cluster/ec: Make background healing optional behavior

Provide options to control number of active background heal count and qlen.

 >Change-Id: Idc2419219d881f47e7d2e9bbc1dcdd999b372033
 >BUG: 1237381
 >Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
 >Reviewed-on: http://review.gluster.org/11473
 >Reviewed-by: Xavier Hernandez <xhernandez@datalab.es>
 >Tested-by: Gluster Build System <jenkins@build.gluster.com>

BUG: 1238476
Change-Id: I22ba902d9911195656db9e458c01b54cf0afcd7a
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
Reviewed-on: http://review.gluster.org/11680
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Xavier Hernandez <xhernandez@datalab.es>

15 files changed, 138 insertions, 38 deletions

diff --git a/tests/basic/afr/arbiter.t b/tests/basic/afr/arbiter.t
index 8a983fb0577..f06fdb1c49f 100644
--- a/tests/basic/afr/arbiter.t
+++ b/tests/basic/afr/arbiter.t
@@ -60,7 +60,7 @@ 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 $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 1
 TEST $CLI volume heal $V0
-EXPECT 0 afr_get_pending_heal_count $V0
+EXPECT 0 get_pending_heal_count $V0
 
 # I/O can resume again.
 TEST cat $M0/file
diff --git a/tests/basic/afr/client-side-heal.t b/tests/basic/afr/client-side-heal.t
index c9b3e355802..18f76265b29 100644
--- a/tests/basic/afr/client-side-heal.t
+++ b/tests/basic/afr/client-side-heal.t
@@ -33,7 +33,7 @@ TEST chmod +x $M0/mdatafile
 #pending entry heal. Also causes pending metadata/data heals on file{1..5}
 TEST touch $M0/dir/file{1..5}
 
-EXPECT 8 afr_get_pending_heal_count $V0
+EXPECT 8 get_pending_heal_count $V0
 
 #After brick comes back up, access from client should not trigger heals
 TEST $CLI volume start $V0 force
@@ -54,7 +54,7 @@ TEST glusterfs --volfile-id=$V0 --volfile-server=$H0 --entry-timeout=0 $M0;
 TEST ls $M0/dir
 
 #No heal must have happened
-EXPECT 8 afr_get_pending_heal_count $V0
+EXPECT 8 get_pending_heal_count $V0
 
 #Enable heal client side heal options and trigger heals
 TEST $CLI volume set $V0 cluster.data-self-heal on
@@ -63,7 +63,7 @@ TEST $CLI volume set $V0 cluster.entry-self-heal on
 
 #Metadata heal is triggered by lookup without need for inode refresh.
 TEST ls $M0/mdatafile
-EXPECT 7 afr_get_pending_heal_count $V0
+EXPECT 7 get_pending_heal_count $V0
 
 #Inode refresh must trigger data and entry heals.
 #To trigger inode refresh for sure, the volume is unmounted and mounted each time.
@@ -74,7 +74,7 @@ TEST cat $M0/datafile
 EXPECT_WITHIN $UMOUNT_TIMEOUT "Y" force_umount $M0
 TEST glusterfs --volfile-id=$V0 --volfile-server=$H0 --entry-timeout=0 $M0;
 TEST ls $M0/dir
-EXPECT 5 afr_get_pending_heal_count $V0
+EXPECT 5 get_pending_heal_count $V0
 
 TEST cat  $M0/dir/file1
 TEST cat  $M0/dir/file2
@@ -82,5 +82,5 @@ TEST cat  $M0/dir/file3
 TEST cat  $M0/dir/file4
 TEST cat  $M0/dir/file5
 
-EXPECT 0 afr_get_pending_heal_count $V0
+EXPECT 0 get_pending_heal_count $V0
 cleanup;
diff --git a/tests/basic/afr/replace-brick-self-heal.t b/tests/basic/afr/replace-brick-self-heal.t
index 8ced7df3c76..fef671a3875 100644
--- a/tests/basic/afr/replace-brick-self-heal.t
+++ b/tests/basic/afr/replace-brick-self-heal.t
@@ -43,7 +43,7 @@ EXPECT_WITHIN $CHILD_UP_TIMEOUT "1" afr_child_up_status_in_shd $V0 1
 TEST $CLI volume heal $V0
 
