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
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
|
# Copyright (c) 2021, PostgreSQL Global Development Group
# Test remove of temporary files after a crash.
use strict;
use warnings;
use PostgreSQL::Test::Cluster;
use PostgreSQL::Test::Utils;
use Test::More;
use Config;
if ($Config{osname} eq 'MSWin32')
{
plan skip_all => 'tests hang on Windows';
exit;
}
else
{
plan tests => 9;
}
# To avoid hanging while expecting some specific input from a psql
# instance being driven by us, add a timeout high enough that it
# should never trigger even on very slow machines, unless something
# is really wrong.
my $psql_timeout = IPC::Run::timer(60);
my $node = PostgreSQL::Test::Cluster->new('node_crash');
$node->init();
$node->start();
# By default, PostgreSQL::Test::Cluster doesn't restart after crash
# Reduce work_mem to generate temporary file with a few number of rows
$node->safe_psql(
'postgres',
q[ALTER SYSTEM SET remove_temp_files_after_crash = on;
ALTER SYSTEM SET log_connections = 1;
ALTER SYSTEM SET work_mem = '64kB';
ALTER SYSTEM SET restart_after_crash = on;
SELECT pg_reload_conf();]);
# create table, insert rows
$node->safe_psql('postgres', q[CREATE TABLE tab_crash (a integer UNIQUE);]);
# Run psql, keeping session alive, so we have an alive backend to kill.
my ($killme_stdin, $killme_stdout, $killme_stderr) = ('', '', '');
my $killme = IPC::Run::start(
[
'psql', '-X', '-qAt', '-v', 'ON_ERROR_STOP=1', '-f', '-', '-d',
$node->connstr('postgres')
],
'<',
\$killme_stdin,
'>',
\$killme_stdout,
'2>',
\$killme_stderr,
$psql_timeout);
# Get backend pid
$killme_stdin .= q[
SELECT pg_backend_pid();
];
ok(pump_until($killme, \$killme_stdout, qr/[[:digit:]]+[\r\n]$/m),
'acquired pid for SIGKILL');
my $pid = $killme_stdout;
chomp($pid);
$killme_stdout = '';
$killme_stderr = '';
# Open a 2nd session that will block the 1st one, using the UNIQUE constraint.
# This will prevent removal of the temporary file created by the 1st session.
my ($killme_stdin2, $killme_stdout2, $killme_stderr2) = ('', '', '');
my $killme2 = IPC::Run::start(
[
'psql', '-X', '-qAt', '-v', 'ON_ERROR_STOP=1', '-f', '-', '-d',
$node->connstr('postgres')
],
'<',
\$killme_stdin2,
'>',
\$killme_stdout2,
'2>',
\$killme_stderr2,
$psql_timeout);
# Insert one tuple and leave the transaction open
$killme_stdin2 .= q[
BEGIN;
INSERT INTO tab_crash (a) VALUES(1);
SELECT $$insert-tuple-to-lock-next-insert$$;
];
pump_until($killme2, \$killme_stdout2, qr/insert-tuple-to-lock-next-insert/m);
$killme_stdout2 = '';
$killme_stderr2 = '';
# Run the query that generates a temporary file and that will be killed before
# it finishes. Since the query that generates the temporary file does not
# return before the connection is killed, use a SELECT before to trigger
# pump_until.
$killme_stdin .= q[
BEGIN;
SELECT $$in-progress-before-sigkill$$;
INSERT INTO tab_crash (a) SELECT i FROM generate_series(1, 5000) s(i);
];
ok(pump_until($killme, \$killme_stdout, qr/in-progress-before-sigkill/m),
'insert in-progress-before-sigkill');
$killme_stdout = '';
$killme_stderr = '';
