From 2b76520ca3e41cbac8f9318dce87e0b8d670c0ee Mon Sep 17 00:00:00 2001
From: Krutika Dhananjay <kdhananj@redhat.com>
Date: Thu, 8 Dec 2016 22:49:48 +0530
Subject: cluster/afr: Fix per-txn optimistic changelog initialisation

Incorrect initialisation of local->optimistic_change_log was leading
to skipped pre-op and post-op even when a brick didn't participate in
the txn because it was down.
The result - missing granular name index resulting in some entries
never getting healed.

FIX:
Initialise local->optimistic_change_log just before pre-op.

Also fixed granular entry heal to create the granular name index in
pre-op as opposed to post-op. This is to prevent loss of granular
information when during an entry txn, the good (src) brick goes
offline before the post-op is done. This would cause self-heal to
do conservative merge (since dirty xattr is the only information
available), which when granular-entry-heal is enabled, expects
granular indices, the lack of which can lead to loss of data in
the worst case.

Change-Id: Ia3ad716d6fb1821555f02180e86e8711a79f958d
BUG: 1402730
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/16075
Smoke: Gluster Build System <jenkins@build.gluster.org>
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org>
CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
---
 tests/bugs/replicate/bug-1402730.t | 42 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)
 create mode 100644 tests/bugs/replicate/bug-1402730.t

(limited to 'tests')

diff --git a/tests/bugs/replicate/bug-1402730.t b/tests/bugs/replicate/bug-1402730.t
new file mode 100644
index 00000000000..c6768a0c678
--- /dev/null
+++ b/tests/bugs/replicate/bug-1402730.t
@@ -0,0 +1,42 @@
+#!/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 granular-entry-heal on
+TEST $CLI volume set $V0 cluster.data-self-heal off
+TEST $CLI volume set $V0 cluster.metadata-self-heal off
+TEST $CLI volume set $V0 cluster.entry-self-heal off
+TEST $CLI volume set $V0 cluster.self-heal-daemon off
+TEST $CLI volume start $V0
+
+TEST glusterfs --volfile-id=$V0 --volfile-server=$H0 --entry-timeout=0 $M0
+
+TEST mkdir -p $M0/a/b/c -p
+cd $M0/a/b/c
+
+TEST kill_brick $V0 $H0 $B0/${V0}2
+rm -rf $B0/${V0}2/*
+rm -rf $B0/${V0}2/.glusterfs
+TEST $CLI volume start $V0 force
+
+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 $V0 2
+
+TEST touch file
+
+GFID_C=$(get_gfid_string $M0/a/b/c)
+TEST stat $B0/${V0}0/.glusterfs/indices/entry-changes/$GFID_C/file
+TEST stat $B0/${V0}1/.glusterfs/indices/entry-changes/$GFID_C/file
+
+EXPECT "00000001" afr_get_specific_changelog_xattr $B0/${V0}0/a/b/c trusted.afr.$V0-client-2 entry
+EXPECT "00000001" afr_get_specific_changelog_xattr $B0/${V0}1/a/b/c trusted.afr.$V0-client-2 entry
+
+cd ~
+
+cleanup
-- 
cgit