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

@@ -828,6 +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

CMakeLists.txt

@@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8.12)
 
 project(vitastor)
 
-set(VITASTOR_VERSION "1.9.1")
+set(VITASTOR_VERSION "1.9.2")
 
 add_subdirectory(src)

README-ru.md

@@ -1,4 +1,4 @@
-## Vitastor
+# Vitastor
 
 [Read English version](README.md)
 
@@ -22,7 +22,7 @@ TCP и RDMA и на хорошем железе может достигать з
 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
 
@@ -51,7 +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

@@ -22,7 +22,7 @@ or internal systems of public clouds.
 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
 

csi/Makefile

@@ -1,4 +1,4 @@
-VITASTOR_VERSION ?= v1.9.1
+VITASTOR_VERSION ?= v1.9.2
 
 all: build push
 

csi/deploy/004-csi-nodeplugin.yaml

@@ -49,7 +49,7 @@ spec:
             capabilities:
               add: ["SYS_ADMIN"]
             allowPrivilegeEscalation: true
-          image: vitalif/vitastor-csi:v1.9.1
+          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:v1.9.1
+          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 v1.8.0 h1:D0vhF3PLIZwlwZEf2eNbpujGCNwspwTYf2idJRJx4xI=
-github.com/container-storage-interface/spec v1.4.0/go.mod h1:6URME8mwIBbpVyZV93Ce5St17xBiQJQY67NDsuohiy4=
+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 v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
-golang.org/x/net v0.0.0-20201202161906-c7110b5ffcbb/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
+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 v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/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 = "1.9.1"
+    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{
+    return nil
-        Confirmed: &csi.ValidateVolumeCapabilitiesResponse_Confirmed{
-            VolumeCapabilities: req.VolumeCapabilities,
-        },
-    }, 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)
+        klog.Errorf("staging path %v is not mounted: %w", stagingTargetPath, err)
-        return nil, fmt.Errorf("staging path %v is not mounted: %v", 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 (1.9.1-1) unstable; urgency=medium
+vitastor (1.9.2-1) unstable; urgency=medium
 
   * Bugfixes
 

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_journal_fsync](layout-osd.en.md#disable_journal_fsync) and
-[disable_meta_fsync](layout-osd.en.yml#disable_meta_fsync), setting it to
+[disable_meta_fsync](layout-osd.en.md#disable_meta_fsync), setting it to
-"all" also requires enabling [disable_data_fsync](layout-osd.en.yml#disable_data_fsync).
+"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
+включения [disable_journal_fsync](layout-osd.ru.md#disable_journal_fsync) и
-[disable_meta_fsync](layout-osd.ru.yml#disable_meta_fsync), значение "all"
+[disable_meta_fsync](layout-osd.ru.md#disable_meta_fsync), значение "all"
-также требует включения [disable_data_fsync](layout-osd.ru.yml#disable_data_fsync).
+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_journal_fsync](layout-osd.en.md#disable_journal_fsync) and
-    [disable_meta_fsync](layout-osd.en.yml#disable_meta_fsync), setting it to
+    [disable_meta_fsync](layout-osd.en.md#disable_meta_fsync), setting it to
-    "all" also requires enabling [disable_data_fsync](layout-osd.en.yml#disable_data_fsync).
+    "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
+    включения [disable_journal_fsync](layout-osd.ru.md#disable_journal_fsync) и
-    [disable_meta_fsync](layout-osd.ru.yml#disable_meta_fsync), значение "all"
+    [disable_meta_fsync](layout-osd.ru.md#disable_meta_fsync), значение "all"
-    также требует включения [disable_data_fsync](layout-osd.ru.yml#disable_data_fsync).
+    также требует включения [disable_data_fsync](layout-osd.ru.md#disable_data_fsync).

docs/installation/opennebula.en.md

@@ -4,6 +4,8 @@
 
 [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:

docs/installation/opennebula.ru.md

@@ -4,6 +4,8 @@
 
 [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:

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
+  Intel DC-P3700/P4500/P4600, Intel D5-P4320, Intel D7-P5500/P5600, Intel Optane, Kingston DC1000B/DC1500M
-- HDD: HGST Ultrastar, Toshiba MG06/MG07/MG08, Seagate EXOS
+- HDD: HGST Ultrastar, Toshiba MG, Seagate EXOS
 
