parsed_cfg.pause = pg_item.second["pause"].bool_value();
                 parsed_cfg.primary = pg_item.second["primary"].uint64_value();
                 parsed_cfg.target_set.clear();
@@ -866,7 +947,7 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
             int n = 0;
             for (auto pg_it = pool_item.second.pg_config.begin(); pg_it != pool_item.second.pg_config.end(); pg_it++)
             {
-                if (pg_it->second.exists && pg_it->first != ++n)
+                if (pg_it->second.config_exists && pg_it->first != ++n)
                 {
                     fprintf(
                         stderr, "Invalid pool %u PG configuration: PG numbers don't cover whole 1..%lu range\n",
@@ -874,7 +955,7 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
                     );
                     for (pg_it = pool_item.second.pg_config.begin(); pg_it != pool_item.second.pg_config.end(); pg_it++)
                     {
-                        pg_it->second.exists = false;
+                        pg_it->second.config_exists = false;
                     }
                     n = 0;
                     break;
@@ -899,6 +980,7 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
             auto & pg_cfg = this->pool_config[pool_id].pg_config[pg_num];
             pg_cfg.target_history.clear();
             pg_cfg.all_peers.clear();
+            pg_cfg.history_exists = !value.is_null();
             // Refuse to start PG if any set of the <osd_sets> has no live OSDs
             for (auto & hist_item: value["osd_sets"].array_items())
             {
@@ -951,11 +1033,15 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
         }
         else if (value.is_null())
         {
-            this->pool_config[pool_id].pg_config[pg_num].cur_primary = 0;
-            this->pool_config[pool_id].pg_config[pg_num].cur_state = 0;
+            auto & pg_cfg = this->pool_config[pool_id].pg_config[pg_num];
+            pg_cfg.state_exists = false;
+            pg_cfg.cur_primary = 0;
+            pg_cfg.cur_state = 0;
         }
         else
         {
+            auto & pg_cfg = this->pool_config[pool_id].pg_config[pg_num];
+            pg_cfg.state_exists = true;
             osd_num_t cur_primary = value["primary"].uint64_value();
             int state = 0;
             for (auto & e: value["state"].array_items())
@@ -983,8 +1069,8 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
                 fprintf(stderr, "Unexpected pool %u PG %u state in etcd: primary=%lu, state=%s\n", pool_id, pg_num, cur_primary, value["state"].dump().c_str());
                 return;
             }
-            this->pool_config[pool_id].pg_config[pg_num].cur_primary = cur_primary;
-            this->pool_config[pool_id].pg_config[pg_num].cur_state = state;
+            pg_cfg.cur_primary = cur_primary;
+            pg_cfg.cur_state = state;
         }
     }
     else if (key.substr(0, etcd_prefix.length()+11) == etcd_prefix+"/osd/state/")
@@ -998,6 +1084,7 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
                 value["port"].int64_value() > 0 && value["port"].int64_value() < 65536)
             {
                 this->peer_states[peer_osd] = value;
+                this->seen_peers.insert(peer_osd);
             }
             else
             {

src/etcd_state_client.h

@@ -3,6 +3,8 @@
 
 #pragma once
 
+#include <set>
+
 #include "json11/json11.hpp"
 #include "osd_id.h"
 #include "timerfd_manager.h"
@@ -11,6 +13,7 @@
 #define ETCD_PG_STATE_WATCH_ID 2
 #define ETCD_PG_HISTORY_WATCH_ID 3
 #define ETCD_OSD_STATE_WATCH_ID 4
+#define ETCD_TOTAL_WATCHES 4
 
 #define DEFAULT_BLOCK_SIZE 128*1024
 #define MIN_DATA_BLOCK_SIZE 4*1024
@@ -25,12 +28,12 @@ struct etcd_kv_t
 {
     std::string key;
     json11::Json value;
-    uint64_t mod_revision;
+    uint64_t mod_revision = 0;
 };
 
 struct pg_config_t
 {
-    bool exists;
+    bool config_exists, history_exists, state_exists;
     osd_num_t primary;
     std::vector<osd_num_t> target_set;
     std::vector<std::vector<osd_num_t>> target_history;
@@ -61,21 +64,21 @@ struct pool_config_t
 
 struct inode_config_t
 {
-    uint64_t num;
+    uint64_t num = 0;
     std::string name;
-    uint64_t size;
-    inode_t parent_id;
-    bool readonly;
+    uint64_t size = 0;
+    inode_t parent_id = 0;
+    bool readonly = false;
     // Arbitrary metadata
     json11::Json meta;
     // Change revision of the metadata in etcd
-    uint64_t mod_revision;
+    uint64_t mod_revision = 0;
 };
 
 struct inode_watch_t
 {
     std::string name;
-    inode_config_t cfg;
+    inode_config_t cfg = {};
 };
 
 struct http_co_t;
@@ -113,6 +116,7 @@ public:
     uint64_t etcd_watch_revision = 0;
     std::map<pool_id_t, pool_config_t> pool_config;
     std::map<osd_num_t, json11::Json> peer_states;
+    std::set<osd_num_t> seen_peers;
     std::map<inode_t, inode_config_t> inode_config;
     std::map<std::string, inode_t> inode_by_name;
 
@@ -138,6 +142,8 @@ public:
     void start_ws_keepalive();
     void load_global_config();
     void load_pgs();
+    void reset_pg_exists();
+    void clean_nonexistent_pgs();
     void parse_state(const etcd_kv_t & kv);
     void parse_config(const json11::Json & config);
     void insert_inode_config(const inode_config_t & cfg);

