]>
Commit | Line | Data |
---|---|---|
1 | .\" Copyright (C) 1994, 1995 by Daniel Quinlan (quinlan@yggdrasil.com) | |
2 | .\" and Copyright (C) 2002-2008 Michael Kerrisk <mtk.manpages@gmail.com> | |
3 | .\" with networking additions from Alan Cox (A.Cox@swansea.ac.uk) | |
4 | .\" and scsi additions from Michael Neuffer (neuffer@mail.uni-mainz.de) | |
5 | .\" and sysctl additions from Andries Brouwer (aeb@cwi.nl) | |
6 | .\" and System V IPC (as well as various other) additions from | |
7 | .\" Michael Kerrisk <mtk.manpages@gmail.com> | |
8 | .\" | |
9 | .\" This is free documentation; you can redistribute it and/or | |
10 | .\" modify it under the terms of the GNU General Public License as | |
11 | .\" published by the Free Software Foundation; either version 2 of | |
12 | .\" the License, or (at your option) any later version. | |
13 | .\" | |
14 | .\" The GNU General Public License's references to "object code" | |
15 | .\" and "executables" are to be interpreted as the output of any | |
16 | .\" document formatting or typesetting system, including | |
17 | .\" intermediate and printed output. | |
18 | .\" | |
19 | .\" This manual is distributed in the hope that it will be useful, | |
20 | .\" but WITHOUT ANY WARRANTY; without even the implied warranty of | |
21 | .\" MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
22 | .\" GNU General Public License for more details. | |
23 | .\" | |
24 | .\" You should have received a copy of the GNU General Public | |
25 | .\" License along with this manual; if not, write to the Free | |
26 | .\" Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111, | |
27 | .\" USA. | |
28 | .\" | |
29 | .\" Modified 1995-05-17 by faith@cs.unc.edu | |
30 | .\" Minor changes by aeb and Marty Leisner (leisner@sdsp.mc.xerox.com). | |
31 | .\" Modified 1996-04-13, 1996-07-22 by aeb@cwi.nl | |
32 | .\" Modified 2001-12-16 by rwhron@earthlink.net | |
33 | .\" Modified 2002-07-13 by jbelton@shaw.ca | |
34 | .\" Modified 2002-07-22, 2003-05-27, 2004-04-06, 2004-05-25 | |
35 | .\" by Michael Kerrisk <mtk.manpages@gmail.com> | |
36 | .\" 2004-11-17, mtk -- updated notes on /proc/loadavg | |
37 | .\" 2004-12-01, mtk, rtsig-max and rtsig-nr went away in 2.6.8 | |
38 | .\" 2004-12-14, mtk, updated 'statm', and fixed error in order of list | |
39 | .\" 2005-05-12, mtk, updated 'stat' | |
40 | .\" 2005-07-13, mtk, added /proc/sys/fs/mqueue/* | |
41 | .\" 2005-09-16, mtk, Added /proc/sys/fs/suid_dumpable | |
42 | .\" 2005-09-19, mtk, added /proc/zoneinfo | |
43 | .\" 2005-03-01, mtk, moved /proc/sys/fs/mqueue/* material to mq_overview.7. | |
44 | .\" 2008-06-05, mtk, Added /proc/[pid]/oom_score, /proc/[pid]/oom_adj, | |
45 | .\" /proc/[pid]/limits, /proc/[pid]/mountinfo, /proc/[pid]/mountstats, | |
46 | .\" and /proc/[pid]/fdinfo/*. | |
47 | .\" 2008-06-19, mtk, Documented /proc/[pid]/status. | |
48 | .\" 2008-07-15, mtk, added /proc/config.gz | |
49 | .\" | |
50 | .\" FIXME 2.6.13 seems to have /proc/vmcore implemented | |
51 | .\" in the source code, but there is no option available under | |
52 | .\" 'make xconfig'; eventually this should be fixed, and then info | |
53 | .\" from the patch-2.6.13 and change log could be used to write an | |
54 | .\" entry in this man page. | |
55 | .\" Needs CONFIG_VMCORE | |
56 | .\" | |
57 | .\" FIXME cross check against Documentation/filesystems/proc.txt | |
58 | .\" to see what information could be imported from that file | |
59 | .\" into this file. | |
60 | .\" | |
61 | .TH PROC 5 2012-08-18 "Linux" "Linux Programmer's Manual" | |
62 | .SH NAME | |
63 | proc \- process information pseudo-file system | |
64 | .SH DESCRIPTION | |
65 | The | |
66 | .I proc | |
67 | file system is a pseudo-file system which is used as an interface to | |
68 | kernel data structures. | |
69 | It is commonly mounted at | |
70 | .IR /proc . | |
71 | Most of it is read-only, but some files allow kernel variables to be | |
72 | changed. | |
73 | .LP | |
74 | The following outline gives a quick tour through the | |
75 | .I /proc | |
76 | hierarchy. | |
77 | .PD 1 | |
78 | .TP | |
79 | .I /proc/[pid] | |
80 | There is a numerical subdirectory for each running process; the | |
81 | subdirectory is named by the process ID. | |
82 | Each such subdirectory contains the following | |
83 | pseudo-files and directories. | |
84 | .\" FIXME Describe /proc/[pid]/attr and | |
85 | .\" /proc/[pid]/task/[tid]/attr | |
86 | .\" This is a directory | |
87 | .\" Added in ??? | |
88 | .\" CONFIG_SECURITY | |
89 | .\" | |
90 | .TP | |
91 | .IR /proc/[pid]/auxv " (since 2.6.0-test7)" | |
92 | This contains the contents of the ELF interpreter information passed | |
93 | to the process at exec time. | |
94 | The format is one \fIunsigned long\fP ID | |
95 | plus one \fIunsigned long\fP value for each entry. | |
96 | The last entry contains two zeros. | |
97 | .TP | |
98 | .IR /proc/[pid]/cgroup " (since Linux 2.6.24)" | |
99 | .\" Info in Documentation/cgroups/cgroups.txt | |
100 | This file describes control groups to which the process/task belongs. | |
101 | For each cgroup hierarchy there is one entry containing | |
102 | colon-separated fields of the form: | |
103 | .nf | |
104 | .ft CW | |
105 | ||
106 | 5:cpuacct,cpu,cpuset:/daemons | |
107 | .ft | |
108 | .fi | |
109 | .IP | |
110 | The colon-separated fields are, from left to right: | |
111 | .RS 11 | |
112 | .IP 1. 3 | |
113 | hierarchy ID number | |
114 | .IP 2. | |
115 | set of subsystems bound to the hierarchy | |
116 | .IP 3. | |
117 | control group in the hierarchy to which the process belongs | |
118 | .RE | |
119 | .IP | |
120 | This file is only present if the | |
121 | .B CONFIG_CGROUPS | |
122 | kernel configuration option is enabled. | |
123 | .\" | |
124 | .\" FIXME Describe /proc/[pid]/clear_refs | |
125 | .\" Added in 2.6.22 | |
126 | .\" "Clears page referenced bits shown in smaps output" | |
127 | .\" write-only | |
128 | .\" CONFIG_PROC_PAGE_MONITOR | |
129 | .TP | |
130 | .I /proc/[pid]/cmdline | |
131 | This holds the complete command line for the process, | |
132 | unless the process is a zombie. | |
133 | .\" In 2.3.26, this also used to be true if the process was swapped out. | |
134 | In the latter case, there is nothing in this file: | |
135 | that is, a read on this file will return 0 characters. | |
136 | The command-line arguments appear in this file as a set of | |
137 | strings separated by null bytes (\(aq\\0\(aq), | |
138 | with a further null byte after the last string. | |
139 | .TP | |
140 | .IR /proc/[pid]/coredump_filter " (since kernel 2.6.23)" | |
141 | See | |
142 | .BR core (5). | |
143 | .TP | |
