cluster: RHEL56 - rgmanager: Work around lockspace release hang

[Lon Hohberger]

Gitweb:        http://git.fedorahosted.org/git/cluster.git?p=cluster.git;a=commitdiff;h=38c...
Commit:        38ca868f6ee9c7ebb4059b7a4983734935c80ca4
Parent:        848f084f51e9890e41071e8a58b3878cedce0dd7
Author:        Lon Hohberger 
AuthorDate:    Thu Oct 28 17:15:16 2010 -0400
Committer:     Lon Hohberger 
CommitterDate: Fri Oct 29 09:57:17 2010 -0400

rgmanager: Work around lockspace release hang

If CMAN dies uncleanly (ex: because of cman_kill_node() call
on another cluster node), rgmanager would hang trying to
release the lock space, preventing it from exiting and causing
it to spin.

This patch works around the hang during unclean shutdown
situations.

Resolves: rhbz#639961

Signed-off-by: Lon Hohberger 
Reviewed-by: Fabio M. Di Nitto 
---
 rgmanager/src/daemons/main.c |   11 ++++++++---
 1 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/rgmanager/src/daemons/main.c b/rgmanager/src/daemons/main.c
index 64c32a3..52e38bc 100644
--- a/rgmanager/src/daemons/main.c
+++ b/rgmanager/src/daemons/main.c
@@ -64,7 +64,7 @@ int node_has_fencing(int nodeid);
 int fence_domain_joined(void);

int cluster_timeout = 10;
-int shutdown_pending = 0, running = 1, need_reconfigure = 0;
+int shutdown_pending = 0, running = 1, need_reconfigure = 0, dying = 0;
 char debug = 0; /* XXX* */
 static int signalled = 0;
 static int port = RG_PORT;
@@ -676,12 +676,14 @@ handle_cluster_event(msgctx_t *ctx)
    	msg_receive(ctx, NULL, 0, 0);
    	clulog(LOG_WARNING, "#67: Shutting down uncleanly\n");
    	rg_set_inquorate();
-		rg_doall(RG_INIT, 1, "Emergency stop of %s");
+		rg_doall(RG_INIT, 1, "Emergency stop of %s\n");
    	rg_clear_initialized(0);
 #if defined(LIBCMAN_VERSION) && LIBCMAN_VERSION >= 2
    	/* cman_replyto_shutdown() */
 #endif
    	running = 0;
+		dying = 1; /* XXX Hack to work around hang during
+		              unclean lockspace release */
    	break;
    }

@@ -1180,7 +1182,10 @@ main(int argc, char **argv)
    	cleanup(cluster_ctx);

out_cleanup:
-	clu_lock_finished(rgmanager_lsname);
+	/* XXX - This hangs if CMAN has died, so we skip if we are
+	 *       exiting uncleanly. */
+	if (!dying)
+		clu_lock_finished(rgmanager_lsname);

out:
    clulog(LOG_NOTICE, "Shutdown complete, exiting\n");