From 2ab72d3db1ab8c916bbc33c5833c161ce98eff63 Mon Sep 17 00:00:00 2001
From: Pranith Kumar K <pkarampu@redhat.com>
Date: Tue, 13 Jun 2017 23:35:40 +0530
Subject: [PATCH 514/525] cluster/ec: lk shouldn't be a transaction

Problem:
When application sends a blocking lock, the lk fop actually waits under
inodelk.  This can lead to a dead-lock.
1) Let's say app-1 takes exculsive-fcntl-lock on the file
2) app-2 attempts an exclusive-fcntl-lock on the file which goes to blocking
   stage note: app-2 is blocked inside transaction which holds an inode-lock
3) app-1 tries to perform write which needs inode-lock so it gets blocked on
   app-2 to unlock inodelk and app-2 is blocked on app-1 to unlock fcntl-lock

Fix:
Correct way to fix this issue and make fcntl locks perform well would be to
introduce
2-phase locking for fcntl lock:
1) Implement a try-lock phase where locks xlator will not merge lk call with
   existing calls until a commit-lock phase.
2) If in try-lock phase we get quorum number of success without any EAGAIN
   error, then send a commit-lock which will merge locks.
3) In case there are any errors, unlock should just delete the lock-object
   which was tried earlier and shouldn't touch the committed locks.

Unfortunately this is a sizeable feature and need to be thought through for any
corner cases.  Until then remove transaction from lk call.

 >BUG: 1455049
 >Change-Id: I18a782903ba0eb43f1e6526fb0cf8c626c460159
 >Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
 >Reviewed-on: https://review.gluster.org/17542
 >Smoke: Gluster Build System <jenkins@build.gluster.org>
 >NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org>
 >CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
 >Reviewed-by: Ashish Pandey <aspandey@redhat.com>
 >Reviewed-by: Xavier Hernandez <xhernandez@datalab.es>

BUG: 1444515
Change-Id: I723e675119a08ec2a9c9073eb5eac73dc455af0d
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
Reviewed-on: https://code.engineering.redhat.com/gerrit/109275
---
 xlators/cluster/ec/src/ec-locks.c | 20 +-------------------
 1 file changed, 1 insertion(+), 19 deletions(-)

diff --git a/xlators/cluster/ec/src/ec-locks.c b/xlators/cluster/ec/src/ec-locks.c
index 70b07c3..ff09852 100644
--- a/xlators/cluster/ec/src/ec-locks.c
+++ b/xlators/cluster/ec/src/ec-locks.c
@@ -1020,12 +1020,6 @@ int32_t ec_manager_lk(ec_fop_data_t * fop, int32_t state)
 
         /* Fall through */
 
-        case EC_STATE_LOCK:
-            ec_lock_prepare_fd(fop, fop->fd, EC_UPDATE_DATA | EC_QUERY_INFO);
-            ec_lock(fop);
-
-            return EC_STATE_DISPATCH;
-
         case EC_STATE_DISPATCH:
             ec_dispatch_all(fop);
 
@@ -1080,10 +1074,9 @@ int32_t ec_manager_lk(ec_fop_data_t * fop, int32_t state)
                              cbk->op_errno, &cbk->flock, cbk->xdata);
             }
 
-            return EC_STATE_LOCK_REUSE;
+            return EC_STATE_END;
 
         case -EC_STATE_INIT:
-        case -EC_STATE_LOCK:
         case -EC_STATE_DISPATCH:
         case -EC_STATE_REPORT:
             GF_ASSERT(fop->error != 0);
@@ -1094,17 +1087,6 @@ int32_t ec_manager_lk(ec_fop_data_t * fop, int32_t state)
                              NULL, NULL);
             }
 
-            return EC_STATE_LOCK_REUSE;
-
-        case -EC_STATE_LOCK_REUSE:
-        case EC_STATE_LOCK_REUSE:
-            ec_lock_reuse(fop);
-
-            return EC_STATE_UNLOCK;
-
-        case -EC_STATE_UNLOCK:
-        case EC_STATE_UNLOCK:
-            ec_unlock(fop);
 
             return EC_STATE_END;
 
-- 
1.8.3.1