summaryrefslogtreecommitdiffstats
path: root/xlators/mgmt
diff options
context:
space:
mode:
authorSamikshan Bairagya <samikshan@gmail.com>2017-05-23 19:32:24 +0530
committerAtin Mukherjee <amukherj@redhat.com>2017-05-24 05:38:40 +0000
commita8624b8b13a1f4222e4d3e33fa5836d7b45369bc (patch)
tree6f8f1a7ae413366961768fb1c5617000614a370a /xlators/mgmt
parent461888bb63b2409f8245c7766aa799ca22f734e6 (diff)
glusterd: Eliminate race in brick compatibility checking stage
In https://review.gluster.org/17307/, while looking for compatible bricks for multiplexing, it is checked if the brick pidfile exists before checking if the corresponding brick process is running. However checking if the brick process is running just after checking if the pidfile exists isn't enough since there might be race conditions where the pidfile has been created but hasn't been updated with a pid value yet. This commit solves that by making sure that we wait iteratively till the pid value is updated as well. Change-Id: Ib7a158f95566486f7c1f84b6357c9b89e4c797ae BUG: 1451248 Signed-off-by: Samikshan Bairagya <samikshan@gmail.com> Reviewed-on: https://review.gluster.org/17375 Smoke: Gluster Build System <jenkins@build.gluster.org> Reviewed-by: Atin Mukherjee <amukherj@redhat.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
Diffstat (limited to 'xlators/mgmt')
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-utils.c7
1 files changed, 5 insertions, 2 deletions
diff --git a/xlators/mgmt/glusterd/src/glusterd-utils.c b/xlators/mgmt/glusterd/src/glusterd-utils.c
index ea8d60cd87b..0a89535211f 100644
--- a/xlators/mgmt/glusterd/src/glusterd-utils.c
+++ b/xlators/mgmt/glusterd/src/glusterd-utils.c
@@ -5225,13 +5225,16 @@ find_compat_brick_in_vol (glusterd_conf_t *conf,
* wait for the pidfile to be populated with a value before
* checking if the service is running */
while (retries > 0) {
- if (sys_access (pidfile2, F_OK) == 0)
+ if (sys_access (pidfile2, F_OK) == 0 &&
+ gf_is_service_running (pidfile2, &pid2)) {
break;
+ }
+
sleep (1);
retries--;
}
- if (!gf_is_service_running (pidfile2, &pid2)) {
+ if (retries == 0) {
gf_log (this->name, GF_LOG_INFO,
"cleaning up dead brick %s:%s",
other_brick->hostname, other_brick->path);