mirrors/ceph-csi
1
0
Fork 0
mirror of https://github.com/ceph/ceph-csi.git synced 2024-11-22 22:30:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

rbd: mark image ready when image state is up+unknown

Browse Source 
To recover from split brain (up+error) state the image need to be
demoted and requested for resync on site-a and then the image on site-b
should gets demoted.The volume should be marked to ready=true when the
image state on both the clusters are up+unknown because during the last
snapshot syncing the data gets copied first and then image state on the
site-a changes to up+unknown.

If the image state on both the sites are up+unknown consider that
complete data is synced as the last snapshot
gets exchanged between the clusters.

* create 10 GB of file and validate the data after resync

* Do Failover when the site-a goes down
* Force promote the image and write data in GiB
* Once the site-a comes back, Demote the image and issue resync
* Demote the image on site-b
* The status will get reflected on the other site when the last
  snapshot sync happens
* The image will go to up+unknown state. and complete data will
  be copied to site a
* Promote the image on site-a and use it

```bash
csi-vol-5633715e-a7eb-11eb-bebb-0242ac110006:
  global_id:   e7f9ec55-06ab-46cb-a1ae-784be75ed96d
  state:       up+unknown
  description: remote image demoted
  service:     a on minicluster1
  last_update: 2021-04-28 07:11:56
  peer_sites:
    name: e47e29f4-96e8-44ed-b6c6-edf15c5a91d6-rook-ceph
    state: up+unknown
    description: remote image demoted
    last_update: 2021-04-28 07:11:41
 ```

* Do Failover when the site-a goes down
* Force promote the image on site-b and write data in GiB
* Demote the image on site-b
* Once the site-a comes back, Demote the image on site-a
* The images on the both site will go to split brain state

```bash
csi-vol-37effcb5-a7f1-11eb-bebb-0242ac110006:
  global_id:   115c3df9-3d4f-4c04-93a7-531b82155ddf
  state:       up+error
  description: split-brain
  service:     a on minicluster2
  last_update: 2021-04-28 07:25:41
  peer_sites:
    name: abbda0f0-0117-4425-8cb2-deb4c853da47-rook-ceph
    state: up+error
    description: split-brain
    last_update: 2021-04-28 07:25:26
```
* Issue resync
* The images cannot be resynced because when we issue resync
  on site a the image on site-b was in demoted state
* To recover from this state (promote and then demote the
  image on site-b after sometime)

```bash
csi-vol-37effcb5-a7f1-11eb-bebb-0242ac110006:
  global_id:   115c3df9-3d4f-4c04-93a7-531b82155ddf
  state:       up+unknown
  description: remote image demoted
  service:     a on minicluster1
  last_update: 2021-04-28 07:32:56
  peer_sites:
    name: e47e29f4-96e8-44ed-b6c6-edf15c5a91d6-rook-ceph
    state: up+unknown
    description: remote image demoted
    last_update: 2021-04-28 07:32:41
```
* Once the data is copied we can see that  the image state
  is moved to up+unknown on both sites
* Promote the image on site-a and use it

Signed-off-by: Madhu Rajanna <madhupr007@gmail.com>
This commit is contained in:
Madhu Rajanna 2021-04-28 13:16:00 +05:30 committed by mergify[bot]
parent 90fd12629f
commit 07a916b84d
1 changed files with 9 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
internal/rbd/replicationcontrollerserver.go
View File

@ -43,15 +43,6 @@ const (
type imageMirroringState string type imageMirroringState string
const ( const (
// If the state is up+replaying, then mirroring is functioning properly.
// up means the rbd-mirror daemon is running, and replaying means
// this image is the target for replication from another storage cluster.
upAndReplaying imageMirroringState = "up+replaying"
// If the state is up+stopped means the rbd-mirror daemon is
// running and stopped means the image is not a target for replication from
// another cluster
upAndStopped imageMirroringState = "up+stopped"
// If the state is up+unknown means the rbd-mirror daemon is // If the state is up+unknown means the rbd-mirror daemon is
// running and the image is demoted on both the clusters. // running and the image is demoted on both the clusters.
upAndUnknown imageMirroringState = "up+unknown" upAndUnknown imageMirroringState = "up+unknown"
@ -445,20 +436,16 @@ func (rs *ReplicationServer) ResyncVolume(ctx context.Context,
} }
ready := false ready := false
state := imageMirroringState(mirrorStatus.State) state := imageMirroringState(mirrorStatus.State)
if state == upAndStopped || state == upAndReplaying { // To recover from split brain (up+error) state the image need to be
// Make sure the peer site image state is up and stopped // demoted and requested for resync on site-a and then the image on site-b
ready = true // should be demoted. The volume should be marked to ready=true when the
for _, s := range mirrorStatus.PeerSites { // image state on both the clusters are up+unknown because during the last
if imageMirroringState(s.State) != upAndStopped { // snapshot syncing the data gets copied first and then image state on the
util.UsefulLog(ctx, "peer site name=%s, mirroring state=%s, description=%s and lastUpdate=%s", s.SiteName, s.State, s.Description, s.LastUpdate) // site-a changes to up+unknown.
ready = false
}
}
}
// when the images are demoted on both clusters and user requests for the // If the image state on both the sites are up+unknown consider that
// resync of the image, the image mirror state will be unknown state in // complete data is synced as the last snapshot
// both clusters. // gets exchanged between the clusters.
if state == upAndUnknown { if state == upAndUnknown {
ready = true ready = true
for _, s := range mirrorStatus.PeerSites { for _, s := range mirrorStatus.PeerSites {