 ## Настройте мониторы
 

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_data_offset SIZE`    | resize data area so it starts at `SIZE`   |
---new_meta_device PATH     use PATH for new metadata
+| `--new_data_len SIZE`       | resize data area to `SIZE` bytes          |
---new_meta_offset SIZE     make new metadata area start at SIZE
+| `--new_meta_device PATH`    | use `PATH` for new metadata               |
---new_meta_len SIZE        make new metadata area SIZE bytes long
+| `--new_meta_offset SIZE`    | make new metadata area start at `SIZE`    |
---new_journal_device PATH  use PATH for new journal
+| `--new_meta_len SIZE`       | make new metadata area `SIZE` bytes long  |
---new_journal_offset SIZE  make new journal area start at SIZE
+| `--new_journal_device PATH` | use `PATH` for new journal                |
---new_journal_len SIZE     make new journal area SIZE bytes long
+| `--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_data_offset РАЗМЕР`    | сдвинуть начало области данных на `РАЗМЕР` байт       |
---new_meta_device ПУТЬ       использовать ПУТЬ как новое устройство метаданных
+| `--new_data_len РАЗМЕР`       | изменить размер области данных до `РАЗМЕР` байт       |
---new_meta_offset РАЗМЕР     разместить новые метаданные по смещению РАЗМЕР байт
+| `--new_meta_device ПУТЬ`      | использовать `ПУТЬ` как новое устройство метаданных   |
---new_meta_len РАЗМЕР        сделать новые метаданные размером РАЗМЕР байт
+| `--new_meta_offset РАЗМЕР`    | разместить новые метаданные по смещению `РАЗМЕР` байт |
---new_journal_device ПУТЬ    использовать ПУТЬ как новое устройство журнала
+| `--new_meta_len РАЗМЕР`       | сделать новые метаданные размером `РАЗМЕР` байт       |
---new_journal_offset РАЗМЕР  разместить новый журнал по смещению РАЗМЕР байт
+| `--new_journal_device ПУТЬ`   | использовать `ПУТЬ` как новое устройство журнала      |
---new_journal_len РАЗМЕР     сделать новый журнал размером РАЗМЕР байт
+| `--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 |
+| `--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_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_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               |
+| `--defrag_iodepth 16`      | Move up to this number of files in parallel during defrag               |
-| --trace                  | Print verbose defragmentation status                                    |
+| `--trace`                  | Print verbose defragmentation status                                    |
-| --dry-run                | Skip modifications, only print status                                   |
+| `--dry-run`                | Skip modifications, only print status                                   |
-| --recalc-stats           | Recalculate all volume statistics                                       |
+| `--recalc-stats`           | Recalculate all volume statistics                                       |
-| --include-empty          | Include old and empty volumes; make sure to restart NFS servers before using it |
+| `--include-empty`          | Include old and empty volumes; make sure to restart NFS servers before using it |
-| --no-rm                  | Move, but do not delete data                                            |
+| `--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 |
+| `--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_percent 50`      | Дефрагментировать только тома, в которых этот % данных удалён           |
-| --defrag_block_count 16  | Читать это количество блоков пула за один раз                           |
+| `--defrag_block_count 16`  | Читать это количество блоков пула за один раз                           |
-| --defrag_iodepth 16      | Перемещать одновременно до этого числа файлов                           |
+| `--defrag_iodepth 16`      | Перемещать одновременно до этого числа файлов                           |
-| --trace                  | Печатать детальную статистику дефрагментации                            |
+| `--trace`                  | Печатать детальную статистику дефрагментации                            |
-| --dry-run                | Не производить никаких изменений, только описать выполняемые действия   |
+| `--dry-run`                | Не производить никаких изменений, только описать выполняемые действия   |
-| --recalc-stats           | Пересчитать и сохранить статистику всех томов                           |
+| `--recalc-stats`           | Пересчитать и сохранить статистику всех томов                           |
-| --include-empty          | Дефрагментировать старые и пустые тома; обязательно перезапустите NFS-сервера после использования этой опции |
+| `--include-empty`          | Дефрагментировать старые и пустые тома; обязательно перезапустите NFS-сервера после использования этой опции |
-| --no-rm                  | Перемещать, но не удалять данные                                        |
+| `--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,
+Debian Linux kernels had these options disabled until 6.6, so make sure you install a newer kernel
-use a kernel from Ubuntu [kernel-ppa/mainline](https://kernel.ubuntu.com/~kernel-ppa/mainline/), Proxmox,
+(from bookworm-backports, trixie or newer Debian version) if you want to try VDUSE. You can also
-or build modules for Debian kernel manually:
+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
+В ядрах в Debian Linux эти опции включены, только начиная с 6.6, так что установите свежее ядро
-на Debian, поставьте ядро из Ubuntu [kernel-ppa/mainline](https://kernel.ubuntu.com/~kernel-ppa/mainline/),
+из bookworm-backports, trixie или из более новой версии Debian, если хотите попробовать VDUSE.
-из Proxmox или соберите модули для ядра Debian вручную:
+Либо же вы можете самостоятельно собрать модули для установленного ядра:
 
 ```
 mkdir build

mon/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vitastor-mon",
-  "version": "1.9.1",
+  "version": "1.9.2",
   "description": "Vitastor SDS monitor service",
   "main": "mon-main.js",
   "scripts": {

opennebula/install.sh

@@ -3,7 +3,9 @@
 set -e
 
 reapply_patch() {
-	if ! patch -f --dry-run -F 0 -R $1 < $2 >/dev/null; then
+	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 < $2; then
 			applied_ok=0
@@ -15,8 +17,13 @@ echo "Reapplying Vitastor patches to OpenNebula's oned.conf, vmm_execrc and down
 already_applied=1
 applied_ok=1
 reapply_patch /var/lib/one/remotes/datastore/downloader.sh /var/lib/one/remotes/datastore/vitastor/downloader-vitastor.sh.diff
-reapply_patch /etc/one/oned.conf /var/lib/one/remotes/datastore/vitastor/oned.conf.diff
 reapply_patch /etc/one/vmm_exec/vmm_execrc /var/lib/one/remotes/datastore/vitastor/vmm_execrc.diff
+if [[ -e /etc/one/oned.conf ]]; then
+	if ! /var/lib/one/remotes/datastore/vitastor/patch-oned-conf.py /etc/one/oned.conf; then
+		applied_ok=0
+		already_applied=0
+	fi
+fi
 if [[ "$already_applied" = 1 ]]; then
 	echo "OK: Vitastor OpenNebula patches are already applied"
 elif [[ "$applied_ok" = 1 ]]; then

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)

patches/cinder-vitastor.py

@@ -50,7 +50,7 @@ from cinder.volume import configuration
 from cinder.volume import driver
 from cinder.volume import volume_utils
 
-VITASTOR_VERSION = '1.9.1'
+VITASTOR_VERSION = '1.9.2'
 
 LOG = logging.getLogger(__name__)
 

rpm/vitastor-el7.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        1.9.1
+Version:        1.9.2
 Release:        1%{?dist}
 Summary:        Vitastor, a fast software-defined clustered block storage
 
 License:        Vitastor Network Public License 1.1
 URL:            https://vitastor.io/
-Source0:        vitastor-1.9.1.el7.tar.gz
+Source0:        vitastor-1.9.2.el7.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

rpm/vitastor-el8.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        1.9.1
+Version:        1.9.2
 Release:        1%{?dist}
 Summary:        Vitastor, a fast software-defined clustered block storage
 
 License:        Vitastor Network Public License 1.1
 URL:            https://vitastor.io/
-Source0:        vitastor-1.9.1.el8.tar.gz
+Source0:        vitastor-1.9.2.el8.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

rpm/vitastor-el9.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        1.9.1
+Version:        1.9.2
 Release:        1%{?dist}
 Summary:        Vitastor, a fast software-defined clustered block storage
 
 License:        Vitastor Network Public License 1.1
 URL:            https://vitastor.io/
-Source0:        vitastor-1.9.1.el9.tar.gz
+Source0:        vitastor-1.9.2.el9.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

src/CMakeLists.txt

@@ -19,7 +19,7 @@ if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
 	set(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
 endif()
 
-add_definitions(-DVITASTOR_VERSION="1.9.1")
+add_definitions(-DVITASTOR_VERSION="1.9.2")
 add_definitions(-D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -Wall -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith -fdiagnostics-color=always -fno-omit-frame-pointer -I ${CMAKE_SOURCE_DIR}/src)
 add_link_options(-fno-omit-frame-pointer)
 if (${WITH_ASAN})

src/blockstore/blockstore_read.cpp

@@ -993,7 +993,8 @@ int blockstore_impl_t::read_bitmap(object_id oid, uint64_t target_version, void
     {
         while (dirty_it->first.oid == oid)
         {
-            if (target_version >= dirty_it->first.version)
+            // Condition has to be the same as in dequeue_read()
+            if (!IS_IN_FLIGHT(dirty_it->second.state) && target_version >= dirty_it->first.version)
             {
                 if (result_version)
                     *result_version = dirty_it->first.version;

src/client/CMakeLists.txt

@@ -10,7 +10,7 @@ endif (IBVERBS_LIBRARIES)
 add_library(vitastor_common STATIC
 	../util/epoll_manager.cpp etcd_state_client.cpp messenger.cpp ../util/addr_util.cpp
 	msgr_stop.cpp msgr_op.cpp msgr_send.cpp msgr_receive.cpp ../util/ringloop.cpp ../../json11/json11.cpp
-	http_client.cpp osd_ops.cpp pg_states.cpp ../util/timerfd_manager.cpp ../util/str_util.cpp ${MSGR_RDMA}
+	http_client.cpp osd_ops.cpp pg_states.cpp ../util/timerfd_manager.cpp ../util/str_util.cpp ../util/json_util.cpp ${MSGR_RDMA}
 )
 target_link_libraries(vitastor_common pthread)
 target_compile_options(vitastor_common PUBLIC -fPIC)
@@ -88,7 +88,7 @@ add_executable(test_cluster_client
 	EXCLUDE_FROM_ALL
 	../test/test_cluster_client.cpp
 	pg_states.cpp osd_ops.cpp cluster_client.cpp cluster_client_list.cpp cluster_client_wb.cpp msgr_op.cpp ../test/mock/messenger.cpp msgr_stop.cpp
