From d7c30458c87f1341295f764e1a2a539dc4248ecc Mon Sep 17 00:00:00 2001
From: Ravishankar N <ravishankar@redhat.com>
Date: Wed, 15 Apr 2015 22:22:08 +0530
Subject: afr: add arbitration support

Backport of http://review.gluster.org/#/c/10258/

Add logic in afr to work in conjunction with the arbiter xlator when a
replica 3 arbiter volume is created. More specifically, this patch:

* Enables full locks for afr data transaction for such volumes.
* Removes the upfront marking of pending xattrs at the time of pre-op
  and defer it to post-op. (This is an arbiter independent change and is made for all afr transactions.)
* After pre-op stage, check if we can proceed with the fop stage without
  ending up in split-brain by examining the changelog xattrs.
* Unwinds the fop with failure if only one source was available at the
   time of pre-op and the fop happened to fail on particular source brick.
* Skips data self-heal if arbiter brick is the only source available.
* Adds the arbiter-count option to the shd graph.

This patch is a part of the arbiter logic implementation for 3 way AFR
details of which can be found at http://review.gluster.org/#/c/9656/

Change-Id: I9603db9d04de5626eb2f4d8d959ef5b46113561d
BUG: 1217689
Signed-off-by: Ravishankar N <ravishankar@redhat.com>
Reviewed-on: http://review.gluster.org/10514
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
---
 tests/basic/afr/arbiter.t | 64 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 64 insertions(+)
 create mode 100644 tests/basic/afr/arbiter.t

(limited to 'tests/basic/afr')

diff --git a/tests/basic/afr/arbiter.t b/tests/basic/afr/arbiter.t
new file mode 100644
index 00000000000..a9d485cd7b4
--- /dev/null
+++ b/tests/basic/afr/arbiter.t
@@ -0,0 +1,64 @@
+#!/bin/bash
+
+. $(dirname $0)/../../include.rc
+. $(dirname $0)/../../volume.rc
+. $(dirname $0)/../../afr.rc
+cleanup;
+
+TEST glusterd;
+TEST pidof glusterd
+
+# Non arbiter replica 3 volumes should not have arbiter-count option enabled.
+TEST $CLI volume create $V0 replica 3 $H0:$B0/${V0}{0,1,2}
+TEST $CLI volume start $V0
+TEST glusterfs --volfile-id=$V0 --volfile-server=$H0 --entry-timeout=0 $M0;
+TEST ! stat $M0/.meta/graphs/active/$V0-replicate-0/options/arbiter-count
+TEST umount $M0
+TEST $CLI volume stop $V0
+TEST $CLI volume delete $V0
+
+# Create and mount a replica 3 arbiter volume.
+TEST $CLI volume create $V0 replica 3 arbiter 1 $H0:$B0/${V0}{0,1,2}
+TEST $CLI volume set $V0 performance.write-behind 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 stat $M0/.meta/graphs/active/$V0-replicate-0/options/arbiter-count
+EXPECT "1" cat $M0/.meta/graphs/active/$V0-replicate-0/options/arbiter-count
+
+# Write data and metadata
+TEST `echo hello >> $M0/file`
+TEST setfattr -n user.name -v value1  $M0/file
+
+# Data I/O will fail if arbiter is the only source.
+TEST kill_brick $V0 $H0 $B0/${V0}0
+TEST `echo "B0 is down, B1 and B2 are sources" >> $M0/file`
+TEST setfattr -n user.name -v value2  $M0/file
+TEST $CLI volume start $V0 force
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 0
+TEST kill_brick $V0 $H0 $B0/${V0}1
+TEST `echo "B2 is down, B3 is the only source, writes will fail" >> $M0/file`
+TEST ! cat $M0/file
+# Metadata I/O should still succeed.
+TEST getfattr -n user.name $M0/file
+TEST setfattr -n user.name -v value3 $M0/file
+
+#shd should not data self-heal from arbiter to the sinks.
+TEST $CLI volume set $V0 cluster.self-heal-daemon on
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "Y" glustershd_up_status
+TEST $CLI volume heal $V0
+EXPECT_WITHIN $HEAL_TIMEOUT '1' echo $(count_sh_entries $B0/$V0"1")
+EXPECT_WITHIN $HEAL_TIMEOUT '1' echo $(count_sh_entries $B0/$V0"2")
+
+TEST $CLI volume start $V0 force
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "Y" glustershd_up_status
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 1
+TEST $CLI volume heal $V0
+EXPECT 0 afr_get_pending_heal_count $V0
+
+# I/O can resume again.
+TEST cat $M0/file
+TEST getfattr -n user.name $M0/file
+TEST `echo append>> $M0/file`
+TEST umount $M0
+cleanup
-- 
cgit