From: Ruoyu <lian...@ucweb.com>
zookeeper session establishment is asynchronous. It means that
we cannot judge the session is connected by checking the
return value of the func zookeeper_init. Instead, we should
check the zookeeper handler's state in a loop to ensure
the session is connected.
Signed-off-by: Ruoyu <lian...@ucweb.com>
Signed-off-by: Hitoshi Mitake <mitake.hito...@lab.ntt.co.jp>
---
sheep/cluster/zookeeper.c | 16 ++++++++++++++--
1 file changed, 14 insertions(+), 2 deletions(-)
diff --git a/sheep/cluster/zookeeper.c b/sheep/cluster/zookeeper.c
index 30a5f35..3908d01 100644
--- a/sheep/cluster/zookeeper.c
+++ b/sheep/cluster/zookeeper.c
@@ -1350,7 +1350,7 @@ static void zk_unlock(uint64_t lock_id)
static int zk_init(const char *option)
{
char *hosts, *to, *p;
- int ret;
+ int ret, interval, retry = 0, max_retry;
if (!option) {
sd_err("You must specify zookeeper servers.");
@@ -1370,10 +1370,22 @@ static int zk_init(const char *option)
ZOO_MINOR_VERSION, ZOO_PATCH_VERSION, hosts, zk_timeout);
zhandle = zookeeper_init(hosts, zk_watcher, zk_timeout, NULL, NULL, 0);
if (!zhandle) {
- sd_err("failed to connect to zk server %s", option);
+ sd_err("failed to initialize zk server %s", option);
return -1;
}
+ /* the simplest way to wait and check zk connection */
+ interval = 100;
+ max_retry = zk_timeout / interval;
+ while (zoo_state(zhandle) != ZOO_CONNECTED_STATE) {
+ usleep(interval * 1000);
+ if (++retry >= max_retry) {
+ sd_err("failed to connect to zk server %s "
+ "after %d retries", option, retry);
+ return -1;
+ }
+ }
+
uatomic_set_false(&stop);
uatomic_set_false(&is_master);
if (zk_queue_init() != ZOK)
--
1.9.1
--
sheepdog mailing list
sheepdog@lists.wpkg.org
http://lists.wpkg.org/mailman/listinfo/sheepdog
