Heilig IOS
Activity
09/22/2020
- 06:15 PM CephFS Bug #47582: MDS failover takes 10-15 hours: Ceph MDS stays in "up:replay" state for hours
- Thank you for the provided information.
I will test the MDS failover in a day. Quick question regarding "mds_log_m... - 02:40 PM CephFS Bug #47582: MDS failover takes 10-15 hours: Ceph MDS stays in "up:replay" state for hours
- Still no changes. The "mds_log_max_segments" didn't help. The MDS failover is running for 30 minutes already. What el...
- 02:04 PM CephFS Bug #47582: MDS failover takes 10-15 hours: Ceph MDS stays in "up:replay" state for hours
- I decreased it with these commands:...
- 01:47 PM CephFS Bug #47582: MDS failover takes 10-15 hours: Ceph MDS stays in "up:replay" state for hours
- Current value: mds_log_max_segments = 100000
- 01:24 PM CephFS Bug #47582: MDS failover takes 10-15 hours: Ceph MDS stays in "up:replay" state for hours
- I have this issue right now. No, there is no "mds behind on trim" warning.
- 12:16 PM CephFS Bug #47582 (Rejected): MDS failover takes 10-15 hours: Ceph MDS stays in "up:replay" state for hours
- We have 9 nodes Ceph cluster. Ceph version is 15.2.5. The cluster has 175 OSD (HDD) + 3 NVMe for cache tier for "ceph...
Also available in: Atom