glusterd: big lock - a coarse-grained locking to prevent races

There are primarily three lists that are part of glusterd process,
that are concurrently accessed. Namely, priv->volumes, priv->peers
and volinfo->bricks_list.

Big-lock approach
-----------------
WHAT IS IT?
Big lock is a coarse-grained lock which protects all three
lists, mentioned above, from racy access.

HOW DOES IT WORK?
At any given point in time, glusterd's thread(s) are in execution
_iff_ there is a preceding, inbound network event. Of course, the
sigwaiter thread and timer thread are exceptions.
A network event is an external trigger to glusterd, via the epoll
thread, in the form of POLLIN and POLLERR.
As long as we take the big-lock at all such entry points and yield
it when we are done, we are guaranteed that all the network events,
accessing the global lists, are serialised.

This amounts to holding the big lock at
- all the handlers of all the actors in glusterd. (POLLIN)
- all the cbks in glusterd. (POLLIN)
- rpc_notify (DISCONNECT event), if we access/modify
  one of the three lists. (POLLERR)

In the case of synctask'ized volume operations, we must remember that,
if we held the big lock for the entire duration of the handler,
we may block other non-synctask rpc actors from executing.
For eg, volume-start would block in PMAP SIGNIN, if done incorrectly.
To prevent this, we need to yield the big lock, when we yield the
synctask, and reacquire on waking up of the synctask.

Change-Id: Ib929f9905b55fb6c3fc27fefb497a26dba058e4f
BUG: 948686
Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com>
Reviewed-on: http://review.gluster.org/4784
Reviewed-by: Jeff Darcy <jdarcy@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>

1 files changed, 51 insertions, 6 deletions

diff --git a/xlators/mgmt/glusterd/src/glusterd-volume-ops.c b/xlators/mgmt/glusterd/src/glusterd-volume-ops.c
index fd4e0268a57..50b03f71e49 100644
--- a/xlators/mgmt/glusterd/src/glusterd-volume-ops.c
+++ b/xlators/mgmt/glusterd/src/glusterd-volume-ops.c
@@ -31,7 +31,7 @@
         glusterd_op_stop_volume_args_get (dict, volname, flags)
 
 int
-glusterd_handle_create_volume (rpcsvc_request_t *req)
+__glusterd_handle_create_volume (rpcsvc_request_t *req)
 {
         int32_t                 ret         = -1;
         gf_cli_req              cli_req     = {{0,}};
@@ -192,7 +192,14 @@ out:
 }
 
 int
-glusterd_handle_cli_start_volume (rpcsvc_request_t *req)
+glusterd_handle_create_volume (rpcsvc_request_t *req)
+{
+        return glusterd_big_locked_handler (req,
+                                            __glusterd_handle_create_volume);
+}
+
+int
+__glusterd_handle_cli_start_volume (rpcsvc_request_t *req)
 {
         int32_t                         ret = -1;
         gf_cli_req                      cli_req = {{0,}};
@@ -257,9 +264,15 @@ out:
         return ret;
 }
 
+int
+glusterd_handle_cli_start_volume (rpcsvc_request_t *req)
+{
+        return glusterd_big_locked_handler (req,
+                                            __glusterd_handle_cli_start_volume);
+}
 
 int
-glusterd_handle_cli_stop_volume (rpcsvc_request_t *req)
+__glusterd_handle_cli_stop_volume (rpcsvc_request_t *req)
 {
         int32_t                         ret = -1;
         gf_cli_req                      cli_req = {{0,}};
@@ -327,7 +340,14 @@ out:
 }
 
 int
-glusterd_handle_cli_delete_volume (rpcsvc_request_t *req)
+glusterd_handle_cli_stop_volume (rpcsvc_request_t *req)
+{
+        return glusterd_big_locked_handler (req,
+                                            __glusterd_handle_cli_stop_volume);
+}
+
+int
+__glusterd_handle_cli_delete_volume (rpcsvc_request_t *req)
 {
         int32_t        ret         = -1;
         gf_cli_req     cli_req     = {{0,},};
@@ -397,7 +417,14 @@ out:
 }
 
 int
-glusterd_handle_cli_heal_volume (rpcsvc_request_t *req)
+glusterd_handle_cli_delete_volume (rpcsvc_request_t *req)
+{
+        return glusterd_big_locked_handler (req,
+                                            __glusterd_handle_cli_delete_volume);
+}
+
+int
+__glusterd_handle_cli_heal_volume (rpcsvc_request_t *req)
 {
         int32_t                         ret = -1;
         gf_cli_req                      cli_req = {{0,}};
@@ -481,7 +508,14 @@ out:
 }
 
 int
-glusterd_handle_cli_statedump_volume (rpcsvc_request_t *req)
+glusterd_handle_cli_heal_volume (rpcsvc_request_t *req)
+{
+        return glusterd_big_locked_handler (req,
+                                            __glusterd_handle_cli_heal_volume);
+}
+
+int
+__glusterd_handle_cli_statedump_volume (rpcsvc_request_t *req)
 {
         int32_t                         ret = -1;
         gf_cli_req                      cli_req = {{0,}};
@@ -562,6 +596,13 @@ out:
         return ret;
 }
 
+int
+glusterd_handle_cli_statedump_volume (rpcsvc_request_t *req)
+{
+        return glusterd_big_locked_handler (req,
+                                            __glusterd_handle_cli_statedump_volume);
+}
+
 #ifdef HAVE_BD_XLATOR
 int
 glusterd_is_valid_vg (const char *name)
@@ -1852,7 +1893,9 @@ glusterd_clearlocks_unmount (glusterd_volinfo_t *volinfo, char *mntpt)
         runner_add_args (&runner, "/bin/umount", "-f", NULL);
         runner_argprintf (&runner, "%s", mntpt);
 
+        synclock_unlock (&priv->big_lock);
         ret = runner_run (&runner);
+        synclock_lock (&priv->big_lock);
         if (ret) {
                 ret = 0;
                 gf_log ("", GF_LOG_DEBUG,
@@ -1924,7 +1967,9 @@ glusterd_clearlocks_mount (glusterd_volinfo_t *volinfo, char **xl_opts,
         }
 
         runner_argprintf (&runner, "%s", mntpt);
+        synclock_unlock (&priv->big_lock);
         ret = runner_run (&runner);
+        synclock_lock (&priv->big_lock);
         if (ret) {
                 gf_log (THIS->name, GF_LOG_DEBUG,
                         "Could not start glusterfs");