Add --restart_interval to tests

.gitea/workflows/buildenv.Dockerfile

@@ -1,36 +0,0 @@
-FROM node:16-bullseye
-
-WORKDIR /root
-
-ADD ./docker/vitastor.gpg /etc/apt/trusted.gpg.d
-
-RUN echo 'deb http://deb.debian.org/debian bullseye-backports main' >> /etc/apt/sources.list; \
-    echo 'deb http://vitastor.io/debian bullseye main' >> /etc/apt/sources.list; \
-    echo >> /etc/apt/preferences; \
-    echo 'Package: *' >> /etc/apt/preferences; \
-    echo 'Pin: release a=bullseye-backports' >> /etc/apt/preferences; \
-    echo 'Pin-Priority: 500' >> /etc/apt/preferences; \
-    echo >> /etc/apt/preferences; \
-    echo 'Package: *' >> /etc/apt/preferences; \
-    echo 'Pin: origin "vitastor.io"' >> /etc/apt/preferences; \
-    echo 'Pin-Priority: 1000' >> /etc/apt/preferences; \
-    grep '^deb ' /etc/apt/sources.list | perl -pe 's/^deb/deb-src/' >> /etc/apt/sources.list; \
-    echo 'APT::Install-Recommends false;' >> /etc/apt/apt.conf; \
-    echo 'APT::Install-Suggests false;' >> /etc/apt/apt.conf
-
-RUN apt-get update
-RUN apt-get -y install etcd qemu-system-x86 qemu-block-extra qemu-utils fio libasan5 \
-    liburing1 liburing-dev libgoogle-perftools-dev devscripts libjerasure-dev cmake libibverbs-dev libisal-dev
-RUN apt-get -y build-dep fio qemu=`dpkg -s qemu-system-x86|grep ^Version:|awk '{print $2}'`
-RUN apt-get -y install jq lp-solve sudo
-RUN apt-get --download-only source fio qemu=`dpkg -s qemu-system-x86|grep ^Version:|awk '{print $2}'`
-
-RUN set -ex; \
-    mkdir qemu-build; \
-    cd qemu-build; \
-    dpkg-source -x /root/qemu*.dsc; \
-    cd qemu*/; \
-    debian/rules configure-qemu || debian/rules b/configure-stamp; \
-    cd b/qemu; \
-    make -j8 config-poison.h || true; \
-    make -j8 qapi/qapi-builtin-types.h

.gitea/workflows/test.Dockerfile

@@ -1,16 +0,0 @@
-FROM git.yourcmc.ru/vitalif/vitastor/buildenv
-
-ADD . /root/vitastor
-
-RUN set -e -x; \
-    mkdir -p /root/fio-build/; \
-    cd /root/fio-build/; \
-    dpkg-source -x /root/fio*.dsc; \
-    cd /root/vitastor; \
-    ln -s /root/fio-build/fio-*/ ./fio; \
-    ln -s /root/qemu-build/qemu-*/ ./qemu; \
-    ls /usr/include/linux/raw.h || cp ./debian/raw.h /usr/include/linux/raw.h; \
-    mkdir build; \
-    cd build; \
-    cmake .. -DWITH_ASAN=yes -DWITH_QEMU=yes; \
-    make -j16

