Fix "is already mounted" checks in CSI

New features:
- Support resizing normal vitastor-disk partitions and moving journal/metadata: [vitastor-disk resize](https://vitastor.io/docs/usage/disk.html#resize)
- Support simple forms of vitastor-disk {dump,write}-{meta,journal} for OSD partitions

Bug fixes:
- Fix block RWX volumes broken after introducing stage/unstage support
- Do not allow to create non-block RWX volumes in CSI
- Fix vitastor-disk prepare not seeing the newly created partition in rare cases
- Fix non-array tags not showing up in ls-osd/osd-tree
- Make OpenNebula oned.conf patching during installation smarter
- Fix iseek option in vitastor-cli dd not working
- Validate conv=, iflag=, oflag= options in vitastor-cli dd
- Fix vitastor-disk write-meta not writing header checksum to the disk
- Fix JSON format in vitastor-disk dump-meta
- Fix read_chain_bitmap not working for snapshot in another pool
- Fix a possible OSD crash during parallel read & write to an image with snapshots
- Several followups to the READ_CHAIN_BITMAP fix: avoid data reads, fix possible overflow in is_zero(), fix bitmap size

.gitea/workflows/test.yml

@@ -16,6 +16,7 @@ env:
   BUILDENV_IMAGE: git.yourcmc.ru/vitalif/vitastor/buildenv
   TEST_IMAGE: git.yourcmc.ru/vitalif/vitastor/test
   OSD_ARGS: '--etcd_quick_timeout 2000'
+  USE_RAMDISK: 1
 
 concurrency:
   group: ci-${{ github.ref }}
@@ -197,6 +198,24 @@ jobs:
           echo ""
         done
 
+  test_etcd_fail_antietcd:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 10
+      run: ANTIETCD=1 /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_interrupted_rebalance:
     runs-on: ubuntu-latest
     needs: build
@@ -539,6 +558,24 @@ jobs:
           echo ""
         done
 
+  test_dd:
+    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_dd.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_root_node:
     runs-on: ubuntu-latest
     needs: build
@@ -665,6 +702,24 @@ jobs:
           echo ""
         done
 
+  test_heal_antietcd:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 10
+      run: ANTIETCD=1 /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_csum_32k_dmj:
     runs-on: ubuntu-latest
     needs: build
@@ -773,6 +828,24 @@ jobs:
           echo ""
         done
 
+  test_snapshot_pool2:
+    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_pool2.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_osd_tags:
     runs-on: ubuntu-latest
     needs: build

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

@@ -34,6 +34,10 @@ for my $line (<>)
             {
                 $test_name .= '_imm';
             }
+            elsif ($1 eq 'ANTIETCD')
+            {
+                $test_name .= '_antietcd';
+            }
             else
             {
                 $test_name .= '_'.lc($1).'_'.$2;

CMakeLists.txt

@@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8.12)
 
 project(vitastor)
 
-set(VERSION "1.7.0")
+set(VITASTOR_VERSION "1.9.2")
 
 add_subdirectory(src)

README-ru.md

@@ -1,4 +1,4 @@
-## Vitastor
+# Vitastor
 
 [Read English version](README.md)
 
@@ -19,10 +19,10 @@ Vitastor нацелен в первую очередь на SSD и SSD+HDD кл
 TCP и RDMA и на хорошем железе может достигать задержки 4 КБ чтения и записи на уровне ~0.1 мс,
 что примерно в 10 раз быстрее, чем Ceph и другие популярные программные СХД.
 
-Vitastor поддерживает QEMU-драйвер, протоколы NBD и NFS, драйверы OpenStack, Proxmox, Kubernetes.
+Vitastor поддерживает QEMU-драйвер, протоколы NBD и NFS, драйверы OpenStack, OpenNebula, Proxmox, Kubernetes.
 Другие драйверы могут также быть легко реализованы.
 
-Подробности смотрите в документации по ссылкам ниже.
+Подробности смотрите в документации по ссылкам. Можете начать отсюда: [Быстрый старт](docs/intro/quickstart.ru.md).
 
 ## Презентации и записи докладов
 
@@ -42,6 +42,7 @@ Vitastor поддерживает QEMU-драйвер, протоколы NBD и
 - Установка
   - [Пакеты](docs/installation/packages.ru.md)
   - [Proxmox](docs/installation/proxmox.ru.md)
+  - [OpenNebula](docs/installation/opennebula.ru.md)
   - [OpenStack](docs/installation/openstack.ru.md)
   - [Kubernetes CSI](docs/installation/kubernetes.ru.md)
   - [Сборка из исходных кодов](docs/installation/source.ru.md)
@@ -50,7 +51,7 @@ Vitastor поддерживает QEMU-драйвер, протоколы NBD и
   - Параметры
     - [Общие](docs/config/common.ru.md)
     - [Сетевые](docs/config/network.ru.md)
-    - [Клиентский код](docs/config/client.en.md)
+    - [Клиентский код](docs/config/client.ru.md)
     - [Глобальные дисковые параметры](docs/config/layout-cluster.ru.md)
     - [Дисковые параметры OSD](docs/config/layout-osd.ru.md)
     - [Прочие параметры OSD](docs/config/osd.ru.md)

README.md

@@ -19,10 +19,10 @@ supports TCP and RDMA and may achieve 4 KB read and write latency as low as ~0.1
 with proper hardware which is ~10 times faster than other popular SDS's like Ceph
 or internal systems of public clouds.
 
-Vitastor supports QEMU, NBD, NFS protocols, OpenStack, Proxmox, Kubernetes drivers.
+Vitastor supports QEMU, NBD, NFS protocols, OpenStack, OpenNebula, Proxmox, Kubernetes drivers.
 More drivers may be created easily.
 
-Read more details below in the documentation.
+Read more details in the documentation. You can start from here: [Quick Start](docs/intro/quickstart.en.md).
 
 ## Talks and presentations
 
@@ -42,6 +42,7 @@ Read more details below in the documentation.
 - Installation
   - [Packages](docs/installation/packages.en.md)
   - [Proxmox](docs/installation/proxmox.en.md)
+  - [OpenNebula](docs/installation/opennebula.en.md)
   - [OpenStack](docs/installation/openstack.en.md)
   - [Kubernetes CSI](docs/installation/kubernetes.en.md)
   - [Building from Source](docs/installation/source.en.md)

csi/Makefile

@@ -1,9 +1,9 @@
-VERSION ?= v1.7.0
+VITASTOR_VERSION ?= v1.9.2
 
 all: build push
 
 build:
-	@docker build --rm -t vitalif/vitastor-csi:$(VERSION) .
+	@docker build --rm -t vitalif/vitastor-csi:$(VITASTOR_VERSION) .
 
 push:
-	@docker push vitalif/vitastor-csi:$(VERSION)
+	@docker push vitalif/vitastor-csi:$(VITASTOR_VERSION)

csi/deploy/004-csi-nodeplugin.yaml

@@ -49,7 +49,7 @@ spec:
             capabilities:
               add: ["SYS_ADMIN"]
             allowPrivilegeEscalation: true
-          image: vitalif/vitastor-csi:v1.7.0
+          image: vitalif/vitastor-csi:v1.9.2
           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:v1.7.0
+          image: vitalif/vitastor-csi:v1.9.2
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/go.mod

@@ -3,10 +3,10 @@ module vitastor.io/csi
 go 1.15
 
 require (
-	github.com/container-storage-interface/spec v1.4.0
+	github.com/container-storage-interface/spec v1.8.0
 	github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b
 	github.com/kubernetes-csi/csi-lib-utils v0.9.1
-	golang.org/x/net v0.0.0-20201202161906-c7110b5ffcbb
+	golang.org/x/net v0.7.0
 	golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1 // indirect
 	google.golang.org/grpc v1.33.1
 	google.golang.org/protobuf v1.24.0

csi/go.sum

@@ -41,8 +41,8 @@ github.com/chzyer/logex v1.1.10/go.mod h1:+Ywpsq7O8HXn0nuIou7OrIPyXbp3wmkHB+jjWR
 github.com/chzyer/readline v0.0.0-20180603132655-2972be24d48e/go.mod h1:nSuG5e5PlCu98SY8svDHJxuZscDgtXS6KTTbou5AhLI=
 github.com/chzyer/test v0.0.0-20180213035817-a1ea475d72b1/go.mod h1:Q3SI9o4m/ZMnBNeIyt5eFwwo7qiLfzFZmjNmxjkiQlU=
 github.com/container-storage-interface/spec v1.2.0/go.mod h1:6URME8mwIBbpVyZV93Ce5St17xBiQJQY67NDsuohiy4=
-github.com/container-storage-interface/spec v1.4.0 h1:ozAshSKxpJnYUfmkpZCTYyF/4MYeYlhdXbAvPvfGmkg=
-github.com/container-storage-interface/spec v1.4.0/go.mod h1:6URME8mwIBbpVyZV93Ce5St17xBiQJQY67NDsuohiy4=
+github.com/container-storage-interface/spec v1.8.0 h1:D0vhF3PLIZwlwZEf2eNbpujGCNwspwTYf2idJRJx4xI=
+github.com/container-storage-interface/spec v1.8.0/go.mod h1:ROLik+GhPslwwWRNFF1KasPzroNARibH2rfz1rkg4H0=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
@@ -182,6 +182,7 @@ github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UV
 github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
 github.com/stretchr/testify v1.5.1 h1:nOGnQDM7FYENwehXlg/kFVnos3rEvtKTjRvOWSzb6H4=
 github.com/stretchr/testify v1.5.1/go.mod h1:5W2xD1RspED5o8YsWQXVCued0rvSQ+mT+I5cxcmMvtA=
+github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
 go.opencensus.io v0.21.0/go.mod h1:mSImk1erAIZhrmZN+AvHh14ztQfjbGwt4TtuofqLduU=
 go.opencensus.io v0.22.0/go.mod h1:+kGneAE2xo2IficOXnaByMWTGM9T73dGwxeWcUqIpI8=
 go.opencensus.io v0.22.2/go.mod h1:yxeiOL68Rb0Xd1ddK5vPZ/oVn4vY4Ynel7k9FzqtOIw=
@@ -195,6 +196,7 @@ golang.org/x/crypto v0.0.0-20190605123033-f99c8df09eb5/go.mod h1:yigFU9vqHzYiE8U
 golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/crypto v0.0.0-20191206172530-e9b2fee46413/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
 golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
+golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20190306152737-a1d7652674e8/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20190510132918-efd6b22b2522/go.mod h1:ZjyILWgesfNpC6sMxTJOJm9Kp84zZh5NQWvqDGG3Qr8=
@@ -213,6 +215,7 @@ golang.org/x/mobile v0.0.0-20190719004257-d2bd2a29d028/go.mod h1:E/iHnbuqvinMTCc
 golang.org/x/mod v0.0.0-20190513183733-4bf6d317e70e/go.mod h1:mXi4GBBbnImb6dmsKGUJ2LatrhH/nqhxcFungHvyanc=
 golang.org/x/mod v0.1.0/go.mod h1:0QHyrYULN0/3qlju5TqG8bIK38QM8yzMo5ekMj3DlcY=
 golang.org/x/mod v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg=
+golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
 golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20180906233101-161cd47e91fd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
@@ -228,8 +231,10 @@ golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLL
 golang.org/x/net v0.0.0-20191209160850-c0dbc17a3553/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20200324143707-d3edc9973b7e/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
 golang.org/x/net v0.0.0-20200707034311-ab3426394381/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
-golang.org/x/net v0.0.0-20201202161906-c7110b5ffcbb h1:eBmm0M9fYhWpKZLjQUUKka/LtIxf46G4fxeEz5KJr9U=
-golang.org/x/net v0.0.0-20201202161906-c7110b5ffcbb/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
+golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
+golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
+golang.org/x/net v0.7.0 h1:rJrUqqhjsgNp7KqAIc25s9pZnjU7TUcSY7HcVZjdn1g=
+golang.org/x/net v0.7.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20190226205417-e64efc72b421/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
 golang.org/x/oauth2 v0.0.0-20190604053449-0f29369cfe45/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
@@ -240,6 +245,7 @@ golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJ
 golang.org/x/sync v0.0.0-20190227155943-e225da77a7e6/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20180909124046-d0be0721c37e/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20181116152217-5ac8a444bdc5/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
@@ -259,13 +265,22 @@ golang.org/x/sys v0.0.0-20200302150141-5c8b2ff67527/go.mod h1:h1NjWce9XRLGQEsW7w
 golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200615200032-f1bc736245b1/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200622214017-ed371f2e16b4/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f h1:+Nyd8tzPX9R7BWHguqsrbFdRx3WQ/1ib8I44HXV5yTA=
-golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.5.0 h1:MUK/U/4lj1t1oPg0HfuXDN/Z1wv31ZJ/YcPiGccS4DU=
+golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
+golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
+golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.1-0.20180807135948-17ff2d5776d2/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
-golang.org/x/text v0.3.3 h1:cokOdA+Jmi5PJGXLlLllQSgYigAEfHXJAERHVMaCc2k=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
+golang.org/x/text v0.7.0 h1:4BRB4x83lYWy72KwLD/qYDuTu7q9PjSagHvijDw7cLo=
+golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
 golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20191024005414-555d28b269f0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
@@ -286,8 +301,10 @@ golang.org/x/tools v0.0.0-20190628153133-6cdbf07be9d0/go.mod h1:/rFqwRUd4F7ZHNgw
 golang.org/x/tools v0.0.0-20190816200558-6889da9d5479/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.0.0-20190911174233-4f2ddba30aff/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.0.0-20191012152004-8de300cfc20a/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.0.0-20191125144606-a911d9008d1f/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.0.0-20191227053925-7b8e75db28f4/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
+golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=

csi/src/config.go

@@ -5,7 +5,7 @@ package vitastor
 
 const (
     vitastorCSIDriverName    = "csi.vitastor.io"
-    vitastorCSIDriverVersion = "1.7.0"
+    vitastorCSIDriverVersion = "1.9.2"
 )
 
 // Config struct fills the parameters of request or user input

csi/src/controllerserver.go

@@ -8,11 +8,9 @@ import (
     "encoding/json"
     "fmt"
     "strings"
-    "bytes"
     "strconv"
     "time"
     "os"
-    "os/exec"
     "io/ioutil"
 
     "github.com/kubernetes-csi/csi-lib-utils/protosanitizer"
@@ -114,22 +112,6 @@ func GetConnectionParams(params map[string]string) (map[string]string, error)
     return ctxVars, nil
 }
 
-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
-    err := c.Run()
-    if (err != nil)
-    {
-        stdoutStr, stderrStr := string(stdout.Bytes()), string(stderr.Bytes())
-        klog.Errorf(program+" "+strings.Join(args, " ")+" failed: %s, status %s\n", stdoutStr+stderrStr, err)
-        return nil, nil, status.Error(codes.Internal, stdoutStr+stderrStr+" (status "+err.Error()+")")
-    }
-    return stdout.Bytes(), stderr.Bytes(), nil
-}
-
 func invokeCLI(ctxVars map[string]string, args []string) ([]byte, error)
 {
     if (ctxVars["configPath"] != "")
@@ -158,6 +140,12 @@ func (cs *ControllerServer) CreateVolume(ctx context.Context, req *csi.CreateVol
         return nil, status.Error(codes.InvalidArgument, "volume capabilities is a required field")
     }
 
+    err := cs.checkCaps(volumeCapabilities)
+    if (err != nil)
+    {
+        return nil, err
+    }
+
     etcdVolumePrefix := req.Parameters["etcdVolumePrefix"]
     poolId, _ := strconv.ParseUint(req.Parameters["poolId"], 10, 64)
     if (poolId == 0)
@@ -301,13 +289,44 @@ func (cs *ControllerServer) ValidateVolumeCapabilities(ctx context.Context, req
         return nil, status.Error(codes.InvalidArgument, "volumeCapabilities is nil")
     }
 
+    err := cs.checkCaps(volumeCapabilities)
+    if (err != nil)
+    {
+        return nil, err
+    }
+
+    return &csi.ValidateVolumeCapabilitiesResponse{
+        Confirmed: &csi.ValidateVolumeCapabilitiesResponse_Confirmed{
+            VolumeCapabilities: req.VolumeCapabilities,
+        },
+    }, nil
+}
+
+func (cs *ControllerServer) checkCaps(volumeCapabilities []*csi.VolumeCapability) error
+{
     var volumeCapabilityAccessModes []*csi.VolumeCapability_AccessMode
     for _, mode := range []csi.VolumeCapability_AccessMode_Mode{
         csi.VolumeCapability_AccessMode_SINGLE_NODE_WRITER,
-        csi.VolumeCapability_AccessMode_MULTI_NODE_MULTI_WRITER,
+        csi.VolumeCapability_AccessMode_SINGLE_NODE_READER_ONLY,
+        csi.VolumeCapability_AccessMode_MULTI_NODE_READER_ONLY,
+        csi.VolumeCapability_AccessMode_SINGLE_NODE_SINGLE_WRITER,
+        csi.VolumeCapability_AccessMode_SINGLE_NODE_MULTI_WRITER,
     } {
         volumeCapabilityAccessModes = append(volumeCapabilityAccessModes, &csi.VolumeCapability_AccessMode{Mode: mode})
     }
+    for _, capability := range volumeCapabilities
+    {
+        if (capability.GetBlock() != nil)
+        {
+            for _, mode := range []csi.VolumeCapability_AccessMode_Mode{
+                csi.VolumeCapability_AccessMode_MULTI_NODE_SINGLE_WRITER,
+                csi.VolumeCapability_AccessMode_MULTI_NODE_MULTI_WRITER,
+            } {
+                volumeCapabilityAccessModes = append(volumeCapabilityAccessModes, &csi.VolumeCapability_AccessMode{Mode: mode})
+            }
+            break
+        }
+    }
 
     capabilitySupport := false
     for _, capability := range volumeCapabilities
@@ -323,14 +342,10 @@ func (cs *ControllerServer) ValidateVolumeCapabilities(ctx context.Context, req
 
     if (!capabilitySupport)
     {
-        return nil, status.Errorf(codes.NotFound, "%v not supported", req.GetVolumeCapabilities())
+        return status.Errorf(codes.NotFound, "%v not supported", volumeCapabilities)
     }
 
-    return &csi.ValidateVolumeCapabilitiesResponse{
-        Confirmed: &csi.ValidateVolumeCapabilitiesResponse_Confirmed{
-            VolumeCapabilities: req.VolumeCapabilities,
-        },
-    }, nil
+    return nil
 }
 
 // ListVolumes returns a list of volumes

csi/src/nodeserver.go

@@ -227,7 +227,32 @@ func (ns *NodeServer) NodeStageVolume(ctx context.Context, req *csi.NodeStageVol
     isBlock := req.GetVolumeCapability().GetBlock() != nil
 
     // Check that it's not already mounted
-    _, err = mount.IsNotMountPoint(ns.mounter, targetPath)
+    notmnt, err := mount.IsNotMountPoint(ns.mounter, targetPath)
+    if (err == nil)
+    {
+        if (!notmnt)
+        {
+            klog.Errorf("target path %s is already mounted", targetPath)
+            return nil, fmt.Errorf("target path %s is already mounted", targetPath)
+        }
+        var finfo os.FileInfo
+        finfo, err = os.Stat(targetPath)
+        if (err != nil)
+        {
+            klog.Errorf("failed to stat %s: %v", targetPath, err)
+            return nil, err
+        }
+        if (finfo.IsDir() != (!isBlock))
+        {
+            err = os.Remove(targetPath)
+            if (err != nil)
+            {
+                klog.Errorf("failed to remove %s (to recreate it with correct type): %v", targetPath, err)
+                return nil, err
+            }
+            err = os.ErrNotExist
+        }
+    }
     if (err != nil)
     {
         if (os.IsNotExist(err))
@@ -280,6 +305,7 @@ func (ns *NodeServer) NodeStageVolume(ctx context.Context, req *csi.NodeStageVol
     diskMounter := &mount.SafeFormatAndMount{Interface: ns.mounter, Exec: utilexec.New()}
     if (isBlock)
     {
+        klog.Infof("bind-mounting %s to %s", devicePath, targetPath)
         err = diskMounter.Mount(devicePath, targetPath, "", []string{"bind"})
     }
     else
@@ -309,39 +335,40 @@ func (ns *NodeServer) NodeStageVolume(ctx context.Context, req *csi.NodeStageVol
         readOnly := Contains(opt, "ro")
         if (existingFormat == "" && !readOnly)
         {
-            var cmdOut []byte
             switch fsType
             {
                 case "ext4":
                     args := []string{"-m0", "-Enodiscard,lazy_itable_init=1,lazy_journal_init=1", devicePath}
-                    cmdOut, err = diskMounter.Exec.Command("mkfs.ext4", args...).CombinedOutput()
+                    _, err = systemCombined("mkfs.ext4", args...)
                 case "xfs":
-                    cmdOut, err = diskMounter.Exec.Command("mkfs.xfs", "-K", devicePath).CombinedOutput()
+                    _, err = systemCombined("mkfs.xfs", "-K", devicePath)
             }
             if (err != nil)
             {
-                klog.Errorf("failed to run mkfs error: %v, output: %v", err, string(cmdOut))
                 goto unmap
             }
         }
 
+        klog.Infof("formatting and mounting %s to %s with FS %s, options: %v", devicePath, targetPath, fsType, opt)
         err = diskMounter.FormatAndMount(devicePath, targetPath, fsType, opt)
+        if (err == nil)
+        {
+            klog.Infof("successfully mounted %s to %s", devicePath, targetPath)
+        }
 
         // Try to run online resize on mount.
         // FIXME: Implement online resize. It requires online resize support in vitastor-nbd.
         if (err == nil && existingFormat != "" && !readOnly)
         {
-            var cmdOut []byte
             switch (fsType)
             {
                 case "ext4":
-                    cmdOut, err = diskMounter.Exec.Command("resize2fs", devicePath).CombinedOutput()
+                    _, err = systemCombined("resize2fs", devicePath)
                 case "xfs":
-                    cmdOut, err = diskMounter.Exec.Command("xfs_growfs", devicePath).CombinedOutput()
+                    _, err = systemCombined("xfs_growfs", devicePath)
             }
             if (err != nil)
             {
-                klog.Errorf("failed to run resizefs error: %v, output: %v", err, string(cmdOut))
                 goto unmap
             }
         }
@@ -385,7 +412,7 @@ func (ns *NodeServer) NodeUnstageVolume(ctx context.Context, req *csi.NodeUnstag
     defer ns.unlockVolume(ctxVars["configPath"]+":"+volName)
 
     targetPath := req.GetStagingTargetPath()
-    devicePath, refCount, err := mount.GetDeviceNameFromMount(ns.mounter, targetPath)
+    devicePath, _, err := mount.GetDeviceNameFromMount(ns.mounter, targetPath)
     if (err != nil)
     {
         if (os.IsNotExist(err))
@@ -402,6 +429,16 @@ func (ns *NodeServer) NodeUnstageVolume(ctx context.Context, req *csi.NodeUnstag
         return &csi.NodeUnstageVolumeResponse{}, nil
     }
 
+    refList, err := ns.mounter.GetMountRefs(targetPath)
+    if (err != nil)
+    {
+        return nil, err
+    }
+    if (len(refList) > 0)
+    {
+        klog.Warningf("%s is still referenced: %v", targetPath, refList)
+    }
+
     // unmount
     err = mount.CleanupMountPoint(targetPath, ns.mounter, false)
     if (err != nil)
@@ -410,7 +447,7 @@ func (ns *NodeServer) NodeUnstageVolume(ctx context.Context, req *csi.NodeUnstag
     }
 
     // unmap device
-    if (refCount == 1)
+    if (len(refList) == 0)
     {
         if (!ns.useVduse)
         {
@@ -451,15 +488,20 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
     isBlock := req.GetVolumeCapability().GetBlock() != nil
 
     // Check that stagingTargetPath is mounted
-    _, err = mount.IsNotMountPoint(ns.mounter, stagingTargetPath)
+    notmnt, err := mount.IsNotMountPoint(ns.mounter, stagingTargetPath)
     if (err != nil)
     {
-        klog.Errorf("staging path %v is not mounted: %v", stagingTargetPath, err)
-        return nil, fmt.Errorf("staging path %v is not mounted: %v", stagingTargetPath, err)
+        klog.Errorf("staging path %v is not mounted: %w", stagingTargetPath, err)
+        return nil, fmt.Errorf("staging path %v is not mounted: %w", stagingTargetPath, err)
+    }
+    else if (notmnt)
+    {
+        klog.Errorf("staging path %v is not mounted", stagingTargetPath)
+        return nil, fmt.Errorf("staging path %v is not mounted", stagingTargetPath)
     }
 
     // Check that targetPath is not already mounted
-    _, err = mount.IsNotMountPoint(ns.mounter, targetPath)
+    notmnt, err = mount.IsNotMountPoint(ns.mounter, targetPath)
     if (err != nil)
     {
         if (os.IsNotExist(err))
@@ -494,6 +536,11 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
             return nil, err
         }
     }
+    else if (!notmnt)
+    {
+        klog.Errorf("target path %s is already mounted", targetPath)
+        return nil, fmt.Errorf("target path %s is already mounted", targetPath)
+    }
 
     execArgs := []string{"--bind", stagingTargetPath, targetPath}
     if (req.GetReadonly())

csi/src/utils.go

@@ -4,6 +4,7 @@
 package vitastor
 
 import (
+    "bytes"
     "errors"
     "encoding/json"
     "fmt"
@@ -15,6 +16,8 @@ import (
     "syscall"
 
     "k8s.io/klog"
+    "google.golang.org/grpc/codes"
+    "google.golang.org/grpc/status"
 )
 
 func Contains(list []string, s string) bool
@@ -73,6 +76,10 @@ func checkVduseSupport() bool
             " For VDUSE you need at least Linux 5.15 and the following kernel modules: vdpa, virtio-vdpa, vduse.",
         )
     }
+    else
+    {
+        klog.Infof("VDUSE support enabled successfully")
+    }
     return vduse
 }
 
@@ -97,6 +104,7 @@ func mapNbd(volName string, ctxVars map[string]string, readonly bool) (string, e
     {
         return "", fmt.Errorf("vitastor-nbd did not return the name of NBD device. output: %s", stderr)
     }
+    klog.Infof("Attached volume %s via NBD as %s", volName, dev)
     return dev, err
 }
 
@@ -217,6 +225,7 @@ func mapVduse(stateDir string, volName string, ctxVars map[string]string, readon
                     err = os.WriteFile(stateFile, stateJSON, 0600)
                     if (err == nil)
                     {
+                        klog.Infof("Attached volume %s via VDUSE as %s (VDPA ID %s)", volName, blockdev, vdpaId)
                         return blockdev, vdpaId, nil
                     }
                 }
@@ -299,3 +308,35 @@ func unmapVduseById(stateDir, vdpaId string)
         os.Remove(pidFile)
     }
 }
+
+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
+    err := c.Run()
+    if (err != nil)
+    {
+        stdoutStr, stderrStr := string(stdout.Bytes()), string(stderr.Bytes())
+        klog.Errorf(program+" "+strings.Join(args, " ")+" failed: %s\nOutput:\n%s", err, stdoutStr+stderrStr)
+        return nil, nil, status.Error(codes.Internal, stdoutStr+stderrStr+" (status "+err.Error()+")")
+    }
+    return stdout.Bytes(), stderr.Bytes(), nil
+}
+
+func systemCombined(program string, args ...string) ([]byte, error)
+{
+    klog.Infof("Running "+program+" "+strings.Join(args, " "))
+    c := exec.Command(program, args...)
+    var out bytes.Buffer
+    c.Stdout, c.Stderr = &out, &out
+    err := c.Run()
+    if (err != nil)
+    {
+        outStr := string(out.Bytes())
+        klog.Errorf(program+" "+strings.Join(args, " ")+" failed: %s, status %s\n", outStr, err)
+        return nil, status.Error(codes.Internal, outStr+" (status "+err.Error()+")")
+    }
+    return out.Bytes(), nil
+}

debian/changelog

@@ -1,4 +1,4 @@
-vitastor (1.7.0-1) unstable; urgency=medium
+vitastor (1.9.2-1) unstable; urgency=medium
 
   * Bugfixes
 

debian/control

@@ -53,3 +53,9 @@ Architecture: amd64
 Depends: ${shlibs:Depends}, ${misc:Depends}, vitastor-client (= ${binary:Version})
 Description: Vitastor Proxmox Virtual Environment storage plugin
  Vitastor storage plugin for Proxmox Virtual Environment.
+
+Package: vitastor-opennebula
+Architecture: amd64
+Depends: ${shlibs:Depends}, ${misc:Depends}, vitastor-client, patch, python3, jq
+Description: Vitastor OpenNebula storage plugin
+ Vitastor storage plugin for OpenNebula.

debian/vitastor-opennebula.install

@@ -0,0 +1,3 @@
+opennebula/remotes var/lib/one/
+opennebula/sudoers.d etc/
+opennebula/install.sh var/lib/one/remotes/datastore/vitastor/

debian/vitastor-opennebula.postinst

@@ -0,0 +1,7 @@
+#!/bin/sh
+
+set -e
+
+if [ "$1" = "configure" ]; then
+	/var/lib/one/remotes/datastore/vitastor/install.sh
+fi

debian/vitastor-opennebula.triggers

@@ -0,0 +1,4 @@
+interest /var/lib/one/remotes/datastore/downloader.sh
+interest /etc/one/oned.conf
+interest /etc/one/vmm_exec/vmm_execrc
+interest /etc/apparmor.d/local/abstractions/libvirt-qemu

docs/config/layout-cluster.en.md

@@ -106,8 +106,8 @@ SSD cache or "media-cache" - for example, a lot of Seagate EXOS drives have
 it (they have internal SSD cache even though it's not stated in datasheets).
 
 Setting this parameter to "all" or "small" in OSD parameters requires enabling
-[disable_journal_fsync](layout-osd.en.yml#disable_journal_fsync) and
-[disable_meta_fsync](layout-osd.en.yml#disable_meta_fsync), setting it to
-"all" also requires enabling [disable_data_fsync](layout-osd.en.yml#disable_data_fsync).
+[disable_journal_fsync](layout-osd.en.md#disable_journal_fsync) and
+[disable_meta_fsync](layout-osd.en.md#disable_meta_fsync), setting it to
+"all" also requires enabling [disable_data_fsync](layout-osd.en.md#disable_data_fsync).
 vitastor-disk tried to do that by default, first checking/disabling drive cache.
 If it can't disable drive cache, OSD get initialized with "none".

docs/config/layout-cluster.ru.md

@@ -112,6 +112,6 @@ HDD-дисках с внутренним SSD или "медиа" кэшем - н
 указано в спецификациях).
 
 Указание "all" или "small" в настройках / командной строке OSD требует
-включения [disable_journal_fsync](layout-osd.ru.yml#disable_journal_fsync) и
-[disable_meta_fsync](layout-osd.ru.yml#disable_meta_fsync), значение "all"
-также требует включения [disable_data_fsync](layout-osd.ru.yml#disable_data_fsync).
+включения [disable_journal_fsync](layout-osd.ru.md#disable_journal_fsync) и
+[disable_meta_fsync](layout-osd.ru.md#disable_meta_fsync), значение "all"
+также требует включения [disable_data_fsync](layout-osd.ru.md#disable_data_fsync).

docs/config/pool.en.md

@@ -55,7 +55,7 @@ Examples:
 OSD placement tree is set in a separate etcd key `/vitastor/config/node_placement`
 in the following JSON format:
 
-`
+```
 {
   "<node name or OSD number>": {
     "level": "<level>",
@@ -63,7 +63,7 @@ in the following JSON format:
   },
   ...
 }
-`
+```
 
 Here, if a node name is a number then it is assumed to refer to an OSD.
 Level of the OSD is always "osd" and cannot be overriden. You may only

docs/config/pool.ru.md

@@ -54,7 +54,7 @@
 Дерево размещения OSD задаётся в отдельном ключе etcd `/vitastor/config/node_placement`
 в следующем JSON-формате:
 
-`
+```
 {
   "<имя узла или номер OSD>": {
     "level": "<уровень>",
@@ -62,7 +62,7 @@
   },
   ...
 }
-`
+```
 
 Здесь, если название узла - число, считается, что это OSD. Уровень OSD
 всегда равен "osd" и не может быть переопределён. Для OSD вы можете только

docs/config/src/layout-cluster.yml

@@ -97,9 +97,9 @@
     it (they have internal SSD cache even though it's not stated in datasheets).
 
     Setting this parameter to "all" or "small" in OSD parameters requires enabling
-    [disable_journal_fsync](layout-osd.en.yml#disable_journal_fsync) and
-    [disable_meta_fsync](layout-osd.en.yml#disable_meta_fsync), setting it to
-    "all" also requires enabling [disable_data_fsync](layout-osd.en.yml#disable_data_fsync).
+    [disable_journal_fsync](layout-osd.en.md#disable_journal_fsync) and
+    [disable_meta_fsync](layout-osd.en.md#disable_meta_fsync), setting it to
+    "all" also requires enabling [disable_data_fsync](layout-osd.en.md#disable_data_fsync).
     vitastor-disk tried to do that by default, first checking/disabling drive cache.
     If it can't disable drive cache, OSD get initialized with "none".
   info_ru: |
@@ -156,6 +156,6 @@
     указано в спецификациях).
 
