summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorSakshi <sabansal@redhat.com>2015-05-26 09:53:55 +0530
committerAtin Mukherjee <amukherj@redhat.com>2016-02-28 08:23:48 -0800
commit368e26f454fe35477e46dc698fa6b8c3c608ea8d (patch)
tree5a9f46d6eaccbf684c896c8a4edf7bc374d01fb9
parent15602865865386672bcb996dab8259d25b684900 (diff)
glusterd: check if glusterd is started on all nodes and all
bricks are started before performing rebalance Change-Id: I458ea9cd86cf35bdb7d758be55f951ae9f3e66f0 BUG: 1224857 Signed-off-by: Sakshi <sabansal@redhat.com> Reviewed-on: http://review.gluster.org/10906 Smoke: Gluster Build System <jenkins@build.gluster.com> CentOS-regression: Gluster Build System <jenkins@build.gluster.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> Reviewed-by: Atin Mukherjee <amukherj@redhat.com>
-rw-r--r--tests/bugs/distribute/bug-860663.t9
-rw-r--r--xlators/mgmt/glusterd/src/glusterd-rebalance.c37
2 files changed, 44 insertions, 2 deletions
diff --git a/tests/bugs/distribute/bug-860663.t b/tests/bugs/distribute/bug-860663.t
index f250a736e41..ebae0e5d824 100644
--- a/tests/bugs/distribute/bug-860663.t
+++ b/tests/bugs/distribute/bug-860663.t
@@ -1,5 +1,6 @@
#!/bin/bash
+. $(dirname $0)/../../volume.rc
. $(dirname $0)/../../include.rc
cleanup;
@@ -36,13 +37,17 @@ TEST [ $ORIG_FILE_COUNT -ge 10000 ]
# Kill a brick process
kill -9 `cat $GLUSTERD_WORKDIR/vols/$V0/run/$H0-d-backends-${V0}1.pid`;
+TEST ! $CLI volume rebalance $V0 fix-layout start
+
+TEST $CLI volume start $V0 force
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" brick_up_status $V0 $H0 $B0/${V0}1
+
TEST $CLI volume rebalance $V0 fix-layout start
-sleep 30;
+EXPECT_WITHIN $REBALANCE_TIMEOUT "fix-layout completed" rebalance_status_field $V0;
TEST ! $(dirname $0)/bug-860663 $M0/files 10000
-TEST $CLI volume start $V0 force
sleep 5;
diff --git a/xlators/mgmt/glusterd/src/glusterd-rebalance.c b/xlators/mgmt/glusterd/src/glusterd-rebalance.c
index 815b0aa6ae6..5bf456ba00b 100644
--- a/xlators/mgmt/glusterd/src/glusterd-rebalance.c
+++ b/xlators/mgmt/glusterd/src/glusterd-rebalance.c
@@ -631,6 +631,8 @@ glusterd_op_stage_rebalance (dict_t *dict, char **op_errstr)
int32_t cmd = 0;
char msg[2048] = {0};
glusterd_volinfo_t *volinfo = NULL;
+ glusterd_brickinfo_t *brickinfo = NULL;
+ glusterd_peerinfo_t *peerinfo = NULL;
char *task_id_str = NULL;
dict_t *op_ctx = NULL;
xlator_t *this = 0;
@@ -698,6 +700,41 @@ glusterd_op_stage_rebalance (dict_t *dict, char **op_errstr)
goto out;
}
+ cds_list_for_each_entry (brickinfo, &volinfo->bricks,
+ brick_list) {
+ if (glusterd_is_local_brick (THIS, volinfo, brickinfo)) {
+ if (brickinfo->status != GF_BRICK_STARTED) {
+ gf_asprintf (op_errstr, "Received"
+ " rebalance on volume with "
+ " stopped brick %s",
+ brickinfo->path);
+ ret = -1;
+ goto out;
+ }
+ } else {
+ rcu_read_lock ();
+ peerinfo = glusterd_peerinfo_find_by_uuid
+ (brickinfo->uuid);
+ if (!peerinfo) {
+ gf_asprintf (op_errstr, "Host node of "
+ "brick %s doesn't belong "
+ "to cluster",
+ brickinfo->path);
+ ret = -1;
+ rcu_read_unlock ();
+ goto out;
+ } else if (!peerinfo->connected) {
+ gf_asprintf (op_errstr, "Host node of "
+ "brick %s is down",
+ brickinfo->path);
+ ret = -1;
+ rcu_read_unlock ();
+ goto out;
+ }
+ rcu_read_unlock ();
+ }
+ }
+
case GF_DEFRAG_CMD_START_FORCE:
if (is_origin_glusterd (dict)) {
op_ctx = glusterd_op_get_ctx ();