144 | .IR /proc/[pid]/cpuset " (since kernel 2.6.12)" | |
145 | .\" and/proc/[pid]/task/[tid]/cpuset | |
146 | See | |
147 | .BR cpuset (7). | |
148 | .TP | |
149 | .I /proc/[pid]/cwd | |
150 | This is a symbolic link to the current working directory of the process. | |
151 | To find out the current working directory of process 20, | |
152 | for instance, you can do this: | |
153 | ||
154 | .in +4n | |
155 | .nf | |
156 | .RB "$" " cd /proc/20/cwd; /bin/pwd" | |
157 | .fi | |
158 | .in | |
159 | ||
160 | Note that the | |
161 | .I pwd | |
162 | command is often a shell built-in, and might | |
163 | not work properly. | |
164 | In | |
165 | .BR bash (1), | |
166 | you may use | |
167 | .IR "pwd\ \-P" . | |
168 | ||
169 | .\" The following was still true as at kernel 2.6.13 | |
170 | In a multithreaded process, the contents of this symbolic link | |
171 | are not available if the main thread has already terminated | |
172 | (typically by calling | |
173 | .BR pthread_exit (3)). | |
174 | .TP | |
175 | .I /proc/[pid]/environ | |
176 | This file contains the environment for the process. | |
177 | The entries are separated by null bytes (\(aq\\0\(aq), | |
178 | and there may be a null byte at the end. | |
179 | Thus, to print out the environment of process 1, you would do: | |
180 | .in +4n | |
181 | .nf | |
182 | ||
183 | .ft CW | |
184 | .RB "$" " (cat /proc/1/environ; echo) | tr \(aq\e000\(aq \(aq\en\(aq" | |
185 | .fi | |
186 | .ft P | |
187 | .in | |
188 | .TP | |
189 | .I /proc/[pid]/exe | |
190 | Under Linux 2.2 and later, this file is a symbolic link | |
191 | containing the actual pathname of the executed command. | |
192 | This symbolic link can be dereferenced normally; attempting to open | |
193 | it will open the executable. | |
194 | You can even type | |
195 | .I /proc/[pid]/exe | |
196 | to run another copy of the same executable as is being run by | |
197 | process [pid]. | |
198 | .\" The following was still true as at kernel 2.6.13 | |
199 | In a multithreaded process, the contents of this symbolic link | |
200 | are not available if the main thread has already terminated | |
201 | (typically by calling | |
202 | .BR pthread_exit (3)). | |
203 | ||
204 | Under Linux 2.0 and earlier | |
205 | .I /proc/[pid]/exe | |
206 | is a pointer to the binary which was executed, | |
207 | and appears as a symbolic link. | |
208 | A | |
209 | .BR readlink (2) | |
210 | call on this file under Linux 2.0 returns a string in the format: | |
211 | ||
212 | [device]:inode | |
213 | ||
214 | For example, [0301]:1502 would be inode 1502 on device major 03 (IDE, | |
215 | MFM, etc. drives) minor 01 (first partition on the first drive). | |
216 | ||
217 | .BR find (1) | |
218 | with the | |
219 | .I \-inum | |
220 | option can be used to locate the file. | |
221 | .TP | |
222 | .I /proc/[pid]/fd | |
223 | This is a subdirectory containing one entry for each file which the | |
224 | process has open, named by its file descriptor, and which is a | |
225 | symbolic link to the actual file. | |
226 | Thus, 0 is standard input, 1 standard output, 2 standard error, etc. | |
227 | ||
228 | .\" The following was still true as at kernel 2.6.13 | |
229 | In a multithreaded process, the contents of this directory | |
230 | are not available if the main thread has already terminated | |
231 | (typically by calling | |
232 | .BR pthread_exit (3)). | |
233 | ||
234 | Programs that will take a filename as a command-line argument, | |
235 | but will not take input from standard input if no argument is supplied, | |
236 | or that write to a file named as a command-line argument, | |
237 | but will not send their output to standard output | |
238 | if no argument is supplied, can nevertheless be made to use | |
239 | standard input or standard out using | |
240 | .IR /proc/[pid]/fd . | |
241 | For example, assuming that | |
242 | .I \-i | |
243 | is the flag designating an input file and | |
244 | .I \-o | |
245 | is the flag designating an output file: | |
246 | .in +4n | |
247 | .nf | |
248 | ||
249 | .RB "$" " foobar \-i /proc/self/fd/0 \-o /proc/self/fd/1 ..." | |
250 | .fi | |
251 | .in | |
252 | ||
253 | and you have a working filter. | |
254 | .\" The following is not true in my tests (MTK): | |
255 | .\" Note that this will not work for | |
256 | .\" programs that seek on their files, as the files in the fd directory | |
257 | .\" are not seekable. | |
258 | ||
259 | .I /proc/self/fd/N | |
260 | is approximately the same as | |
261 | .I /dev/fd/N | |
262 | in some UNIX and UNIX-like systems. | |
263 | Most Linux MAKEDEV scripts symbolically link | |
264 | .I /dev/fd | |
265 | to | |
266 | .IR /proc/self/fd , | |
267 | in fact. | |
268 | ||
269 | Most systems provide symbolic links | |
270 | .IR /dev/stdin , | |
271 | .IR /dev/stdout , | |
272 | and | |
273 | .IR /dev/stderr , | |
274 | which respectively link to the files | |
275 | .IR 0 , | |
276 | .IR 1 , | |
277 | and | |
278 | .IR 2 | |
279 | in | |
280 | .IR /proc/self/fd . | |
281 | Thus the example command above could be written as: | |
282 | .in +4n | |
283 | .nf | |
284 | ||
285 | .RB "$" " foobar \-i /dev/stdin \-o /dev/stdout ..." | |
286 | .fi | |
287 | .in | |
288 | .\" FIXME Describe /proc/[pid]/loginuid | |
289 | .\" Added in 2.6.11; updating requires CAP_AUDIT_CONTROL | |
290 | .\" CONFIG_AUDITSYSCALL | |
291 | .TP | |
292 | .IR /proc/[pid]/fdinfo/ " (since kernel 2.6.22)" | |
293 | This is a subdirectory containing one entry for each file which the | |
294 | process has open, named by its file descriptor. | |
295 | The contents of each file can be read to obtain information | |
296 | about the corresponding file descriptor, for example: | |
297 | .in +4n | |
298 | .nf | |
299 | ||
300 | .RB "$" " cat /proc/12015/fdinfo/4" | |
301 | pos: 1000 | |
302 | flags: 01002002 | |
303 | .fi | |
304 | .in | |
305 | ||
306 | The | |
307 | .I pos | |
308 | field is a decimal number showing the current file offset. | |
309 | The | |
310 | .I flags | |
311 | field is an octal number that displays the | |
312 | file access mode and file status flags (see | |
313 | .BR open (2)). | |
314 | ||
315 | The files in this directory are readable only by the owner of the process. | |
316 | .\" FIXME document /proc/[pid]/io | |
317 | .\" .TP | |
318 | .\" .IR /proc/[pid]/io " (since kernel 2.6.20)" | |
319 | .TP | |
320 | .IR /proc/[pid]/limits " (since kernel 2.6.24)" | |
321 | This file displays the soft limit, hard limit, and units of measurement | |
322 | for each of the process's resource limits (see | |
323 | .BR getrlimit (2)). | |
324 | The file is protected to only allow reading by the real UID of the process. | |