     Указание "all" или "small" в настройках / командной строке OSD требует
-    включения [disable_journal_fsync](layout-osd.ru.yml#disable_journal_fsync) и
-    [disable_meta_fsync](layout-osd.ru.yml#disable_meta_fsync), значение "all"
-    также требует включения [disable_data_fsync](layout-osd.ru.yml#disable_data_fsync).
+    включения [disable_journal_fsync](layout-osd.ru.md#disable_journal_fsync) и
+    [disable_meta_fsync](layout-osd.ru.md#disable_meta_fsync), значение "all"
+    также требует включения [disable_data_fsync](layout-osd.ru.md#disable_data_fsync).

docs/installation/opennebula.en.md

@@ -0,0 +1,186 @@
+[Documentation](../../README.md#documentation) → Installation → OpenNebula
+
+-----
+
+[Читать на русском](opennebula.ru.md)
+
+# OpenNebula
+
+## Automatic Installation
+
+OpenNebula plugin is packaged as `vitastor-opennebula` Debian and RPM package since Vitastor 1.9.0. So:
+
+- Run `apt-get install vitastor-opennebula` or `yum install vitastor-opennebula` after installing OpenNebula on all nodes
+- Check that it prints "OK, Vitastor OpenNebula patches successfully applied" or "OK, Vitastor OpenNebula patches are already applied"
+- If it does not, refer to [Manual Installation](#manual-installation) and apply configuration file changes manually
+- Make sure that Vitastor patched versions of QEMU and libvirt are installed
+  (`dpkg -l qemu-system-x86`, `dpkg -l | grep libvirt`, `rpm -qa | grep qemu`, `rpm -qa | grep qemu`, `rpm -qa | grep libvirt-libs` should show "vitastor" in version names)
+- [Block VM access to Vitastor cluster](#block-vm-access-to-vitastor-cluster)
+
+## Manual Installation
+
+Install OpenNebula. Then, on each node:
+
+- Copy [opennebula/remotes](../../opennebula/remotes) into `/var/lib/one` recursively: `cp -r opennebula/remotes /var/lib/one/`
+- Copy [opennebula/sudoers.d](../../opennebula/sudoers.d) to `/etc`: `cp -r opennebula/sudoers.d /etc/`
+- Apply [downloader-vitastor.sh.diff](../../opennebula/remotes/datastore/vitastor/downloader-vitastor.sh.diff) to `/var/lib/one/remotes/datastore/downloader.sh`:
+  `patch /var/lib/one/remotes/datastore/downloader.sh < opennebula/remotes/datastore/vitastor/downloader-vitastor.sh.diff` - or read the patch and apply the same change manually
+- Add `kvm-vitastor` to `LIVE_DISK_SNAPSHOTS` in `/etc/one/vmm_exec/vmm_execrc`
+- If on Debian or Ubuntu (and AppArmor is used), add Vitastor config file path(s) to `/etc/apparmor.d/local/abstractions/libvirt-qemu`: for example,
+  `echo '  "/etc/vitastor/vitastor.conf" r,' >> /etc/apparmor.d/local/abstractions/libvirt-qemu`
+- Apply changes to `/etc/one/oned.conf`
+
+### oned.conf changes
+
+1. Add deploy script override in kvm VM_MAD: add `-l deploy.vitastor` to ARGUMENTS.
+
+```diff
+ VM_MAD = [
+     NAME           = "kvm",
+     SUNSTONE_NAME  = "KVM",
+     EXECUTABLE     = "one_vmm_exec",
+-    ARGUMENTS      = "-t 15 -r 0 kvm -p",
++    ARGUMENTS      = "-t 15 -r 0 kvm -p -l deploy=deploy.vitastor",
+     DEFAULT        = "vmm_exec/vmm_exec_kvm.conf",
+     TYPE           = "kvm",
+     KEEP_SNAPSHOTS = "yes",
+     LIVE_RESIZE    = "yes",
+     SUPPORT_SHAREABLE    = "yes",
+     IMPORTED_VMS_ACTIONS = "terminate, terminate-hard, hold, release, suspend,
+         resume, delete, reboot, reboot-hard, resched, unresched, disk-attach,
+         disk-detach, nic-attach, nic-detach, snapshot-create, snapshot-delete,
+         resize, updateconf, update"
+ ]
+```
+
+Optional: if you also want to save VM RAM checkpoints to Vitastor, use
+`-l deploy=deploy.vitastor,save=save.vitastor,restore=restore.vitastor`
+instead of just `-l deploy=deploy.vitastor`.
+
+2. Add `vitastor` to TM_MAD.ARGUMENTS and DATASTORE_MAD.ARGUMENTS:
+
+```diff
+ TM_MAD = [
+     EXECUTABLE = "one_tm",
+-    ARGUMENTS = "-t 15 -d dummy,lvm,shared,fs_lvm,fs_lvm_ssh,qcow2,ssh,ceph,dev,vcenter,iscsi_libvirt"
++    ARGUMENTS = "-t 15 -d dummy,lvm,shared,fs_lvm,fs_lvm_ssh,qcow2,ssh,ceph,vitastor,dev,vcenter,iscsi_libvirt"
+ ]
+
+ DATASTORE_MAD = [
+     EXECUTABLE = "one_datastore",
+-    ARGUMENTS  = "-t 15 -d dummy,fs,lvm,ceph,dev,iscsi_libvirt,vcenter,restic,rsync -s shared,ssh,ceph,fs_lvm,fs_lvm_ssh,qcow2,vcenter"
++    ARGUMENTS  = "-t 15 -d dummy,fs,lvm,ceph,vitastor,dev,iscsi_libvirt,vcenter,restic,rsync -s shared,ssh,ceph,vitastor,fs_lvm,fs_lvm_ssh,qcow2,vcenter"
+ ]
+```
+
+3. Add INHERIT_DATASTORE_ATTR for two Vitastor attributes:
+
+```
+INHERIT_DATASTORE_ATTR = "VITASTOR_CONF"
+INHERIT_DATASTORE_ATTR = "IMAGE_PREFIX"
+```
+
+4. Add TM_MAD_CONF and DS_MAD_CONF for Vitastor:
+
+```
+TM_MAD_CONF = [
+    NAME = "vitastor", LN_TARGET = "NONE", CLONE_TARGET = "SELF", SHARED = "YES",
+    DS_MIGRATE = "NO", DRIVER = "raw", ALLOW_ORPHANS="format",
+    TM_MAD_SYSTEM = "ssh,shared", LN_TARGET_SSH = "SYSTEM", CLONE_TARGET_SSH = "SYSTEM",
+    DISK_TYPE_SSH = "FILE", LN_TARGET_SHARED = "NONE",
+    CLONE_TARGET_SHARED = "SELF", DISK_TYPE_SHARED = "FILE"
+]
+
+DS_MAD_CONF = [
+    NAME = "vitastor",
+    REQUIRED_ATTRS = "DISK_TYPE,BRIDGE_LIST",
+    PERSISTENT_ONLY = "NO",
+    MARKETPLACE_ACTIONS = "export"
+]
+```
+
+## Create Datastores
+
+Example Image and System Datastore definitions:
+[opennebula/vitastor-imageds.conf](../../opennebula/vitastor-imageds.conf) and
+[opennebula/vitastor-systemds.conf](../../opennebula/vitastor-systemds.conf).
+
+Change parameters to your will:
+
+- POOL_NAME is Vitastor pool name to store images.
+- IMAGE_PREFIX is a string prepended to all Vitastor image names.
+- BRIDGE_LIST is a list of hosts with access to Vitastor cluster, mostly used for image (not system) datastore operations.
+- VITASTOR_CONF is the path to cluster configuration. Note that it should be also added to `/etc/apparmor.d/local/abstractions/libvirt-qemu` if you use AppArmor.
+- STAGING_DIR is a temporary directory used when importing external images. Should have free space sufficient for downloading external images.
+
+Then create datastores using `onedatastore create vitastor-imageds.conf` and `onedatastore create vitastor-systemds.conf` (or use UI).
+
+## Block VM access to Vitastor cluster
+
+Vitastor doesn't support any authentication yet, so you MUST block VM guest access to the Vitastor cluster at the network level.
+
+If you use VLAN networking for VMs - make sure you use different VLANs for VMs and hypervisor/storage network and
+block access between them using your firewall/switch configuration.
+
+If you use something more stupid like bridged networking, you probably have to use manual firewall/iptables setup
+to only allow access to Vitastor from hypervisor IPs.
+
+Also you need to switch network to "Bridged & Security Groups" and enable IP spoofing filters in OpenNebula.
+Problem is that OpenNebula's IP spoofing filter doesn't affect local interfaces of the hypervisor i.e. when
+it's enabled a VM can't talk to other VMs or to the outer world using a spoofed IP, but it CAN talk to the
+hypervisor if it takes an IP from its subnet. To fix that you also need some more iptables.
+
+So the complete "stupid" bridged network filter setup could look like the following
+(here `10.0.3.0/24` is the VM subnet and `10.0.2.0/24` is the hypervisor subnet):
+
+```
+# Allow incoming traffic from physical device
+iptables -A INPUT -m physdev --physdev-in eth0 -j ACCEPT
+# Do not allow incoming traffic from VMs, but not from VM subnet
+iptables -A INPUT ! -s 10.0.3.0/24 -i onebr0 -j DROP
+# Drop traffic from VMs to hypervisor/storage subnet
+iptables -I FORWARD 1 -s 10.0.3.0/24 -d 10.0.2.0/24 -j DROP
+```
+
+## Testing
+
+The OpenNebula plugin includes quite a bit of bash scripts, so here's their description to get an idea about what they actually do.
+
+| Script                  | Action                                    | How to Test                                                                          |
+| ----------------------- | ----------------------------------------- | ------------------------------------------------------------------------------------ |
+| vmm/kvm/deploy.vitastor | Start a VM                                | Create and start a VM with Vitastor disk(s): persistent / non-persistent / volatile. |
+| vmm/kvm/save.vitastor   | Save VM memory checkpoint                 | Stop a VM using "Stop" command.                                                      |
+| vmm/kvm/restore.vitastor| Restore VM memory checkpoint              | Start a VM back after stopping it.                                                   |
+| datastore/clone         | Copy an image as persistent               | Create a VM template and instantiate it as persistent.                               |
+| datastore/cp            | Import an external image                  | Import a VM template with images from Marketplace.                                   |
+| datastore/export        | Export an image as URL                    | Probably: export a VM template with images to Marketplace.                           |
+| datastore/mkfs          | Create an image with FS                   | Storage → Images → Create → Type: Datablock, Location: Empty disk image, Filesystem: Not empty. |
+| datastore/monitor       | Monitor used space in image datastore     | Check reported used/free space in image datastore list.                              |
+| datastore/rm            | Remove a persistent image                 | Storage → Images → Select an image → Delete.                                         |
+| datastore/snap_delete   | Delete a snapshot of a persistent image   | Storage → Images → Select an image → Select a snapshot → Delete; <br> To create an image with snapshot: attach a persistent image to a VM; create a snapshot; detach the image. |
+| datastore/snap_flatten  | Revert an image to snapshot and delete other snapshots | Storage → Images → Select an image → Select a snapshot → Flatten.       |
+| datastore/snap_revert   | Revert an image to snapshot               | Storage → Images → Select an image → Select a snapshot → Revert.                     |
+| datastore/stat          | Get virtual size of an image in MB        | No idea. Seems to be unused both in Vitastor and Ceph datastores.                    |
+| tm/clone                | Clone a non-persistent image to a VM disk | Attach a non-persistent image to a VM.                                               |
+| tm/context              | Generate a contextualisation VM disk      | Create a VM with enabled contextualisation (default). Common host FS-based version is used in Vitastor and Ceph datastores. |
+| tm/cpds                 | Copy a VM disk / its snapshot to an image | Select a VM → Select a disk → Optionally select a snapshot → Save as.                |
+| tm/delete               | Delete a cloned or volatile VM disk       | Detach a volatile disk or a non-persistent image from a VM.                          |
+| tm/failmigrate          | Handle live migration failure             | No action. Script is empty in Vitastor and Ceph. In other datastores, should roll back actions done by tm/premigrate. |
+| tm/ln                   | Attach a persistent image to a VM         | No action. Script is empty in Vitastor and Ceph.                                     |
+| tm/mkimage              | Create a volatile disk, maybe with FS     | Attach a volatile disk to a VM, with or without file system.                         |
+| tm/mkswap               | Create a volatile swap disk               | Attach a volatile disk to a VM, formatted as swap.                                   |
+| tm/monitor              | Monitor used space in system datastore    | Check reported used/free space in system datastore list.                             |
+| tm/mv                   | Move a migrated VM disk between hosts     | Migrate a VM between hosts. In Vitastor and Ceph datastores, doesn't do any storage action. |
+| tm/mvds                 | Detach a persistent image from a VM       | No action. The opposite of tm/ln. Script is empty in Vitastor and Ceph. In other datastores, script may copy the image from VM host back to the datastore. |
+| tm/postbackup           | Executed after backup                     | Seems that the script just removes temporary files after backup. Perform a VM backup and check that temporary files are cleaned up. |
+| tm/postbackup_live      | Executed after backup of a running VM     | Same as tm/postbackup, but for a running VM.                                         |
+| tm/postmigrate          | Executed after VM live migration          | No action. Only executed for system datastore, so the script tries to call other TMs for other disks. Except that, the script does nothing in Vitastor and Ceph datastores. |
+| tm/prebackup            | Actual backup script: backup VM disks     | Set up "rsync" backup datastore → Backup a VM to it.                                 |
+| tm/prebackup_live       | Backup VM disks of a running VM           | Same as tm/prebackup, but also does fsfreeze/thaw. So perform a live backup, restore it and check that disks are consistent. |
+| tm/premigrate           | Executed before live migration            | No action. Only executed for system datastore, so the script tries to call other TMs for other disks. Except that, the script does nothing in Vitastor and Ceph datastores. |
+| tm/resize               | Resize a VM disk                          | Select a VM → Select a non-persistent disk → Resize.                                 |
+| tm/restore              | Restore VM disks from backup              | Set up "rsync" backup datastore → Backup a VM to it → Restore it back.               |
+| tm/snap_create          | Create a VM disk snapshot                 | Select a VM → Select a disk → Create snapshot.                                       |
+| tm/snap_create_live     | Create a VM disk snapshot for a live VM   | Select a running VM → Select a disk → Create snapshot.                               |
+| tm/snap_delete          | Delete a VM disk snapshot                 | Select a VM → Select a disk → Select a snapshot → Delete.                            |
+| tm/snap_revert          | Revert a VM disk to a snapshot            | Select a VM → Select a disk → Select a snapshot → Revert.                            |

docs/installation/opennebula.ru.md

@@ -0,0 +1,189 @@
+[Документация](../../README-ru.md#документация) → Установка → OpenNebula
+
+-----
+
+[Read in English](opennebula.en.md)
+
+# OpenNebula
+
+## Автоматическая установка
+
+Плагин OpenNebula Vitastor распространяется как Debian и RPM пакет `vitastor-opennebula`, начиная с версии Vitastor 1.9.0. Так что:
+
+- Запустите `apt-get install vitastor-opennebula` или `yum install vitastor-opennebula` после установки OpenNebula на всех серверах
+- Проверьте, что он выводит "OK, Vitastor OpenNebula patches successfully applied" или "OK, Vitastor OpenNebula patches are already applied" в процессе установки
+- Если сообщение не выведено, пройдите по шагам инструкцию [Ручная установка](#ручная-установка) и примените правки файлов конфигурации вручную
+- Удостоверьтесь, что установлены версии QEMU и libvirt с изменениями Vitastor
+  (`dpkg -l qemu-system-x86`, `dpkg -l | grep libvirt`, `rpm -qa | grep qemu`, `rpm -qa | grep qemu`, `rpm -qa | grep libvirt-libs` должны показывать "vitastor" в номере версии)
+- [Заблокируйте доступ виртуальных машин в Vitastor](#блокировка-доступа-вм-в-vitastor)
+
+## Ручная установка
+
+Сначала установите саму OpenNebula. После этого, на каждом сервере:
+
+- Скопируйте директорию [opennebula/remotes](../../opennebula/remotes) в `/var/lib/one`: `cp -r opennebula/remotes /var/lib/one/`
+- Скопируйте директорию [opennebula/sudoers.d](../../opennebula/sudoers.d) в `/etc`: `cp -r opennebula/sudoers.d /etc/`
+- Примените патч [downloader-vitastor.sh.diff](../../opennebula/remotes/datastore/vitastor/downloader-vitastor.sh.diff) к `/var/lib/one/remotes/datastore/downloader.sh`:
+  `patch /var/lib/one/remotes/datastore/downloader.sh < opennebula/remotes/datastore/vitastor/downloader-vitastor.sh.diff` - либо прочитайте патч и примените изменение вручную
+- Добавьте `kvm-vitastor` в список `LIVE_DISK_SNAPSHOTS` в файле `/etc/one/vmm_exec/vmm_execrc`
+- Если вы используете Debian или Ubuntu (и AppArmor), добавьте пути к файлу(ам) конфигурации Vitastor в файл `/etc/apparmor.d/local/abstractions/libvirt-qemu`: например,
+  `echo '  "/etc/vitastor/vitastor.conf" r,' >> /etc/apparmor.d/local/abstractions/libvirt-qemu`
+- Примените изменения `/etc/one/oned.conf`
+
+### Изменения oned.conf
+
+1. Добавьте переопределение скрипта deploy в VM_MAD kvm, добавив `-l deploy.vitastor` в `ARGUMENTS`:
+
+```diff
+ VM_MAD = [
+     NAME           = "kvm",
+     SUNSTONE_NAME  = "KVM",
+     EXECUTABLE     = "one_vmm_exec",
+-    ARGUMENTS      = "-t 15 -r 0 kvm -p",
++    ARGUMENTS      = "-t 15 -r 0 kvm -p -l deploy=deploy.vitastor",
+     DEFAULT        = "vmm_exec/vmm_exec_kvm.conf",
+     TYPE           = "kvm",
+     KEEP_SNAPSHOTS = "yes",
+     LIVE_RESIZE    = "yes",
+     SUPPORT_SHAREABLE    = "yes",
+     IMPORTED_VMS_ACTIONS = "terminate, terminate-hard, hold, release, suspend,
+         resume, delete, reboot, reboot-hard, resched, unresched, disk-attach,
+         disk-detach, nic-attach, nic-detach, snapshot-create, snapshot-delete,
+         resize, updateconf, update"
+ ]
+```
+
+Опционально: если вы хотите также сохранять снимки памяти ВМ в Vitastor, добавьте
+`-l deploy=deploy.vitastor,save=save.vitastor,restore=restore.vitastor`
+вместо просто `-l deploy=deploy.vitastor`.
+
+2. Добавьте `vitastor` в значения TM_MAD.ARGUMENTS и DATASTORE_MAD.ARGUMENTS:
+
+```diff
+ TM_MAD = [
+     EXECUTABLE = "one_tm",
+-    ARGUMENTS = "-t 15 -d dummy,lvm,shared,fs_lvm,fs_lvm_ssh,qcow2,ssh,ceph,dev,vcenter,iscsi_libvirt"
++    ARGUMENTS = "-t 15 -d dummy,lvm,shared,fs_lvm,fs_lvm_ssh,qcow2,ssh,ceph,vitastor,dev,vcenter,iscsi_libvirt"
+ ]
+
+ DATASTORE_MAD = [
+     EXECUTABLE = "one_datastore",
+-    ARGUMENTS  = "-t 15 -d dummy,fs,lvm,ceph,dev,iscsi_libvirt,vcenter,restic,rsync -s shared,ssh,ceph,fs_lvm,fs_lvm_ssh,qcow2,vcenter"
++    ARGUMENTS  = "-t 15 -d dummy,fs,lvm,ceph,vitastor,dev,iscsi_libvirt,vcenter,restic,rsync -s shared,ssh,ceph,vitastor,fs_lvm,fs_lvm_ssh,qcow2,vcenter"
+ ]
+```
+
+3. Добавьте строчки с INHERIT_DATASTORE_ATTR для двух атрибутов Vitastor-хранилищ:
+
+```
+INHERIT_DATASTORE_ATTR = "VITASTOR_CONF"
+INHERIT_DATASTORE_ATTR = "IMAGE_PREFIX"
+```
+
+4. Добавьте TM_MAD_CONF и DS_MAD_CONF для Vitastor:
+
+```
+TM_MAD_CONF = [
+    NAME = "vitastor", LN_TARGET = "NONE", CLONE_TARGET = "SELF", SHARED = "YES",
+    DS_MIGRATE = "NO", DRIVER = "raw", ALLOW_ORPHANS="format",
+    TM_MAD_SYSTEM = "ssh,shared", LN_TARGET_SSH = "SYSTEM", CLONE_TARGET_SSH = "SYSTEM",
+    DISK_TYPE_SSH = "FILE", LN_TARGET_SHARED = "NONE",
+    CLONE_TARGET_SHARED = "SELF", DISK_TYPE_SHARED = "FILE"
+]
+
+DS_MAD_CONF = [
+    NAME = "vitastor",
+    REQUIRED_ATTRS = "DISK_TYPE,BRIDGE_LIST",
+    PERSISTENT_ONLY = "NO",
+    MARKETPLACE_ACTIONS = "export"
+]
+```
+
+## Создайте хранилища
+
+Примеры настроек хранилищ образов (image) и дисков ВМ (system):
+[opennebula/vitastor-imageds.conf](../../opennebula/vitastor-imageds.conf) и
+[opennebula/vitastor-systemds.conf](../../opennebula/vitastor-systemds.conf).
+
+Скопируйте настройки и поменяйте следующие параметры так, как вам необходимо:
+
+- POOL_NAME - имя пула Vitastor для сохранения образов дисков.
+- IMAGE_PREFIX - строка, добавляемая в начало имён образов дисков.
+- BRIDGE_LIST - список серверов с доступом к кластеру Vitastor, используемых для операций с хранилищем образов (image, не system).
+- VITASTOR_CONF - путь к конфигурации Vitastor. Имейте в виду, что этот путь также надо добавить в `/etc/apparmor.d/local/abstractions/libvirt-qemu`, если вы используете AppArmor.
+- STAGING_DIR - путь к временному каталогу, используемому при импорте внешних образов. Должен иметь достаточно свободного места, чтобы вмещать скачанные образы.
+
+После этого создайте хранилища с помощью команд `onedatastore create vitastor-imageds.conf` и `onedatastore create vitastor-systemds.conf` (либо через UI).
+
+## Блокировка доступа ВМ в Vitastor
+
+Vitastor пока не поддерживает никакую аутентификацию, так что вы ДОЛЖНЫ заблокировать доступ гостевых ВМ
+в кластер Vitastor на сетевом уровне.
+
+Если вы используете VLAN-сети для ВМ - удостоверьтесь, что ВМ и гипервизор/сеть хранения помещены в разные
+изолированные друг от друга VLAN-ы.
+
+Если вы используете что-то более примитивное, например, мосты (bridge), вам, скорее всего, придётся вручную
+настроить iptables / межсетевой экран, чтобы разрешить доступ к Vitastor только с IP гипервизоров.
+
+Также в этом случае нужно будет переключить обычные мосты на "Bridged & Security Groups" и включить фильтр
+спуфинга IP в OpenNebula. Правда, реализация этого фильтра пока не полная, и она не блокирует доступ к
+локальным интерфейсам гипервизора. То есть, включённый фильтр спуфинга IP запрещает ВМ отправлять трафик
+с чужими IP к другим ВМ или во внешний мир, но не запрещает отправлять его напрямую гипервизору. Чтобы
+исправить это, тоже нужны дополнительные правила iptables.
+
+Таким образом, более-менее полная блокировка при использовании простой сети на сетевых мостах может
+выглядеть так (здесь `10.0.3.0/24` - подсеть ВМ, `10.0.2.0/24` - подсеть гипервизора):
+
+```
+# Разрешаем входящий трафик с физического устройства
+iptables -A INPUT -m physdev --physdev-in eth0 -j ACCEPT
+# Запрещаем трафик со всех ВМ, но с IP не из подсети ВМ
+iptables -A INPUT ! -s 10.0.3.0/24 -i onebr0 -j DROP
+# Запрещаем трафик от ВМ к сети гипервизора
+iptables -I FORWARD 1 -s 10.0.3.0/24 -d 10.0.2.0/24 -j DROP
+```
+
+## Тестирование
+
+Плагин OpenNebula по большей части состоит из bash-скриптов, и чтобы было понятнее, что они
+вообще делают - ниже приведены описания процедур, которыми можно протестировать каждый из них.
+
+| Скрипт                  | Описание                                      | Как протестировать                                                                   |
+| ----------------------- | --------------------------------------------- | ------------------------------------------------------------------------------------ |
+| vmm/kvm/deploy.vitastor | Запустить виртуальную машину                  | Создайте и запустите виртуальную машину с дисками Vitastor: постоянным / непостоянным / волатильным (временным). |
+| vmm/kvm/save.vitastor   | Сохранить снимок памяти ВМ                    | Остановите виртуальную машину командой "Остановить".                                 |
+| vmm/kvm/restore.vitastor| Восстановить снимок памяти ВМ                 | Запустите ВМ после остановки обратно.                                                |
+| datastore/clone         | Скопировать образ как "постоянный"            | Создайте шаблон ВМ и создайте из него постоянную ВМ.                                 |
+| datastore/cp            | Импортировать внешний образ                   | Импортируйте шаблон ВМ с образами дисков из Магазина OpenNebula.                     |
+| datastore/export        | Экспортировать образ как URL                  | Вероятно: экспортируйте шаблон ВМ с образами в Магазин.                              |
+| datastore/mkfs          | Создать образ с файловой системой             | Хранилище → Образы → Создать → Тип: базовый блок данных, Расположение: пустой образ диска, Файловая система: любая непустая. |
+| datastore/monitor       | Вывод статистики места в хранилище образов    | Проверьте статистику свободного/занятого места в списке хранилищ образов.            |
+| datastore/rm            | Удалить "постоянный" образ                    | Хранилище → Образы → Выберите образ → Удалить.                                       |
+| datastore/snap_delete   | Удалить снимок "постоянного" образа           | Хранилище → Образы → Выберите образ → Выберите снимок → Удалить; <br> Чтобы создать образ со снимком: подключите постоянный образ к ВМ, создайте снимок, отключите образ. |
+| datastore/snap_flatten  | Откатить образ к снимку, удалив другие снимки | Хранилище → Образы → Выберите образ → Выберите снимок → "Выровнять" (flatten).       |
+| datastore/snap_revert   | Откатить образ к снимку                       | Хранилище → Образы → Выберите образ → Выберите снимок → Откатить.                    |
+| datastore/stat          | Показать виртуальный размер образа в МБ       | Неизвестно. По-видимому, в плагинах Vitastor и Ceph не используется.                 |
+| tm/clone                | Клонировать "непостоянный" образ в диск ВМ    | Подключите "непостоянный" образ к ВМ.                                                |
+| tm/context              | Создать диск контекстуализации ВМ             | Создайте ВМ с контекстуализацией, как обычно. Но тестировать особенно нечего: в плагинах Vitastor и Ceph образ контекста хранится в локальной ФС гипервизора. |
+| tm/cpds                 | Копировать диск ВМ/его снимок в новый образ   | Выберите ВМ → Выберите диск → Опционально выберите снимок → "Сохранить как".         |
+| tm/delete               | Удалить диск-клон или волатильный диск ВМ     | Отключите волатильный или не-постоянный диск от ВМ.                                  |
+| tm/failmigrate          | Обработать неудачную миграцию                 | Тестировать нечего. Скрипт пуст в плагинах Vitastor и Ceph. В других плагинах скрипт должен откатывать действия tm/premigrate. |
+| tm/ln                   | Подключить "постоянный" образ к ВМ            | Тестировать нечего. Скрипт пуст в плагинах Vitastor и Ceph.                          |
+| tm/mkimage              | Создать волатильный диск, без или с ФС        | Подключите волатильный диск к ВМ, с или без файловой системы.                        |
+| tm/mkswap               | Создать волатильный диск подкачки             | Подключите волатильный диск к ВМ, форматированный как диск подкачки (swap).          |
+| tm/monitor              | Вывод статистики места в хранилище дисков ВМ  | Проверьте статистику свободного/занятого места в списке хранилищ дисков ВМ.          |
+| tm/mv                   | Мигрировать диск ВМ между хостами             | Мигрируйте ВМ между серверами. Правда, с точки зрения хранилища в плагинах Vitastor и Ceph этот скрипт ничего не делает. |
+| tm/mvds                 | Отключить "постоянный" образ от ВМ            | Тестировать нечего. Скрипт пуст в плагинах Vitastor и Ceph. В целом же скрипт обратный к tm/ln и в других хранилищах он может, например, копировать образ ВМ с диска гипервизора обратно в хранилище. |
+| tm/postbackup           | Выполняется после бэкапа                      | По-видимому, скрипт просто удаляет временные файлы после резервного копирования. Так что можно провести его и проверить, что на серверах не осталось временных файлов. |
+| tm/postbackup_live      | Выполняется после бэкапа запущенной ВМ        | То же, что tm/postbackup, но для запущенной ВМ.                                      |
+| tm/postmigrate          | Выполняется после миграции ВМ                 | Тестировать нечего. Однако, OpenNebula запускает скрипт только для системного хранилища, поэтому он вызывает аналогичные скрипты для хранилищ других дисков той же ВМ. Помимо этого в плагинах Vitastor и Ceph скрипт ничего не делает. |
+| tm/prebackup            | Выполнить резервное копирование дисков ВМ     | Создайте хранилище резервных копий типа "rsync" → Забэкапьте в него ВМ.              |
+| tm/prebackup_live       | То же самое для запущенной ВМ                 | То же, что tm/prebackup, но запускает fsfreeze/thaw (остановку доступа к дискам). Так что смысл теста - проведите резервное копирование и проверьте, что данные скопировались консистентно. |
+| tm/premigrate           | Выполняется перед миграцией ВМ                | Тестировать нечего. Аналогично tm/postmigrate запускается только для системного хранилища. |
+| tm/resize               | Изменить размер диска ВМ                      | Выберите ВМ → Выберите непостоянный диск → Измените его размер.                      |
+| tm/restore              | Восстановить диски ВМ из бэкапа               | Создайте хранилище резервных копий → Забэкапьте в него ВМ → Восстановите её обратно. |
+| tm/snap_create          | Создать снимок диска ВМ                       | Выберите ВМ → Выберите диск → Создайте снимок.                                       |
+| tm/snap_create_live     | Создать снимок диска запущенной ВМ            | Выберите запущенную ВМ → Выберите диск → Создайте снимок.                            |
+| tm/snap_delete          | Удалить снимок диска ВМ                       | Выберите ВМ → Выберите диск → Выберите снимок → Удалить.                             |
+| tm/snap_revert          | Откатить диск ВМ к снимку                     | Выберите ВМ → Выберите диск → Выберите снимок → Откатить.                            |

docs/installation/proxmox.en.md

@@ -17,10 +17,10 @@ To enable Vitastor support in Proxmox Virtual Environment (6.4-8.1 are supported
 - Restart pvedaemon: `systemctl restart pvedaemon`
 
 `/etc/pve/storage.cfg` example (the only required option is vitastor_pool, all others
-are listed below with their default values):
+are listed below with their default values; `vitastor_ssd` is Proxmox storage pool id):
 
 ```
-vitastor: vitastor
+vitastor: vitastor_ssd
     # pool to put new images into
     vitastor_pool testpool
     # path to the configuration file

docs/installation/proxmox.ru.md

@@ -16,10 +16,10 @@
 - Перезапустите демон Proxmox: `systemctl restart pvedaemon`
 
 Пример `/etc/pve/storage.cfg` (единственная обязательная опция - vitastor_pool, все остальные
-перечислены внизу для понимания значений по умолчанию):
+перечислены внизу для понимания значений по умолчанию; `vitastor_ssd` - имя хранилища в Proxmox):
 
 ```
-vitastor: vitastor
+vitastor: vitastor_ssd
     # Пул, в который будут помещаться образы дисков
     vitastor_pool testpool
     # Путь к файлу конфигурации

docs/intro/features.en.md

@@ -39,6 +39,10 @@
 
 ## Plugins and tools
 
+- [Proxmox storage plugin and packages](../installation/proxmox.en.md)
+- [OpenNebula storage plugin](../installation/opennebula.en.md)
+- [CSI plugin for Kubernetes](../installation/kubernetes.en.md)
+- [OpenStack support: Cinder driver, Nova and libvirt patches](../installation/openstack.en.md)
 - [Debian and CentOS packages](../installation/packages.en.md)
 - [Image management CLI (vitastor-cli)](../usage/cli.en.md)
 - [Disk management CLI (vitastor-disk)](../usage/disk.en.md)
@@ -46,9 +50,6 @@
 - [Native QEMU driver](../usage/qemu.en.md)
 - [Loadable fio engine for benchmarks](../usage/fio.en.md)
 - [NBD proxy for kernel mounts](../usage/nbd.en.md)
-- [CSI plugin for Kubernetes](../installation/kubernetes.en.md)
-- [OpenStack support: Cinder driver, Nova and libvirt patches](../installation/openstack.en.md)
-- [Proxmox storage plugin and packages](../installation/proxmox.en.md)
 - [Simplified NFS proxy for file-based image access emulation (suitable for VMWare)](../usage/nfs.en.md#pseudo-fs)
 
 ## Roadmap
@@ -58,7 +59,6 @@ The following features are planned for the future:
 - Control plane optimisation
 - Other administrative tools
 - Web GUI
-- OpenNebula plugin
 - iSCSI and NVMeoF gateways
 - Multi-threaded client
 - Faster failover

docs/intro/features.ru.md

@@ -41,6 +41,10 @@
 
 ## Драйверы и инструменты
 
+- [Плагин для Proxmox](../installation/proxmox.ru.md)
+- [Плагин для OpenNebula](../installation/opennebula.ru.md)
+- [CSI-плагин для Kubernetes](../installation/kubernetes.ru.md)
+- [Базовая поддержка OpenStack: драйвер Cinder, патчи для Nova и libvirt](../installation/openstack.ru.md)
 - [Пакеты для Debian и CentOS](../installation/packages.ru.md)
 - [Консольный интерфейс управления образами (vitastor-cli)](../usage/cli.ru.md)
 - [Инструмент управления дисками (vitastor-disk)](../usage/disk.ru.md)
@@ -48,9 +52,6 @@
 - [Драйвер диска для QEMU](../usage/qemu.ru.md)
 - [Драйвер диска для утилиты тестирования производительности fio](../usage/fio.ru.md)
 - [NBD-прокси для монтирования образов ядром](../usage/nbd.ru.md) ("блочное устройство в режиме пользователя")
-- [CSI-плагин для Kubernetes](../installation/kubernetes.ru.md)
-- [Базовая поддержка OpenStack: драйвер Cinder, патчи для Nova и libvirt](../installation/openstack.ru.md)
-- [Плагин для Proxmox](../installation/proxmox.ru.md)
 - [Упрощённая NFS-прокси для эмуляции файлового доступа к образам (подходит для VMWare)](../usage/nfs.ru.md#псевдо-фс)
 
 ## Планы развития
@@ -58,7 +59,6 @@
 - Оптимизация слоя управления
 - Другие инструменты администрирования
 - Web-интерфейс
-- Плагин для OpenNebula
 - iSCSI и NVMeoF прокси
 - Многопоточный клиент
 - Более быстрое переключение при отказах

docs/intro/quickstart.en.md

@@ -32,7 +32,7 @@
 
 - SATA SSD: Micron 5100/5200/5300/5400, Samsung PM863/PM883/PM893, Intel D3-S4510/4520/4610/4620, Kingston DC500M
 - NVMe: Micron 9100/9200/9300/9400, Micron 7300/7450, Samsung PM983/PM9A3, Samsung PM1723/1735/1743,
-  Intel DC-P3700/P4500/P4600, Intel D7-P5500/P5600, Intel Optane, Kingston DC1000B/DC1500M
+  Intel DC-P3700/P4500/P4600, Intel D5-P4320, Intel D7-P5500/P5600, Intel Optane, Kingston DC1000B/DC1500M
 - HDD: HGST Ultrastar, Toshiba MG, Seagate EXOS
 
 ## Configure monitors

docs/intro/quickstart.ru.md

@@ -22,7 +22,7 @@
   использовать и десктопные SSD, включив режим отложенного fsync, но производительность будет хуже.
   О конденсаторах читайте [здесь](../config/layout-cluster.ru.md#immediate_commit).
 - Если хотите использовать HDD, берите современные модели с Media или SSD кэшем - HGST Ultrastar,
-  Toshiba MG08, Seagate EXOS или что-то похожее. Если такого кэша у ваших дисков нет,
+  Toshiba MG, Seagate EXOS или что-то похожее. Если такого кэша у ваших дисков нет,
   обязательно возьмите SSD под метаданные и журнал (маленькие, буквально 2 ГБ на 1 ТБ HDD-места).
 - Возьмите быструю сеть, минимум 10 гбит/с. Идеал - что-то вроде Mellanox ConnectX-4 с RoCEv2.
 - Для лучшей производительности отключите энергосбережение CPU: `cpupower idle-set -D 0 && cpupower frequency-set -g performance`.
@@ -32,8 +32,8 @@
 
 - SATA SSD: Micron 5100/5200/5300/5400, Samsung PM863/PM883/PM893, Intel D3-S4510/4520/4610/4620, Kingston DC500M
 - NVMe: Micron 9100/9200/9300/9400, Micron 7300/7450, Samsung PM983/PM9A3, Samsung PM1723/1735/1743,
-  Intel DC-P3700/P4500/P4600, Intel D7-P5500/P5600, Intel Optane, Kingston DC1000B/DC1500M
-- HDD: HGST Ultrastar, Toshiba MG06/MG07/MG08, Seagate EXOS
+  Intel DC-P3700/P4500/P4600, Intel D5-P4320, Intel D7-P5500/P5600, Intel Optane, Kingston DC1000B/DC1500M
+- HDD: HGST Ultrastar, Toshiba MG, Seagate EXOS
 
 ## Настройте мониторы
 

docs/usage/admin.en.md

@@ -42,7 +42,7 @@ PG state always includes exactly 1 of the following base states:
 - **offline** — PG isn't activated by any OSD at all. Either primary OSD isn't set for
   this PG at all (if the pool is just created), or an unavailable OSD is set as primary,
   or the primary OSD refuses to start this PG (for example, because of wrong block_size),
-  or the PG is stopped by the monitor using `pause: true` flag in `/vitastor/config/pgs` in etcd.
+  or the PG is stopped by the monitor using `pause: true` flag in `/vitastor/pg/config` in etcd.
 - **starting** — primary OSD has acquired PG lock in etcd, PG is starting.
 - **peering** — primary OSD requests PG object listings from secondary OSDs and calculates
   the PG state.
@@ -107,16 +107,17 @@ If a PG is active it can also have any number of the following additional states
 
 ## Removing a healthy disk
 
-Befor removing a healthy disk from the cluster set its OSD weight(s) to 0 to
-move data away. To do that, add `"reweight":0` to etcd key `/vitastor/config/osd/<OSD_NUMBER>`.
-For example:
+Before removing a healthy disk from the cluster set its OSD weight(s) to 0 to
+move data away. To do that, run `vitastor-cli modify-osd --reweight 0 <НОМЕР_OSD>`.
+
+Then wait until rebalance finishes and remove OSD by running `vitastor-disk purge /dev/vitastor/osdN-data`.
+
+Zero weight can also be put manually into etcd key `/vitastor/config/osd/<НОМЕР_OSD>`, for example:
 
 ```
 etcdctl --endpoints=http://1.1.1.1:2379/v3 put /vitastor/config/osd/1 '{"reweight":0}'
 ```
 
-Then wait until rebalance finishes and remove OSD by running `vitastor-disk purge /dev/vitastor/osdN-data`.
-
 ## Removing a failed disk
 