.gitea/workflows/test.yml

@@ -1,552 +0,0 @@
-name: Test
-
-on:
-  push:
-    branches:
-    - '*'
-    paths:
-    - '.gitea/**'
-    - 'src/**'
-    - 'mon/**'
-    - 'json11'
-    - 'cpp-btree'
-    - 'tests/**'
-
-env:
-  BUILDENV_IMAGE: git.yourcmc.ru/vitalif/vitastor/buildenv
-  TEST_IMAGE: git.yourcmc.ru/vitalif/vitastor/test
-  OSD_ARGS: '--etcd_quick_timeout 2000'
-
-concurrency:
-  group: ci-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-
-  buildenv:
-    runs-on: ubuntu-latest
-    container: git.yourcmc.ru/vitalif/gitea-ci-dind
-    steps:
-    - uses: actions/checkout@v3
-
-    - name: Build and push
-      run: |
-        set -ex
-        if ! docker manifest inspect $BUILDENV_IMAGE >/dev/null; then
-          docker build -t $BUILDENV_IMAGE -f .gitea/workflows/buildenv.Dockerfile .
-          docker login git.yourcmc.ru -u vitalif -p "${{secrets.TOKEN}}"
-          docker push $BUILDENV_IMAGE
-        fi
-
-  build:
-    runs-on: ubuntu-latest
-    needs: buildenv
-    container: git.yourcmc.ru/vitalif/gitea-ci-dind
-    steps:
-    - uses: actions/checkout@v3
-      with:
-        submodules: true
-
-    - name: Build and push
-      run: |
-        set -ex
-        if ! docker manifest inspect $TEST_IMAGE:$GITHUB_SHA >/dev/null; then
-          docker build -t $TEST_IMAGE:$GITHUB_SHA -f .gitea/workflows/test.Dockerfile .
-          docker login git.yourcmc.ru -u vitalif -p "${{secrets.TOKEN}}"
-          docker push $TEST_IMAGE:$GITHUB_SHA
-        fi
-
-  make_test:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    # leak sanitizer sometimes crashes
-    - run: cd /root/vitastor/build && ASAN_OPTIONS=detect_leaks=0 make -j16 test
-
-  test_add_osd:
-    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_add_osd.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_cas:
-    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_cas.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_change_pg_count:
-    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_change_pg_count.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_change_pg_count_ec:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 3
-      run: SCHEME=ec /root/vitastor/tests/test_change_pg_count.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_change_pg_size:
-    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_change_pg_size.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_create_nomaxid:
-    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_create_nomaxid.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_etcd_fail:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 10
-      run: /root/vitastor/tests/test_etcd_fail.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_failure_domain:
-    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_failure_domain.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_interrupted_rebalance:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 10
-      run: /root/vitastor/tests/test_interrupted_rebalance.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_interrupted_rebalance_imm:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 10
-      run: IMMEDIATE_COMMIT=1 /root/vitastor/tests/test_interrupted_rebalance.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_interrupted_rebalance_ec:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 10
-      run: SCHEME=ec /root/vitastor/tests/test_interrupted_rebalance.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_interrupted_rebalance_ec_imm:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 10
-      run: SCHEME=ec IMMEDIATE_COMMIT=1 /root/vitastor/tests/test_interrupted_rebalance.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_minsize_1:
-    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_minsize_1.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_move_reappear:
-    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_move_reappear.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_rebalance_verify:
-    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_rebalance_verify.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_rebalance_verify_imm:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 3
-      run: IMMEDIATE_COMMIT=1 /root/vitastor/tests/test_rebalance_verify.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_rebalance_verify_ec:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 3
-      run: SCHEME=ec /root/vitastor/tests/test_rebalance_verify.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_rebalance_verify_ec_imm:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 3
-      run: SCHEME=ec IMMEDIATE_COMMIT=1 /root/vitastor/tests/test_rebalance_verify.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_rm:
-    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_rm.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_snapshot:
-    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_snapshot.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_snapshot_ec:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 3
-      run: SCHEME=ec /root/vitastor/tests/test_snapshot.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_splitbrain:
-    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_splitbrain.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
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 3
-      run: /root/vitastor/tests/test_write.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_xor:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 3
-      run: SCHEME=xor /root/vitastor/tests/test_write.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_no_same:
-    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_write_no_same.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_heal_pg_size_2:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 10
-      run: PG_SIZE=2 /root/vitastor/tests/test_heal.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_heal_ec:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 10
-      run: SCHEME=ec /root/vitastor/tests/test_heal.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
-

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

@@ -1,68 +0,0 @@
-#!/usr/bin/perl
-
-use strict;
-
-for my $line (<>)
-{
-    if ($line =~ /\.\/(test_[^\.]+)/s)
-    {
-        chomp $line;
-        my $test_name = $1;
-        my $timeout = 3;
-        if ($test_name eq 'test_etcd_fail' || $test_name eq 'test_heal' || $test_name eq 'test_interrupted_rebalance')
-        {
-            $timeout = 10;
-        }
-        while ($line =~ /([^\s=]+)=(\S+)/gs)
-        {
-            if ($1 eq 'SCHEME' && $2 eq 'ec')
-            {
-                $test_name .= '_ec';
-            }
-            elsif ($1 eq 'SCHEME' && $2 eq 'xor')
-            {
-                $test_name .= '_xor';
-            }
-            elsif ($1 eq 'IMMEDIATE_COMMIT')
-            {
-                $test_name .= '_imm';
-            }
-            else
-            {
-                $test_name .= '_'.lc($1).'_'.$2;
-            }
-        }
-        $line =~ s!\./test_!/root/vitastor/tests/test_!;
-        # Gitea CI doesn't support artifacts yet, lol
-        #- name: Upload results
-        #  uses: actions/upload-artifact\@v3
-        #  if: always()
-        #  with:
-        #    name: ${test_name}_result
-        #    path: |
-        #      /root/vitastor/testdata
-        #      !/root/vitastor/testdata/*.bin
-        #    retention-days: 5
-        print <<"EOF"
-  $test_name:
-    runs-on: ubuntu-latest
-    needs: build
-    container: \${{env.TEST_IMAGE}}:\${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: $timeout
-      run: $line
-    - 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
-
-EOF
-;
-    }
-}

CMakeLists.txt

@@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8.12)
 
 project(vitastor)
 
-set(VERSION "0.8.9")
+set(VERSION "0.8.8")
 
 add_subdirectory(src)

csi/Makefile

@@ -1,4 +1,4 @@
-VERSION ?= v0.8.9
+VERSION ?= v0.8.8
 
 all: build push
 

csi/deploy/004-csi-nodeplugin.yaml

@@ -49,7 +49,7 @@ spec:
             capabilities:
               add: ["SYS_ADMIN"]
             allowPrivilegeEscalation: true
-          image: vitalif/vitastor-csi:v0.8.9
+          image: vitalif/vitastor-csi:v0.8.8
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/deploy/007-csi-provisioner.yaml