src/messenger.cpp

@@ -45,11 +45,12 @@ void osd_messenger_t::init()
 #endif
     keepalive_timer_id = tfd->set_timer(1000, true, [this](int)
     {
-        std::vector<int> to_stop;
-        std::vector<osd_op_t*> to_ping;
-        for (auto cl_it = clients.begin(); cl_it != clients.end(); cl_it++)
+        auto cl_it = clients.begin();
+        while (cl_it != clients.end())
         {
             auto cl = cl_it->second;
+            cl_it++;
+            auto peer_fd = cl->peer_fd;
             if (!cl->osd_num || cl->peer_state != PEER_CONNECTED && cl->peer_state != PEER_RDMA)
             {
                 // Do not run keepalive on regular clients
@@ -62,7 +63,9 @@ void osd_messenger_t::init()
                 {
                     // Ping timed out, stop the client
                     fprintf(stderr, "Ping timed out for OSD %lu (client %d), disconnecting peer\n", cl->osd_num, cl->peer_fd);
-                    to_stop.push_back(cl->peer_fd);
+                    stop_client(peer_fd, true);
+                    // Restart iterator because it may be invalidated
+                    cl_it = clients.upper_bound(peer_fd);
                 }
             }
             else if (cl->idle_time_remaining > 0)
@@ -100,9 +103,11 @@ void osd_messenger_t::init()
                             stop_client(fail_fd, true);
                         }
                     };
-                    to_ping.push_back(op);
                     cl->ping_time_remaining = osd_ping_timeout;
                     cl->idle_time_remaining = osd_idle_timeout;
+                    outbox_push(op);
+                    // Restart iterator because it may be invalidated
+                    cl_it = clients.upper_bound(peer_fd);
                 }
             }
             else
@@ -110,15 +115,6 @@ void osd_messenger_t::init()
                 cl->idle_time_remaining = osd_idle_timeout;
             }
         }
-        // Don't stop clients while a 'clients' iterator is still active
-        for (int peer_fd: to_stop)
-        {
-            stop_client(peer_fd, true);
-        }
-        for (auto op: to_ping)
-        {
-            outbox_push(op);
-        }
     });
 }
 

src/messenger.h

@@ -149,7 +149,7 @@ public:
     std::map<osd_num_t, osd_wanted_peer_t> wanted_peers;
     std::map<uint64_t, int> osd_peer_fds;
     // op statistics
-    osd_op_stats_t stats;
+    osd_op_stats_t stats, recovery_stats;
 
     void init();
     void parse_config(const json11::Json & config);
@@ -175,6 +175,7 @@ public:
     bool connect_rdma(int peer_fd, std::string rdma_address, uint64_t client_max_msg);
 #endif
 
+    void inc_op_stats(osd_op_stats_t & stats, uint64_t opcode, timespec & tv_begin, timespec & tv_end, uint64_t len);
     void measure_exec(osd_op_t *cur_op);
 
 protected:

src/msgr_op.cpp

@@ -24,3 +24,17 @@ osd_op_t::~osd_op_t()
         free(buf);
     }
 }
+
+bool osd_op_t::is_recovery_related()
+{
+    return (req.hdr.opcode == OSD_OP_SEC_READ ||
+        req.hdr.opcode == OSD_OP_SEC_WRITE ||
+        req.hdr.opcode == OSD_OP_SEC_WRITE_STABLE) &&
+        (req.sec_rw.flags & OSD_OP_RECOVERY_RELATED) ||
+        req.hdr.opcode == OSD_OP_SEC_DELETE &&
+        (req.sec_del.flags & OSD_OP_RECOVERY_RELATED) ||
+        req.hdr.opcode == OSD_OP_SEC_STABILIZE &&
+        (req.sec_stab.flags & OSD_OP_RECOVERY_RELATED) ||
+        req.hdr.opcode == OSD_OP_SEC_SYNC &&
+        (req.sec_sync.flags & OSD_OP_RECOVERY_RELATED);
+}

src/msgr_op.h

@@ -173,4 +173,6 @@ struct osd_op_t
     osd_op_buf_list_t iov;
 
     ~osd_op_t();
+
+    bool is_recovery_related();
 };

src/msgr_send.cpp

@@ -131,6 +131,23 @@ void osd_messenger_t::outbox_push(osd_op_t *cur_op)
     }
 }
 
+void osd_messenger_t::inc_op_stats(osd_op_stats_t & stats, uint64_t opcode, timespec & tv_begin, timespec & tv_end, uint64_t len)
+{
+    uint64_t usecs = (
+        (tv_end.tv_sec - tv_begin.tv_sec)*1000000 +
+        (tv_end.tv_nsec - tv_begin.tv_nsec)/1000
+    );
+    stats.op_stat_count[opcode]++;
+    if (!stats.op_stat_count[opcode])
+    {
+        stats.op_stat_count[opcode] = 1;
+        stats.op_stat_sum[opcode] = 0;
+        stats.op_stat_bytes[opcode] = 0;
+    }
+    stats.op_stat_sum[opcode] += usecs;
+    stats.op_stat_bytes[opcode] += len;
+}
+
 void osd_messenger_t::measure_exec(osd_op_t *cur_op)
 {
     // Measure execution latency
@@ -142,29 +159,24 @@ void osd_messenger_t::measure_exec(osd_op_t *cur_op)
     {
         clock_gettime(CLOCK_REALTIME, &cur_op->tv_end);
     }
-    stats.op_stat_count[cur_op->req.hdr.opcode]++;
-    if (!stats.op_stat_count[cur_op->req.hdr.opcode])
-    {
-        stats.op_stat_count[cur_op->req.hdr.opcode]++;
-        stats.op_stat_sum[cur_op->req.hdr.opcode] = 0;
-        stats.op_stat_bytes[cur_op->req.hdr.opcode] = 0;
-    }
-    stats.op_stat_sum[cur_op->req.hdr.opcode] += (
-        (cur_op->tv_end.tv_sec - cur_op->tv_begin.tv_sec)*1000000 +
-        (cur_op->tv_end.tv_nsec - cur_op->tv_begin.tv_nsec)/1000
-    );
+    uint64_t len = 0;
     if (cur_op->req.hdr.opcode == OSD_OP_READ ||
         cur_op->req.hdr.opcode == OSD_OP_WRITE ||
         cur_op->req.hdr.opcode == OSD_OP_SCRUB)
     {
         // req.rw.len is internally set to the full object size for scrubs
-        stats.op_stat_bytes[cur_op->req.hdr.opcode] += cur_op->req.rw.len;
+        len = cur_op->req.rw.len;
     }
     else if (cur_op->req.hdr.opcode == OSD_OP_SEC_READ ||
         cur_op->req.hdr.opcode == OSD_OP_SEC_WRITE ||
         cur_op->req.hdr.opcode == OSD_OP_SEC_WRITE_STABLE)
     {
-        stats.op_stat_bytes[cur_op->req.hdr.opcode] += cur_op->req.sec_rw.len;
+        len = cur_op->req.sec_rw.len;
+    }
+    inc_op_stats(stats, cur_op->req.hdr.opcode, cur_op->tv_begin, cur_op->tv_end, len);
+    if (cur_op->is_recovery_related())
+    {
+        inc_op_stats(recovery_stats, cur_op->req.hdr.opcode, cur_op->tv_begin, cur_op->tv_end, len);
     }
 }
 