 If a disk is already dead, its OSD(s) are likely already stopped.
@@ -149,7 +150,7 @@ POOL_ID=1
 ALL_OSDS=$(etcdctl --endpoints=your_etcd_address:2379 get --keys-only --prefix /vitastor/osd/stats/ | \
     perl -e '$/ = undef; $a = <>; $a =~ s/\s*$//; $a =~ s!/vitastor/osd/stats/!!g; $a =~ s/\s+/,/g; print $a')
 for i in $(seq 1 $PG_COUNT); do
-    etcdctl --endpoints=your_etcd_address:2379 put /vitastor/pg/history/$POOL_ID/$i '{"all_peers":['$ALL_OSDS']}'; done
+    etcdctl --endpoints=your_etcd_address:2379 put /vitastor/pg/history/$POOL_ID/$i '{"all_peers":['$ALL_OSDS']}'
 done
 ```
 
@@ -168,21 +169,63 @@ Upgrading is performed without stopping clients (VMs/containers), you just need
 upgrade and restart servers one by one. However, ideally you should restart VMs too
 to make them use the new version of the client library.
 
-Exceptions (specific upgrade instructions):
-- Upgrading <= 1.1.x to 1.2.0 or later, if you use EC n+k with k>=2, is recommended
-  to be performed with full downtime: first you should stop all clients, then all OSDs,
-  then upgrade and start everything back — because versions before 1.2.0 have several
-  bugs leading to invalid data being read in EC n+k, k>=2 configurations in degraded pools.
-- Versions <= 0.8.7 are incompatible with versions >= 0.9.0, so you should first
-  upgrade from <= 0.8.7 to 0.8.8 or 0.8.9, and only then to >= 0.9.x. If you upgrade
-  without this intermediate step, client I/O will hang until the end of upgrade process.
-- Upgrading from <= 0.5.x to >= 0.6.x is not supported.
+### 1.7.x to 1.8.0
 
-Rollback:
-- Version 1.0.0 has a new disk format, so OSDs initiaziled on 1.0.0 can't be rolled
-  back to 0.9.x or previous versions.
-- Versions before 0.8.0 don't have vitastor-disk, so OSDs, initialized by it, won't
-  start with 0.7.x or 0.6.x. :-)
+After upgrading version <= 1.7.x to version >= 1.8.0, BUT <= 1.9.0: restart all clients
+(VMs and so on), otherwise they will hang when monitor clears old PG configuration key,
+which happens 24 hours after upgrade.
+
+This is fixed in 1.9.1. So, after upgrading version <= 1.7.x directly to version >= 1.9.1,
+you DO NOT have to restart all old clients immediately - they will work like before until
+you decide to upgrade them too. The downside is that you'll have to remove the old PG
+configuration key (`/vitastor/config/pgs`) from etcd by hand when you make sure that all
+your clients are restarted.
+
+### 1.1.x to 1.2.0
+
+Upgrading version <= 1.1.x to version >= 1.2.0, if you use EC n+k with k>=2, is recommended
+to be performed with full downtime: first you should stop all clients, then all OSDs,
+then upgrade and start everything back — because versions before 1.2.0 have several
+bugs leading to invalid data being read in EC n+k, k>=2 configurations in degraded pools.
+
+### 0.8.7 to 0.9.0
+
+Versions <= 0.8.7 are incompatible with versions >= 0.9.0, so you should first
+upgrade from <= 0.8.7 to 0.8.8 or 0.8.9, and only then to >= 0.9.x. If you upgrade
+without this intermediate step, client I/O will hang until the end of upgrade process.
+
+### 0.5.x to 0.6.x
+
+Upgrading from <= 0.5.x to >= 0.6.x is not supported.
+
+## Downgrade
+
+Downgrade are also allowed freely, except the following specific instructions:
+
+### 1.8.0 to 1.7.1
+
+Before downgrading from version >= 1.8.0 to version <= 1.7.1
+you have to copy /vitastor/pg/config etcd key to /vitastor/config/pgs:
+
+```
+etcdctl --endpoints=http://... get --print-value-only /vitastor/pg/config | \
+  etcdctl --endpoints=http://... put /vitastor/config/pgs
+```
+
+Then you can just install older packages and restart all services.
+
+If you performed downgrade without first copying that key, run "add all OSDs into the
+history records of all PGs" from [Restoring from lost pool configuration](#restoring-from-lost-pool-configuration).
+
+### 1.0.0 to 0.9.x
+
+Version 1.0.0 has a new disk format, so OSDs initialized on 1.0.0 or later can't
+be rolled back to 0.9.x or previous versions.
+
+### 0.8.0 to 0.7.x
+
+Versions before 0.8.0 don't have vitastor-disk, so OSDs, initialized by it, won't
+start with older versions (0.4.x - 0.7.x). :-)
 
 ## OSD memory usage
 

docs/usage/admin.ru.md

@@ -42,7 +42,7 @@
 - **offline** — PG вообще не активирована ни одним OSD. Либо первичный OSD не назначен вообще
   (если пул только создан), либо в качестве первичного назначен недоступный OSD, либо
   назначенный OSD отказывается запускать эту PG (например, из-за несовпадения block_size),
-  либо PG остановлена монитором через флаг `pause: true` в `/vitastor/config/pgs` в etcd.
+  либо PG остановлена монитором через флаг `pause: true` в `/vitastor/pg/config` в etcd.
 - **starting** — первичный OSD захватил блокировку PG в etcd, PG запускается.
 - **peering** — первичный OSD опрашивает вторичные OSD на предмет списков объектов данной PG и рассчитывает её состояние.
 - **repeering** — PG ожидает завершения текущих операций ввода-вывода, после чего перейдёт в состояние **peering**.
@@ -105,14 +105,16 @@ PG должны очень быстро переходить из них в др
 ## Удаление исправного диска
 
 Перед удалением исправного диска из кластера установите его OSD вес в 0, чтобы убрать с него данные.
-Для этого добавьте в ключ `/vitastor/config/osd/<НОМЕР_OSD>` в etcd значение `"reweight":0`, например:
+Для этого выполните команду `vitastor-cli modify-osd --reweight 0 <НОМЕР_OSD>`.
+
+Дождитесь завершения перебалансировки данных, после чего удалите OSD командой `vitastor-disk purge /dev/vitastor/osdN-data`.
+
+Также вес 0 можно прописать вручную прямо в etcd в ключ `/vitastor/config/osd/<НОМЕР_OSD>`, например:
 
 ```
 etcdctl --endpoints=http://1.1.1.1:2379/v3 put /vitastor/config/osd/1 '{"reweight":0}'
 ```
 
-Дождитесь завершения ребаланса, после чего удалите OSD командой `vitastor-disk purge /dev/vitastor/osdN-data`.
-
 ## Удаление неисправного диска
 
 Если диск уже умер, его OSD, скорее всего, уже будет/будут остановлен(ы).
@@ -145,7 +147,7 @@ POOL_ID=1
 ALL_OSDS=$(etcdctl --endpoints=your_etcd_address:2379 get --keys-only --prefix /vitastor/osd/stats/ | \
     perl -e '$/ = undef; $a = <>; $a =~ s/\s*$//; $a =~ s!/vitastor/osd/stats/!!g; $a =~ s/\s+/,/g; print $a')
 for i in $(seq 1 $PG_COUNT); do
-    etcdctl --endpoints=your_etcd_address:2379 put /vitastor/pg/history/$POOL_ID/$i '{"all_peers":['$ALL_OSDS']}'; done
+    etcdctl --endpoints=your_etcd_address:2379 put /vitastor/pg/history/$POOL_ID/$i '{"all_peers":['$ALL_OSDS']}'
 done
 ```
 
@@ -164,21 +166,63 @@ done
 достаточно обновлять серверы по одному. Однако, конечно, чтобы запущенные виртуальные машины
 начали использовать новую версию клиентской библиотеки, их тоже нужно перезапустить.
 
-Исключения (особые указания при обновлении):
-- Обновляться с версий <= 1.1.x до версий >= 1.2.0, если вы используете EC n+k и k>=2,
-  рекомендуется с временной остановкой кластера — сначала нужно остановить всех клиентов,
-  потом все OSD, потом обновить и запустить всё обратно — из-за нескольких багов, которые
-  могли приводить к некорректному чтению данных в деградированных EC-пулах.
-- Версии <= 0.8.7 несовместимы с версиями >= 0.9.0, поэтому при обновлении с <= 0.8.7
-  нужно сначала обновиться до 0.8.8 или 0.8.9, а уже потом до любых версий >= 0.9.x.
-  Иначе клиентский ввод-вывод зависнет до завершения обновления.
-- Обновление с версий 0.5.x и более ранних до 0.6.x и более поздних не поддерживается.
+### 1.7.x -> 1.8.0
 
-Откат:
-- В версии 1.0.0 поменялся дисковый формат, поэтому OSD, созданные на версии >= 1.0.0,
-  нельзя откатить до версии 0.9.x и более ранних.
-- В версиях ранее 0.8.0 нет vitastor-disk, значит, созданные им OSD нельзя откатить
-  до 0.7.x или 0.6.x. :-)
+После обновления с версий <= 1.7.x до версий >= 1.8.0, НО <= 1.9.0: перезапустите всех
+клиентов (процессы виртуальных машин можно перезапустить путём миграции на другой сервер),
+иначе они зависнут, когда монитор удалит старый ключ конфигурации PG, что происходит через
+24 часа после обновления.
+
+Однако, это исправлено в 1.9.1. Так что, если вы обновляетесь с <= 1.7.x сразу до >= 1.9.1,
+вам НЕ нужно сразу перезапускать всех клиентов - они будут работать, как раньше. Минус,
+правда, в том, что старый ключ конфигурации PG (`/vitastor/config/pgs`) будет нужно удалить
+вам из etcd вручную - после того, как вы убедитесь, что все клиенты перезапущены.
+
+### 1.1.x -> 1.2.0
+
+Обновляться с версий <= 1.1.x до версий >= 1.2.0, если вы используете EC n+k и k>=2,
+рекомендуется с временной остановкой кластера — сначала нужно остановить всех клиентов,
+потом все OSD, потом обновить и запустить всё обратно — из-за нескольких багов, которые
+могли приводить к некорректному чтению данных в деградированных EC-пулах.
+
+### 0.8.7 -> 0.9.0
+
+Версии <= 0.8.7 несовместимы с версиями >= 0.9.0, поэтому при обновлении с <= 0.8.7
+нужно сначала обновиться до 0.8.8 или 0.8.9, а уже потом до любых версий >= 0.9.x.
+Иначе клиентский ввод-вывод зависнет до завершения обновления.
+
+### 0.5.x -> 0.6.x
+
+Обновление с версий 0.5.x и более ранних до 0.6.x и более поздних не поддерживается.
+
+## Откат версии
+
+Откат (понижение версии) тоже свободно разрешён, кроме указанных ниже случаев:
+
+### 1.8.0 -> 1.7.1
+
+Перед понижением версии с >= 1.8.0 до <= 1.7.1 вы должны скопировать ключ
+etcd `/vitastor/pg/config` в `/vitastor/config/pgs`:
+
+```
+etcdctl --endpoints=http://... get --print-value-only /vitastor/pg/config | \
+  etcdctl --endpoints=http://... put /vitastor/config/pgs
+```
+
+После этого можно просто установить более старые пакеты и перезапустить все сервисы.
+
+Если вы откатили версию, не скопировав предварительно этот ключ - выполните "добавление всех
+OSD в исторические записи всех PG" из раздела [Восстановление потерянной конфигурации пулов](#восстановление-потерянной-конфигурации-пулов).
+
+### 1.0.0 -> 0.9.x
+
+В версии 1.0.0 поменялся дисковый формат, поэтому OSD, созданные на версии >= 1.0.0,
+нельзя откатить до версии 0.9.x и более ранних.
+
+### 0.8.0 -> 0.7.x
+
+В версиях ранее 0.8.0 нет vitastor-disk, значит, созданные им OSD не запустятся на
+более ранних версиях (0.4.x - 0.7.x). :-)
 
 ## Потребление памяти OSD
 

docs/usage/cli.en.md

@@ -16,6 +16,7 @@ It supports the following commands:
 - [create](#create)
 - [snap-create](#create)
 - [modify](#modify)
+- [dd](#dd)
 - [rm](#rm)
 - [flatten](#flatten)
 - [rm-data](#rm-data)
@@ -26,6 +27,8 @@ It supports the following commands:
 - [rm-osd](#rm-osd)
 - [osd-tree](#osd-tree)
 - [ls-osd](#ls-osd)
+- [modify-osd](#modify-osd)
+- [pg-list](#pg-list)
 - [create-pool](#create-pool)
 - [modify-pool](#modify-pool)
 - [ls-pools](#ls-pools)
@@ -146,19 +149,60 @@ You should resize file system in the image, if present, before shrinking it.
 * `-f|--force` - Proceed with shrinking or setting readwrite flag even if the image has children.
 * `--down-ok` - Proceed with shrinking even if some data will be left on unavailable OSDs.
 
+## dd
+
+```
+vitastor-cli dd [iimg=<image> | if=<file>] [oimg=<image> | of=<file>] [bs=1M] \
+    [count=N] [seek/oseek=N] [skip/iseek=M] [iodepth=N] [status=progress] \
+    [conv=nocreat,noerror,nofsync,trunc,nosparse] [iflag=direct] [oflag=direct,append]
+```
+
+Copy data between Vitastor images, files and pipes.
+
+Options can be specified in classic dd style (`key=value`) or like usual (`--key value`).
+
+| <!-- -->        | <!-- -->                                                                |
+|-----------------|-------------------------------------------------------------------------|
+| `iimg=<image>`  | Copy from Vitastor image `<image>`                                      |
+| `if=<file>`     | Copy from file `<file>`                                                 |
+| `oimg=<image>`  | Copy to Vitastor image `<image>`                                        |
+| `of=<file>`     | Copy to file `<file>`                                                   |
+| `bs=1M`         | Set copy block size                                                     |
+| `count=N`       | Copy only N input blocks. If N ends in B it counts bytes, not blocks    |
+| `seek/oseek=N`  | Skip N output blocks. If N ends in B it counts bytes, not blocks        |
+| `skip/iseek=N`  | Skip N input blocks. If N ends in B it counts bytes, not blocks         |
+| `iodepth=N`     | Send N reads or writes in parallel (default 4)                          |
+| `status=LEVEL`  | The LEVEL of information to print to stderr: none/noxfer/progress       |
+| `size=N`        | Specify size for the created output file/image (defaults to input size) |
+| `iflag=direct`  | For input files only: use direct I/O                                    |
+| `oflag=direct`  | For output files only: use direct I/O                                   |
+| `oflag=append`  | For files only: append to output file                                   |
+| `conv=nocreat`  | Do not create output file/image                                         |
+| `conv=trunc`    | Truncate output file/image                                              |
+| `conv=noerror`  | Continue copying after errors                                           |
+| `conv=nofsync`  | Do not call fsync before finishing (default behaviour is fsync)         |
+| `conv=nosparse` | Write all output blocks including all-zero blocks                       |
+
 ## rm
 
 `vitastor-cli rm <from> [<to>] [--writers-stopped] [--down-ok]`
 
-Remove `<from>` or all layers between `<from>` and `<to>` (`<to>` must be a child of `<from>`),
-rebasing all their children accordingly. --writers-stopped allows merging to be a bit
-more effective in case of a single 'slim' read-write child and 'fat' removed parent:
-the child is merged into parent and parent is renamed to child in that case.
-In other cases parent layers are always merged into children.
+`vitastor-cli rm (--exact|--matching) <glob> ...`
 
-Other options:
+Remove layer(s) and rebase all their children accordingly.
 
-* `--down-ok` - Continue deletion/merging even if some data will be left on unavailable OSDs.
+In the first form, remove `<from>` or layers between `<from>` and its child `<to>`.
+
+In the second form, remove all images with exact or pattern-matched names.
+
+Options:
+
+* `--writers-stopped` allows optimised removal in case of a single 'slim' read-write
+  child and 'fat' removed parent: the child is merged into parent and parent is renamed
+  to child in that case. In other cases parent layers are always merged into children.
+* `--exact` - remove multiple images with names matching given glob patterns.
+* `--matching` - remove multiple images with given names
+* `--down-ok` - continue deletion/merging even if some data will be left on unavailable OSDs.
 
 ## flatten
 
@@ -305,7 +349,25 @@ OSD  PARENT            UP    SIZE  USED%    TAGS          WEIGHT  BLOCK  BITMAP
 
 `vitastor-cli modify-osd [--tags tag1,tag2,...] [--reweight <number>] [--noout true/false] <osd_number>`
 
-Set OSD reweight, tags or noout flag. See detail description in [OSD config documentation](../config.pool.en.md#osd-settings).
+Set OSD reweight, tags or noout flag. See detail description in [OSD config documentation](../config/pool.en.md#osd-settings).
+
+## pg-list
+
+`vitastor-cli pg-list|pg-ls|list-pg|ls-pg|ls-pgs [OPTIONS] [state1+state2] [^state3] [...]`
+
+List PGs with any of listed state filters (^ or ! in the beginning is negation). Options:
+
+```
+--pool <pool name or number>  Only list PGs of the given pool.
+--min <min pg number>         Only list PGs with number >= min.
+--max <max pg number>         Only list PGs with number <= max.
+```
+
+Examples:
+
+`vitastor-cli pg-list active+degraded`
+
+`vitastor-cli pg-list ^active`
 
 ## create-pool
 

docs/usage/cli.ru.md

@@ -17,6 +17,7 @@ vitastor-cli - интерфейс командной строки для адм
 - [create](#create)
 - [snap-create](#create)
 - [modify](#modify)
+- [dd](#dd)
 - [rm](#rm)
 - [flatten](#flatten)
 - [rm-data](#rm-data)
@@ -25,6 +26,8 @@ vitastor-cli - интерфейс командной строки для адм
 - [rm-osd](#rm-osd)
 - [osd-tree](#osd-tree)
 - [ls-osd](#ls-osd)
+- [modify-osd](#modify-osd)
+- [pg-list](#pg-list)
 - [create-pool](#create-pool)
 - [modify-pool](#modify-pool)
 - [ls-pools](#ls-pools)
@@ -149,23 +152,61 @@ vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
 * `-f|--force` - Разрешить уменьшение или перевод в чтение-запись образа, у которого есть клоны.
 * `--down-ok` - Разрешить уменьшение, даже если часть данных останется неудалённой на недоступных OSD.
 
+## dd
+
+```
+vitastor-cli dd [iimg=<image> | if=<file>] [oimg=<image> | of=<file>] [bs=1M] \
+    [count=N] [seek/oseek=N] [skip/iseek=M] [iodepth=N] [status=progress] \
+    [conv=nocreat,noerror,nofsync,trunc,nosparse] [iflag=direct] [oflag=direct,append]
+```
+
+Копировать данные между образами Vitastor, файлами и каналами.
+
+Опции можно передавать в классическом стиле dd (`key=value`) или как обычно (`--key value`).
+
+| <!-- -->        | <!-- -->                                                                |
+|-----------------|-------------------------------------------------------------------------|
+| `iimg=<image>`  | Копировать из образа Vitastor `<image>`                                 |
+| `if=<file>`     | Копировать из файла `<file>`                                            |
+| `oimg=<image>`  | Копировать в образ Vitastor `<image>`                                   |
+| `of=<file>`     | Копировать в файл `<file>`                                              |
+| `bs=1M`         | Задать размер блока копирования                                         |
+| `count=N`       | Копировать не более N блоков. Если N заканчивается на B - то N байт.    |
+| `seek/oseek=N`  | Пропустить N выходных блоков. Если N заканчивается на B - то N байт.    |
+| `skip/iseek=N`  | Пропустить N входных блоков. Если N заканчивается на B - то N байт.     |
+| `iodepth=N`     | Отправлять N чтений/записей параллельно (по умолчанию 4).               |
+| `status=LEVEL`  | Уровень вывода в консоль: none/noxfer/progress                          |
+| `size=N`        | Задать размер выходного файла/образа (по умолчанию равен размеру входа).|
+| `iflag=direct`  | Только для входного файла: использовать прямой ввод-вывод               |
+| `oflag=direct`  | Только для выходного файла: использовать прямой ввод-вывод              |
+| `oflag=append`  | Только для файлов: дописывать в конец выходного файла                   |
+| `conv=nocreat`  | Не создавать выходной файл/образ                                        |
+| `conv=trunc`    | Обрезать выходной файл/образ до размера входа                           |
+| `conv=noerror`  | Продолжать копирование после ошибок                                     |
+| `conv=nofsync`  | Не вызывать fsync перед завершением                                     |
+| `conv=nosparse` | Записывать все выходные блоки, включая пустые                           |
+
 ## rm
 
 `vitastor-cli rm <from> [<to>] [--writers-stopped] [--down-ok]`
 
-Удалить образ `<from>` или все слои от `<from>` до `<to>` (`<to>` должен быть дочерним
-образом `<from>`), одновременно меняя родительские образы их клонов (если таковые есть).
+`vitastor-cli rm (--exact|--matching) <glob> ...`
 
-`--writers-stopped` позволяет чуть более эффективно удалять образы в частом случае, когда
-у удаляемой цепочки есть только один дочерний образ, содержащий небольшой объём данных.
-В этом случае дочерний образ вливается в родительский и удаляется, а родительский
-переименовывается в дочерний.
+Удалить образ(ы), корректно перебазируя их дочерние образы.
 
-В других случаях родительские слои вливаются в дочерние.
+В первой форме удаляет один образ `<from>` или все слои между `<from>` и его дочерним `<to>`.
 
-Другие опции:
+Во второй форме, удаляет все образы с точными именами или именами, подходящими под шаблон(ы).
 
-* `--down-ok` - Продолжать удаление/слияние, даже если часть данных останется неудалённой на недоступных OSD.
+Опции:
+
+* `--writers-stopped` позволяет чуть более эффективно удалять образы в частом случае, когда
+  у удаляемой цепочки есть только один дочерний образ, содержащий небольшой объём данных.
+  В этом случае дочерний образ вливается в родительский и удаляется, а родительский
+  переименовывается в дочерний.
+* `--exact` - удалить все образы с именами, подходящими под переданные glob-шаблоны.
+* `--matching` - удалить все образы с точно заданными именами.
+* `--down-ok` - продолжать удаление/слияние, даже если часть данных останется неудалённой на недоступных OSD.
 
 ## flatten
 
@@ -322,7 +363,26 @@ OSD  PARENT            UP    SIZE  USED%    TAGS          WEIGHT  BLOCK  BITMAP
 
 `vitastor-cli modify-osd [--tags tag1,tag2,...] [--reweight <number>] [--noout true/false] <osd_number>`
 
-Установить вес OSD, теги или флаг noout. Смотрите подробное описание в [документации настроек OSD](../config.pool.ru.md#настройки-osd).
+Установить вес OSD, теги или флаг noout. Смотрите подробное описание в [документации настроек OSD](../config/pool.ru.md#настройки-osd).
+
+## pg-list
+
+`vitastor-cli pg-list|pg-ls|list-pg|ls-pg|ls-pgs [OPTIONS] [state1+state2] [^state3] [...]`
+
+Вывести список PG с состояними, удовлетворяющими любому из переданных фильтров (^ или !
+в начале фильтра означает отрицание). Опции:
+
+```
+--pool <pool name or number>  Only list PGs of the given pool.
+--min <min pg number>         Only list PGs with number >= min.
+--max <max pg number>         Only list PGs with number <= max.
+```
+
+Примеры:
+
+`vitastor-cli pg-list active+degraded`
+
+`vitastor-cli pg-list ^active`
 
 ## create-pool
 

docs/usage/disk.en.md

@@ -13,6 +13,7 @@ It supports the following commands:
 - [prepare](#prepare)
 - [upgrade-simple](#upgrade-simple)
 - [resize](#resize)
+- [raw-resize](#raw-resize)
 - [start/stop/restart/enable/disable](#start/stop/restart/enable/disable)
 - [purge](#purge)
 - [read-sb](#read-sb)
@@ -127,25 +128,49 @@ Requires the `sfdisk` utility.
 
 ## resize
 
-`vitastor-disk resize <ALL_OSD_PARAMETERS> <NEW_LAYOUT> [--iodepth 32]`
+`vitastor-disk resize <osd_num>|<osd_device> [OPTIONS]`
 
-Resize data area and/or rewrite/move journal and metadata.
+Resize data area and/or move journal and metadata:
+
+| <!-- -->                  | <!-- -->                               |
+|---------------------------|----------------------------------------|
+| `--move-journal TARGET`   | move journal to `TARGET`               |
+| `--move-meta TARGET`      | move metadata to `TARGET`              |
+| `--journal-size NEW_SIZE` | resize journal to `NEW_SIZE`           |
+| `--data-size NEW_SIZE`    | resize data device to `NEW_SIZE`       |
+| `--dry-run`               | only show new layout, do not apply it  |
+
+`NEW_SIZE` may include k/m/g/t suffixes.
+
+`TARGET` may be one of:
+
+| <!-- -->       | <!-- -->                                                                 |
+|----------------|--------------------------------------------------------------------------|
+| `<partition>`  | move journal/metadata to an existing GPT partition                       |
+| `<raw_device>` | create a GPT partition on `<raw_device>` and move journal/metadata to it |
+| `""`           | (empty string) move journal/metadata back to the data device             |
+
+## raw-resize
+
+`vitastor-disk raw-resize <ALL_OSD_PARAMETERS> <NEW_LAYOUT> [--iodepth 32]`
+
+Resize data area and/or rewrite/move journal and metadata (manual format).
 
 `ALL_OSD_PARAMETERS` must include all (at least all disk-related)
 parameters from OSD command line (i.e. from systemd unit or superblock).
 
 `NEW_LAYOUT` may include new disk layout parameters:
 
-```
---new_data_offset SIZE     resize data area so it starts at SIZE
---new_data_len SIZE        resize data area to SIZE bytes
---new_meta_device PATH     use PATH for new metadata
---new_meta_offset SIZE     make new metadata area start at SIZE
---new_meta_len SIZE        make new metadata area SIZE bytes long
---new_journal_device PATH  use PATH for new journal
---new_journal_offset SIZE  make new journal area start at SIZE
---new_journal_len SIZE     make new journal area SIZE bytes long
-```
+| <!-- -->                    | <!-- -->                                  |
+|-----------------------------|-------------------------------------------|
+| `--new_data_offset SIZE`    | resize data area so it starts at `SIZE`   |
+| `--new_data_len SIZE`       | resize data area to `SIZE` bytes          |
+| `--new_meta_device PATH`    | use `PATH` for new metadata               |
+| `--new_meta_offset SIZE`    | make new metadata area start at `SIZE`    |
+| `--new_meta_len SIZE`       | make new metadata area `SIZE` bytes long  |
+| `--new_journal_device PATH` | use `PATH` for new journal                |
+| `--new_journal_offset SIZE` | make new journal area start at `SIZE`     |
+| `--new_journal_len SIZE`    | make new journal area `SIZE` bytes long   |
 
 SIZE may include k/m/g/t suffixes. If any of the new layout parameter
 options are not specified, old values will be used.
@@ -217,10 +242,14 @@ Intended for use from startup scripts (i.e. from systemd units).
 
 ## dump-journal
 
+`vitastor-disk dump-journal [OPTIONS] <osd_device>`
+
 `vitastor-disk dump-journal [OPTIONS] <journal_file> <journal_block_size> <offset> <size>`
 
 Dump journal in human-readable or JSON (if `--json` is specified) format.
 
+You can specify any OSD device (data, metadata or journal), or the layout manually.
+
 Options:
 
 ```
@@ -233,23 +262,35 @@ Options:
 
 ## write-journal
 
+`vitastor-disk write-journal <osd_device>`
+
 `vitastor-disk write-journal <journal_file> <journal_block_size> <bitmap_size> <offset> <size>`
 
 Write journal from JSON taken from standard input in the same format as produced by
 `dump-journal --json --format data`.
 
+You can specify any OSD device (data, metadata or journal), or the layout manually.
+
 ## dump-meta
 
+`vitastor-disk dump-meta <osd_device>`
+
 `vitastor-disk dump-meta <meta_file> <meta_block_size> <offset> <size>`
 
 Dump metadata in JSON format.
 
+You can specify any OSD device (data, metadata or journal), or the layout manually.
+
 ## write-meta
 
+`vitastor-disk write-meta <osd_device>`
+
 `vitastor-disk write-meta <meta_file> <offset> <size>`
 
 Write metadata from JSON taken from standard input in the same format as produced by `dump-meta`.
 
+You can specify any OSD device (data, metadata or journal), or the layout manually.
+
 ## simple-offsets
 
 `vitastor-disk simple-offsets <device>`

docs/usage/disk.ru.md

@@ -13,6 +13,7 @@ vitastor-disk - инструмент командной строки для уп
 - [prepare](#prepare)
 - [upgrade-simple](#upgrade-simple)
 - [resize](#resize)
+- [raw-resize](#raw-resize)
 - [start/stop/restart/enable/disable](#start/stop/restart/enable/disable)
 - [purge](#purge)
 - [read-sb](#read-sb)
@@ -129,27 +130,51 @@ throttle_target_mbs, throttle_target_parallelism, throttle_threshold_us.
 
 ## resize
 
-`vitastor-disk resize <ALL_OSD_PARAMETERS> <NEW_LAYOUT> [--iodepth 32]`
+`vitastor-disk resize <osd_num>|<osd_device> [OPTIONS]`
 
-Изменить размер области данных и/или переместить журнал и метаданные.
+Изменить размер области данных и/или переместить журнал и метаданные:
 
-В `ALL_OSD_PARAMETERS` нужно указать все относящиеся к диску параметры OSD
+| <!-- -->                      | <!-- -->                                       |
+|-------------------------------|------------------------------------------------|
+| `--move-journal ЦЕЛЬ`         | переместить журнал на `ЦЕЛЬ`                   |
+| `--move-meta ЦЕЛЬ`            | переместить метаданные на `ЦЕЛЬ`               |
+| `--journal-size НОВЫЙ_РАЗМЕР` | изменить размер журнала на `НОВЫЙ_РАЗМЕР`      |
+| `--data-size НОВЫЙ_РАЗМЕР`    | изменить размер диска данных на `НОВЫЙ_РАЗМЕР` |
+| `--dry-run`                   | показать новые параметры, но не применять их   |
+
+`НОВЫЙ_РАЗМЕР` может быть указан с суффиксами k/m/g/t (кило/мега/гига/терабайт).
+
+`ЦЕЛЬ` может быть одним из:
+
+| <!-- -->        | <!-- -->                                                                            |
+|-----------------|-------------------------------------------------------------------------------------|
+| `<раздел>`      | переместить журнал/метаданные на существующий GPT-раздел                            |
+| `<полный_диск>` | создать GPT-раздел на диске `<полный_диск>` и переместить журнал/метаданные на него |
+| `""`            | (пустая строка) переместить журнал/метаданные обратно на диск данных                |
+
+## raw-resize
+
+`vitastor-disk raw-resize <ВСЕ_ПАРАМЕТРЫ_OSD> <НОВЫЕ_РАЗМЕРЫ> [--iodepth 32]`
+
+Изменить размер области данных и/или переместить журнал и метаданные (ручной формат).
+
+В `ВСЕ_ПАРАМЕТРЫ_OSD` нужно указать все относящиеся к диску параметры OSD
 из суперблока OSD или из файла сервиса systemd (в старых версиях).
 
-В `NEW_LAYOUT` нужно указать новые параметры расположения данных:
+В `НОВЫЕ_РАЗМЕРЫ` нужно указать новые параметры расположения данных:
 
-```
---new_data_offset РАЗМЕР     сдвинуть начало области данных на РАЗМЕР байт
---new_data_len РАЗМЕР        изменить размер области данных до РАЗМЕР байт
---new_meta_device ПУТЬ       использовать ПУТЬ как новое устройство метаданных
---new_meta_offset РАЗМЕР     разместить новые метаданные по смещению РАЗМЕР байт
---new_meta_len РАЗМЕР        сделать новые метаданные размером РАЗМЕР байт
---new_journal_device ПУТЬ    использовать ПУТЬ как новое устройство журнала
---new_journal_offset РАЗМЕР  разместить новый журнал по смещению РАЗМЕР байт
---new_journal_len РАЗМЕР     сделать новый журнал размером РАЗМЕР байт
-```
+| <!-- -->                      | <!-- -->                                              |
+|-------------------------------|-------------------------------------------------------|
+| `--new_data_offset РАЗМЕР`    | сдвинуть начало области данных на `РАЗМЕР` байт       |
+| `--new_data_len РАЗМЕР`       | изменить размер области данных до `РАЗМЕР` байт       |
+| `--new_meta_device ПУТЬ`      | использовать `ПУТЬ` как новое устройство метаданных   |
+| `--new_meta_offset РАЗМЕР`    | разместить новые метаданные по смещению `РАЗМЕР` байт |
+| `--new_meta_len РАЗМЕР`       | сделать новые метаданные размером `РАЗМЕР` байт       |
+| `--new_journal_device ПУТЬ`   | использовать `ПУТЬ` как новое устройство журнала      |
+| `--new_journal_offset РАЗМЕР` | разместить новый журнал по смещению `РАЗМЕР` байт     |
+| `--new_journal_len РАЗМЕР`    | сделать новый журнал размером `РАЗМЕР` байт           |
 
-РАЗМЕР может быть указан с суффиксами k/m/g/t. Если любой из новых параметров
+`РАЗМЕР` может быть указан с суффиксами k/m/g/t. Если любой из новых параметров
 расположения не указан, он принимается равным старому значению.
 
 ## start/stop/restart/enable/disable
@@ -224,10 +249,15 @@ OSD отключены fsync-и.
 
 ## dump-journal
 
+`vitastor-disk dump-journal <osd_device>`
+
 `vitastor-disk dump-journal [OPTIONS] <journal_file> <journal_block_size> <offset> <size>`
 
 Вывести журнал в человекочитаемом или в JSON (с опцией `--json`) виде.
 
+Вы можете указать любой раздел OSD - данных, журнала или метаданных - либо указать все
+параметры расположения вручную.
+
 Опции:
 
 ```
@@ -240,22 +270,37 @@ OSD отключены fsync-и.
 
 ## write-journal
 
+`vitastor-disk write-journal <osd_device>`
+
 `vitastor-disk write-journal <journal_file> <journal_block_size> <bitmap_size> <offset> <size>`
 
 Записать журнал из JSON со стандартного ввода в формате, аналогичном `dump-journal --json --format data`.
 
+Вы можете указать любой раздел OSD - данных, журнала или метаданных - либо указать все
+параметры расположения вручную.
+
 ## dump-meta
 
+`vitastor-disk dump-meta <osd_device>`
+
 `vitastor-disk dump-meta <meta_file> <meta_block_size> <offset> <size>`
 
 Вывести метаданные в формате JSON.
 
+Вы можете указать любой раздел OSD - данных, журнала или метаданных - либо указать все
+параметры расположения вручную.
+
 ## write-meta
 
+`vitastor-disk write-meta <osd_device>`
+
 `vitastor-disk write-meta <meta_file> <offset> <size>`
 
 Записать метаданные из JSON со стандартного ввода в формате, аналогичном `dump-meta`.
 
