From: Sage Weil <sage@newdream.net>
Date: Mon, 15 Feb 2010 20:11:51 +0000 (-0800)
Subject: ceph: reset osd connections after fault
X-Git-Url: http://drtracing.org/?a=commitdiff_plain;h=153a008bf7915ea9127341409170cb197d111282;p=deliverable%2Flinux.git

ceph: reset osd connections after fault

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>
---

diff --git a/fs/ceph/osd_client.c b/fs/ceph/osd_client.c
index 7f8a26fdcc2c..fa0f73703954 100644
--- a/fs/ceph/osd_client.c
+++ b/fs/ceph/osd_client.c
@@ -369,7 +369,6 @@ static void osd_reset(struct ceph_connection *con)
 		return;
 	dout("osd_reset osd%d\n", osd->o_osd);
 	osdc = osd->o_osdc;
-	osd->o_incarnation++;
 	down_read(&osdc->map_sem);
 	kick_requests(osdc, osd);
 	up_read(&osdc->map_sem);
@@ -921,7 +920,9 @@ static void kick_requests(struct ceph_osd_client *osdc,
 
 	dout("kick_requests osd%d\n", kickosd ? kickosd->o_osd : -1);
 	mutex_lock(&osdc->request_mutex);
-	if (!kickosd) {
+	if (kickosd) {
+		__reset_osd(osdc, kickosd);
+	} else {
 		for (p = rb_first(&osdc->osds); p; p = n) {
 			struct ceph_osd *osd =
 				rb_entry(p, struct ceph_osd, o_node);