-	etcd_state_client.cpp ../util/timerfd_manager.cpp ../util/str_util.cpp ../../json11/json11.cpp
+	etcd_state_client.cpp ../util/timerfd_manager.cpp ../util/str_util.cpp ../util/json_util.cpp ../../json11/json11.cpp
 )
 target_compile_definitions(test_cluster_client PUBLIC -D__MOCK__)
 target_include_directories(test_cluster_client BEFORE PUBLIC ${CMAKE_SOURCE_DIR}/src/test/mock)

src/client/cluster_client.cpp

@@ -4,7 +4,7 @@
 #include <stdexcept>
 #include <assert.h>
 #include "cluster_client_impl.h"
-#include "http_client.h" // json_is_true
+#include "json_util.h"
 
 cluster_client_t::cluster_client_t(ring_loop_t *ringloop, timerfd_manager_t *tfd, json11::Json config)
 {
@@ -955,7 +955,7 @@ void cluster_client_t::slice_rw(cluster_op_t *op)
             ? (stripe + pg_block_size) : (op->offset + op->len);
         op->parts[i].iov.reset();
         op->parts[i].flags = 0;
-        if (op->cur_inode != op->inode || op->opcode == OSD_OP_READ && dirty_copied)
+        if (op->opcode != OSD_OP_READ_CHAIN_BITMAP && op->cur_inode != op->inode || op->opcode == OSD_OP_READ && dirty_copied)
         {
             // Read remaining parts from upper layers
             uint64_t prev = begin, cur = begin;

src/client/http_client.cpp

@@ -15,6 +15,7 @@
 
 #include "addr_util.h"
 #include "str_util.h"
+#include "json_util.h"
 #include "json11/json11.hpp"
 #include "http_client.h"
 #include "timerfd_manager.h"
@@ -724,22 +725,3 @@ static bool ws_parse_frame(std::string & buf, int & type, std::string & res)
     buf = buf.substr(hdr+len);
     return true;
 }
-
-// FIXME: move to utils
-bool json_is_true(const json11::Json & val)
-{
-    if (val.is_string())
-        return val == "true" || val == "yes" || val == "1";
-    return val.bool_value();
-}
-
-bool json_is_false(const json11::Json & val)
-{
-    if (val.is_string())
-        return val.string_value() == "false" || val.string_value() == "no" || val.string_value() == "0";
-    if (val.is_number())
-        return val.number_value() == 0;
-    if (val.is_bool())
-        return !val.bool_value();
-    return false;
-}

src/client/http_client.h

@@ -48,9 +48,3 @@ void http_request(http_co_t *handler, const std::string & host, const std::strin
     const http_options_t & options, std::function<void(const http_response_t *response)> response_callback);
 void http_post_message(http_co_t *handler, int type, const std::string & msg);
 void http_close(http_co_t *co);
-
-// Utils
-std::string strtolower(const std::string & in);
-// FIXME: move to json11
-bool json_is_true(const json11::Json & val);
-bool json_is_false(const json11::Json & val);

src/client/vitastor.pc.in

@@ -6,7 +6,7 @@ includedir=${prefix}/@CMAKE_INSTALL_INCLUDEDIR@
 
 Name: Vitastor
 Description: Vitastor client library
-Version: 1.9.1
+Version: 1.9.2
 Libs: -L${libdir} -lvitastor_client
 Cflags: -I${includedir}
 

src/cmd/cli_dd.cpp

@@ -369,6 +369,7 @@ struct cli_dd_t
 {
     cli_tool_t *parent;
 
+    std::vector<std::string> conv, iflag, oflag;
     dd_in_info_t iinfo;
     dd_out_info_t oinfo;
 
@@ -766,6 +767,49 @@ struct cli_dd_t
             goto resume_3;
         else if (state == 4)
             goto resume_4;
+        for (int i = 0; i < conv.size(); i++)
+        {
+            if (conv[i] == "nofsync")
+                oinfo.end_fsync = false;
+            else if (conv[i] == "trunc")
+                oinfo.out_trunc = true;
+            else if (conv[i] == "nocreat")
+                oinfo.out_create = false;
+            else if (conv[i] == "noerror")
+                ignore_errors = true;
+            else if (conv[i] == "nosparse")
+                write_zero = true;
+            else
+            {
+                result = (cli_result_t){ .err = EINVAL, .text = "Unknown option conv="+conv[i] };
+                state = 100;
+                return;
+            }
+        }
+        for (int i = 0; i < iflag.size(); i++)
+        {
+            if (iflag[i] == "direct")
+                iinfo.in_direct = true;
+            else
+            {
+                result = (cli_result_t){ .err = EINVAL, .text = "Unknown option iflag="+iflag[i] };
+                state = 100;
+                return;
+            }
+        }
+        for (int i = 0; i < oflag.size(); i++)
+        {
+            if (oflag[i] == "direct")
+                oinfo.out_direct = true;
+            else if (oflag[i] == "append")
+                oinfo.out_append = true;
+            else
+            {
+                result = (cli_result_t){ .err = EINVAL, .text = "Unknown option oflag="+oflag[i] };
+                state = 100;
+                return;
+            }
+        }
         if ((oinfo.oimg != "" && oinfo.ofile != "") || (iinfo.iimg != "" && iinfo.ifile != ""))
         {
             result = (cli_result_t){ .err = EINVAL, .text = "Image and file can't be specified at the same time" };
@@ -908,6 +952,18 @@ static uint64_t parse_blocks(json11::Json v, uint64_t bs, uint64_t def)
     return res;
 }
 
+static std::vector<std::string> explode_json(const std::string & sep, json11::Json opt)
+{
+    if (opt.is_array())
+    {
+        std::vector<std::string> arr;
+        for (auto & item: opt.array_items())
+            arr.push_back(item.as_string());
+        return arr;
+    }
+    return explode(sep, opt.as_string(), true);
+}
+
 std::function<bool(cli_result_t &)> cli_tool_t::start_dd(json11::Json cfg)
 {
     auto dd = new cli_dd_t();
@@ -923,7 +979,7 @@ std::function<bool(cli_result_t &)> cli_tool_t::start_dd(json11::Json cfg)
     dd->oseek = parse_blocks(cfg["oseek"], dd->blocksize, 0);
     if (!dd->oseek)
         dd->oseek = parse_blocks(cfg["seek"], dd->blocksize, 0);
-    dd->iseek = parse_blocks(cfg["oseek"], dd->blocksize, 0);
+    dd->iseek = parse_blocks(cfg["iseek"], dd->blocksize, 0);
     if (!dd->iseek)
         dd->iseek = parse_blocks(cfg["skip"], dd->blocksize, 0);
     dd->iodepth = cfg["iodepth"].uint64_value();
@@ -935,25 +991,9 @@ std::function<bool(cli_result_t &)> cli_tool_t::start_dd(json11::Json cfg)
         progress = true;
     dd->iinfo.detect_size = cfg["size"].is_null();
     dd->oinfo.out_size = parse_size(cfg["size"].as_string());
-    std::vector<std::string> conv = explode(",", cfg["conv"].string_value(), true);
+    dd->conv = explode_json(",", cfg["conv"]);
-    if (std::find(conv.begin(), conv.end(), "nofsync") != conv.end())
+    dd->iflag = explode_json(",", cfg["iflag"]);
-        dd->oinfo.end_fsync = false;
+    dd->oflag = explode_json(",", cfg["oflag"]);
-    if (std::find(conv.begin(), conv.end(), "trunc") != conv.end())
-        dd->oinfo.out_trunc = true;
-    if (std::find(conv.begin(), conv.end(), "nocreat") != conv.end())
-        dd->oinfo.out_create = false;
-    if (std::find(conv.begin(), conv.end(), "noerror") != conv.end())
-        dd->ignore_errors = true;
-    if (std::find(conv.begin(), conv.end(), "nosparse") != conv.end())
-        dd->write_zero = true;
-    conv = explode(",", cfg["iflag"].string_value(), true);
-    if (std::find(conv.begin(), conv.end(), "direct") != conv.end())
-        dd->iinfo.in_direct = true;
-    conv = explode(",", cfg["oflag"].string_value(), true);
-    if (std::find(conv.begin(), conv.end(), "direct") != conv.end())
-        dd->oinfo.out_direct = true;
-    if (std::find(conv.begin(), conv.end(), "append") != conv.end())
-        dd->oinfo.out_append = true;
     return [dd](cli_result_t & result)
     {
         dd->loop();

src/cmd/cli_fix.cpp

@@ -5,6 +5,7 @@
 #include "cluster_client.h"
 #include "pg_states.h"
 #include "str_util.h"
+#include "json_util.h"
 
 struct cli_fix_t
 {

src/cmd/cli_fix.h

@@ -21,6 +21,3 @@ template<class T> void remove_duplicates(std::vector<T> & ret)
     }
     ret.resize(j+1);
 }
-
-// from http_client.cpp...
-bool json_is_false(const json11::Json & val);

src/cmd/cli_modify_osd.cpp

@@ -4,6 +4,7 @@
 #include "cli.h"
 #include "cluster_client.h"
 #include "str_util.h"
+#include "json_util.h"
 #include "http_client.h"
 
 // Reweight OSD, change tags or set noout flag

src/cmd/cli_osd_tree.cpp

@@ -156,6 +156,8 @@ resume_1:
                     for (auto & jtag: osd_cfg["tags"].array_items())
                         osd.tags.push_back(jtag.string_value());
                 }
+                else if (osd_cfg["tags"].is_string())
+                    osd.tags.push_back(osd_cfg["tags"].string_value());
                 osd.noout = osd_cfg["noout"].bool_value();
             }
             auto np_it = node_placement.find(std::to_string(osd.num));

src/cmd/cli_status.cpp

@@ -4,6 +4,7 @@
 #include "cli.h"
 #include "cluster_client.h"
 #include "str_util.h"
+#include "json_util.h"
 #include "pg_states.h"
 #include "http_client.h"
 

src/disk_tool/CMakeLists.txt

@@ -5,8 +5,9 @@ project(vitastor)
 # vitastor-disk
 add_executable(vitastor-disk
 	disk_tool.cpp disk_simple_offsets.cpp
-	disk_tool_journal.cpp disk_tool_meta.cpp disk_tool_prepare.cpp disk_tool_resize.cpp disk_tool_udev.cpp disk_tool_utils.cpp disk_tool_upgrade.cpp
+	disk_tool_journal.cpp disk_tool_meta.cpp disk_tool_prepare.cpp disk_tool_resize.cpp
-	../util/crc32c.c ../util/str_util.cpp ../../json11/json11.cpp ../util/rw_blocking.cpp ../util/allocator.cpp ../util/ringloop.cpp ../blockstore/blockstore_disk.cpp
+	disk_tool_resize_auto.cpp disk_tool_udev.cpp disk_tool_utils.cpp disk_tool_upgrade.cpp
+	../util/crc32c.c ../util/str_util.cpp ../util/json_util.cpp ../../json11/json11.cpp ../util/rw_blocking.cpp ../util/allocator.cpp ../util/ringloop.cpp ../blockstore/blockstore_disk.cpp
 )
 target_link_libraries(vitastor-disk
 	tcmalloc_minimal

src/disk_tool/disk_tool.cpp

@@ -92,8 +92,22 @@ static const char *help_text =
     "  \n"
     "  Requires the `sfdisk` utility.\n"
     "\n"
-    "vitastor-disk resize <ALL_OSD_PARAMETERS> <NEW_LAYOUT> [--iodepth 32]\n"
+    "vitastor-disk resize <osd_num>|<osd_device> [OPTIONS]\n"
-    "  Resize data area and/or rewrite/move journal and metadata\n"
+    "  Resize data area and/or move journal and metadata:\n"
+    "    --move-journal TARGET    move journal to TARGET\n"
+    "    --move-meta TARGET       move metadata to TARGET\n"
+    "    --journal-size NEW_SIZE  resize journal to NEW_SIZE\n"
+    "    --data-size NEW_SIZE     resize data device to NEW_SIZE\n"
+    "    --dry-run                only show new layout, do not apply it\n"
+    "  \n"
+    "  NEW_SIZE may include k/m/g/t suffixes.\n"
+    "  TARGET may be one of:\n"
+    "    <partition>    move journal/metadata to an existing GPT partition\n"