+Вы можете указать любой раздел OSD - данных, журнала или метаданных - либо указать все
+параметры расположения вручную.
+
 ## simple-offsets
 
 `vitastor-disk simple-offsets <device>`

docs/usage/nfs.en.md

@@ -156,17 +156,17 @@ behind. Defragmentation removes garbage and moves data still in use to new volum
 
 Options:
 
-| <!-- -->                 | <!-- -->                                                                |
-|--------------------------|------------------------------------------------------------------------ |
-| --volume_untouched 86400 | Defragment volumes last appended to at least this number of seconds ago |
-| --defrag_percent 50      | Defragment volumes with at least this % of removed data                 |
-| --defrag_block_count 16  | Read this number of pool blocks at once during defrag                   |
-| --defrag_iodepth 16      | Move up to this number of files in parallel during defrag               |
-| --trace                  | Print verbose defragmentation status                                    |
-| --dry-run                | Skip modifications, only print status                                   |
-| --recalc-stats           | Recalculate all volume statistics                                       |
-| --include-empty          | Include old and empty volumes; make sure to restart NFS servers before using it |
-| --no-rm                  | Move, but do not delete data                                            |
+| <!-- -->                   | <!-- -->                                                                |
+|----------------------------|------------------------------------------------------------------------ |
+| `--volume_untouched 86400` | Defragment volumes last appended to at least this number of seconds ago |
+| `--defrag_percent 50`      | Defragment volumes with at least this % of removed data                 |
+| `--defrag_block_count 16`  | Read this number of pool blocks at once during defrag                   |
+| `--defrag_iodepth 16`      | Move up to this number of files in parallel during defrag               |
+| `--trace`                  | Print verbose defragmentation status                                    |
+| `--dry-run`                | Skip modifications, only print status                                   |
+| `--recalc-stats`           | Recalculate all volume statistics                                       |
+| `--include-empty`          | Include old and empty volumes; make sure to restart NFS servers before using it |
+| `--no-rm`                  | Move, but do not delete data                                            |
 
 ## Common options
 

docs/usage/nfs.ru.md

@@ -164,17 +164,17 @@ JSON-формате :-). Для инспекции содержимого БД
 
 Опции:
 
-| <!-- -->                 | <!-- -->                                                                |
-|--------------------------|------------------------------------------------------------------------ |
-| --volume_untouched 86400 | Дефрагментировать только тома, в которые уже не писали это число секунд |
-| --defrag_percent 50      | Дефрагментировать только тома, в которых этот % данных удалён           |
-| --defrag_block_count 16  | Читать это количество блоков пула за один раз                           |
-| --defrag_iodepth 16      | Перемещать одновременно до этого числа файлов                           |
-| --trace                  | Печатать детальную статистику дефрагментации                            |
-| --dry-run                | Не производить никаких изменений, только описать выполняемые действия   |
-| --recalc-stats           | Пересчитать и сохранить статистику всех томов                           |
-| --include-empty          | Дефрагментировать старые и пустые тома; обязательно перезапустите NFS-сервера после использования этой опции |
-| --no-rm                  | Перемещать, но не удалять данные                                        |
+| <!-- -->                   | <!-- -->                                                                |
+|----------------------------|------------------------------------------------------------------------ |
+| `--volume_untouched 86400` | Дефрагментировать только тома, в которые уже не писали это число секунд |
+| `--defrag_percent 50`      | Дефрагментировать только тома, в которых этот % данных удалён           |
+| `--defrag_block_count 16`  | Читать это количество блоков пула за один раз                           |
+| `--defrag_iodepth 16`      | Перемещать одновременно до этого числа файлов                           |
+| `--trace`                  | Печатать детальную статистику дефрагментации                            |
+| `--dry-run`                | Не производить никаких изменений, только описать выполняемые действия   |
+| `--recalc-stats`           | Пересчитать и сохранить статистику всех томов                           |
+| `--include-empty`          | Дефрагментировать старые и пустые тома; обязательно перезапустите NFS-сервера после использования этой опции |
+| `--no-rm`                  | Перемещать, но не удалять данные                                        |
 
 ## Общие опции
 

docs/usage/qemu.en.md

@@ -151,9 +151,9 @@ Example performance comparison:
 To try VDUSE you need at least Linux 5.15, built with VDUSE support
 (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,
-or build modules for Debian kernel manually:
+Debian Linux kernels had these options disabled until 6.6, so make sure you install a newer kernel
+(from bookworm-backports, trixie or newer Debian version) if you want to try VDUSE. You can also
+build modules for an existing kernel manually:
 
 ```
 mkdir build

docs/usage/qemu.ru.md

@@ -154,9 +154,9 @@ VDUSE - на данный момент лучший интерфейс для п
 Чтобы попробовать VDUSE, вам нужно ядро Linux как минимум версии 5.15, собранное с поддержкой
 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/),
-из Proxmox или соберите модули для ядра Debian вручную:
+В ядрах в Debian Linux эти опции включены, только начиная с 6.6, так что установите свежее ядро
+из bookworm-backports, trixie или из более новой версии Debian, если хотите попробовать VDUSE.
+Либо же вы можете самостоятельно собрать модули для установленного ядра:
 
 ```
 mkdir build

mon/antietcd_adapter.js

@@ -1,8 +1,6 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 (see README.md for details)
 
-const fs = require('fs');
-
 const AntiEtcd = require('antietcd');
 
 const vitastor_persist_filter = require('./vitastor_persist_filter.js');
@@ -15,21 +13,15 @@ class AntiEtcdAdapter
         let antietcd;
         if (config.use_antietcd)
         {
-            let fileConfig = {};
-            if (fs.existsSync(config.config_path||'/etc/vitastor/vitastor.conf'))
-            {
-                fileConfig = JSON.parse(fs.readFileSync(config.config_path||'/etc/vitastor/vitastor.conf', { encoding: 'utf-8' }));
-            }
-            let mergedConfig = { ...fileConfig, ...config };
-            let cluster = mergedConfig.etcd_address;
+            let cluster = config.etcd_address;
             if (!(cluster instanceof Array))
                 cluster = cluster ? (''+(cluster||'')).split(/,+/) : [];
             cluster = Object.keys(cluster.reduce((a, url) =>
             {
-                a[url.toLowerCase().replace(/^https?:\/\//, '').replace(/\/.*$/, '')] = true;
+                a[url.toLowerCase().replace(/^(https?:\/\/)/, '').replace(/\/.*$/, '')] = true;
                 return a;
             }, {}));
-            const cfg_port = mergedConfig.antietcd_port;
+            const cfg_port = config.antietcd_port;
             const is_local = local_ips(true).reduce((a, c) => { a[c] = true; return a; }, {});
             const selected = cluster.map(s => s.split(':', 2)).filter(ip => is_local[ip[0]] && (!cfg_port || ip[1] == cfg_port));
             if (selected.length > 1)
@@ -42,12 +34,13 @@ class AntiEtcdAdapter
                 const antietcd_config = {
                     ip: selected[0][0],
                     port: selected[0][1],
-                    data: mergedConfig.antietcd_data_file || ((mergedConfig.antietcd_data_dir || '/var/lib/vitastor') + '/mon_'+selected[0][1]+'.json.gz'),
-                    persist_filter: vitastor_persist_filter(mergedConfig.etcd_prefix || '/vitastor'),
+                    data: config.antietcd_data_file || ((config.antietcd_data_dir || '/var/lib/vitastor') + '/mon_'+selected[0][1]+'.json.gz'),
+                    persist_filter: vitastor_persist_filter({ vitastor_prefix: config.etcd_prefix || '/vitastor' }),
                     node_id: selected[0][0]+':'+selected[0][1], // node_id = ip:port
-                    cluster: (cluster.length == 1 ? null : cluster),
-                    cluster_key: (mergedConfig.etcd_prefix || '/vitastor'),
+                    cluster: (cluster.length == 1 ? null : cluster.reduce((a, c) => { a[c] = "http://"+c; return a; }, {})),
+                    cluster_key: (config.etcd_prefix || '/vitastor'),
                     stale_read: 1,
+                    log_level: 1,
                 };
                 for (const key in config)
                 {
@@ -60,6 +53,7 @@ class AntiEtcdAdapter
                         }
                     }
                 }
+                console.log('Starting Antietcd node '+antietcd_config.node_id);
                 antietcd = new AntiEtcd(antietcd_config);
                 await antietcd.start();
             }
@@ -128,20 +122,23 @@ class AntiEtcdAdapter
 
     async become_master()
     {
-        if (!this.antietcd.raft)
+        if (!this.antietcd.cluster)
         {
             console.log('Running in non-clustered mode');
         }
         else
         {
             console.log('Waiting to become master');
-            await new Promise(ok => this.on_leader.push(ok));
+            if (this.antietcd.cluster.raft.state !== 'leader')
+            {
+                await new Promise(ok => this.on_leader.push(ok));
+            }
         }
         const state = { ...this.mon.get_mon_state(), id: ''+this.mon.etcd_lease_id };
         await this.etcd_call('/kv/txn', {
             success: [ { requestPut: { key: b64(this.mon.config.etcd_prefix+'/mon/master'), value: b64(JSON.stringify(state)), lease: ''+this.mon.etcd_lease_id } } ],
         }, this.mon.config.etcd_start_timeout, 0);
-        if (this.antietcd.raft)
+        if (this.antietcd.cluster)
         {
             console.log('Became master');
         }

mon/etcd_schema.js

@@ -6,7 +6,7 @@ const etcd_nonempty_keys = {
     'config/global': 1,
     'config/node_placement': 1,
     'config/pools': 1,
-    'config/pgs': 1,
+    'pg/config': 1,
     'history/last_clean_pgs': 1,
     'stats': 1,
 };
@@ -15,7 +15,8 @@ const etcd_allow = new RegExp('^'+[
     'config/node_placement',
     'config/pools',
     'config/osd/[1-9]\\d*',
-    'config/pgs',
+    'config/pgs', // old name
+    'pg/config',
     'config/inode/[1-9]\\d*/[1-9]\\d*',
     'osd/state/[1-9]\\d*',
     'osd/stats/[1-9]\\d*',
@@ -24,7 +25,8 @@ const etcd_allow = new RegExp('^'+[
     'mon/master',
     'mon/member/[a-f0-9]+',
     'pg/state/[1-9]\\d*/[1-9]\\d*',
-    'pg/stats/[1-9]\\d*/[1-9]\\d*',
+    'pg/stats/[1-9]\\d*/[1-9]\\d*', // old name
+    'pgstats/[1-9]\\d*/[1-9]\\d*',
     'pg/history/[1-9]\\d*/[1-9]\\d*',
     'history/last_clean_pgs',
     'inode/stats/[1-9]\\d*/\\d+',
@@ -205,19 +207,6 @@ const etcd_tree = {
         osd: {
             /* <id>: { reweight?: 1, tags?: [ 'nvme', ... ], noout?: true }, ... */
         },
-        /* pgs: {
-            hash: string,
-            items: {
-                <pool_id>: {
-                    <pg_id>: {
-                        osd_set: [ 1, 2, 3 ],
-                        primary: 1,
-                        pause: false,
-                    }
-                }
-            }
-        }, */
-        pgs: {},
         /* inode: {
             <pool_id>: {
                 <inode_t>: {
@@ -290,6 +279,19 @@ const etcd_tree = {
         },
     },
     pg: {
+        /* config: {
+            hash: string,
+            items: {
+                <pool_id>: {
+                    <pg_id>: {
+                        osd_set: [ 1, 2, 3 ],
+                        primary: 1,
+                        pause: false,
+                    }
+                }
+            }
+        }, */
+        config: {},
         state: {
             /* <pool_id>: {
                 <pg_id>: {
@@ -300,18 +302,6 @@ const etcd_tree = {
                 }
             }, */
         },
-        stats: {
-            /* <pool_id>: {
-                <pg_id>: {
-                    object_count: uint64_t,
-                    clean_count: uint64_t,
-                    misplaced_count: uint64_t,
-                    degraded_count: uint64_t,
-                    incomplete_count: uint64_t,
-                    write_osd_set: osd_num_t[],
-                },
-            }, */
-        },
         history: {
             /* <pool_id>: {
                 <pg_id>: {
@@ -323,6 +313,18 @@ const etcd_tree = {
             }, */
         },
     },
+    pgstats: {
+        /* <pool_id>: {
+            <pg_id>: {
+                object_count: uint64_t,
+                clean_count: uint64_t,
+                misplaced_count: uint64_t,
+                degraded_count: uint64_t,
+                incomplete_count: uint64_t,
+                write_osd_set: osd_num_t[],
+            },
+        }, */
+    },
     inode: {
         stats: {
             /* <pool_id>: {

mon/http_server.js

@@ -30,7 +30,11 @@ async function create_http_server(cfg, handler)
     }
     try
     {
+        let err;
+        server.once('error', e => err = e);
         server.listen(cfg.mon_http_port || 8060, cfg.mon_http_ip || undefined);
+        if (err)
+            throw err;
     }
     catch (e)
     {

mon/mon.js

@@ -22,12 +22,13 @@ class Mon
 {
     static async run_forever(config)
     {
+        let mergedConfig = config;
         if (fs.existsSync(config.config_path||'/etc/vitastor/vitastor.conf'))
         {
             const fileConfig = JSON.parse(fs.readFileSync(config.config_path||'/etc/vitastor/vitastor.conf', { encoding: 'utf-8' }));
-            config = { ...fileConfig, config };
+            mergedConfig = { ...fileConfig, ...config };
         }
-        let antietcd = await AntiEtcdAdapter.start_antietcd(config);
+        let antietcd = await AntiEtcdAdapter.start_antietcd(mergedConfig);
         let mon;
         const run = () =>
         {
@@ -74,6 +75,8 @@ class Mon
         this.prev_stats = { osd_stats: {}, osd_diff: {} };
         this.recheck_pgs_active = false;
         this.watcher_active = false;
+        this.old_pg_config = false;
+        this.old_pg_stats_seen = false;
     }
 
     async start()
@@ -121,7 +124,7 @@ class Mon
                 !Number(this.state.pool.stats[pool_id].pg_real_size))
             {
                 // Generate missing data in etcd
-                this.state.config.pgs.hash = null;
+                this.state.pg.config.hash = null;
                 break;
             }
         }
@@ -200,16 +203,25 @@ class Mon
                 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/')
+            else if (key.substr(0, 11) == '/osd/stats/' || key.substr(0, 9) == '/pgstats/' || key.substr(0, 16) == '/osd/inodestats/')
             {
                 stats_changed = true;
             }
+            else if (key.substr(0, 10) == '/pg/stats/')
+            {
+                this.old_pg_stats_seen = true;
+                stats_changed = true;
+            }
             else if (key.substr(0, 10) == '/pg/state/')
             {
                 pg_states_changed = true;
             }
             else if (key != '/stats' && key.substr(0, 13) != '/inode/stats/')
             {
+                if (key == '/config/pgs' && !kv.value)
+                {
+                    this.old_pg_config = false;
+                }
                 changed = true;
             }
             if (this.config.verbose)
@@ -284,7 +296,7 @@ class Mon
                     continue next_pool;
                 }
             }
-            new_clean_pgs.items[pool_id] = this.state.config.pgs.items[pool_id];
+            new_clean_pgs.items[pool_id] = this.state.pg.config.items[pool_id];
         }
         this.state.history.last_clean_pgs = new_clean_pgs;
         await this.etcd.etcd_call('/kv/txn', {
@@ -395,6 +407,26 @@ class Mon
                 this.parse_kv(kv);
             }
         }
+        if (Object.keys((this.state.config.pgs||{}).items||{}).length)
+        {
+            // Support seamless upgrade to new OSDs
+            if (!Object.keys((this.state.pg.config||{}).items||{}).length)
+            {
+                const pgs = JSON.stringify(this.state.config.pgs);
+                this.state.pg.config = JSON.parse(pgs);
+                const res = await this.etcd.etcd_call('/kv/txn', {
+                    success: [
+                        { requestPut: { key: b64(this.config.etcd_prefix+'/pg/config'), value: b64(pgs) } },
+                    ],
+                    compare: [
+                        { key: b64(this.config.etcd_prefix+'/pg/config'), target: 'MOD', mod_revision: ''+this.etcd_watch_revision, result: 'LESS' },
+                    ],
+                }, this.config.etcd_mon_timeout, this.config.etcd_mon_retries);
+                if (!res.succeeded)
+                    throw new Error('Failed to duplicate old PG config to new PG config');
+            }
+            this.old_pg_config = true;
+        }
     }
 
     all_osds()
@@ -405,7 +437,7 @@ class Mon
     async stop_all_pgs(pool_id)
     {
         let has_online = false, paused = true;
-        for (const pg in this.state.config.pgs.items[pool_id]||{})
+        for (const pg in this.state.pg.config.items[pool_id]||{})
         {
             // FIXME: Change all (||{}) to ?. (optional chaining) at some point
             const cur_state = (((this.state.pg.state[pool_id]||{})[pg]||{}).state||[]).join(',');
@@ -413,7 +445,7 @@ class Mon
             {
                 has_online = true;
             }
-            if (!this.state.config.pgs.items[pool_id][pg].pause)
+            if (!this.state.pg.config.items[pool_id][pg].pause)
             {
                 paused = false;
             }
@@ -421,7 +453,7 @@ class Mon
         if (!paused)
         {
             console.log('Stopping all PGs for pool '+pool_id+' before changing PG count');
-            const new_cfg = JSON.parse(JSON.stringify(this.state.config.pgs));
+            const new_cfg = JSON.parse(JSON.stringify(this.state.pg.config));
             for (const pg in new_cfg.items[pool_id])
             {
                 new_cfg.items[pool_id][pg].pause = true;
@@ -429,22 +461,26 @@ class Mon
             // Check that no OSDs change their state before we pause PGs
             // Doing this we make sure that OSDs don't wake up in the middle of our "transaction"
             // and can't see the old PG configuration
-            const checks = [];
+            const checks = [
+                { key: b64(this.config.etcd_prefix+'/mon/master'), target: 'LEASE', lease: ''+this.etcd_lease_id },
+                { key: b64(this.config.etcd_prefix+'/pg/config'), target: 'MOD', mod_revision: ''+this.etcd_watch_revision, result: 'LESS' },
+            ];
             for (const osd_num of this.all_osds())
             {
                 const key = b64(this.config.etcd_prefix+'/osd/state/'+osd_num);
                 checks.push({ key, target: 'MOD', result: 'LESS', mod_revision: ''+this.etcd_watch_revision });
             }
-            await this.etcd.etcd_call('/kv/txn', {
-                compare: [
-                    { key: b64(this.config.etcd_prefix+'/mon/master'), target: 'LEASE', lease: ''+this.etcd_lease_id },
-                    { key: b64(this.config.etcd_prefix+'/config/pgs'), target: 'MOD', mod_revision: ''+this.etcd_watch_revision, result: 'LESS' },
-                    ...checks,
-                ],
+            const txn = {
+                compare: checks,
                 success: [
-                    { requestPut: { key: b64(this.config.etcd_prefix+'/config/pgs'), value: b64(JSON.stringify(new_cfg)) } },
+                    { requestPut: { key: b64(this.config.etcd_prefix+'/pg/config'), value: b64(JSON.stringify(new_cfg)) } },
                 ],
-            }, this.config.etcd_mon_timeout, 0);
+            };
+            if (this.old_pg_config)
+            {
+                txn.success.push({ requestPut: { key: b64(this.config.etcd_prefix+'/config/pgs'), value: b64(JSON.stringify(new_cfg)) } });
+            }
+            await this.etcd.etcd_call('/kv/txn', txn, this.config.etcd_mon_timeout, 0);
             return false;
         }
         return !has_online;
@@ -472,7 +508,7 @@ class Mon
             pools: this.state.config.pools,
         };
         const tree_hash = sha1hex(stableStringify(tree_cfg));
-        if (this.state.config.pgs.hash != tree_hash)
+        if (this.state.pg.config.hash != tree_hash)
         {
             // Something has changed
             console.log('Pool configuration or OSD tree changed, re-optimizing');
@@ -513,10 +549,10 @@ class Mon
         else
         {
             // Nothing changed, but we still want to recheck the distribution of primaries
-            let new_config_pgs = recheck_primary(this.state, this.config, up_osds, osd_tree);
-            if (new_config_pgs)
+            let new_pg_config = recheck_primary(this.state, this.config, up_osds, osd_tree);
+            if (new_pg_config)
             {
-                const ok = await this.save_pg_config(new_config_pgs);
+                const ok = await this.save_pg_config(new_pg_config);
                 if (ok)
                     console.log('PG configuration successfully changed');
                 else
@@ -531,12 +567,12 @@ class Mon
 
     async apply_pool_pgs(results, up_osds, osd_tree, tree_hash)
     {
-        for (const pool_id in (this.state.config.pgs||{}).items||{})
+        for (const pool_id in (this.state.pg.config||{}).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))
+                this.state.pg.config.items[pool_id] && this.state.config.pools[pool_id].pg_count !=
+                Object.keys(this.state.pg.config.items[pool_id]).reduce((a, c) => (a < (0|c) ? (0|c) : a), 0))
             {
                 if (!await this.stop_all_pgs(pool_id))
                 {
@@ -544,22 +580,22 @@ class Mon
                 }
             }
         }
-        const new_config_pgs = JSON.parse(JSON.stringify(this.state.config.pgs));
+        const new_pg_config = JSON.parse(JSON.stringify(this.state.pg.config));
         const etcd_request = { compare: [], success: [] };
-        for (const pool_id in (new_config_pgs||{}).items||{})
+        for (const pool_id in (new_pg_config||{}).items||{})
         {
             if (!this.state.config.pools[pool_id])
             {
                 const prev_pgs = [];
-                for (const pg in new_config_pgs.items[pool_id]||{})
+                for (const pg in new_pg_config.items[pool_id]||{})
                 {
-                    prev_pgs[pg-1] = new_config_pgs.items[pool_id][pg].osd_set;
+                    prev_pgs[pg-1] = new_pg_config.items[pool_id][pg].osd_set;
                 }
                 // Also delete pool statistics
                 etcd_request.success.push({ requestDeleteRange: {
                     key: b64(this.config.etcd_prefix+'/pool/stats/'+pool_id),
                 } });
-                save_new_pgs_txn(new_config_pgs, etcd_request, this.state, this.config.etcd_prefix,
+                save_new_pgs_txn(new_pg_config, etcd_request, this.state, this.config.etcd_prefix,
                     this.etcd_watch_revision, pool_id, up_osds, osd_tree, prev_pgs, [], []);
             }
         }
@@ -568,7 +604,7 @@ class Mon
             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]||{}))
+            for (const pg in ((this.state.pg.config.items||{})[pool_id]||{}))
             {
                 if (this.state.pg.history[pool_id] &&
                     this.state.pg.history[pool_id][pg])
@@ -577,9 +613,9 @@ class Mon
                 }
             }
             const real_prev_pgs = [];
-            for (const pg in ((this.state.config.pgs.items||{})[pool_id]||{}))
+            for (const pg in ((this.state.pg.config.items||{})[pool_id]||{}))
             {
-                real_prev_pgs[pg-1] = [ ...this.state.config.pgs.items[pool_id][pg].osd_set ];
+                real_prev_pgs[pg-1] = [ ...this.state.pg.config.items[pool_id][pg].osd_set ];
             }
             if (real_prev_pgs.length > 0 && real_prev_pgs.length != pool_res.pgs.length)
             {
@@ -590,8 +626,8 @@ class Mon
                 pg_history = scale_pg_history(pg_history, real_prev_pgs, pool_res.pgs);
                 // Drop stats
                 etcd_request.success.push({ requestDeleteRange: {
-                    key: b64(this.config.etcd_prefix+'/pg/stats/'+pool_id+'/'),
-                    range_end: b64(this.config.etcd_prefix+'/pg/stats/'+pool_id+'0'),
+                    key: b64(this.config.etcd_prefix+'/pgstats/'+pool_id+'/'),
+                    range_end: b64(this.config.etcd_prefix+'/pgstats/'+pool_id+'0'),
                 } });
             }
             const stats = {
@@ -602,22 +638,26 @@ class Mon
                 key: b64(this.config.etcd_prefix+'/pool/stats/'+pool_id),
                 value: b64(JSON.stringify(stats)),
             } });
-            save_new_pgs_txn(new_config_pgs, etcd_request, this.state, this.config.etcd_prefix,
+            save_new_pgs_txn(new_pg_config, etcd_request, this.state, this.config.etcd_prefix,
                 this.etcd_watch_revision, 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);
+        new_pg_config.hash = tree_hash;
+        return await this.save_pg_config(new_pg_config, etcd_request);
     }
 
-    async save_pg_config(new_config_pgs, etcd_request = { compare: [], success: [] })
+    async save_pg_config(new_pg_config, etcd_request = { compare: [], success: [] })
     {
         etcd_request.compare.push(
             { key: b64(this.config.etcd_prefix+'/mon/master'), target: 'LEASE', lease: ''+this.etcd_lease_id },
-            { key: b64(this.config.etcd_prefix+'/config/pgs'), target: 'MOD', mod_revision: ''+this.etcd_watch_revision, result: 'LESS' },
+            { key: b64(this.config.etcd_prefix+'/pg/config'), target: 'MOD', mod_revision: ''+this.etcd_watch_revision, result: 'LESS' },
         );
         etcd_request.success.push(
-            { requestPut: { key: b64(this.config.etcd_prefix+'/config/pgs'), value: b64(JSON.stringify(new_config_pgs)) } },
+            { requestPut: { key: b64(this.config.etcd_prefix+'/pg/config'), value: b64(JSON.stringify(new_pg_config)) } },
         );
+        if (this.old_pg_config)
+        {
+            etcd_request.success.push({ requestPut: { key: b64(this.config.etcd_prefix+'/config/pgs'), value: b64(JSON.stringify(new_pg_config)) } });
+        }
         const txn_res = await this.etcd.etcd_call('/kv/txn', etcd_request, this.config.etcd_mon_timeout, 0);
         return txn_res.succeeded;
     }

mon/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vitastor-mon",
-  "version": "1.7.0",
+  "version": "1.9.2",
   "description": "Vitastor SDS monitor service",
   "main": "mon-main.js",
   "scripts": {
@@ -9,7 +9,7 @@
   "author": "Vitaliy Filippov",
   "license": "UNLICENSED",
   "dependencies": {
-    "antietcd": "^1.0.5",
+    "antietcd": "^1.1.0",
     "sprintf-js": "^1.1.2",
     "ws": "^7.2.5"
   },

mon/pg_gen.js

@@ -57,7 +57,7 @@ function pick_primary(pool_config, osd_set, up_osds, aff_osds)
 
 function recheck_primary(state, global_config, up_osds, osd_tree)
 {
-    let new_config_pgs;
+    let new_pg_config;
     for (const pool_id in state.config.pools)
     {
         const pool_cfg = state.config.pools[pool_id];
@@ -69,30 +69,30 @@ function recheck_primary(state, global_config, up_osds, osd_tree)
         reset_rng();
         for (let pg_num = 1; pg_num <= pool_cfg.pg_count; pg_num++)
         {
-            if (!state.config.pgs.items[pool_id])
+            if (!state.pg.config.items[pool_id])
             {
                 continue;
             }
-            const pg_cfg = state.config.pgs.items[pool_id][pg_num];
+            const pg_cfg = state.pg.config.items[pool_id][pg_num];
             if (pg_cfg)
             {
                 const new_primary = pick_primary(state.config.pools[pool_id], pg_cfg.osd_set, up_osds, aff_osds);
                 if (pg_cfg.primary != new_primary)
                 {
-                    if (!new_config_pgs)
+                    if (!new_pg_config)
                     {
-                        new_config_pgs = JSON.parse(JSON.stringify(state.config.pgs));
+                        new_pg_config = JSON.parse(JSON.stringify(state.pg.config));
                     }
                     console.log(
                         `Moving pool ${pool_id} (${pool_cfg.name || 'unnamed'}) PG ${pg_num}`+
                         ` primary OSD from ${pg_cfg.primary} to ${new_primary}`
                     );
-                    new_config_pgs.items[pool_id][pg_num].primary = new_primary;
+                    new_pg_config.items[pool_id][pg_num].primary = new_primary;
                 }
             }
         }
     }
-    return new_config_pgs;
+    return new_pg_config;
 }
 
 function save_new_pgs_txn(save_to, request, state, etcd_prefix, etcd_watch_revision, pool_id, up_osds, osd_tree, prev_pgs, new_pgs, pg_history)
@@ -185,10 +185,10 @@ async function generate_pool_pgs(state, global_config, pool_id, osd_tree, levels
     }
     if (!prev_pgs.length)
     {
-        // Fall back to config/pgs if it's empty
-        for (const pg in ((state.config.pgs.items||{})[pool_id]||{}))
+        // Fall back to pg/config if it's empty
+        for (const pg in ((state.pg.config.items||{})[pool_id]||{}))
         {
-            prev_pgs[pg-1] = [ ...state.config.pgs.items[pool_id][pg].osd_set ];
+            prev_pgs[pg-1] = [ ...state.pg.config.items[pool_id][pg].osd_set ];
         }
     }
     const old_pg_count = prev_pgs.length;
@@ -205,8 +205,8 @@ async function generate_pool_pgs(state, global_config, pool_id, osd_tree, levels
         ordered: pool_cfg.scheme != 'replicated',
     };
     let optimize_result;
-    // Re-shuffle PGs if config/pgs.hash is empty
-    if (old_pg_count > 0 && state.config.pgs.hash)
+    // Re-shuffle PGs if pg/config.hash is empty
+    if (old_pg_count > 0 && state.pg.config.hash)
     {
         if (prev_pgs.length != pool_cfg.pg_count)
         {

mon/prometheus.js

@@ -166,7 +166,7 @@ function export_prometheus_metrics(st)
         res += `vitastor_pool_used_raw_tb{${pool_label}} ${pool_stat.used_raw_tb||0}\n`;
 
         // PG states and pool up/down status
-        const real_pg_count = (Object.keys(((st.config.pgs||{}).items||{})[pool_id]||{}).length) || (0|pool_cfg.pg_count);
+        const real_pg_count = (Object.keys(((st.pg.config||{}).items||{})[pool_id]||{}).length) || (0|pool_cfg.pg_count);
         const per_state = {
             active: 0,
             starting: 0,

mon/stats.js

@@ -100,10 +100,19 @@ function sum_object_counts(state, global_config)
 {
     const object_counts = { object: 0n, clean: 0n, misplaced: 0n, degraded: 0n, incomplete: 0n };
     const object_bytes = { object: 0n, clean: 0n, misplaced: 0n, degraded: 0n, incomplete: 0n };
-    for (const pool_id in state.pg.stats)
+    let pgstats = state.pgstats;
+    if (state.pg.stats)
+    {
+        // Merge with old stats for seamless transition to new stats
+        for (const pool_id in state.pg.stats)
+        {
+            pgstats[pool_id] = { ...(state.pg.stats[pool_id] || {}), ...(pgstats[pool_id] || {}) };
+        }
+    }
+    for (const pool_id in pgstats)
     {
         let object_size = 0;
-        for (const osd_num of state.pg.stats[pool_id].write_osd_set||[])
+        for (const osd_num of pgstats[pool_id].write_osd_set||[])
         {
             if (osd_num && state.osd.stats[osd_num] && state.osd.stats[osd_num].block_size)
             {
@@ -121,9 +130,9 @@ function sum_object_counts(state, global_config)
             object_size *= ((pool_cfg.pg_size||0) - (pool_cfg.parity_chunks||0));
         }
         object_size = BigInt(object_size);
-        for (const pg_num in state.pg.stats[pool_id])
+        for (const pg_num in pgstats[pool_id])
         {
-            const st = state.pg.stats[pool_id][pg_num];
+            const st = pgstats[pool_id][pg_num];
             if (st)
             {
                 for (const k in object_counts)

mon/vitastor_persist_filter.js

@@ -24,7 +24,7 @@ function vitastor_persist_filter(cfg)
                 catch (e)
                 {
                     console.error('invalid JSON in '+key+' = '+value+': '+e);
-                    value = {};
+                    value = '{}';
                 }
             }
             else
@@ -35,7 +35,8 @@ function vitastor_persist_filter(cfg)
         }
         else if (key.substr(0, prefix.length+'/osd/'.length) == prefix+'/osd/' ||
             key.substr(0, prefix.length+'/inode/stats/'.length) == prefix+'/inode/stats/' ||
-            key.substr(0, prefix.length+'/pg/stats/'.length) == prefix+'/pg/stats/' ||
+            key.substr(0, prefix.length+'/pg/stats/'.length) == prefix+'/pg/stats/' || // old name
+            key.substr(0, prefix.length+'/pgstats/'.length) == prefix+'/pgstats/' ||
             key.substr(0, prefix.length+'/pool/stats/'.length) == prefix+'/pool/stats/' ||
             key == prefix+'/stats')
         {

node-binding/addon.cc

@@ -24,7 +24,7 @@ NAN_MODULE_INIT(InitAddon)
 
     tpl = Nan::New<v8::FunctionTemplate>(NodeVitastorImage::Create);
     tpl->SetClassName(Nan::New("Image").ToLocalChecked());
-    tpl->InstanceTemplate()->SetInternalFieldCount(2);
+    tpl->InstanceTemplate()->SetInternalFieldCount(1);
 
     Nan::SetPrototypeMethod(tpl, "read", NodeVitastorImage::Read);
     Nan::SetPrototypeMethod(tpl, "write", NodeVitastorImage::Write);
@@ -67,7 +67,7 @@ NAN_MODULE_INIT(InitAddon)
 
     tpl = Nan::New<v8::FunctionTemplate>(NodeVitastorKVListing::Create);
     tpl->SetClassName(Nan::New("KVListing").ToLocalChecked());
-    tpl->InstanceTemplate()->SetInternalFieldCount(2);
+    tpl->InstanceTemplate()->SetInternalFieldCount(1);
 
     Nan::SetPrototypeMethod(tpl, "next", NodeVitastorKVListing::Next);
     Nan::SetPrototypeMethod(tpl, "close", NodeVitastorKVListing::Close);

node-binding/addon.h

@@ -11,10 +11,10 @@
 
 #define ERRORF(format, ...) fprintf(stderr, format "\n", __VA_ARGS__);
 
-#define TRACEF(format, ...) fprintf(stderr, format "\n", __VA_ARGS__);
-#define TRACE(msg) fprintf(stderr, "%s\n", msg);
+//#define TRACEF(format, ...) fprintf(stderr, format "\n", __VA_ARGS__);
+//#define TRACE(msg) fprintf(stderr, "%s\n", msg);
 
-//#define TRACEF(format, arg) ;
-//#define TRACE(msg) ;
+#define TRACEF(format, ...) ;
+#define TRACE(msg) ;
 
 #endif

node-binding/binding.gyp

@@ -13,7 +13,8 @@
         '<!(pkg-config --cflags vitastor)'
       ],
       'libraries': [
-        '<!(pkg-config --libs vitastor)'
+        '<!(pkg-config --libs vitastor)',
+        '-lvitastor_kv'
       ]
     }
   ]

node-binding/client.cc

@@ -18,12 +18,15 @@
 class NodeVitastorRequest: public Nan::AsyncResource
 {
 public:
-    NodeVitastorRequest(v8::Local<v8::Function> cb): Nan::AsyncResource("NodeVitastorRequest")
+    NodeVitastorRequest(NodeVitastor *cli, v8::Local<v8::Function> cb): Nan::AsyncResource("NodeVitastorRequest")
     {
+        this->cli = cli;
         callback.Reset(cb);
     }
 
     iovec iov;
+    std::vector<iovec> iov_list;
+    NodeVitastor *cli = NULL;
     NodeVitastorImage *img = NULL;
     int op = 0;
     uint64_t offset = 0, len = 0, version = 0;
@@ -31,6 +34,13 @@ public:
     Nan::Persistent<v8::Function> callback;
 };
 
+static uint64_t get_ui64(const v8::Local<v8::Value> & val)
+{
+    if (val->IsBigInt())
+        return val->ToBigInt(Nan::GetCurrentContext()).ToLocalChecked()->Uint64Value();
+    return Nan::To<int64_t>(val).FromJust();
+}
+
 //////////////////////////////////////////////////
 // NodeVitastor
 //////////////////////////////////////////////////
@@ -43,6 +53,7 @@ NodeVitastor::NodeVitastor(): Nan::ObjectWrap()
 
 NodeVitastor::~NodeVitastor()
 {
+    TRACE("NodeVitastor: destructor");
     uv_poll_stop(&poll_watcher);
     vitastor_c_destroy(c);
     c = NULL;
@@ -74,9 +85,10 @@ NAN_METHOD(NodeVitastor::Create)
     if (res >= 0)
     {
         cli->eventfd = res;
-        res = uv_poll_init_socket(uv_default_loop(), &cli->poll_watcher, cli->eventfd);
+        res = uv_poll_init(uv_default_loop(), &cli->poll_watcher, cli->eventfd);
         if (res >= 0)
             res = uv_poll_start(&cli->poll_watcher, UV_READABLE, on_io_readable);
+        on_io_readable(&cli->poll_watcher, 0, UV_READABLE);
     }
     if (res < 0)
     {
@@ -97,15 +109,14 @@ void NodeVitastor::on_io_readable(uv_poll_t* handle, int status, int revents)
     if (revents & UV_READABLE)
     {
         NodeVitastor* self = (NodeVitastor*)handle->data;
-        std::unique_lock<std::mutex> lock(self->mu);
         vitastor_c_uring_handle_events(self->c);
     }
 }
 
-static NodeVitastorRequest* getReadRequest(const Nan::FunctionCallbackInfo<v8::Value> & info, int argpos)
+NodeVitastorRequest* NodeVitastor::get_read_request(const Nan::FunctionCallbackInfo<v8::Value> & info, int argpos)
 {
-    uint64_t offset = Nan::To<int64_t>(info[argpos+0]).FromJust();
-    uint64_t len = Nan::To<int64_t>(info[argpos+1]).FromJust();
+    uint64_t offset = get_ui64(info[argpos+0]);
+    uint64_t len = get_ui64(info[argpos+1]);
     uint8_t *buf = (uint8_t*)malloc(len);
     if (!buf)
     {
@@ -113,7 +124,7 @@ static NodeVitastorRequest* getReadRequest(const Nan::FunctionCallbackInfo<v8::V
         return NULL;
     }
     v8::Local<v8::Function> callback = info[argpos+2].As<v8::Function>();
-    auto req = new NodeVitastorRequest(callback);
+    auto req = new NodeVitastorRequest(this, callback);
 
     req->offset = offset;
     req->len = len;
@@ -126,73 +137,101 @@ static NodeVitastorRequest* getReadRequest(const Nan::FunctionCallbackInfo<v8::V
 NAN_METHOD(NodeVitastor::Read)
 {
     TRACE("NodeVitastor::Read");
+    if (info.Length() < 5)
+        Nan::ThrowError("Not enough arguments to read(pool, inode, offset, len, callback(err, buffer, version))");
 
     NodeVitastor* self = Nan::ObjectWrap::Unwrap<NodeVitastor>(info.This());
 
-    uint64_t pool = Nan::To<int64_t>(info[0]).FromJust();
-    uint64_t inode = Nan::To<int64_t>(info[1]).FromJust();
+    uint64_t pool = get_ui64(info[0]);
+    uint64_t inode = get_ui64(info[1]);
 
-    auto req = getReadRequest(info, 2);
+    auto req = self->get_read_request(info, 2);
 
-    std::unique_lock<std::mutex> lock(self->mu);
+    self->Ref();
     vitastor_c_read(self->c, ((pool << (64-POOL_ID_BITS)) | inode), req->offset, req->len, &req->iov, 1, on_read_finish, req);
 }
 