 # Wait for heal to complete
-EXPECT_WITHIN $HEAL_TIMEOUT "0" afr_get_pending_heal_count $V0
+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}1_new | sort)
diff --git a/tests/basic/afr/root-squash-self-heal.t b/tests/basic/afr/root-squash-self-heal.t
index fa9a163e623..8337432dbc9 100644
--- a/tests/basic/afr/root-squash-self-heal.t
+++ b/tests/basic/afr/root-squash-self-heal.t
@@ -20,6 +20,6 @@ echo abc > $M0/a
 TEST $CLI volume start $V0 force
 EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 0
 find $M0 | xargs stat > /dev/null
-EXPECT_WITHIN $HEAL_TIMEOUT "0" afr_get_pending_heal_count $V0
+EXPECT_WITHIN $HEAL_TIMEOUT "0" get_pending_heal_count $V0
 
 cleanup
diff --git a/tests/basic/afr/self-heal.t b/tests/basic/afr/self-heal.t
index dbd89619c09..e1ac17c2d79 100644
--- a/tests/basic/afr/self-heal.t
+++ b/tests/basic/afr/self-heal.t
@@ -53,7 +53,7 @@ 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
 TEST $CLI volume heal $V0
-EXPECT_WITHIN $HEAL_TIMEOUT "0" afr_get_pending_heal_count $V0
+EXPECT_WITHIN $HEAL_TIMEOUT "0" get_pending_heal_count $V0
 
 #check all files created/deleted on brick1 are also replicated on brick 0
 #(i.e. no reverse heal has happened)
@@ -82,7 +82,7 @@ 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
 TEST $CLI volume heal $V0
-EXPECT_WITHIN $HEAL_TIMEOUT "0" afr_get_pending_heal_count $V0
+EXPECT_WITHIN $HEAL_TIMEOUT "0" get_pending_heal_count $V0
 
 #check heal has happened in the correct direction
 TEST test -d $B0/brick0/file
@@ -105,7 +105,7 @@ 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
 TEST $CLI volume heal $V0
-EXPECT_WITHIN $HEAL_TIMEOUT "0" afr_get_pending_heal_count $V0
+EXPECT_WITHIN $HEAL_TIMEOUT "0" get_pending_heal_count $V0
 
 #check heal has happened in the correct direction
 EXPECT "777" stat -c %a $B0/brick0/file
@@ -129,7 +129,7 @@ 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
 TEST $CLI volume heal $V0
-EXPECT_WITHIN $HEAL_TIMEOUT "0" afr_get_pending_heal_count $V0
+EXPECT_WITHIN $HEAL_TIMEOUT "0" get_pending_heal_count $V0
 
 #check heal has happened in the correct direction
 EXPECT "$NEW_UID$NEW_GID" stat -c %u%g $B0/brick0/file
@@ -160,7 +160,7 @@ 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
 TEST $CLI volume heal $V0
-EXPECT_WITHIN $HEAL_TIMEOUT "0" afr_get_pending_heal_count $V0
+EXPECT_WITHIN $HEAL_TIMEOUT "0" get_pending_heal_count $V0
 
 #check heal has happened in the correct direction
 EXPECT 0 stat -c %s $B0/brick1/file
@@ -183,7 +183,7 @@ 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
 TEST $CLI volume heal $V0
-EXPECT_WITHIN $HEAL_TIMEOUT "0" afr_get_pending_heal_count $V0
+EXPECT_WITHIN $HEAL_TIMEOUT "0" get_pending_heal_count $V0
 