+    "    <raw_device>   create a GPT partition on <raw_device> and move journal/metadata to it\n"
+    "    \"\"           (empty string) move journal/metadata back to the data device\n"
+    "\n"
+    "vitastor-disk raw-resize <ALL_OSD_PARAMETERS> <NEW_LAYOUT> [--iodepth 32]\n"
+    "  Resize data area and/or rewrite/move journal and metadata (manual format).\n"
     "  ALL_OSD_PARAMETERS must include all (at least all disk-related)\n"
     "  parameters from OSD command line (i.e. from systemd unit or superblock).\n"
     "  NEW_LAYOUT may include new disk layout parameters:\n"
@@ -143,8 +157,10 @@ static const char *help_text =
     "  For now, this only checks that device cache is in write-through mode if fsync is disabled.\n"
     "  Intended for use from startup scripts (i.e. from systemd units).\n"
     "\n"
+    "vitastor-disk dump-journal [OPTIONS] <osd_device>\n"
     "vitastor-disk dump-journal [OPTIONS] <journal_file> <journal_block_size> <offset> <size>\n"
-    "  Dump journal in human-readable or JSON (if --json is specified) format.\n"
+    "  Dump journal in text or JSON (if --json is specified) format.\n"
+    "  You can specify any OSD device (data, metadata or journal), or the layout manually.\n"
     "  Options:\n"
     "  --all             Scan the whole journal area for entries and dump them, even outdated ones\n"
     "  --json            Dump journal in JSON format\n"
@@ -152,16 +168,21 @@ static const char *help_text =
     "  --format data     Same as \"entries\", but also include small write data\n"
     "  --format blocks   Dump as an array of journal blocks each containing array of entries\n"
     "\n"
+    "vitastor-disk write-journal <osd_device>\n"
     "vitastor-disk write-journal <journal_file> <journal_block_size> <bitmap_size> <offset> <size>\n"
     "  Write journal from JSON taken from standard input in the same format as produced by\n"
     "  `dump-journal --json --format data`.\n"
+    "  You can specify any OSD device (data, metadata or journal), or the layout manually.\n"
     "\n"
+    "vitastor-disk dump-meta <osd_device>\n"
     "vitastor-disk dump-meta <meta_file> <meta_block_size> <offset> <size>\n"
     "  Dump metadata in JSON format.\n"
+    "  You can specify any OSD device (data, metadata or journal), or the layout manually.\n"
     "\n"
+    "vitastor-disk write-meta <osd_device>\n"
     "vitastor-disk write-meta <meta_file> <offset> <size>\n"
-    "  Write metadata from JSON taken from standard input in the same format as produced by\n"
+    "  Write metadata from JSON taken from standard input in the same format as produced by `dump-meta`.\n"
-    "  `dump-meta`. Intended for debugging.\n"
+    "  You can specify any OSD device (data, metadata or journal), or the layout manually.\n"
     "\n"
     "vitastor-disk simple-offsets <device>\n"
     "  Calculate offsets for old simple&stupid (no superblock) OSD deployment. Options:\n"
@@ -229,6 +250,10 @@ int main(int argc, char *argv[])
         {
             self.options["force"] = "1";
         }
+        else if (!strcmp(argv[i], "--dry-run") || !strcmp(argv[i], "--dry_run"))
+        {
+            self.options["dry_run"] = "1";
+        }
         else if (!strcmp(argv[i], "--allow-data-loss"))
         {
             self.options["allow_data_loss"] = "1";
@@ -236,7 +261,7 @@ int main(int argc, char *argv[])
         else if (argv[i][0] == '-' && argv[i][1] == '-' && i < argc-1)
         {
             char *key = argv[i]+2;
-            self.options[key] = argv[++i];
+            self.options[str_replace(key, "-", "_")] = argv[++i];
         }
         else
         {
@@ -249,29 +274,49 @@ int main(int argc, char *argv[])
     }
     if (!strcmp(cmd[0], "dump-journal"))
     {
-        if (cmd.size() < 5)
+        if (cmd.size() != 2 && cmd.size() < 5)
         {
             print_help(help_text, aliased ? "vitastor-dump-journal" : "vitastor-disk", cmd[0], false);
             return 1;
         }
         self.dsk.journal_device = cmd[1];
-        self.dsk.journal_block_size = strtoul(cmd[2], NULL, 10);
+        if (cmd.size() > 2)
-        self.dsk.journal_offset = strtoull(cmd[3], NULL, 10);
+        {
-        self.dsk.journal_len = strtoull(cmd[4], NULL, 10);
+            self.dsk.journal_block_size = strtoul(cmd[2], NULL, 10);
+            self.dsk.journal_offset = strtoull(cmd[3], NULL, 10);
+            self.dsk.journal_len = strtoull(cmd[4], NULL, 10);
+        }
+        else
+        {
+            // First argument is an OSD device - take metadata layout parameters from it
+            if (self.dump_load_check_superblock(self.dsk.journal_device))
+                return 1;
+        }
         return self.dump_journal();
     }
     else if (!strcmp(cmd[0], "write-journal"))
     {
-        if (cmd.size() < 6)
+        if (cmd.size() != 2 && cmd.size() < 6)
         {
             print_help(help_text, "vitastor-disk", cmd[0], false);
             return 1;
         }
         self.new_journal_device = cmd[1];
-        self.dsk.journal_block_size = strtoul(cmd[2], NULL, 10);
+        if (cmd.size() > 2)
-        self.dsk.clean_entry_bitmap_size = strtoul(cmd[3], NULL, 10);
+        {
-        self.new_journal_offset = strtoull(cmd[4], NULL, 10);
+            self.dsk.journal_block_size = strtoul(cmd[2], NULL, 10);
-        self.new_journal_len = strtoull(cmd[5], NULL, 10);
+            self.dsk.clean_entry_bitmap_size = strtoul(cmd[3], NULL, 10);
+            self.new_journal_offset = strtoull(cmd[4], NULL, 10);
+            self.new_journal_len = strtoull(cmd[5], NULL, 10);
+        }
+        else
+        {
+            // First argument is an OSD device - take metadata layout parameters from it
+            if (self.dump_load_check_superblock(self.new_journal_device))
+                return 1;
+            self.new_journal_offset = self.dsk.journal_offset;
+            self.new_journal_len = self.dsk.journal_len;
+        }
         std::string json_err;
         json11::Json entries = json11::Json::parse(read_all_fd(0), json_err);
         if (json_err != "")
@@ -296,27 +341,47 @@ int main(int argc, char *argv[])
     }
     else if (!strcmp(cmd[0], "dump-meta"))
     {
-        if (cmd.size() < 5)
+        if (cmd.size() != 2 && cmd.size() < 5)
         {
             print_help(help_text, "vitastor-disk", cmd[0], false);
             return 1;
         }
         self.dsk.meta_device = cmd[1];
-        self.dsk.meta_block_size = strtoul(cmd[2], NULL, 10);
+        if (cmd.size() > 2)
-        self.dsk.meta_offset = strtoull(cmd[3], NULL, 10);
+        {
-        self.dsk.meta_len = strtoull(cmd[4], NULL, 10);
+            self.dsk.meta_block_size = strtoul(cmd[2], NULL, 10);
+            self.dsk.meta_offset = strtoull(cmd[3], NULL, 10);
+            self.dsk.meta_len = strtoull(cmd[4], NULL, 10);
+        }
+        else
+        {
+            // First argument is an OSD device - take metadata layout parameters from it
+            if (self.dump_load_check_superblock(self.dsk.meta_device))
+                return 1;
+        }
         return self.dump_meta();
     }
     else if (!strcmp(cmd[0], "write-meta"))
     {
-        if (cmd.size() < 4)
+        if (cmd.size() != 2 && cmd.size() < 4)
         {
             print_help(help_text, "vitastor-disk", cmd[0], false);
             return 1;
         }
         self.new_meta_device = cmd[1];
-        self.new_meta_offset = strtoull(cmd[2], NULL, 10);
+        if (cmd.size() > 2)
-        self.new_meta_len = strtoull(cmd[3], NULL, 10);
+        {
+            self.new_meta_offset = strtoull(cmd[2], NULL, 10);
+            self.new_meta_len = strtoull(cmd[3], NULL, 10);
+        }
+        else
+        {
+            // First argument is an OSD device - take metadata layout parameters from it
+            if (self.dump_load_check_superblock(self.new_meta_device))
+                return 1;
+            self.new_meta_offset = self.dsk.meta_offset;
+            self.new_meta_len = self.dsk.meta_len;
+        }
         std::string json_err;
         json11::Json meta = json11::Json::parse(read_all_fd(0), json_err);
         if (json_err != "")
@@ -328,7 +393,16 @@ int main(int argc, char *argv[])
     }
     else if (!strcmp(cmd[0], "resize"))
     {
-        return self.resize_data();
+        if (cmd.size() != 2)
+        {
+            fprintf(stderr, "Exactly 1 OSD number or OSD device path argument is required\n");
+            return 1;
+        }
+        return self.resize_data(cmd[1]);
+    }
+    else if (!strcmp(cmd[0], "raw-resize"))
+    {
+        return self.raw_resize();
     }
     else if (!strcmp(cmd[0], "simple-offsets"))
     {

src/disk_tool/disk_tool.h

@@ -93,10 +93,16 @@ struct disk_tool_t
     void dump_meta_header(blockstore_meta_header_v2_t *hdr);
     void dump_meta_entry(uint64_t block_num, clean_disk_entry *entry, uint8_t *bitmap);
 
+    int dump_load_check_superblock(const std::string & device);
+
     int write_json_journal(json11::Json entries);
     int write_json_meta(json11::Json meta);
 
-    int resize_data();
+    int resize_data(std::string device);
+    int resize_parse_move_journal(std::map<std::string, std::string> & move_options, bool dry_run);
+    int resize_parse_move_meta(std::map<std::string, std::string> & move_options, bool dry_run);
+
+    int raw_resize();
     int resize_parse_params();
     void resize_init(blockstore_meta_header_v2_t *hdr);
     int resize_remap_blocks();
@@ -114,11 +120,13 @@ struct disk_tool_t
     int systemd_start_stop_osds(const std::vector<std::string> & cmd, const std::vector<std::string> & devices);
     int pre_exec_osd(std::string device);
     int purge_devices(const std::vector<std::string> & devices);
+    int clear_osd_superblock(const std::string & dev);
 
     json11::Json read_osd_superblock(std::string device, bool expect_exist = true, bool ignore_nonref = false);
     uint32_t write_osd_superblock(std::string device, json11::Json params);
 
     int prepare_one(std::map<std::string, std::string> options, int is_hdd = -1);
+    int check_existing_partition(const std::string & dev);
     int prepare(std::vector<std::string> devices);
     std::vector<vitastor_dev_info_t> collect_devices(const std::vector<std::string> & devices);
     json11::Json add_partitions(vitastor_dev_info_t & devinfo, std::vector<std::string> sizes);
@@ -133,8 +141,8 @@ void disk_tool_simple_offsets(json11::Json cfg, bool json_output);
 uint64_t sscanf_json(const char *fmt, const json11::Json & str);
 void fromhexstr(const std::string & from, int bytes, uint8_t *to);
 int disable_cache(std::string dev);
