cluster/afr: Improvement in logging of self heal completion status

Problem:
As the end of the self heal, message logged by
"afr_self_heal_completion_cbk" is inadequate to determine what exactly failed
during the course of afr self heal. It is worth to have knowledge of what all
types of self heal got triggered for an entity and whether the status is success
or failure.

Fix:
At the end of self heal, it will log information about out of 4 types of self
heal (gfid or missing entry self heal, metadata, data and entry self heal),
who all got triggered and who all got failed or successful at the end.

Change-Id: I5360762fbd7d391ac4c6af6706b4835c5801835a
BUG: 968301
Signed-off-by: Venkatesh Somyajulu <vsomyaju@redhat.com>
Reviewed-on: http://review.gluster.org/5106
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Anand Avati <avati@redhat.com>

1 files changed, 19 insertions, 15 deletions

diff --git a/xlators/cluster/afr/src/afr-self-heal-data.c b/xlators/cluster/afr/src/afr-self-heal-data.c
index 2f63ed27d74..fc7f5e7ac4b 100644
--- a/xlators/cluster/afr/src/afr-self-heal-data.c
+++ b/xlators/cluster/afr/src/afr-self-heal-data.c
@@ -335,7 +335,7 @@ afr_sh_data_fail (call_frame_t *frame, xlator_t *this)
         gf_log (this->name, GF_LOG_DEBUG,
                 "finishing failed data selfheal of %s", local->loc.path);
 
-        sh->op_failed = 1;
+        sh->afr_set_self_heal_status (sh, AFR_SELF_HEAL_FAILED);
         if (sh->data_lock_held)
                 afr_sh_data_unlock (frame, this, afr_sh_data_close);
         else
@@ -362,13 +362,13 @@ afr_sh_data_erase_pending_cbk (call_frame_t *frame, void *cookie,
                         "log failed on %s for subvol %s, reason: %s",
                         local->loc.path, priv->children[child_index]->name,
                         strerror (op_errno));
-                sh->op_failed = 1;
+                sh->afr_set_self_heal_status (sh, AFR_SELF_HEAL_FAILED);
         }
 
         call_count = afr_frame_return (frame);
 
         if (call_count == 0) {
-                if (sh->op_failed) {
+                if (is_self_heal_failed (sh)) {
                         if (sh->old_loop_frame)
                                 sh_loop_finish (sh->old_loop_frame, this);
                         sh->old_loop_frame = NULL;
@@ -418,7 +418,7 @@ afr_sh_data_fsync_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
                         priv->children[child_index]->name, strerror (op_errno));
                 LOCK (&frame->lock);
                 {
-                        sh->op_failed = 1;
+                        sh->afr_set_self_heal_status (sh, AFR_SELF_HEAL_FAILED);
                 }
                 UNLOCK (&frame->lock);
                 if (sh->old_loop_frame)
@@ -428,7 +428,7 @@ afr_sh_data_fsync_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
 
         call_count = afr_frame_return (frame);
         if (call_count == 0) {
-                if (sh->op_failed)
+                if (is_self_heal_failed (sh))
                         afr_sh_data_fail (frame, this);
                 else
                         afr_sh_data_erase_pending (frame, this);
@@ -604,7 +604,7 @@ afr_sh_data_trim_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
                                 local->loc.path,
                                 priv->children[child_index]->name,
                                 strerror (op_errno));
-                        sh->op_failed = 1;
+                        sh->afr_set_self_heal_status (sh, AFR_SELF_HEAL_FAILED);
                 } else {
                         gf_log (this->name, GF_LOG_DEBUG,
                                 "ftruncate of %s on subvolume %s completed",
@@ -617,7 +617,7 @@ afr_sh_data_trim_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
         call_count = afr_frame_return (frame);
 
         if (call_count == 0) {
-                if (sh->op_failed)
+                if (is_self_heal_failed (sh))
                         afr_sh_data_fail (frame, this);
                 else
                         afr_sh_data_sync_prepare (frame, this);
@@ -718,7 +718,7 @@ afr_sh_data_fix (call_frame_t *frame, xlator_t *this)
 
         if (sh->background && sh->unwind && !sh->unwound) {
                 sh->unwind (sh->orig_frame, this, sh->op_ret, sh->op_errno,
-                            sh->op_failed);
+                            is_self_heal_failed (sh));
                 sh->unwound = _gf_true;
         }
 
@@ -1342,7 +1342,7 @@ afr_sh_data_open_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
                                 local->loc.path,
                                 priv->children[child_index]->name,
                                 strerror (op_errno));
-                        sh->op_failed = 1;
+                        sh->afr_set_self_heal_status (sh, AFR_SELF_HEAL_FAILED);
                 } else {
                         gf_log (this->name, GF_LOG_TRACE,
                                 "open of %s succeeded on child %s",
@@ -1355,7 +1355,7 @@ afr_sh_data_open_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
         call_count = afr_frame_return (frame);
 
         if (call_count == 0) {
-                if (sh->op_failed) {
+                if (is_self_heal_failed (sh)) {
                         afr_sh_data_fail (frame, this);
                         return 0;
                 }
@@ -1364,11 +1364,12 @@ afr_sh_data_open_cbk (call_frame_t *frame, void *cookie, xlator_t *this,
                         "fd for %s opened, commencing sync",
                         local->loc.path);
 
-		/*
-		 * The read and write self-heal trigger codepaths do not provide
-		 * an unwind callback. We run a trylock in these codepaths
-		 * because we are sensitive to locking latency.
-		 */
+                /*
+                 * The read and write self-heal trigger codepaths do not provide
+                 * an unwind callback. We run a trylock in these codepaths
+                 * because we are sensitive to locking latency.
+                 */
+
 		block = sh->unwind ? _gf_true : _gf_false;
                 afr_sh_data_lock (frame, this, 0, 0, block,
                                   afr_sh_data_big_lock_success,
@@ -1484,7 +1485,10 @@ afr_self_heal_data (call_frame_t *frame, xlator_t *this)
         local = frame->local;
         sh = &local->self_heal;
 
+        sh->afr_set_self_heal_status = afr_set_data_sh_status;
+
         if (afr_can_start_data_self_heal (sh, priv)) {
+                sh->afr_set_self_heal_status (sh, AFR_SELF_HEAL_STARTED);
                 if (IA_ISREG (sh->type)) {
                         afr_sh_data_open (frame, this);
                 } else {