src/osd.cpp

@@ -22,7 +22,7 @@ static blockstore_config_t json_to_bs(const json11::Json::object & config)
     {
         if (kv.second.is_string())
             bs[kv.first] = kv.second.string_value();
-        else
+        else if (!kv.second.is_null())
             bs[kv.first] = kv.second.dump();
     }
     return bs;
@@ -68,14 +68,21 @@ osd_t::osd_t(const json11::Json & config, ring_loop_t *ringloop)
         }
     }
 
-    print_stats_timer_id = this->tfd->set_timer(print_stats_interval*1000, true, [this](int timer_id)
+    if (print_stats_timer_id == -1)
     {
-        print_stats();
-    });
-    slow_log_timer_id = this->tfd->set_timer(slow_log_interval*1000, true, [this](int timer_id)
+        print_stats_timer_id = this->tfd->set_timer(print_stats_interval*1000, true, [this](int timer_id)
+        {
+            print_stats();
+        });
+    }
+    if (slow_log_timer_id == -1)
     {
-        print_slow();
-    });
+        slow_log_timer_id = this->tfd->set_timer(slow_log_interval*1000, true, [this](int timer_id)
+        {
+            print_slow();
+        });
+    }
+    apply_recovery_tune_interval();
 
     msgr.tfd = this->tfd;
     msgr.ringloop = this->ringloop;
@@ -97,6 +104,11 @@ osd_t::~osd_t()
         tfd->clear_timer(slow_log_timer_id);
         slow_log_timer_id = -1;
     }
+    if (rtune_timer_id >= 0)
+    {
+        tfd->clear_timer(rtune_timer_id);
+        rtune_timer_id = -1;
+    }
     if (print_stats_timer_id >= 0)
     {
         tfd->clear_timer(print_stats_timer_id);
@@ -182,7 +194,8 @@ void osd_t::parse_config(bool init)
         if (autosync_interval > MAX_AUTOSYNC_INTERVAL)
             autosync_interval = DEFAULT_AUTOSYNC_INTERVAL;
     }
-    if (!config["autosync_writes"].is_null())
+    if (config["autosync_writes"].is_number() ||
+        config["autosync_writes"].string_value() != "")
     {
         // Allow to set it to 0
         autosync_writes = config["autosync_writes"].uint64_value();
@@ -196,6 +209,32 @@ void osd_t::parse_config(bool init)
     recovery_queue_depth = config["recovery_queue_depth"].uint64_value();
     if (recovery_queue_depth < 1 || recovery_queue_depth > MAX_RECOVERY_QUEUE)
         recovery_queue_depth = DEFAULT_RECOVERY_QUEUE;
+    recovery_sleep_us = config["recovery_sleep_us"].uint64_value();
+    recovery_tune_util_low = config["recovery_tune_util_low"].is_null()
+        ? 0.1 : config["recovery_tune_util_low"].number_value();
+    if (recovery_tune_util_low < 0.01)
+        recovery_tune_util_low = 0.01;
+    recovery_tune_util_high = config["recovery_tune_util_high"].is_null()
+        ? 1.0 : config["recovery_tune_util_high"].number_value();
+    if (recovery_tune_util_high < 0.01)
+        recovery_tune_util_high = 0.01;
+    recovery_tune_client_util_low = config["recovery_tune_client_util_low"].is_null()
+        ? 0 : config["recovery_tune_client_util_low"].number_value();
+    if (recovery_tune_client_util_low < 0.01)
+        recovery_tune_client_util_low = 0.01;
+    recovery_tune_client_util_high = config["recovery_tune_client_util_high"].is_null()
+        ? 0.5 : config["recovery_tune_client_util_high"].number_value();
+    if (recovery_tune_client_util_high < 0.01)
+        recovery_tune_client_util_high = 0.01;
+    auto old_recovery_tune_interval = recovery_tune_interval;
+    recovery_tune_interval = config["recovery_tune_interval"].is_null()
+        ? 1 : config["recovery_tune_interval"].uint64_value();
+    recovery_tune_agg_interval = config["recovery_tune_agg_interval"].is_null()
+        ? 10 : config["recovery_tune_agg_interval"].uint64_value();
+    recovery_tune_sleep_min_us = config["recovery_tune_sleep_min_us"].is_null()
+        ? 10 : config["recovery_tune_sleep_min_us"].uint64_value();
+    recovery_tune_sleep_cutoff_us = config["recovery_tune_sleep_cutoff_us"].is_null()
+        ? 10000000 : config["recovery_tune_sleep_cutoff_us"].uint64_value();
     recovery_pg_switch = config["recovery_pg_switch"].uint64_value();
     if (recovery_pg_switch < 1)
         recovery_pg_switch = DEFAULT_RECOVERY_PG_SWITCH;
@@ -274,6 +313,10 @@ void osd_t::parse_config(bool init)
             print_slow();
         });
     }
+    if (old_recovery_tune_interval != recovery_tune_interval)
+    {
+        apply_recovery_tune_interval();
+    }
 }
 
 void osd_t::bind_socket()
@@ -421,14 +464,6 @@ void osd_t::exec_op(osd_op_t *cur_op)
     }
 }
 
