starlingx/ansible-playbooks
Code Issues Proposed changes

Merge "Check cephfs recovery commands during rook-ceph restore"

Browse Source
This commit is contained in:
Zuul 2025-04-08 15:01:43 +00:00 committed by Gerrit Code Review
commit 72f2833e89
1 changed files with 9 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
playbookconfig/src/playbooks/roles/recover-rook-ceph-data/files/recover_rook_ceph.py
View File

@ -415,12 +415,15 @@ data:
# Try to recover from some common errors
# The timeout command was used because depending on the status of the cluster, it can get stuck
# on "cephfs-journal-tool" commands. But this will not cause any problems in recovery.
timeout 180 cephfs-journal-tool --rank=${FS_NAME}:0 event recover_dentries summary
timeout 180 cephfs-journal-tool --rank=${FS_NAME}:0 journal reset
cephfs-table-tool ${FS_NAME}:0 reset session
cephfs-table-tool ${FS_NAME}:0 reset snap
cephfs-table-tool ${FS_NAME}:0 reset inode
# on "cephfs" commands. But this will not cause any problems in recovery.
CEPHFS_CMD_TIMEOUT=180
timeout ${CEPHFS_CMD_TIMEOUT} cephfs-journal-tool --rank=${FS_NAME}:0 event recover_dentries summary
if [ $? -eq 0 ]; then
timeout ${CEPHFS_CMD_TIMEOUT} cephfs-journal-tool --rank=${FS_NAME}:0 journal reset
timeout ${CEPHFS_CMD_TIMEOUT} cephfs-table-tool ${FS_NAME}:0 reset session
timeout ${CEPHFS_CMD_TIMEOUT} cephfs-table-tool ${FS_NAME}:0 reset snap
timeout ${CEPHFS_CMD_TIMEOUT} cephfs-table-tool ${FS_NAME}:0 reset inode
fi
fi
kubectl -n rook-ceph scale deployment -l app=rook-ceph-osd --replicas 1