+uint64_t get_device_size(const std::string & dev, bool should_exist = false);
 std::string get_parent_device(std::string dev);
-bool json_is_true(const json11::Json & val);
 int shell_exec(const std::vector<std::string> & cmd, const std::string & in, std::string *out, std::string *err);
 int write_zero(int fd, uint64_t offset, uint64_t size);
 json11::Json read_parttable(std::string dev);

src/disk_tool/disk_tool_journal.cpp

@@ -517,6 +517,12 @@ int disk_tool_t::write_json_journal(json11::Json entries)
             uint32_t data_csum_size = !dsk.data_csum_type ? 0 : ne->small_write.len/dsk.csum_block_size*(dsk.data_csum_type & 0xFF);
             fromhexstr(rec["bitmap"].string_value(), dsk.clean_entry_bitmap_size, ((uint8_t*)ne) + sizeof(journal_entry_small_write) + data_csum_size);
             fromhexstr(rec["data"].string_value(), ne->small_write.len, new_journal_data);
+            if (ne->small_write.len > 0 && !rec["data"].is_string())
+            {
+                fprintf(stderr, "Error: entry data is missing, please generate the dump with --json --format data\n");
+                free(new_journal_buf);
+                return 1;
+            }
             if (dsk.data_csum_type)
                 fromhexstr(rec["block_csums"].string_value(), data_csum_size, ((uint8_t*)ne) + sizeof(journal_entry_small_write));
             if (rec["data"].is_string())

src/disk_tool/disk_tool_meta.cpp

@@ -4,6 +4,7 @@
 #include "disk_tool.h"
 #include "rw_blocking.h"
 #include "osd_id.h"
+#include "json_util.h"
 
 int disk_tool_t::process_meta(std::function<void(blockstore_meta_header_v2_t *)> hdr_fn,
     std::function<void(uint64_t, clean_disk_entry*, uint8_t*)> record_fn)
@@ -149,6 +150,31 @@ int disk_tool_t::process_meta(std::function<void(blockstore_meta_header_v2_t *)>
     return 0;
 }
 
+int disk_tool_t::dump_load_check_superblock(const std::string & device)
+{
+    json11::Json sb = read_osd_superblock(device, true, false);
+    if (sb.is_null())
+        return 1;
+    try
+    {
+        auto cfg = json_to_string_map(sb["params"].object_items());
+        dsk.parse_config(cfg);
+        dsk.data_io = dsk.meta_io = dsk.journal_io = "direct";
+        dsk.open_data();
+        dsk.open_meta();
+        dsk.open_journal();
+        dsk.calc_lengths(true);
+    }
+    catch (std::exception & e)
+    {
+        dsk.close_all();
+        fprintf(stderr, "%s\n", e.what());
+        return 1;
+    }
+    dsk.close_all();
+    return 0;
+}
+
 int disk_tool_t::dump_meta()
 {
     int r = process_meta(
@@ -176,7 +202,7 @@ void disk_tool_t::dump_meta_header(blockstore_meta_header_v2_t *hdr)
         {
             printf(
                 "{\"version\":\"0.9\",\"meta_block_size\":%u,\"data_block_size\":%u,\"bitmap_granularity\":%u,"
-                "\"data_csum_type\":%s,\"csum_block_size\":%u,\"entries\":[\n",
+                "\"data_csum_type\":\"%s\",\"csum_block_size\":%u,\"entries\":[\n",
                 hdr->meta_block_size, hdr->data_block_size, hdr->bitmap_granularity,
                 csum_type_str(hdr->data_csum_type).c_str(), hdr->csum_block_size
             );
@@ -243,12 +269,16 @@ int disk_tool_t::write_json_meta(json11::Json meta)
         ? meta["data_block_size"].uint64_value() : 131072;
     new_hdr->bitmap_granularity = meta["bitmap_granularity"].uint64_value()
         ? meta["bitmap_granularity"].uint64_value() : 4096;
-    new_hdr->data_csum_type = meta["data_csum_type"].is_number()
+    if (new_hdr->version >= BLOCKSTORE_META_FORMAT_V2)
-        ? meta["data_csum_type"].uint64_value()
+    {
-        : (meta["data_csum_type"].string_value() == "crc32c"
+        new_hdr->data_csum_type = meta["data_csum_type"].is_number()
-            ? BLOCKSTORE_CSUM_CRC32C
+            ? meta["data_csum_type"].uint64_value()
-            : BLOCKSTORE_CSUM_NONE);
+            : (meta["data_csum_type"].string_value() == "crc32c"
-    new_hdr->csum_block_size = meta["csum_block_size"].uint64_value();
+                ? BLOCKSTORE_CSUM_CRC32C
+                : BLOCKSTORE_CSUM_NONE);
+        new_hdr->csum_block_size = meta["csum_block_size"].uint64_value();
+        new_hdr->header_csum = crc32c(0, new_hdr, sizeof(*new_hdr));
+    }
     uint32_t new_clean_entry_header_size = (new_hdr->version == BLOCKSTORE_META_FORMAT_V1
         ? sizeof(clean_disk_entry) : sizeof(clean_disk_entry) + 4 /*entry_csum*/);
     new_clean_entry_bitmap_size = (new_hdr->data_block_size / new_hdr->bitmap_granularity + 7) / 8;

src/disk_tool/disk_tool_prepare.cpp

@@ -3,6 +3,7 @@
 
 #include "disk_tool.h"
 #include "str_util.h"
+#include "json_util.h"
 #include "osd_id.h"
 
 int disk_tool_t::prepare_one(std::map<std::string, std::string> options, int is_hdd)
@@ -52,24 +53,9 @@ int disk_tool_t::prepare_one(std::map<std::string, std::string> options, int is_
                 return 1;
             }
             if (i == 0 && is_hdd == -1)
-                is_hdd = trim(read_file("/sys/block/"+parent_dev+"/queue/rotational")) == "1";
+                is_hdd = trim(read_file("/sys/block/"+parent_dev.substr(5)+"/queue/rotational")) == "1";
-            std::string out;
+            if (check_existing_partition(dev) != 0)
-            if (shell_exec({ "wipefs", dev }, "", &out, NULL) != 0 || out != "")
-            {
-                fprintf(stderr, "%s contains data, not creating OSD without --force. wipefs shows:\n%s", dev.c_str(), out.c_str());
                 return 1;
-            }
-            json11::Json sb = read_osd_superblock(dev, false);
-            if (!sb.is_null())
-            {
-                fprintf(stderr, "%s already contains Vitastor OSD superblock, not creating OSD without --force\n", dev.c_str());
-                return 1;
-            }
-            if (fix_partition_type(dev) != 0)
-            {
-                fprintf(stderr, "%s has incorrect type and we failed to change it to Vitastor type\n", dev.c_str());
-                return 1;
-            }
         }
     }
     for (auto dev: std::vector<std::string>{"data", "meta", "journal"})
@@ -221,6 +207,28 @@ int disk_tool_t::prepare_one(std::map<std::string, std::string> options, int is_
     return 0;
 }
 
+int disk_tool_t::check_existing_partition(const std::string & dev)
+{
+    std::string out;
+    if (shell_exec({ "wipefs", dev }, "", &out, NULL) != 0 || out != "")
+    {
+        fprintf(stderr, "%s contains data, not creating OSD without --force. wipefs shows:\n%s", dev.c_str(), out.c_str());
+        return 1;
+    }
+    json11::Json sb = read_osd_superblock(dev, false);
+    if (!sb.is_null())
+    {
+        fprintf(stderr, "%s already contains Vitastor OSD superblock, not creating OSD without --force\n", dev.c_str());
+        return 1;
+    }
+    if (fix_partition_type(dev) != 0)
+    {
+        fprintf(stderr, "%s has incorrect type and we failed to change it to Vitastor type\n", dev.c_str());
+        return 1;
+    }
+    return 0;
+}
+
 std::vector<vitastor_dev_info_t> disk_tool_t::collect_devices(const std::vector<std::string> & devices)
 {
     std::vector<vitastor_dev_info_t> devinfo;
@@ -232,33 +240,16 @@ std::vector<vitastor_dev_info_t> disk_tool_t::collect_devices(const std::vector<
             fprintf(stderr, "%s does not start with /dev/, ignoring\n", dev.c_str());
             continue;
         }
-        struct stat dev_st, sys_st;
+        struct stat sys_st;
-        if (stat(dev.c_str(), &dev_st) < 0)
+        uint64_t dev_size = get_device_size(dev, false);
+        if (dev_size == UINT64_MAX)
         {
-            if (errno == ENOENT)
-            {
-                fprintf(stderr, "%s does not exist, skipping\n", dev.c_str());
-                continue;
-            }
-            fprintf(stderr, "Error checking %s: %s\n", dev.c_str(), strerror(errno));
             return {};
         }
-        uint64_t dev_size = dev_st.st_size;
+        else if (!dev_size)
-        if (S_ISBLK(dev_st.st_mode))
         {
-            int fd = open(dev.c_str(), O_DIRECT|O_RDWR);
+            fprintf(stderr, "%s does not exist, skipping\n", dev.c_str());
-            if (fd < 0)
+            continue;
-            {
-                fprintf(stderr, "Failed to open %s: %s\n", dev.c_str(), strerror(errno));
-                return {};
-            }
-            if (ioctl(fd, BLKGETSIZE64, &dev_size) < 0)
-            {
-                fprintf(stderr, "Failed to get %s size: %s\n", dev.c_str(), strerror(errno));
-                close(fd);
-                return {};
-            }
-            close(fd);
         }
         if (stat(("/sys/block/"+dev.substr(5)).c_str(), &sys_st) < 0)
         {
@@ -337,7 +328,7 @@ json11::Json disk_tool_t::add_partitions(vitastor_dev_info_t & devinfo, std::vec
         script += "+ "+size+" "+std::string(VITASTOR_PART_TYPE)+"\n";
     }
     std::string out;
-    if (shell_exec({ "sfdisk", "--no-reread", "--force", devinfo.path }, script, &out, NULL) != 0)
+    if (shell_exec({ "sfdisk", "--no-reread", "--no-tell-kernel", "--force", devinfo.path }, script, &out, NULL) != 0)
     {
         fprintf(stderr, "Failed to add %zu partition(s) with sfdisk\n", sizes.size());
         return {};
@@ -364,8 +355,9 @@ json11::Json disk_tool_t::add_partitions(vitastor_dev_info_t & devinfo, std::vec
     {
         for (const auto & part: new_parts)
         {
+            std::string link_path = "/dev/disk/by-partuuid/"+strtolower(part["uuid"].string_value());
             struct stat st;
-            if (stat(part["node"].string_value().c_str(), &st) < 0)
+            if (lstat(link_path.c_str(), &st) < 0)
             {
                 if (errno == ENOENT)
                 {
@@ -386,7 +378,7 @@ json11::Json disk_tool_t::add_partitions(vitastor_dev_info_t & devinfo, std::vec
                 }
                 else
                 {
-                    fprintf(stderr, "Failed to lstat %s: %s\n", part["node"].string_value().c_str(), strerror(errno));
+                    fprintf(stderr, "Failed to lstat %s: %s\n", link_path.c_str(), strerror(errno));
                     return {};
                 }
             }
@@ -395,8 +387,9 @@ json11::Json disk_tool_t::add_partitions(vitastor_dev_info_t & devinfo, std::vec
     }
     // Wait until device symlinks in /dev/disk/by-partuuid/ appear
     bool exists = false;
+    const int max_iter = 300; // max 30 sec
     iter = 0;
-    while (!exists && iter < 300) // max 30 sec
+    while (!exists && iter < max_iter)
     {
         exists = true;
         for (const auto & part: new_parts)
@@ -406,7 +399,13 @@ json11::Json disk_tool_t::add_partitions(vitastor_dev_info_t & devinfo, std::vec