-void osd_t::reset_stats()
-{
-    msgr.stats = {};
-    prev_stats = {};
-    memset(recovery_stat_count, 0, sizeof(recovery_stat_count));
-    memset(recovery_stat_bytes, 0, sizeof(recovery_stat_bytes));
-}
-
 void osd_t::print_stats()
 {
     for (int i = OSD_OP_MIN; i <= OSD_OP_MAX; i++)
@@ -466,19 +501,20 @@ void osd_t::print_stats()
     }
     for (int i = 0; i < 2; i++)
     {
-        if (recovery_stat_count[0][i] != recovery_stat_count[1][i])
+        if (recovery_stat[i].count > recovery_print_prev[i].count)
         {
-            uint64_t bw = (recovery_stat_bytes[0][i] - recovery_stat_bytes[1][i]) / print_stats_interval;
+            uint64_t bw = (recovery_stat[i].bytes - recovery_print_prev[i].bytes) / print_stats_interval;
             printf(
-                "[OSD %lu] %s recovery: %.1f op/s, B/W: %.2f %s\n", osd_num, recovery_stat_names[i],
-                (recovery_stat_count[0][i] - recovery_stat_count[1][i]) * 1.0 / print_stats_interval,
+                "[OSD %lu] %s recovery: %.1f op/s, B/W: %.2f %s, avg latency %ld us, delay %ld us\n", osd_num, recovery_stat_names[i],
+                (recovery_stat[i].count - recovery_print_prev[i].count) * 1.0 / print_stats_interval,
                 (bw > 1024*1024*1024 ? bw/1024.0/1024/1024 : (bw > 1024*1024 ? bw/1024.0/1024 : bw/1024.0)),
-                (bw > 1024*1024*1024 ? "GB/s" : (bw > 1024*1024 ? "MB/s" : "KB/s"))
+                (bw > 1024*1024*1024 ? "GB/s" : (bw > 1024*1024 ? "MB/s" : "KB/s")),
+                (recovery_stat[i].usec - recovery_print_prev[i].usec) / (recovery_stat[i].count - recovery_print_prev[i].count),
+                recovery_target_sleep_us
             );
-            recovery_stat_count[1][i] = recovery_stat_count[0][i];
-            recovery_stat_bytes[1][i] = recovery_stat_bytes[0][i];
         }
     }
+    memcpy(recovery_print_prev, recovery_stat, sizeof(recovery_stat));
     if (corrupted_objects > 0)
     {
         printf("[OSD %lu] %lu object(s) corrupted\n", osd_num, corrupted_objects);
@@ -572,8 +608,8 @@ void osd_t::print_slow()
                     op->req.hdr.opcode == OSD_OP_SEC_STABILIZE || op->req.hdr.opcode == OSD_OP_SEC_ROLLBACK ||
                     op->req.hdr.opcode == OSD_OP_SEC_READ_BMP)
                 {
-                    bufprintf(" state=%d", PRIV(op->bs_op)->op_state);
-                    int wait_for = PRIV(op->bs_op)->wait_for;
+                    bufprintf(" state=%d", op->bs_op ? PRIV(op->bs_op)->op_state : -1);
+                    int wait_for = op->bs_op ? PRIV(op->bs_op)->wait_for : 0;
                     if (wait_for)
                     {
                         bufprintf(" wait=%d (detail=%lu)", wait_for, PRIV(op->bs_op)->wait_detail);

src/osd.h

@@ -34,7 +34,7 @@
 #define DEFAULT_AUTOSYNC_INTERVAL 5
 #define DEFAULT_AUTOSYNC_WRITES 128
 #define MAX_RECOVERY_QUEUE 2048
-#define DEFAULT_RECOVERY_QUEUE 4
+#define DEFAULT_RECOVERY_QUEUE 1
 #define DEFAULT_RECOVERY_PG_SWITCH 128
 #define DEFAULT_RECOVERY_BATCH 16
 
@@ -87,6 +87,11 @@ struct osd_chain_read_t
 
 struct osd_rmw_stripe_t;
 
+struct recovery_stat_t
+{
+    uint64_t count, usec, bytes;
+};
+
 class osd_t
 {
     // config
@@ -111,7 +116,16 @@ class osd_t
     int immediate_commit = IMMEDIATE_NONE;
     int autosync_interval = DEFAULT_AUTOSYNC_INTERVAL; // "emergency" sync every 5 seconds
     int autosync_writes = DEFAULT_AUTOSYNC_WRITES;
-    int recovery_queue_depth = DEFAULT_RECOVERY_QUEUE;
+    uint64_t recovery_queue_depth = 1;
+    uint64_t recovery_sleep_us = 0;
+    double recovery_tune_util_low = 0.1;
+    double recovery_tune_client_util_low = 0;
+    double recovery_tune_util_high = 1.0;
+    double recovery_tune_client_util_high = 0.5;
+    int recovery_tune_interval = 1;
+    int recovery_tune_agg_interval = 10;
+    int recovery_tune_sleep_min_us = 10;
+    int recovery_tune_sleep_cutoff_us = 10000000;
     int recovery_pg_switch = DEFAULT_RECOVERY_PG_SWITCH;
     int recovery_sync_batch = DEFAULT_RECOVERY_BATCH;
     int inode_vanish_time = 60;
@@ -189,8 +203,18 @@ class osd_t
     std::map<uint64_t, inode_stats_t> inode_stats;
     std::map<uint64_t, timespec> vanishing_inodes;
     const char* recovery_stat_names[2] = { "degraded", "misplaced" };
-    uint64_t recovery_stat_count[2][2] = {};
-    uint64_t recovery_stat_bytes[2][2] = {};
+    recovery_stat_t recovery_stat[2];
+    recovery_stat_t recovery_print_prev[2];
+
+    // recovery auto-tuning
+    int rtune_timer_id = -1;
+    uint64_t rtune_avg_lat = 0;
+    double rtune_client_util = 0, rtune_target_util = 1;
+    osd_op_stats_t rtune_prev_stats, rtune_prev_recovery_stats;
+    std::vector<uint64_t> recovery_target_sleep_items;
+    uint64_t recovery_target_sleep_us = 0;
+    uint64_t recovery_target_sleep_total = 0;
+    int recovery_target_sleep_cur = 0, recovery_target_sleep_count = 0;
 