-static NodeVitastorRequest* getWriteRequest(const Nan::FunctionCallbackInfo<v8::Value> & info, int argpos)
+NodeVitastorRequest* NodeVitastor::get_write_request(const Nan::FunctionCallbackInfo<v8::Value> & info, int argpos)
 {
-    uint64_t offset = Nan::To<int64_t>(info[argpos+0]).FromJust();
-    char *buf = node::Buffer::Data(info[argpos+1]);
-    uint64_t len = node::Buffer::Length(info[argpos+1]);
+    uint64_t offset = get_ui64(info[argpos+0]);
+    const auto & bufarg = info[argpos+1];
     uint64_t version = 0;
-
-    if (!info[argpos+2].IsEmpty() && info[argpos+2]->IsObject())
+    if (!info[argpos+2].IsEmpty() &&
+        !info[argpos+2]->IsFunction() &&
+        info[argpos+2]->IsObject())
     {
         auto key = Nan::New<v8::String>("version").ToLocalChecked();
         auto params = info[argpos+2].As<v8::Object>();
         auto versionObj = Nan::Get(params, key).ToLocalChecked();
         if (!versionObj.IsEmpty())
-            version = Nan::To<int64_t>(versionObj).FromJust();
+            version = get_ui64(versionObj);
         argpos++;
     }
 
     v8::Local<v8::Function> callback = info[argpos+2].As<v8::Function>();
-    auto req = new NodeVitastorRequest(callback);
+    auto req = new NodeVitastorRequest(this, callback);
 
     req->offset = offset;
-    req->len = len;
     req->version = version;
-    req->iov = { .iov_base = buf, .iov_len = req->len };
+
+    if (bufarg->IsArray())
+    {
+        auto buffers = bufarg.As<v8::Array>();
+        req->len = 0;
+        for (uint32_t i = 0; i < buffers->Length(); i++)
+        {
+            auto buffer_obj = Nan::Get(buffers, i).ToLocalChecked();
+            char *buf = node::Buffer::Data(buffer_obj);
+            uint64_t len = node::Buffer::Length(buffer_obj);
+            req->iov_list.push_back({ .iov_base = buf, .iov_len = len });
+            req->len += len;
+        }
+    }
+    else
+    {
+        char *buf = node::Buffer::Data(bufarg);
+        uint64_t len = node::Buffer::Length(bufarg);
+        req->iov = { .iov_base = buf, .iov_len = len };
+        req->len = len;
+    }
 
     return req;
 }
 
-// write(pool, inode, offset, buffer, { version }?, callback(err))
+// write(pool, inode, offset, buf: Buffer | Buffer[], { version }?, callback(err))
 NAN_METHOD(NodeVitastor::Write)
 {
     TRACE("NodeVitastor::Write");
+    if (info.Length() < 5)
+        Nan::ThrowError("Not enough arguments to write(pool, inode, offset, buf: Buffer | Buffer[], { version }?, callback(err))");
 
     NodeVitastor* self = Nan::ObjectWrap::Unwrap<NodeVitastor>(info.This());
 
-    uint64_t pool = Nan::To<int64_t>(info[0]).FromJust();
-    uint64_t inode = Nan::To<int64_t>(info[1]).FromJust();
+    uint64_t pool = get_ui64(info[0]);
+    uint64_t inode = get_ui64(info[1]);
 
-    auto req = getWriteRequest(info, 2);
+    auto req = self->get_write_request(info, 2);
 
-    std::unique_lock<std::mutex> lock(self->mu);
-    vitastor_c_write(self->c, ((pool << (64-POOL_ID_BITS)) | inode), req->offset, req->len, req->version, &req->iov, 1, on_write_finish, req);
+    self->Ref();
+    vitastor_c_write(self->c, ((pool << (64-POOL_ID_BITS)) | inode), req->offset, req->len, req->version,
+        req->iov_list.size() ? req->iov_list.data() : &req->iov,
+        req->iov_list.size() ? req->iov_list.size() : 1,
+        on_write_finish, req);
 }
 
 // sync(callback(err))
 NAN_METHOD(NodeVitastor::Sync)
 {
     TRACE("NodeVitastor::Sync");
+    if (info.Length() < 1)
+        Nan::ThrowError("Not enough arguments to sync(callback(err))");
 
     NodeVitastor* self = Nan::ObjectWrap::Unwrap<NodeVitastor>(info.This());
 
     v8::Local<v8::Function> callback = info[0].As<v8::Function>();
-    auto req = new NodeVitastorRequest(callback);
+    auto req = new NodeVitastorRequest(self, callback);
 
-    std::unique_lock<std::mutex> lock(self->mu);
+    self->Ref();
     vitastor_c_sync(self->c, on_write_finish, req);
 }
 
@@ -200,17 +239,20 @@ NAN_METHOD(NodeVitastor::Sync)
 NAN_METHOD(NodeVitastor::ReadBitmap)
 {
     TRACE("NodeVitastor::ReadBitmap");
+    if (info.Length() < 6)
+        Nan::ThrowError("Not enough arguments to read_bitmap(pool, inode, offset, len, with_parents, callback(err, bitmap_buffer))");
 
     NodeVitastor* self = Nan::ObjectWrap::Unwrap<NodeVitastor>(info.This());
 
-    uint64_t pool = Nan::To<int64_t>(info[0]).FromJust();
-    uint64_t inode = Nan::To<int64_t>(info[1]).FromJust();
-    uint64_t offset = Nan::To<int64_t>(info[2]).FromJust();
-    uint64_t len = Nan::To<int64_t>(info[3]).FromJust();
+    uint64_t pool = get_ui64(info[0]);
+    uint64_t inode = get_ui64(info[1]);
+    uint64_t offset = get_ui64(info[2]);
+    uint64_t len = get_ui64(info[3]);
     bool with_parents = Nan::To<bool>(info[4]).FromJust();
     v8::Local<v8::Function> callback = info[5].As<v8::Function>();
 
-    auto req = new NodeVitastorRequest(callback);
+    auto req = new NodeVitastorRequest(self, callback);
+    self->Ref();
     vitastor_c_read_bitmap(self->c, ((pool << (64-POOL_ID_BITS)) | inode), offset, len, with_parents, on_read_bitmap_finish, req);
 }
 
@@ -227,6 +269,7 @@ static void on_error(NodeVitastorRequest *req, Nan::Callback & nanCallback, long
 
 void NodeVitastor::on_read_finish(void *opaque, long retval, uint64_t version)
 {
+    TRACE("NodeVitastor::on_read_finish");
     Nan::HandleScope scope;
     NodeVitastorRequest *req = (NodeVitastorRequest *)opaque;
     Nan::Callback nanCallback(Nan::New(req->callback));
@@ -235,7 +278,7 @@ void NodeVitastor::on_read_finish(void *opaque, long retval, uint64_t version)
         free(req->iov.iov_base);
         nanCallback.Call(0, NULL, req);
     }
-    else if (retval < 0)
+    else if (retval < 0 || (uint64_t)retval != req->len)
     {
         free(req->iov.iov_base);
         on_error(req, nanCallback, retval);
@@ -248,20 +291,33 @@ void NodeVitastor::on_read_finish(void *opaque, long retval, uint64_t version)
         args[2] = v8::BigInt::NewFromUnsigned(v8::Isolate::GetCurrent(), version);
         nanCallback.Call(3, args, req);
     }
+    req->cli->Unref();
     delete req;
 }
 
 void NodeVitastor::on_write_finish(void *opaque, long retval)
 {
+    TRACE("NodeVitastor::on_write_finish");
     Nan::HandleScope scope;
     NodeVitastorRequest *req = (NodeVitastorRequest *)opaque;
     Nan::Callback nanCallback(Nan::New(req->callback));
-    on_error(req, nanCallback, retval);
+    if (retval < 0 || (uint64_t)retval != req->len)
+    {
+        on_error(req, nanCallback, retval);
+    }
+    else
+    {
+        v8::Local<v8::Value> args[1];
+        args[0] = Nan::Null();
+        nanCallback.Call(1, args, req);
+    }
+    req->cli->Unref();
     delete req;
 }
 
 void NodeVitastor::on_read_bitmap_finish(void *opaque, long retval, uint8_t *bitmap)
 {
+    TRACE("NodeVitastor::on_read_bitmap_finish");
     Nan::HandleScope scope;
     NodeVitastorRequest *req = (NodeVitastorRequest *)opaque;
     Nan::Callback nanCallback(Nan::New(req->callback));
@@ -276,6 +332,7 @@ void NodeVitastor::on_read_bitmap_finish(void *opaque, long retval, uint8_t *bit
         args[1] = Nan::NewBuffer((char*)bitmap, (retval+7)/8).ToLocalChecked();
         nanCallback.Call(2, args, req);
     }
+    req->cli->Unref();
     delete req;
 }
 
@@ -291,21 +348,23 @@ void NodeVitastor::on_read_bitmap_finish(void *opaque, long retval, uint8_t *bit
 NAN_METHOD(NodeVitastorImage::Create)
 {
     TRACE("NodeVitastorImage::Create");
+    if (info.Length() < 2)
+        Nan::ThrowError("Not enough arguments to Image(client, name)");
 
     v8::Local<v8::Object> parent = info[0].As<v8::Object>();
     std::string name = std::string(*Nan::Utf8String(info[1].As<v8::String>()));
     NodeVitastor *cli = Nan::ObjectWrap::Unwrap<NodeVitastor>(parent);
 
     NodeVitastorImage *img = new NodeVitastorImage();
+    img->Wrap(info.This());
+
     img->cli = cli;
     img->name = name;
 
     img->Ref();
     cli->Ref();
-    std::unique_lock<std::mutex> lock(cli->mu);
     vitastor_c_watch_inode(cli->c, (char*)img->name.c_str(), on_watch_start, img);
 
-    img->Wrap(info.This());
     info.GetReturnValue().Set(info.This());
 }
 
@@ -323,10 +382,12 @@ NodeVitastorImage::~NodeVitastorImage()
 NAN_METHOD(NodeVitastorImage::Read)
 {
     TRACE("NodeVitastorImage::Read");
+    if (info.Length() < 3)
+        Nan::ThrowError("Not enough arguments to read(offset, len, callback(err, buffer, version))");
 
     NodeVitastorImage* img = Nan::ObjectWrap::Unwrap<NodeVitastorImage>(info.This());
 
-    auto req = getReadRequest(info, 0);
+    auto req = img->cli->get_read_request(info, 0);
     req->img = img;
     req->op = NODE_VITASTOR_READ;
 
@@ -337,24 +398,29 @@ NAN_METHOD(NodeVitastorImage::Read)
 NAN_METHOD(NodeVitastorImage::Write)
 {
     TRACE("NodeVitastorImage::Write");
+    if (info.Length() < 3)
+        Nan::ThrowError("Not enough arguments to write(offset, buffer, { version }?, callback(err))");
 
     NodeVitastorImage* img = Nan::ObjectWrap::Unwrap<NodeVitastorImage>(info.This());
 
-    auto req = getWriteRequest(info, 0);
+    auto req = img->cli->get_write_request(info, 0);
     req->img = img;
     req->op = NODE_VITASTOR_WRITE;
 
     img->exec_or_wait(req);
 }
 
+// sync(callback(err))
 NAN_METHOD(NodeVitastorImage::Sync)
 {
     TRACE("NodeVitastorImage::Sync");
+    if (info.Length() < 1)
+        Nan::ThrowError("Not enough arguments to sync(callback(err))");
 
     NodeVitastorImage* img = Nan::ObjectWrap::Unwrap<NodeVitastorImage>(info.This());
 
     v8::Local<v8::Function> callback = info[0].As<v8::Function>();
-    auto req = new NodeVitastorRequest(callback);
+    auto req = new NodeVitastorRequest(img->cli, callback);
     req->img = img;
     req->op = NODE_VITASTOR_SYNC;
 
@@ -365,15 +431,17 @@ NAN_METHOD(NodeVitastorImage::Sync)
 NAN_METHOD(NodeVitastorImage::ReadBitmap)
 {
     TRACE("NodeVitastorImage::ReadBitmap");
+    if (info.Length() < 4)
+        Nan::ThrowError("Not enough arguments to read_bitmap(offset, len, with_parents, callback(err, bitmap_buffer))");
 
     NodeVitastorImage* img = Nan::ObjectWrap::Unwrap<NodeVitastorImage>(info.This());
 
-    uint64_t offset = Nan::To<int64_t>(info[0]).FromJust();
-    uint64_t len = Nan::To<int64_t>(info[1]).FromJust();
+    uint64_t offset = get_ui64(info[0]);
+    uint64_t len = get_ui64(info[1]);
     bool with_parents = Nan::To<bool>(info[2]).FromJust();
     v8::Local<v8::Function> callback = info[3].As<v8::Function>();
 
-    auto req = new NodeVitastorRequest(callback);
+    auto req = new NodeVitastorRequest(img->cli, callback);
     req->img = img;
     req->op = NODE_VITASTOR_READ_BITMAP;
     req->offset = offset;
@@ -383,14 +451,17 @@ NAN_METHOD(NodeVitastorImage::ReadBitmap)
     img->exec_or_wait(req);
 }
 
+// get_info(callback({ num, name, size, parent_id?, readonly?, meta?, mod_revision, block_size, bitmap_granularity, immediate_commit }))
 NAN_METHOD(NodeVitastorImage::GetInfo)
 {
-    TRACE("NodeVitastorImage::Sync");
+    TRACE("NodeVitastorImage::GetInfo");
+    if (info.Length() < 1)
+        Nan::ThrowError("Not enough arguments to get_info(callback({ num, name, size, parent_id?, readonly?, meta?, mod_revision, block_size, bitmap_granularity, immediate_commit }))");
 
     NodeVitastorImage* img = Nan::ObjectWrap::Unwrap<NodeVitastorImage>(info.This());
 
     v8::Local<v8::Function> callback = info[0].As<v8::Function>();
-    auto req = new NodeVitastorRequest(callback);
+    auto req = new NodeVitastorRequest(img->cli, callback);
     req->img = img;
     req->op = NODE_VITASTOR_GET_INFO;
 
@@ -412,21 +483,26 @@ void NodeVitastorImage::exec_or_wait(NodeVitastorRequest *req)
 
 void NodeVitastorImage::exec_request(NodeVitastorRequest *req)
 {
-    std::unique_lock<std::mutex> lock(cli->mu);
     if (req->op == NODE_VITASTOR_READ)
     {
         uint64_t ino = vitastor_c_inode_get_num(watch);
+        cli->Ref();
         vitastor_c_read(cli->c, ino, req->offset, req->len, &req->iov, 1, NodeVitastor::on_read_finish, req);
     }
     else if (req->op == NODE_VITASTOR_WRITE)
     {
         uint64_t ino = vitastor_c_inode_get_num(watch);
-        vitastor_c_write(cli->c, ino, req->offset, req->len, req->version, &req->iov, 1, NodeVitastor::on_write_finish, req);
+        cli->Ref();
+        vitastor_c_write(cli->c, ino, req->offset, req->len, req->version,
+            req->iov_list.size() ? req->iov_list.data() : &req->iov,
+            req->iov_list.size() ? req->iov_list.size() : 1,
+            NodeVitastor::on_write_finish, req);
     }
     else if (req->op == NODE_VITASTOR_SYNC)
     {
         uint64_t ino = vitastor_c_inode_get_num(watch);
         uint32_t imm = vitastor_c_inode_get_immediate_commit(cli->c, ino);
+        cli->Ref();
         if (imm != IMMEDIATE_ALL)
         {
             vitastor_c_sync(cli->c, NodeVitastor::on_write_finish, req);
@@ -439,6 +515,7 @@ void NodeVitastorImage::exec_request(NodeVitastorRequest *req)
     else if (req->op == NODE_VITASTOR_READ_BITMAP)
     {
         uint64_t ino = vitastor_c_inode_get_num(watch);
+        cli->Ref();
         vitastor_c_read_bitmap(cli->c, ino, req->offset, req->len, req->with_parents, NodeVitastor::on_read_bitmap_finish, req);
     }
     else if (req->op == NODE_VITASTOR_GET_INFO)
@@ -508,10 +585,14 @@ void NodeVitastorImage::on_watch_start(void *opaque, long retval)
 // NodeVitastorKV
 //////////////////////////////////////////////////
 
+Nan::Persistent<v8::Function> NodeVitastorKV::listing_class;
+
 // constructor(node_vitastor)
 NAN_METHOD(NodeVitastorKV::Create)
 {
     TRACE("NodeVitastorKV::Create");
+    if (info.Length() < 1)
+        Nan::ThrowError("Not enough arguments to new KV(client)");
 
     v8::Local<v8::Object> parent = info[0].As<v8::Object>();
     NodeVitastor *cli = Nan::ObjectWrap::Unwrap<NodeVitastor>(parent);
@@ -519,29 +600,32 @@ NAN_METHOD(NodeVitastorKV::Create)
     NodeVitastorKV *kv = new NodeVitastorKV();
     kv->cli = cli;
     {
-        std::unique_lock<std::mutex> lock(cli->mu);
         kv->dbw = new vitastorkv_dbw_t((cluster_client_t*)vitastor_c_get_internal_client(cli->c));
     }
 
     kv->Wrap(info.This());
+    cli->Ref();
     info.GetReturnValue().Set(info.This());
 }
 
 NodeVitastorKV::~NodeVitastorKV()
 {
     delete dbw;
+    cli->Unref();
 }
 
-// open(inode_id, { ...config }, callback(err))
+// open(pool_id, inode_num, { ...config }, callback(err))
 NAN_METHOD(NodeVitastorKV::Open)
 {
     TRACE("NodeVitastorKV::Open");
+    if (info.Length() < 4)
+        Nan::ThrowError("Not enough arguments to open(pool_id, inode_num, { ...config }, callback(err))");
 
     NodeVitastorKV* kv = Nan::ObjectWrap::Unwrap<NodeVitastorKV>(info.This());
 
-    uint64_t inode_id = Nan::To<int64_t>(info[0]).FromJust();
+    uint64_t inode_id = INODE_WITH_POOL(get_ui64(info[0]), get_ui64(info[1]));
 
-    v8::Local<v8::Object> jsParams = info[1].As<v8::Object>();
+    v8::Local<v8::Object> jsParams = info[2].As<v8::Object>();
     v8::Local<v8::Array> keys = Nan::GetOwnPropertyNames(jsParams).ToLocalChecked();
     std::map<std::string, std::string> cfg;
     for (uint32_t i = 0; i < keys->Length(); i++)
@@ -550,8 +634,8 @@ NAN_METHOD(NodeVitastorKV::Open)
         cfg[std::string(*Nan::Utf8String(key))] = std::string(*Nan::Utf8String(Nan::Get(jsParams, key).ToLocalChecked()));
     }
 
-    v8::Local<v8::Function> callback = info[2].As<v8::Function>();
-    auto req = new NodeVitastorRequest(callback);
+    v8::Local<v8::Function> callback = info[3].As<v8::Function>();
+    auto req = new NodeVitastorRequest(kv->cli, callback);
 
     kv->Ref();
     kv->dbw->open(inode_id, cfg, [kv, req](int res)
@@ -570,11 +654,13 @@ NAN_METHOD(NodeVitastorKV::Open)
 NAN_METHOD(NodeVitastorKV::Close)
 {
     TRACE("NodeVitastorKV::Close");
+    if (info.Length() < 1)
+        Nan::ThrowError("Not enough arguments to close(callback(err))");
 
     NodeVitastorKV* kv = Nan::ObjectWrap::Unwrap<NodeVitastorKV>(info.This());
 
     v8::Local<v8::Function> callback = info[0].As<v8::Function>();
-    auto req = new NodeVitastorRequest(callback);
+    auto req = new NodeVitastorRequest(kv->cli, callback);
 
     kv->Ref();
     kv->dbw->close([kv, req]()
@@ -591,6 +677,8 @@ NAN_METHOD(NodeVitastorKV::Close)
 NAN_METHOD(NodeVitastorKV::SetConfig)
 {
     TRACE("NodeVitastorKV::SetConfig");
+    if (info.Length() < 1)
+        Nan::ThrowError("Not enough arguments to set_config({ ...config })");
 
     NodeVitastorKV* kv = Nan::ObjectWrap::Unwrap<NodeVitastorKV>(info.This());
 
@@ -627,7 +715,7 @@ void NodeVitastorKV::get_impl(const Nan::FunctionCallbackInfo<v8::Value> & info,
     std::string key(*Nan::Utf8String(info[0].As<v8::String>()));
 
     v8::Local<v8::Function> callback = info[1].As<v8::Function>();
-    auto req = new NodeVitastorRequest(callback);
+    auto req = new NodeVitastorRequest(kv->cli, callback);
 
     kv->Ref();
     kv->dbw->get(key, [kv, req](int res, const std::string & value)
@@ -647,6 +735,8 @@ void NodeVitastorKV::get_impl(const Nan::FunctionCallbackInfo<v8::Value> & info,
 NAN_METHOD(NodeVitastorKV::Get)
 {
     TRACE("NodeVitastorKV::Get");
+    if (info.Length() < 2)
+        Nan::ThrowError("Not enough arguments to get(key, callback(err, value))");
     get_impl(info, false);
 }
 
@@ -654,6 +744,8 @@ NAN_METHOD(NodeVitastorKV::Get)
 NAN_METHOD(NodeVitastorKV::GetCached)
 {
     TRACE("NodeVitastorKV::GetCached");
+    if (info.Length() < 2)
+        Nan::ThrowError("Not enough arguments to get_cached(key, callback(err, value))");
     get_impl(info, true);
 }
 
@@ -672,10 +764,12 @@ static std::function<bool(int, const std::string &)> make_cas_callback(NodeVitas
     };
 }
 
-// set(key, value, callback(err), cas_compare(old_value))
+// set(key, value, callback(err), cas_compare(old_value)?)
 NAN_METHOD(NodeVitastorKV::Set)
 {
     TRACE("NodeVitastorKV::Set");
+    if (info.Length() < 3)
+        Nan::ThrowError("Not enough arguments to set(key, value, callback(err), cas_compare(old_value)?)");
 
     NodeVitastorKV* kv = Nan::ObjectWrap::Unwrap<NodeVitastorKV>(info.This());
 
@@ -684,13 +778,13 @@ NAN_METHOD(NodeVitastorKV::Set)
     std::string value(*Nan::Utf8String(info[1].As<v8::String>()));
 
     v8::Local<v8::Function> callback = info[2].As<v8::Function>();
-    NodeVitastorRequest *req = new NodeVitastorRequest(callback), *cas_req = NULL;
+    NodeVitastorRequest *req = new NodeVitastorRequest(kv->cli, callback), *cas_req = NULL;
 
     std::function<bool(int, const std::string &)> cas_cb;
     if (info.Length() > 3 && info[3]->IsObject())
     {
         v8::Local<v8::Function> cas_callback = info[3].As<v8::Function>();
-        cas_req = new NodeVitastorRequest(cas_callback);
+        cas_req = new NodeVitastorRequest(kv->cli, cas_callback);
         cas_cb = make_cas_callback(cas_req);
     }
 
@@ -709,10 +803,12 @@ NAN_METHOD(NodeVitastorKV::Set)
     }, cas_cb);
 }
 
-// del(key, callback(err), cas_compare(old_value))
+// del(key, callback(err), cas_compare(old_value)?)
 NAN_METHOD(NodeVitastorKV::Del)
 {
     TRACE("NodeVitastorKV::Del");
+    if (info.Length() < 2)
+        Nan::ThrowError("Not enough arguments to del(key, callback(err), cas_compare(old_value)?)");
 
     NodeVitastorKV* kv = Nan::ObjectWrap::Unwrap<NodeVitastorKV>(info.This());
 
@@ -720,13 +816,13 @@ NAN_METHOD(NodeVitastorKV::Del)
     std::string key(*Nan::Utf8String(info[0].As<v8::String>()));
 
     v8::Local<v8::Function> callback = info[1].As<v8::Function>();
-    NodeVitastorRequest *req = new NodeVitastorRequest(callback), *cas_req = NULL;
+    NodeVitastorRequest *req = new NodeVitastorRequest(kv->cli, callback), *cas_req = NULL;
 
     std::function<bool(int, const std::string &)> cas_cb;
     if (info.Length() > 2 && info[2]->IsObject())
     {
         v8::Local<v8::Function> cas_callback = info[2].As<v8::Function>();
-        cas_req = new NodeVitastorRequest(cas_callback);
+        cas_req = new NodeVitastorRequest(kv->cli, cas_callback);
         cas_cb = make_cas_callback(cas_req);
     }
 
@@ -762,6 +858,14 @@ NAN_METHOD(NodeVitastorKV::List)
     info.GetReturnValue().Set(Nan::NewInstance(cons, narg, args).ToLocalChecked());
 }
 
+/*NAN_METHOD(NodeVitastorKV::Destroy)
+{
+    TRACE("NodeVitastorKV::Destroy");
+    NodeVitastorKV* kv = Nan::ObjectWrap::Unwrap<NodeVitastorKV>(info.This());
+    if (!kv->dead)
+        kv->Unref();
+}*/
+
 //////////////////////////////////////////////////
 // NodeVitastorKVListing
 //////////////////////////////////////////////////
@@ -783,12 +887,10 @@ NAN_METHOD(NodeVitastorKVListing::Create)
 
     NodeVitastorKVListing *list = new NodeVitastorKVListing();
     list->kv = kv;
-    {
-        std::unique_lock<std::mutex> lock(kv->cli->mu);
-        list->handle = list->kv->dbw->list_start(start_key);
-    }
+    list->handle = list->kv->dbw->list_start(start_key);
 
     list->Wrap(info.This());
+    kv->Ref();
     info.GetReturnValue().Set(info.This());
 }
 
@@ -796,35 +898,54 @@ NodeVitastorKVListing::~NodeVitastorKVListing()
 {
     if (handle)
     {
-        std::unique_lock<std::mutex> lock(kv->cli->mu);
         kv->dbw->list_close(handle);
         handle = NULL;
     }
+    if (iter)
+    {
+        delete iter;
+        iter = NULL;
+    }
+    kv->Unref();
 }
 
-// next(callback(err, value))
+// next(callback(err, value)?)
 NAN_METHOD(NodeVitastorKVListing::Next)
 {
     TRACE("NodeVitastorKVListing::Next");
 
     NodeVitastorKVListing* list = Nan::ObjectWrap::Unwrap<NodeVitastorKVListing>(info.This());
 
-    v8::Local<v8::Function> callback = info[0].As<v8::Function>();
-    auto req = new NodeVitastorRequest(callback);
+    if (info.Length() > 0)
+    {
+        v8::Local<v8::Function> callback = info[0].As<v8::Function>();
+        if (list->iter)
+        {
+            delete list->iter;
+        }
+        list->iter = new NodeVitastorRequest(list->kv->cli, callback);
+    }
     if (!list->handle)
     {
         // Already closed
-        Nan::Callback nanCallback(Nan::New(req->callback));
-        v8::Local<v8::Value> args[1];
-        args[0] = Nan::New<v8::Int32>(-EINVAL);
-        nanCallback.Call(1, args, req);
-        delete req;
+        if (list->iter)
+        {
+            auto req = list->iter;
+            list->iter = NULL;
+            Nan::Callback nanCallback(Nan::New(req->callback));
+            v8::Local<v8::Value> args[1];
+            args[0] = Nan::New<v8::Int32>(-EINVAL);
+            nanCallback.Call(1, args, req);
+            delete req;
+        }
         return;
     }
 
     list->kv->Ref();
-    list->kv->dbw->list_next(list->handle, [list, req](int res, const std::string & key, const std::string & value)
+    list->kv->dbw->list_next(list->handle, [list](int res, const std::string & key, const std::string & value)
     {
+        auto req = list->iter;
+        list->iter = NULL;
         Nan::HandleScope scope;
         Nan::Callback nanCallback(Nan::New(req->callback));
         v8::Local<v8::Value> args[3];
@@ -832,7 +953,10 @@ NAN_METHOD(NodeVitastorKVListing::Next)
         args[1] = !res ? v8::Local<v8::Value>(Nan::New<v8::String>(key).ToLocalChecked()) : v8::Local<v8::Value>(Nan::Null());
         args[2] = !res ? v8::Local<v8::Value>(Nan::New<v8::String>(value).ToLocalChecked()) : v8::Local<v8::Value>(Nan::Null());
         nanCallback.Call(3, args, req);
-        delete req;
+        if (list->iter)
+            delete req;
+        else
+            list->iter = req;
         list->kv->Unref();
     });
 }
@@ -846,8 +970,12 @@ NAN_METHOD(NodeVitastorKVListing::Close)
 
     if (list->handle)
     {
-        std::unique_lock<std::mutex> lock(list->kv->cli->mu);
         list->kv->dbw->list_close(list->handle);
         list->handle = NULL;
     }
+    if (list->iter)
+    {
+        delete list->iter;
+        list->iter = NULL;
+    }
 }

node-binding/client.h

@@ -4,8 +4,6 @@
 #ifndef NODE_VITASTOR_CLIENT_H
 #define NODE_VITASTOR_CLIENT_H
 
-#include <mutex>
-
 #include <nan.h>
 #include <vitastor_c.h>
 #include <vitastor_kv.h>
@@ -19,7 +17,7 @@ public:
     static NAN_METHOD(Create);
     // read(pool, inode, offset, len, callback(err, buffer, version))
     static NAN_METHOD(Read);
-    // write(pool, inode, offset, buffer, { version }?, callback(err))
+    // write(pool, inode, offset, buf: Buffer | Buffer[], { version }?, callback(err))
     static NAN_METHOD(Write);
     // sync(callback(err))
     static NAN_METHOD(Sync);
@@ -34,8 +32,6 @@ private:
     vitastor_c *c = NULL;
     int eventfd = -1;
     uv_poll_t poll_watcher;
-    // FIXME: Is it really needed?
-    std::mutex mu;
 
     NodeVitastor();
 
@@ -44,6 +40,9 @@ private:
     static void on_write_finish(void *opaque, long retval);
     static void on_read_bitmap_finish(void *opaque, long retval, uint8_t *bitmap);
 
+    NodeVitastorRequest* get_read_request(const Nan::FunctionCallbackInfo<v8::Value> & info, int argpos);
+    NodeVitastorRequest* get_write_request(const Nan::FunctionCallbackInfo<v8::Value> & info, int argpos);
+
     friend class NodeVitastorImage;
     friend class NodeVitastorKV;
     friend class NodeVitastorKVListing;
@@ -56,7 +55,7 @@ public:
     static NAN_METHOD(Create);
     // read(offset, len, callback(err, buffer, version))
     static NAN_METHOD(Read);
-    // write(offset, buffer, { version }?, callback(err))
+    // write(offset, buf: Buffer | Buffer[], { version }?, callback(err))
     static NAN_METHOD(Write);
     // sync(callback(err))
     static NAN_METHOD(Sync);
@@ -74,8 +73,6 @@ private:
     std::vector<NodeVitastorRequest*> on_init;
     Nan::Persistent<v8::Object> cliObj;
 
-    NodeVitastorImage();
-
     static void on_watch_start(void *opaque, long retval);
     void exec_request(NodeVitastorRequest *req);
     void exec_or_wait(NodeVitastorRequest *req);
@@ -86,7 +83,7 @@ class NodeVitastorKV: public Nan::ObjectWrap
 public:
     // constructor(node_vitastor)
     static NAN_METHOD(Create);
-    // open(inode_id, { ...config }, callback(err))
+    // open(pool_id, inode_num, { ...config }, callback(err))
     static NAN_METHOD(Open);
     // set_config({ ...config })
     static NAN_METHOD(SetConfig);
@@ -98,9 +95,9 @@ public:
     static NAN_METHOD(Get);
     // get_cached(key, callback(err, value))
     static NAN_METHOD(GetCached);
-    // set(key, value, callback(err), cas_compare(old_value))
+    // set(key, value, callback(err), cas_compare(old_value)?)
     static NAN_METHOD(Set);
-    // del(key, callback(err), cas_compare(old_value))
+    // del(key, callback(err), cas_compare(old_value)?)
     static NAN_METHOD(Del);
     // list(start_key?)
     static NAN_METHOD(List);
@@ -113,8 +110,6 @@ private:
     NodeVitastor *cli = NULL;
     vitastorkv_dbw_t *dbw = NULL;
 
-    NodeVitastorKV();
-
     static void get_impl(const Nan::FunctionCallbackInfo<v8::Value> & info, bool allow_cache);
 
     friend class NodeVitastorKVListing;
@@ -125,7 +120,7 @@ class NodeVitastorKVListing: public Nan::ObjectWrap
 public:
     // constructor(node_vitastor_kv, start_key?)
     static NAN_METHOD(Create);
-    // next(callback(err, value))
+    // next(callback(err, value)?)
     static NAN_METHOD(Next);
     // close()
     static NAN_METHOD(Close);
@@ -135,8 +130,7 @@ public:
 private:
     NodeVitastorKV *kv = NULL;
     void *handle = NULL;
-
-    NodeVitastorKVListing();
+    NodeVitastorRequest *iter = NULL;
 };
 
 #endif

node-binding/index.js

@@ -0,0 +1 @@
+module.exports = require('bindings')('addon.node');

opennebula/README.md

@@ -0,0 +1 @@
+See [../docs/installation/opennebula.en.md](../docs/installation/opennebula.en.md).

