afr : Enable auto heal when replica count increases

This patch is part two change to prevent data loss
in a replicate volume on doing a add-brick operation.

Problem: After doing add-brick, there is a chance
that self heal might happen from the newly added
brick rather than the source brick, leading to data loss.

Solution: Mark pending changelogs on afr children for
the new afr-child so that heal is performed in the
correct direction.

Change-Id: I11871e55eef3593aec874f92214a2d97da229b17
BUG: 1276203
Signed-off-by: Anuradha Talur <atalur@redhat.com>
Reviewed-on: http://review.gluster.org/12454
Smoke: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
Tested-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
CentOS-regression: Gluster Build System <jenkins@build.gluster.com>
NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org>

1 files changed, 67 insertions, 0 deletions

diff --git a/tests/basic/afr/add-brick-self-heal.t b/tests/basic/afr/add-brick-self-heal.t
new file mode 100644
index 00000000000..748d36758e7
--- /dev/null
+++ b/tests/basic/afr/add-brick-self-heal.t
@@ -0,0 +1,67 @@
+#!/bin/bash
+. $(dirname $0)/../../include.rc
+. $(dirname $0)/../../volume.rc
+cleanup;
+
+TEST glusterd
+TEST pidof glusterd
+TEST $CLI volume create $V0 replica 2 $H0:$B0/${V0}{0,1}
+TEST $CLI volume start $V0
+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 $V0 self-heal-daemon off
+TEST glusterfs --volfile-id=$V0 --volfile-server=$H0 $M0;
+
+# Create files
+for i in {1..5}
+do
+        echo $i > $M0/file$i.txt
+done
+
+# Metadata changes
+TEST setfattr -n user.test -v qwerty $M0/file5.txt
+
+# Add brick1
+TEST $CLI volume add-brick $V0 replica 3 $H0:$B0/${V0}2
+
+# New-brick should accuse the old-bricks (Simulating case for data-loss)
+TEST setfattr -n trusted.afr.$V0-client-0 -v 0x000000000000000000000001 $B0/${V0}2/
+TEST setfattr -n trusted.afr.$V0-client-1 -v 0x000000000000000000000001 $B0/${V0}2/
+
+# Check if pending xattr and dirty-xattr are set for newly-added-brick
+EXPECT "000000000000000100000001" get_hex_xattr trusted.afr.$V0-client-2 $B0/${V0}0
+EXPECT "000000000000000100000001" get_hex_xattr trusted.afr.$V0-client-2 $B0/${V0}1
+EXPECT "000000000000000000000001" get_hex_xattr trusted.afr.dirty $B0/${V0}2
+
+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 $CLI volume set $V0 self-heal-daemon on
+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
+
+# Wait for heal to complete
+EXPECT_WITHIN $HEAL_TIMEOUT "^0$" get_pending_heal_count $V0
+
+# Check if entry-heal has happened
+TEST diff <(ls $B0/${V0}0 | sort) <(ls $B0/${V0}2 | sort)
+TEST diff <(ls $B0/${V0}1 | sort) <(ls $B0/${V0}2 | sort)
+
+# Test if data was healed
+TEST diff $B0/${V0}0/file1.txt $B0/${V0}2/file1.txt
+
+# Test if metadata was healed and exists on both the bricks
+EXPECT "qwerty" get_text_xattr user.test $B0/${V0}2/file5.txt
+EXPECT "qwerty" get_text_xattr user.test $B0/${V0}0/file5.txt
+
+EXPECT "000000000000000000000000" get_hex_xattr trusted.afr.$V0-client-2 $B0/${V0}0
+EXPECT "000000000000000000000000" get_hex_xattr trusted.afr.$V0-client-2 $B0/${V0}1
+EXPECT "000000000000000000000000" get_hex_xattr trusted.afr.dirty $B0/${V0}2
+
+cleanup;