     // cluster connection
     void parse_config(bool init);
@@ -208,8 +232,9 @@ class osd_t
     void create_osd_state();
     void renew_lease(bool reload);
     void print_stats();
+    void tune_recovery();
+    void apply_recovery_tune_interval();
     void print_slow();
-    void reset_stats();
     json11::Json get_statistics();
     void report_statistics();
     void report_pg_state(pg_t & pg);
@@ -238,6 +263,7 @@ class osd_t
     bool submit_flush_op(pool_id_t pool_id, pg_num_t pg_num, pg_flush_batch_t *fb, bool rollback, osd_num_t peer_osd, int count, obj_ver_id *data);
     bool pick_next_recovery(osd_recovery_op_t &op);
     void submit_recovery_op(osd_recovery_op_t *op);
+    void finish_recovery_op(osd_recovery_op_t *op);
     bool continue_recovery();
     pg_osd_set_state_t* change_osd_set(pg_osd_set_state_t *st, pg_t *pg);
 
@@ -257,6 +283,7 @@ class osd_t
     void exec_sync_stab_all(osd_op_t *cur_op);
     void exec_show_config(osd_op_t *cur_op);
     void exec_secondary(osd_op_t *cur_op);
+    void exec_secondary_real(osd_op_t *cur_op);
     void secondary_op_callback(osd_op_t *cur_op);
 
     // primary ops
@@ -279,7 +306,7 @@ class osd_t
     bool remember_unstable_write(osd_op_t *cur_op, pg_t & pg, pg_osd_set_t & loc_set, int base_state);
     void handle_primary_subop(osd_op_t *subop, osd_op_t *cur_op);
     void handle_primary_bs_subop(osd_op_t *subop);
-    void add_bs_subop_stats(osd_op_t *subop);
+    void add_bs_subop_stats(osd_op_t *subop, bool recovery_related = false);
     void pg_cancel_write_queue(pg_t & pg, osd_op_t *first_op, object_id oid, int retval);
 
     void submit_primary_subops(int submit_type, uint64_t op_version, const uint64_t* osd_set, osd_op_t *cur_op);

src/osd_cluster.cpp

@@ -213,12 +213,14 @@ json11::Json osd_t::get_statistics()
     st["subop_stats"] = subop_stats;
     st["recovery_stats"] = json11::Json::object {
         { recovery_stat_names[0], json11::Json::object {
-            { "count", recovery_stat_count[0][0] },
-            { "bytes", recovery_stat_bytes[0][0] },
+            { "count", recovery_stat[0].count },
+            { "bytes", recovery_stat[0].bytes },
+            { "usec", recovery_stat[0].usec },
         } },
         { recovery_stat_names[1], json11::Json::object {
-            { "count", recovery_stat_count[0][1] },
-            { "bytes", recovery_stat_bytes[0][1] },
+            { "count", recovery_stat[1].count },
+            { "bytes", recovery_stat[1].bytes },
+            { "usec", recovery_stat[1].usec },
         } },
     };
     return st;
@@ -260,7 +262,8 @@ void osd_t::report_statistics()
     for (auto st_it = inode_stats.begin(); st_it != inode_stats.end(); )
     {
         auto & kv = *st_it;
-        if (!bs_inode_space[kv.first])
+        auto spc_it = bs_inode_space.find(kv.first);
+        if (spc_it == bs_inode_space.end() || !spc_it->second) // prevent autovivification
         {
             // Is it an empty inode?
             if (!tv_now.tv_sec)
@@ -649,7 +652,7 @@ void osd_t::apply_pg_config()
         {
             pg_num_t pg_num = kv.first;
             auto & pg_cfg = kv.second;
-            bool take = pg_cfg.exists && pg_cfg.primary == this->osd_num &&
+            bool take = pg_cfg.config_exists && pg_cfg.primary == this->osd_num &&
                 !pg_cfg.pause && (!pg_cfg.cur_primary || pg_cfg.cur_primary == this->osd_num);
             auto pg_it = this->pgs.find({ .pool_id = pool_id, .pg_num = pg_num });
             bool currently_taken = pg_it != this->pgs.end() && pg_it->second.state != PG_OFFLINE;
@@ -840,7 +843,13 @@ void osd_t::report_pg_states()
                     pg_state_exists = true;
                     if (pg.state == PG_OFFLINE && pg_it->second.cur_primary != this->osd_num)
                     {
-                        // Nothing to check or report, PG is already taken over by another OSD
+                        // Nothing to report, PG is already taken over by another OSD
+                        checks.push_back(json11::Json::object {
+                            { "target", "MOD" },
+                            { "key", state_key_base64 },
+                            { "result", "LESS" },
+                            { "mod_revision", st_cli.etcd_watch_revision+1 },
+                        });
                         continue;
                     }
                 }
@@ -848,11 +857,6 @@ void osd_t::report_pg_states()
         }
         if (!pg_state_exists)
         {
-            if (pg.state == PG_OFFLINE)
-            {
-                // Nothing to check or report, PG is already stopped
-                continue;
-            }
             // Check that the PG key does not exist
             // Failed check indicates an unsuccessful PG lock attempt in this case
             checks.push_back(json11::Json::object {

src/osd_flush.cpp

@@ -325,26 +325,133 @@ void osd_t::submit_recovery_op(osd_recovery_op_t *op)
         {
             printf("Recovery operation done for %lx:%lx\n", op->oid.inode, op->oid.stripe);
         }
-        // CAREFUL! op = &recovery_ops[op->oid]. Don't access op->* after recovery_ops.erase()
-        op->osd_op = NULL;
-        recovery_ops.erase(op->oid);
-        delete osd_op;
-        if (immediate_commit != IMMEDIATE_ALL)
-        {
-            recovery_done++;
-            if (recovery_done >= recovery_sync_batch)
-            {
-                // Force sync every <recovery_sync_batch> operations
-                // This is required not to pile up an excessive amount of delete operations
-                autosync();
-                recovery_done = 0;
-            }
-        }
-        continue_recovery();
+        finish_recovery_op(op);
     };
     exec_op(op->osd_op);
 }
 
