Merge pull request #261 from j-griffith/default_multiwrite_blockmode

Default multiwrite blockmode

docs/deploy-rbd.md

@@ -58,21 +58,6 @@ Parameter | Required | Description
 `csi.storage.k8s.io/provisioner-secret-name`, `csi.storage.k8s.io/node-publish-secret-name` | for Kubernetes | name of the Kubernetes Secret object containing Ceph client credentials. Both parameters should have the same value
 `csi.storage.k8s.io/provisioner-secret-namespace`, `csi.storage.k8s.io/node-publish-secret-namespace` | for Kubernetes | namespaces of the above Secret objects
 `mounter`| no | if set to `rbd-nbd`, use `rbd-nbd` on nodes that have `rbd-nbd` and `nbd` kernel modules to map rbd images
-`fsType` | no | allows setting to `ext3 | ext-4 | xfs`, default is `ext-4`
-`multiNodeWritable` | no | if set to `enabled` allows RBD volumes with MultiNode Access Modes to bypass watcher checks.  By default multiple attachments of an RBD volume are NOT allowed. Even if this option is set in the StorageClass, it's ignored if a standard SingleNodeWriter Access Mode is requested
-
-**Warning for multiNodeWritable:**
-
-*NOTE* the `multiNodeWritable` setting is NOT safe for use by workloads
-that are not designed to coordinate access.  This does NOT add any sort
-of a clustered filesystem or write syncronization, it's specifically for
-special workloads that handle access coordination on their own
-(ie Active/Passive scenarios).
-
-Using this mode for general purposes *WILL RESULT IN DATA CORRUPTION*.
-We attempt to limit exposure to trouble here but ignoring the Storage Class
-setting unless your Volume explicitly asks for multi node access, and assume
-you know what you're doing.
 
 **Required secrets:**
 

examples/README.md

@@ -115,52 +115,30 @@ kubectl create -f pvc-restore.yaml
 kubectl create -f pod-restore.yaml
 ```
 
-## How to enable multi node attach support for RBD
+## How to test RBD MULTI_NODE_MULTI_WRITER BLOCK feature
+
+Requires feature-gates: `BlockVolume=true` `CSIBlockVolume=true`
+
+*NOTE* The MULTI_NODE_MULTI_WRITER capability is only available for
+Volumes that are of access_type `block`
 
 *WARNING*  This feature is strictly for workloads that know how to deal
-with concurrent acces to the Volume (eg Active/Passive applications).
+with concurrent access to the Volume (eg Active/Passive applications).
 Using RWX modes on non clustered file systems with applications trying
 to simultaneously access the Volume will likely result in data corruption!
 
-### Example process to test the multiNodeWritable feature
+Following are examples for issuing a request for a `Block`
-
+`ReadWriteMany` Claim, and using the resultant Claim for a POD
-Modify your current storage class, or create a new storage class specifically
-for multi node writers by adding the `multiNodeWritable: "enabled"` entry to
-your parameters.  Here's an example:
-
-```yaml
-apiVersion: storage.k8s.io/v1
-kind: StorageClass
-metadata:
-   name: csi-rbd
-provisioner: rbd.csi.ceph.com
-parameters:
-    monitors: rook-ceph-mon-b.rook-ceph.svc.cluster.local:6789
-    pool: rbd
-    imageFormat: "2"
-    imageFeatures: layering
-    csiProvisionerSecretName: csi-rbd-secret
-    csiProvisionerSecretNamespace: default
-    csiNodePublishSecretName: csi-rbd-secret
-    csiNodePublishSecretNamespace: default
-    adminid: admin
-    userid: admin
-    fsType: xfs
-    multiNodeWritable: "enabled"
-reclaimPolicy: Delete
-```
-
-Now, you can request Claims from the configured storage class that include
-the `ReadWriteMany` access mode:
 
 ```yaml
 apiVersion: v1
 kind: PersistentVolumeClaim
 metadata:
-  name: pvc-1
+  name: block-pvc
 spec:
   accessModes:
   - ReadWriteMany
+  volumeMode: Block
   resources:
     requests:
       storage: 1Gi
@@ -173,108 +151,65 @@ Create a POD that uses this PVC:
 apiVersion: v1
 kind: Pod
 metadata:
-  name: test-1
+  name: my-pod
 spec:
   containers:
-   - name: web-server
+    - name: my-container
-     image: nginx
+      image: debian
-     volumeMounts:
+      command: ["/bin/bash", "-c"]
-       - name: mypvc
+      args: [ "tail -f /dev/null" ]
-         mountPath: /var/lib/www/html
+      volumeDevices:
+        - devicePath: /dev/rbdblock
+          name: my-volume
+      imagePullPolicy: IfNotPresent
   volumes:
-   - name: mypvc
+    - name: my-volume
       persistentVolumeClaim:
-       claimName: pvc-1
+        claimName: block-pvc
-       readOnly: false
-```
 