@@ -116,7 +116,7 @@ spec:
             privileged: true
             capabilities:
               add: ["SYS_ADMIN"]
-          image: vitalif/vitastor-csi:v0.8.9
+          image: vitalif/vitastor-csi:v0.8.8
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/src/config.go

@@ -5,7 +5,7 @@ package vitastor
 
 const (
     vitastorCSIDriverName    = "csi.vitastor.io"
-    vitastorCSIDriverVersion = "0.8.9"
+    vitastorCSIDriverVersion = "0.8.8"
 )
 
 // Config struct fills the parameters of request or user input

debian/changelog

@@ -1,10 +1,10 @@
-vitastor (0.8.9-1) unstable; urgency=medium
+vitastor (0.8.8-1) unstable; urgency=medium
 
   * Bugfixes
 
  -- Vitaliy Filippov <vitalif@yourcmc.ru>  Fri, 03 Jun 2022 02:09:44 +0300
 
-vitastor (0.8.9-1) unstable; urgency=medium
+vitastor (0.8.8-1) unstable; urgency=medium
 
   * Implement NFS proxy
   * Add documentation

debian/vitastor.Dockerfile

@@ -34,8 +34,8 @@ RUN set -e -x; \
     mkdir -p /root/packages/vitastor-$REL; \
     rm -rf /root/packages/vitastor-$REL/*; \
     cd /root/packages/vitastor-$REL; \
-    cp -r /root/vitastor vitastor-0.8.9; \
-    cd vitastor-0.8.9; \
+    cp -r /root/vitastor vitastor-0.8.8; \
+    cd vitastor-0.8.8; \
     ln -s /root/fio-build/fio-*/ ./fio; \
     FIO=$(head -n1 fio/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
     ls /usr/include/linux/raw.h || cp ./debian/raw.h /usr/include/linux/raw.h; \
@@ -48,8 +48,8 @@ RUN set -e -x; \
     rm -rf a b; \
     echo "dep:fio=$FIO" > debian/fio_version; \
     cd /root/packages/vitastor-$REL; \
-    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_0.8.9.orig.tar.xz vitastor-0.8.9; \
-    cd vitastor-0.8.9; \
+    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_0.8.8.orig.tar.xz vitastor-0.8.8; \
+    cd vitastor-0.8.8; \
     V=$(head -n1 debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
     DEBFULLNAME="Vitaliy Filippov <vitalif@yourcmc.ru>" dch -D $REL -v "$V""$REL" "Rebuild for $REL"; \
     DEB_BUILD_OPTIONS=nocheck dpkg-buildpackage --jobs=auto -sa; \

mon/mon-main.js

@@ -13,7 +13,7 @@ for (let i = 2; i < process.argv.length; i++)
     {
         console.error('USAGE: '+process.argv[0]+' '+process.argv[1]+' [--verbose 1]'+
             ' [--etcd_address "http://127.0.0.1:2379,..."] [--config_path /etc/vitastor/vitastor.conf]'+
-            ' [--etcd_prefix "/vitastor"] [--etcd_start_timeout 5]');
+            ' [--etcd_prefix "/vitastor"] [--etcd_start_timeout 5] [--restart_interval 5]');
         process.exit();
     }
     else if (process.argv[i].substr(0, 2) == '--')

mon/mon.js

@@ -561,7 +561,7 @@ class Mon
         }
         if (!this.ws)
         {
-            this.die('Failed to open etcd watch websocket');
+            await this.die('Failed to open etcd watch websocket');
         }
         const cur_addr = this.selected_etcd_url;
         this.ws_alive = true;
@@ -728,7 +728,7 @@ 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');
+                await this.die('Lease expired');
             }
         }, this.config.etcd_mon_timeout);
         if (!this.signals_set)
@@ -741,9 +741,32 @@ class Mon
 
     async on_stop(status)
     {
-        clearInterval(this.lease_timer);
-        await this.etcd_call('/lease/revoke', { ID: this.etcd_lease_id }, this.config.etcd_mon_timeout, this.config.etcd_mon_retries);
-        process.exit(status);
+        if (this.ws_keepalive_timer)
+        {
+            clearInterval(this.ws_keepalive_timer);
+            this.ws_keepalive_timer = null;
+        }
+        if (this.lease_timer)
+        {
+            clearInterval(this.lease_timer);
+            this.lease_timer = null;
+        }
+        if (this.etcd_lease_id)
+        {
+            const lease_id = this.etcd_lease_id;
+            this.etcd_lease_id = null;
+            await this.etcd_call('/lease/revoke', { ID: lease_id }, this.config.etcd_mon_timeout, this.config.etcd_mon_retries);
+        }
+        if (!status || !this.initConfig.restart_interval)
+        {
+            process.exit(status);
+        }
+        else
+        {
+            console.log('Restarting after '+this.initConfig.restart_interval+' seconds');
+            await new Promise(ok => setTimeout(ok, this.initConfig.restart_interval*1000));
+            await this.start();
+        }
     }
 
     async become_master()
@@ -1771,14 +1794,13 @@ class Mon
                 return res.json;
             }
         }
-        this.die();
+        await this.die();
     }
 
