cluster/afr: split-brain resolution CLI

Extend the AFR heal command to include automated split-brain resolution.

This patch [3/3] is the final patch for afr automated split-brain resolution
implementation.

"gluster volume heal <VOLNAME> [full | statistics [heal-count [replica
<HOSTNAME:BRICKNAME>]] |info [healed | heal-failed | split-brain]| split-brain
{bigger-file <FILE> |source-brick <HOSTNAME:BRICKNAME> [<FILE>]}]"

The new additions being:
1.gluster volume heal <VOLNAME> split-brain bigger-file <FILE>
Locates the replica containing the FILE, selects bigger-file as source and
completes heal.

2.gluster volume heal <VOLNAME> split-brain source-brick <HOSTNAME:BRICKNAME>
<FILE>
Selects <FILE> present in <HOSTNAME:BRICKNAME> as source and completes heal.

3.gluster volume heal <VOLNAME> split-brain <HOSTNAME:BRICKNAME>
Selects all split-brained files in <HOSTNAME:BRICKNAME> as source and completes
heal.

Note: <FILE> can be either the full file name as seen from the root of the
volume (or) the gfid-string representation of the file, which sometimes gets
displayed in the heal info command's output.

Entry/gfid split-brain resolution is not supported.

Example can be found in the test case.

Change-Id: I4649733922d406f14f28ee9033a5cb627b9538b3
BUG: 1136769
Signed-off-by: Ravishankar N <ravishankar@redhat.com>
Reviewed-on: http://review.gluster.org/9377
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
Tested-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>