opennebula/install.sh

@@ -0,0 +1,36 @@
+#!/bin/bash
+
+set -e
+
+reapply_patch() {
+	if ! [[ -e $1 ]]; then
+		echo "$1 does not exist, OpenNebula is not installed"
+	elif ! patch -f --dry-run -F 0 -R $1 < $2 >/dev/null; then
+		already_applied=0
+		if ! patch --no-backup-if-mismatch -r - -F 0 -f $1 < $2; then
+			applied_ok=0
+			echo "ERROR: Failed to patch file $1, please apply the patch $2 manually"
+		fi
+	fi
+}
+echo "Reapplying Vitastor patches to OpenNebula's oned.conf, vmm_execrc and downloader.sh"
+already_applied=1
+applied_ok=1
+reapply_patch /var/lib/one/remotes/datastore/downloader.sh /var/lib/one/remotes/datastore/vitastor/downloader-vitastor.sh.diff
+reapply_patch /etc/one/vmm_exec/vmm_execrc /var/lib/one/remotes/datastore/vitastor/vmm_execrc.diff
+if [[ -e /etc/one/oned.conf ]]; then
+	if ! /var/lib/one/remotes/datastore/vitastor/patch-oned-conf.py /etc/one/oned.conf; then
+		applied_ok=0
+		already_applied=0
+	fi
+fi
+if [[ "$already_applied" = 1 ]]; then
+	echo "OK: Vitastor OpenNebula patches are already applied"
+elif [[ "$applied_ok" = 1 ]]; then
+	echo "OK: Vitastor OpenNebula patches successfully applied"
+fi
+if [[ -f /etc/apparmor.d/local/abstractions/libvirt-qemu ]]; then
+	if ! grep -q /etc/vitastor/vitastor.conf /etc/apparmor.d/local/abstractions/libvirt-qemu; then
+		echo '  "/etc/vitastor/vitastor.conf" r,' >> /etc/apparmor.d/local/abstractions/libvirt-qemu
+	fi
+fi

opennebula/remotes/datastore/vitastor/clone

@@ -0,0 +1,76 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# This script is used to copy a VM image (SRC) to the image repository as DST
+
+# -------- Set up the environment to source common tools & conf ------------
+if [ -z "${ONE_LOCATION}" ]; then
+    LIB_LOCATION=/usr/lib/one
+else
+    LIB_LOCATION=$ONE_LOCATION/lib
+fi
+
+. $LIB_LOCATION/sh/scripts_common.sh
+
+DRIVER_PATH=$(dirname $0)
+source ${DRIVER_PATH}/../libfs.sh
+
+# -------- Get cp and datastore arguments from OpenNebula core ------------
+
+DRV_ACTION=`cat -`
+ID=$1
+
+XPATH="${DRIVER_PATH}/../xpath.rb -b $DRV_ACTION"
+
+unset i XPATH_ELEMENTS
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <($XPATH \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/BASE_PATH \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/BRIDGE_LIST \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/POOL_NAME \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/IMAGE_PREFIX \
+    /DS_DRIVER_ACTION_DATA/IMAGE/PATH \
+    /DS_DRIVER_ACTION_DATA/IMAGE/SIZE \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/VITASTOR_CONF)
+
+unset i
+
+BASE_PATH="${XPATH_ELEMENTS[i++]}"
+BRIDGE_LIST="${XPATH_ELEMENTS[i++]}"
+POOL_NAME="${XPATH_ELEMENTS[i++]}"
+IMAGE_PREFIX="${XPATH_ELEMENTS[i++]:-one}"
+SRC="${XPATH_ELEMENTS[i++]}"
+SIZE="${XPATH_ELEMENTS[i++]}"
+VITASTOR_CONF="${XPATH_ELEMENTS[i++]}"
+
+DST_HOST=`get_destination_host $ID`
+
+if [ -z "$DST_HOST" ]; then
+    error_message "Datastore template missing 'BRIDGE_LIST' attribute."
+    exit -1
+fi
+
+CLI=vitastor-cli
+if [ -n "$VITASTOR_CONF" ]; then
+    CLI="$CLI --config_path ${VITASTOR_CONF}"
+fi
+if [ -n "$POOL_NAME" ]; then
+    CLI="$CLI --pool ${POOL_NAME}"
+fi
+
+SAFE_DIRS=""
+
+DST="${IMAGE_PREFIX}-${ID}"
+
+ssh_exec_and_log "$DST_HOST" "$CLI create --parent $SRC $DST" \
+    "Error during $CLI create --parent $SRC $DST in $DST_HOST"
+
+ssh_exec_and_log "$DST_HOST" "$CLI flatten $DST" \
+    "Error during $CLI create flatten $DST in $DST_HOST"
+
+echo "$DST raw"

opennebula/remotes/datastore/vitastor/cp

@@ -0,0 +1,135 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# This script is used to copy a local image SRC to the image repository as DST
+
+# -------- Set up the environment to source common tools & conf ------------
+
+if [ -z "${ONE_LOCATION}" ]; then
+    LIB_LOCATION=/usr/lib/one
+else
+    LIB_LOCATION=$ONE_LOCATION/lib
+fi
+
+. $LIB_LOCATION/sh/scripts_common.sh
+
+DRIVER_PATH=$(dirname $0)
+source ${DRIVER_PATH}/../libfs.sh
+
+# -------- Get cp and datastore arguments from OpenNebula core ------------
+
+DRV_ACTION=`cat -`
+ID=$1
+
+export DRV_ACTION
+
+UTILS_PATH="${DRIVER_PATH}/.."
+
+XPATH="$UTILS_PATH/xpath.rb -b $DRV_ACTION"
+
+unset i XPATH_ELEMENTS
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <($XPATH \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/BASE_PATH \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/RESTRICTED_DIRS \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/SAFE_DIRS \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/BRIDGE_LIST \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/POOL_NAME \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/IMAGE_PREFIX \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/STAGING_DIR \
+    /DS_DRIVER_ACTION_DATA/IMAGE/PATH \
+    /DS_DRIVER_ACTION_DATA/IMAGE/SIZE \
+    /DS_DRIVER_ACTION_DATA/IMAGE/TEMPLATE/MD5 \
+    /DS_DRIVER_ACTION_DATA/IMAGE/TEMPLATE/SHA1 \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/NO_DECOMPRESS \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/LIMIT_TRANSFER_BW \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/VITASTOR_CONF)
+
+unset i
+
+BASE_PATH="${XPATH_ELEMENTS[i++]}"
+RESTRICTED_DIRS="${XPATH_ELEMENTS[i++]}"
+SAFE_DIRS="${XPATH_ELEMENTS[i++]}"
+BRIDGE_LIST="${XPATH_ELEMENTS[i++]}"
+POOL_NAME="${XPATH_ELEMENTS[i++]}"
+IMAGE_PREFIX="${XPATH_ELEMENTS[i++]:-one}"
+STAGING_DIR="${XPATH_ELEMENTS[i++]:-/var/tmp}"
+SRC="${XPATH_ELEMENTS[i++]}"
+SIZE="${XPATH_ELEMENTS[i++]}"
+MD5="${XPATH_ELEMENTS[i++]}"
+SHA1="${XPATH_ELEMENTS[i++]}"
+NO_DECOMPRESS="${XPATH_ELEMENTS[i++]}"
+LIMIT_TRANSFER_BW="${XPATH_ELEMENTS[i++]}"
+VITASTOR_CONF="${XPATH_ELEMENTS[i++]}"
+
+DST_HOST=`get_destination_host $ID`
+
+if [ -z "$DST_HOST" ]; then
+    error_message "Datastore template missing 'BRIDGE_LIST' attribute."
+    exit -1
+fi
+
+CLI=vitastor-cli
+QEMU_ARG=""
+if [ -n "$VITASTOR_CONF" ]; then
+    CLI="$CLI --config_path ${VITASTOR_CONF}"
+    QEMU_ARG=":config_path=${VITASTOR_CONF}"
+fi
+if [ -n "$POOL_NAME" ]; then
+    CLI="$CLI --pool ${POOL_NAME}"
+fi
+
+set_up_datastore "$BASE_PATH" "$RESTRICTED_DIRS" "$SAFE_DIRS"
+
+IMAGE_HASH=`generate_image_hash`
+TMP_DST="$STAGING_DIR/$IMAGE_HASH"
+
+DST="${IMAGE_PREFIX}-${ID}"
+
+DOWNLOADER_ARGS=`set_downloader_args "$MD5" "$SHA1" "$NO_DECOMPRESS" "$LIMIT_TRANSFER_BW" "$SRC" -`
+
+COPY_COMMAND="$UTILS_PATH/downloader.sh $DOWNLOADER_ARGS"
+
+case $SRC in
+http://*|https://*)
+    log "Downloading $SRC to the image repository"
+
+    DUMP="$COPY_COMMAND"
+    ;;
+
+*)
+    if [ `check_restricted $SRC` -eq 1 ]; then
+        log_error "Not allowed to copy images from $RESTRICTED_DIRS"
+        error_message "Not allowed to copy image file $SRC"
+        exit -1
+    fi
+
+    log "Copying local image $SRC to the image repository"
+
+    DUMP="$COPY_COMMAND"
+    ;;
+esac
+
+multiline_exec_and_log "set -e -o pipefail; $DUMP | $SSH $DST_HOST $DD of=$TMP_DST bs=1M" \
+    "Error copying $SRC to $DST_HOST:$TMP_DST"
+
+REGISTER_CMD=$(cat <<EOF
+    set -e -o pipefail
+
+    SIZE=\$($QEMU_IMG info --output json "$TMP_DST" | jq -r '.["virtual-size"]')
+    $CLI create -s \$SIZE "$DST"
+    $QEMU_IMG convert -O raw "$TMP_DST" "vitastor:image=$DST$QEMU_ARG"
+
+    # remove original
+    $RM -f $TMP_DST
+EOF
+)
+
+ssh_exec_and_log "$DST_HOST" "$REGISTER_CMD" "Error registering $DST in $DST_HOST"
+
+echo "$DST raw"

opennebula/remotes/datastore/vitastor/downloader-patched.sh

@@ -0,0 +1,555 @@
+#!/bin/bash
+
+# -------------------------------------------------------------------------- #
+# Copyright 2002-2023, OpenNebula Project, OpenNebula Systems                #
+#                                                                            #
+# Licensed under the Apache License, Version 2.0 (the "License"); you may    #
+# not use this file except in compliance with the License. You may obtain    #
+# a copy of the License at                                                   #
+#                                                                            #
+# http://www.apache.org/licenses/LICENSE-2.0                                 #
+#                                                                            #
+# Unless required by applicable law or agreed to in writing, software        #
+# distributed under the License is distributed on an "AS IS" BASIS,          #
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.   #
+# See the License for the specific language governing permissions and        #
+# limitations under the License.                                             #
+#--------------------------------------------------------------------------- #
+
+if [ -z "${ONE_LOCATION}" ]; then
+    LIB_LOCATION=/usr/lib/one
+    VAR_LOCATION=/var/lib/one
+else
+    LIB_LOCATION=$ONE_LOCATION/lib
+    VAR_LOCATION=$ONE_LOCATION/var
+fi
+
+. $LIB_LOCATION/sh/scripts_common.sh
+
+DRIVER_PATH=$(dirname $0)
+
+# Escape single quotes
+function esc_sq
+{
+    echo "$1" | sed -e "s/'/'\\\''/g"
+}
+
+# Execute a command (first parameter) and use the first kb of stdout
+# to determine the file type
+function get_type
+{
+    if [ "$NO_DECOMPRESS" = "yes" ]; then
+        echo "application/octet-stream"
+    else
+        command=$1
+
+        ( eval "$command" | head -n 1024 | file -b --mime-type - ) 2>/dev/null
+    fi
+}
+
+# Gets the command needed to decompress an stream.
+function get_decompressor
+{
+    type=$1
+
+    case "$type" in
+    "application/x-gzip"|"application/gzip")
+        echo "gunzip -c -"
+        ;;
+    "application/x-bzip2")
+        echo "bunzip2 -qc -"
+        ;;
+    "application/x-xz")
+        echo "unxz -c -"
+        ;;
+    *)
+        echo "cat"
+        ;;
+    esac
+}
+
+# Function called to decompress a stream. The first parameter is the command
+# used to decompress the stream. Second parameter is the output file or
+# - for stdout.
+function decompress
+{
+    command="$1"
+    to="$2"
+
+    if [ "$to" = "-" ]; then
+        $command
+    else
+        $command > "$to"
+    fi
+}
+
+# Function called to hash a stream. First parameter is the algorithm name.
+function hasher
+{
+    if [ -n "$1" ]; then
+        openssl dgst -$1 | awk '{print $NF}' > $HASH_FILE
+    else
+        # Needs something consuming stdin or the pipe will break
+        cat >/dev/null
+    fi
+}
+
+# Unarchives a tar or a zip a file to a directory with the same name.
+function unarchive
+{
+    TO="$1"
+
+    file_type=$(get_type "cat $TO")
+
+    tmp="$TO"
+
+    # Add full path if it is relative
+    if [ ${tmp:0:1} != "/" ]; then
+        tmp="$PWD/$tmp"
+    fi
+
+    IN="$tmp.tmp"
+    OUT="$tmp"
+
+    case "$file_type" in
+    "application/x-tar")
+        command="tar -xf $IN -C $OUT"
+        ;;
+    "application/zip")
+        command="unzip -d $OUT $IN"
+        ;;
+    *)
+        command=""
+        ;;
+    esac
+
+    if [ -n "$command" ]; then
+        mv "$OUT" "$IN"
+        mkdir "$OUT"
+
+        $command
+
+        if [ "$?" != "0" ]; then
+            echo "Error uncompressing archive" >&2
+            exit -1
+        fi
+
+        rm "$IN"
+    fi
+}
+
+function s3_env
+{
+    XPATH="$DRIVER_PATH/xpath.rb -b $DRV_ACTION"
+
+    unset i j XPATH_ELEMENTS
+
+    while IFS= read -r -d '' element; do
+        XPATH_ELEMENTS[i++]="$element"
+    done < <($XPATH     /DS_DRIVER_ACTION_DATA/MARKETPLACE/TEMPLATE/ACCESS_KEY_ID \
+                        /DS_DRIVER_ACTION_DATA/MARKETPLACE/TEMPLATE/SECRET_ACCESS_KEY \
+                        /DS_DRIVER_ACTION_DATA/MARKETPLACE/TEMPLATE/REGION \
+                        /DS_DRIVER_ACTION_DATA/MARKETPLACE/TEMPLATE/AWS \
+                        /DS_DRIVER_ACTION_DATA/MARKETPLACE/TEMPLATE/ENDPOINT)
+
+    S3_ACCESS_KEY_ID="${XPATH_ELEMENTS[j++]}"
+    S3_SECRET_ACCESS_KEY="${XPATH_ELEMENTS[j++]}"
+    S3_REGION="${XPATH_ELEMENTS[j++]}"
+    S3_AWS="${XPATH_ELEMENTS[j++]}"
+    S3_ENDPOINT="${XPATH_ELEMENTS[j++]}"
+
+    CURRENT_DATE_DAY="$(date -u '+%Y%m%d')"
+    CURRENT_DATE_ISO8601="${CURRENT_DATE_DAY}T$(date -u '+%H%M%S')Z"
+}
+
+# Create an SHA-256 hash in hexadecimal.
+# Usage:
+#   hash_sha256 <string>
+function hash_sha256 {
+  printf "${1}" | openssl dgst -sha256 | sed 's/^.* //'
+}
+
+# Create an SHA-256 hmac in hexadecimal.
+# Usage:
+#   hmac_sha256 <key> <data>
+function hmac_sha256 {
+  printf "${2}" | openssl dgst -sha256 -mac HMAC -macopt "${1}" | sed 's/^.* //'
+}
+
+# Create the signature.
+# Usage:
+#   create_signature
+function create_signature {
+    stringToSign="AWS4-HMAC-SHA256\n${CURRENT_DATE_ISO8601}\n${CURRENT_DATE_DAY}/${S3_REGION}/s3/aws4_request\n$(hash_sha256 "${HTTP_CANONICAL_REQUEST}")"
+    dateKey=$(hmac_sha256 key:"AWS4${S3_SECRET_ACCESS_KEY}" "${CURRENT_DATE_DAY}")
+    regionKey=$(hmac_sha256 hexkey:"${dateKey}" "${S3_REGION}")
+    serviceKey=$(hmac_sha256 hexkey:"${regionKey}" "s3")
+    signingKey=$(hmac_sha256 hexkey:"${serviceKey}" "aws4_request")
+
+    printf "${stringToSign}" | openssl dgst -sha256 -mac HMAC -macopt hexkey:"${signingKey}" | sed 's/.*(stdin)= //'
+}
+
+function s3_curl_args
+{
+    FROM="$1"
+
+    ENDPOINT="$S3_ENDPOINT"
+    OBJECT=$(basename "$FROM")
+    BUCKET=$(basename $(dirname "$FROM"))
+
+    DATE="`date -u +'%a, %d %b %Y %H:%M:%S GMT'`"
+    AUTH_STRING="GET\n\n\n${DATE}\n/${BUCKET}/${OBJECT}"
+
+    SIGNED_AUTH_STRING=`echo -en "$AUTH_STRING" | \
+                        openssl sha1 -hmac ${S3_SECRET_ACCESS_KEY} -binary | \
+                        base64`
+
+    echo " -H \"Date: ${DATE}\"" \
+         " -H \"Authorization: AWS ${S3_ACCESS_KEY_ID}:${SIGNED_AUTH_STRING}\"" \
+         " '$(esc_sq "${ENDPOINT}/${BUCKET}/${OBJECT}")'"
+}
+
+function s3_curl_args_aws
+{
+    FROM="$1"
+
+    OBJECT=$(basename "$FROM")
+    BUCKET=$(basename "$(dirname "$FROM")")
+
+    ENDPOINT="$BUCKET.s3.amazonaws.com"
+
+    AWS_S3_PATH="$(echo $OBJECT | sed 's;^\([^/]\);/\1;')"
+
+    HTTP_REQUEST_PAYLOAD_HASH="$(echo "" | openssl dgst -sha256 | sed 's/^.* //')"
+    HTTP_CANONICAL_REQUEST_URI="${AWS_S3_PATH}"
+    HTTP_REQUEST_CONTENT_TYPE='application/octet-stream'
+
+    HTTP_CANONICAL_REQUEST_HEADERS="content-type:${HTTP_REQUEST_CONTENT_TYPE}
+host:${ENDPOINT}
+x-amz-content-sha256:${HTTP_REQUEST_PAYLOAD_HASH}
+x-amz-date:${CURRENT_DATE_ISO8601}"
+
+    HTTP_REQUEST_SIGNED_HEADERS="content-type;host;x-amz-content-sha256;x-amz-date"
+HTTP_CANONICAL_REQUEST="GET
+${HTTP_CANONICAL_REQUEST_URI}\n
+${HTTP_CANONICAL_REQUEST_HEADERS}\n
+${HTTP_REQUEST_SIGNED_HEADERS}
+${HTTP_REQUEST_PAYLOAD_HASH}"
+
+    SIGNATURE="$(create_signature)"
+    HTTP_REQUEST_AUTHORIZATION_HEADER="AWS4-HMAC-SHA256 Credential=${S3_ACCESS_KEY_ID}/${CURRENT_DATE_DAY}/${S3_REGION}/s3/aws4_request, SignedHeaders=${HTTP_REQUEST_SIGNED_HEADERS}, Signature=${SIGNATURE}"
+
+    echo " -H \"Authorization: ${HTTP_REQUEST_AUTHORIZATION_HEADER}\"" \
+         " -H \"content-type: ${HTTP_REQUEST_CONTENT_TYPE}\"" \
+         " -H \"x-amz-content-sha256: ${HTTP_REQUEST_PAYLOAD_HASH}\"" \
+         " -H \"x-amz-date: ${CURRENT_DATE_ISO8601}\"" \
+         " \"https://${ENDPOINT}${HTTP_CANONICAL_REQUEST_URI}\""
+}
+
+function get_rbd_cmd
+{
+    local i j URL_ELEMENTS
+
+    FROM="$1"
+
+    URL_RB="$DRIVER_PATH/url.rb"
+
+    while IFS= read -r -d '' element; do
+        URL_ELEMENTS[i++]="$element"
+    done < <($URL_RB    "$FROM" \
+                        USER \
+                        HOST \
+                        SOURCE \
+                        PARAM_DS \
+                        PARAM_CEPH_USER \
+                        PARAM_CEPH_KEY \
+                        PARAM_CEPH_CONF)
+
+    USER="${URL_ELEMENTS[j++]}"
+    DST_HOST="${URL_ELEMENTS[j++]}"
+    SOURCE="${URL_ELEMENTS[j++]}"
+    DS="${URL_ELEMENTS[j++]}"
+    CEPH_USER="${URL_ELEMENTS[j++]}"
+    CEPH_KEY="${URL_ELEMENTS[j++]}"
+    CEPH_CONF="${URL_ELEMENTS[j++]}"
+
+    # Remove leading '/'
+    SOURCE="${SOURCE#/}"
+
+    if [ -n "$USER" ]; then
+        DST_HOST="$USER@$DST_HOST"
+    fi
+
+    if [ -n "$CEPH_USER" ]; then
+        RBD="$RBD --id '$(esc_sq "${CEPH_USER}")'"
+    fi
+
+    if [ -n "$CEPH_KEY" ]; then
+        RBD="$RBD --keyfile '$(esc_sq "${CEPH_KEY}")'"
+    fi
+
+    if [ -n "$CEPH_CONF" ]; then
+        RBD="$RBD --conf '$(esc_sq "${CEPH_CONF}")'"
+    fi
+
+    echo "ssh '$(esc_sq "$DST_HOST")' \"$RBD export '$(esc_sq "$SOURCE")' -\""
+}
+
+function get_vitastor_cmd
+{
+    local i j URL_ELEMENTS
+
+    FROM="$1"
+
+    URL_RB="$DRIVER_PATH/url.rb"
+
+    while IFS= read -r -d '' element; do
+        URL_ELEMENTS[i++]="$element"
+    done < <($URL_RB    "$FROM" \
+                        USER \
+                        HOST \
+                        SOURCE \
+                        PARAM_DS \
+                        PARAM_VITASTOR_CONF)
+
+    USER="${URL_ELEMENTS[j++]}"
+    DST_HOST="${URL_ELEMENTS[j++]}"
+    SOURCE="${URL_ELEMENTS[j++]}"
+    DS="${URL_ELEMENTS[j++]}"
+    VITASTOR_CONF="${URL_ELEMENTS[j++]}"
+
+    # Remove leading '/'
+    SOURCE="${SOURCE#/}"
+
+    if [ -n "$USER" ]; then
+        DST_HOST="$USER@$DST_HOST"
+    fi
+
+    local CLI
+    CLI="vitastor-cli"
+    if [ -n "$VITASTOR_CONF" ]; then
+        CLI="$CLI --config_path '$(esc_sq "${VITASTOR_CONF}")'"
+    fi
+
+    echo "ssh '$(esc_sq "$DST_HOST")' \"$CLI dd iimg='$(esc_sq "$SOURCE")'\""
+}
+
+# Compare 2 version strings using sort -V
+# Usage:
+#   verlte "3.2.9" "3.4.0"
+function verlte() {
+    [  "$1" = "`echo -e "$1\n$2" | sort -V | head -n1`" ]
+}
+
+# Returns curl retry options based on its version
+function curl_retry_args {
+    [ "$NO_RETRY" = "yes" ] && return
+
+    RETRY_ARGS="--retry 3 --retry-delay 3"
+
+    CURL_VER=`curl --version | grep -o 'curl [0-9\.]*' | awk '{print $2}'`
+
+    # To retry also on conn-reset-by-peer fresh curl is needed
+    if verlte "7.71.0" "$CURL_VER" && [ -z ${MAX_SIZE} ] ; then
+        RETRY_ARGS+=" --retry-all-errors"
+    fi
+
+    echo $RETRY_ARGS
+}
+
+TEMP=`getopt -o m:s:l:c:no -l md5:,sha1:,limit:,max-size:,nodecomp,noretry -- "$@"`
+
+if [ $? != 0 ] ; then
+    echo "Arguments error" >&2
+    exit -1
+fi
+
+eval set -- "$TEMP"
+
+while true; do
+    case "$1" in
+        -m|--md5)
+            HASH_TYPE=md5
+            HASH=$2
+            shift 2
+            ;;
+        -s|--sha1)
+            HASH_TYPE=sha1
+            HASH=$2
+            shift 2
+            ;;
+        -n|--nodecomp)
+            export NO_DECOMPRESS="yes"
+            shift
+            ;;
+        -l|--limit)
+            export LIMIT_RATE="$2"
+            shift 2
+            ;;
+        -c|--max-size)
+            export MAX_SIZE="$2"
+            shift 2
+            ;;
+        -o|--noretry)
+            export NO_RETRY="yes"
+            shift
+            ;;
+        --)
+            shift
+            break
+            ;;
+        *)
+            shift
+            ;;
+    esac
+done
+
+FROM="$1"
+TO="$2"
+
+if [ -n "${HASH_TYPE}" -a -n "${MAX_SIZE}" ]; then
+    echo "Hash check not supported for partial downloads" >&2
+    exit -1
+else
+    # File used by the hasher function to store the resulting hash
+    export HASH_FILE="/tmp/downloader.hash.$$"
+fi
+
+GLOBAL_CURL_ARGS="--fail -sS -k -L $(curl_retry_args)"
+
+case "$FROM" in
+http://*|https://*)
+    # -k  so it does not check the certificate
+    # -L  to follow redirects
+    # -sS to hide output except on failure
+    # --limit_rate to limit the bw
+    curl_args="$GLOBAL_CURL_ARGS '$(esc_sq "${FROM}")'"
+
+    if [ -n "$LIMIT_RATE" ]; then
+        curl_args="--limit-rate $LIMIT_RATE $curl_args"
+    fi
+
+    command="curl $curl_args"
+    ;;
+ssh://*)
+    # pseudo-url for ssh transfers ssh://user@host:path
+    # -l to limit the bw
+    ssh_src=${FROM#ssh://}
+    ssh_arg=(${ssh_src/:/ })
+
+    rmt_cmd="\"cat '$(esc_sq "${ssh_arg[1]}")'\""
+
+    command="ssh ${ssh_arg[0]} $rmt_cmd"
+    ;;
+s3://*)
+    # Read s3 environment
+    s3_env
+
+    if [ -z "$S3_ACCESS_KEY_ID" -o -z "$S3_SECRET_ACCESS_KEY" ]; then
+        echo "S3_ACCESS_KEY_ID and S3_SECRET_ACCESS_KEY are required" >&2
+        exit -1
+    fi
+
+    curl_args=""
+
+    if [[ "$S3_AWS" =~ (no|NO) ]]; then
+        curl_args="$(s3_curl_args "$FROM")"
+    else
+        curl_args="$(s3_curl_args_aws "$FROM")"
+    fi
+
+    command="curl $GLOBAL_CURL_ARGS $curl_args"
+    ;;
+rbd://*)
+    command="$(get_rbd_cmd "$FROM")"
+    ;;
+vitastor://*)
+    command="$(get_vitastor_cmd "$FROM")"
+    ;;
+vcenter://*)
+    command="$VAR_LOCATION/remotes/datastore/vcenter_downloader.rb '$(esc_sq "$FROM")'"
+    ;;
+lxd://*)
+    file_type="application/octet-stream"
+    command="$VAR_LOCATION/remotes/datastore/lxd_downloader.sh \"$FROM\""
+    ;;
+restic://*)
+    eval `$VAR_LOCATION/remotes/datastore/restic_downloader.rb "$FROM" | grep -e '^command=' -e '^clean_command='`
+    ;;
+rsync://*)
+    eval `$VAR_LOCATION/remotes/datastore/rsync_downloader.rb "$FROM" | grep -e '^command=' -e '^clean_command='`
+    ;;
+*)
+    if [ ! -r $FROM ]; then
+        echo "Cannot read from $FROM" >&2
+        exit -1
+    fi
+    command="cat '$(esc_sq "$FROM")'"
+    ;;
+esac
+
+[ -z "$file_type" ] && file_type=$(get_type "$command")
+decompressor=$(get_decompressor "$file_type")
+
+if [ -z "${MAX_SIZE}" ]; then
+    eval "$command" | \
+        tee >( hasher $HASH_TYPE) | \
+        decompress "$decompressor" "$TO"
+
+    if [ "$?" != "0" -o "$PIPESTATUS" != "0" ]; then
+        echo "Error copying" >&2
+        exit -1
+    fi
+else
+    # Order of the 'head' command is here on purpose:
+    # 1. We want to download more bytes than needed to get a requested
+    #    number of bytes on the output. Decompressor may need more
+    #    data to decompress the stream.
+    # 2. Decompressor command is also misused to detect SIGPIPE error.
+    eval "$command" | \
+        decompress "$decompressor" "$TO" 2>/dev/null | \
+        head -c "${MAX_SIZE}"
+
+    # Following table shows exit codes of each command
+    # in the pipe for various scenarios:
+    #
+    # ----------------------------------------------------
+    # | $COMMAND | TYPE          | PIPESTATUS | BEHAVIOUR
+    # ----------------------------------------------------
+    # | cat      | partial       | 141 141  0 | OK
+    # | cat      | full          |   0   0  0 | OK
+    # | cat      | error         |   1   0  0 | fail
+    # | curl     | partial       |  23 141  0 | OK
+    # | curl     | full          |   0   0  0 | OK
+    # | curl     | error         |  22   0  0 | fail
+    # | ssh      | partial       | 255 141  0 | OK
+    # | ssh      | full          |   0   0  0 | OK
+    # | ssh      | error ssh     | 255   0  0 | fail
+    # | ssh      | error ssh cat |   1   0  0 | fail
+    if [ \( "${PIPESTATUS[0]}" != '0' -a "${PIPESTATUS[1]}" = '0' \) \
+         -o \( "${PIPESTATUS[1]}" != '0' -a "${PIPESTATUS[1]}" != '141' \) \
+         -o \( "${PIPESTATUS[2]}" != "0" \) ];
+    then
+        echo "Error copying" >&2
+        exit -1
+    fi
+fi
+
+if [ -n "$HASH_TYPE" ]; then
+    HASH_RESULT=$( cat $HASH_FILE)
+    rm $HASH_FILE
+    if [ "$HASH_RESULT" != "$HASH" ]; then
+        echo "Hash does not match" >&2
+        exit -1
+    fi
+fi
+
+# Unarchive only if the destination is filesystem
+if [ "$TO" != "-" ]; then
+    unarchive "$TO"
+fi
+
+# Perform any clean operation
+if [ -n "${clean_command}" ]; then
+    eval "$clean_command"
+fi

opennebula/remotes/datastore/vitastor/downloader-vitastor.sh.diff

@@ -0,0 +1,60 @@
+diff --git /var/lib/one/remotes/datastore/downloader.sh /var/lib/one/remotes/datastore/downloader.sh
+index 9b75d8ee4b..09d2a5d41d 100755
+--- /var/lib/one/remotes/datastore/downloader.sh
++++ /var/lib/one/remotes/datastore/downloader.sh
+@@ -295,6 +295,45 @@ function get_rbd_cmd
+     echo "ssh '$(esc_sq "$DST_HOST")' \"$RBD export '$(esc_sq "$SOURCE")' -\""
+ }
+ 
++function get_vitastor_cmd
++{
++    local i j URL_ELEMENTS
++
++    FROM="$1"
++
++    URL_RB="$DRIVER_PATH/url.rb"
++
++    while IFS= read -r -d '' element; do
++        URL_ELEMENTS[i++]="$element"
++    done < <($URL_RB    "$FROM" \
++                        USER \
++                        HOST \
++                        SOURCE \
++                        PARAM_DS \
++                        PARAM_VITASTOR_CONF)
++
++    USER="${URL_ELEMENTS[j++]}"
++    DST_HOST="${URL_ELEMENTS[j++]}"
++    SOURCE="${URL_ELEMENTS[j++]}"
++    DS="${URL_ELEMENTS[j++]}"
++    VITASTOR_CONF="${URL_ELEMENTS[j++]}"
++
++    # Remove leading '/'
++    SOURCE="${SOURCE#/}"
++
++    if [ -n "$USER" ]; then
++        DST_HOST="$USER@$DST_HOST"
++    fi
++
++    local CLI
++    CLI="vitastor-cli"
++    if [ -n "$VITASTOR_CONF" ]; then
++        CLI="$CLI --config_path '$(esc_sq "${VITASTOR_CONF}")'"
++    fi
++
++    echo "ssh '$(esc_sq "$DST_HOST")' \"$CLI dd iimg='$(esc_sq "$SOURCE")'\""
++}
++
+ # Compare 2 version strings using sort -V
+ # Usage:
+ #   verlte "3.2.9" "3.4.0"
+@@ -424,6 +463,9 @@ s3://*)
+ rbd://*)
+     command="$(get_rbd_cmd "$FROM")"
+     ;;
++vitastor://*)
++    command="$(get_vitastor_cmd "$FROM")"
++    ;;
+ vcenter://*)
+     command="$VAR_LOCATION/remotes/datastore/vcenter_downloader.rb '$(esc_sq "$FROM")'"
+     ;;

opennebula/remotes/datastore/vitastor/export

@@ -0,0 +1,114 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# This script is used to export an image to qcow2 file
+
+# ------------ Set up the environment to source common tools ------------
+
+if [ -z "${ONE_LOCATION}" ]; then
+    LIB_LOCATION=/usr/lib/one
+else
+    LIB_LOCATION=$ONE_LOCATION/lib
+fi
+
+. $LIB_LOCATION/sh/scripts_common.sh
+
+DRIVER_PATH=$(dirname $0)
+source ${DRIVER_PATH}/../libfs.sh
+
+# -------- Get rm and datastore arguments from OpenNebula core ------------
+
+DRV_ACTION=`cat -`
+ID=$1
+
+XPATH="${DRIVER_PATH}/../xpath.rb -b $DRV_ACTION"
+
+unset i XPATH_ELEMENTS
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <($XPATH \
+    /DS_DRIVER_ACTION_DATA/IMAGE/SOURCE \
+    /DS_DRIVER_ACTION_DATA/IMAGE/SIZE \
+    /DS_DRIVER_ACTION_DATA/IMAGE/TEMPLATE/MD5 \
+    /DS_DRIVER_ACTION_DATA/IMAGE/TEMPLATE/SHA1 \
+    /DS_DRIVER_ACTION_DATA/IMAGE/TEMPLATE/FORMAT \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/BRIDGE_LIST \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/VITASTOR_CONF)
+
+unset i
+
+SRC="${XPATH_ELEMENTS[i++]}"
+SIZE="${XPATH_ELEMENTS[i++]}"
+MD5="${XPATH_ELEMENTS[i++]}"
+SHA1="${XPATH_ELEMENTS[i++]}"
+FORMAT="${XPATH_ELEMENTS[i++]:-raw}"
+BRIDGE_LIST="${XPATH_ELEMENTS[i++]}"
+VITASTOR_CONF="${XPATH_ELEMENTS[i++]}"
+
+DST_HOST=`get_destination_host $ID`
+
+if [ -z "$DST_HOST" ]; then
+    error_message "Datastore template missing 'BRIDGE_LIST' attribute."
+    exit -1
+fi
+
+IMPORT_SOURCE="vitastor://$DST_HOST/$SRC"
+IS_JOIN="?"
+
+CLI=vitastor-cli
+if [ -n "$VITASTOR_CONF" ]; then
+    CLI="$CLI --config_path $VITASTOR_CONF"
+    IMPORT_SOURCE="${IMPORT_SOURCE}${IS_JOIN}VITASTOR_CONF=${VITASTOR_CONF}"
+fi
+
+# FIXME: this is inefficient - it pipes the image twice...
+
+INFO_SCRIPT=$(cat <<EOF
+if [ -z "$MD5" ]; then
+    CHECKSUM=\$(
+        $CLI dd iimg=${SRC} | ${MD5SUM} | cut -f1 -d' '
+        ps=\$PIPESTATUS
+
+        if [ "\$ps" != "0" ]; then
+            exit \$ps
+        fi
+    )
+
+    status=\$?
+
+    [ "\$status" != "0" ] && exit \$status
+else
+    CHECKSUM="$MD5"
+fi
+
+if [ -z "\$CHECKSUM" ]; then
+    exit 1
+fi
+
+cat <<EOT
+<MD5><![CDATA[\$CHECKSUM]]></MD5>
+<SIZE><![CDATA[$SIZE]]></SIZE>
+<FORMAT><![CDATA[${FORMAT}]]></FORMAT>
+EOT
+EOF
+)
+
+INFO=$(ssh_monitor_and_log "$DST_HOST" "$INFO_SCRIPT" "Image info script" 2>&1)
+INFO_STATUS=$?
+
+if [ "$INFO_STATUS" != "0" ]; then
+    echo "$INFO"
+    exit $INFO_STATUS
+fi
+
+cat <<EOF
+<IMPORT_INFO>
+    <IMPORT_SOURCE><![CDATA[$IMPORT_SOURCE]]></IMPORT_SOURCE>
+    $INFO
+    <DISPOSE>NO</DISPOSE>
+</IMPORT_INFO>"
+EOF

opennebula/remotes/datastore/vitastor/mkfs

@@ -0,0 +1,124 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# This script is used to create a VM image (SRC) of size (SIZE) and formatted as (FS)
+
+# -------- Set up the environment to source common tools & conf ------------
+
+if [ -z "${ONE_LOCATION}" ]; then
+    LIB_LOCATION=/usr/lib/one
+else
+    LIB_LOCATION=$ONE_LOCATION/lib
+fi
+
+. $LIB_LOCATION/sh/scripts_common.sh
+
+DRIVER_PATH=$(dirname $0)
+source ${DRIVER_PATH}/../libfs.sh
+source ${DRIVER_PATH}/../../etc/datastore/datastore.conf
+
+# -------- Get mkfs and datastore arguments from OpenNebula core ------------
+
+DRV_ACTION=`cat -`
+ID=$1
+
+XPATH="${DRIVER_PATH}/../xpath.rb -b $DRV_ACTION"
+
+unset i XPATH_ELEMENTS
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <($XPATH \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/BASE_PATH \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/RESTRICTED_DIRS \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/SAFE_DIRS \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/BRIDGE_LIST \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/POOL_NAME \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/IMAGE_PREFIX \
+    /DS_DRIVER_ACTION_DATA/IMAGE/FORMAT \
+    /DS_DRIVER_ACTION_DATA/IMAGE/SIZE \
+    /DS_DRIVER_ACTION_DATA/IMAGE/FS \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/VITASTOR_CONF)
+
+unset i
+
+BASE_PATH="${XPATH_ELEMENTS[i++]}"
+RESTRICTED_DIRS="${XPATH_ELEMENTS[i++]}"
+SAFE_DIRS="${XPATH_ELEMENTS[i++]}"
+BRIDGE_LIST="${XPATH_ELEMENTS[i++]}"
+POOL_NAME="${XPATH_ELEMENTS[i++]}"
+IMAGE_PREFIX="${XPATH_ELEMENTS[i++]:-one}"
+FORMAT="${XPATH_ELEMENTS[i++]}"
+SIZE="${XPATH_ELEMENTS[i++]}"
+FS="${XPATH_ELEMENTS[i++]}"
+VITASTOR_CONF="${XPATH_ELEMENTS[i++]}"
+
+DST_HOST=`get_destination_host $ID`
+
+if [ -z "$DST_HOST" ]; then
+    error_message "Datastore template missing 'BRIDGE_LIST' attribute."
+    exit -1
+fi
+
+CLI=
+if [ -n "$VITASTOR_CONF" ]; then
+    CLI="$CLI --config_path ${VITASTOR_CONF}"
+fi
+if [ -n "$POOL_NAME" ]; then
+    CLI="$CLI --pool ${POOL_NAME}"
+fi
+
+set_up_datastore "$BASE_PATH" "$RESTRICTED_DIRS" "$SAFE_DIRS"
+
+IMAGE_NAME="${IMAGE_PREFIX}-${ID}"
+
+# ------------ Image to save_as disk, no need to create a new image ------------
+
+if [ "$FORMAT" = "save_as" ]; then
+    echo "$IMAGE_NAME"
+    exit 0
+fi
+
+# ------------ Create the image in the repository ------------
+
+# FIXME: Duplicate code with tm/vitastor/mkimage
+
+MKIMAGE_CMD=$(cat <<EOF
+    set -e -o pipefail
+    export PATH=/usr/sbin:/sbin:\$PATH
+    vitastor-cli $CLI create --pool "${POOL_NAME}" "$IMAGE_NAME" --size "${SIZE}M"
+EOF
+)
+
+if [ -n "$FS" -o "$FORMAT" = "swap" ]; then
+    MKFS_CMD=`mkfs_command '$NBD' raw "$SIZE" "$SUPPORTED_FS" "$FS" "$FS_OPTS" | grep -v $QEMU_IMG`
+fi
+
+MKIMAGE_CMD=$(cat <<EOF
+    set -e -o pipefail
+    export PATH=/usr/sbin:/sbin:\$PATH
+    vitastor-cli $CLI create --pool "${POOL_NAME}" "$IMAGE_NAME" --size "${SIZE}M"
+EOF
+)
+if [ ! -z $FS ]; then
+    set -e -o pipefail
+
+    IMAGE_HASH=`generate_image_hash`
+    FS_OPTS=$(eval $(echo "echo \$FS_OPTS_$FS"))
+
+    MKFS_CMD=`mkfs_command '$NBD' raw "$SIZE" "$SUPPORTED_FS" "$FS" "$FS_OPTS" | grep -v $QEMU_IMG`
+    MKIMAGE_CMD=$(cat <<EOF
+    $MKIMAGE_CMD
+    NBD=\$(sudo vitastor-nbd $CLI map --image "$IMAGE_NAME")
+    trap "sudo vitastor-nbd $CLI unmap \$NBD" EXIT
+    $MKFS_CMD
+EOF
+)
+fi
+
+ssh_exec_and_log "$DST_HOST" "$MKIMAGE_CMD" "Error registering $IMAGE_NAME in $DST_HOST"
+
+echo "$IMAGE_NAME"