-    _die(err)
+    async _die(err)
     {
-        // In fact we can just try to rejoin
         console.error(new Error(err || 'Cluster connection failed'));
-        process.exit(1);
+        await this.on_stop(1);
     }
 
     local_ips(all)
@@ -1823,7 +1845,7 @@ function POST(url, body, timeout)
             clearTimeout(timer_id);
             let res_body = '';
             res.setEncoding('utf8');
-            res.on('error', (error) => ok({ error }));
+            res.on('error', no);
             res.on('data', chunk => { res_body += chunk; });
             res.on('end', () =>
             {
@@ -1843,8 +1865,8 @@ function POST(url, body, timeout)
                 }
             });
         });
-        req.on('error', (error) => ok({ error }));
-        req.on('close', () => ok({ error: new Error('Connection closed prematurely') }));
+        req.on('error', no);
+        req.on('close', () => no(new Error('Connection closed prematurely')));
         req.write(body_text);
         req.end();
     });

patches/cinder-vitastor.py

@@ -50,7 +50,7 @@ from cinder.volume import configuration
 from cinder.volume import driver
 from cinder.volume import volume_utils
 
-VERSION = '0.8.9'
+VERSION = '0.8.8'
 
 LOG = logging.getLogger(__name__)
 

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-0.8.9/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-0.8.9$(rpm --eval '%dist').tar.gz *
+tar --transform 's#^#vitastor-0.8.8/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-0.8.8$(rpm --eval '%dist').tar.gz *

rpm/vitastor-el7.Dockerfile

@@ -35,7 +35,7 @@ ADD . /root/vitastor
 RUN set -e; \
     cd /root/vitastor/rpm; \
     sh build-tarball.sh; \
-    cp /root/vitastor-0.8.9.el7.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-0.8.8.el7.tar.gz ~/rpmbuild/SOURCES; \
     cp vitastor-el7.spec ~/rpmbuild/SPECS/vitastor.spec; \
     cd ~/rpmbuild/SPECS/; \
     rpmbuild -ba vitastor.spec; \

rpm/vitastor-el7.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        0.8.9
+Version:        0.8.8
 Release:        1%{?dist}
 Summary:        Vitastor, a fast software-defined clustered block storage
 
 License:        Vitastor Network Public License 1.1
 URL:            https://vitastor.io/
-Source0:        vitastor-0.8.9.el7.tar.gz
+Source0:        vitastor-0.8.8.el7.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

rpm/vitastor-el8.Dockerfile

@@ -35,7 +35,7 @@ ADD . /root/vitastor
 RUN set -e; \
     cd /root/vitastor/rpm; \
     sh build-tarball.sh; \
-    cp /root/vitastor-0.8.9.el8.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-0.8.8.el8.tar.gz ~/rpmbuild/SOURCES; \
     cp vitastor-el8.spec ~/rpmbuild/SPECS/vitastor.spec; \
     cd ~/rpmbuild/SPECS/; \
     rpmbuild -ba vitastor.spec; \

rpm/vitastor-el8.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        0.8.9
+Version:        0.8.8
 Release:        1%{?dist}
 Summary:        Vitastor, a fast software-defined clustered block storage
 
 License:        Vitastor Network Public License 1.1
 URL:            https://vitastor.io/
-Source0:        vitastor-0.8.9.el8.tar.gz
+Source0:        vitastor-0.8.8.el8.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

rpm/vitastor-el9.Dockerfile

@@ -18,7 +18,7 @@ ADD . /root/vitastor
 RUN set -e; \
     cd /root/vitastor/rpm; \
     sh build-tarball.sh; \
-    cp /root/vitastor-0.8.9.el9.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-0.8.8.el9.tar.gz ~/rpmbuild/SOURCES; \
     cp vitastor-el9.spec ~/rpmbuild/SPECS/vitastor.spec; \
     cd ~/rpmbuild/SPECS/; \
     rpmbuild -ba vitastor.spec; \

rpm/vitastor-el9.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        0.8.9
+Version:        0.8.8
 Release:        1%{?dist}
 Summary:        Vitastor, a fast software-defined clustered block storage
 
 License:        Vitastor Network Public License 1.1
 URL:            https://vitastor.io/
-Source0:        vitastor-0.8.9.el9.tar.gz
+Source0:        vitastor-0.8.8.el9.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

src/CMakeLists.txt

@@ -16,7 +16,7 @@ if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
 	set(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
 endif()
 