1 files changed, 183 insertions, 0 deletions

diff --git a/tests/basic/afr/split-brain-healing.t b/tests/basic/afr/split-brain-healing.t
new file mode 100644
index 00000000000..1dc317df8dd
--- /dev/null
+++ b/tests/basic/afr/split-brain-healing.t
@@ -0,0 +1,183 @@
+#!/bin/bash
+
+#Test the split-brain resolution CLI commands.
+. $(dirname $0)/../../include.rc
+. $(dirname $0)/../../volume.rc
+
+function get_replicate_subvol_number {
+        local filename=$1
+        #get_backend_paths
+        if [ -f $B0/${V0}1/$filename ]
+        then
+                echo 0
+        elif [ -f $B0/${V0}3/$filename ]
+        then    echo 1
+        else
+                echo -1
+        fi
+}
+
+cleanup;
+
+AREQUAL_PATH=$(dirname $0)/../../utils
+CFLAGS=""
+test "`uname -s`" != "Linux" && {
+    CFLAGS="$CFLAGS -I$(dirname $0)/../../../contrib/argp-standalone ";
+    CFLAGS="$CFLAGS -L$(dirname $0)/../../../contrib/argp-standalone -largp ";
+    CFLAGS="$CFLAGS -lintl";
+}
+build_tester $AREQUAL_PATH/arequal-checksum.c $CFLAGS
+TEST glusterd
+TEST pidof glusterd
+TEST $CLI volume create $V0 replica 2 $H0:$B0/${V0}{1,2,3,4}
+TEST $CLI volume set $V0 cluster.self-heal-daemon off
+TEST $CLI volume start $V0
+TEST glusterfs --volfile-id=/$V0 --volfile-server=$H0 $M0 --attribute-timeout=0 --entry-timeout=0
+
+cd $M0
+for i in {1..10}
+do
+        echo "Initial content">>file$i
+done
+
+replica_0_files_list=(`ls $B0/${V0}1`)
+replica_1_files_list=(`ls $B0/${V0}3`)
+
+############ Create data split-brain in the files. ###########################
+TEST kill_brick $V0 $H0 $B0/${V0}1
+for file in ${!replica_0_files_list[*]}
+do
+        echo "B1 is down">>${replica_0_files_list[$file]}
+done
+TEST kill_brick $V0 $H0 $B0/${V0}3
+for file in ${!replica_1_files_list[*]}
+do
+        echo "B3 is down">>${replica_1_files_list[$file]}
+done
+
+SMALLER_FILE_SIZE=$(stat -c %s file1)
+
+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 2
+
+TEST kill_brick $V0 $H0 $B0/${V0}2
+for file in ${!replica_0_files_list[*]}
+do
+        echo "B2 is down">>${replica_0_files_list[$file]}
+        echo "appending more content to make it the bigger file">>${replica_0_files_list[$file]}
+done
+TEST kill_brick $V0 $H0 $B0/${V0}4
+for file in ${!replica_1_files_list[*]}
+do
+        echo "B4 is down">>${replica_1_files_list[$file]}
+        echo "appending more content to make it the bigger file">>${replica_1_files_list[$file]}
+done
+
+BIGGER_FILE_SIZE=$(stat -c %s file1)
+
+TEST $CLI volume start $V0 force
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 1
+EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 3
+
+
+############### Acessing the files should now give EIO. ###############################
+TEST ! cat file1
+TEST ! cat file2
+TEST ! cat file3
+TEST ! cat file4
+TEST ! cat file5
+TEST ! cat file6
+TEST ! cat file7
+TEST ! cat file8
+TEST ! cat file9
+TEST ! cat file10
+###################
+TEST $CLI volume set $V0 cluster.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
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "1" afr_child_up_status_in_shd $V0 3
+
+################ Heal file1 using the bigger-file option  ##############
+$CLI volume heal $V0 split-brain bigger-file /file1
+EXPECT "0" echo $?
+EXPECT $BIGGER_FILE_SIZE stat -c %s file1
+
+################ Heal file2 using the bigger-file option and its gfid ##############
+subvolume=$(get_replicate_subvol_number file2)
+if [ $subvolume == 0 ]
+then
+        GFID=$(gf_get_gfid_xattr $B0/${V0}1/file2)
+elif [ $subvolume == 1 ]
+then
+        GFID=$(gf_get_gfid_xattr $B0/${V0}3/file2)
+fi
+GFIDSTR="gfid:$(gf_gfid_xattr_to_str $GFID)"
+$CLI volume heal $V0 split-brain bigger-file $GFIDSTR
+EXPECT "0" echo $?
+
+################ Heal file3 using the source-brick option  ##############
+################ Use the brick having smaller file size as source #######
+subvolume=$(get_replicate_subvol_number file3)
+if [ $subvolume == 0 ]
+then
+        $CLI volume heal $V0 split-brain source-brick $H0:$B0/${V0}2 /file3
+elif [ $subvolume == 1]
+then
+        $CLI volume heal $V0 split-brain source-brick $H0:$B0/${V0}4 /file3
+fi
+EXPECT "0" echo $?
+EXPECT $SMALLER_FILE_SIZE stat -c %s file3
+
+################ Heal file4 using the source-brick option and it's gfid ##############
+################ Use the brick having smaller file size as source #######
+subvolume=$(get_replicate_subvol_number file4)
+if [ $subvolume == 0 ]
+then
+        GFID=$(gf_get_gfid_xattr $B0/${V0}1/file4)
+        GFIDSTR="gfid:$(gf_gfid_xattr_to_str $GFID)"
+        $CLI volume heal $V0 split-brain source-brick $H0:$B0/${V0}2 $GFIDSTR
+elif [ $subvolume == 1]
+then
+        GFID=$(gf_get_gfid_xattr $B0/${V0}3/file4)
+        GFIDSTR="gfid:$(gf_gfid_xattr_to_str $GFID)"
+        $CLI volume heal $V0 split-brain source-brick $H0:$B0/${V0}4 $GFIDSTR
+fi
+EXPECT "0" echo $?
+EXPECT $SMALLER_FILE_SIZE stat -c %s file4
+
+################ Heal remaining SB'ed files of replica_0 using B1 as source ##############
+$CLI volume heal $V0 split-brain source-brick $H0:$B0/${V0}1
+EXPECT "0" echo $?
+
+################ Heal remaining SB'ed files of replica_1 using B3 as source ##############
+$CLI volume heal $V0 split-brain source-brick $H0:$B0/${V0}3
+EXPECT "0" echo $?
+
+############### Reading the files should now suceed. ###############################
+TEST  cat file1
+TEST  cat file2
+TEST  cat file3
+TEST  cat file4
+TEST  cat file5
+TEST  cat file6
+TEST  cat file7
+TEST  cat file8
+TEST  cat file9
+TEST  cat file10
+
+################ File contents on the bricks must be same. ################################
+TEST diff <(arequal-checksum -p $B0/$V01 -i .glusterfs) <(arequal-checksum -p $B0/$V02 -i .glusterfs)
+TEST diff <(arequal-checksum -p $B0/$V03 -i .glusterfs) <(arequal-checksum -p $B0/$V04 -i .glusterfs)
+
+############### Trying to heal files not in SB should fail. ###############################
+$CLI volume heal $V0 split-brain bigger-file /file1
+EXPECT "1" echo $?
+$CLI volume heal $V0 split-brain source-brick $H0:$B0/${V0}4 /file3
+EXPECT "1" echo $?
+
+cd -
+TEST rm $AREQUAL_PATH/arequal-checksum
+cleanup