+void osd_t::apply_recovery_tune_interval()
+{
+    if (rtune_timer_id >= 0)
+    {
+        tfd->clear_timer(rtune_timer_id);
+        rtune_timer_id = -1;
+    }
+    if (recovery_tune_interval != 0)
+    {
+        rtune_timer_id = this->tfd->set_timer(recovery_tune_interval*1000, true, [this](int timer_id)
+        {
+            tune_recovery();
+        });
+    }
+    else
+    {
+        recovery_target_sleep_us = recovery_sleep_us;
+    }
+}
+
+void osd_t::finish_recovery_op(osd_recovery_op_t *op)
+{
+    // CAREFUL! op = &recovery_ops[op->oid]. Don't access op->* after recovery_ops.erase()
+    delete op->osd_op;
+    op->osd_op = NULL;
+    recovery_ops.erase(op->oid);
+    if (immediate_commit != IMMEDIATE_ALL)
+    {
+        recovery_done++;
+        if (recovery_done >= recovery_sync_batch)
+        {
+            // Force sync every <recovery_sync_batch> operations
+            // This is required not to pile up an excessive amount of delete operations
+            autosync();
+            recovery_done = 0;
+        }
+    }
+    continue_recovery();
+}
+
+void osd_t::tune_recovery()
+{
+    static int accounted_ops[] = {
+        OSD_OP_SEC_READ, OSD_OP_SEC_WRITE, OSD_OP_SEC_WRITE_STABLE,
+        OSD_OP_SEC_STABILIZE, OSD_OP_SEC_SYNC, OSD_OP_SEC_DELETE
+    };
+    uint64_t total_client_usec = 0, total_recovery_usec = 0, recovery_count = 0;
+    for (int i = 0; i < sizeof(accounted_ops)/sizeof(accounted_ops[0]); i++)
+    {
+        total_client_usec += (msgr.stats.op_stat_sum[accounted_ops[i]]
+            - rtune_prev_stats.op_stat_sum[accounted_ops[i]]);
+        total_recovery_usec += (msgr.recovery_stats.op_stat_sum[accounted_ops[i]]
+            - rtune_prev_recovery_stats.op_stat_sum[accounted_ops[i]]);
+        recovery_count += (msgr.recovery_stats.op_stat_count[accounted_ops[i]]
+            - rtune_prev_recovery_stats.op_stat_count[accounted_ops[i]]);
+        rtune_prev_stats.op_stat_sum[accounted_ops[i]] = msgr.stats.op_stat_sum[accounted_ops[i]];
+        rtune_prev_recovery_stats.op_stat_sum[accounted_ops[i]] = msgr.recovery_stats.op_stat_sum[accounted_ops[i]];
+        rtune_prev_recovery_stats.op_stat_count[accounted_ops[i]] = msgr.recovery_stats.op_stat_count[accounted_ops[i]];
+    }
+    total_client_usec -= total_recovery_usec;
+    if (recovery_count == 0)
+    {
+        return;
+    }
+    // example:
+    // total 3 GB/s
+    // recovery queue 1
+    // 120 OSDs
+    // EC 5+3
+    // 128kb block_size => 640kb object
+    // 3000*1024/640/120 = 40 MB/s per OSD = 64 recovered objects per OSD
+    //   = 64*8*2 subops = 1024 recovery subop iops
+    // 8 recovery subop queue
+    // => subop avg latency = 0.0078125 sec
+    // utilisation = 8
+    // target util 1
+    // intuitively target latency should be 8x of real
+    // target_lat = rtune_avg_lat * utilisation / target_util
+    //            = rtune_avg_lat * rtune_avg_lat * rtune_avg_iops / target_util
+    //            = 0.0625
+    // recovery utilisation will be 1
+    rtune_client_util = total_client_usec/1000000.0/recovery_tune_interval;
+    rtune_target_util = (rtune_client_util < recovery_tune_client_util_low
+        ? recovery_tune_util_high
+        : recovery_tune_util_low + (rtune_client_util >= recovery_tune_client_util_high
+            ? 0 : (recovery_tune_util_high-recovery_tune_util_low)*
+                (recovery_tune_client_util_high-rtune_client_util)/(recovery_tune_client_util_high-recovery_tune_client_util_low)
+        )
+    );
+    rtune_avg_lat = total_recovery_usec/recovery_count;
+    uint64_t target_lat = rtune_avg_lat * rtune_avg_lat/1000000.0 * recovery_count/recovery_tune_interval / rtune_target_util;
+    auto sleep_us = target_lat > rtune_avg_lat+recovery_tune_sleep_min_us ? target_lat-rtune_avg_lat : 0;
+    if (sleep_us > recovery_tune_sleep_cutoff_us)
+    {
+        return;
+    }
+    if (recovery_target_sleep_items.size() != recovery_tune_agg_interval)
+    {
+        recovery_target_sleep_items.resize(recovery_tune_agg_interval);
+        for (int i = 0; i < recovery_tune_agg_interval; i++)
+            recovery_target_sleep_items[i] = 0;
+        recovery_target_sleep_total = 0;
+        recovery_target_sleep_cur = 0;
+        recovery_target_sleep_count = 0;
+    }
+    recovery_target_sleep_total -= recovery_target_sleep_items[recovery_target_sleep_cur];
+    recovery_target_sleep_items[recovery_target_sleep_cur] = sleep_us;
+    recovery_target_sleep_cur = (recovery_target_sleep_cur+1) % recovery_tune_agg_interval;
+    recovery_target_sleep_total += sleep_us;
+    if (recovery_target_sleep_count < recovery_tune_agg_interval)
+        recovery_target_sleep_count++;
+    recovery_target_sleep_us = recovery_target_sleep_total / recovery_target_sleep_count;
+    if (log_level > 1)
+    {
+        printf(
+            "[OSD %lu] auto-tune: client util: %.2f, recovery util: %.2f, lat: %lu us -> target util %.2f, delay %lu us\n",
+            osd_num, rtune_client_util, total_recovery_usec/1000000.0/recovery_tune_interval,
+            rtune_avg_lat, rtune_target_util, recovery_target_sleep_us
+        );
+    }
+}
+
 // Just trigger write requests for degraded objects. They'll be recovered during writing
 bool osd_t::continue_recovery()
 {

src/osd_ops.h

@@ -34,6 +34,7 @@
 #define OSD_OP_MAX                  18
 #define OSD_RW_MAX                  64*1024*1024
 #define OSD_PROTOCOL_VERSION        1
+#define OSD_OP_RECOVERY_RELATED     (uint32_t)1
 
