cluster/afr: Delegate metadata heal with pending xattrs to SHD

Problem:
When metadata-self-heal is triggered on the mount, it blocks
lookup until metadata-self-heal completes. But that can lead
to hangs when lot of clients are accessing a directory which
needs metadata heal and all of them trigger heals waiting
for other clients to complete heal.

Fix:
Only when the heal is needed but the pending xattrs are not set,
trigger metadata heal that could block lookup. This is the only
case where different clients may give different metadata to the
clients without heals, which should be avoided.

Updates bz#1625588
Change-Id: I6089e9fda0770a83fb287941b229c882711f4e66
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>

3 files changed, 47 insertions, 38 deletions

diff --git a/xlators/cluster/afr/src/afr-common.c b/xlators/cluster/afr/src/afr-common.c
index f17ae09cccd..aa054541755 100644
--- a/xlators/cluster/afr/src/afr-common.c
+++ b/xlators/cluster/afr/src/afr-common.c
@@ -2575,6 +2575,42 @@ out:
         return 0;
 }
 
+gf_boolean_t
+afr_is_pending_set (xlator_t *this, dict_t *xdata, int type)
+{
+        int idx = -1;
+        afr_private_t *priv = NULL;
+        void *pending_raw = NULL;
+        int *pending_int = NULL;
+        int i = 0;
+
+        priv = this->private;
+        idx = afr_index_for_transaction_type (type);
+
+        if (dict_get_ptr (xdata, AFR_DIRTY, &pending_raw) == 0) {
+                if (pending_raw) {
+                        pending_int = pending_raw;
+
+                        if (ntoh32 (pending_int[idx]))
+                                return _gf_true;
+                }
+        }
+
+        for (i = 0; i < priv->child_count; i++) {
+                if (dict_get_ptr (xdata, priv->pending_key[i],
+                                  &pending_raw))
+                        continue;
+                if (!pending_raw)
+                        continue;
+                pending_int = pending_raw;
+
+                if (ntoh32 (pending_int[idx]))
+                        return _gf_true;
+        }
+
+        return _gf_false;
+}
+
 static gf_boolean_t
 afr_can_start_metadata_self_heal(call_frame_t *frame, xlator_t *this)
 {
@@ -2601,6 +2637,14 @@ afr_can_start_metadata_self_heal(call_frame_t *frame, xlator_t *this)
                         continue;
                 }
 
+                if (afr_is_pending_set (this, replies[i].xdata,
+                                        AFR_METADATA_TRANSACTION)) {
+                        /* Let shd do the heal so that lookup is not blocked
+                         * on getting metadata lock/doing the heal */
+                        start = _gf_false;
+                        break;
+                }
+
                 if (gf_uuid_compare (stbuf.ia_gfid, replies[i].poststat.ia_gfid)) {
                         start = _gf_false;
                         break;
diff --git a/xlators/cluster/afr/src/afr-self-heal-common.c b/xlators/cluster/afr/src/afr-self-heal-common.c
index c2d5058081c..a84386d0afb 100644
--- a/xlators/cluster/afr/src/afr-self-heal-common.c
+++ b/xlators/cluster/afr/src/afr-self-heal-common.c
@@ -2176,44 +2176,6 @@ afr_selfheal_unentrylk (call_frame_t *frame, xlator_t *this, inode_t *inode,
 	return 0;
 }
 
-
-gf_boolean_t
-afr_is_pending_set (xlator_t *this, dict_t *xdata, int type)
-{
-	int idx = -1;
-	afr_private_t *priv = NULL;
-	void *pending_raw = NULL;
-	int *pending_int = NULL;
-	int i = 0;
-
-	priv = this->private;
-	idx = afr_index_for_transaction_type (type);
-
-	if (dict_get_ptr (xdata, AFR_DIRTY, &pending_raw) == 0) {
-		if (pending_raw) {
-			pending_int = pending_raw;
-
-			if (ntoh32 (pending_int[idx]))
-				return _gf_true;
-		}
-	}
-
-	for (i = 0; i < priv->child_count; i++) {
-		if (dict_get_ptr (xdata, priv->pending_key[i],
-				  &pending_raw))
-			continue;
-		if (!pending_raw)
-			continue;
-		pending_int = pending_raw;
-
-		if (ntoh32 (pending_int[idx]))
-			return _gf_true;
-	}
-
-	return _gf_false;
-}
-
-
 gf_boolean_t
 afr_is_data_set (xlator_t *this, dict_t *xdata)
 {
diff --git a/xlators/cluster/afr/src/afr.h b/xlators/cluster/afr/src/afr.h
index 36333a3cfaa..8d11f2bb644 100644
--- a/xlators/cluster/afr/src/afr.h
+++ b/xlators/cluster/afr/src/afr.h
@@ -1287,4 +1287,7 @@ afr_write_subvol_reset (call_frame_t *frame, xlator_t *this);
 
 int
 afr_set_inode_local (xlator_t *this, afr_local_t *local, inode_t *inode);
+
+gf_boolean_t
+afr_is_pending_set (xlator_t *this, dict_t *xdata, int type);
 #endif /* __AFR_H__ */