Feature #23979
Limit pg log length during recovery/backfill so that we don't run out of memory.
% Done:
0%
Source:
Development
Tags:
Backport:
mimic, luminous
Reviewed:
Affected Versions:
Component(RADOS):
Pull request ID:
Description
This means if there's another failure, we'll need to restart backfill or go from recovery to backfill, but that's better than running out of memory.
Treating osd_max_pg_log_entries as a hard cap should be sufficient.
Related issues
History
#1 Updated by David Zafman almost 6 years ago
- Source set to Development
- Backport set to luminous
#2 Updated by David Zafman almost 6 years ago
- Assignee changed from David Zafman to Josh Durgin
#3 Updated by Josh Durgin almost 6 years ago
- Assignee changed from Josh Durgin to Neha Ojha
Initial testing is referenced here: https://github.com/ceph/ceph/pull/21508
#4 Updated by Josh Durgin almost 6 years ago
- Backport changed from luminous to mimic, luminous
#5 Updated by Neha Ojha over 5 years ago
- Status changed from 12 to Fix Under Review
#6 Updated by Josh Durgin over 5 years ago
- Status changed from Fix Under Review to Pending Backport
#7 Updated by Nathan Cutler over 5 years ago
- Copied to Backport #24988: luminous: Limit pg log length during recovery/backfill so that we don't run out of memory. added
#8 Updated by Nathan Cutler over 5 years ago
- Copied to Backport #24989: mimic: Limit pg log length during recovery/backfill so that we don't run out of memory. added
#9 Updated by Neha Ojha over 5 years ago
- Related to Bug #25198: FAILED assert(trim_to <= info.last_complete) in PGLog::trim() added
#10 Updated by Neha Ojha over 5 years ago
- Related to Bug #26868: PGLog.cc: saw valgrind issues while accessing complete_to->version added
#11 Updated by Nathan Cutler over 5 years ago
- Status changed from Pending Backport to Resolved