325 | .TP | |
326 | .I /proc/[pid]/maps | |
327 | A file containing the currently mapped memory regions and their access | |
328 | permissions. | |
329 | ||
330 | The format is: | |
331 | ||
332 | .nf | |
333 | .ft CW | |
334 | address perms offset dev inode pathname | |
335 | 08048000-08056000 r-xp 00000000 03:0c 64593 /usr/sbin/gpm | |
336 | 08056000-08058000 rw-p 0000d000 03:0c 64593 /usr/sbin/gpm | |
337 | 08058000-0805b000 rwxp 00000000 00:00 0 | |
338 | 40000000-40013000 r-xp 00000000 03:0c 4165 /lib/ld-2.2.4.so | |
339 | 40013000-40015000 rw-p 00012000 03:0c 4165 /lib/ld-2.2.4.so | |
340 | 4001f000-40135000 r-xp 00000000 03:0c 45494 /lib/libc-2.2.4.so | |
341 | 40135000-4013e000 rw-p 00115000 03:0c 45494 /lib/libc-2.2.4.so | |
342 | 4013e000-40142000 rw-p 00000000 00:00 0 | |
343 | bffff000-c0000000 rwxp 00000000 00:00 0 | |
344 | .ft | |
345 | .fi | |
346 | ||
347 | where "address" is the address space in the process that it occupies, | |
348 | "perms" is a set of permissions: | |
349 | ||
350 | .nf | |
351 | .in +5 | |
352 | r = read | |
353 | w = write | |
354 | x = execute | |
355 | s = shared | |
356 | p = private (copy on write) | |
357 | .fi | |
358 | .in | |
359 | ||
360 | "offset" is the offset into the file/whatever, "dev" is the device | |
361 | (major:minor), and "inode" is the inode on that device. | |
362 | 0 indicates that no inode is associated with the memory region, | |
363 | as the case would be with BSS (uninitialized data). | |
364 | ||
365 | Under Linux 2.0 there is no field giving pathname. | |
366 | .TP | |
367 | .I /proc/[pid]/mem | |
368 | This file can be used to access the pages of a process's memory through | |
369 | .BR open (2), | |
370 | .BR read (2), | |
371 | and | |
372 | .BR lseek (2). | |
373 | .TP | |
374 | .IR /proc/[pid]/mountinfo " (since Linux 2.6.26)" | |
375 | .\" This info adapted from Documentation/filesystems/proc.txt | |
376 | This file contains information about mount points. | |
377 | It contains lines of the form: | |
378 | .nf | |
379 | .ft CW | |
380 | ||
381 | 36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue | |
382 | (1)(2)(3) (4) (5) (6) (7) (8) (9) (10) (11) | |
383 | .ft | |
384 | .fi | |
385 | .IP | |
386 | The numbers in parentheses are labels for the descriptions below: | |
387 | .RS 7 | |
388 | .TP 5 | |
389 | (1) | |
390 | mount ID: unique identifier of the mount (may be reused after | |
391 | .BR umount (2)). | |
392 | .TP | |
393 | (2) | |
394 | parent ID: ID of parent mount (or of self for the top of the mount tree). | |
395 | .TP | |
396 | (3) | |
397 | major:minor: value of | |
398 | .I st_dev | |
399 | for files on file system (see | |
400 | .BR stat (2)). | |
401 | .TP | |
402 | (4) | |
403 | root: root of the mount within the file system. | |
404 | .TP | |
405 | (5) | |
406 | mount point: mount point relative to the process's root. | |
407 | .TP | |
408 | (6) | |
409 | mount options: per-mount options. | |
410 | .TP | |
411 | (7) | |
412 | optional fields: zero or more fields of the form "tag[:value]". | |
413 | .TP | |
414 | (8) | |
415 | separator: marks the end of the optional fields. | |
416 | .TP | |
417 | (9) | |
418 | file system type: name of file system in the form "type[.subtype]". | |
419 | .TP | |
420 | (10) | |
421 | mount source: file system-specific information or "none". | |
422 | .TP | |
423 | (11) | |
424 | super options: per-super block options. | |
425 | .RE | |
426 | .IP | |
427 | Parsers should ignore all unrecognized optional fields. | |
428 | Currently the possible optional fields are: | |
429 | .RS 12 | |
430 | .TP 18 | |
431 | shared:X | |
432 | mount is shared in peer group X | |
433 | .TP | |
434 | master:X | |
435 | mount is slave to peer group X | |
436 | .TP | |
437 | propagate_from:X | |
438 | mount is slave and receives propagation from peer group X (*) | |
439 | .TP | |
440 | unbindable | |
441 | mount is unbindable | |
442 | .RE | |
443 | .IP | |
444 | (*) X is the closest dominant peer group under the process's root. | |
445 | If X is the immediate master of the mount, | |
446 | or if there is no dominant peer group under the same root, | |
447 | then only the "master:X" field is present | |
448 | and not the "propagate_from:X" field. | |
449 | ||
450 | For more information on mount propagation see: | |
451 | .I Documentation/filesystems/sharedsubtree.txt | |
452 | in the kernel source tree. | |
453 | .TP | |
454 | .IR /proc/[pid]/mounts " (since Linux 2.4.19)" | |
455 | This is a list of all the file systems currently mounted in the | |
456 | process's mount namespace. | |
457 | The format of this file is documented in | |
458 | .BR fstab (5). | |
459 | Since kernel version 2.6.15, this file is pollable: | |
460 | after opening the file for reading, a change in this file | |
461 | (i.e., a file system mount or unmount) causes | |
462 | .BR select (2) | |
463 | to mark the file descriptor as readable, and | |
464 | .BR poll (2) | |
465 | and | |
466 | .BR epoll_wait (2) | |
467 | mark the file as having an error condition. | |
468 | .TP | |
469 | .IR /proc/[pid]/mountstats " (since Linux 2.6.17)" | |
470 | This file exports information (statistics, configuration information) | |
471 | about the mount points in the process's name space. | |
472 | Lines in this file have the form: | |
473 | .nf | |
474 | ||
475 | device /dev/sda7 mounted on /home with fstype ext3 [statistics] | |
476 | ( 1 ) ( 2 ) (3 ) (4) | |
477 | .fi | |
478 | .IP | |
479 | The fields in each line are: | |
480 | .RS 7 | |
481 | .TP 5 | |
482 | (1) | |
483 | The name of the mounted device | |
484 | (or "nodevice" if there is no corresponding device). | |
485 | .TP | |
486 | (2) | |
487 | The mount point within the file system tree. | |
488 | .TP | |
489 | (3) | |
490 | The file system type. | |
491 | .TP | |
492 | (4) | |
493 | Optional statistics and configuration information. | |
494 | Currently (as at Linux 2.6.26), only NFS file systems export | |
495 | information via this field. | |
496 | .RE | |
497 | .IP | |
498 | This file is only readable by the owner of the process. | |
499 | .TP | |
500 | .IR /proc/[pid]/ns/ " (since Linux 3.0)" | |
501 | .\" See commit 6b4e306aa3dc94a0545eb9279475b1ab6209a31f | |
502 | This is a subdirectory containing one entry for each namespace that | |
503 | supports being manipulated by | |
504 | .BR setns (2). | |
505 | For information about namespaces, see | |
506 | .BR clone (2). | |
507 | .TP | |
508 | .IR /proc/[pid]/ns/ipc " (since Linux 3.0)" | |
509 | Bind mounting this file (see | |
510 | .BR mount (2)) | |
511 | to somewhere else in the filesystem keeps | |