-Wait for the POD to enter Running state, write some data to
+```
-`/var/lib/www/html`
 
 Now, we can create a second POD (ensure the POD is scheduled on a different
 node; multiwriter single node works without this feature) that also uses this
-PVC at the same time
+PVC at the same time, again wait for the pod to enter running state, and verify
+the block device is available.
 
 ```yaml
 apiVersion: v1
 kind: Pod
 metadata:
-  name: test-2
+  name: another-pod
 spec:
   containers:
-   - name: web-server
+    - name: my-container
-     image: nginx
+      image: debian
-     volumeMounts:
+      command: ["/bin/bash", "-c"]
-       - name: mypvc
-         mountPath: /var/lib/www/html
-  volumes:
-   - name: mypvc
-     persistentVolumeClaim:
-       claimName: pvc-1
-       readOnly: false
-```
-
-If you access the pod you can check that your data is avaialable at
-`/var/lib/www/html`
-
-## Testing Raw Block feature in kubernetes with RBD volumes
-
-CSI block volume support is feature-gated and turned off by default. To run CSI
-with block volume support enabled, a cluster administrator must enable the
-feature for each Kubernetes component using the following feature gate flags:
-
---feature-gates=BlockVolume=true,CSIBlockVolume=true
-
-these feature-gates must be enabled on both api-server and kubelet
-
-### create a raw-block PVC
-
-```yaml
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  name: raw-block-pvc
-spec:
-  accessModes:
-    - ReadWriteOnce
-  volumeMode: Block
-  resources:
-    requests:
-      storage: 1Gi
-  storageClassName: csi-rbd
-```
-
-create raw block pvc
-
-```console
-kubectl create -f raw-block-pvc.yaml
-```
-
-### create a pod to mount raw-block PVC
-
-```yaml
----
-apiVersion: v1
-kind: Pod
-metadata:
-  name: pod-with-raw-block-volume
-spec:
-  containers:
-    - name: fc-container
-      image: fedora:26
-      command: ["/bin/sh", "-c"]
       args: [ "tail -f /dev/null" ]
       volumeDevices:
-        - name: data
+        - devicePath: /dev/rbdblock
-          devicePath: /dev/xvda
+          name: my-volume
+      imagePullPolicy: IfNotPresent
   volumes:
-    - name: data
+    - name: my-volume
       persistentVolumeClaim:
-        claimName: raw-block-pvc
+        claimName: block-pvc
 ```
 
-Create a POD that uses raw block PVC
+Wait for the PODs to enter Running state, check that our block device
+is available in the container at `/dev/rdbblock` in both containers:
 