             if (lstat(link_path.c_str(), &st) < 0)
             {
                 if (errno == ENOENT)
+                {
                     exists = false;
+                    if (iter == 4)
+                    {
+                        fprintf(stderr, "Waiting for %s to appear for up to %d sec...\n", link_path.c_str(), max_iter/10);
+                    }
+                }
                 else
                 {
                     fprintf(stderr, "Failed to lstat %s: %s\n", link_path.c_str(), strerror(errno));

src/disk_tool/disk_tool_resize.cpp

@@ -18,7 +18,7 @@ struct resizer_data_moving_t
     uint64_t old_loc, new_loc;
 };
 
-int disk_tool_t::resize_data()
+int disk_tool_t::raw_resize()
 {
     int r;
     // Parse parameters

src/disk_tool/disk_tool_resize_auto.cpp

@@ -0,0 +1,296 @@
+// Copyright (c) Vitaliy Filippov, 2019+
+// License: VNPL-1.1 (see README.md for details)
+
+#include "disk_tool.h"
+#include "rw_blocking.h"
+#include "str_util.h"
+#include "json_util.h"
+
+int disk_tool_t::resize_data(std::string device)
+{
+    if (options.find("move_journal") == options.end() &&
+        options.find("move_data") == options.end() &&
+        options.find("journal_size") == options.end() &&
+        options.find("data_size") == options.end())
+    {
+        fprintf(stderr, "None of --move-journal, --move-data, --journal-size, --data-size options are specified - nothing to do!\n");
+        return 1;
+    }
+    if (stoull_full(device))
+        device = "/dev/vitastor/osd"+device+"-data";
+    json11::Json sb = read_osd_superblock(device, true, false);
+    if (sb.is_null())
+        return 1;
+    auto sb_params = json_to_string_map(sb["params"].object_items());
+    try
+    {
+        dsk.parse_config(sb_params);
+        dsk.data_io = dsk.meta_io = dsk.journal_io = "cached";
+        dsk.open_data();
+        dsk.open_meta();
+        dsk.open_journal();
+        dsk.calc_lengths(true);
+    }
+    catch (std::exception & e)
+    {
+        dsk.close_all();
+        fprintf(stderr, "%s\n", e.what());
+        return 1;
+    }
+    dsk.close_all();
+    bool dry_run = options.find("dry_run") != options.end();
+    auto old_journal_device = dsk.journal_device;
+    auto old_meta_device = dsk.meta_device;
+    new_journal_len = dsk.journal_len;
+    if (options.find("journal_size") != options.end())
+    {
+        new_journal_len = parse_size(options["journal_size"]);
+        if (options.find("move_journal") == options.end())
+            options["move_journal"] = dsk.journal_device == dsk.data_device ? "" : dsk.journal_device;
+    }
+    std::map<std::string, std::string> move_options;
+    if (options.find("move_journal") != options.end())
+    {
+        if (resize_parse_move_journal(move_options, dry_run) != 0)
+            return 1;
+    }
+    if (options.find("move_meta") != options.end())
+    {
+        if (resize_parse_move_meta(move_options, dry_run) != 0)
+            return 1;
+    }
+    auto new_journal_device = move_options.find("new_journal_device") != move_options.end()
+        ? move_options["new_journal_device"] : dsk.journal_device;
+    auto new_meta_device = move_options.find("new_meta_device") != move_options.end()
+        ? move_options["new_meta_device"] : dsk.meta_device;
+    // Calculate new data & meta offsets
+    new_data_offset = 4096 + (new_journal_device == dsk.data_device ? new_journal_len : 0) +
+        (new_meta_device == dsk.data_device ? dsk.meta_len : 0);
+    new_data_offset += ((dsk.data_offset-new_data_offset) % dsk.data_block_size);
+    if (new_data_offset != dsk.data_offset)
+        move_options["new_data_offset"] = std::to_string(new_data_offset);
+    if (options.find("data_size") != options.end())
+    {
+        auto new_data_dev_size = parse_size(options["data_size"]);
+        new_data_dev_size = options["data_size"] == "max" || new_data_dev_size > dsk.data_device_size
+            ? dsk.data_device_size : new_data_dev_size;
+        if (new_data_dev_size-dsk.data_offset != dsk.data_len)
+            move_options["new_data_len"] = std::to_string(new_data_dev_size-new_data_offset);
+    }
+    new_meta_offset = 4096 + (new_meta_device == new_journal_device ? new_journal_len : 0);
+    if (new_meta_offset != dsk.meta_offset)
+        move_options["new_meta_offset"] = std::to_string(new_meta_offset);
+    // Run resize
+    auto orig_options = std::move(options);
+    options = sb_params;
+    for (auto & kv: move_options)
+        options[kv.first] = kv.second;
+    if (!json)
+    {
+        std::string cmd;
+        for (auto & kv: move_options)
+            cmd += "  "+kv.first+" = "+kv.second+"\n";
+        fprintf(stderr, "Running resize:\n%s", cmd.c_str());
+    }
+    if (!dry_run && raw_resize() != 0)
+        return 1;
+    // Write new superblocks
+    json11::Json::object new_sb_params = sb["params"].object_items();
+    if (move_options.find("new_journal_device") != move_options.end())
+        new_sb_params["journal_device"] = move_options["new_journal_device"];
+    if (move_options.find("new_meta_device") != move_options.end())
+        new_sb_params["meta_device"] = move_options["new_meta_device"];
+    new_sb_params["data_offset"] = new_data_offset;
+    new_sb_params["meta_offset"] = new_meta_offset;
+    if (move_options.find("new_data_len") != move_options.end())
+        new_sb_params["data_size"] = stoull_full(move_options["new_data_len"]);
+    std::set<std::string> clear_superblocks, write_superblocks;
+    write_superblocks.insert(dsk.data_device);
+    write_superblocks.insert(new_journal_device);
+    write_superblocks.insert(new_meta_device);
+    if (write_superblocks.find(old_journal_device) == write_superblocks.end())
+        clear_superblocks.insert(old_journal_device);
+    if (write_superblocks.find(old_meta_device) == write_superblocks.end())
+        clear_superblocks.insert(old_meta_device);
+    for (auto & dev: clear_superblocks)
+    {
+        if (!json)
+            fprintf(stderr, "Clearing OSD superblock on %s\n", dev.c_str());
+        if (!dry_run && clear_osd_superblock(dev) != 0)
+            return 1;
+    }
+    for (auto & dev: write_superblocks)
+    {
+        if (!json)
+            fprintf(stderr, "Writing new OSD superblock to %s\n", dev.c_str());
+        if (!dry_run && !write_osd_superblock(dev, new_sb_params))
+            return 1;
+    }
+    if (json)
+    {
+        printf("%s\n", json11::Json(json11::Json::object {
+            { "new_sb_params", new_sb_params },
+        }).dump().c_str());
+    }
+    return 0;
+}
+
+int disk_tool_t::resize_parse_move_journal(std::map<std::string, std::string> & move_options, bool dry_run)
+{
+    if (options["move_journal"] == "")
+    {
+        // move back to the data device
+        // but first check if not already there :)
+        if (dsk.journal_device == dsk.data_device && new_journal_len == dsk.journal_len)
+        {
+            // already there
+            fprintf(stderr, "journal is already on data device and has the same size\n");
+            return 0;
+        }
+        move_options["new_journal_device"] = dsk.data_device;
+        move_options["new_journal_offset"] = "4096";
+        move_options["new_journal_len"] = std::to_string(new_journal_len);
+    }
+    else
+    {
+        std::string real_dev = realpath_str(options["move_journal"], false);
+        if (real_dev == "")
+            return 1;
+        std::string parent_dev = get_parent_device(real_dev);
+        if (parent_dev == "")
+            return 1;
+        if (parent_dev == real_dev)
+        {
+            // whole disk - create partition
+            std::string old_real_dev = realpath_str(dsk.journal_device);
+            if (old_real_dev == "")
+                return 1;
+            if (options.find("force") == options.end() &&
+                get_parent_device(old_real_dev) == parent_dev)
+            {
+                // already there
+                fprintf(stderr, "journal is already on a partition of %s, add --force to create a new partition\n", options["move_journal"].c_str());
+                return 0;
+            }
+            new_journal_len = ((new_journal_len+1024*1024-1)/1024/1024)*1024*1024;
+            if (!dry_run)
+            {
+                auto devinfos = collect_devices({ real_dev });
+                if (devinfos.size() == 0)
+                    return 1;
+                std::vector<std::string> sizes;
+                sizes.push_back(std::to_string(new_journal_len/1024/1024)+"MiB");
+                auto new_parts = add_partitions(devinfos[0], sizes);
+                if (!new_parts.array_items().size())
+                    return 1;
+                options["move_journal"] = "/dev/disk/by-partuuid/"+strtolower(new_parts[0]["uuid"].string_value());
+            }
+            else
+                options["move_journal"] = "<new journal partition on "+parent_dev+">";
+        }
+        else if (options["move_journal"].substr(0, 22) != "/dev/disk/by-partuuid/")
+        {
+            // Partitions should be identified by GPT partition UUID
+            fprintf(stderr, "%s does not start with /dev/disk/by-partuuid/. Partitions should be identified by GPT partition UUIDs\n", options["move_journal"].c_str());
+            return 1;
+        }
+        else
+        {
+            // already a partition - check that it's a GPT partition with correct type
+            if (options.find("force") == options.end() &&
+                check_existing_partition(real_dev) != 0)
+            {
+                return 1;
+            }
+            new_journal_len = get_device_size(options["move_journal"], true);
+            if (new_journal_len == UINT64_MAX)
+                return 1;
+        }
+        new_journal_len -= 4096;
+        move_options["new_journal_device"] = options["move_journal"];
+        move_options["new_journal_offset"] = "4096";
+        move_options["new_journal_len"] = std::to_string(new_journal_len);
+    }
+    return 0;
+}
+
+int disk_tool_t::resize_parse_move_meta(std::map<std::string, std::string> & move_options, bool dry_run)
+{
+    if (options["move_meta"] == "")
+    {
+        // move back to the data device
+        // but first check if not already there :)
+        if (dsk.meta_device == dsk.data_device)
+        {
+            // already there
+            fprintf(stderr, "metadata is already on data device\n");
+            return 0;
+        }
+        auto new_journal_device = move_options.find("new_journal_device") != move_options.end()