 // Memory alignment for direct I/O (usually 512 bytes)
 #ifndef DIRECT_IO_ALIGNMENT
@@ -88,7 +89,8 @@ struct __attribute__((__packed__)) osd_op_sec_rw_t
     uint32_t len;
     // bitmap/attribute length - bitmap comes after header, but before data
     uint32_t attr_len;
-    uint32_t pad0;
+    // the only possible flag is OSD_OP_RECOVERY_RELATED
+    uint32_t flags;
 };
 
 struct __attribute__((__packed__)) osd_reply_sec_rw_t
@@ -109,6 +111,9 @@ struct __attribute__((__packed__)) osd_op_sec_del_t
     object_id oid;
     // delete version (automatic or specific)
     uint64_t version;
+    // the only possible flag is OSD_OP_RECOVERY_RELATED
+    uint32_t flags;
+    uint32_t pad0;
 };
 
 struct __attribute__((__packed__)) osd_reply_sec_del_t
@@ -121,6 +126,9 @@ struct __attribute__((__packed__)) osd_reply_sec_del_t
 struct __attribute__((__packed__)) osd_op_sec_sync_t
 {
     osd_op_header_t header;
+    // the only possible flag is OSD_OP_RECOVERY_RELATED
+    uint32_t flags;
+    uint32_t pad0;
 };
 
 struct __attribute__((__packed__)) osd_reply_sec_sync_t
@@ -134,6 +142,9 @@ struct __attribute__((__packed__)) osd_op_sec_stab_t
     osd_op_header_t header;
     // obj_ver_id array length in bytes
     uint64_t len;
+    // the only possible flag is OSD_OP_RECOVERY_RELATED
+    uint32_t flags;
+    uint32_t pad0;
 };
 typedef osd_op_sec_stab_t osd_op_sec_rollback_t;
 

src/osd_peering.cpp

@@ -222,6 +222,9 @@ void osd_t::start_pg_peering(pg_t & pg)
     }
     if (pg.pg_cursize < pg.pg_minsize)
     {
+        // FIXME: Incomplete EC PGs may currently easily lead to write hangs ("slow ops" in OSD logs)
+        // because such PGs don't flush unstable entries on secondary OSDs so they can't remove these
+        // entries from their journals...
         pg.state = PG_INCOMPLETE;
         report_pg_state(pg);
         return;

src/osd_primary.cpp

@@ -706,6 +706,26 @@ resume_5:
         remove_object_from_state(op_data->oid, &op_data->object_state, pg);
         deref_object_state(pg, &op_data->object_state, true);
     }
+    // Mark PG and OSDs as dirty
+    for (auto & chunk: (op_data->object_state ? op_data->object_state->osd_set : pg.cur_loc_set))
+    {
+        this->dirty_osds.insert(chunk.osd_num);
+    }
+    for (auto cl_it = msgr.clients.find(cur_op->peer_fd); cl_it != msgr.clients.end(); )
+    {
+        cl_it->second->dirty_pgs.insert({ .pool_id = pg.pool_id, .pg_num = pg.pg_num });
+        break;
+    }
+    dirty_pgs.insert({ .pool_id = pg.pool_id, .pg_num = pg.pg_num });
+    if (immediate_commit == IMMEDIATE_NONE)
+    {
+        unstable_write_count++;
+        if (unstable_write_count >= autosync_writes)
+        {
+            unstable_write_count = 0;
+            autosync();
+        }
+    }
     pg.total_count--;
     cur_op->reply.hdr.retval = 0;
 continue_others:

src/osd_primary_subops.cpp

@@ -3,13 +3,15 @@
 
 #include "osd_primary.h"
 
+#define SELF_FD -1
+
 void osd_t::autosync()
 {
     if (immediate_commit != IMMEDIATE_ALL && !autosync_op)
     {
         autosync_op = new osd_op_t();
         autosync_op->op_type = OSD_OP_IN;
-        autosync_op->peer_fd = -1;
+        autosync_op->peer_fd = SELF_FD;
         autosync_op->req = (osd_any_op_t){
             .sync = {
                 .header = {
@@ -85,9 +87,13 @@ void osd_t::finish_op(osd_op_t *cur_op, int retval)
     cur_op->reply.hdr.id = cur_op->req.hdr.id;
     cur_op->reply.hdr.opcode = cur_op->req.hdr.opcode;
     cur_op->reply.hdr.retval = retval;
-    if (cur_op->peer_fd == -1)
+    if (cur_op->peer_fd == SELF_FD)
     {
-        msgr.measure_exec(cur_op);
+        // Do not include internal primary writes (recovery/rebalance) into client op statistics
+        if (cur_op->req.hdr.opcode != OSD_OP_WRITE)
+        {
+            msgr.measure_exec(cur_op);
+        }
         // Copy lambda to be unaffected by `delete op`
         std::function<void(osd_op_t*)>(cur_op->callback)(cur_op);
     }
@@ -215,6 +221,7 @@ int osd_t::submit_primary_subop_batch(int submit_type, inode_t inode, uint64_t o
                     .offset = wr ? si->write_start : si->read_start,
                     .len = subop_len,
                     .attr_len = wr ? clean_entry_bitmap_size : 0,
+                    .flags = cur_op->peer_fd == SELF_FD && cur_op->req.hdr.opcode != OSD_OP_SCRUB ? OSD_OP_RECOVERY_RELATED : 0,
                 };
 #ifdef OSD_DEBUG
                 printf(
@@ -294,7 +301,8 @@ void osd_t::handle_primary_bs_subop(osd_op_t *subop)
             " retval = "+std::to_string(bs_op->retval)+")"
         );
     }
-    add_bs_subop_stats(subop);
+    bool recovery_related = cur_op->peer_fd == SELF_FD && cur_op->req.hdr.opcode != OSD_OP_SCRUB;
+    add_bs_subop_stats(subop, recovery_related);
     subop->req.hdr.opcode = bs_op_to_osd_op[bs_op->opcode];
     subop->reply.hdr.retval = bs_op->retval;
     if (bs_op->opcode == BS_OP_READ || bs_op->opcode == BS_OP_WRITE || bs_op->opcode == BS_OP_WRITE_STABLE)
@@ -306,30 +314,33 @@ void osd_t::handle_primary_bs_subop(osd_op_t *subop)
     }
     delete bs_op;
     subop->bs_op = NULL;
-    subop->peer_fd = -1;
-    handle_primary_subop(subop, cur_op);
+    subop->peer_fd = SELF_FD;
+    if (recovery_related && recovery_target_sleep_us)
+    {
+        tfd->set_timer_us(recovery_target_sleep_us, false, [=](int timer_id)
+        {
+            handle_primary_subop(subop, cur_op);
+        });
+    }
+    else
+    {
+        handle_primary_subop(subop, cur_op);
+    }
 }
 