512 | the IPC namespace of the process specified by | |
513 | .I pid | |
514 | alive even if all processes currently in the namespace terminate. | |
515 | ||
516 | Opening this file returns a file handle for the IPC namespace | |
517 | of the process specified by | |
518 | .IR pid . | |
519 | As long as this file descriptor remains open, | |
520 | the IPC namespace will remain alive, | |
521 | even if all processes in the namespace terminate. | |
522 | The file descriptor can be passed to | |
523 | .BR setns (2). | |
524 | .TP | |
525 | .IR /proc/[pid]/ns/net " (since Linux 3.0)" | |
526 | Bind mounting this file (see | |
527 | .BR mount (2)) | |
528 | to somewhere else in the filesystem keeps | |
529 | the network namespace of the process specified by | |
530 | .I pid | |
531 | alive even if all processes in the namespace terminate. | |
532 | ||
533 | Opening this file returns a file handle for the network namespace | |
534 | of the process specified by | |
535 | .IR pid . | |
536 | As long as this file descriptor remains open, | |
537 | the network namespace will remain alive, | |
538 | even if all processes in the namespace terminate. | |
539 | The file descriptor can be passed to | |
540 | .BR setns (2). | |
541 | .TP | |
542 | .IR /proc/[pid]/ns/uts " (since Linux 3.0)" | |
543 | Bind mounting this file (see | |
544 | .BR mount (2)) | |
545 | to somewhere else in the filesystem keeps | |
546 | the UTS namespace of the process specified by | |
547 | .I pid | |
548 | alive even if all processes currently in the namespace terminate. | |
549 | ||
550 | Opening this file returns a file handle for the UTS namespace | |
551 | of the process specified by | |
552 | .IR pid . | |
553 | As long as this file descriptor remains open, | |
554 | the UTS namespace will remain alive, | |
555 | even if all processes in the namespace terminate. | |
556 | The file descriptor can be passed to | |
557 | .BR setns (2). | |
558 | .TP | |
559 | .IR /proc/[pid]/numa_maps " (since Linux 2.6.14)" | |
560 | See | |
561 | .BR numa (7). | |
562 | .TP | |
563 | .IR /proc/[pid]/oom_adj " (since Linux 2.6.11)" | |
564 | This file can be used to adjust the score used to select which process | |
565 | should be killed in an out-of-memory (OOM) situation. | |
566 | The kernel uses this value for a bit-shift operation of the process's | |
567 | .IR oom_score | |
568 | value: | |
569 | valid values are in the range \-16 to +15, | |
570 | plus the special value \-17, | |
571 | which disables OOM-killing altogether for this process. | |
572 | A positive score increases the likelihood of this | |
573 | process being killed by the OOM-killer; | |
574 | a negative score decreases the likelihood. | |
575 | The default value for this file is 0; | |
576 | a new process inherits its parent's | |
577 | .I oom_adj | |
578 | setting. | |
579 | A process must be privileged | |
580 | .RB ( CAP_SYS_RESOURCE ) | |
581 | to update this file. | |
582 | .TP | |
583 | .IR /proc/[pid]/oom_score " (since Linux 2.6.11)" | |
584 | .\" See mm/oom_kill.c::badness() in the 2.6.25 sources | |
585 | This file displays the current score that the kernel gives to | |
586 | this process for the purpose of selecting a process | |
587 | for the OOM-killer. | |
588 | A higher score means that the process is more likely to be | |
589 | selected by the OOM-killer. | |
590 | The basis for this score is the amount of memory used by the process, | |
591 | with increases (+) or decreases (\-) for factors including: | |
592 | .\" See mm/oom_kill.c::badness() in the 2.6.25 sources | |
593 | .RS | |
594 | .IP * 2 | |
595 | whether the process creates a lot of children using | |
596 | .BR fork (2) | |
597 | (+); | |
598 | .IP * | |
599 | whether the process has been running a long time, | |
600 | or has used a lot of CPU time (\-); | |
601 | .IP * | |
602 | whether the process has a low nice value (i.e., > 0) (+); | |
603 | .IP * | |
604 | whether the process is privileged (\-); and | |
605 | .\" More precisely, if it has CAP_SYS_ADMIN or CAP_SYS_RESOURCE | |
606 | .IP * | |
607 | whether the process is making direct hardware access (\-). | |
608 | .\" More precisely, if it has CAP_SYS_RAWIO | |
609 | .RE | |
610 | .IP | |
611 | The | |
612 | .I oom_score | |
613 | also reflects the bit-shift adjustment specified by the | |
614 | .I oom_adj | |
615 | setting for the process. | |
616 | .\" FIXME Describe /proc/[pid]/pagemap | |
617 | .\" Added in 2.6.25 | |
618 | .\" CONFIG_PROC_PAGE_MONITOR | |
619 | .TP | |
620 | .I /proc/[pid]/root | |
621 | UNIX and Linux support the idea of a per-process root of the | |
622 | file system, set by the | |
623 | .BR chroot (2) | |
624 | system call. | |
625 | This file is a symbolic link that points to the process's | |
626 | root directory, and behaves as exe, fd/*, etc. do. | |
627 | ||
628 | .\" The following was still true as at kernel 2.6.13 | |
629 | In a multithreaded process, the contents of this symbolic link | |
630 | are not available if the main thread has already terminated | |
631 | (typically by calling | |
632 | .BR pthread_exit (3)). | |
633 | .\" FIXME Describe /proc/[pid]/seccomp | |
634 | .\" Added in 2.6.12 | |
635 | .\" FIXME Describe /proc/[pid]/sessionid | |
636 | .\" Added in 2.6.25; read-only; only readable by real UID | |
637 | .\" CONFIG_AUDITSYSCALL | |
638 | .\" FIXME Describe /proc/[pid]/sched | |
639 | .\" Added in 2.6.23 | |
640 | .\" CONFIG_SCHED_DEBUG, and additional fields if CONFIG_SCHEDSTATS | |
641 | .\" Displays various scheduling parameters | |
642 | .\" This file can be written, to reset stats | |
643 | .\" FIXME Describe /proc/[pid]/schedstats and | |
644 | .\" /proc/[pid]/task/[tid]/schedstats | |
645 | .\" Added in 2.6.9 | |
646 | .\" CONFIG_SCHEDSTATS | |
647 | .TP | |
648 | .IR /proc/[pid]/smaps " (since Linux 2.6.14)" | |
649 | .\" CONFIG_PROC_PAGE_MONITOR | |
650 | This file shows memory consumption for each of the process's mappings. | |
651 | For each of mappings there is a series of lines such as the following: | |
652 | .in +4n | |
653 | .nf | |
654 | ||
655 | 08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash | |
656 | Size: 464 kB | |
657 | Rss: 424 kB | |
658 | Shared_Clean: 424 kB | |
659 | Shared_Dirty: 0 kB | |
660 | Private_Clean: 0 kB | |
661 | Private_Dirty: 0 kB | |
662 | ||
663 | .fi | |
664 | .in | |
665 | The first of these lines shows the same information as is displayed | |
666 | for the mapping in | |
667 | .IR /proc/[pid]/maps . | |
668 | The remaining lines show the size of the mapping, | |
669 | the amount of the mapping that is currently resident in RAM, | |
