forked from rook/rook
parth-gr
0999cf9b56
mds liveness probe call ceph cmd with mons and keyring, but ceph actually looks for the ceph keyring at default folder first and then use the cmd line keyring path, So to avoid that use ceph_args env variable to expose the keyring folder path, Workaround for https://tracker.ceph.com/issues/70167 closes: https://github.com/rook/rook/issues/15373 Signed-off-by: parth-gr <partharora1010@gmail.com>
31 lines
1.3 KiB
Bash
31 lines
1.3 KiB
Bash
#!/usr/bin/env bash
|
|
# do not use 'set -e -u' etc. because it is important to only fail this probe when failure is certain
|
|
# spurious failures risk destabilizing ceph or the filesystem
|
|
|
|
MDS_ID="{{ .MdsId }}"
|
|
FILESYSTEM_NAME="{{ .FilesystemName }}"
|
|
KEYRING="{{ .Keyring }}"
|
|
CMD_TIMEOUT="{{ .CmdTimeout }}"
|
|
|
|
export CEPH_ARGS="--keyring $KEYRING" # workaround for https://tracker.ceph.com/issues/70167
|
|
outp="$(ceph fs dump --mon-host="$ROOK_CEPH_MON_HOST" --mon-initial-members="$ROOK_CEPH_MON_INITIAL_MEMBERS" --name="mds.$MDS_ID" --connect-timeout="$CMD_TIMEOUT" --format json)"
|
|
rc=$?
|
|
if [ $rc -ne 0 ]; then
|
|
echo "ceph MDS dump check failed with the following output:"
|
|
echo "$outp"
|
|
echo "passing probe to avoid restarting MDS. cannot determine if MDS is unhealthy. restarting MDS risks destabilizing ceph/filesystem, which is likely unreachable or in error state"
|
|
exit 0
|
|
fi
|
|
|
|
# get the active and standby MDS in the fs map
|
|
standbyMds=$(echo "$outp" | jq ".standbys | map(.name) | any(.[]; . == \"$MDS_ID\")")
|
|
activeMds=$(echo "$outp" | jq ".filesystems[] | select(.mdsmap.fs_name == \"$FILESYSTEM_NAME\") | .mdsmap.info | map(.name) | any(.[]; . == \"$MDS_ID\")")
|
|
|
|
if [[ $standbyMds == true || $activeMds == true ]]; then
|
|
echo "MDS ID present in MDS map, no need to re-start the container"
|
|
exit 0
|
|
fi
|
|
|
|
echo "Error: MDS ID not present in MDS map"
|
|
exit 1
|