# Wait until the batch insert gets stuck on the lock.
$killme_stdin2 .= q[
DO $c$
DECLARE
c INT;
BEGIN
LOOP
SELECT COUNT(*) INTO c FROM pg_locks WHERE pid = ] . $pid
. q[ AND NOT granted;
IF c > 0 THEN
EXIT;
END IF;
END LOOP;
END; $c$;
SELECT $$insert-tuple-lock-waiting$$;
];
pump_until($killme2, \$killme_stdout2, qr/insert-tuple-lock-waiting/m);
$killme_stdout2 = '';
$killme_stderr2 = '';
# Kill with SIGKILL
my $ret = PostgreSQL::Test::Utils::system_log('pg_ctl', 'kill', 'KILL', $pid);
is($ret, 0, 'killed process with KILL');
# Close psql session
$killme->finish;
$killme2->finish;
# Wait till server restarts
$node->poll_query_until('postgres', undef, '');
# Check for temporary files
is( $node->safe_psql(
'postgres', 'SELECT COUNT(1) FROM pg_ls_dir($$base/pgsql_tmp$$)'),
qq(0),
'no temporary files');
#
# Test old behavior (don't remove temporary files after crash)
#
$node->safe_psql(
'postgres',
q[ALTER SYSTEM SET remove_temp_files_after_crash = off;
SELECT pg_reload_conf();]);
# Restart psql session
($killme_stdin, $killme_stdout, $killme_stderr) = ('', '', '');
$killme->run();
# Get backend pid
$killme_stdin .= q[
SELECT pg_backend_pid();
];
ok(pump_until($killme, \$killme_stdout, qr/[[:digit:]]+[\r\n]$/m),
'acquired pid for SIGKILL');
$pid = $killme_stdout;
chomp($pid);
$killme_stdout = '';
$killme_stderr = '';
# Restart the 2nd psql session
($killme_stdin2, $killme_stdout2, $killme_stderr2) = ('', '', '');
$killme2->run();
# Insert one tuple and leave the transaction open
$killme_stdin2 .= q[
BEGIN;
INSERT INTO tab_crash (a) VALUES(1);
SELECT $$insert-tuple-to-lock-next-insert$$;
];
pump_until($killme2, \$killme_stdout2, qr/insert-tuple-to-lock-next-insert/m);
$killme_stdout2 = '';
$killme_stderr2 = '';
# Run the query that generates a temporary file and that will be killed before
# it finishes. Since the query that generates the temporary file does not
# return before the connection is killed, use a SELECT before to trigger
# pump_until.
$killme_stdin .= q[
BEGIN;
SELECT $$in-progress-before-sigkill$$;
INSERT INTO tab_crash (a) SELECT i FROM generate_series(1, 5000) s(i);
];
ok(pump_until($killme, \$killme_stdout, qr/in-progress-before-sigkill/m),
'insert in-progress-before-sigkill');
$killme_stdout = '';
$killme_stderr = '';
# Wait until the batch insert gets stuck on the lock.
$killme_stdin2 .= q[
DO $c$
DECLARE
c INT;
BEGIN
LOOP
SELECT COUNT(*) INTO c FROM pg_locks WHERE pid = ] . $pid
. q[ AND NOT granted;
IF c > 0 THEN
EXIT;
END IF;
END LOOP;
END; $c$;
SELECT $$insert-tuple-lock-waiting$$;
];
pump_until($killme2, \$killme_stdout2, qr/insert-tuple-lock-waiting/m);
$killme_stdout2 = '';
$killme_stderr2 = '';
# Kill with SIGKILL
$ret = PostgreSQL::Test::Utils::system_log('pg_ctl', 'kill', 'KILL', $pid);
is($ret, 0, 'killed process with KILL');
# Close psql session
$killme->finish;
$killme2->finish;
# Wait till server restarts
$node->poll_query_until('postgres', undef, '');
# Check for temporary files -- should be there
is( $node->safe_psql(
'postgres', 'SELECT COUNT(1) FROM pg_ls_dir($$base/pgsql_tmp$$)'),
qq(1),
'one temporary file');
# Restart should remove the temporary files
$node->restart();
# Check the temporary files -- should be gone
is( $node->safe_psql(
'postgres', 'SELECT COUNT(1) FROM pg_ls_dir($$base/pgsql_tmp$$)'),
qq(0),
'temporary file was removed');
$node->stop();
# Pump until string is matched, or timeout occurs
sub pump_until
{
my ($proc, $stream, $untl) = @_;
$proc->pump_nb();
while (1)
{
last if $$stream =~ /$untl/;
if ($psql_timeout->is_expired)
{
diag("aborting wait: program timed out");
diag("stream contents: >>", $$stream, "<<");
diag("pattern searched for: ", $untl);
return 0;
}
if (not $proc->pumpable())
{
diag("aborting wait: program died");
diag("stream contents: >>", $$stream, "<<");
diag("pattern searched for: ", $untl);
return 0;
}
$proc->pump();
}
return 1;
}
|