670 | the number of clean and dirty shared pages in the mapping, | |
671 | and the number of clean and dirty private pages in the mapping. | |
672 | ||
673 | This file is only present if the | |
674 | .B CONFIG_MMU | |
675 | kernel configuration | |
676 | option is enabled. | |
677 | .TP | |
678 | .I /proc/[pid]/stat | |
679 | Status information about the process. | |
680 | This is used by | |
681 | .BR ps (1). | |
682 | It is defined in | |
683 | .IR /usr/src/linux/fs/proc/array.c "." | |
684 | ||
685 | The fields, in order, with their proper | |
686 | .BR scanf (3) | |
687 | format specifiers, are: | |
688 | .RS | |
689 | .TP 12 | |
690 | \fIpid\fP %d | |
691 | The process ID. | |
692 | .TP | |
693 | \fIcomm\fP %s | |
694 | The filename of the executable, in parentheses. | |
695 | This is visible whether or not the executable is swapped out. | |
696 | .TP | |
697 | \fIstate\fP %c | |
698 | One character from the string "RSDZTW" where R is running, S is | |
699 | sleeping in an interruptible wait, D is waiting in uninterruptible | |
700 | disk sleep, Z is zombie, T is traced or stopped (on a signal), | |
701 | and W is paging. | |
702 | .TP | |
703 | \fIppid\fP %d | |
704 | The PID of the parent. | |
705 | .TP | |
706 | \fIpgrp\fP %d | |
707 | The process group ID of the process. | |
708 | .TP | |
709 | \fIsession\fP %d | |
710 | The session ID of the process. | |
711 | .TP | |
712 | \fItty_nr\fP %d | |
713 | The controlling terminal of the process. | |
714 | (The minor device number is contained in the combination of bits | |
715 | 31 to 20 and 7 to 0; | |
716 | the major device number is in bits 15 to 8.) | |
717 | .TP | |
718 | \fItpgid\fP %d | |
719 | .\" This field and following, up to and including wchan added 0.99.1 | |
720 | The ID of the foreground process group of the controlling | |
721 | terminal of the process. | |
722 | .TP | |
723 | \fIflags\fP %u (%lu before Linux 2.6.22) | |
724 | The kernel flags word of the process. | |
725 | For bit meanings, | |
726 | see the PF_* defines in the kernel source file | |
727 | .IR include/linux/sched.h . | |
728 | Details depend on the kernel version. | |
729 | .TP | |
730 | \fIminflt\fP %lu | |
731 | The number of minor faults the process has made which have not | |
732 | required loading a memory page from disk. | |
733 | .TP | |
734 | .\" field 11 | |
735 | \fIcminflt\fP %lu | |
736 | The number of minor faults that the process's | |
737 | waited-for children have made. | |
738 | .TP | |
739 | \fImajflt\fP %lu | |
740 | The number of major faults the process has made which have | |
741 | required loading a memory page from disk. | |
742 | .TP | |
743 | \fIcmajflt\fP %lu | |
744 | The number of major faults that the process's | |
745 | waited-for children have made. | |
746 | .TP | |
747 | \fIutime\fP %lu | |
748 | Amount of time that this process has been scheduled in user mode, | |
749 | measured in clock ticks (divide by | |
750 | .IR sysconf(_SC_CLK_TCK) ). | |
751 | This includes guest time, \fIguest_time\fP | |
752 | (time spent running a virtual CPU, see below), | |
753 | so that applications that are not aware of the guest time field | |
754 | do not lose that time from their calculations. | |
755 | .TP | |
756 | \fIstime\fP %lu | |
757 | Amount of time that this process has been scheduled in kernel mode, | |
758 | measured in clock ticks (divide by | |
759 | .IR sysconf(_SC_CLK_TCK) ). | |
760 | .TP | |
761 | \fIcutime\fP %ld | |
762 | Amount of time that this process's | |
763 | waited-for children have been scheduled in user mode, | |
764 | measured in clock ticks (divide by | |
765 | .IR sysconf(_SC_CLK_TCK) ). | |
766 | (See also | |
767 | .BR times (2).) | |
768 | This includes guest time, \fIcguest_time\fP | |
769 | (time spent running a virtual CPU, see below). | |
770 | .TP | |
771 | \fIcstime\fP %ld | |
772 | Amount of time that this process's | |
773 | waited-for children have been scheduled in kernel mode, | |
774 | measured in clock ticks (divide by | |
775 | .IR sysconf(_SC_CLK_TCK) ). | |
776 | .TP | |
777 | \fIpriority\fP %ld | |
778 | (Explanation for Linux 2.6) | |
779 | For processes running a real-time scheduling policy | |
780 | .RI ( policy | |
781 | below; see | |
782 | .BR sched_setscheduler (2)), | |
783 | this is the negated scheduling priority, minus one; | |
784 | that is, a number in the range \-2 to \-100, | |
785 | corresponding to real-time priorities 1 to 99. | |
786 | For processes running under a non-real-time scheduling policy, | |
787 | this is the raw nice value | |
788 | .RB ( setpriority (2)) | |
789 | as represented in the kernel. | |
790 | The kernel stores nice values as numbers | |
791 | in the range 0 (high) to 39 (low), | |
792 | corresponding to the user-visible nice range of \-20 to 19. | |
793 | ||
794 | Before Linux 2.6, this was a scaled value based on | |
795 | the scheduler weighting given to this process. | |
796 | .\" And back in kernel 1.2 days things were different again. | |
797 | .TP | |
798 | \fInice\fP %ld | |
799 | The nice value (see | |
800 | .BR setpriority (2)), | |
801 | a value in the range 19 (low priority) to \-20 (high priority). | |
802 | .\" Back in kernel 1.2 days things were different. | |
803 | .TP | |
804 | .\" .TP | |
805 | .\" \fIcounter\fP %ld | |
806 | .\" The current maximum size in jiffies of the process's next timeslice, | |
807 | .\" or what is currently left of its current timeslice, if it is the | |
808 | .\" currently running process. | |
809 | .\" .TP | |
810 | .\" \fItimeout\fP %u | |
811 | .\" The time in jiffies of the process's next timeout. | |
812 | .\" timeout was removed sometime around 2.1/2.2 | |
813 | \fInum_threads\fP %ld | |
814 | Number of threads in this process (since Linux 2.6). | |
815 | Before kernel 2.6, this field was hard coded to 0 as a placeholder | |
816 | for an earlier removed field. | |
817 | .TP | |
818 | .\" field 21 | |
819 | \fIitrealvalue\fP %ld | |
820 | The time in jiffies before the next | |
821 | .B SIGALRM | |
822 | is sent to the process due to an interval timer. | |
823 | Since kernel 2.6.17, this field is no longer maintained, | |
824 | and is hard coded as 0. | |
825 | .TP | |
826 | \fIstarttime\fP %llu (was %lu before Linux 2.6) | |
827 | The time the process started after system boot. | |
828 | In kernels before Linux 2.6, this value was expressed in jiffies. | |
829 | Since Linux 2.6, the value is expressed in clock ticks (divide by | |
830 | .IR sysconf(_SC_CLK_TCK) ). | |
831 | .TP | |
832 | \fIvsize\fP %lu | |
833 | Virtual memory size in bytes. | |
834 | .TP | |
835 | \fIrss\fP %ld | |