-add_definitions(-DVERSION="0.8.9")
+add_definitions(-DVERSION="0.8.8")
 add_definitions(-Wall -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith -fdiagnostics-color=always -I ${CMAKE_SOURCE_DIR}/src)
 if (${WITH_ASAN})
 	add_definitions(-fsanitize=address -fno-omit-frame-pointer)

src/cluster_client.cpp

@@ -743,16 +743,15 @@ resume_3:
         erase_op(op);
         return 1;
     }
-    else if (op->retval != 0 && op->retval != -EPIPE && op->retval != -EIO && op->retval != -ENOSPC)
+    else if (op->retval != 0 && op->retval != -EPIPE)
     {
-        // Fatal error (neither -EPIPE, -EIO nor -ENOSPC)
-        // FIXME: Add a parameter to allow to not wait for EIOs (incomplete or corrupted objects) to heal
+        // Fatal error (not -EPIPE)
         erase_op(op);
         return 1;
     }
     else
     {
-        // Non-fatal error - clear the error and retry
+        // -EPIPE - clear the error and retry
         op->retval = 0;
         if (op->needs_reslice)
         {
@@ -1049,7 +1048,7 @@ resume_1:
                 uw_it->second.state = CACHE_DIRTY;
             }
         }
-        if (op->retval == -EPIPE || op->retval == -EIO || op->retval == -ENOSPC)
+        if (op->retval == -EPIPE)
         {
             // Retry later
             op->parts.clear();
@@ -1120,13 +1119,13 @@ void cluster_client_t::handle_op_part(cluster_op_part_t *part)
     {
         // Operation failed, retry
         part->flags |= PART_ERROR;
-        if (!op->retval || op->retval == -EPIPE || part->op.reply.hdr.retval == -EIO)
+        if (!op->retval || op->retval == -EPIPE)
         {
-            // Error priority: EIO > ENOSPC > EPIPE
+            // Don't overwrite other errors with -EPIPE
             op->retval = part->op.reply.hdr.retval;
         }
         int stop_fd = -1;
-        if (op->retval != -EINTR && op->retval != -EIO && op->retval != -ENOSPC)
+        if (op->retval != -EINTR && op->retval != -EIO)
         {
             stop_fd = part->op.peer_fd;
             fprintf(
@@ -1134,25 +1133,21 @@ void cluster_client_t::handle_op_part(cluster_op_part_t *part)
                 osd_op_names[part->op.req.hdr.opcode], part->osd_num, part->op.reply.hdr.retval, expected
             );
         }
-        else
-        {
-            fprintf(
-                stderr, "%s operation failed on OSD %lu: retval=%ld (expected %d)\n",
-                osd_op_names[part->op.req.hdr.opcode], part->osd_num, part->op.reply.hdr.retval, expected
-            );
-        }
         // All next things like timer, continue_sync/rw and stop_client may affect the operation again
         // So do all these things after modifying operation state, otherwise we may hit reenterability bugs
         // FIXME postpone such things to set_immediate here to avoid bugs
-        // Mark op->up_wait = true to retry operation after a short pause (not immediately)
-        op->up_wait = true;
-        if (!retry_timeout_id)
+        if (part->op.reply.hdr.retval == -EPIPE)
         {
-            retry_timeout_id = tfd->set_timer(up_wait_retry_interval, false, [this](int)
+            // Mark op->up_wait = true before stopping the client
+            op->up_wait = true;
+            if (!retry_timeout_id)
             {
-                retry_timeout_id = 0;
-                continue_ops(true);
-            });
+                retry_timeout_id = tfd->set_timer(up_wait_retry_interval, false, [this](int)
+                {
+                    retry_timeout_id = 0;
+                    continue_ops(true);
+                });
+            }
         }
         if (op->inflight_count == 0)
         {

src/msgr_receive.cpp

@@ -103,10 +103,7 @@ bool osd_messenger_t::handle_read(int result, osd_client_t *cl)
             cl->recv_list.eat(result);
             if (cl->recv_list.done >= cl->recv_list.count)
             {
-                if (!handle_finished_read(cl))
-                {
-                    goto fin;
-                }
+                handle_finished_read(cl);
             }
         }
         if (result >= cl->read_iov.iov_len)

src/osd_cluster.cpp

@@ -812,21 +812,11 @@ void osd_t::report_pg_states()
                     pg_it->second.cur_state != 0)
                 {
                     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
-                        continue;
-                    }
                 }
             }
         }
         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 {
@@ -911,15 +901,6 @@ void osd_t::report_pg_states()
     {
         etcd_reporting_pg_state = false;
         if (!data["succeeded"].bool_value())
-        {
-            std::string rpgnames = "";
-            for (auto pp: reporting_pgs)
-            {
-                rpgnames += (rpgnames.size() ? ", " : "")+std::to_string(pp.pool_pg_num.pool_id)+"/"+std::to_string(pp.pool_pg_num.pg_num);
-            }
-            printf("Error reporting PG %s states, will repeat the attempt: %s\n", rpgnames.c_str(), err.c_str());
-        }
-        if (!data["succeeded"].bool_value())
         {
             // One of PG state updates failed, put dirty flags back
             for (auto pp: reporting_pgs)

