ceph: reset osd connections after fault
authorSage Weil <sage@newdream.net>
Mon, 15 Feb 2010 20:11:51 +0000 (12:11 -0800)
committerSage Weil <sage@newdream.net>
Mon, 15 Feb 2010 20:11:51 +0000 (12:11 -0800)
A single osd connection fault (e.g. tcp disconnect) wasn't
reopening the connection, which causes all current and future
requests for that osd to hang.

Signed-off-by: Sage Weil <sage@newdream.net>

No differences found