afr: mark pending xattrs as a part of metadata heal

...if pending xattrs are zero for all children.

Problem:
If there are no pending xattrs and a metadata heal needs to be
performed, it can be possible that we end up with xattrs inadvertendly
deleted from all bricks, as explained in the  BZ.

Fix:
After picking one among the sources as the good copy, mark pending xattrs on
all sources to blame the sinks. Now even if this metadata heal fails midway,
a subsequent heal will still choose one of the valid sources that it
picked previously.

Updates: #1067
Change-Id: If1b050b70b0ad911e162c04db4d89b263e2b8d7b
Signed-off-by: Ravishankar N <ravishankar@redhat.com>
(cherry picked from commit 2d5ba449e9200b16184b1e7fc84cabd015f1f779)

2 files changed, 120 insertions, 1 deletions

diff --git a/tests/bugs/replicate/mdata-heal-no-xattrs.t b/tests/bugs/replicate/mdata-heal-no-xattrs.t
new file mode 100644
index 00000000000..d3b0c504c80
--- /dev/null
+++ b/tests/bugs/replicate/mdata-heal-no-xattrs.t
@@ -0,0 +1,59 @@
+#!/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 cluster.self-heal-daemon off
+TEST $CLI volume start $V0
+
+TEST glusterfs --volfile-id=/$V0 --volfile-server=$H0 $M0 --attribute-timeout=0 --entry-timeout=0
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 0
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 1
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 2
+echo "Data">$M0/FILE
+ret=$?
+TEST [ $ret -eq 0 ]
+
+# Change permission on brick-0: simulates the case where there is metadata
+# mismatch but no pending xattrs. This brick will become the source for heal.
+TEST chmod +x $B0/$V0"0"/FILE
+
+# Add gfid to xattrop
+xattrop_b0=$(afr_get_index_path $B0/$V0"0")
+base_entry_b0=`ls $xattrop_b0`
+gfid_str_FILE=$(gf_gfid_xattr_to_str $(gf_get_gfid_xattr $B0/$V0"0"/FILE))
+TEST ln $xattrop_b0/$base_entry_b0 $xattrop_b0/$gfid_str_FILE
+EXPECT_WITHIN $HEAL_TIMEOUT "^1$" get_pending_heal_count $V0
+
+TEST $CLI volume set $V0 cluster.self-heal-daemon on
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "1" afr_child_up_status_in_shd $V0 0
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "1" afr_child_up_status_in_shd $V0 1
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "1" afr_child_up_status_in_shd $V0 2
+TEST $CLI volume heal $V0
+EXPECT_WITHIN $HEAL_TIMEOUT "^0$" get_pending_heal_count $V0
+
+# Brick-0 should contain xattrs blaming other 2 bricks.
+# The values will be zero because heal is over.
+EXPECT "000000000000000000000000" get_hex_xattr trusted.afr.$V0-client-1 $B0/${V0}0/FILE
+EXPECT "000000000000000000000000" get_hex_xattr trusted.afr.$V0-client-2 $B0/${V0}0/FILE
+TEST ! getfattr -n trusted.afr.$V0-client-0 $B0/${V0}0/FILE
+
+# Brick-1 and Brick-2 must not contain any afr xattrs.
+TEST ! getfattr -n trusted.afr.$V0-client-0 $B0/${V0}1/FILE
+TEST ! getfattr -n trusted.afr.$V0-client-1 $B0/${V0}1/FILE
+TEST ! getfattr -n trusted.afr.$V0-client-2 $B0/${V0}1/FILE
+TEST ! getfattr -n trusted.afr.$V0-client-0 $B0/${V0}2/FILE
+TEST ! getfattr -n trusted.afr.$V0-client-1 $B0/${V0}2/FILE
+TEST ! getfattr -n trusted.afr.$V0-client-2 $B0/${V0}2/FILE
+
+# check permission bits.
+EXPECT '755' stat -c %a $B0/${V0}0/FILE
+EXPECT '755' stat -c %a $B0/${V0}1/FILE
+EXPECT '755' stat -c %a $B0/${V0}2/FILE
+
+EXPECT_WITHIN $UMOUNT_TIMEOUT "Y" force_umount $M0
+cleanup;
diff --git a/xlators/cluster/afr/src/afr-self-heal-metadata.c b/xlators/cluster/afr/src/afr-self-heal-metadata.c
index ecfa791b8cb..13ef6e887a0 100644
--- a/xlators/cluster/afr/src/afr-self-heal-metadata.c
+++ b/xlators/cluster/afr/src/afr-self-heal-metadata.c
@@ -190,6 +190,59 @@ out:
     return ret;
 }
 
+static int
+__afr_selfheal_metadata_mark_pending_xattrs(call_frame_t *frame, xlator_t *this,
+                                            inode_t *inode,
+                                            struct afr_reply *replies,
+                                            unsigned char *sources)
+{
+    int ret = 0;
+    int i = 0;
+    int m_idx = 0;
+    afr_private_t *priv = NULL;
+    int raw[AFR_NUM_CHANGE_LOGS] = {0};
+    dict_t *xattr = NULL;
+
+    priv = this->private;
+    m_idx = afr_index_for_transaction_type(AFR_METADATA_TRANSACTION);
+    raw[m_idx] = 1;
+
+    xattr = dict_new();
+    if (!xattr)
+        return -ENOMEM;
+
+    for (i = 0; i < priv->child_count; i++) {
+        if (sources[i])
+            continue;
+        ret = dict_set_static_bin(xattr, priv->pending_key[i], raw,
+                                  sizeof(int) * AFR_NUM_CHANGE_LOGS);
+        if (ret) {
+            ret = -1;
+            goto out;
+        }
+    }
+
+    for (i = 0; i < priv->child_count; i++) {
+        if (!sources[i])
+            continue;
+        ret = afr_selfheal_post_op(frame, this, inode, i, xattr, NULL);
+        if (ret < 0) {
+            gf_msg(this->name, GF_LOG_INFO, -ret, AFR_MSG_SELF_HEAL_INFO,
+                   "Failed to set pending metadata xattr on child %d for %s", i,
+                   uuid_utoa(inode->gfid));
+            goto out;
+        }
+    }
+
+    afr_replies_wipe(replies, priv->child_count);
+    ret = afr_selfheal_unlocked_discover(frame, inode, inode->gfid, replies);
+
+out:
+    if (xattr)
+        dict_unref(xattr);
+    return ret;
+}
+
 /*
  * Look for mismatching uid/gid or mode or user xattrs even if
  * AFR xattrs don't say so, and pick one arbitrarily as winner. */
@@ -210,6 +263,7 @@ __afr_selfheal_metadata_finalize_source(call_frame_t *frame, xlator_t *this,
     };
     int source = -1;
     int sources_count = 0;
+    int ret = 0;
 
     priv = this->private;
 
@@ -300,7 +354,13 @@ __afr_selfheal_metadata_finalize_source(call_frame_t *frame, xlator_t *this,
             healed_sinks[i] = 1;
         }
     }
-
+    if ((sources_count == priv->child_count) && (source > -1) &&
+        (AFR_COUNT(healed_sinks, priv->child_count) != 0)) {
+        ret = __afr_selfheal_metadata_mark_pending_xattrs(frame, this, inode,
+                                                          replies, sources);
+        if (ret < 0)
+            return ret;
+    }
 out:
     afr_mark_active_sinks(this, sources, locked_on, healed_sinks);
     return source;