src/osd_primary_write.cpp

@@ -81,7 +81,7 @@ resume_1:
         if (!cur_op->rmw_buf)
         {
             // Refuse partial overwrite of an incomplete object
-            cur_op->reply.hdr.retval = -EIO;
+            cur_op->reply.hdr.retval = -EINVAL;
             goto continue_others;
         }
     }
@@ -197,11 +197,6 @@ resume_5:
     }
     if (op_data->errors > 0)
     {
-        // FIXME: Handle ENOSPC. If one of the subops fail with ENOSPC here,
-        // next writes to the same object will also fail because they'll try
-        // to overwrite the same version number which will result in EEXIST.
-        // To fix it, we should mark the object as degraded for replicas,
-        // and rollback successful part updates in case of EC.
         pg_cancel_write_queue(pg, cur_op, op_data->oid, op_data->errcode);
         return;
     }

src/qemu_driver.c

@@ -218,7 +218,6 @@ static void coroutine_fn vitastor_co_get_metadata(VitastorRPC *task)
     }
 }
 
-// FIXME: Fix thread safety of the driver - now it segfaults when iothread is enabled in QEMU
 static void vitastor_aio_set_fd_handler(void *ctx, int fd, int unused1, IOHandler *fd_read, IOHandler *fd_write, void *unused2, void *opaque)
 {
     aio_set_fd_handler(ctx, fd,

src/vitastor.pc.in

@@ -6,7 +6,7 @@ includedir=${prefix}/@CMAKE_INSTALL_INCLUDEDIR@
 
 Name: Vitastor
 Description: Vitastor client library
-Version: 0.8.9
+Version: 0.8.8
 Libs: -L${libdir} -lvitastor_client
 Cflags: -I${includedir}
 

tests/common.sh

@@ -53,12 +53,12 @@ start_etcd()
 for i in $(seq 1 $ETCD_COUNT); do
     start_etcd $i
 done
-for i in {1..30}; do
+for i in {1..10}; do
     ${ETCD}ctl --endpoints=$ETCD_URL --dial-timeout=1s --command-timeout=1s member list >/dev/null && break
-    if [[ $i = 30 ]]; then
-        format_error "Failed to start etcd"
-    fi
 done
+if [[ $i = 10 ]]; then
+    format_error "Failed to start etcd"
+fi
 
 echo leak:fio >> testdata/lsan-suppress.txt
 echo leak:tcmalloc >> testdata/lsan-suppress.txt

tests/run_3osds.sh

@@ -39,19 +39,19 @@ done
 cd mon
 npm install
 cd ..
-(while true; do node mon/mon-main.js --etcd_url $ETCD_URL --etcd_prefix "/vitastor" --verbose 1 || true; done) &>./testdata/mon.log &
+node mon/mon-main.js --etcd_url $ETCD_URL --etcd_prefix "/vitastor" --verbose 1 --restart_interval 5 &>./testdata/mon.log &
 MON_PID=$!
 
 if [ "$SCHEME" = "ec" ]; then
     PG_SIZE=${PG_SIZE:-5}
-    PG_MINSIZE=${PG_MINSIZE:-4}
-    PG_DATA_SIZE=${PG_DATA_SIZE:-3}
-    POOLCFG='"scheme":"ec","parity_chunks":'$((PG_SIZE-PG_DATA_SIZE))
+    PG_MINSIZE=${PG_MINSIZE:-3}
+    PG_DATA_SIZE=$PG_MINSIZE
+    POOLCFG='"scheme":"ec","parity_chunks":'$((PG_SIZE-PG_MINSIZE))
 elif [ "$SCHEME" = "xor" ]; then
     PG_SIZE=${PG_SIZE:-3}
-    PG_MINSIZE=${PG_MINSIZE:-3}
-    PG_DATA_SIZE=$((PG_SIZE-1))
-    POOLCFG='"scheme":"xor","parity_chunks":1'
+    PG_MINSIZE=${PG_MINSIZE:-2}
+    PG_DATA_SIZE=$PG_MINSIZE
+    POOLCFG='"scheme":"xor","parity_chunks":'$((PG_SIZE-PG_MINSIZE))
 else
     PG_SIZE=${PG_SIZE:-2}
     PG_MINSIZE=${PG_MINSIZE:-2}

tests/run_tests.sh

@@ -44,5 +44,5 @@ SCHEME=xor ./test_write.sh
 
 ./test_write_no_same.sh
 
-PG_SIZE=2 ./test_heal.sh
-SCHEME=ec ./test_heal.sh
+./test_heal.sh
+SCHEME=ec PG_MINSIZE=2 ./test_heal.sh

tests/test_add_osd.sh

@@ -28,7 +28,7 @@ if ! ($ETCDCTL get /vitastor/config/pgs --print-value-only |\
     format_error "FAILED: OSD NOT ADDED INTO DISTRIBUTION"
 fi
 
