summaryrefslogtreecommitdiffstats
path: root/tests/00-geo-rep
diff options
context:
space:
mode:
authorMohit Agrawal <moagrawal@redhat.com>2018-11-23 09:39:43 +0530
committerAmar Tumballi <amarts@redhat.com>2018-12-13 04:46:50 +0000
commitfb917bf10b4783d5c669e81a5be1f902ca48cb84 (patch)
tree81a61c54de77f598c1c23648d5e38a3f0fff54aa /tests/00-geo-rep
parent52d3f82db2f032eae1b60ffa2f283109858ce3df (diff)
[geo-rep]: Worker still ACTIVE after killing bricks
Problem: In changelog xlator after destroying listener it call's unlink to delete changelog socket file but socket file reference is not cleaned up from process memory Solution: 1) To cleanup reference completely from process memory serialize transport cleanup for changelog and then unlink socket file 2) Brick xlator will notify GF_EVENT_PARENT_DOWN to next xlator only after cleanup all xprts Test: To test the same run below steps 1) Setup some volume and enable brick mux 2) kill anyone brick with gf_attach 3) check changelog socket for specific to killed brick in lsof, it should cleanup completely fixes: bz#1600145 Change-Id: Iba06cbf77d8a87b34a60fce50f6d8c0d427fa491 Signed-off-by: Mohit Agrawal <moagrawal@redhat.com>
Diffstat (limited to 'tests/00-geo-rep')
-rw-r--r--tests/00-geo-rep/bug-1600145.t109
1 files changed, 109 insertions, 0 deletions
diff --git a/tests/00-geo-rep/bug-1600145.t b/tests/00-geo-rep/bug-1600145.t
new file mode 100644
index 0000000..1d38bf9
--- /dev/null
+++ b/tests/00-geo-rep/bug-1600145.t
@@ -0,0 +1,109 @@
+#!/bin/bash
+
+. $(dirname $0)/../include.rc
+. $(dirname $0)/../volume.rc
+. $(dirname $0)/../geo-rep.rc
+. $(dirname $0)/../env.rc
+
+### Basic Tests with Distribute Replicate volumes
+
+##Cleanup and start glusterd
+cleanup;
+SCRIPT_TIMEOUT=600
+TEST glusterd;
+TEST pidof glusterd
+
+##Variables
+GEOREP_CLI="$CLI volume geo-replication"
+master=$GMV0
+SH0="127.0.0.1"
+slave=${SH0}::${GSV0}
+num_active=2
+num_passive=2
+master_mnt=$M0
+slave_mnt=$M1
+
+############################################################
+#SETUP VOLUMES AND GEO-REPLICATION
+############################################################
+
+##create_and_start_master_volume
+TEST $CLI volume create $GMV0 replica 2 $H0:$B0/${GMV0}{1,2};
+gluster v set all cluster.brick-multiplex on
+TEST $CLI volume start $GMV0
+
+##create_and_start_slave_volume
+TEST $CLI volume create $GSV0 replica 2 $H0:$B0/${GSV0}{1,2};
+TEST $CLI volume start $GSV0
+
+##Create, start and mount meta_volume
+TEST $CLI volume create $META_VOL replica 3 $H0:$B0/${META_VOL}{1,2,3};
+TEST $CLI volume start $META_VOL
+TEST mkdir -p $META_MNT
+TEST glusterfs -s $H0 --volfile-id $META_VOL $META_MNT
+
+############################################################
+#BASIC GEO-REPLICATION TESTS
+############################################################
+
+#Create geo-rep session
+TEST create_georep_session $master $slave
+
+#Config gluster-command-dir
+TEST $GEOREP_CLI $master $slave config gluster-command-dir ${GLUSTER_CMD_DIR}
+
+#Config gluster-command-dir
+TEST $GEOREP_CLI $master $slave config slave-gluster-command-dir ${GLUSTER_CMD_DIR}
+
+#Enable_metavolume
+TEST $GEOREP_CLI $master $slave config use_meta_volume true
+
+#Wait for common secret pem file to be created
+EXPECT_WITHIN $GEO_REP_TIMEOUT 0 check_common_secret_file
+
+#Verify the keys are distributed
+
+EXPECT_WITHIN $GEO_REP_TIMEOUT 0 check_keys_distributed
+
+#Count no. of changelog socket
+brick_pid=`ps -aef | grep glusterfsd | grep -v "shared_storage" | grep -v grep | awk -F " " '{print $2}'`
+n=$(grep -Fc "changelog" /proc/$brick_pid/net/unix)
+
+#Start_georep
+TEST $GEOREP_CLI $master $slave start
+
+EXPECT_WITHIN $GEO_REP_TIMEOUT 1 check_status_num_rows "Active"
+EXPECT_WITHIN $GEO_REP_TIMEOUT 1 check_status_num_rows "Passive"
+
+#Count no. of changelog socket
+brick_pid=`ps -aef | grep glusterfsd | grep -v "shared_storage" | grep -v grep | awk -F " " '{print $2}'`
+c=$(grep -Fc "changelog" /proc/$brick_pid/net/unix)
+let expected=n+2
+TEST [ "$c" -eq "$expected" ]
+
+#Kill the "Active" brick
+brick=$($GEOREP_CLI $master $slave status | grep -F "Active" | awk {'print $3'})
+cat /proc/$brick_pid/net/unix | grep "changelog"
+TEST kill_brick $GMV0 $H0 $brick
+#Expect geo-rep status to be "Faulty"
+EXPECT_WITHIN $GEO_REP_TIMEOUT 1 check_status_num_rows "Faulty"
+EXPECT_WITHIN $GEO_REP_TIMEOUT 1 check_status_num_rows "Active"
+
+#Count no. of changelog socket
+brick_pid=`ps -aef | grep glusterfsd | grep -v "shared_storage" | grep -v grep | awk -F " " '{print $2}'`
+cat /proc/$brick_pid/net/unix | grep "changelog"
+ls -lrth /proc/$brick_pid/fd | grep "socket"
+c=$(grep -Fc "changelog" /proc/$brick_pid/net/unix)
+TEST [ "$c" -eq "$n" ]
+
+#Stop Geo-rep
+TEST $GEOREP_CLI $master $slave stop
+
+#Delete Geo-rep
+TEST $GEOREP_CLI $master $slave delete
+
+#Cleanup authorized keys
+sed -i '/^command=.*SSH_ORIGINAL_COMMAND#.*/d' ~/.ssh/authorized_keys
+sed -i '/^command=.*gsyncd.*/d' ~/.ssh/authorized_keys
+
+cleanup;