Cleanup #929
closed
mds: make journal replay readahead less silly
Added by Sage Weil about 13 years ago.
Updated over 7 years ago.
Description
I think the journal replay is reading large chunks of the journal, then processing, then repeating. It should be processing data as it gets it, but prefetching N segments ahead of the read position.
Verify that it's doing the right thing, and if not, fix!
- Status changed from New to Resolved
- Assignee set to Sage Weil
- Target version set to v0.27
- Translation missing: en.field_position set to 545
- Translation missing: en.field_story_points set to 3
- Translation missing: en.field_position deleted (
561)
- Translation missing: en.field_position set to 344
- Translation missing: en.field_position deleted (
346)
- Translation missing: en.field_position set to 11
- Project changed from Ceph to CephFS
- Category deleted (
1)
- Target version deleted (
v0.27)
Bulk updating project=ceph category=mds bugs so that I can remove the MDS category from the Ceph project to avoid confusion.
Also available in: Atom
PDF