cluster/afr: prevent piggyback on stale pre_op

Here are the logs of a file on which we saw EIO because of size mismatch:
[root@lizzie ~]# grep 38f18204 /var/log/glusterfs/mnt-x-.log
Reporting Unstable write for 38f18204-2840-408e-ae65-c01f4106b8c4
for offset: 0, len: 7680

Cleared unstable write flag for 38f18204-2840-408e-ae65-c01f4106b8c4:
offset 0 length 7680

Reporting Unstable write for 38f18204-2840-408e-ae65-c01f4106b8c4 for
offset: 7680, len: 71680

Reporting Unstable write for 38f18204-2840-408e-ae65-c01f4106b8c4 for
offset: 79360, len: 15716

fsync completed on 38f18204-2840-408e-ae65-c01f4106b8c4 for
offset 0 length 7680 with changelog status: -1 -1

According to these logs fsync did not happen after writev with
offset: 79360, len: 15716. Which is the reason for this problem.

In total 3 writes came. lets call them w1, w2, w3
w1 does pre_op so pre_op_done[0], pre_op_done[1] counts become 1 and 1
then is_piggyback_post_op() is called for w1 and it returns *false*

w1's fsync is fired

Now w2 and w3 come and see that pre_op_done[0], pre_op_done[1] are both 1,
so pre_op_piggyback[0] and pre_op_piggyback[1] are both incremented twice,
once by w2, one more time by w3 and become 2, 2  ------- Step-A

Now fsync of w1 is complete and it goes ahead with post op and decrements
pre_op_done[0], pre_op_done[1] to 0, 0

Now w2, w3 writevs complete and is_piggyback_post_op will return *true* for
both w2, w3.
So fsync is not fired for both w2, w3

this patch prevents Step-A from happening.

Change-Id: I8b6af1f1875b2cf5f718caa3c16ee7ff3dc96b5c
BUG: 927146
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
Reviewed-on: http://review.gluster.org/4752
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Jeff Darcy <jdarcy@redhat.com>

1 files changed, 2 insertions, 33 deletions

diff --git a/xlators/cluster/afr/src/afr-transaction.c b/xlators/cluster/afr/src/afr-transaction.c
index e766b65cdc8..50c15c3463f 100644
--- a/xlators/cluster/afr/src/afr-transaction.c
+++ b/xlators/cluster/afr/src/afr-transaction.c
@@ -146,36 +146,6 @@ out:
         return;
 }
 
-
-static void
-__mark_pre_op_undone_on_fd (call_frame_t *frame, xlator_t *this, int child_index)
-{
-        afr_local_t   *local = NULL;
-        afr_fd_ctx_t  *fd_ctx = NULL;
-
-        local = frame->local;
-
-        if (!local->fd)
-                return;
-
-        fd_ctx = afr_fd_ctx_get (local->fd, this);
-
-        if (!fd_ctx)
-                goto out;
-
-        LOCK (&local->fd->lock);
-        {
-                if (local->transaction.type == AFR_DATA_TRANSACTION) {
-                        GF_ASSERT (fd_ctx->pre_op_done[child_index]);
-                        fd_ctx->pre_op_done[child_index]--;
-                }
-        }
-        UNLOCK (&local->fd->lock);
-out:
-        return;
-}
-
-
 static void
 __mark_non_participant_children (int32_t *pending[], int child_count,
                                  unsigned char *participants,
@@ -691,9 +661,6 @@ afr_changelog_post_op_now (call_frame_t *frame, xlator_t *this)
                                 afr_changelog_post_op_cbk (frame, (void *)(long)i,
                                                            this, 1, 0, xattr[i], NULL);
                         } else {
-                                if (!piggyback)
-                                        __mark_pre_op_undone_on_fd (frame, this,
-                                                                    i);
                                 STACK_WIND_COOKIE (frame,
                                                    afr_changelog_post_op_cbk,
                                                    (void *) (long) i,
@@ -1392,6 +1359,8 @@ is_piggyback_post_op (call_frame_t *frame, fd_t *fd)
 				   if necesssary
 				*/
 				piggyback = _gf_false;
+                                GF_ASSERT (fdctx->pre_op_done[i]);
+                                fdctx->pre_op_done[i]--;
 			}
 		}
 	}