summaryrefslogtreecommitdiffstats
path: root/xlators/protocol/server/src/server-handshake.c
diff options
context:
space:
mode:
authorMohit Agrawal <moagrawa@redhat.com>2018-03-12 19:43:15 +0530
committerRaghavendra G <rgowdapp@redhat.com>2018-04-19 04:31:51 +0000
commit0043c63f70776444f69667a4ef9596217ecb42b7 (patch)
treee6c239e4b27198d40bca329edcce317ded59de09 /xlators/protocol/server/src/server-handshake.c
parentbe26b0da2f1a7fe336400de6a1c016716983bd38 (diff)
gluster: Sometimes Brick process is crashed at the time of stopping brick
Problem: Sometimes brick process is getting crashed at the time of stop brick while brick mux is enabled. Solution: Brick process was getting crashed because of rpc connection was not cleaning properly while brick mux is enabled.In this patch after sending GF_EVENT_CLEANUP notification to xlator(server) waits for all rpc client connection destroy for specific xlator.Once rpc connections are destroyed in server_rpc_notify for all associated client for that brick then call xlator_mem_cleanup for for brick xlator as well as all child xlators.To avoid races at the time of cleanup introduce two new flags at each xlator cleanup_starting, call_cleanup. BUG: 1544090 Signed-off-by: Mohit Agrawal <moagrawa@redhat.com> Note: Run all test-cases in separate build (https://review.gluster.org/#/c/19700/) with same patch after enable brick mux forcefully, all test cases are passed. Change-Id: Ic4ab9c128df282d146cf1135640281fcb31997bf updates: bz#1544090
Diffstat (limited to 'xlators/protocol/server/src/server-handshake.c')
-rw-r--r--xlators/protocol/server/src/server-handshake.c25
1 files changed, 24 insertions, 1 deletions
diff --git a/xlators/protocol/server/src/server-handshake.c b/xlators/protocol/server/src/server-handshake.c
index de90a6b..08f76de 100644
--- a/xlators/protocol/server/src/server-handshake.c
+++ b/xlators/protocol/server/src/server-handshake.c
@@ -474,6 +474,7 @@ server_setvolume (rpcsvc_request_t *req)
struct _child_status *tmp = NULL;
char *subdir_mount = NULL;
char *client_name = NULL;
+ gf_boolean_t cleanup_starting = _gf_false;
params = dict_new ();
reply = dict_new ();
@@ -575,11 +576,13 @@ server_setvolume (rpcsvc_request_t *req)
"initialised yet. Try again later");
goto fail;
}
+
list_for_each_entry (tmp, &conf->child_status->status_list,
status_list) {
if (strcmp (tmp->name, name) == 0)
break;
}
+
if (!tmp->name) {
gf_msg (this->name, GF_LOG_ERROR, 0,
PS_MSG_CHILD_STATUS_FAILED,
@@ -593,6 +596,7 @@ server_setvolume (rpcsvc_request_t *req)
"Failed to set 'child_up' for xlator %s "
"in the reply dict", tmp->name);
}
+
ret = dict_get_str (params, "process-uuid", &client_uid);
if (ret < 0) {
ret = dict_set_str (reply, "ERROR",
@@ -634,8 +638,27 @@ server_setvolume (rpcsvc_request_t *req)
goto fail;
}
- if (req->trans->xl_private != client)
+ pthread_mutex_lock (&conf->mutex);
+ if (xl->cleanup_starting) {
+ cleanup_starting = _gf_true;
+ } else if (req->trans->xl_private != client) {
req->trans->xl_private = client;
+ }
+ pthread_mutex_unlock (&conf->mutex);
+
+ if (cleanup_starting) {
+ op_ret = -1;
+ op_errno = EAGAIN;
+
+ ret = dict_set_str (reply, "ERROR",
+ "cleanup flag is set for xlator. "
+ " Try again later");
+ if (ret < 0)
+ gf_msg_debug (this->name, 0, "failed to set error: "
+ "cleanup flag is set for xlator. "
+ "Try again later");
+ goto fail;
+ }
auth_set_username_passwd (params, config_params, client);
if (req->trans->ssl_name) {