-void osd_t::add_bs_subop_stats(osd_op_t *subop)
+void osd_t::add_bs_subop_stats(osd_op_t *subop, bool recovery_related)
 {
     // Include local blockstore ops in statistics
     uint64_t opcode = bs_op_to_osd_op[subop->bs_op->opcode];
     timespec tv_end;
     clock_gettime(CLOCK_REALTIME, &tv_end);
-    msgr.stats.op_stat_count[opcode]++;
-    if (!msgr.stats.op_stat_count[opcode])
+    uint64_t len = (opcode == OSD_OP_SEC_READ || opcode == OSD_OP_SEC_WRITE)
+        ? subop->bs_op->len : 0;
+    msgr.inc_op_stats(msgr.stats, opcode, subop->tv_begin, tv_end, len);
+    if (recovery_related)
     {
-        msgr.stats.op_stat_count[opcode] = 1;
-        msgr.stats.op_stat_sum[opcode] = 0;
-        msgr.stats.op_stat_bytes[opcode] = 0;
-    }
-    msgr.stats.op_stat_sum[opcode] += (
-        (tv_end.tv_sec - subop->tv_begin.tv_sec)*1000000 +
-        (tv_end.tv_nsec - subop->tv_begin.tv_nsec)/1000
-    );
-    if (opcode == OSD_OP_SEC_READ || opcode == OSD_OP_SEC_WRITE)
-    {
-        msgr.stats.op_stat_bytes[opcode] += subop->bs_op->len;
+        // It is OSD_OP_RECOVERY_RELATED
+        msgr.inc_op_stats(msgr.recovery_stats, opcode, subop->tv_begin, tv_end, len);
     }
 }
 
@@ -552,6 +563,7 @@ void osd_t::submit_primary_del_batch(osd_op_t *cur_op, obj_ver_osd_t *chunks_to_
                 },
                 .oid = chunk.oid,
                 .version = chunk.version,
+                .flags = cur_op->peer_fd == SELF_FD && cur_op->req.hdr.opcode != OSD_OP_SCRUB ? OSD_OP_RECOVERY_RELATED : 0,
             } };
             subops[i].callback = [cur_op, this](osd_op_t *subop)
             {
@@ -609,6 +621,7 @@ int osd_t::submit_primary_sync_subops(osd_op_t *cur_op)
                     .id = msgr.next_subop_id++,
                     .opcode = OSD_OP_SEC_SYNC,
                 },
+                .flags = cur_op->peer_fd == SELF_FD && cur_op->req.hdr.opcode != OSD_OP_SCRUB ? OSD_OP_RECOVERY_RELATED : 0,
             } };
             subops[i].callback = [cur_op, this](osd_op_t *subop)
             {
@@ -668,6 +681,7 @@ void osd_t::submit_primary_stab_subops(osd_op_t *cur_op)
                     .opcode = OSD_OP_SEC_STABILIZE,
                 },
                 .len = (uint64_t)(stab_osd.len * sizeof(obj_ver_id)),
+                .flags = cur_op->peer_fd == SELF_FD && cur_op->req.hdr.opcode != OSD_OP_SCRUB ? OSD_OP_RECOVERY_RELATED : 0,
             } };
             subops[i].iov.push_back(op_data->unstable_writes + stab_osd.start, stab_osd.len * sizeof(obj_ver_id));
             subops[i].callback = [cur_op, this](osd_op_t *subop)

src/osd_primary_write.cpp

@@ -292,16 +292,26 @@ resume_7:
     {
         {
             int recovery_type = op_data->object_state->state & (OBJ_DEGRADED|OBJ_INCOMPLETE) ? 0 : 1;
-            recovery_stat_count[0][recovery_type]++;
-            if (!recovery_stat_count[0][recovery_type])
+            recovery_stat[recovery_type].count++;
+            if (!recovery_stat[recovery_type].count) // wrapped
             {
-                recovery_stat_count[0][recovery_type]++;
-                recovery_stat_bytes[0][recovery_type] = 0;
+                memset(&recovery_print_prev[recovery_type], 0, sizeof(recovery_print_prev[recovery_type]));
+                memset(&recovery_stat[recovery_type], 0, sizeof(recovery_stat[recovery_type]));
+                recovery_stat[recovery_type].count++;
             }
             for (int role = 0; role < (op_data->scheme == POOL_SCHEME_REPLICATED ? 1 : pg.pg_size); role++)
             {
-                recovery_stat_bytes[0][recovery_type] += op_data->stripes[role].write_end - op_data->stripes[role].write_start;
+                recovery_stat[recovery_type].bytes += op_data->stripes[role].write_end - op_data->stripes[role].write_start;
             }
+            if (!cur_op->tv_end.tv_sec)
+            {
+                clock_gettime(CLOCK_REALTIME, &cur_op->tv_end);
+            }
+            uint64_t usec = (
+                (cur_op->tv_end.tv_sec - cur_op->tv_begin.tv_sec)*1000000 +
+                (cur_op->tv_end.tv_nsec - cur_op->tv_begin.tv_nsec)/1000
+            );
+            recovery_stat[recovery_type].usec += usec;
         }
         // Any kind of a non-clean object can have extra chunks, because we don't record objects
         // as degraded & misplaced or incomplete & misplaced at the same time. So try to remove extra chunks