summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorAnuradha Talur <atalur@redhat.com>2016-05-13 15:34:06 +0530
committerPranith Kumar Karampuri <pkarampu@redhat.com>2016-05-23 22:21:35 -0700
commit324329deee862ba28873172b3124031b5783471e (patch)
tree997a9bd9db485884276f7e07a78cd0e68de5f1b4
parentb632ff7e3f614c46d9209f87847a9c0c0892e51e (diff)
cluster/afr : Do post-op in case of symmetric errors
Backport of: http://review.gluster.org/#/c/14310/ In afr_changelog_post_op_now(), if there was any error, meaning op_ret < 0, post-op was not being done even when the errors were symmetric and there were no "failed subvols". Fix: When the errors are symmetric, perform post-op. How was the bug found : In a 1 X 3 volume with shard and write behind on when writes were done into a file with one brick down, the trusted.afr.dirty xattr's value for .shard directory would keep increasing as post op was not done but pre-op was. This incorrectly showed .shard to be in split-brain. RCA: When WB is on, due to multiple writes being sent on offset lying in the same shard, chances are that same shard file will be created more than once with the second one failing with op_ret < 0 and op_errno = EEXIST. As op_ret was negative, afr wouldn't do post-op, leading to no decrement of trusted.afr.dirty xattr. Thus showing .shard directory to be in split-brain. >Change-Id: I711bdeaa1397244e6a7790e96f0c84501798fc59 >BUG: 1335652 >Signed-off-by: Anuradha Talur <atalur@redhat.com> Change-Id: I711bdeaa1397244e6a7790e96f0c84501798fc59 BUG: 1335836 Signed-off-by: Anuradha Talur <atalur@redhat.com> Reviewed-on: http://review.gluster.org/14332 Smoke: Gluster Build System <jenkins@build.gluster.com> NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org> CentOS-regression: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Ravishankar N <ravishankar@redhat.com> Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
-rw-r--r--tests/bugs/replicate/bug-1335652.t29
-rw-r--r--xlators/cluster/afr/src/afr-transaction.c8
2 files changed, 35 insertions, 2 deletions
diff --git a/tests/bugs/replicate/bug-1335652.t b/tests/bugs/replicate/bug-1335652.t
new file mode 100644
index 00000000000..653a1b05ce2
--- /dev/null
+++ b/tests/bugs/replicate/bug-1335652.t
@@ -0,0 +1,29 @@
+#!/bin/bash
+. $(dirname $0)/../../include.rc
+. $(dirname $0)/../../volume.rc
+cleanup;
+
+TEST glusterd
+TEST pidof glusterd
+TEST $CLI volume create $V0 replica 3 $H0:$B0/${V0}{0,1,2}
+TEST $CLI volume set $V0 shard on
+TEST $CLI volume set $V0 self-heal-daemon off
+TEST $CLI volume set $V0 data-self-heal off
+TEST $CLI volume set $V0 entry-self-heal off
+TEST $CLI volume set $V0 metadata-self-heal off
+TEST $CLI volume start $V0
+
+TEST glusterfs --volfile-id=$V0 --volfile-server=$H0 $M0;
+
+#Kill the zero'th brick so that 1st and 2nd get marked dirty
+TEST kill_brick $V0 $H0 $B0/${V0}0
+
+TEST dd if=/dev/urandom of=$M0/file bs=10MB count=20
+
+#At any point value of dirty should not be greater than 0 on source bricks
+EXPECT "000000000000000000000000" get_hex_xattr trusted.afr.dirty $B0/${V0}1/.shard
+EXPECT "000000000000000000000000" get_hex_xattr trusted.afr.dirty $B0/${V0}2/.shard
+
+rm -rf $M0/file;
+
+cleanup;
diff --git a/xlators/cluster/afr/src/afr-transaction.c b/xlators/cluster/afr/src/afr-transaction.c
index 908c6bea0b7..2bb4e827c76 100644
--- a/xlators/cluster/afr/src/afr-transaction.c
+++ b/xlators/cluster/afr/src/afr-transaction.c
@@ -537,10 +537,14 @@ afr_handle_symmetric_errors (call_frame_t *frame, xlator_t *this)
}
i_errno = local->replies[i].op_errno;
- if (i_errno == ENOTCONN) {
+ if (i_errno == ENOTCONN || i_errno == EDQUOT ||
+ i_errno == ENOSPC) {
/* ENOTCONN is not a symmetric error. We do not
know if the operation was performed on the
backend or not.
+ * Before reaching EDQUOT and ENOSPC, each brick would
+ * have written some amount of data, hence this is not
+ * symmetric error.
*/
matching_errors = _gf_false;
break;
@@ -719,7 +723,7 @@ afr_changelog_post_op_now (call_frame_t *frame, xlator_t *this)
else
need_undirty = _gf_true;
- if (local->op_ret < 0) {
+ if (local->op_ret < 0 && !nothing_failed) {
afr_changelog_post_op_done (frame, this);
goto out;
}