+            ? move_options["new_journal_device"] : dsk.journal_device;
+        move_options["new_meta_device"] = dsk.data_device;
+        move_options["new_meta_len"] = std::to_string(dsk.meta_len);
+    }
+    else
+    {
+        std::string real_dev = realpath_str(options["move_meta"], false);
+        if (real_dev == "")
+            return 1;
+        std::string parent_dev = get_parent_device(real_dev);
+        if (parent_dev == "")
+            return 1;
+        uint64_t new_meta_len = 0;
+        if (parent_dev == real_dev)
+        {
+            // whole disk - create partition
+            std::string old_real_dev = realpath_str(dsk.meta_device);
+            if (old_real_dev == "")
+                return 1;
+            if (options.find("force") == options.end() &&
+                get_parent_device(old_real_dev) == parent_dev)
+            {
+                // already there
+                fprintf(stderr, "metadata is already on a partition of %s\n", options["move_meta"].c_str());
+                return 0;
+            }
+            new_meta_len = ((dsk.meta_len+1024*1024-1)/1024/1024)*1024*1024;
+            if (!dry_run)
+            {
+                auto devinfos = collect_devices({ real_dev });
+                if (devinfos.size() == 0)
+                    return 1;
+                std::vector<std::string> sizes;
+                sizes.push_back(std::to_string(new_meta_len/1024/1024)+"MiB");
+                auto new_parts = add_partitions(devinfos[0], sizes);
+                if (!new_parts.array_items().size())
+                    return 1;
+                options["move_meta"] = "/dev/disk/by-partuuid/"+strtolower(new_parts[0]["uuid"].string_value());
+            }
+            else
+                options["move_meta"] = "<new metadata partition on "+parent_dev+">";
+        }
+        else if (options["move_meta"].substr(0, 22) != "/dev/disk/by-partuuid/")
+        {
+            // Partitions should be identified by GPT partition UUID
+            fprintf(stderr, "%s does not start with /dev/disk/by-partuuid/. Partitions should be identified by GPT partition UUIDs\n", options["move_meta"].c_str());
+            return 1;
+        }
+        else
+        {
+            // already a partition - check that it's a GPT partition with correct type
+            if (options.find("force") == options.end() &&
+                check_existing_partition(real_dev) != 0)
+            {
+                return 1;
+            }
+            new_meta_len = get_device_size(options["move_meta"], true);
+            if (new_meta_len == UINT64_MAX)
+                return 1;
+        }
+        new_meta_len -= 4096;
+        move_options["new_meta_len"] = std::to_string(new_meta_len);
+        move_options["new_meta_device"] = options["move_meta"];
+        move_options["new_meta_offset"] = "4096";
+    }
+    return 0;
+}

src/disk_tool/disk_tool_udev.cpp

@@ -6,6 +6,7 @@
 #include "disk_tool.h"
 #include "rw_blocking.h"
 #include "str_util.h"
+#include "json_util.h"
 
 struct __attribute__((__packed__)) vitastor_disk_superblock_t
 {
@@ -381,6 +382,34 @@ int disk_tool_t::pre_exec_osd(std::string device)
     return 0;
 }
 
+int disk_tool_t::clear_osd_superblock(const std::string & dev)
+{
+    uint8_t *buf = (uint8_t*)memalign_or_die(MEM_ALIGNMENT, 4096);
+    int fd = -1, r = open(dev.c_str(), O_DIRECT|O_RDWR);
+    if (r >= 0)
+    {
+        fd = r;
+        r = read_blocking(fd, buf, 4096);
+        if (r == 4096)
+        {
+            // Clear magic and CRC
+            memset(buf, 0, 12);
+            r = lseek64(fd, 0, 0);
+            if (r == 0)
+            {
+                r = write_blocking(fd, buf, 4096);
+                if (r == 4096)
+                    r = 0;
+            }
+        }
+    }
+    if (fd >= 0)
+        close(fd);
+    free(buf);
+    buf = NULL;
+    return r;
+}
+
 int disk_tool_t::purge_devices(const std::vector<std::string> & devices)
 {
     std::set<uint64_t> osd_numbers;
@@ -439,7 +468,6 @@ int disk_tool_t::purge_devices(const std::vector<std::string> & devices)
         return 1;
     }
     // Destroy OSD superblocks
-    uint8_t *buf = (uint8_t*)memalign_or_die(MEM_ALIGNMENT, 4096);
     for (auto & sb: superblocks)
     {
         for (auto dev_type: std::vector<std::string>{ "data", "meta", "journal" })
@@ -447,26 +475,7 @@ int disk_tool_t::purge_devices(const std::vector<std::string> & devices)
             auto dev = sb["real_"+dev_type+"_device"].string_value();
             if (dev != "")
             {
-                int fd = -1, r = open(dev.c_str(), O_DIRECT|O_RDWR);
+                int r = clear_osd_superblock(dev);
-                if (r >= 0)
-                {
-                    fd = r;
-                    r = read_blocking(fd, buf, 4096);
-                    if (r == 4096)
-                    {
-                        // Clear magic and CRC
-                        memset(buf, 0, 12);
-                        r = lseek64(fd, 0, 0);
-                        if (r == 0)
-                        {
-                            r = write_blocking(fd, buf, 4096);
-                            if (r == 4096)
-                                r = 0;
-                        }
-                    }
-                }
-                if (fd >= 0)
-                    close(fd);
                 if (r != 0)
                 {
                     fprintf(stderr, "Failed to clear OSD %ju %s device %s superblock: %s\n",
@@ -487,7 +496,7 @@ int disk_tool_t::purge_devices(const std::vector<std::string> & devices)
                         fprintf(stderr, "Failed to delete partition %s: failed to find parent device\n", dev.c_str());
                         continue;
                     }
-                    auto pt = read_parttable("/dev/"+parent_dev);
+                    auto pt = read_parttable(parent_dev);
                     if (!pt.is_object())
                         continue;
                     json11::Json::array newpt = pt["partitions"].array_items();
@@ -498,7 +507,7 @@ int disk_tool_t::purge_devices(const std::vector<std::string> & devices)
                             auto old_part = newpt[i];
                             newpt.erase(newpt.begin()+i, newpt.begin()+i+1);
                             vitastor_dev_info_t devinfo = {
-                                .path = "/dev/"+parent_dev,
+                                .path = parent_dev,
                                 .pt = json11::Json::object{ { "partitions", newpt } },
                             };
                             add_partitions(devinfo, {});
@@ -507,7 +516,7 @@ int disk_tool_t::purge_devices(const std::vector<std::string> & devices)
                                 errno != ENOENT)
                             {
                                 std::string out;
-                                shell_exec({ "partprobe", "/dev/"+parent_dev }, "", &out, NULL);
+                                shell_exec({ "partprobe", parent_dev }, "", &out, NULL);
                             }
                             break;
                         }
@@ -516,7 +525,5 @@ int disk_tool_t::purge_devices(const std::vector<std::string> & devices)
             }
         }
     }
-    free(buf);
-    buf = NULL;
     return 0;
 }

src/disk_tool/disk_tool_upgrade.cpp

@@ -101,7 +101,7 @@ int disk_tool_t::upgrade_simple_unit(std::string unit)
         resizer.options = options;
         for (auto & kv: resize)
             resizer.options[kv.first] = std::to_string(kv.second);
-        if (resizer.resize_data() != 0)
+        if (resizer.raw_resize() != 0)
         {
             // FIXME: Resize with backup or journal
             fprintf(

src/disk_tool/disk_tool_utils.cpp

@@ -60,14 +60,14 @@ int disable_cache(std::string dev)
     auto parent_dev = get_parent_device(dev);
     if (parent_dev == "")
         return 1;
-    auto scsi_disk = "/sys/block/"+parent_dev+"/device/scsi_disk";
+    auto scsi_disk = "/sys/block/"+parent_dev.substr(5)+"/device/scsi_disk";
     DIR *dir = opendir(scsi_disk.c_str());
     if (!dir)
     {
         if (errno == ENOENT)
         {
             // Not a SCSI/SATA device, just check /sys/block/.../queue/write_cache
-            return check_queue_cache(dev.substr(5), parent_dev);
+            return check_queue_cache(dev.substr(5), parent_dev.substr(5));
         }
         else
         {
@@ -84,7 +84,7 @@ int disable_cache(std::string dev)
         {
             // Not a SCSI/SATA device, just check /sys/block/.../queue/write_cache
             closedir(dir);
-            return check_queue_cache(dev.substr(5), parent_dev);
+            return check_queue_cache(dev.substr(5), parent_dev.substr(5));
         }
         scsi_disk += "/";
         scsi_disk += de->d_name;
@@ -117,6 +117,38 @@ int disable_cache(std::string dev)
     return 0;
 }
 
+uint64_t get_device_size(const std::string & dev, bool should_exist)
+{
+    struct stat dev_st;
+    if (stat(dev.c_str(), &dev_st) < 0)
+    {
+        if (errno == ENOENT && !should_exist)
+        {
+            return 0;
+        }
+        fprintf(stderr, "Error checking %s: %s\n", dev.c_str(), strerror(errno));
+        return UINT64_MAX;
+    }
+    uint64_t dev_size = dev_st.st_size;
+    if (S_ISBLK(dev_st.st_mode))
+    {
+        int fd = open(dev.c_str(), O_DIRECT|O_RDWR);
+        if (fd < 0)
+        {
+            fprintf(stderr, "Failed to open %s: %s\n", dev.c_str(), strerror(errno));
+            return UINT64_MAX;
+        }
+        if (ioctl(fd, BLKGETSIZE64, &dev_size) < 0)
+        {
+            fprintf(stderr, "Failed to get %s size: %s\n", dev.c_str(), strerror(errno));
+            close(fd);
+            return UINT64_MAX;
+        }
+        close(fd);
+    }
+    return dev_size;
+}
+
 std::string get_parent_device(std::string dev)
 {
     if (dev.substr(0, 5) != "/dev/")
@@ -125,16 +157,26 @@ std::string get_parent_device(std::string dev)
         return "";
     }
     dev = dev.substr(5);
+    // check if it's a partition - partitions aren't present in /sys/block/
+    struct stat st;
+    auto chk = "/sys/block/"+dev;
+    if (stat(chk.c_str(), &st) == 0)
+    {
+        // present in /sys/block/ - not a partition
+        return "/dev/"+dev;
+    }
+    else if (errno != ENOENT)
+    {
+        fprintf(stderr, "Failed to stat %s: %s\n", chk.c_str(), strerror(errno));
+        return "";
+    }
     int i = dev.size();
     while (i > 0 && isdigit(dev[i-1]))
         i--;
-    if (i >= 1 && dev[i-1] == '-') // dm-0, dm-1
