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
|
/*
* fork_process.c
* A simple wrapper on top of fork(). This does not handle the
* EXEC_BACKEND case; it might be extended to do so, but it would be
* considerably more complex.
*
* Copyright (c) 1996-2022, PostgreSQL Global Development Group
*
* IDENTIFICATION
* src/backend/postmaster/fork_process.c
*/
#include "postgres.h"
#include <fcntl.h>
#include <time.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <unistd.h>
#include "postmaster/fork_process.h"
#ifndef WIN32
/*
* Wrapper for fork(). Return values are the same as those for fork():
* -1 if the fork failed, 0 in the child process, and the PID of the
* child in the parent process.
*/
pid_t
fork_process(void)
{
pid_t result;
const char *oomfilename;
#ifdef LINUX_PROFILE
struct itimerval prof_itimer;
#endif
/*
* Flush stdio channels just before fork, to avoid double-output problems.
*/
fflush(NULL);
#ifdef LINUX_PROFILE
/*
* Linux's fork() resets the profiling timer in the child process. If we
* want to profile child processes then we need to save and restore the
* timer setting. This is a waste of time if not profiling, however, so
* only do it if commanded by specific -DLINUX_PROFILE switch.
*/
getitimer(ITIMER_PROF, &prof_itimer);
#endif
result = fork();
if (result == 0)
{
/* fork succeeded, in child */
#ifdef LINUX_PROFILE
setitimer(ITIMER_PROF, &prof_itimer, NULL);
#endif
/*
* By default, Linux tends to kill the postmaster in out-of-memory
* situations, because it blames the postmaster for the sum of child
* process sizes *including shared memory*. (This is unbelievably
* stupid, but the kernel hackers seem uninterested in improving it.)
* Therefore it's often a good idea to protect the postmaster by
* setting its OOM score adjustment negative (which has to be done in
* a root-owned startup script). Since the adjustment is inherited by
* child processes, this would ordinarily mean that all the
* postmaster's children are equally protected against OOM kill, which
* is not such a good idea. So we provide this code to allow the
* children to change their OOM score adjustments again. Both the
* file name to write to and the value to write are controlled by
* environment variables, which can be set by the same startup script
* that did the original adjustment.
*/
oomfilename = getenv("PG_OOM_ADJUST_FILE");
if (oomfilename != NULL)
{
/*
* Use open() not stdio, to ensure we control the open flags. Some
* Linux security environments reject anything but O_WRONLY.
*/
int fd = open(oomfilename, O_WRONLY, 0);
/* We ignore all errors */
if (fd >= 0)
{
const char *oomvalue = getenv("PG_OOM_ADJUST_VALUE");
int rc;
if (oomvalue == NULL) /* supply a useful default */
oomvalue = "0";
rc = write(fd, oomvalue, strlen(oomvalue));
(void) rc;
close(fd);
}
}
/* do post-fork initialization for random number generation */
pg_strong_random_init();
}
return result;
}
#endif /* ! WIN32 */
|