opennebula/remotes/datastore/vitastor/monitor

@@ -0,0 +1,64 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# This script is used to monitor the free and used space of a datastore
+
+# -------- Set up the environment to source common tools & conf ------------
+
+if [ -z "${ONE_LOCATION}" ]; then
+    LIB_LOCATION=/usr/lib/one
+else
+    LIB_LOCATION=$ONE_LOCATION/lib
+fi
+
+. $LIB_LOCATION/sh/scripts_common.sh
+
+DRIVER_PATH=$(dirname $0)
+source ${DRIVER_PATH}/../../datastore/libfs.sh
+
+# -------- Get datastore arguments from OpenNebula core ------------
+
+DRV_ACTION=`cat -`
+ID=$1
+
+XPATH="${DRIVER_PATH}/../../datastore/xpath.rb -b $DRV_ACTION"
+
+unset i j XPATH_ELEMENTS
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <($XPATH \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/BRIDGE_LIST \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/POOL_NAME \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/VITASTOR_CONF)
+
+BRIDGE_LIST="${XPATH_ELEMENTS[j++]}"
+POOL_NAME="${XPATH_ELEMENTS[j++]}"
+VITASTOR_CONF="${XPATH_ELEMENTS[j++]}"
+
+HOST=`get_destination_host`
+
+if [ -z "$HOST" ]; then
+    error_message "Datastore template missing 'BRIDGE_LIST' attribute."
+    exit -1
+fi
+
+CLI=vitastor-cli
+if [ -n "$VITASTOR_CONF" ]; then
+    CLI="$CLI --config_path ${VITASTOR_CONF}"
+fi
+
+# ------------ Compute datastore usage -------------
+
+MONITOR_SCRIPT=$(cat <<EOF
+vitastor-cli df --json | jq -r '.[] | select(.name == "${POOL_NAME}") |
+    "TOTAL_MB="+(.total_raw/.raw_to_usable/1024/1024 | tostring)+
+    "\nUSED_MB="+(.used_raw/.raw_to_usable/1024/1024 | tostring)+
+    "\nFREE_MB="+(.max_available/1024/1024 | tostring)'
+EOF
+)
+
+ssh_monitor_and_log $HOST "$MONITOR_SCRIPT 2>&1" "Error monitoring ${POOL_NAME} in $HOST"

opennebula/remotes/datastore/vitastor/oned.conf.diff

@@ -0,0 +1,73 @@
+diff --git /etc/one/oned.conf /etc/one/oned.conf
+index be02d646a8..27f876ec36 100644
+--- /etc/one/oned.conf
++++ /etc/one/oned.conf
+@@ -481,7 +481,7 @@ VM_MAD = [
+     NAME           = "kvm",
+     SUNSTONE_NAME  = "KVM",
+     EXECUTABLE     = "one_vmm_exec",
+-    ARGUMENTS      = "-t 15 -r 0 kvm -p",
++    ARGUMENTS      = "-t 15 -r 0 kvm -p -l deploy=deploy.vitastor",
+     DEFAULT        = "vmm_exec/vmm_exec_kvm.conf",
+     TYPE           = "kvm",
+     KEEP_SNAPSHOTS = "yes",
+@@ -592,7 +592,7 @@ VM_MAD = [
+ 
+ TM_MAD = [
+     EXECUTABLE = "one_tm",
+-    ARGUMENTS = "-t 15 -d dummy,lvm,shared,fs_lvm,fs_lvm_ssh,qcow2,ssh,ceph,dev,vcenter,iscsi_libvirt"
++    ARGUMENTS = "-t 15 -d dummy,lvm,shared,fs_lvm,fs_lvm_ssh,qcow2,ssh,ceph,vitastor,dev,vcenter,iscsi_libvirt"
+ ]
+ 
+ #*******************************************************************************
+@@ -612,7 +612,7 @@ TM_MAD = [
+ 
+ DATASTORE_MAD = [
+     EXECUTABLE = "one_datastore",
+-    ARGUMENTS  = "-t 15 -d dummy,fs,lvm,ceph,dev,iscsi_libvirt,vcenter,restic,rsync -s shared,ssh,ceph,fs_lvm,fs_lvm_ssh,qcow2,vcenter"
++    ARGUMENTS  = "-t 15 -d dummy,fs,lvm,ceph,vitastor,dev,iscsi_libvirt,vcenter,restic,rsync -s shared,ssh,ceph,vitastor,fs_lvm,fs_lvm_ssh,qcow2,vcenter"
+ ]
+ 
+ #*******************************************************************************
+@@ -1050,6 +1050,9 @@ INHERIT_DATASTORE_ATTR  = "VCENTER_DS_IMAGE_DIR"
+ INHERIT_DATASTORE_ATTR  = "VCENTER_DS_VOLATILE_DIR"
+ INHERIT_DATASTORE_ATTR  = "VCENTER_INSTANCE_ID"
+ 
++INHERIT_DATASTORE_ATTR  = "VITASTOR_CONF"
++INHERIT_DATASTORE_ATTR  = "IMAGE_PREFIX"
++
+ INHERIT_IMAGE_ATTR      = "DISK_TYPE"
+ INHERIT_IMAGE_ATTR      = "VCENTER_ADAPTER_TYPE"
+ INHERIT_IMAGE_ATTR      = "VCENTER_DISK_TYPE"
+@@ -1180,6 +1183,14 @@ TM_MAD_CONF = [
+     CLONE_TARGET_SHARED = "SELF", DISK_TYPE_SHARED = "RBD"
+ ]
+ 
++TM_MAD_CONF = [
++    NAME = "vitastor", LN_TARGET = "NONE", CLONE_TARGET = "SELF", SHARED = "YES",
++    DS_MIGRATE = "NO", DRIVER = "raw", ALLOW_ORPHANS="format",
++    TM_MAD_SYSTEM = "ssh,shared", LN_TARGET_SSH = "SYSTEM", CLONE_TARGET_SSH = "SYSTEM",
++    DISK_TYPE_SSH = "FILE", LN_TARGET_SHARED = "NONE",
++    CLONE_TARGET_SHARED = "SELF", DISK_TYPE_SHARED = "FILE"
++]
++
+ TM_MAD_CONF = [
+     NAME = "iscsi_libvirt", LN_TARGET = "NONE", CLONE_TARGET = "SELF", SHARED = "YES",
+     DS_MIGRATE = "NO", DRIVER = "raw"
+@@ -1263,9 +1274,16 @@ DS_MAD_CONF = [
+     NAME = "ceph",
+     REQUIRED_ATTRS = "DISK_TYPE,BRIDGE_LIST",
+     PERSISTENT_ONLY = "NO",
+     MARKETPLACE_ACTIONS = "export"
++]
++
++DS_MAD_CONF = [
++    NAME = "vitastor",
++    REQUIRED_ATTRS = "DISK_TYPE,BRIDGE_LIST",
++    PERSISTENT_ONLY = "NO",
++    MARKETPLACE_ACTIONS = "export"
+ ]
+ 
+ DS_MAD_CONF = [
+     NAME = "dev", REQUIRED_ATTRS = "DISK_TYPE", PERSISTENT_ONLY = "YES"
+ ]

opennebula/remotes/datastore/vitastor/patch-oned-conf.py

@@ -0,0 +1,115 @@
+#!/usr/bin/env python3
+# Patch /etc/one/oned.conf for Vitastor support
+# -s = also enable save.vitastor/restore.vitastor overrides
+
+import re
+import os
+import sys
+
+class Fixer:
+    save_restore = 0
+
+    def require_sub_cb(self, m, cb):
+        self.found = 1
+        return cb(m)
+
+    def require_sub(self, regexp, cb, text, error):
+        self.found = 0
+        new_text = re.sub(regexp, lambda m: self.require_sub_cb(m, cb), text)
+        if not self.found and error:
+            self.errors.append(error)
+        return new_text
+
+    def fix(self, oned_conf):
+        self.errors = []
+        self.kvm_found = 0
+        oned_conf = self.require_sub(r'((?:^|\n)[ \t]*VM_MAD\s*=\s*\[)([^\]]+)\]', lambda m: m.group(1)+self.fix_vm_mad(m.group(2))+']', oned_conf, 'VM_MAD not found')
+        if not self.kvm_found:
+            self.errors.append("VM_MAD[NAME=kvm].ARGUMENTS not found")
+        oned_conf = self.require_sub(r'((?:^|\n)[ \t]*TM_MAD\s*=\s*\[)([^\]]+)\]', lambda m: m.group(1)+self.fix_tm_mad(m.group(2))+']', oned_conf, 'TM_MAD not found')
+        oned_conf = self.require_sub(r'((?:^|\n)[ \t]*DATASTORE_MAD\s*=\s*\[)([^\]]+)\]', lambda m: m.group(1)+self.fix_datastore_mad(m.group(2))+']', oned_conf, 'DATASTORE_MAD not found')
+        if oned_conf[-1:] != '\n':
+            oned_conf += '\n'
+        if not re.compile(r'(^|\n)[ \t]*INHERIT_DATASTORE_ATTR\s*=\s*"VITASTOR_CONF"').search(oned_conf):
+            oned_conf += '\nINHERIT_DATASTORE_ATTR="VITASTOR_CONF"\n'
+        if not re.compile(r'(^|\n)[ \t]*INHERIT_DATASTORE_ATTR\s*=\s*"IMAGE_PREFIX"').search(oned_conf):
+            oned_conf += '\nINHERIT_DATASTORE_ATTR="IMAGE_PREFIX"\n'
+        if not re.compile(r'(^|\n)[ \t]*TM_MAD_CONF\s*=\s*\[[^\]]*NAME\s*=\s*"vitastor"').search(oned_conf):
+            oned_conf += ('\nTM_MAD_CONF = [\n'+
+                '    NAME = "vitastor", LN_TARGET = "NONE", CLONE_TARGET = "SELF", SHARED = "YES",\n'+
+                '    DS_MIGRATE = "NO", DRIVER = "raw", ALLOW_ORPHANS="format",\n'+
+                '    TM_MAD_SYSTEM = "ssh,shared", LN_TARGET_SSH = "SYSTEM", CLONE_TARGET_SSH = "SYSTEM",\n'+
+                '    DISK_TYPE_SSH = "FILE", LN_TARGET_SHARED = "NONE",\n'+
+                '    CLONE_TARGET_SHARED = "SELF", DISK_TYPE_SHARED = "FILE"\n'+
+                ']\n')
+        if not re.compile(r'(^|\n)[ \t]*DS_MAD_CONF\s*=\s*\[[^\]]*NAME\s*=\s*"vitastor"').search(oned_conf):
+            oned_conf += ('\nDS_MAD_CONF = [\n'+
+                '    NAME = "vitastor",\n'+
+                '    REQUIRED_ATTRS = "DISK_TYPE,BRIDGE_LIST",\n'+
+                '    PERSISTENT_ONLY = "NO",\n'+
+                '    MARKETPLACE_ACTIONS = "export"\n'+
+                ']\n')
+        return oned_conf
+
+    def fix_vm_mad(self, vm_mad_params):
+        if re.compile(r'\bNAME\s*=\s*"kvm"').search(vm_mad_params):
+            vm_mad_params = re.sub(r'\b(ARGUMENTS\s*=\s*")([^"]+)"', lambda m: m.group(1)+self.fix_vm_mad_args(m.group(2))+'"', vm_mad_params)
+            self.kvm_found = 1
+        return vm_mad_params
+
+    def fix_vm_mad_args(self, args):
+        args = self.fix_vm_mad_override(args, 'deploy')
+        if self.save_restore:
+            args = self.fix_vm_mad_override(args, 'save')
+            args = self.fix_vm_mad_override(args, 'restore')
+        return args
+
+    def fix_vm_mad_override(self, args, override):
+        m = re.compile(r'-l (\S+)').search(args)
+        if m and re.compile(override+'='+override+'.vitastor').search(m.group(1)):
+            return args
+        elif m and re.compile(override+'=').search(m.group(1)):
+            self.errors.append(override+"= is already overridden in -l option in VM_MAD[NAME=kvm].ARGUMENTS")
+            return args
+        elif m:
+            return self.require_sub(r'-l (\S+)', lambda m: '-l '+m.group(1)+','+override+'='+override+'.vitastor', args, '-l option not found in VM_MAD[NAME=kvm].ARGUMENTS')
+        else:
+            return args+' -l '+override+'='+override+'.vitastor'
+
+    def fix_tm_mad(self, params):
+        return self.require_sub(r'\b(ARGUMENTS\s*=\s*")([^"]+)"', lambda m: m.group(1)+self.fix_tm_mad_args('d', m.group(2), "TM_MAD")+'"', params, "TM_MAD.ARGUMENTS not found")
+
+    def fix_tm_mad_args(self, opt, args, v):
+        return self.require_sub('(-'+opt+r') (\S+)', lambda m: self.fix_tm_mad_arg(m), args, "-"+opt+" option not found in "+v+".ARGUMENTS")
+
+    def fix_tm_mad_arg(self, m):
+        a = m.group(2).split(',')
+        if 'vitastor' not in a:
+            a += [ 'vitastor' ]
+        return m.group(1)+' '+(','.join(a))
+
+    def fix_datastore_mad(self, params):
+        params = self.require_sub(r'\b(ARGUMENTS\s*=\s*")([^"]+)"', lambda m: m.group(1)+self.fix_tm_mad_args('d', m.group(2), "DATASTORE_MAD")+'"', params, "DATASTORE_MAD.ARGUMENTS not found")
+        return self.require_sub(r'\b(ARGUMENTS\s*=\s*")([^"]+)"', lambda m: m.group(1)+self.fix_tm_mad_args('s', m.group(2), "DATASTORE_MAD")+'"', params, "")
+
+fixer = Fixer()
+oned_conf_file = ''
+for arg in sys.argv[1:]:
+    if arg == '-s':
+        fixer.save_restore = 1
+    else:
+        oned_conf_file = arg
+        break
+if not oned_conf_file:
+    sys.stderr.write("USAGE: ./patch-oned-conf.py [-s] /etc/one/oned.conf\n-s means also enable save.vitastor/restore.vitastor overrides\n")
+    sys.exit(1)
+with open(oned_conf_file, 'r') as fd:
+    oned_conf = fd.read()
+new_conf = fixer.fix(oned_conf)
+if new_conf != oned_conf:
+    os.rename(oned_conf_file, oned_conf_file+'.bak')
+    with open(oned_conf_file, 'w') as fd:
+        fd.write(new_conf)
+if len(fixer.errors) > 0:
+    sys.stderr.write("ERROR: Failed to patch "+oned_conf_file+", patch it manually. Errors:\n- "+('\n- '.join(fixer.errors))+'\n')
+    sys.exit(1)

opennebula/remotes/datastore/vitastor/rm

@@ -0,0 +1,63 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# This script is used to remove a VM image from the image repository
+
+# ------------ Set up the environment to source common tools ------------
+if [ -z "${ONE_LOCATION}" ]; then
+    LIB_LOCATION=/usr/lib/one
+else
+    LIB_LOCATION=$ONE_LOCATION/lib
+fi
+
+. $LIB_LOCATION/sh/scripts_common.sh
+
+DRIVER_PATH=$(dirname $0)
+
+source ${DRIVER_PATH}/../libfs.sh
+
+# -------- Get rm and datastore arguments from OpenNebula core ------------
+
+DRV_ACTION=`cat -`
+ID=$1
+
+XPATH="${DRIVER_PATH}/../xpath.rb -b $DRV_ACTION"
+
+unset i j XPATH_ELEMENTS
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <($XPATH \
+    /DS_DRIVER_ACTION_DATA/IMAGE/SOURCE \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/BRIDGE_LIST \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/VITASTOR_CONF)
+
+IMAGE_NAME="${XPATH_ELEMENTS[j++]}"
+BRIDGE_LIST="${XPATH_ELEMENTS[j++]}"
+VITASTOR_CONF="${XPATH_ELEMENTS[j++]}"
+
+DST_HOST=`get_destination_host $ID`
+
+if [ -z "$DST_HOST" ]; then
+    error_message "Datastore template missing 'BRIDGE_LIST' attribute."
+    exit -1
+fi
+
+CLI=vitastor-cli
+if [ -n "$VITASTOR_CONF" ]; then
+    CLI="$CLI --config_path ${VITASTOR_CONF}"
+fi
+
+# -------- Remove Image from Datastore ------------
+
+log "Removing $IMAGE_NAME from the image repository in $DST_HOST"
+
+DELETE_CMD=$(cat <<EOF
+    $CLI rm $IMAGE_NAME
+EOF
+)
+
+ssh_exec_and_log "$DST_HOST" "$DELETE_CMD" "Error deleting $IMAGE_NAME in $DST_HOST"

opennebula/remotes/datastore/vitastor/snap_delete

@@ -0,0 +1,64 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# This script is used to delete a snapshot of an image
+
+# -------- Set up the environment to source common tools & conf ------------
+
+if [ -z "${ONE_LOCATION}" ]; then
+    LIB_LOCATION=/usr/lib/one
+else
+    LIB_LOCATION=$ONE_LOCATION/lib
+fi
+
+. $LIB_LOCATION/sh/scripts_common.sh
+
+DRIVER_PATH=$(dirname $0)
+
+source ${DRIVER_PATH}/../libfs.sh
+
+# -------- Get image and datastore arguments from OpenNebula core ------------
+
+DRV_ACTION=`cat -`
+ID=$1
+
+XPATH="${DRIVER_PATH}/../xpath.rb -b $DRV_ACTION"
+
+unset i XPATH_ELEMENTS
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <($XPATH \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/BRIDGE_LIST \
+    /DS_DRIVER_ACTION_DATA/IMAGE/SOURCE \
+    /DS_DRIVER_ACTION_DATA/IMAGE/TARGET_SNAPSHOT \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/VITASTOR_CONF)
+
+unset i
+
+BRIDGE_LIST="${XPATH_ELEMENTS[i++]}"
+IMAGE_NAME="${XPATH_ELEMENTS[i++]}"
+SNAP_ID="${XPATH_ELEMENTS[i++]}"
+VITASTOR_CONF="${XPATH_ELEMENTS[i++]}"
+
+DST_HOST=`get_destination_host $ID`
+
+if [ -z "$DST_HOST" ]; then
+    error_message "Datastore template missing 'BRIDGE_LIST' attribute."
+    exit -1
+fi
+
+CLI=vitastor-cli
+if [ -n "$VITASTOR_CONF" ]; then
+    CLI="$CLI --config_path ${VITASTOR_CONF}"
+fi
+
+SNAP_DELETE_CMD=$(cat <<EOF
+    $CLI rm ${IMAGE_NAME}@${SNAP_ID}
+EOF
+)
+
+ssh_exec_and_log "$DST_HOST" "$SNAP_DELETE_CMD" "Error deleting snapshot $IMAGE_NAME-$SNAP_ID@$SNAP_ID"

opennebula/remotes/datastore/vitastor/snap_flatten

@@ -0,0 +1,69 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# This script is used to flatten a snapshot of a persistent image
+
+# -------- Set up the environment to source common tools & conf ------------
+
+if [ -z "${ONE_LOCATION}" ]; then
+    LIB_LOCATION=/usr/lib/one
+else
+    LIB_LOCATION=$ONE_LOCATION/lib
+fi
+
+. $LIB_LOCATION/sh/scripts_common.sh
+
+DRIVER_PATH=$(dirname $0)
+
+source ${DRIVER_PATH}/../libfs.sh
+
+# -------- Get image and datastore arguments from OpenNebula core ------------
+
+DRV_ACTION=`cat -`
+ID=$1
+
+XPATH="${DRIVER_PATH}/../xpath.rb -b $DRV_ACTION"
+
+unset i XPATH_ELEMENTS
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <($XPATH \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/BRIDGE_LIST \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/POOL_NAME \
+    /DS_DRIVER_ACTION_DATA/IMAGE/SOURCE \
+    /DS_DRIVER_ACTION_DATA/IMAGE/TARGET_SNAPSHOT \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/VITASTOR_CONF)
+
+unset i
+
+BRIDGE_LIST="${XPATH_ELEMENTS[i++]}"
+POOL_NAME="${XPATH_ELEMENTS[i++]}"
+IMAGE_NAME="${XPATH_ELEMENTS[i++]}"
+SNAP_ID="${XPATH_ELEMENTS[i++]}"
+VITASTOR_CONF="${XPATH_ELEMENTS[i++]}"
+
+DST_HOST=`get_destination_host $ID`
+
+if [ -z "$DST_HOST" ]; then
+    error_message "Datastore template missing 'BRIDGE_LIST' attribute."
+    exit -1
+fi
+
+CLI=vitastor-cli
+if [ -n "$VITASTOR_CONF" ]; then
+    CLI="$CLI --config_path ${VITASTOR_CONF}"
+fi
+
+SNAP_FLATTEN_CMD=$(cat <<EOF
+    set -e
+    $CLI flatten "$IMAGE_NAME@$SNAP_ID"
+    $CLI modify "$IMAGE_NAME@$SNAP_ID" --rename "$IMAGE_NAME"
+    $CLI rm --matching "$IMAGE_NAME@*"
+EOF
+)
+
+ssh_exec_and_log "$DST_HOST" "$SNAP_FLATTEN_CMD" "Error flattening snapshot $SNAP_ID for $IMAGE_NAME"

opennebula/remotes/datastore/vitastor/snap_revert

@@ -0,0 +1,72 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# This script is used to revert a snapshot of an image
+
+# -------- Set up the environment to source common tools & conf ------------
+
+if [ -z "${ONE_LOCATION}" ]; then
+    LIB_LOCATION=/usr/lib/one
+else
+    LIB_LOCATION=$ONE_LOCATION/lib
+fi
+
+. $LIB_LOCATION/sh/scripts_common.sh
+
+DRIVER_PATH=$(dirname $0)
+
+source ${DRIVER_PATH}/../libfs.sh
+
+# -------- Get image and datastore arguments from OpenNebula core ------------
+
+DRV_ACTION=`cat -`
+ID=$1
+
+XPATH="${DRIVER_PATH}/../xpath.rb -b $DRV_ACTION"
+
+unset i XPATH_ELEMENTS
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <($XPATH \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/BRIDGE_LIST \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/POOL_NAME \
+    /DS_DRIVER_ACTION_DATA/IMAGE/SOURCE \
+    /DS_DRIVER_ACTION_DATA/IMAGE/TARGET_SNAPSHOT \
+    /DS_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/VITASTOR_CONF)
+
+unset i
+
+BRIDGE_LIST="${XPATH_ELEMENTS[i++]}"
+POOL_NAME="${XPATH_ELEMENTS[i++]}"
+IMAGE_NAME="${XPATH_ELEMENTS[i++]}"
+SNAP_ID="${XPATH_ELEMENTS[i++]}"
+VITASTOR_CONF="${XPATH_ELEMENTS[i++]}"
+
+DST_HOST=`get_destination_host $ID`
+
+if [ -z "$DST_HOST" ]; then
+    error_message "Datastore template missing 'BRIDGE_LIST' attribute."
+    exit -1
+fi
+
+CLI=vitastor-cli
+if [ -n "$VITASTOR_CONF" ]; then
+    CLI="$CLI --config_path ${VITASTOR_CONF}"
+fi
+if [ -n "$POOL_NAME" ]; then
+    CLI="$CLI --pool ${POOL_NAME}"
+fi
+
+SNAP_REVERT_CMD=$(cat <<EOF
+    $CLI rm ${IMAGE_NAME}.flatten || true
+    $CLI create --pool "${POOL_NAME}" --parent ${IMAGE_NAME}@${SNAP_ID} ${IMAGE_NAME}.flatten
+    $CLI rm ${IMAGE_NAME} || true
+    $CLI modify ${IMAGE_NAME}.flatten --rename ${IMAGE_NAME}
+EOF
+)
+
+ssh_exec_and_log "$DST_HOST" "$SNAP_REVERT_CMD" "Error reverting snapshot $SNAP_ID for $IMAGE_NAME"

opennebula/remotes/datastore/vitastor/stat

@@ -0,0 +1 @@
+../ceph/stat

opennebula/remotes/datastore/vitastor/vmm_execrc.diff

@@ -0,0 +1,12 @@
+diff --git /etc/one/vmm_exec/vmm_execrc /etc/one/vmm_exec/vmm_execrc
+index e210526e63..cb51d3b5e8 100644
+--- /etc/one/vmm_exec/vmm_execrc
++++ /etc/one/vmm_exec/vmm_execrc
+@@ -1,6 +1,6 @@
+ # Space separated list of VMM-TM pairs that support live disk snapshots. VMM
+ # and TM must be separated by '-'
+-LIVE_DISK_SNAPSHOTS="kvm-qcow2 kvm-shared kvm-ceph kvm-ssh qemu-qcow2 qemu-shared qemu-ceph qemu-ssh"
++LIVE_DISK_SNAPSHOTS="kvm-qcow2 kvm-shared kvm-ceph kvm-vitastor kvm-ssh qemu-qcow2 qemu-shared qemu-ceph qemu-ssh"
+ 
+ # Space separated list VNM_MAD-ACTION pairs that run locally
+ VNMAD_LOCAL_ACTIONS="elastic-post elastic-clean"

opennebula/remotes/tm/vitastor/clone

@@ -0,0 +1,97 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# clone fe:SOURCE host:remote_system_ds/disk.i size
+#   - fe is the front-end hostname
+#   - SOURCE is the path of the disk image in the form DS_BASE_PATH/disk
+#   - host is the target host to deploy the VM
+#   - remote_system_ds is the path for the system datastore in the host
+
+SRC=$1
+DST=$2
+VM_ID=$3
+DS_ID=$4
+
+#--------------------------------------------------------------------------------
+
+if [ -z "${ONE_LOCATION}" ]; then
+    TMCOMMON=/var/lib/one/remotes/tm/tm_common.sh
+    LIB_LOCATION=/usr/lib/one
+else
+    TMCOMMON=$ONE_LOCATION/var/remotes/tm/tm_common.sh
+    LIB_LOCATION=$ONE_LOCATION/lib
+fi
+
+DRIVER_PATH=$(dirname $0)
+
+source $TMCOMMON
+
+#-------------------------------------------------------------------------------
+# Compute the destination image name
+#-------------------------------------------------------------------------------
+
+DST_HOST=`arg_host $DST`
+
+SRC_PATH=`arg_path $SRC`
+DST_PATH=`arg_path $DST`
+
+DST_DIR=`dirname $DST_PATH`
+
+DISK_ID=$(echo $DST|awk -F. '{print $NF}')
+VM_DST="${SRC_PATH}-${VM_ID}-${DISK_ID}"
+DST_DS_ID=`echo $DST | sed s#//*#/#g | awk -F/ '{print $(NF-2)}'`
+
+#-------------------------------------------------------------------------------
+# Get Image information
+#-------------------------------------------------------------------------------
+
+XPATH="${DRIVER_PATH}/../../datastore/xpath.rb --stdin"
+
+unset i j XPATH_ELEMENTS
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <(onevm show -x $VM_ID | $XPATH  \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/VITASTOR_CONF \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/SIZE)
+
+VITASTOR_CONF="${XPATH_ELEMENTS[j++]}"
+SIZE="${XPATH_ELEMENTS[j++]}"
+
+#-------------------------------------------------------------------------------
+# Get Datastore information
+#-------------------------------------------------------------------------------
+
+unset i j XPATH_ELEMENTS
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <(onedatastore show -x $DST_DS_ID | $XPATH \
+    /DATASTORE/TEMPLATE/POOL_NAME)
+
+POOL_NAME="${XPATH_ELEMENTS[j++]}"
+
+disable_local_monitoring $DST_HOST $DST_DIR
+
+#-------------------------------------------------------------------------------
+# Clone the image
+#-------------------------------------------------------------------------------
+
+CLI=vitastor-cli
+if [ -n "$VITASTOR_CONF" ]; then
+    CLI="$CLI --config_path ${VITASTOR_CONF}"
+fi
+if [ -n "$POOL_NAME" ]; then
+    CLI="$CLI --pool ${POOL_NAME}"
+fi
+
+CLONE_CMD=$(cat <<EOF
+    $CLI create --parent $SRC_PATH --size ${SIZE}M $VM_DST
+EOF
+)
+
+ssh_exec_and_log "$DST_HOST" "$CLONE_CMD" "Error cloning $SRC_PATH to $VM_DST in $DST_HOST"
+exit 0

opennebula/remotes/tm/vitastor/context

@@ -0,0 +1 @@
+../ceph/context

opennebula/remotes/tm/vitastor/cpds

@@ -0,0 +1,113 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# cpds host:remote_system_ds/disk.i fe:SOURCE snapid vmid dsid
+#   - fe is the front-end hostname
+#   - SOURCE is the path of the disk image in the form DS_BASE_PATH/disk
+#   - host is the target host to deploy the VM
+#   - remote_system_ds is the path for the system datastore in the host
+#   - snapid is the snapshot id. "-1" for none
+
+SRC=$1
+DST=$2
+SNAP_ID=$3
+VM_ID=$4
+DS_ID=$5
+
+#--------------------------------------------------------------------------------
+
+if [ -z "${ONE_LOCATION}" ]; then
+    TMCOMMON=/var/lib/one/remotes/tm/tm_common.sh
+    LIB_LOCATION=/usr/lib/one
+else
+    TMCOMMON=$ONE_LOCATION/var/remotes/tm/tm_common.sh
+    LIB_LOCATION=$ONE_LOCATION/lib
+fi
+
+DRIVER_PATH=$(dirname $0)
+
+source $TMCOMMON
+source ${DRIVER_PATH}/../../datastore/libfs.sh
+source ${DRIVER_PATH}/../../etc/vmm/kvm/kvmrc
+
+#-------------------------------------------------------------------------------
+# Set dst path and dir
+#-------------------------------------------------------------------------------
+
+SRC_HOST=`arg_host $SRC`
+SRC_PATH=`arg_path $SRC`
+
+#-------------------------------------------------------------------------------
+# Get Image information
+#-------------------------------------------------------------------------------
+
+DISK_ID=$(echo "$SRC_PATH" | $AWK -F. '{print $NF}')
+
+XPATH="${DRIVER_PATH}/../../datastore/xpath.rb --stdin"
+
+unset i j XPATH_ELEMENTS
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <(onevm show -x $VM_ID | $XPATH \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/SOURCE \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/CLONE \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/VITASTOR_CONF \
+    /VM/LCM_STATE)
+
+SRC_IMAGE="${XPATH_ELEMENTS[j++]}"
+CLONE="${XPATH_ELEMENTS[j++]}"
+VITASTOR_CONF="${XPATH_ELEMENTS[j++]}"
+LCM_STATE="${XPATH_ELEMENTS[j++]}"
+
+#-------------------------------------------------------------------------------
+# Get Datastore information
+#-------------------------------------------------------------------------------
+
+unset i j XPATH_ELEMENTS
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <(onedatastore show -x $DS_ID | $XPATH \
+    /DATASTORE/TEMPLATE/POOL_NAME \
+    /DATASTORE/TEMPLATE/BRIDGE_LIST)
+
+POOL_NAME="${XPATH_ELEMENTS[j++]}"
+BRIDGE_LIST="${XPATH_ELEMENTS[j++]}"
+
+#-------------------------------------------------------------------------------
+# Copy Image back to the datastore
+#-------------------------------------------------------------------------------
+
+if [ "$CLONE" = "YES" ]; then
+    SRC_IMAGE="${SRC_IMAGE}-${VM_ID}-${DISK_ID}"
+fi
+
+CLI=vitastor-cli
+if [ -n "$VITASTOR_CONF" ]; then
+    CLI="$CLI --config_path ${VITASTOR_CONF}"
+fi
+if [ -n "$POOL_NAME" ]; then
+    CLI="$CLI --pool ${POOL_NAME}"
+fi
+
+# Undeployed VM state, do not use front-end, choose host from bridge_list
+if [ "$LCM_STATE" = '67' ] || [ "$LCM_STATE" = '68' ]; then
+    if [ -n "$BRIDGE_LIST" ]; then
+        SRC_HOST=`get_destination_host`
+    fi
+fi
+
+if [ "$SNAP_ID" != "-1" ]; then
+    SRC_IMAGE=$SRC_IMAGE@$SNAP_ID
+fi
+
+COPY_CMD=$(cat <<EOF
+    $CLI dd iimg=$SRC_IMAGE oimg=$DST
+EOF
+)
+
+ssh_exec_and_log "$SRC_HOST" "$COPY_CMD" "Error cloning $SRC_IMAGE to $DST in $SRC_HOST"

opennebula/remotes/tm/vitastor/delete

@@ -0,0 +1,139 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# DELETE <host:remote_system_ds/disk.i|host:remote_system_ds/>
+#   - host is the target host to deploy the VM
+#   - remote_system_ds is the path for the system datastore in the host
+
+DST=$1
+VM_ID=$2
+DS_ID=$3
+
+#--------------------------------------------------------------------------------
+
+if [ -z "${ONE_LOCATION}" ]; then
+    TMCOMMON=/var/lib/one/remotes/tm/tm_common.sh
+    LIB_LOCATION=/usr/lib/one
+else
+    TMCOMMON=$ONE_LOCATION/var/remotes/tm/tm_common.sh
+    LIB_LOCATION=$ONE_LOCATION/lib
+fi
+
+DRIVER_PATH=$(dirname $0)
+
+source $TMCOMMON
+source ${DRIVER_PATH}/../../datastore/libfs.sh
+
+#-------------------------------------------------------------------------------
+# Process destination
+#-------------------------------------------------------------------------------
+
+DST_PATH=`arg_path $DST`
+DST_HOST=`arg_host $DST`
+
+XPATH="${DRIVER_PATH}/../../datastore/xpath.rb --stdin"
+
+#-------------------------------------------------------------------------------
+# Delete and exit if directory
+#-------------------------------------------------------------------------------
+
+if [ `is_disk $DST_PATH` -eq 0 ]; then
+    # Directory: delete checkpoint and directory
+
+    unset i j XPATH_ELEMENTS
+
+    while IFS= read -r -d '' element; do
+        XPATH_ELEMENTS[i++]="$element"
+    done < <(onedatastore show -x $DS_ID | $XPATH \
+        /DATASTORE/TEMPLATE/SOURCE \
+        /DATASTORE/TEMPLATE/CLONE \
+        /DATASTORE/TEMPLATE/VITASTOR_CONF \
+        /DATASTORE/TEMPLATE/IMAGE_PREFIX \
+        /DATASTORE/TEMPLATE/POOL_NAME)
+
+    SRC="${XPATH_ELEMENTS[j++]}"
+    CLONE="${XPATH_ELEMENTS[j++]}"
+    VITASTOR_CONF="${XPATH_ELEMENTS[j++]}"
+    IMAGE_PREFIX="${XPATH_ELEMENTS[j++]:-one}"
+    POOL_NAME="${XPATH_ELEMENTS[j++]}"
+
+    CLI=vitastor-cli
+    if [ -n "$VITASTOR_CONF" ]; then
+        CLI="$CLI --config_path ${VITASTOR_CONF}"
+    fi
+
+    SRC_CHECKPOINT="${IMAGE_PREFIX}-sys-${VM_ID}-checkpoint"
+
+    ssh_exec_and_log "$DST_HOST" "$CLI rm $SRC_CHECKPOINT 2>/dev/null || exit 0" \
+        "Error deleting $SRC_CHECKPOINT in $DST_HOST"
+
+    log "Deleting $DST_PATH"
+    ssh_exec_and_log "$DST_HOST" "rm -rf $DST_PATH" "Error deleting $DST_PATH"
+    exit 0
+fi
+
+#-------------------------------------------------------------------------------
+# Get Image information
+#-------------------------------------------------------------------------------
+
+DISK_ID=$(echo "$DST_PATH" | $AWK -F. '{print $NF}')
+
+# Reads the disk parameters -- taken from image datastore
+unset i j XPATH_ELEMENTS
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <(onevm show -x $VM_ID | $XPATH \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/SOURCE \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/CLONE \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/VITASTOR_CONF \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/IMAGE_PREFIX \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/POOL_NAME)
+
+SRC="${XPATH_ELEMENTS[j++]}"
+CLONE="${XPATH_ELEMENTS[j++]}"
+VITASTOR_CONF="${XPATH_ELEMENTS[j++]}"
+IMAGE_PREFIX="${XPATH_ELEMENTS[j++]:-one}"
+POOL_NAME="${XPATH_ELEMENTS[j++]}"
+
+if is_undeployed "$VM_ID" "$DST_HOST"; then
+    # get BRIDGE_LIST from datastore
+    XPATH="${DRIVER_PATH}/../../datastore/xpath.rb --stdin"
+    IFS= read -r -d '' BRIDGE_LIST < <(onedatastore show -x "$DS_ID" \
+        | $XPATH /DATASTORE/TEMPLATE/BRIDGE_LIST )
+
+    if [ -n "$BRIDGE_LIST" ]; then
+        DST_HOST=$(get_destination_host)
+    fi
+fi
+
+# No need to delete not cloned images
+if [ "$CLONE" = "NO" ]; then
+    exit 0
+fi
+
+CLI=vitastor-cli
+if [ -n "$VITASTOR_CONF" ]; then
+    CLI="$CLI --config_path ${VITASTOR_CONF}"
+fi
+
+if [ -n "$SRC" ]; then
+    # cloned, so the name will be "one-<imageid>-<vmid>-<diskid>"
+    SRC_IMAGE="${SRC}-${VM_ID}-${DISK_ID}"
+else
+    # volatile
+    SRC_IMAGE="${IMAGE_PREFIX}-sys-${VM_ID}-${DISK_ID}"
+fi
+
+# Delete the image
+
+log "Deleting $DST_PATH"
+
+DELETE_CMD=$(cat <<EOF
+    $CLI rm $SRC_IMAGE
+EOF
+)
+
+ssh_exec_and_log "$DST_HOST" "$DELETE_CMD" "Error deleting $SRC_IMAGE in $DST_HOST"