+    if (i >= 2 && dev[i-1] == 'p' && isdigit(dev[i-2])) // nvme0n1p1
-        return dev;
-    else if (i >= 2 && dev[i-1] == 'p' && isdigit(dev[i-2])) // nvme0n1p1
         i--;
     // Check that such block device exists
-    struct stat st;
+    chk = "/sys/block/"+dev.substr(0, i);
-    auto chk = "/sys/block/"+dev.substr(0, i);
     if (stat(chk.c_str(), &st) < 0)
     {
         if (errno != ENOENT)
@@ -142,16 +184,9 @@ std::string get_parent_device(std::string dev)
             fprintf(stderr, "Failed to stat %s: %s\n", chk.c_str(), strerror(errno));
             return "";
         }
-        return dev;
+        return "/dev/"+dev;
     }
-    return dev.substr(0, i);
+    return "/dev/"+dev.substr(0, i);
-}
-
-bool json_is_true(const json11::Json & val)
-{
-    if (val.is_string())
-        return val == "true" || val == "yes" || val == "1";
-    return val.bool_value();
 }
 
 int shell_exec(const std::vector<std::string> & cmd, const std::string & in, std::string *out, std::string *err)
@@ -314,7 +349,7 @@ int fix_partition_type(std::string dev_by_uuid)
     std::string parent_dev = get_parent_device(realpath_str(dev_by_uuid, false));
     if (parent_dev == "")
         return 1;
-    auto pt = read_parttable("/dev/"+parent_dev);
+    auto pt = read_parttable(parent_dev);
     if (pt.is_null() || pt.is_bool())
         return 1;
     std::string script = "label: gpt\n\n";
@@ -342,7 +377,7 @@ int fix_partition_type(std::string dev_by_uuid)
         script += "\n";
     }
     std::string out;
-    return shell_exec({ "sfdisk", "--no-reread", "--force", "/dev/"+parent_dev }, script, &out, NULL);
+    return shell_exec({ "sfdisk", "--no-reread", "--no-tell-kernel", "--force", parent_dev }, script, &out, NULL);
 }
 
 std::string csum_type_str(uint32_t data_csum_type)

src/nfs/nfs_proxy.cpp

@@ -19,6 +19,7 @@
 
 #include "addr_util.h"
 #include "str_util.h"
+#include "json_util.h"
 #include "nfs_proxy.h"
 #include "nfs_kv.h"
 #include "nfs_block.h"

src/osd/osd.cpp

@@ -14,19 +14,7 @@
 #include "osd.h"
 #include "http_client.h"
 #include "str_util.h"
-
+#include "json_util.h"
-static blockstore_config_t json_to_bs(const json11::Json::object & config)
-{
-    blockstore_config_t bs;
-    for (auto kv: config)
-    {
-        if (kv.second.is_string())
-            bs[kv.first] = kv.second.string_value();
-        else if (!kv.second.is_null())
-            bs[kv.first] = kv.second.dump();
-    }
-    return bs;
-}
 
 osd_t::osd_t(const json11::Json & config, ring_loop_t *ringloop)
 {
@@ -46,7 +34,7 @@ osd_t::osd_t(const json11::Json & config, ring_loop_t *ringloop)
 
     if (!json_is_true(this->config["disable_blockstore"]))
     {
-        auto bs_cfg = json_to_bs(this->config);
+        auto bs_cfg = json_to_string_map(this->config);
         this->bs = new blockstore_t(bs_cfg, ringloop, tfd);
         // Wait for blockstore initialisation before actually starting OSD logic
         // to prevent peering timeouts during restart with filled databases
@@ -151,7 +139,7 @@ void osd_t::parse_config(bool init)
     }
     if (bs)
     {
-        auto bs_cfg = json_to_bs(config);
+        auto bs_cfg = json_to_string_map(config);
         bs->parse_config(bs_cfg);
     }
     st_cli.parse_config(config);

src/osd/osd_primary_chain.cpp

@@ -337,7 +337,7 @@ std::vector<osd_chain_read_t> osd_t::collect_chained_read_requests(osd_op_t *cur
     {
         uint8_t *part_bitmap = ((uint8_t*)op_data->snapshot_bitmaps) + chain_pos*stripe_count*clean_entry_bitmap_size;
         int start = !cur_op->req.rw.len ? 0 : (cur_op->req.rw.offset - op_data->oid.stripe)/bs_bitmap_granularity;
-        int end = !cur_op->req.rw.len ? op_data->pg_data_size*clean_entry_bitmap_size : start + cur_op->req.rw.len/bs_bitmap_granularity;
+        int end = !cur_op->req.rw.len ? op_data->pg_data_size*clean_entry_bitmap_size*8 : start + cur_op->req.rw.len/bs_bitmap_granularity;
         // Skip unneeded part in the beginning
         while (start < end && (
             ((global_bitmap[start>>3] >> (start&7)) & 1) ||
@@ -369,12 +369,15 @@ std::vector<osd_chain_read_t> osd_t::collect_chained_read_requests(osd_op_t *cur
                 global_bitmap[cur>>3] = global_bitmap[cur>>3] | (part_bitmap[cur>>3] & (1 << (cur&7)));
             }
             // Add request
-            chain_reads.push_back((osd_chain_read_t){
+            if (cur_op->req.rw.len)
-                .chain_pos = chain_pos,
+            {
-                .inode = op_data->read_chain[chain_pos],
+                chain_reads.push_back((osd_chain_read_t){
-                .offset = start*bs_bitmap_granularity,
+                    .chain_pos = chain_pos,
-                .len = (end-start)*bs_bitmap_granularity,
+                    .inode = op_data->read_chain[chain_pos],
-            });
+                    .offset = start*bs_bitmap_granularity,
+                    .len = (end-start)*bs_bitmap_granularity,
+                });
+            }
         }
     }
     return chain_reads;

src/test/mock/messenger.cpp

@@ -55,10 +55,3 @@ json11::Json::object osd_messenger_t::merge_configs(const json11::Json::object &
 {
     return cli_config;
 }
-
-bool json_is_true(const json11::Json & val)
-{
-    if (val.is_string())
-        return val == "true" || val == "yes" || val == "1";
-    return val.bool_value();
-}

src/util/json_util.cpp

@@ -0,0 +1,35 @@
+// Copyright (c) Vitaliy Filippov, 2019+
+// License: VNPL-1.1 or GNU GPL-2.0+ (see README.md for details)
+
+#include "json_util.h"
+
+std::map<std::string, std::string> json_to_string_map(const json11::Json::object & config)
+{
+    std::map<std::string, std::string> bs;
+    for (auto kv: config)
+    {
+        if (kv.second.is_string())
+            bs[kv.first] = kv.second.string_value();
+        else if (!kv.second.is_null())
+            bs[kv.first] = kv.second.dump();
+    }
+    return bs;
+}
+
+bool json_is_true(const json11::Json & val)
+{
+    if (val.is_string())
+        return val == "true" || val == "yes" || val == "1";
+    return val.bool_value();
+}
+
+bool json_is_false(const json11::Json & val)
+{
+    if (val.is_string())
+        return val.string_value() == "false" || val.string_value() == "no" || val.string_value() == "0";
+    if (val.is_number())
+        return val.number_value() == 0;
+    if (val.is_bool())
+        return !val.bool_value();
+    return false;
+}

src/util/json_util.h

@@ -0,0 +1,13 @@
+// Copyright (c) Vitaliy Filippov, 2019+
+// License: VNPL-1.1 or GNU GPL-2.0+ (see README.md for details)
+
+#pragma once
+
+#include <map>
+#include <string>
+
+#include "json11/json11.hpp"
+
+std::map<std::string, std::string> json_to_string_map(const json11::Json::object & config);
+bool json_is_true(const json11::Json & val);
+bool json_is_false(const json11::Json & val);

src/util/str_util.cpp

@@ -489,7 +489,7 @@ std::string format_datetime(uint64_t unixtime)
 bool is_zero(void *buf, size_t size)
 {
     size_t i = 0;
-    while (i <= size-8)
+    while (i+8 <= size)
     {
         if (*(uint64_t*)((uint8_t*)buf + i))
             return false;

tests/run_3osds.sh

@@ -83,16 +83,19 @@ fi
 POOLCFG='"name":"testpool","failure_domain":"osd",'$POOLCFG
 $ETCDCTL put /vitastor/config/pools '{"1":{'$POOLCFG',"pg_size":'$PG_SIZE',"pg_minsize":'$PG_MINSIZE',"pg_count":'$PG_COUNT'}}'
 
-wait_up()
+wait_pool_up()
 {
     local sec=$1
+    local pool=$2
+    local pgsize=$3
+    local pgcount=$4
     local i=0
     local configured=0
     while [[ $i -lt $sec ]]; do
-        if $ETCDCTL get /vitastor/pg/config --print-value-only | jq -s -e '(. | length) != 0 and ([ .[0].items["1"][] |
+        if $ETCDCTL get /vitastor/pg/config --print-value-only | jq -s -e '(. | length) != 0 and ([ .[0].items["'$pool'"][] |
-            select(((.osd_set | select(. != 0) | sort | unique) | length) == '$PG_SIZE') ] | length) == '$PG_COUNT; then
+            select(((.osd_set | select(. != 0) | sort | unique) | length) == '$pgsize') ] | length) == '$pgcount; then
             configured=1
-            if $ETCDCTL get /vitastor/pg/state/1/ --prefix --print-value-only | jq -s -e '[ .[] | select(.state == ["active"]) ] | length == '$PG_COUNT; then
+            if $ETCDCTL get /vitastor/pg/state/$pool/ --prefix --print-value-only | jq -s -e '[ .[] | select(.state == ["active"]) ] | length == '$pgcount; then
                 break
             fi
         fi
@@ -107,6 +110,11 @@ wait_up()
     done
 }
 
+wait_up()
+{
+    wait_pool_up "$1" 1 $PG_SIZE $PG_COUNT
+}
+
 if [[ $OSD_COUNT -gt 0 ]]; then
     wait_up 120
 fi

tests/run_tests.sh

@@ -68,6 +68,8 @@ TEST_NAME=csum_4k_dmj  OSD_ARGS="--data_csum_type crc32c --inmemory_metadata fal
 TEST_NAME=csum_4k_dj   OSD_ARGS="--data_csum_type crc32c --inmemory_journal false" OFFSET_ARGS=$OSD_ARGS ./test_heal.sh
 TEST_NAME=csum_4k      OSD_ARGS="--data_csum_type crc32c" OFFSET_ARGS=$OSD_ARGS ./test_heal.sh
 
+./test_snapshot_pool2.sh
+
 ./test_osd_tags.sh
 
 ./test_enospc.sh

tests/test_snapshot_pool2.sh

@@ -0,0 +1,38 @@
+#!/bin/bash -ex
+
+. `dirname $0`/run_3osds.sh
+check_qemu
+
+# snapshot in another pool
+
+build/src/cmd/vitastor-cli --etcd_address $ETCD_URL create-pool testpool2 -s 3 -n 4 --failure_domain osd
+
+wait_pool_up 30 2 3 4
+
+build/src/cmd/vitastor-cli --etcd_address $ETCD_URL create -s 128M testchain -p testpool
+
+LD_PRELOAD="build/src/client/libfio_vitastor.so" \
+    fio -thread -name=test -ioengine=build/src/client/libfio_vitastor.so -bs=1M -direct=1 -iodepth=4 -fsync=1 -rw=write \
+        -etcd=$ETCD_URL -image=testchain -mirror_file=./testdata/bin/mirror.bin -buffer_pattern=0xabcd
+
+build/src/cmd/vitastor-cli --etcd_address $ETCD_URL snap-create testchain@snap1 -p testpool2
+
+LD_PRELOAD="build/src/client/libfio_vitastor.so" \
+    fio -thread -name=test -ioengine=build/src/client/libfio_vitastor.so -bs=4k -direct=1 -iodepth=4 -end_fsync=1 -rw=randwrite -number_ios=32 \
+        -etcd=$ETCD_URL -image=testchain -mirror_file=./testdata/bin/mirror.bin -buffer_pattern=0xabcd
+
+build/src/cmd/vitastor-cli --etcd_address $ETCD_URL dd iimg=testchain of=./testdata/bin/res.bin bs=128k iodepth=4
+
+cmp ./testdata/bin/res.bin ./testdata/bin/mirror.bin
+
+build/src/cmd/vitastor-cli --etcd_address $ETCD_URL dd iimg=testchain of=./testdata/bin/res.bin bs=32k iodepth=4 conv=nosparse
+
+cmp ./testdata/bin/res.bin ./testdata/bin/mirror.bin
+
+qemu-img convert -p \
+    -f raw "vitastor:etcd_host=127.0.0.1\:$ETCD_PORT/v3:image=testchain" \
+    -O raw ./testdata/bin/res.bin
+
+cmp ./testdata/bin/res.bin ./testdata/bin/mirror.bin
+
+format_green OK