Bug #2365
osd: don't notice when nodes in probe set are down
| Status: | Resolved | Start date: | 04/30/2012 | |
|---|---|---|---|---|
| Priority: | Urgent | Due date: | ||
| Assignee: | - | % Done: | 0% | |
| Category: | OSD | Spent time: | - | |
| Target version: | v0.47 | |||
| Source: | Development | Severity: | ||
| Backport: | Reviewed: | |||
| Tags: |
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 about 1 year ago
- Status changed from Verified to Resolved