Project

General

Profile

Bug #2365

osd: don't notice when nodes in probe set are down

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

Status:
Resolved
Priority:
Urgent
Assignee:
-
Category:
OSD
Target version:
% Done:

0%

Source:
Development
Tags:
Backport:
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Pull request ID:
Crash signature:

Description

we currently do

set<int> new_peers;
if (role == 0) {
for (unsigned i=0; i<acting.size(); i++)
new_peers.insert(acting[i]);
for (unsigned i=0; i<up.size(); i++)
new_peers.insert(up[i]);
for (map<int,pg_info_t>::iterator p = peer_info.begin(); p != peer_info.end(); ++p)
new_peers.insert(p->first);
}

but we need to include anything in the prior probe set.. and/or anything else we might depend on to recover. not sure the cleanest way to slurp that out of a recovery state machine state...

History

#1 Updated by Samuel Just over 8 years ago

  • Status changed from 12 to Resolved

Also available in: Atom PDF