-wait_finish_rebalance 60
+wait_finish_rebalance 20
 
 sleep 1
 kill -9 $OSD4_PID
@@ -50,6 +50,6 @@ if ! ($ETCDCTL get /vitastor/config/pgs --print-value-only |\
     format_error "FAILED: OSD NOT REMOVED FROM DISTRIBUTION"
 fi
 
-wait_finish_rebalance 60
+wait_finish_rebalance 20
 
 format_green OK

tests/test_change_pg_count.sh

@@ -21,7 +21,7 @@ try_change()
 
     $ETCDCTL put /vitastor/config/pools '{"1":{'$POOLCFG',"pg_size":'$PG_SIZE',"pg_minsize":'$PG_MINSIZE',"pg_count":'$n'}}'
 
-    for i in {1..60}; do
+    for i in {1..10}; do
         ($ETCDCTL get /vitastor/config/pgs --print-value-only | jq -s -e '(.[0].items["1"] | map((.osd_set | select(. > 0)) | length == 2) | length) == '$n) && \
             ($ETCDCTL get --prefix /vitastor/pg/state/ --print-value-only | jq -s -e '([ .[] | select(.state == ["active"] or .state == ["active", "has_misplaced"]) ] | length) == '$n'') && \
             break

tests/test_failure_domain.sh

@@ -18,7 +18,7 @@ $ETCDCTL put /vitastor/config/pools '{"1":{"name":"testpool","scheme":"replicate
 cd mon
 npm install
 cd ..
-node mon/mon-main.js --etcd_url $ETCD_URL --etcd_prefix "/vitastor" &>./testdata/mon.log &
+node mon/mon-main.js --etcd_url $ETCD_URL --etcd_prefix "/vitastor" --verbose 1 --restart_interval 5 &>./testdata/mon.log &
 MON_PID=$!
 
 sleep 2

tests/test_heal.sh

@@ -2,11 +2,7 @@
 
 # Kill OSDs while writing
 
-PG_SIZE=${PG_SIZE:-3}
-if [[ "$SCHEME" = "ec" ]]; then
-    PG_DATA_SIZE=${PG_DATA_SIZE:-2}
-    PG_MINSIZE=${PG_MINSIZE:-3}
-fi
+PG_SIZE=3
 OSD_COUNT=7
 PG_COUNT=32
 . `dirname $0`/run_3osds.sh

tests/test_interrupted_rebalance.sh

@@ -30,11 +30,8 @@ try_reweight 4 1
 
 try_reweight 5 1
 
-# Allow rebalance to start
-sleep 5
-
 # Wait for the rebalance to finish
-wait_finish_rebalance 300
+wait_finish_rebalance 60
 
 # Check that PGs never had degraded objects !
 # FIXME: In fact, the test doesn't guarantee it because PGs aren't always peered only with full prior OSD sets :-(

tests/test_move_reappear.sh

@@ -15,14 +15,11 @@ $ETCDCTL put /vitastor/config/pools '{"1":{"name":"testpool","scheme":"replicate
 
 $ETCDCTL put /vitastor/config/pgs '{"items":{"1":{"1":{"osd_set":[1,0],"primary":1}}}}'
 
-for i in {1..30}; do
-    sleep 1
-    if ($ETCDCTL get /vitastor/pg/state/1/1 --print-value-only | jq -s -e '(. | length) != 0 and .[0].state == ["active","degraded"]'); then
-        break
-    elif [[ $i = 30 ]]; then
-        format_error "Failed to start the PG active+degraded"
-    fi
-done
+sleep 2
+
+if ! ($ETCDCTL get /vitastor/pg/state/1/1 --print-value-only | jq -s -e '(. | length) != 0 and .[0].state == ["active","degraded"]'); then
+    format_error "Failed to start the PG active+degraded"
+fi
 
 LD_PRELOAD="build/src/libfio_vitastor.so" \
 fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bs=4M -direct=1 -iodepth=1 -fsync=1 -rw=write \
@@ -30,60 +27,45 @@ fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bs=4M -direct=1 -
 
 $ETCDCTL put /vitastor/config/pgs '{"items":{"1":{"1":{"osd_set":[1,0],"primary":0}}}}'
 
-for i in {1..30}; do
-    sleep 1
-    if [[ "`$ETCDCTL get /vitastor/pg/state/1/1 --print-value-only`" = "" ]]; then
-        break
-    elif [[ $i = 30 ]]; then
-        format_error "Failed to stop the PG"
-    fi
-done
+sleep 2
+
+if [ "`$ETCDCTL get /vitastor/pg/state/1/1 --print-value-only`" != "" ]; then
+    format_error "Failed to stop the PG"
+fi
 
 $ETCDCTL put /vitastor/pg/history/1/1 '{"all_peers":[1,2,3]}'
 