opennebula/remotes/tm/vitastor/failmigrate

@@ -0,0 +1 @@
+../ceph/failmigrate

opennebula/remotes/tm/vitastor/ln

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# <CLONE|LN>(.tm_mad_system) tm_mad fe:SOURCE host:remote_system_ds/disk.i vmid dsid
+
+# LN = Attach disk to a VM (Vitastor doesn't need to do anything in this case)
+
+SRC=$1
+DST=$2
+VM_ID=$3
+DS_ID=$4
+
+exit 0

opennebula/remotes/tm/vitastor/mkimage

@@ -0,0 +1,120 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# mkimage size format host:remote_system_ds/disk.i vmid dsid
+#   - size in MB of the image
+#   - format for the image
+#   - host is the target host to deploy the VM
+#   - remote_system_ds is the path for the system datastore in the host
+#   - vmid is the id of the VM
+#   - dsid is the target datastore (0 is the system datastore)
+
+SIZE=$1
+FORMAT=$2
+DST=$3
+
+VMID=$4
+DSID=$5
+
+#-------------------------------------------------------------------------------
+
+if [ -z "${ONE_LOCATION}" ]; then
+    TMCOMMON=/var/lib/one/remotes/tm/tm_common.sh
+    LIB_LOCATION=/usr/lib/one
+else
+    TMCOMMON=$ONE_LOCATION/var/remotes/tm/tm_common.sh
+    LIB_LOCATION=$ONE_LOCATION/lib
+fi
+
+DRIVER_PATH=$(dirname $0)
+
+source $TMCOMMON
+
+source ${DRIVER_PATH}/../../etc/datastore/datastore.conf
+source ${DRIVER_PATH}/../../datastore/libfs.sh
+
+#-------------------------------------------------------------------------------
+# Set dst path and dir
+#-------------------------------------------------------------------------------
+
+DST_PATH=`arg_path $DST`
+DST_HOST=`arg_host $DST`
+DST_DIR=`dirname $DST_PATH`
+
+DISK_ID=$(echo $DST|awk -F. '{print $NF}')
+
+#-------------------------------------------------------------------------------
+# Get Image information
+#-------------------------------------------------------------------------------
+
+XPATH="${DRIVER_PATH}/../../datastore/xpath.rb --stdin"
+
+unset i j XPATH_ELEMENTS
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <(onevm show -x $VMID | $XPATH \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/VITASTOR_CONF \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/POOL_NAME \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/IMAGE_PREFIX \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/FS)
+
+VITASTOR_CONF="${XPATH_ELEMENTS[j++]}"
+POOL_NAME="${XPATH_ELEMENTS[j++]}"
+IMAGE_PREFIX="${XPATH_ELEMENTS[j++]:-one}"
+FS="${XPATH_ELEMENTS[j++]}"
+
+CLI=
+QEMU_ARG=""
+if [ -n "$VITASTOR_CONF" ]; then
+    CLI="$CLI --config_path ${VITASTOR_CONF}"
+    QEMU_ARG=":config_path=${VITASTOR_CONF}"
+fi
+
+IMAGE_NAME="${IMAGE_PREFIX}-sys-${VMID}-${DISK_ID}"
+
+ssh_make_path $DST_HOST $DST_DIR
+
+set -e -o pipefail
+
+# if user requested a swap or specifies a FS, we need to create a local
+# formatted image and upload into existing Vitastor image
+FS_OPTS=$(eval $(echo "echo \$FS_OPTS_$FS"))
+
+MKIMAGE_CMD=$(cat <<EOF
+    set -e -o pipefail
+    export PATH=/usr/sbin:/sbin:\$PATH
+    vitastor-cli $CLI create --pool "${POOL_NAME}" "$IMAGE_NAME" --size "${SIZE}M"
+EOF
+)
+
+if [ -n "$FS" -o "$FORMAT" = "swap" ]; then
+    MKFS_CMD=`mkfs_command '$NBD' raw "$SIZE" "$SUPPORTED_FS" "$FS" "$FS_OPTS" | grep -v $QEMU_IMG`
+    MKIMAGE_CMD=$(cat <<EOF
+    $MKIMAGE_CMD
+    NBD=\$(sudo vitastor-nbd $CLI map --image "$IMAGE_NAME")
+    trap "sudo vitastor-nbd $CLI unmap \$NBD" EXIT
+    $MKFS_CMD
+EOF
+)
+fi
+
+DELIMAGE_CMD=$(cat <<EOF
+    vitastor-cli $CLI rm "$IMAGE_NAME"
+EOF
+)
+
+log "Making volatile disk of ${SIZE}M at $DST"
+
+ssh_exec_and_log_no_error "$DST_HOST" "$MKIMAGE_CMD" "Error creating volatile disk.$DISK_ID ($IMAGE_NAME) in $DST_HOST in pool $POOL_NAME."
+
+rc=$?
+
+if [ $rc != 0 ]; then
+    ssh_exec_and_log_no_error "$DST_HOST" "$DELIMAGE_CMD" "Error removing image"
+fi
+
+exit $rc

opennebula/remotes/tm/vitastor/mkswap

@@ -0,0 +1 @@
+../ceph/mkswap

opennebula/remotes/tm/vitastor/monitor

@@ -0,0 +1 @@
+../../datastore/vitastor/monitor

opennebula/remotes/tm/vitastor/mv

@@ -0,0 +1 @@
+../ceph/mv

opennebula/remotes/tm/vitastor/mvds

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# mvds host:remote_system_ds/disk.i fe:SOURCE vmid dsid
+#   - fe is the front-end hostname
+#   - SOURCE is the path of the disk image in the form DS_BASE_PATH/disk
+#   - host is the target host to deploy the VM
+#   - remote_system_ds is the path for the system datastore in the host
+#   - vmid is the id of the VM
+#   - dsid is the target datastore (0 is the system datastore)
+
+exit 0

opennebula/remotes/tm/vitastor/postbackup

@@ -0,0 +1 @@
+postbackup_live

opennebula/remotes/tm/vitastor/postbackup_live

@@ -0,0 +1 @@
+../ceph/postbackup_live

opennebula/remotes/tm/vitastor/postmigrate

@@ -0,0 +1 @@
+../ceph/postmigrate

opennebula/remotes/tm/vitastor/prebackup

@@ -0,0 +1,152 @@
+#!/usr/bin/env ruby
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+ONE_LOCATION = ENV['ONE_LOCATION']
+LIVE = ENV['LIVE']
+
+if !ONE_LOCATION
+    RUBY_LIB_LOCATION = '/usr/lib/one/ruby'
+    GEMS_LOCATION     = '/usr/share/one/gems'
+    VMDIR             = '/var/lib/one'
+    CONFIG_FILE       = '/var/lib/one/config'
+else
+    RUBY_LIB_LOCATION = ONE_LOCATION + '/lib/ruby'
+    GEMS_LOCATION     = ONE_LOCATION + '/share/gems'
+    VMDIR             = ONE_LOCATION + '/var'
+    CONFIG_FILE       = ONE_LOCATION + '/var/config'
+end
+
+# %%RUBYGEMS_SETUP_BEGIN%%
+if File.directory?(GEMS_LOCATION)
+    real_gems_path = File.realpath(GEMS_LOCATION)
+    if !defined?(Gem) || Gem.path != [real_gems_path]
+        $LOAD_PATH.reject! {|l| l =~ /vendor_ruby/ }
+
+        # Suppress warnings from Rubygems
+        # https://github.com/OpenNebula/one/issues/5379
+        begin
+            verb = $VERBOSE
+            $VERBOSE = nil
+            require 'rubygems'
+            Gem.use_paths(real_gems_path)
+        ensure
+            $VERBOSE = verb
+        end
+    end
+end
+# %%RUBYGEMS_SETUP_END%%
+
+$LOAD_PATH << RUBY_LIB_LOCATION
+
+require 'rexml/document'
+
+require_relative '../lib/tm_action'
+require_relative '../lib/kvm'
+require_relative '../lib/datastore'
+
+if LIVE
+    # TODO: fsfreeze for each hypervisor based on VM_MAD
+    include TransferManager::KVM
+end
+
+#-------------------------------------------------------------------------------
+# BACKUP tm_mad host:remote_dir DISK_ID:...:DISK_ID deploy_id bjid vmid dsid
+#-------------------------------------------------------------------------------
+TransferManager::Datastore.load_env
+
+vm_xml = STDIN.read
+
+dir       = ARGV[0].split ':'
+disks     = ARGV[1].split ':'
+deploy_id = ARGV[2]
+_bjid     = ARGV[3]
+vmid      = ARGV[4]
+_dsid     = ARGV[5]
+
+rhost     = dir[0]
+rdir      = dir[1]
+
+xml_doc = REXML::Document.new(vm_xml)
+vm      = xml_doc.root
+
+ds = TransferManager::Datastore.from_vm_backup_ds(:vm_xml => vm_xml)
+
+base_path = ENV['BACKUP_BASE_PATH']
+
+bck_dir = if base_path
+              "#{base_path}/#{vmid}/backup"
+          else
+              "#{rdir}/backup"
+          end
+
+snap_cmd = ''
+expo_cmd = ''
+clup_cmd = ''
+
+vm.elements.each 'TEMPLATE/DISK' do |d|
+    did = d.elements['DISK_ID'].text
+    next unless disks.include? did
+
+    src  = d.elements['SOURCE'].text
+    clon = d.elements['CLONE'].text
+
+    src_image = if clon == 'NO' then src else "#{src}-#{vmid}-#{did}" end
+
+    cmd = 'vitastor-cli'
+    qemu_arg = ''
+    if d.elements['VITASTOR_CONF']
+        cmd = cmd + ' --config_path ' + d.elements['VITASTOR_CONF']
+        qemu_arg += 'config_path='+d.elements['VITASTOR_CONF']+':'
+    end
+
+    draw = "#{bck_dir}/disk.#{did}.raw"
+    ddst = "#{bck_dir}/disk.#{did}.0"
+
+    expo_cmd << ds.cmd_confinement("qemu-img convert -m 4 -O qcow2 'vitastor:#{qemu_arg}image=#{src_image}' #{ddst}\n", rdir)
+
+    clup_cmd << "rm -f #{draw}\n"
+rescue StandardError => e
+    STDERR.puts "Missing configuration attributes in DISK: #{e.message}"
+    exit(1)
+end
+
+if LIVE
+    freeze, thaw = fsfreeze(vm, deploy_id)
+end
+
+script = <<~EOS
+    set -ex -o pipefail
+
+    # Prepare backup folder
+    [ -d #{bck_dir} ] && rm -rf #{bck_dir}
+
+    mkdir -p #{bck_dir}
+
+    echo "#{Base64.encode64(vm_xml)}" > #{bck_dir}/vm.xml
+
+    #{freeze}
+
+    #{snap_cmd}
+
+    #{thaw}
+
+    #{expo_cmd}
+
+    #{clup_cmd}
+EOS
+
+rc = TransferManager::Action.ssh('prebackup_live',
+    :host => rhost,
+    :cmds => script,
+    :nostdout => false,
+    :nostderr => false
+)
+
+if rc.code != 0
+    STDERR.puts "Error preparing disk files: #{rc.stdout} #{rc.stderr}"
+end
+
+exit(rc.code)

opennebula/remotes/tm/vitastor/prebackup_live

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+export LIVE=1
+`dirname $0`/prebackup $@

opennebula/remotes/tm/vitastor/premigrate

@@ -0,0 +1 @@
+../ceph/premigrate

opennebula/remotes/tm/vitastor/resize

@@ -0,0 +1,81 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# resize image size vmid
+
+SRC=$1
+SIZE=$2
+VM_ID=$3
+
+#--------------------------------------------------------------------------------
+
+if [ -z "${ONE_LOCATION}" ]; then
+    TMCOMMON=/var/lib/one/remotes/tm/tm_common.sh
+    LIB_LOCATION=/usr/lib/one
+else
+    TMCOMMON=$ONE_LOCATION/var/remotes/tm/tm_common.sh
+    LIB_LOCATION=$ONE_LOCATION/lib
+fi
+
+DRIVER_PATH=$(dirname $0)
+
+source $TMCOMMON
+
+#-------------------------------------------------------------------------------
+# Set dst path and dir
+#-------------------------------------------------------------------------------
+
+SRC_HOST=`arg_host $SRC`
+SRC_PATH=`arg_path $SRC`
+
+#-------------------------------------------------------------------------------
+# Get Image information
+#-------------------------------------------------------------------------------
+
+DISK_ID=$(echo "$SRC_PATH" | $AWK -F. '{print $NF}')
+
+XPATH="${DRIVER_PATH}/../../datastore/xpath.rb --stdin"
+
+unset i j XPATH_ELEMENTS
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <(onevm show -x $VM_ID | $XPATH \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/SOURCE \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/VITASTOR_CONF \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/IMAGE_PREFIX \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/PERSISTENT)
+
+SRC_IMAGE="${XPATH_ELEMENTS[j++]}"
+VITASTOR_CONF="${XPATH_ELEMENTS[j++]}"
+IMAGE_PREFIX="${XPATH_ELEMENTS[j++]:-one}"
+PERSISTENT="${XPATH_ELEMENTS[j++]}"
+
+if [ -n "${SRC_IMAGE}" ]; then
+    if [ "${PERSISTENT}" != 'YES' ]; then
+        SRC_IMAGE="${SRC_IMAGE}-${VM_ID}-${DISK_ID}"
+    fi
+else
+    SRC_IMAGE="${IMAGE_PREFIX}-sys-${VM_ID}-${DISK_ID}"
+fi
+
+#-------------------------------------------------------------------------------
+# Resize disk
+#-------------------------------------------------------------------------------
+
+CLI=vitastor-cli
+if [ -n "$VITASTOR_CONF" ]; then
+    CLI="$CLI --config_path ${VITASTOR_CONF}"
+fi
+
+RESIZE_CMD=$(cat <<EOF
+    $CLI modify --resize ${SIZE}M "$SRC_IMAGE"
+EOF
+)
+
+ssh_exec_and_log "$SRC_HOST" "$RESIZE_CMD" "Error resizing disk $SRC_IMAGE"
+
+exit 0

opennebula/remotes/tm/vitastor/restore

@@ -0,0 +1,201 @@
+#!/usr/bin/env ruby
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+ONE_LOCATION = ENV['ONE_LOCATION']
+
+if !ONE_LOCATION
+    RUBY_LIB_LOCATION = '/usr/lib/one/ruby'
+    GEMS_LOCATION     = '/usr/share/one/gems'
+    VMDIR             = '/var/lib/one'
+    CONFIG_FILE       = '/var/lib/one/config'
+else
+    RUBY_LIB_LOCATION = ONE_LOCATION + '/lib/ruby'
+    GEMS_LOCATION     = ONE_LOCATION + '/share/gems'
+    VMDIR             = ONE_LOCATION + '/var'
+    CONFIG_FILE       = ONE_LOCATION + '/var/config'
+end
+
+# %%RUBYGEMS_SETUP_BEGIN%%
+if File.directory?(GEMS_LOCATION)
+    real_gems_path = File.realpath(GEMS_LOCATION)
+    if !defined?(Gem) || Gem.path != [real_gems_path]
+        $LOAD_PATH.reject! {|l| l =~ /vendor_ruby/ }
+
+        # Suppress warnings from Rubygems
+        # https://github.com/OpenNebula/one/issues/5379
+        begin
+            verb = $VERBOSE
+            $VERBOSE = nil
+            require 'rubygems'
+            Gem.use_paths(real_gems_path)
+        ensure
+            $VERBOSE = verb
+        end
+    end
+end
+# %%RUBYGEMS_SETUP_END%%
+
+$LOAD_PATH << RUBY_LIB_LOCATION
+
+require 'rexml/document'
+require 'json'
+require 'securerandom'
+
+require_relative '../lib/tm_action'
+require_relative '../lib/datastore'
+
+def get_vitastor_disks(vm_xml)
+    vm_xml  = REXML::Document.new(vm_xml) if vm_xml.is_a?(String)
+    vm      = vm_xml.root
+    vmid    = vm.elements['VMID'].text
+
+    indexed_disks = []
+    vm.elements.each('DISK[TM_MAD="vitastor"]') do |d|
+        disk = new(vmid, d)
+        indexed_disks[disk.id] = disk
+    end
+
+    indexed_disks
+end
+
+#-------------------------------------------------------------------------------
+# RESTORE vm_id img_id inc_id disk_id
+#-------------------------------------------------------------------------------
+_dir      = ARGV[0].split ':'
+vm_id     = ARGV[1]
+bk_img_id = ARGV[2].to_i
+inc_id    = ARGV[3]
+disk_id   = ARGV[4].to_i
+
+begin
+    action = TransferManager::Action.new(:action_name => 'restore',
+                                         :vm_id => vm_id)
+    # --------------------------------------------------------------------------
+    # Image & Datastore information
+    # --------------------------------------------------------------------------
+    bk_img = OpenNebula::Image.new_with_id(bk_img_id, action.one)
+
+    rc = bk_img.info
+    raise rc.message.to_s if OpenNebula.is_error?(rc)
+
+    bk_ds = TransferManager::Datastore.from_image_ds(:image  => bk_img,
+                                                     :client => action.one)
+
+    # --------------------------------------------------------------------------
+    # Backup information
+    # sample output: {"0":"rsync://100//0:3ffce7/var/lib/one/datastores/100/1/3ffce7/disk.0.0"}
+    # --------------------------------------------------------------------------
+    xml_data = <<~EOS
+        #{action.vm.to_xml}
+        #{bk_img.to_xml}
+    EOS
+
+    rc = bk_ds.action("ls -i #{inc_id}", xml_data)
+
+    raise 'cannot list backup contents' unless rc.code == 0
+
+    disk_urls = JSON.parse(rc.stdout)
+    disk_urls = disk_urls.select {|id, _url| id.to_i == disk_id } if disk_id != -1
+
+    # --------------------------------------------------------------------------
+    # Restore disk_urls in Host VM folder
+    # --------------------------------------------------------------------------
+    vitastor_disks = get_vitastor_disks(action.vm.template_xml)
+    success_disks = []
+
+    info = {}
+
+    disk_urls.each do |id, url|
+        vitastor_disk = vitastor_disks[id.to_i]
+        randsuffix = SecureRandom.hex(5)
+
+        vitastor_one_ds = OpenNebula::Datastore.new_with_id(
+            action.vm["/VM/TEMPLATE/DISK[DISK_ID = #{id}]/DATASTORE_ID"].to_i, action.one
+        )
+        vitastor_ds = TransferManager::Datastore.new(:ds => vitastor_one_ds, :client => action.one)
+
+        src_image = vitastor_disk.elements['SOURCE'].text
+        disk_id = vitastor_disk.elements['DISK_ID'].text
+        if vitastor_disk.elements['CLONE'].text == 'YES'
+            src_image += '-'+vm_id+'-'+disk_id
+        end
+
+        cli = 'vitastor-cli'
+        config_path = vitastor_disk.elements['VITASTOR_CONF']
+        qemu_args = ''
+        if config_path:
+            cli += ' --config_path "'+config_path.text+'"'
+            qemu_args += ':config_path='+config_path.text
+
+        info[vitastor_disk] = {
+            :br  => vitastor_ds.pick_bridge,
+            :bak => "#{src_image}.backup.#{randsuffix}",
+            :old => "#{src_image}.old.#{randsuffix}",
+            :cli => cli,
+            :img => src_image,
+        }
+
+        upload_vitastor = <<~EOS
+            set -e
+            tmpimg="$(mktemp -t disk#{id}.XXXX)"
+            #{__dir__}/../../datastore/downloader.sh --nodecomp #{url} $tmpimg
+            #{cli} create -s $(qemu-img info --output json $tmpimg | jq -r '.["virtual-size"]') #{info[vitastor_disk][:bak]}
+            qemu-img convert -m 4 -O raw $tmpimg "vitastor:image=#{info[vitastor_disk][:bak]}#{qemu_args}"
+            rm -f $tmpimg
+        EOS
+
+        rc = action.ssh(:host => info[vitastor_disk][:br],
+                        :cmds => upload_ceph,
+                        :forward  => false,
+                        :nostdout => false,
+                        :nostderr => false)
+
+        break if rc.code != 0
+
+        success_disks << vitastor_disk
+    end
+
+    # Rollback and raise error if it was unable to backup all disks
+    if success_disks.length != disk_urls.length
+        success_disks.each do |vitastor_disk|
+            cleanup = <<~EOS
+                #{info[vitastor_disk][:cli]} rm #{info[vitastor_disk][:bak]}
+            EOS
+
+            action.ssh(:host => info[vitastor_disk][:br],
+                       :cmds => cleanup,
+                       :forward  => false,
+                       :nostdout => false,
+                       :nostderr => false)
+        end
+
+        raise "error uploading backup disk to Vitastor (#{success_disks.length}/#{disk_urls.length})"
+    end
+
+    # --------------------------------------------------------------------------
+    # Replace VM disk_urls with backup copies (~prolog)
+    # --------------------------------------------------------------------------
+    success_disks.each do |vitastor_disk|
+        move = <<~EOS
+            set -e
+            #{info[vitastor_disk][:cli]} mv #{info[vitastor_disk][:img]} #{info[vitastor_disk][:old]}
+            #{info[vitastor_disk][:cli]} mv #{info[vitastor_disk][:bak]} #{info[vitastor_disk][:img]}
+            #{info[vitastor_disk][:cli]} rm --matching "#{info[vitastor_disk][:img]}@*"
+            #{info[vitastor_disk][:cli]} rm #{info[vitastor_disk][:old]}
+        EOS
+
+        rc = action.ssh(:host => info[vitastor_disk][:br],
+                        :cmds => move,
+                        :forward  => false,
+                        :nostdout => false,
+                        :nostderr => false)
+
+        warn 'cannot restore disk backup' if rc.code != 0
+    end
+rescue StandardError => e
+    STDERR.puts "Error restoring VM disks: #{e.message}"
+    exit(1)
+end

opennebula/remotes/tm/vitastor/snap_create

@@ -0,0 +1,78 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# snap_create host:parent_image snap_id vmid ds_id
+
+SRC=$1
+SNAP_ID=$2
+VM_ID=$3
+DS_ID=$4
+
+#--------------------------------------------------------------------------------
+
+if [ -z "${ONE_LOCATION}" ]; then
+    TMCOMMON=/var/lib/one/remotes/tm/tm_common.sh
+    LIB_LOCATION=/usr/lib/one
+else
+    TMCOMMON=$ONE_LOCATION/var/remotes/tm/tm_common.sh
+    LIB_LOCATION=$ONE_LOCATION/lib
+fi
+
+DRIVER_PATH=$(dirname $0)
+
+source $TMCOMMON
+
+#-------------------------------------------------------------------------------
+# Set dst path and dir
+#-------------------------------------------------------------------------------
+
+SRC_HOST=`arg_host $SRC`
+SRC_PATH=`arg_path $SRC`
+
+#-------------------------------------------------------------------------------
+# Get Image information
+#-------------------------------------------------------------------------------
+
+DISK_ID=$(echo "$SRC_PATH" | $AWK -F. '{print $NF}')
+
+XPATH="${DRIVER_PATH}/../../datastore/xpath.rb --stdin"
+
+unset i j XPATH_ELEMENTS
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <(onevm show -x $VM_ID | $XPATH \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/SOURCE \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/CLONE \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/VITASTOR_CONF \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/TYPE )
+
+SRC_IMAGE="${XPATH_ELEMENTS[j++]}"
+CLONE="${XPATH_ELEMENTS[j++]}"
+VITASTOR_CONF="${XPATH_ELEMENTS[j++]}"
+TYPE="${XPATH_ELEMENTS[j++]}"
+
+if [ "$CLONE" = "YES" ]; then
+    SRC_IMAGE="${SRC_IMAGE}-${VM_ID}-${DISK_ID}"
+fi
+
+CLI=vitastor-cli
+if [ -n "$VITASTOR_CONF" ]; then
+    CLI="$CLI --config_path ${VITASTOR_CONF}"
+fi
+
+#-------------------------------------------------------------------------------
+# Create snapshots
+#-------------------------------------------------------------------------------
+
+SNAP_CREATE_CMD=$(cat <<EOF
+    $CLI snap-create "$SRC_IMAGE@$SNAP_ID"
+EOF
+)
+
+ssh_exec_and_log "$SRC_HOST" "$SNAP_CREATE_CMD" "Error creating snapshot $SRC_IMAGE@$SNAP_ID"
+
+exit 0

opennebula/remotes/tm/vitastor/snap_create_live

@@ -0,0 +1 @@
+snap_create

opennebula/remotes/tm/vitastor/snap_delete

@@ -0,0 +1,75 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# snap_delete host:parent_image snap_id vmid ds_id
+
+SRC=$1
+SNAP_ID=$2
+VM_ID=$3
+DS_ID=$4
+
+# FIXME: copypaste below, down to "delete snapshot"
+#--------------------------------------------------------------------------------
+
+if [ -z "${ONE_LOCATION}" ]; then
+    TMCOMMON=/var/lib/one/remotes/tm/tm_common.sh
+    LIB_LOCATION=/usr/lib/one
+else
+    TMCOMMON=$ONE_LOCATION/var/remotes/tm/tm_common.sh
+    LIB_LOCATION=$ONE_LOCATION/lib
+fi
+
+DRIVER_PATH=$(dirname $0)
+
+source $TMCOMMON
+
+#-------------------------------------------------------------------------------
+# Set dst path and dir
+#-------------------------------------------------------------------------------
+
+SRC_HOST=`arg_host $SRC`
+SRC_PATH=`arg_path $SRC`
+
+#-------------------------------------------------------------------------------
+# Get Image information
+#-------------------------------------------------------------------------------
+
+DISK_ID=$(echo "$SRC_PATH" | $AWK -F. '{print $NF}')
+
+XPATH="${DRIVER_PATH}/../../datastore/xpath.rb --stdin"
+
+unset i j XPATH_ELEMENTS
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <(onevm show -x $VM_ID | $XPATH \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/SOURCE \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/CLONE \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/VITASTOR_CONF )
+
+SRC_IMAGE="${XPATH_ELEMENTS[j++]}"
+CLONE="${XPATH_ELEMENTS[j++]}"
+VITASTOR_CONF="${XPATH_ELEMENTS[j++]}"
+
+if [ "$CLONE" = "YES" ]; then
+    SRC_IMAGE="${SRC_IMAGE}-${VM_ID}-${DISK_ID}"
+fi
+
+CLI=vitastor-cli
+if [ -n "$VITASTOR_CONF" ]; then
+    CLI="$CLI --config_path ${VITASTOR_CONF}"
+fi
+
+#-------------------------------------------------------------------------------
+# Delete snapshot
+#-------------------------------------------------------------------------------
+
+SNAP_DELETE_CMD=$(cat <<EOF
+    $CLI rm "$SRC_IMAGE@$SNAP_ID"
+EOF
+)
+
+ssh_exec_and_log "$SRC_HOST" "$SNAP_DELETE_CMD" "Error deleting snapshot $SRC_IMAGE@$SNAP_ID"

opennebula/remotes/tm/vitastor/snap_revert

@@ -0,0 +1,79 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+# snap_revert host:parent_image snap_id vmid ds_id
+
+SRC=$1
+SNAP_ID=$2
+VM_ID=$3
+DS_ID=$4
+
+#--------------------------------------------------------------------------------
+
+if [ -z "${ONE_LOCATION}" ]; then
+    TMCOMMON=/var/lib/one/remotes/tm/tm_common.sh
+    LIB_LOCATION=/usr/lib/one
+else
+    TMCOMMON=$ONE_LOCATION/var/remotes/tm/tm_common.sh
+    LIB_LOCATION=$ONE_LOCATION/lib
+fi
+
+DRIVER_PATH=$(dirname $0)
+
+source $TMCOMMON
+
+#-------------------------------------------------------------------------------
+# Set dst path and dir
+#-------------------------------------------------------------------------------
+
+SRC_HOST=`arg_host $SRC`
+SRC_PATH=`arg_path $SRC`
+
+#-------------------------------------------------------------------------------
+# Get Image information
+#-------------------------------------------------------------------------------
+
+DISK_ID=$(echo "$SRC_PATH" | $AWK -F. '{print $NF}')
+
+XPATH="${DRIVER_PATH}/../../datastore/xpath.rb --stdin"
+
+unset i j XPATH_ELEMENTS
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <(onevm show -x $VM_ID | $XPATH \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/SOURCE \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/CLONE \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/VITASTOR_CONF \
+    /VM/TEMPLATE/DISK[DISK_ID=$DISK_ID]/TYPE )
+
+SRC_IMAGE="${XPATH_ELEMENTS[j++]}"
+CLONE="${XPATH_ELEMENTS[j++]}"
+VITASTOR_CONF="${XPATH_ELEMENTS[j++]}"
+TYPE="${XPATH_ELEMENTS[j++]}"
+
+if [ "$CLONE" = "YES" ]; then
+    SRC_IMAGE="${SRC_IMAGE}-${VM_ID}-${DISK_ID}"
+fi
+
+CLI=vitastor-cli
+if [ -n "$VITASTOR_CONF" ]; then
+    CLI="$CLI --config_path ${VITASTOR_CONF}"
+fi
+
+#-------------------------------------------------------------------------------
+# Revert to snapshot (== remove current image and recreate it as a clone)
+#-------------------------------------------------------------------------------
+
+SNAP_REVERT_CMD=$(cat <<EOF
+    set -e
+    $CLI ls --json "$SRC_IMAGE@$SNAP_ID" | jq -s -e '[ .[][] | select(.name == "$SRC_IMAGE@$SNAP_ID") ] | length > 0'
+    $CLI rm "$SRC_IMAGE" || true
+    $CLI create --parent "$SRC_IMAGE@$SNAP_ID" "$SRC_IMAGE"
+EOF
+)
+
+ssh_exec_and_log "$SRC_HOST" "$SNAP_REVERT_CMD" "Error reverting snapshot $SNAP_ID for $SRC_IMAGE"

opennebula/remotes/vmm/kvm/deploy.vitastor

@@ -0,0 +1,18 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+set -e
+
+DRIVER_PATH=$(dirname $0)
+DEP_FILE=$1
+DEP_FILE_LOCATION=$(dirname $DEP_FILE)
+HOST=$2
+
+cat > $DEP_FILE
+
+python3 $DRIVER_PATH/deploy_vitastor.py $DEP_FILE $DEP_FILE_LOCATION/vm.xml
+
+cat "$DEP_FILE" | ssh "$HOST" "'${SCRIPTS_REMOTE_DIR:-/var/tmp/one}/vmm/kvm/deploy' '$DEP_FILE'"

opennebula/remotes/vmm/kvm/deploy_vitastor.py

@@ -0,0 +1,57 @@
+#!/usr/bin/env python3
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+import base64
+from sys import argv, stderr
+from xml.etree import ElementTree as ET
+
+dep_file = argv[1]
+with open(dep_file, 'rb') as fd:
+    dep_txt = base64.b64decode(fd.read())
+dep = ET.fromstring(dep_txt)
+
+vm_file = argv[2]
+with open(vm_file, 'rb') as fd:
+    vm_txt = base64.b64decode(fd.read())
+vm = ET.fromstring(vm_txt)
+
+ET.register_namespace('qemu', 'http://libvirt.org/schemas/domain/qemu/1.0')
+ET.register_namespace('one', 'http://opennebula.org/xmlns/libvirt/1.0')
+
+vm_id = vm.find('./ID').text
+context_disk_id = vm.find('./TEMPLATE/CONTEXT/DISK_ID').text
+changed = 0
+txt = lambda x: '' if x is None else x.text
+
+for disk in dep.findall('./devices/disk[@type="file"]'):
+    try:
+        disk_id = disk.find('./source').attrib['file'].split('.')[-1]
+        vm_disk = vm.find('./TEMPLATE/DISK[DISK_ID="{}"]'.format(disk_id))
+        if vm_disk is None:
+            continue
+        tm_mad = txt(vm_disk.find('./TM_MAD'))
+        if tm_mad != 'vitastor':
+            continue
+        src_image = txt(vm_disk.find('./SOURCE'))
+        clone = txt(vm_disk.find('./CLONE'))
+        vitastor_conf = txt(vm_disk.find('./VITASTOR_CONF'))
+        if clone == "YES":
+            src_image += "-"+vm_id+"-"+disk_id
+        # modify
+        changed = 1
+        disk.attrib['type'] = 'network'
+        disk.remove(disk.find('./source'))
+        src = ET.SubElement(disk, 'source')
+        src.attrib['protocol'] = 'vitastor'
+        src.attrib['name'] = src_image
+        if vitastor_conf:
+            # path to config should be added to /etc/apparmor.d/local/abstractions/libvirt-qemu
+            config = ET.SubElement(src, 'config')
+            config.text = vitastor_conf
+    except Exception as e:
+        print("Error: {}".format(e), file=stderr)
+
+ET.ElementTree(dep).write(dep_file)

opennebula/remotes/vmm/kvm/restore.vitastor

@@ -0,0 +1,40 @@
+#!/bin/bash
+
+# Vitastor OpenNebula driver
+# Copyright (c) Vitaliy Filippov, 2024+
+# License: Apache-2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+DRIVER_PATH=$(dirname $0)
+
+source $DRIVER_PATH/../../etc/vmm/kvm/kvmrc
+source $DRIVER_PATH/../../scripts_common.sh
+
+FILE=$1
+DST_HOST=$2
+DEPLOY_ID=$3
+VM_ID=$4
+DS_ID=$5
+
+XPATH="${DRIVER_PATH}/../../datastore/xpath.rb --stdin"
+
+while IFS= read -r -d '' element; do
+    XPATH_ELEMENTS[i++]="$element"
+done < <(cat | $XPATH \
+    /VMM_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/VITASTOR_CONF \
+    /VMM_DRIVER_ACTION_DATA/DATASTORE/TEMPLATE/IMAGE_PREFIX)
+
+VITASTOR_CONF="${XPATH_ELEMENTS[j++]}"
+IMAGE_PREFIX="${XPATH_ELEMENTS[j++]:-one}"
+
+CLI=vitastor-cli
+if [ -n "$VITASTOR_CONF" ]; then
+    CLI="$CLI --config_path $VITASTOR_CONF"
+fi
+
+SRC_IMAGE="${IMAGE_PREFIX}-sys-${VM_ID}-checkpoint"
+
+ssh_exec_and_log "$DST_HOST" "$CLI dd iimg=$SRC_IMAGE of=$FILE" "Error exporting checkpoint into from $SRC_IMAGE to $FILE"
+ssh_exec_and_log "$DST_HOST" "$CLI rm $SRC_IMAGE" "Error removing checkpoint $SRC_IMAGE"
+
+set -e
+ssh "$DST_HOST" "'${SCRIPTS_REMOTE_DIR:-/var/tmp/one}/vmm/kvm/restore' $@"