cluster/ec: Non-disruptive upgrade on EC volume fails

Problem:
Enabling optimistic changelog on EC volume was not
handling node down scenarios appropriately resulting
in volume data inaccessibility.

Solution:
Update dirty xattr appropriately on good bricks whenever
nodes are down. This would fix the metadata information
as part of heal and thus ensures data accessibility.

BUG: 1468261
Change-Id: I08b0d28df386d9b2b49c3de84b4aac1c729ac057
Signed-off-by: Sunil Kumar Acharya <sheggodu@redhat.com>
Reviewed-on: https://review.gluster.org/17703
Smoke: Gluster Build System <jenkins@build.gluster.org>
CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>

2 files changed, 97 insertions, 0 deletions

diff --git a/tests/basic/ec/ec-1468261.t b/tests/basic/ec/ec-1468261.t
new file mode 100644
index 00000000000..9c4f981ab47
--- /dev/null
+++ b/tests/basic/ec/ec-1468261.t
@@ -0,0 +1,96 @@
+#!/bin/bash
+#
+# This test case verifies handling node down scenario with optimistic
+# changelog enabled on EC volume.
+###
+
+. $(dirname $0)/../../include.rc
+. $(dirname $0)/../../volume.rc
+
+cleanup
+
+#cleate and start volume
+TEST glusterd
+TEST pidof glusterd
+TEST $CLI volume create $V0 disperse 6 redundancy 2 $H0:$B0/${V0}{0..5}
+TEST $CLI volume set $V0 disperse.optimistic-change-log on
+TEST $CLI volume start $V0
+
+#Mount the volume
+TEST $GFS --volfile-id=/$V0 --volfile-server=$H0 $M0;
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "6" ec_child_up_count $V0 0
+
+#Verify that all is good
+TEST mkdir $M0/test_dir
+TEST touch $M0/test_dir/file
+sleep 2
+EXPECT_WITHIN $IO_WAIT_TIMEOUT "^$" get_hex_xattr trusted.ec.dirty $B0/${V0}0/test_dir
+EXPECT_WITHIN $IO_WAIT_TIMEOUT "^$" get_hex_xattr trusted.ec.dirty $B0/${V0}1/test_dir
+EXPECT_WITHIN $IO_WAIT_TIMEOUT "^$" get_hex_xattr trusted.ec.dirty $B0/${V0}2/test_dir
+EXPECT_WITHIN $IO_WAIT_TIMEOUT "^$" get_hex_xattr trusted.ec.dirty $B0/${V0}3/test_dir
+EXPECT_WITHIN $IO_WAIT_TIMEOUT "^$" get_hex_xattr trusted.ec.dirty $B0/${V0}4/test_dir
+EXPECT_WITHIN $IO_WAIT_TIMEOUT "^$" get_hex_xattr trusted.ec.dirty $B0/${V0}5/test_dir
+
+#Touch a file and kill two bricks
+pid0=`get_brick_pid $V0 $H0 $B0/${V0}0`
+pid1=`get_brick_pid $V0 $H0 $B0/${V0}1`
+TEST touch $M0/test_dir/new_file
+kill $pid0
+kill $pid1
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "4" ec_child_up_count $V0 0
+
+#Dirty should be set on up bricks
+EXPECT_WITHIN $IO_WAIT_TIMEOUT "^$" get_hex_xattr trusted.ec.dirty $B0/${V0}0/test_dir
+EXPECT_WITHIN $IO_WAIT_TIMEOUT "^$" get_hex_xattr trusted.ec.dirty $B0/${V0}1/test_dir
+EXPECT_WITHIN $IO_WAIT_TIMEOUT  "^00000000000000010000000000000001$" get_hex_xattr trusted.ec.dirty $B0/${V0}2/test_dir
+EXPECT_WITHIN $IO_WAIT_TIMEOUT  "^00000000000000010000000000000001$" get_hex_xattr trusted.ec.dirty $B0/${V0}3/test_dir
+EXPECT_WITHIN $IO_WAIT_TIMEOUT  "^00000000000000010000000000000001$" get_hex_xattr trusted.ec.dirty $B0/${V0}4/test_dir
+EXPECT_WITHIN $IO_WAIT_TIMEOUT  "^00000000000000010000000000000001$" get_hex_xattr trusted.ec.dirty $B0/${V0}5/test_dir
+
+#Bring up the down bricks
+TEST $CLI volume start $V0 force
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "6" ec_child_up_count $V0 0
+
+#remove mount point contents
+TEST rm -rf $M0"/*" 2>/dev/null
+
+# unmount and remount the volume
+EXPECT_WITHIN $UMOUNT_TIMEOUT "Y" force_umount $M0
+TEST glusterfs -s $H0 --volfile-id $V0 $M0;
+
+#Create a tar file
+TEST mkdir $M0/test_dir
+for i in {1..3000};do
+dd if=/dev/urandom of=$M0/test_dir/file-$i bs=1k count=10;
+done
+tar -cf $M0/test_dir.tar $M0/test_dir/ 2>/dev/null
+rm -rf $M0/test_dir/
+
+#Untar the tar file
+tar -C $M0 -xf $M0/test_dir.tar 2>/dev/null&
+
+#Kill 1st and 2nd brick
+TEST kill_brick $V0 $H0 $B0/${V0}0
+TEST kill_brick $V0 $H0 $B0/${V0}1
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "4" ec_child_up_count $V0 0
+
+#Stop untaring
+TEST kill %1
+
+#Bring up the down bricks
+TEST $CLI volume start $V0 force
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "6" ec_child_up_count $V0 0
+
+#Wait for heal to complete
+EXPECT_WITHIN $HEAL_TIMEOUT "^0$" get_pending_heal_count $V0
+
+#Kill 3rd and 4th brick
+TEST kill_brick $V0 $H0 $B0/${V0}3
+TEST kill_brick $V0 $H0 $B0/${V0}4
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "4" ec_child_up_count $V0 0
+
+#remove mount point contents
+#this will fail if things are wrong
+TEST rm -rf $M0"/*" 2>/dev/null
+
+cleanup
diff --git a/tests/basic/ec/ec-background-heals.t b/tests/basic/ec/ec-background-heals.t
index eb434908bad..b9291bc9c32 100644
--- a/tests/basic/ec/ec-background-heals.t
+++ b/tests/basic/ec/ec-background-heals.t
@@ -16,6 +16,7 @@ TEST $CLI volume set $V0 performance.quick-read off
 TEST $CLI volume set $V0 performance.read-ahead off
 TEST $CLI volume set $V0 performance.io-cache off
 TEST $CLI volume set $V0 disperse.background-heals 0
+TEST $CLI volume set $V0 disperse.eager-lock off
 TEST $CLI volume start $V0
 
 TEST $GFS --volfile-id=/$V0 --volfile-server=$H0 $M0;