-```console
+```bash
-kubectl create -f raw-block-pod.yaml
+$ kubectl exec -it my-pod -- fdisk -l /dev/rbdblock
+Disk /dev/rbdblock: 1 GiB, 1073741824 bytes, 2097152 sectors
+Units: sectors of 1 * 512 = 512 bytes
+Sector size (logical/physical): 512 bytes / 512 bytes
+I/O size (minimum/optimal): 4194304 bytes / 4194304 bytes
+```
+
+```bash
+$ kubectl exec -it another-pod -- fdisk -l /dev/rbdblock
+Disk /dev/rbdblock: 1 GiB, 1073741824 bytes, 2097152 sectors
+Units: sectors of 1 * 512 = 512 bytes
+Sector size (logical/physical): 512 bytes / 512 bytes
+I/O size (minimum/optimal): 4194304 bytes / 4194304 bytes
 ```

examples/rbd/storageclass.yaml

@@ -35,7 +35,4 @@ parameters:
    userid: kubernetes
    # uncomment the following to use rbd-nbd as mounter on supported nodes
    # mounter: rbd-nbd
-   # fsType: xfs
-   # uncomment the following line to enable multi-attach on RBD volumes
-   # multiNodeWritable: enabled
 reclaimPolicy: Delete

pkg/rbd/controllerserver.go

@@ -21,7 +21,6 @@ import (
 	"os/exec"
 	"sort"
 	"strconv"
-	"strings"
 	"syscall"
 
 	csicommon "github.com/ceph/ceph-csi/pkg/csi-common"
@@ -94,16 +93,25 @@ func (cs *ControllerServer) validateVolumeReq(req *csi.CreateVolumeRequest) erro
 func parseVolCreateRequest(req *csi.CreateVolumeRequest) (*rbdVolume, error) {
 	// TODO (sbezverk) Last check for not exceeding total storage capacity
 
-	// MultiNodeWriters are accepted but they're only for special cases, and we skip the watcher checks for them which isn't the greatest
+	isMultiNode := false
-	// let's make sure we ONLY skip that if the user is requesting a MULTI Node accessible mode
+	isBlock := false
-	disableMultiWriter := true
+	for _, cap := range req.VolumeCapabilities {
-	for _, am := range req.VolumeCapabilities {
+		// RO modes need to be handled indepedently (ie right now even if access mode is RO, they'll be RW upon attach)
-		if am.GetAccessMode().GetMode() != csi.VolumeCapability_AccessMode_SINGLE_NODE_WRITER {
+		if cap.GetAccessMode().GetMode() == csi.VolumeCapability_AccessMode_MULTI_NODE_MULTI_WRITER {
-			disableMultiWriter = false
+			isMultiNode = true
+		}
+		if cap.GetBlock() != nil {
+			isBlock = true
 		}
 	}
 
-	rbdVol, err := getRBDVolumeOptions(req.GetParameters(), disableMultiWriter)
+	// We want to fail early if the user is trying to create a RWX on a non-block type device
+	if isMultiNode && !isBlock {
+		return nil, status.Error(codes.InvalidArgument, "multi node access modes are only supported on rbd `block` type volumes")
+	}
+
+	// if it's NOT SINGLE_NODE_WRITER and it's BLOCK we'll set the parameter to ignore the in-use checks
+	rbdVol, err := getRBDVolumeOptions(req.GetParameters(), (isMultiNode && isBlock))
 	if err != nil {
 		return nil, status.Error(codes.InvalidArgument, err.Error())
 	}
@@ -344,20 +352,11 @@ func (cs *ControllerServer) ListVolumes(ctx context.Context, req *csi.ListVolume
 // ValidateVolumeCapabilities checks whether the volume capabilities requested
 // are supported.
 func (cs *ControllerServer) ValidateVolumeCapabilities(ctx context.Context, req *csi.ValidateVolumeCapabilitiesRequest) (*csi.ValidateVolumeCapabilitiesResponse, error) {
-	params := req.GetParameters()
-	multiWriter := params["multiNodeWritable"]
-	if strings.ToLower(multiWriter) == "enabled" {
-		klog.V(3).Info("detected multiNodeWritable parameter in Storage Class, allowing multi-node access modes")
-
-	} else {
 	for _, cap := range req.VolumeCapabilities {
 		if cap.GetAccessMode().GetMode() != csi.VolumeCapability_AccessMode_SINGLE_NODE_WRITER {
 			return &csi.ValidateVolumeCapabilitiesResponse{Message: ""}, nil
 		}
 	}
-
-	}
-
 	return &csi.ValidateVolumeCapabilitiesResponse{
 		Confirmed: &csi.ValidateVolumeCapabilitiesResponse_Confirmed{
 			VolumeCapabilities: req.VolumeCapabilities,

pkg/rbd/nodeserver.go

@@ -48,6 +48,7 @@ type NodeServer struct {
 func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublishVolumeRequest) (*csi.NodePublishVolumeResponse, error) {
 	targetPath := req.GetTargetPath()
 	targetPathMutex.LockKey(targetPath)
+	disableInUseChecks := false
 
 	defer func() {
 		if err := targetPathMutex.UnlockKey(targetPath); err != nil {
@@ -71,18 +72,20 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
 		return &csi.NodePublishVolumeResponse{}, nil
 	}
 
-	// if our access mode is a simple SINGLE_NODE_WRITER we're going to ignore the SC directive and use the
+	// MULTI_NODE_MULTI_WRITER is supported by default for Block access type volumes
-	// watcher still
+	if req.VolumeCapability.AccessMode.Mode == csi.VolumeCapability_AccessMode_MULTI_NODE_MULTI_WRITER {
-	ignoreMultiWriterEnabled := true
