blob: 77d82a4996fd7f9aaa387d8fc7d9985d56a8c640 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
|
#!/bin/bash
#Test the split-brain resolution CLI commands.
. $(dirname $0)/../include.rc
. $(dirname $0)/../volume.rc
cleanup;
TEST glusterd
TEST pidof glusterd
#Create replica 2 volume
TEST $CLI volume create $V0 replica 2 $H0:$B0/${V0}{0,1}
TEST $CLI volume set $V0 performance.write-behind off
TEST $CLI volume set $V0 cluster.self-heal-daemon off
TEST $CLI volume set $V0 cluster.entry-self-heal off
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.heal-timeout 5
TEST $CLI volume start $V0
TEST $GFS --volfile-id=/$V0 --volfile-server=$H0 $M0
TEST touch $M0/file
############ Healing using favorite-child-policy = ctime #################
TEST kill_brick $V0 $H0 $B0/${V0}0
TEST dd if=/dev/urandom of=$M0/file bs=1024 count=1024
TEST $CLI volume start $V0 force
EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" brick_up_status $V0 $H0 $B0/${V0}0
EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 0
TEST kill_brick $V0 $H0 $B0/${V0}1
TEST dd if=/dev/urandom of=$M0/file bs=1024 count=1024
TEST $CLI volume start $V0 force
EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" brick_up_status $V0 $H0 $B0/${V0}1
EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 1
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
TEST $CLI volume heal $V0
#file still in split-brain
cat $M0/file > /dev/null
EXPECT "1" echo $?
# Umount to prevent further FOPS on the file, then find the brick with latest ctime.
EXPECT_WITHIN $UMOUNT_TIMEOUT "Y" force_umount $M0
ctime1=`stat -c "%.Z" $B0/${V0}0/file`
ctime2=`stat -c "%.Z" $B0/${V0}1/file`
if (( $(echo "$ctime1 > $ctime2" | bc -l) )); then
LATEST_CTIME_MD5=$(md5sum $B0/${V0}0/file | cut -d\ -f1)
else
LATEST_CTIME_MD5=$(md5sum $B0/${V0}1/file | cut -d\ -f1)
fi
TEST $CLI volume set $V0 cluster.favorite-child-policy ctime
TEST $CLI volume start $V0 force
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 $HEAL_TIMEOUT "^0$" get_pending_heal_count $V0
B0_MD5=$(md5sum $B0/${V0}0/file | cut -d\ -f1)
B1_MD5=$(md5sum $B0/${V0}1/file | cut -d\ -f1)
TEST [ "$LATEST_CTIME_MD5" == "$B0_MD5" ]
TEST [ "$LATEST_CTIME_MD5" == "$B1_MD5" ]
TEST glusterfs --volfile-id=/$V0 --volfile-server=$H0 $M0 --attribute-timeout=0 --entry-timeout=0
cat $M0/file > /dev/null
EXPECT "0" echo $?
############ Healing using favorite-child-policy = mtime #################
TEST $CLI volume set $V0 cluster.favorite-child-policy none
TEST $CLI volume set $V0 cluster.self-heal-daemon off
TEST kill_brick $V0 $H0 $B0/${V0}1
TEST dd if=/dev/urandom of=$M0/file bs=1024 count=1024
TEST $CLI volume start $V0 force
EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" brick_up_status $V0 $H0 $B0/${V0}1
EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 1
TEST kill_brick $V0 $H0 $B0/${V0}0
TEST dd if=/dev/urandom of=$M0/file bs=1024 count=1024
TEST $CLI volume start $V0 force
EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" brick_up_status $V0 $H0 $B0/${V0}0
EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 0
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
TEST $CLI volume heal $V0
#file still in split-brain
cat $M0/file > /dev/null
EXPECT "1" echo $?
#We know that the second brick has latest mtime.
