Project

General

Profile

Feature #6029

cachepool: osd: separate object version from pg version

Added by Sage Weil over 9 years ago. Updated over 9 years ago.

Status:
Resolved
Priority:
Normal
Assignee:
Greg Farnum
Category:
-
Target version:
v0.68 - continued
% Done:

0%

Source:
other
Tags:
Backport:
Reviewed:
Affected Versions:
Pull request ID:

History

#1 Updated by Sage Weil over 9 years ago

  • Subject changed from osd: separate object version from pg version to osd: cachepool: separate object version from pg version

#2 Updated by Samuel Just over 9 years ago

librados visible version seperate from PG version. There must also be an Objecter interface usable (in the future) from the OSD for specifying the new version on a write so that the cache pool osd can update the slow pool with the actual new version on demotion.

#3 Updated by Sage Weil over 9 years ago

  • Subject changed from osd: cachepool: separate object version from pg version to cachepool: osd: separate object version from pg version

#4 Updated by Sage Weil over 9 years ago

  • translation missing: en.field_story_points set to 3.00

#5 Updated by Sage Weil over 9 years ago

  • Assignee set to Greg Farnum

#6 Updated by Greg Farnum over 9 years ago

  • Status changed from New to In Progress

Huh, thought I updated this already. Sage went over it and liked what he'd seen, but there were some test failures I need to look into.

#7 Updated by Greg Farnum over 9 years ago

  • Status changed from In Progress to 7

A-hah, I think I found it. Running an updated branch through a short set of tests and updating the documentation, then will clean up the bug fixes and docs and do final tests for merging.

#8 Updated by Greg Farnum over 9 years ago

  • Status changed from 7 to Fix Under Review

There's a pull request at https://github.com/ceph/ceph/pull/549. Would also like to schedule another suite on it, but I don't expect any issues since the only issue we saw passed through the rbd suite (including a previous trigger) already.

#9 Updated by Greg Farnum over 9 years ago

  • Status changed from Fix Under Review to Resolved

I merged this in this morning, be9a39b766ba825ef348ca6e2de1f4db7c091dff

A suite run saw a lot of the btrfs locking failures, but the only other thing that turned up was a scrub failure which I realized this morning (after running it all night) was actually on the monitors. :D

Also available in: Atom PDF