 #check heal has happened in the correct direction
 EXPECT "$GFID" gf_get_gfid_xattr $B0/brick0/file
@@ -207,7 +207,7 @@ 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
 TEST $CLI volume heal $V0
-EXPECT_WITHIN $HEAL_TIMEOUT "0" afr_get_pending_heal_count $V0
+EXPECT_WITHIN $HEAL_TIMEOUT "0" get_pending_heal_count $V0
 
 #check heal has happened in the correct direction
 TEST test -f $B0/brick0/hard_link_to_file
@@ -233,7 +233,7 @@ 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
 TEST $CLI volume heal $V0
-EXPECT_WITHIN $HEAL_TIMEOUT "0" afr_get_pending_heal_count $V0
+EXPECT_WITHIN $HEAL_TIMEOUT "0" get_pending_heal_count $V0
 
 TEST diff <(echo "user.myattr_1=\"My_attribute_1_modified\"") <(getfattr -n user.myattr_1 $B0/brick1/file|grep user.myattr_1)
 TEST diff <(echo "user.myattr_3=\"My_attribute_3\"") <(getfattr -n user.myattr_3 $B0/brick1/file|grep user.myattr_3)
diff --git a/tests/basic/afr/self-heald.t b/tests/basic/afr/self-heald.t
index ee0afaf9d4e..b8bee5cf0a1 100644
--- a/tests/basic/afr/self-heald.t
+++ b/tests/basic/afr/self-heald.t
@@ -68,7 +68,7 @@ done
 HEAL_FILES=$(($HEAL_FILES + 3))
 
 cd ~
-EXPECT "$HEAL_FILES" afr_get_pending_heal_count $V0
+EXPECT "$HEAL_FILES" get_pending_heal_count $V0
 
 #When bricks are down, it says Transport End point Not connected for them
 EXPECT "3" disconnected_brick_count $V0
@@ -78,12 +78,12 @@ EXPECT "3" disconnected_brick_count $V0
 #replica pair.
 for i in {11..20}; do echo abc > $M0/$i; done
 HEAL_FILES=$(($HEAL_FILES + 10)) #count extra 10 files
-EXPECT "$HEAL_FILES" afr_get_pending_heal_count $V0
+EXPECT "$HEAL_FILES" get_pending_heal_count $V0
 #delete the files now, so that stale indices will remain.
 for i in {11..20}; do rm -f $M0/$i; done
 #After deleting files they should not appear in heal info
 HEAL_FILES=$(($HEAL_FILES - 10))
-EXPECT "$HEAL_FILES" afr_get_pending_heal_count $V0
+EXPECT "$HEAL_FILES" get_pending_heal_count $V0
 
 
 TEST ! $CLI volume heal $V0
@@ -99,10 +99,10 @@ check_bricks_up $V0
 TEST $CLI volume heal $V0
 sleep 5 #Until the heal-statistics command implementation
 #check that this heals the contents partially
-TEST [ $HEAL_FILES -gt $(afr_get_pending_heal_count $V0) ]
+TEST [ $HEAL_FILES -gt $(get_pending_heal_count $V0) ]
 
 TEST $CLI volume heal $V0 full
-EXPECT_WITHIN 30 "0" afr_get_pending_heal_count $V0
+EXPECT_WITHIN 30 "0" get_pending_heal_count $V0
 
 #Test that ongoing IO is not considered as Pending heal
 (dd if=/dev/zero of=$M0/file1 bs=1k 2>/dev/null 1>/dev/null)&
@@ -115,7 +115,7 @@ back_pid3=$!;
 back_pid4=$!;
 (dd if=/dev/zero of=$M0/file5 bs=1k 2>/dev/null 1>/dev/null)&
 back_pid5=$!;
-EXPECT 0 afr_get_pending_heal_count $V0
+EXPECT 0 get_pending_heal_count $V0
 kill -SIGTERM $back_pid1;
 kill -SIGTERM $back_pid2;
 kill -SIGTERM $back_pid3;
@@ -132,13 +132,13 @@ TEST $CLI volume set $V0 cluster.data-self-heal off
 EXPECT "off" volume_option $V0 cluster.data-self-heal
 kill_multiple_bricks $V0 $H0 $B0
 echo abc > $M0/f
-EXPECT 1 afr_get_pending_heal_count $V0
+EXPECT 1 get_pending_heal_count $V0
 TEST $CLI volume start $V0 force
 EXPECT_WITHIN 20 "Y" glustershd_up_status
 check_bricks_up $V0
 
