Fix block RWX volumes broken after introducing stage/unstage support

csi/go.mod

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

csi/go.sum

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

csi/src/controllerserver.go

@@ -158,6 +158,12 @@ 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 +307,43 @@ 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_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 +359,10 @@ func (cs *ControllerServer) ValidateVolumeCapabilities(ctx context.Context, req
 
     if (!capabilitySupport)
     {
-        return nil, status.Errorf(codes.NotFound, "%v not supported", req.GetVolumeCapabilities())
+        return status.Errorf(codes.NotFound, "%v not supported", volumeCapabilities)
     }
 
-    return &csi.ValidateVolumeCapabilitiesResponse{
-        Confirmed: &csi.ValidateVolumeCapabilitiesResponse_Confirmed{
-            VolumeCapabilities: req.VolumeCapabilities,
-        },
-    }, nil
+    return nil
 }
 
 // ListVolumes returns a list of volumes

csi/src/nodeserver.go

@@ -228,6 +228,26 @@ func (ns *NodeServer) NodeStageVolume(ctx context.Context, req *csi.NodeStageVol
 
     // Check that it's not already mounted
     _, err = mount.IsNotMountPoint(ns.mounter, targetPath)
+    if (err == nil)
+    {
+        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))
@@ -385,7 +405,7 @@ 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 +422,16 @@ 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 +440,7 @@ func (ns *NodeServer) NodeUnstageVolume(ctx context.Context, req *csi.NodeUnstag
     }
 
     // unmap device
-    if (refCount == 1)
+    if (len(refList) == 0)
     {
         if (!ns.useVduse)
         {

src/disk_tool/CMakeLists.txt

@@ -5,7 +5,8 @@ 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
+	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

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"
-    "  Resize data area and/or rewrite/move journal and metadata\n"
+    "vitastor-disk resize <osd_num>|<osd_device> [OPTIONS]\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"
@@ -236,6 +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";
@@ -243,7 +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
         {
@@ -375,7 +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

@@ -98,7 +98,11 @@ struct disk_tool_t
     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();

src/disk_tool/disk_tool_meta.cpp

@@ -159,7 +159,7 @@ int disk_tool_t::dump_load_check_superblock(const std::string & device)
     {
         auto cfg = json_to_string_map(sb["params"].object_items());
         dsk.parse_config(cfg);
-        dsk.data_io = dsk.meta_io = dsk.journal_io = "cached";
+        dsk.data_io = dsk.meta_io = dsk.journal_io = "direct";
         dsk.open_data();
         dsk.open_meta();
         dsk.open_journal();

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_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(