Public bug reported:
Steps to reproduce:
1. juju deploy a fresh squid ceph cluster
2. juju add-unit ceph-fs
3. Observe the existing mds got restarted unexpectedly.
The time required for mds failover process to complete can take several
minutes, especially for large scaled cephfs cluster. During the failover,
clients operation will be completely stalled, which may lead to notable
business impact.
We should only avoid this unnecessary mds restart.
** Affects: ceph (Ubuntu)
Importance: Undecided
Status: New
--
You received this bug notification because you are a member of Ubuntu
Bugs, which is subscribed to Ubuntu.
https://bugs.launchpad.net/bugs/2127242
Title:
Existing mds restarted unexpectedly when adding new ceph-fs unit
To manage notifications about this bug go to:
https://bugs.launchpad.net/ubuntu/+source/ceph/+bug/2127242/+subscriptions
--
ubuntu-bugs mailing list
[email protected]
https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