 $ETCDCTL put /vitastor/config/pgs '{"items":{"1":{"1":{"osd_set":[4,5],"primary":4}}}}'
 
 sleep 5
-for i in {1..30}; do
-    sleep 1
-    if ($ETCDCTL get /vitastor/pg/state/1/1 --print-value-only | jq -s -e '(. | length) != 0 and .[0].state == ["active"]'); then
-        break
-    elif [[ $i = 30 ]]; then
-        format_error "Failed to move degraded objects to the clean OSD set"
-    fi
-done
+
+if ! ($ETCDCTL get /vitastor/pg/state/1/1 --print-value-only | jq -s -e '(. | length) != 0 and .[0].state == ["active"]'); then
+    format_error "Failed to move degraded objects to the clean OSD set"
+fi
 
 $ETCDCTL put /vitastor/config/pgs '{"items":{"1":{"1":{"osd_set":[4,5],"primary":0}}}}'
 
 $ETCDCTL put /vitastor/pg/history/1/1 '{"all_peers":[1,2,3]}'
 
-for i in {1..30}; do
-    sleep 1
-    if [ "`$ETCDCTL get /vitastor/pg/state/1/1 --print-value-only`" = "" ]; then
-        break
-    elif [[ $i = 30 ]]; then
-        format_error "Failed to stop the PG after degraded recovery"
-    fi
-done
+sleep 2
+
+if [ "`$ETCDCTL get /vitastor/pg/state/1/1 --print-value-only`" != "" ]; then
+    format_error "Failed to stop the PG after degraded recovery"
+fi
 
 cp testdata/osd4.log testdata/osd4_pre.log
 >testdata/osd4.log
 
 $ETCDCTL put /vitastor/config/pgs '{"items":{"1":{"1":{"osd_set":[4,5],"primary":4}}}}'
 
-for i in {1..30}; do
-    sleep 1
-    if grep -q 'PG 1/1.*is.*has_' testdata/osd4.log; then
-        if [[ $i = 30 ]]; then
-            format_error "PG has degraded or misplaced objects after a full re-peer following a degraded recovery"
-        fi
-    elif ! ($ETCDCTL get /vitastor/pg/state/1/1 --print-value-only | jq -s -e '(. | length) != 0 and .[0].state == ["active"]'); then
-        if [[ $i = 30 ]]; then
-            format_error "PG not active+clean after a full re-peer following a degraded recovery"
-        fi
-    else
-        break
-    fi
-done
+sleep 2
+
+if grep -q 'PG 1/1.*is.*has_' testdata/osd4.log; then
+    format_error "PG has degraded or misplaced objects after a full re-peer following a degraded recovery"
+fi
+
+if ! ($ETCDCTL get /vitastor/pg/state/1/1 --print-value-only | jq -s -e '(. | length) != 0 and .[0].state == ["active"]'); then
+    format_error "PG not active+clean after a full re-peer following a degraded recovery"
+fi
 
 format_green OK

tests/test_rebalance_verify.sh

@@ -10,7 +10,7 @@ IMG_SIZE=256
 
 $ETCDCTL put /vitastor/config/inode/1/1 '{"name":"testimg","size":'$((IMG_SIZE*1024*1024))'}'
 
-NBD_DEV=$(sudo build/src/vitastor-nbd map --nbd_timeout 180 --etcd_address $ETCD_URL --image testimg --logfile ./testdata/nbd.log &)
+NBD_DEV=$(sudo build/src/vitastor-nbd map --etcd_address $ETCD_URL --image testimg --logfile ./testdata/nbd.log &)
 
 trap "sudo build/src/vitastor-nbd unmap $NBD_DEV"'; kill -9 $(jobs -p)' EXIT
 

tests/test_splitbrain.sh

@@ -21,7 +21,7 @@ LD_PRELOAD="build/src/libfio_vitastor.so" \
 # Kill OSD 2, start OSD 1
 
 kill $OSD2_PID
-build/src/vitastor-osd --osd_num 1 --bind_address 127.0.0.1 $NO_SAME $OSD_ARGS --etcd_address $ETCD_URL \
+build/src/vitastor-osd --osd_num 1 --bind_address 127.0.0.1 $OSD_ARGS --etcd_address $ETCD_URL \
     $(build/src/vitastor-disk simple-offsets --format options --device ./testdata/test_osd2.bin 2>/dev/null) >>./testdata/osd2.log 2>&1 &
 sleep 2
 

tests/test_vm_cont.sh

@@ -14,7 +14,7 @@ for i in $(seq 1 $OSD_COUNT); do
     eval OSD${i}_PID=$!
 done
 
-(while true; do node mon/mon-main.js --etcd_url $ETCD_URL --etcd_prefix "/vitastor" --verbose 1 || true; done) &>./testdata/mon.log &
+node mon/mon-main.js --etcd_url $ETCD_URL --etcd_prefix "/vitastor" --verbose 1 --restart_interval 5 &>./testdata/mon.log &
 MON_PID=$!
 
 sleep 3