summaryrefslogtreecommitdiffstats
path: root/xlators/cluster
diff options
context:
space:
mode:
authorRavishankar N <ravishankar@redhat.com>2017-04-02 18:08:04 +0530
committerPranith Kumar Karampuri <pkarampu@redhat.com>2017-04-18 22:29:25 -0400
commit10dad995c989e9d77c341135d7c48817baba966c (patch)
treebe377c185b2bdaa186d7d534b26d14e7d0765c5f /xlators/cluster
parent43695cfba3bcbb53d7127128e37a724862f65017 (diff)
afr: don't do a post-op on a brick if op failed
Problem: In afr-v2, self-blaming xattrs are not there by design. But if the FOP failed on a brick due to an error other than ENOTCONN (or even due to ENOTCONN, but we regained connection before postop was wound), we wind the post-op also on the failed brick, leading to setting self-blaming xattrs on that brick. This can lead to undesired results like healing of files in split-brain etc. Fix: If a fop failed on a brick on which pre-op was successful, do not perform post-op on it. This also produces the desired effect of not resetting the dirty xattr on the brick, which is how it should be because if the fop failed on a brick, there is no reason to clear the dirty bit which actually serves as an indication of the failure. Change-Id: I5f1caf4d1b39f36cf8093ccef940118638caa9c4 BUG: 1438255 Signed-off-by: Ravishankar N <ravishankar@redhat.com> Reviewed-on: https://review.gluster.org/16976 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: Pranith Kumar Karampuri <pkarampu@redhat.com>
Diffstat (limited to 'xlators/cluster')
-rw-r--r--xlators/cluster/afr/src/afr-transaction.c21
1 files changed, 15 insertions, 6 deletions
diff --git a/xlators/cluster/afr/src/afr-transaction.c b/xlators/cluster/afr/src/afr-transaction.c
index cbfddf2009d..7dda3da67ab 100644
--- a/xlators/cluster/afr/src/afr-transaction.c
+++ b/xlators/cluster/afr/src/afr-transaction.c
@@ -35,6 +35,7 @@ afr_changelog_pre_op_update (call_frame_t *frame, xlator_t *this);
int
afr_changelog_call_count (afr_transaction_type type,
unsigned char *pre_op_subvols,
+ unsigned char *failed_subvols,
unsigned int child_count);
int
afr_post_op_unlock_do (call_frame_t *frame, xlator_t *this, dict_t *xattr,
@@ -590,11 +591,17 @@ afr_locked_nodes_get (afr_transaction_type type, afr_internal_lock_t *int_lock)
int
afr_changelog_call_count (afr_transaction_type type,
unsigned char *pre_op_subvols,
+ unsigned char *failed_subvols,
unsigned int child_count)
{
+ int i = 0;
int call_count = 0;
- call_count = AFR_COUNT(pre_op_subvols, child_count);
+ for (i = 0; i < child_count; i++) {
+ if (pre_op_subvols[i] && !failed_subvols[i]) {
+ call_count++;
+ }
+ }
if (type == AFR_ENTRY_RENAME_TRANSACTION)
call_count *= 2;
@@ -1352,6 +1359,7 @@ afr_changelog_prepare (xlator_t *this, call_frame_t *frame, int *call_count,
*call_count = afr_changelog_call_count (local->transaction.type,
local->transaction.pre_op,
+ local->transaction.failed_subvols,
priv->child_count);
if (*call_count == 0) {
@@ -1418,7 +1426,8 @@ afr_pre_op_fop_do (call_frame_t *frame, xlator_t *this, dict_t *xattr,
for (i = 0; i < priv->child_count; i++) {
/* Means lock did not succeed on this brick */
- if (!local->transaction.pre_op[i])
+ if (!local->transaction.pre_op[i] ||
+ local->transaction.failed_subvols[i])
continue;
STACK_WIND_COOKIE (frame, compound_cbk,
@@ -1562,9 +1571,8 @@ afr_post_op_unlock_do (call_frame_t *frame, xlator_t *this, dict_t *xattr,
local->c_args = args;
for (i = 0; i < priv->child_count; i++) {
- /* pre_op[i] has to be true for all nodes that were
- * successfully locked. */
- if (!local->transaction.pre_op[i])
+ if (!local->transaction.pre_op[i] ||
+ local->transaction.failed_subvols[i])
continue;
STACK_WIND_COOKIE (frame, afr_post_op_unlock_cbk,
(void *) (long) i,
@@ -1606,7 +1614,8 @@ afr_changelog_do (call_frame_t *frame, xlator_t *this, dict_t *xattr,
return 0;
for (i = 0; i < priv->child_count; i++) {
- if (!local->transaction.pre_op[i])
+ if (!local->transaction.pre_op[i] ||
+ local->transaction.failed_subvols[i])
continue;
switch (local->transaction.type) {