 TEST $CLI volume heal $V0
-EXPECT_WITHIN 30 "0" afr_get_pending_heal_count $V0
+EXPECT_WITHIN 30 "0" get_pending_heal_count $V0
 TEST $CLI volume set $V0 cluster.data-self-heal on
 
 #METADATA
@@ -147,13 +147,13 @@ EXPECT "off" volume_option $V0 cluster.metadata-self-heal
 kill_multiple_bricks $V0 $H0 $B0
 
 TEST chmod 777 $M0/f
-EXPECT 1 afr_get_pending_heal_count $V0
+EXPECT 1 get_pending_heal_count $V0
 TEST $CLI volume start $V0 force
 EXPECT_WITHIN 20 "Y" glustershd_up_status
 check_bricks_up $V0
 
 TEST $CLI volume heal $V0
-EXPECT_WITHIN 30 "0" afr_get_pending_heal_count $V0
+EXPECT_WITHIN 30 "0" get_pending_heal_count $V0
 TEST $CLI volume set $V0 cluster.metadata-self-heal on
 
 #ENTRY
@@ -163,13 +163,13 @@ kill_multiple_bricks $V0 $H0 $B0
 TEST touch $M0/d/a
 # 4 if mtime/ctime is modified for d in bricks without a
 # 2 otherwise
-PENDING=$( afr_get_pending_heal_count $V0 )
+PENDING=$( get_pending_heal_count $V0 )
 TEST test $PENDING -eq 2 -o $PENDING -eq 4
 TEST $CLI volume start $V0 force
 EXPECT_WITHIN 20 "Y" glustershd_up_status
 check_bricks_up $V0
 TEST $CLI volume heal $V0
-EXPECT_WITHIN 30 "0" afr_get_pending_heal_count $V0
+EXPECT_WITHIN 30 "0" get_pending_heal_count $V0
 TEST $CLI volume set $V0 cluster.entry-self-heal on
 
 #Negative test cases
diff --git a/tests/basic/afr/sparse-file-self-heal.t b/tests/basic/afr/sparse-file-self-heal.t
index 1bc915e062c..4101e6d1db7 100644
--- a/tests/basic/afr/sparse-file-self-heal.t
+++ b/tests/basic/afr/sparse-file-self-heal.t
@@ -49,7 +49,7 @@ 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
 TEST gluster volume heal $V0 full
-EXPECT_WITHIN $HEAL_TIMEOUT "0" afr_get_pending_heal_count $V0
+EXPECT_WITHIN $HEAL_TIMEOUT "0" get_pending_heal_count $V0
 
 big_md5sum_0=$(md5sum $B0/${V0}0/big | awk '{print $1}')
 small_md5sum_0=$(md5sum $B0/${V0}0/small | awk '{print $1}')
@@ -114,7 +114,7 @@ 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
 TEST gluster volume heal $V0 full
-EXPECT_WITHIN $HEAL_TIMEOUT "0" afr_get_pending_heal_count $V0
+EXPECT_WITHIN $HEAL_TIMEOUT "0" get_pending_heal_count $V0
 
 big_md5sum_0=$(md5sum $B0/${V0}0/big | awk '{print $1}')
 small_md5sum_0=$(md5sum $B0/${V0}0/small | awk '{print $1}')
diff --git a/tests/basic/afr/split-brain-resolution.t b/tests/basic/afr/split-brain-resolution.t
index fa1342e2cd5..84b2cc8db51 100644
--- a/tests/basic/afr/split-brain-resolution.t
+++ b/tests/basic/afr/split-brain-resolution.t
@@ -38,7 +38,7 @@ 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 1
 
