cluster/afr: Send truncate on arbiter brick from SHD

Problem:
In an arbiter volume configuration SHD will not send any writes onto the arbiter
brick even if there is data pending marker for the arbiter brick. If we have a
arbiter setup on the geo-rep master and there are data pending markers for the files
on arbiter brick, SHD will not mark any data changelog during healing. While syncing
the data from master to slave, if the arbiter-brick is considered as ACTIVE, then
there is a chance that slave will miss out some data. If the arbiter brick is being
newly added or replaced there is a chance of slave missing all the data during sync.

Fix:
If there is data pending marker for the arbiter brick, send truncate on the arbiter
brick during heal, so that it will record truncate as the data transaction in changelog.

Change-Id: I3242ba6cea6da495c418ef860d9c3359c5459dec
fixes: bz#1687672
Signed-off-by: karthik-us <ksubrahm@redhat.com>

2 files changed, 39 insertions, 1 deletions

diff --git a/tests/bugs/replicate/bug-1686568-send-truncate-on-arbiter-from-shd.t b/tests/bugs/replicate/bug-1686568-send-truncate-on-arbiter-from-shd.t
new file mode 100644
index 00000000000..78581e99614
--- /dev/null
+++ b/tests/bugs/replicate/bug-1686568-send-truncate-on-arbiter-from-shd.t
@@ -0,0 +1,38 @@
+#!/bin/bash
+. $(dirname $0)/../../include.rc
+. $(dirname $0)/../../volume.rc
+cleanup;
+
+CHANGELOG_PATH_0="$B0/${V0}2/.glusterfs/changelogs"
+ROLLOVER_TIME=100
+
+TEST glusterd
+TEST pidof glusterd
+TEST $CLI volume create $V0 replica 2 $H0:$B0/${V0}{0,1}
+TEST $CLI volume set $V0 changelog.changelog on
+TEST $CLI volume set $V0 changelog.rollover-time $ROLLOVER_TIME
+TEST $CLI volume start $V0
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" brick_up_status $V0 $H0 $B0/${V0}0
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" brick_up_status $V0 $H0 $B0/${V0}1
+
+TEST $GFS --volfile-id=$V0 --volfile-server=$H0 $M0;
+TEST dd if=/dev/zero of=$M0/file1 bs=128K count=5
+
+TEST $CLI volume profile $V0 start
+TEST $CLI volume add-brick $V0 replica 3 arbiter 1 $H0:$B0/${V0}2
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" brick_up_status $V0 $H0 $B0/${V0}2
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "Y" glustershd_up_status
+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
+
+TEST $CLI volume profile $V0 info
+truncate_count=$($CLI volume profile $V0 info | grep TRUNCATE | awk '{count += $8} END {print count}')
+
+EXPECT "1" echo $truncate_count
+EXPECT "1" check_changelog_op ${CHANGELOG_PATH_0} "^ D "
+
+cleanup;
diff --git a/tests/volume.rc b/tests/volume.rc
index 261c6554d46..87ca9589305 100644
--- a/tests/volume.rc
+++ b/tests/volume.rc
@@ -879,5 +879,5 @@ function check_changelog_op {
         local clog_path=$1
         local op=$2
 
-        $PYTHON $(dirname $0)/../../utils/changelogparser.py ${clog_path}/CHANGELOG | grep $op | wc -l
+        $PYTHON $(dirname $0)/../../utils/changelogparser.py ${clog_path}/CHANGELOG | grep "$op" | wc -l
 }