Bug 1251327 - backport EC fast reads
Summary: backport EC fast reads
Keywords:
Status: CLOSED NEXTRELEASE
Alias: None
Product: Red Hat Ceph Storage
Classification: Red Hat Storage
Component: RADOS
Version: 1.3.0
Hardware: Unspecified
OS: Unspecified
unspecified
medium
Target Milestone: rc
: 1.3.4
Assignee: Samuel Just
QA Contact: ceph-qe-bugs
URL:
Whiteboard:
Depends On:
Blocks:
TreeView+ depends on / blocked
 
Reported: 2015-08-07 01:45 UTC by Sage Weil
Modified: 2022-02-21 18:23 UTC (History)
5 users (show)

Fixed In Version:
Doc Type: Bug Fix
Doc Text:
Clone Of:
Environment:
Last Closed: 2016-08-03 21:27:06 UTC
Embargoed:

Attachments (Terms of Use)


Links
System ID Private Priority Status Summary Last Updated
Ceph Project Bug Tracker 12316 0 None None None Never
Red Hat Issue Tracker RHCEPH-3398 0 None None None 2022-02-21 18:23:19 UTC

Description Sage Weil 2015-08-07 01:45:45 UTC 
Backport EC fast read feature from Yahoo to hammer/1.3.x:

  https://github.com/ceph/ceph/pull/5309

This optionally lowers the latency on reads from an EC pool at the expense of a bit of extra wasted IO and CPU by reading from all shards and decoding once K out of K+M replies come back.
Comment 2 Ken Dreyer (Red Hat) 2016-08-03 19:46:29 UTC 
It looks like this was fixed in some version of Hammer but I can't tell which version.
Comment 3 Samuel Just 2016-08-03 21:19:11 UTC 
This hasn't been backported to hammer.  I don't really think it's a good idea.
Comment 4 Ken Dreyer (Red Hat) 2016-08-03 21:27:06 UTC 
Thanks Sam. Looks like the feature is in Jewel so users can upgrade to RHCS 2 for this.
Note You need to log in before you can comment on or make changes to this bug.