-EXPECT 4 afr_get_pending_heal_count $V0
+EXPECT 4 get_pending_heal_count $V0
 
 TEST ! cat $M0/data-split-brain.txt
 TEST ! getfattr -n user.test $M0/metadata-split-brain.txt
@@ -82,6 +82,6 @@ TEST setfattr -n replica.split-brain-heal-finalize -v $V0-client-1 $M0/data-spli
 EXPECT "brick0" get_text_xattr user.test $M0/metadata-split-brain.txt
 EXPECT "brick1_alive" cat $M0/data-split-brain.txt
 
-EXPECT 0 afr_get_pending_heal_count $V0
+EXPECT 0 get_pending_heal_count $V0
 
 cleanup;
diff --git a/tests/basic/ec/ec-background-heals.t b/tests/basic/ec/ec-background-heals.t
new file mode 100644
index 00000000000..e0fa3a1e3b2
--- /dev/null
+++ b/tests/basic/ec/ec-background-heals.t
@@ -0,0 +1,100 @@
+#!/bin/bash
+
+. $(dirname $0)/../../include.rc
+. $(dirname $0)/../../volume.rc
+
+# This test checks background heals option
+
+cleanup
+TEST glusterd
+TEST pidof glusterd
+TEST $CLI volume create $V0 disperse 3 redundancy 1 $H0:$B0/${V0}{0..2}
+TEST $CLI volume heal $V0 disable
+TEST $CLI volume set $V0 performance.stat-prefetch off
+TEST $CLI volume set $V0 performance.write-behind off
+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 start $V0
+
+TEST $GFS --volfile-id=/$V0 --volfile-server=$H0 $M0;
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "3" ec_child_up_count $V0 0
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "0" mount_get_option_value $M0 $V0-disperse-0 background-heals
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "0" mount_get_option_value $M0 $V0-disperse-0 heal-wait-qlength
+TEST touch $M0/a
+TEST kill_brick $V0 $H0 $B0/${V0}2
+echo abc > $M0/a
+EXPECT 2 get_pending_heal_count $V0 #One for each active brick
+$CLI volume start $V0 force
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "3" ec_child_up_count $V0 0
+#Accessing file shouldn't heal the file
+EXPECT "abc" cat $M0/a
+sleep 3
+EXPECT 2 get_pending_heal_count $V0 #One for each active brick
+TEST $CLI volume set $V0 disperse.background-heals 1
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "1" mount_get_option_value $M0 $V0-disperse-0 background-heals
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "128" mount_get_option_value $M0 $V0-disperse-0 heal-wait-qlength
+#Accessing file should heal the file now
+EXPECT "abc" cat $M0/a
+EXPECT_WITHIN $HEAL_TIMEOUT 0 get_pending_heal_count $V0
+
+#Test above test cases with reset instead of setting background-heals to 1
+TEST $CLI volume set $V0 disperse.heal-wait-qlength 1024
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "1" mount_get_option_value $M0 $V0-disperse-0 background-heals
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "1024" mount_get_option_value $M0 $V0-disperse-0 heal-wait-qlength
+TEST $CLI volume set $V0 disperse.background-heals 0
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "0" mount_get_option_value $M0 $V0-disperse-0 background-heals
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "0" mount_get_option_value $M0 $V0-disperse-0 heal-wait-qlength
+TEST $CLI volume set $V0 disperse.heal-wait-qlength 200 #Changing qlength shouldn't affect anything now