836 | Resident Set Size: number of pages the process has in real memory. | |
837 | This is just the pages which | |
838 | count toward text, data, or stack space. | |
839 | This does not include pages | |
840 | which have not been demand-loaded in, or which are swapped out. | |
841 | .TP | |
842 | \fIrsslim\fP %lu | |
843 | Current soft limit in bytes on the rss of the process; | |
844 | see the description of | |
845 | .B RLIMIT_RSS | |
846 | in | |
847 | .BR getrlimit (2). | |
848 | .TP | |
849 | \fIstartcode\fP %lu | |
850 | The address above which program text can run. | |
851 | .TP | |
852 | \fIendcode\fP %lu | |
853 | The address below which program text can run. | |
854 | .TP | |
855 | \fIstartstack\fP %lu | |
856 | The address of the start (i.e., bottom) of the stack. | |
857 | .TP | |
858 | \fIkstkesp\fP %lu | |
859 | The current value of ESP (stack pointer), as found in the | |
860 | kernel stack page for the process. | |
861 | .TP | |
862 | \fIkstkeip\fP %lu | |
863 | The current EIP (instruction pointer). | |
864 | .TP | |
865 | .\" field 31 | |
866 | \fIsignal\fP %lu | |
867 | The bitmap of pending signals, displayed as a decimal number. | |
868 | Obsolete, because it does not provide information on real-time signals; use | |
869 | .I /proc/[pid]/status | |
870 | instead. | |
871 | .TP | |
872 | \fIblocked\fP %lu | |
873 | The bitmap of blocked signals, displayed as a decimal number. | |
874 | Obsolete, because it does not provide information on real-time signals; use | |
875 | .I /proc/[pid]/status | |
876 | instead. | |
877 | .TP | |
878 | \fIsigignore\fP %lu | |
879 | The bitmap of ignored signals, displayed as a decimal number. | |
880 | Obsolete, because it does not provide information on real-time signals; use | |
881 | .I /proc/[pid]/status | |
882 | instead. | |
883 | .TP | |
884 | \fIsigcatch\fP %lu | |
885 | The bitmap of caught signals, displayed as a decimal number. | |
886 | Obsolete, because it does not provide information on real-time signals; use | |
887 | .I /proc/[pid]/status | |
888 | instead. | |
889 | .TP | |
890 | \fIwchan\fP %lu | |
891 | This is the "channel" in which the process is waiting. | |
892 | It is the | |
893 | address of a system call, and can be looked up in a namelist if you | |
894 | need a textual name. | |
895 | (If you have an up-to-date | |
896 | .IR /etc/psdatabase , | |
897 | then | |
898 | try \fIps \-l\fP to see the WCHAN field in action.) | |
899 | .TP | |
900 | \fInswap\fP %lu | |
901 | .\" nswap was added in 2.0 | |
902 | Number of pages swapped (not maintained). | |
903 | .TP | |
904 | \fIcnswap\fP %lu | |
905 | .\" cnswap was added in 2.0 | |
906 | Cumulative \fInswap\fP for child processes (not maintained). | |
907 | .TP | |
908 | \fIexit_signal\fP %d (since Linux 2.1.22) | |
909 | Signal to be sent to parent when we die. | |
910 | .TP | |
911 | \fIprocessor\fP %d (since Linux 2.2.8) | |
912 | CPU number last executed on. | |
913 | .TP | |
914 | \fIrt_priority\fP %u (since Linux 2.5.19; was %lu before Linux 2.6.22) | |
915 | Real-time scheduling priority, a number in the range 1 to 99 for | |
916 | processes scheduled under a real-time policy, | |
917 | or 0, for non-real-time processes (see | |
918 | .BR sched_setscheduler (2)). | |
919 | .TP | |
920 | .\" field 41 | |
921 | \fIpolicy\fP %u (since Linux 2.5.19; was %lu before Linux 2.6.22) | |
922 | Scheduling policy (see | |
923 | .BR sched_setscheduler (2)). | |
924 | Decode using the SCHED_* constants in | |
925 | .IR linux/sched.h . | |
926 | .TP | |
927 | \fIdelayacct_blkio_ticks\fP %llu (since Linux 2.6.18) | |
928 | Aggregated block I/O delays, measured in clock ticks (centiseconds). | |
929 | .TP | |
930 | \fIguest_time\fP %lu (since Linux 2.6.24) | |
931 | Guest time of the process (time spent running a virtual CPU | |
932 | for a guest operating system), measured in clock ticks (divide by | |
933 | .IR sysconf(_SC_CLK_TCK) ). | |
934 | .TP | |
935 | \fIcguest_time\fP %ld (since Linux 2.6.24) | |
936 | Guest time of the process's children, measured in clock ticks (divide by | |
937 | .IR sysconf(_SC_CLK_TCK) ). | |
938 | .RE | |
939 | .TP | |
940 | .I /proc/[pid]/statm | |
941 | Provides information about memory usage, measured in pages. | |
942 | The columns are: | |
943 | .in +4n | |
944 | .nf | |
945 | ||
946 | size total program size | |
947 | (same as VmSize in \fI/proc/[pid]/status\fP) | |
948 | resident resident set size | |
949 | (same as VmRSS in \fI/proc/[pid]/status\fP) | |
950 | share shared pages (from shared mappings) | |
951 | text text (code) | |
952 | .\" (not including libs; broken, includes data segment) | |
953 | lib library (unused in Linux 2.6) | |
954 | data data + stack | |
955 | .\" (including libs; broken, includes library text) | |
956 | dt dirty pages (unused in Linux 2.6) | |
957 | .fi | |
958 | .in | |
959 | .TP | |
960 | .I /proc/[pid]/status | |
961 | Provides much of the information in | |
962 | .I /proc/[pid]/stat | |
963 | and | |
964 | .I /proc/[pid]/statm | |
965 | in a format that's easier for humans to parse. | |
966 | Here's an example: | |
967 | .in +4n | |
968 | .nf | |
969 | ||
970 | .RB "$" " cat /proc/$$/status" | |
971 | Name: bash | |
972 | State: S (sleeping) | |
973 | Tgid: 3515 | |
974 | Pid: 3515 | |
975 | PPid: 3452 | |
976 | TracerPid: 0 | |
977 | Uid: 1000 1000 1000 1000 | |
978 | Gid: 100 100 100 100 | |
979 | FDSize: 256 | |
980 | Groups: 16 33 100 | |
981 | VmPeak: 9136 kB | |
982 | VmSize: 7896 kB | |
983 | VmLck: 0 kB | |
984 | VmHWM: 7572 kB | |
985 | VmRSS: 6316 kB | |
986 | VmData: 5224 kB | |
987 | VmStk: 88 kB | |
988 | VmExe: 572 kB | |
989 | VmLib: 1708 kB | |
990 | VmPTE: 20 kB | |
991 | Threads: 1 | |
992 | SigQ: 0/3067 | |
993 | SigPnd: 0000000000000000 | |
994 | ShdPnd: 0000000000000000 | |
995 | SigBlk: 0000000000010000 | |
996 | SigIgn: 0000000000384004 | |
997 | SigCgt: 000000004b813efb | |
998 | CapInh: 0000000000000000 | |
999 | CapPrm: 0000000000000000 | |
1000 | CapEff: 0000000000000000 | |
1001 | CapBnd: ffffffffffffffff | |
1002 | Cpus_allowed: 00000001 | |
1003 | Cpus_allowed_list: 0 | |
1004 | Mems_allowed: 1 | |
1005 | Mems_allowed_list: 0 | |
1006 | voluntary_ctxt_switches: 150 | |
1007 | nonvoluntary_ctxt_switches: 545 | |
1008 | .fi | |
1009 | .in | |
1010 | .IP | |
1011 | The fields are as follows: | |
1012 | .RS | |
1013 | .IP * 2 | |
1014 | .IR Name : | |
1015 | Command run by this process. | |
1016 | .IP * | |
1017 | .IR State : | |
1018 | Current state of the process. | |
1019 | One of | |
1020 | "R (running)", | |
1021 | "S (sleeping)", | |
1022 | "D (disk sleep)", | |
1023 | "T (stopped)", | |