+		if isBlock {
-	if req.VolumeCapability.AccessMode.Mode != csi.VolumeCapability_AccessMode_SINGLE_NODE_WRITER {
+			disableInUseChecks = true
-		ignoreMultiWriterEnabled = false
+		} else {
+			klog.Warningf("MULTI_NODE_MULTI_WRITER currently only supported with volumes of access type `block`, invalid AccessMode for volume: %v", req.GetVolumeId())
+			return nil, status.Error(codes.InvalidArgument, "rbd: RWX access mode request is only valid for volumes with access type `block`")
+		}
 	}
 
-	volOptions, err := getRBDVolumeOptions(req.GetVolumeContext(), ignoreMultiWriterEnabled)
+	volOptions, err := getRBDVolumeOptions(req.GetVolumeContext(), disableInUseChecks)
 	if err != nil {
 		return nil, err
 	}
-
 	volOptions.VolName = volName
 	// Mapping RBD image
 	devicePath, err := attachRBDImage(volOptions, volOptions.UserID, req.GetSecrets())

pkg/rbd/rbd.go

@@ -105,10 +105,12 @@ func (r *Driver) Run(driverName, nodeID, endpoint string, containerized bool, ca
 		csi.ControllerServiceCapability_RPC_CLONE_VOLUME,
 	})
 
-	// TODO: JDG Should also look at remaining modes like MULT_NODE_READER (SINGLE_READER)
+	// We only support the multi-writer option when using block, but it's a supported capability for the plugin in general
+	// In addition, we want to add the remaining modes like MULTI_NODE_READER_ONLY,
+	// MULTI_NODE_SINGLE_WRITER etc, but need to do some verification of RO modes first
+	// will work those as follow up features
 	r.cd.AddVolumeCapabilityAccessModes(
-		[]csi.VolumeCapability_AccessMode_Mode{
+		[]csi.VolumeCapability_AccessMode_Mode{csi.VolumeCapability_AccessMode_SINGLE_NODE_WRITER,
-			csi.VolumeCapability_AccessMode_SINGLE_NODE_WRITER,
 			csi.VolumeCapability_AccessMode_MULTI_NODE_MULTI_WRITER})
 
 	// Create GRPC servers

pkg/rbd/rbd_attach.go

@@ -258,6 +258,7 @@ func attachRBDImage(volOptions *rbdVolume, userID string, credentials map[string
 			Factor:   rbdImageWatcherFactor,
 			Steps:    rbdImageWatcherSteps,
 		}
+
 		err = waitForrbdImage(backoff, volOptions, userID, credentials)
 
 		if err != nil {
@@ -313,16 +314,12 @@ func waitForrbdImage(backoff wait.Backoff, volOptions *rbdVolume, userID string,
 		if err != nil {
 			return false, fmt.Errorf("fail to check rbd image status with: (%v), rbd output: (%s)", err, rbdOutput)
 		}
-		// In the case of multiattach we want to short circuit the retries when used (so r`if used; return used`)
+		if (volOptions.DisableInUseChecks) && (used) {
-		// otherwise we're setting this to false which translates to !ok, which means backoff and try again
+			klog.V(2).Info("valid multi-node attach requested, ignoring watcher in-use result")
-		// NOTE: we ONLY do this if an multi-node access mode is requested for this volume
-		if (strings.ToLower(volOptions.MultiNodeWritable) == "enabled") && (used) {
-			klog.V(2).Info("detected MultiNodeWritable enabled, ignoring watcher in-use result")
 			return used, nil
 		}
 		return !used, nil
 	})
-
 	// return error if rbd image has not become available for the specified timeout
 	if err == wait.ErrWaitTimeout {
 		return fmt.Errorf("rbd image %s is still being used", imagePath)

pkg/rbd/rbd_util.go

@@ -51,7 +51,7 @@ type rbdVolume struct {
 	AdminID            string `json:"adminId"`
 	UserID             string `json:"userId"`
 	Mounter            string `json:"mounter"`
-	MultiNodeWritable  string `json:"multiNodeWritable"`
+	DisableInUseChecks bool   `json:"disableInUseChecks"`
 }
 
 type rbdSnapshot struct {
@@ -227,7 +227,7 @@ func execCommand(command string, args []string) ([]byte, error) {
 	return cmd.CombinedOutput()
 }
 
-func getRBDVolumeOptions(volOptions map[string]string, ignoreMultiNodeWritable bool) (*rbdVolume, error) {
+func getRBDVolumeOptions(volOptions map[string]string, disableInUseChecks bool) (*rbdVolume, error) {
 	var ok bool
 	rbdVol := &rbdVolume{}
 	rbdVol.Pool, ok = volOptions["pool"]
@@ -260,13 +260,11 @@ func getRBDVolumeOptions(volOptions map[string]string, ignoreMultiNodeWritable b
 		}
 
 	}
-	getCredsFromVol(rbdVol, volOptions)
 
-	klog.V(3).Infof("ignoreMultiNodeWritable flag in parse getRBDVolumeOptions is: %v", ignoreMultiNodeWritable)
+	klog.V(3).Infof("setting disableInUseChecks on rbd volume to: %v", disableInUseChecks)
-	// If the volume we're working with is NOT requesting multi-node attach then don't treat it special, ignore the setting in the SC and just keep our watcher checks
+	rbdVol.DisableInUseChecks = disableInUseChecks
-	if !ignoreMultiNodeWritable {
+
-		rbdVol.MultiNodeWritable = volOptions["multiNodeWritable"]
+	getCredsFromVol(rbdVol, volOptions)
-	}
 	return rbdVol, nil
 }