LATEST_CTIME_MD5=$(md5sum $B0/${V0}1/file | cut -d\ -f1)
TEST $CLI volume set $V0 cluster.favorite-child-policy mtime
TEST $CLI volume start $V0 force
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 $HEAL_TIMEOUT "^0$" get_pending_heal_count $V0
cat $M0/file > /dev/null
EXPECT "0" echo $?
HEALED_MD5=$(md5sum $B0/${V0}0/file | cut -d\ -f1)
TEST [ "$LATEST_CTIME_MD5" == "$HEALED_MD5" ]
############ Healing using favorite-child-policy = size #################
TEST $CLI volume set $V0 cluster.favorite-child-policy none
TEST $CLI volume set $V0 cluster.self-heal-daemon off
TEST kill_brick $V0 $H0 $B0/${V0}1
TEST dd if=/dev/urandom of=$M0/file bs=1024 count=1024
TEST $CLI volume start $V0 force
EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" brick_up_status $V0 $H0 $B0/${V0}1
EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 1
TEST kill_brick $V0 $H0 $B0/${V0}0
TEST dd if=/dev/urandom of=$M0/file bs=1024 count=10240
TEST $CLI volume start $V0 force
EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" brick_up_status $V0 $H0 $B0/${V0}0
EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 0
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
TEST $CLI volume heal $V0
#file still in split-brain
cat $M0/file > /dev/null
EXPECT "1" echo $?
#We know that the second brick has the bigger size file.
BIGGER_FILE_MD5=$(md5sum $B0/${V0}1/file | cut -d\ -f1)
TEST $CLI volume set $V0 cluster.favorite-child-policy size
TEST $CLI volume start $V0 force
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 $HEAL_TIMEOUT "^0$" get_pending_heal_count $V0
cat $M0/file > /dev/null
EXPECT "0" echo $?
HEALED_MD5=$(md5sum $B0/${V0}0/file | cut -d\ -f1)
TEST [ "$BIGGER_FILE_MD5" == "$HEALED_MD5" ]
############ Healing using favorite-child-policy = majority on replica-3 #################
#Convert volume to replica-3
TEST $CLI volume add-brick $V0 replica 3 $H0:$B0/${V0}2
EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" brick_up_status $V0 $H0 $B0/${V0}2
EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 2
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
EXPECT_WITHIN $HEAL_TIMEOUT "^0$" get_pending_heal_count $V0
TEST $CLI volume set $V0 cluster.quorum-type none
TEST $CLI volume set $V0 cluster.favorite-child-policy none
TEST $CLI volume set $V0 cluster.self-heal-daemon off
TEST kill_brick $V0 $H0 $B0/${V0}0
TEST dd if=/dev/urandom of=$M0/file bs=1024 count=1024
TEST $CLI volume start $V0 force
EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" brick_up_status $V0 $H0 $B0/${V0}0
EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" afr_child_up_status $V0 0
TEST kill_brick $V0 $H0 $B0/${V0}1
TEST kill_brick $V0 $H0 $B0/${V0}2
TEST dd if=/dev/urandom of=$M0/file bs=1024 count=10240
TEST $CLI volume start $V0 force
EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" brick_up_status $V0 $H0 $B0/${V0}1
EXPECT_WITHIN $PROCESS_UP_TIMEOUT "1" brick_up_status $V0 $H0 $B0/${V0}2
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 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
TEST $CLI volume heal $V0
#file still in split-brain
cat $M0/file > /dev/null
EXPECT "1" echo $?
#We know that the second and third bricks agree with each other. Pick any one of them.
MAJORITY_MD5=$(md5sum $B0/${V0}1/file | cut -d\ -f1)
TEST $CLI volume set $V0 cluster.favorite-child-policy majority
TEST $CLI volume start $V0 force
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
EXPECT_WITHIN $HEAL_TIMEOUT "^0$" get_pending_heal_count $V0
cat $M0/file > /dev/null
EXPECT "0" echo $?
HEALED_MD5=$(md5sum $B0/${V0}0/file | cut -d\ -f1)
TEST [ "$MAJORITY_MD5" == "$HEALED_MD5" ]
TEST force_umount $M0
cleanup
|