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "0" mount_get_option_value $M0 $V0-disperse-0 background-heals
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "0" mount_get_option_value $M0 $V0-disperse-0 heal-wait-qlength
+TEST kill_brick $V0 $H0 $B0/${V0}2
+echo abc > $M0/a
+EXPECT 2 get_pending_heal_count $V0 #One for each active brick
+$CLI volume start $V0 force
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "3" ec_child_up_count $V0 0
+#Accessing file shouldn't heal the file
+EXPECT "abc" cat $M0/a
+sleep 3
+EXPECT 2 get_pending_heal_count $V0 #One for each active brick
+TEST $CLI volume reset $V0 disperse.background-heals
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "8" mount_get_option_value $M0 $V0-disperse-0 background-heals
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "200" mount_get_option_value $M0 $V0-disperse-0 heal-wait-qlength
+#Accessing file should heal the file now
+EXPECT "abc" cat $M0/a
+EXPECT_WITHIN $HEAL_TIMEOUT 0 get_pending_heal_count $V0
+
+#Test that disabling background-heals still drains the queue
+TEST $CLI volume set $V0 disperse.background-heals 1
+TEST touch $M0/{a,b,c,d}
+TEST kill_brick $V0 $H0 $B0/${V0}2
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "1" mount_get_option_value $M0 $V0-disperse-0 background-heals
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "200" mount_get_option_value $M0 $V0-disperse-0 heal-wait-qlength
+TEST truncate -s 1GB $M0/a
+echo abc > $M0/b
+echo abc > $M0/c
+echo abc > $M0/d
+TEST $CLI volume start $V0 force
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "3" ec_child_up_count $V0 0
+TEST chown root:root $M0/{a,b,c,d}
+TEST $CLI volume set $V0 disperse.background-heals 0
+EXPECT_NOT "0" mount_get_option_value $M0 $V0-disperse-0 heal-waiters
+TEST truncate -s 0 $M0/a # This completes the heal fast ;-)
+EXPECT_WITHIN $HEAL_TIMEOUT 0 get_pending_heal_count $V0
+
+#Test that background heals get rejected on meeting background-qlen limit
+TEST $CLI volume set $V0 disperse.background-heals 1
+TEST $CLI volume set $V0 disperse.heal-wait-qlength 0
+TEST kill_brick $V0 $H0 $B0/${V0}2
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "1" mount_get_option_value $M0 $V0-disperse-0 background-heals
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "0" mount_get_option_value $M0 $V0-disperse-0 heal-wait-qlength
+TEST truncate -s 1GB $M0/a
+echo abc > $M0/b
+echo abc > $M0/c
+echo abc > $M0/d
+TEST $CLI volume start $V0 force
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "3" ec_child_up_count $V0 0
+TEST chown root:root $M0/{a,b,c,d}
+EXPECT "0" mount_get_option_value $M0 $V0-disperse-0 heal-waiters
+cleanup
diff --git a/tests/bugs/glusterfs/bug-861015-index.t b/tests/bugs/glusterfs/bug-861015-index.t
index 05f3e8b1ee0..74ffc45bf2e 100644
--- a/tests/bugs/glusterfs/bug-861015-index.t
+++ b/tests/bugs/glusterfs/bug-861015-index.t
@@ -25,7 +25,7 @@ done
 HEAL_FILES=$(($HEAL_FILES+3)) #count brick root distribute-subvol num of times
 