1024 | "T (tracing stop)", | |
1025 | "Z (zombie)", | |
1026 | or | |
1027 | "X (dead)". | |
1028 | .IP * | |
1029 | .IR Tgid : | |
1030 | Thread group ID (i.e., Process ID). | |
1031 | .IP * | |
1032 | .IR Pid : | |
1033 | Thread ID (see | |
1034 | .BR gettid (2)). | |
1035 | .IP * | |
1036 | .IR PPid : | |
1037 | PID of parent process. | |
1038 | .IP * | |
1039 | .IR TracerPid : | |
1040 | PID of process tracing this process (0 if not being traced). | |
1041 | .IP * | |
1042 | .IR Uid ", " Gid : | |
1043 | Real, effective, saved set, and file system UIDs (GIDs). | |
1044 | .IP * | |
1045 | .IR FDSize : | |
1046 | Number of file descriptor slots currently allocated. | |
1047 | .IP * | |
1048 | .IR Groups : | |
1049 | Supplementary group list. | |
1050 | .IP * | |
1051 | .IR VmPeak : | |
1052 | Peak virtual memory size. | |
1053 | .IP * | |
1054 | .IR VmSize : | |
1055 | Virtual memory size. | |
1056 | .IP * | |
1057 | .IR VmLck : | |
1058 | Locked memory size (see | |
1059 | .BR mlock (3)). | |
1060 | .IP * | |
1061 | .IR VmHWM : | |
1062 | Peak resident set size ("high water mark"). | |
1063 | .IP * | |
1064 | .IR VmRSS : | |
1065 | Resident set size. | |
1066 | .IP * | |
1067 | .IR VmData ", " VmStk ", " VmExe : | |
1068 | Size of data, stack, and text segments. | |
1069 | .IP * | |
1070 | .IR VmLib : | |
1071 | Shared library code size. | |
1072 | .IP * | |
1073 | .IR VmPTE : | |
1074 | Page table entries size (since Linux 2.6.10). | |
1075 | .IP * | |
1076 | .IR Threads : | |
1077 | Number of threads in process containing this thread. | |
1078 | .IP * | |
1079 | .IR SigQ : | |
1080 | This field contains two slash-separated numbers that relate to | |
1081 | queued signals for the real user ID of this process. | |
1082 | The first of these is the number of currently queued | |
1083 | signals for this real user ID, and the second is the | |
1084 | resource limit on the number of queued signals for this process | |
1085 | (see the description of | |
1086 | .BR RLIMIT_SIGPENDING | |
1087 | in | |
1088 | .BR getrlimit (2)). | |
1089 | .IP * | |
1090 | .IR SigPnd ", " ShdPnd : | |
1091 | Number of signals pending for thread and for process as a whole (see | |
1092 | .BR pthreads (7) | |
1093 | and | |
1094 | .BR signal (7)). | |
1095 | .IP * | |
1096 | .IR SigBlk ", " SigIgn ", " SigCgt : | |
1097 | Masks indicating signals being blocked, ignored, and caught (see | |
1098 | .BR signal (7)). | |
1099 | .IP * | |
1100 | .IR CapInh ", " CapPrm ", " CapEff : | |
1101 | Masks of capabilities enabled in inheritable, permitted, and effective sets | |
1102 | (see | |
1103 | .BR capabilities (7)). | |
1104 | .IP * | |
1105 | .IR CapBnd : | |
1106 | Capability Bounding set | |
1107 | (since kernel 2.6.26, see | |
1108 | .BR capabilities (7)). | |
1109 | .IP * | |
1110 | .IR Cpus_allowed : | |
1111 | Mask of CPUs on which this process may run | |
1112 | (since Linux 2.6.24, see | |
1113 | .BR cpuset (7)). | |
1114 | .IP * | |
1115 | .IR Cpus_allowed_list : | |
1116 | Same as previous, but in "list format" | |
1117 | (since Linux 2.6.26, see | |
1118 | .BR cpuset (7)). | |
1119 | .IP * | |
1120 | .IR Mems_allowed : | |
1121 | Mask of memory nodes allowed to this process | |
1122 | (since Linux 2.6.24, see | |
1123 | .BR cpuset (7)). | |
1124 | .IP * | |
1125 | .IR Mems_allowed_list : | |
1126 | Same as previous, but in "list format" | |
1127 | (since Linux 2.6.26, see | |
1128 | .BR cpuset (7)). | |
1129 | .IP * | |
1130 | .IR voluntary_context_switches ", " nonvoluntary_context_switches : | |
1131 | Number of voluntary and involuntary context switches (since Linux 2.6.23). | |
1132 | .RE | |
1133 | .TP | |
1134 | .IR /proc/[pid]/task " (since Linux 2.6.0-test6)" | |
1135 | This is a directory that contains one subdirectory | |
1136 | for each thread in the process. | |
1137 | The name of each subdirectory is the numerical thread ID | |
1138 | .RI ( [tid] ) | |
1139 | of the thread (see | |
1140 | .BR gettid (2)). | |
1141 | Within each of these subdirectories, there is a set of | |
1142 | files with the same names and contents as under the | |
1143 | .I /proc/[pid] | |
1144 | directories. | |
1145 | For attributes that are shared by all threads, the contents for | |
1146 | each of the files under the | |
1147 | .I task/[tid] | |
1148 | subdirectories will be the same as in the corresponding | |
1149 | file in the parent | |
1150 | .I /proc/[pid] | |
1151 | directory | |
1152 | (e.g., in a multithreaded process, all of the | |
1153 | .I task/[tid]/cwd | |
1154 | files will have the same value as the | |
1155 | .I /proc/[pid]/cwd | |
1156 | file in the parent directory, since all of the threads in a process | |
1157 | share a working directory). | |
1158 | For attributes that are distinct for each thread, | |
1159 | the corresponding files under | |
1160 | .I task/[tid] | |
1161 | may have different values (e.g., various fields in each of the | |
1162 | .I task/[tid]/status | |
1163 | files may be different for each thread). | |
1164 | ||
1165 | .\" The following was still true as at kernel 2.6.13 | |
1166 | In a multithreaded process, the contents of the | |
1167 | .I /proc/[pid]/task | |
1168 | directory are not available if the main thread has already terminated | |
1169 | (typically by calling | |
1170 | .BR pthread_exit (3)). | |
1171 | .TP | |
1172 | .I /proc/apm | |
1173 | Advanced power management version and battery information when | |
1174 | .B CONFIG_APM | |
1175 | is defined at kernel compilation time. | |
1176 | .TP | |
1177 | .I /proc/bus | |
1178 | Contains subdirectories for installed busses. | |
1179 | .TP | |
1180 | .I /proc/bus/pccard | |
1181 | Subdirectory for PCMCIA devices when | |
1182 | .B CONFIG_PCMCIA | |
1183 | is set at kernel compilation time. | |
1184 | .TP | |
1185 | .I /proc/bus/pccard/drivers | |
1186 | .TP | |
1187 | .I /proc/bus/pci | |
1188 | Contains various bus subdirectories and pseudo-files containing | |
1189 | information about PCI busses, installed devices, and device | |
1190 | drivers. | |
1191 | Some of these files are not ASCII. | |
1192 | .TP | |
1193 | .I /proc/bus/pci/devices | |
1194 | Information about PCI devices. | |
1195 | They may be accessed through | |
1196 | .BR lspci (8) | |
1197 | and | |
1198 | .BR setpci (8). | |
1199 | .TP | |
1200 | .I /proc/cmdline | |
1201 | Arguments passed to the Linux kernel at boot time. | |
1202 | Often done via a boot manager such as | |
1203 | .BR lilo (8) | |
1204 | or | |
1205 | .BR grub (8). | |
1206 | .TP | |
1207 | .IR /proc/config.gz " (since Linux 2.6)" | |
1208 | This file exposes the configuration options that were used | |
