Project

General

Profile

Bug #651

osd_client: need to recalculate request mapping for every osdmap incremental

Added by Sage Weil over 8 years ago. Updated over 8 years ago.

Status:
Resolved
Priority:
High
Assignee:
Category:
libceph
Target version:
Start date:
12/14/2010
Due date:
% Done:

0%

Spent time:
Source:
Tags:
Backport:
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:

Description

Currently if we get an osdmap message with multiple incrementals, and a request maps to a different osd and then back to the original one, the osd_client won't notice and the request will not be resent. We will eventually time out and resubmit, but it will take a long time (and timeouts can be disabled by the admin).

History

#1 Updated by Sage Weil over 8 years ago

  • Target version set to v2.6.38

#2 Updated by Sage Weil over 8 years ago

  • Assignee set to Sage Weil

#3 Updated by Sage Weil over 8 years ago

  • Category set to libceph
  • Status changed from New to Resolved

fix in usntable, commit:05d7263709810c998d396a47dcf09ccb2f643c90 'libceph: fix osd request queuing on osdmap updates'

Also available in: Atom PDF