 cd ~
-EXPECT "$HEAL_FILES" afr_get_pending_heal_count $V0
+EXPECT "$HEAL_FILES" get_pending_heal_count $V0
 TEST rm -f $M0/*
 EXPECT_WITHIN $UMOUNT_TIMEOUT "Y" force_umount $M0
 TEST $CLI volume heal $V0 info
diff --git a/tests/bugs/quota/afr-quota-xattr-mdata-heal.t b/tests/bugs/quota/afr-quota-xattr-mdata-heal.t
index beb90a0ab5f..cac06a52960 100644
--- a/tests/bugs/quota/afr-quota-xattr-mdata-heal.t
+++ b/tests/bugs/quota/afr-quota-xattr-mdata-heal.t
@@ -58,7 +58,7 @@ TEST $CLI volume set $V0 cluster.self-heal-daemon on
 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_in_shd $V0 0
-EXPECT_WITHIN $HEAL_TIMEOUT "0" afr_get_pending_heal_count $V0
+EXPECT_WITHIN $HEAL_TIMEOUT "0" get_pending_heal_count $V0
 
 #Check external xattrs match
 EXPECT "bar" echo $(getfattr -d -m. -e text $B0/${V0}0/d | grep trusted.foo)
diff --git a/tests/bugs/replicate/bug-1180545.t b/tests/bugs/replicate/bug-1180545.t
index 748d5defa91..e9531625ee2 100644
--- a/tests/bugs/replicate/bug-1180545.t
+++ b/tests/bugs/replicate/bug-1180545.t
@@ -43,6 +43,6 @@ TEST $CLI volume heal $V0
 EXPECT_WITHIN $HEAL_TIMEOUT '2' count_sh_entries $B0/brick0
 EXPECT_WITHIN $HEAL_TIMEOUT '2' count_sh_entries $B0/brick1
 #Two entries for DIR and two for FILE
-EXPECT_WITHIN $HEAL_TIMEOUT "4" afr_get_pending_heal_count $V0
+EXPECT_WITHIN $HEAL_TIMEOUT "4" get_pending_heal_count $V0
 TEST diff <(ls $B0/brick0/DIR) <(ls $B0/brick1/DIR)
 cleanup
diff --git a/tests/bugs/replicate/bug-1190069-afr-stale-index-entries.t b/tests/bugs/replicate/bug-1190069-afr-stale-index-entries.t
index a476563e31e..2da960f6c7c 100644
--- a/tests/bugs/replicate/bug-1190069-afr-stale-index-entries.t
+++ b/tests/bugs/replicate/bug-1190069-afr-stale-index-entries.t
@@ -50,7 +50,7 @@ TEST setfattr -n trusted.afr.$V0-client-1 -v 0x000000000000000000000000 $B0/${V0
 TEST setfattr -n trusted.afr.$V0-client-0 -v 0x000000000000000000000000 $B0/${V0}1/mdatafile
 
 TEST $CLI volume heal $V0
-EXPECT_WITHIN $HEAL_TIMEOUT "0" afr_get_pending_heal_count $V0
+EXPECT_WITHIN $HEAL_TIMEOUT "0" get_pending_heal_count $V0
 EXPECT_WITHIN $HEAL_TIMEOUT '0' echo $(count_sh_entries $B0/$V0"0")
 EXPECT_WITHIN $HEAL_TIMEOUT '0' echo $(count_sh_entries $B0/$V0"1")
 
diff --git a/tests/bugs/replicate/bug-918437-sh-mtime.t b/tests/bugs/replicate/bug-918437-sh-mtime.t
index 04ac02f6337..6a194b14a9b 100644
--- a/tests/bugs/replicate/bug-918437-sh-mtime.t
+++ b/tests/bugs/replicate/bug-918437-sh-mtime.t
@@ -54,7 +54,7 @@ TEST stat $M0/b
 TEST gluster volume heal $V0 full
 EXPECT_WITHIN $HEAL_TIMEOUT "Y" file_exists $B0/gfs0/brick01/a
 EXPECT_WITHIN $HEAL_TIMEOUT "Y" file_exists $B0/gfs0/brick02/b
-EXPECT_WITHIN $HEAL_TIMEOUT 0 afr_get_pending_heal_count $V0
+EXPECT_WITHIN $HEAL_TIMEOUT 0 get_pending_heal_count $V0
 
 size=`stat -c '%s' /etc/passwd`
 EXPECT $size stat -c '%s' $B0/gfs0/brick01/a
diff --git a/tests/volume.rc b/tests/volume.rc
index 63e991fefb5..e62db1b17fc 100644
--- a/tests/volume.rc
+++ b/tests/volume.rc
@@ -216,7 +216,7 @@ function afr_get_changelog_xattr {
         echo $xval
 }
 
-function afr_get_pending_heal_count {
+function get_pending_heal_count {
         local vol=$1
         gluster volume heal $vol info | grep "Number of entries" | awk '{ sum+=$4} END {print sum}'
 }