[sheepdog] [PATCH v4 2/2] sheep/cluster: re-create znode of 'lock-id' if it isn't exists

[Robin Dong]

From: Robin Dong <sanbai at taobao.com>

When a sheep daemon call zk_unlock(), it will remove the whole znode of 'lock-id' and
make zoo_create() fail in zk_lock() which called by another sheep daemon.
To avoid this, we should try to create a znode of 'lock-id' if zoo_create() fail.

Signed-off-by: Robin Dong <sanbai at taobao.com>
---
 sheep/cluster/zookeeper.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/sheep/cluster/zookeeper.c b/sheep/cluster/zookeeper.c
index fd6dcaf..784bba3 100644
--- a/sheep/cluster/zookeeper.c
+++ b/sheep/cluster/zookeeper.c
@@ -1240,6 +1240,7 @@ static void zk_lock(uint64_t lock_id)
 	int rc, len = MAX_NODE_STR_LEN;
 	char *my_path;
 	char parent[MAX_NODE_STR_LEN];
+	char parent_node[MAX_NODE_STR_LEN];
 	char lowest_seq_path[MAX_NODE_STR_LEN];
 	char owner_name[MAX_NODE_STR_LEN];
 	struct cluster_lock *cluster_lock;
@@ -1251,21 +1252,25 @@ static void zk_lock(uint64_t lock_id)
 	/* compete owner of lock is just like zk_compete_master() */
 	snprintf(parent, MAX_NODE_STR_LEN, LOCK_ZNODE "/%"PRIu64"/",
 		 cluster_lock->id);
+	snprintf(parent_node, MAX_NODE_STR_LEN, LOCK_ZNODE "/%"PRIu64,
+		 cluster_lock->id);
 	while (true) {
 		rc = zk_create_node(parent, "", 0, &ZOO_OPEN_ACL_UNSAFE,
 				     flags, my_path, MAX_NODE_STR_LEN);
 		if (rc == ZOK)
 			break;
+		if (rc == ZNONODE) {
+			zk_init_node(parent_node);
+			continue;
+		}
 		sd_err("failed to create path:%s, %s", my_path, zerror(rc));
 		zk_wait();
 	}
 	sd_debug("create path %s success", my_path);
 
 	/* create node ok now */
-	snprintf(parent, MAX_NODE_STR_LEN, LOCK_ZNODE "/%"PRIu64,
-		 cluster_lock->id);
 	while (true) {
-		zk_get_least_seq(parent, lowest_seq_path, MAX_NODE_STR_LEN,
+		zk_get_least_seq(parent_node, lowest_seq_path, MAX_NODE_STR_LEN,
 				 owner_name, &len);
 
 		/* I got the lock */
-- 
1.7.12.4