1209 | to build the currently running kernel, | |
1210 | in the same format as they would be shown in the | |
1211 | .I .config | |
1212 | file that resulted when configuring the kernel (using | |
1213 | .IR "make xconfig" , | |
1214 | .IR "make config" , | |
1215 | or similar). | |
1216 | The file contents are compressed; view or search them using | |
1217 | .BR zcat (1), | |
1218 | .BR zgrep (1), | |
1219 | etc. | |
1220 | As long as no changes have been made to the following file, | |
1221 | the contents of | |
1222 | .I /proc/config.gz | |
1223 | are the same as those provided by : | |
1224 | .in +4n | |
1225 | .nf | |
1226 | ||
1227 | cat /lib/modules/$(uname \-r)/build/.config | |
1228 | .fi | |
1229 | .in | |
1230 | .IP | |
1231 | .I /proc/config.gz | |
1232 | is only provided if the kernel is configured with | |
1233 | .BR CONFIG_IKCONFIG_PROC . | |
1234 | .TP | |
1235 | .I /proc/cpuinfo | |
1236 | This is a collection of CPU and system architecture dependent items, | |
1237 | for each supported architecture a different list. | |
1238 | Two common entries are \fIprocessor\fP which gives CPU number and | |
1239 | \fIbogomips\fP; a system constant that is calculated | |
1240 | during kernel initialization. | |
1241 | SMP machines have information for | |
1242 | each CPU. | |
1243 | .TP | |
1244 | .I /proc/devices | |
1245 | Text listing of major numbers and device groups. | |
1246 | This can be used by MAKEDEV scripts for consistency with the kernel. | |
1247 | .TP | |
1248 | .IR /proc/diskstats " (since Linux 2.5.69)" | |
1249 | This file contains disk I/O statistics for each disk device. | |
1250 | See the kernel source file | |
1251 | .I Documentation/iostats.txt | |
1252 | for further information. | |
1253 | .TP | |
1254 | .I /proc/dma | |
1255 | This is a list of the registered \fIISA\fP DMA (direct memory access) | |
1256 | channels in use. | |
1257 | .TP | |
1258 | .I /proc/driver | |
1259 | Empty subdirectory. | |
1260 | .TP | |
1261 | .I /proc/execdomains | |
1262 | List of the execution domains (ABI personalities). | |
1263 | .TP | |
1264 | .I /proc/fb | |
1265 | Frame buffer information when | |
1266 | .B CONFIG_FB | |
1267 | is defined during kernel compilation. | |
1268 | .TP | |
1269 | .I /proc/filesystems | |
1270 | A text listing of the file systems which are supported by the kernel, | |
1271 | namely file systems which were compiled into the kernel or whose kernel | |
1272 | modules are currently loaded. | |
1273 | (See also | |
1274 | .BR filesystems (5).) | |
1275 | If a file system is marked with "nodev", | |
1276 | this means that it does not require a block device to be mounted | |
1277 | (e.g., virtual file system, network file system). | |
1278 | ||
1279 | Incidentally, this file may be used by | |
1280 | .BR mount (8) | |
1281 | when no file system is specified and it didn't manage to determine the | |
1282 | file system type. | |
1283 | Then file systems contained in this file are tried | |
1284 | (excepted those that are marked with "nodev"). | |
1285 | .TP | |
1286 | .I /proc/fs | |
1287 | Empty subdirectory. | |
1288 | .TP | |
1289 | .I /proc/ide | |
1290 | This directory | |
1291 | exists on systems with the IDE bus. | |
1292 | There are directories for each IDE channel and attached device. | |
1293 | Files include: | |
1294 | ||
1295 | .in +4n | |
1296 | .nf | |
1297 | cache buffer size in KB | |
1298 | capacity number of sectors | |
1299 | driver driver version | |
1300 | geometry physical and logical geometry | |
1301 | identify in hexadecimal | |
1302 | media media type | |
1303 | model manufacturer's model number | |
1304 | settings drive settings | |
1305 | smart_thresholds in hexadecimal | |
1306 | smart_values in hexadecimal | |
1307 | .fi | |
1308 | .in | |
1309 | ||
1310 | The | |
1311 | .BR hdparm (8) | |
1312 | utility provides access to this information in a friendly format. | |
1313 | .TP | |
1314 | .I /proc/interrupts | |
1315 | This is used to record the number of interrupts per CPU per IO device. | |
1316 | Since Linux 2.6.24, | |
1317 | for the i386 and x86_64 architectures, at least, this also includes | |
1318 | interrupts internal to the system (that is, not associated with a device | |
1319 | as such), such as NMI (nonmaskable interrupt), LOC (local timer interrupt), | |
1320 | and for SMP systems, TLB (TLB flush interrupt), RES (rescheduling | |
1321 | interrupt), CAL (remote function call interrupt), and possibly others. | |
1322 | Very easy to read formatting, done in ASCII. | |
1323 | .TP | |
1324 | .I /proc/iomem | |
1325 | I/O memory map in Linux 2.4. | |
1326 | .TP | |
1327 | .I /proc/ioports | |
1328 | This is a list of currently registered Input-Output port regions that | |
1329 | are in use. | |
1330 | .TP | |
1331 | .IR /proc/kallsyms " (since Linux 2.5.71)" | |
1332 | This holds the kernel exported symbol definitions used by the | |
1333 | .BR modules (X) | |
1334 | tools to dynamically link and bind loadable modules. | |
1335 | In Linux 2.5.47 and earlier, a similar file with slightly different syntax | |
1336 | was named | |
1337 | .IR ksyms . | |
1338 | .TP | |
1339 | .I /proc/kcore | |
1340 | This file represents the physical memory of the system and is stored | |
1341 | in the ELF core file format. | |
1342 | With this pseudo-file, and an unstripped | |
1343 | kernel | |
1344 | .RI ( /usr/src/linux/vmlinux ) | |
1345 | binary, GDB can be used to | |
1346 | examine the current state of any kernel data structures. | |
1347 | ||
1348 | The total length of the file is the size of physical memory (RAM) plus | |
1349 | 4KB. | |
1350 | .TP | |
1351 | .I /proc/kmsg | |
1352 | This file can be used instead of the | |
1353 | .BR syslog (2) | |
1354 | system call to read kernel messages. | |
1355 | A process must have superuser | |
1356 | privileges to read this file, and only one process should read this | |
1357 | file. | |
1358 | This file should not be read if a syslog process is running | |
1359 | which uses the | |
1360 | .BR syslog (2) | |
1361 | system call facility to log kernel messages. | |
1362 | ||
1363 | Information in this file is retrieved with the | |
1364 | .BR dmesg (1) | |
1365 | program. | |
1366 | .TP | |
1367 | .IR /proc/ksyms " (Linux 1.1.23-2.5.47)" | |
1368 | See | |
1369 | .IR /proc/kallsyms . | |
1370 | .TP | |
1371 | .I /proc/loadavg | |
1372 | The first three fields in this file are load average figures | |
1373 | giving the number of jobs in the run queue (state R) | |
1374 | or waiting for disk I/O (state D) averaged over 1, 5, and 15 minutes. | |
1375 | They are the same as the load average numbers given by | |
1376 | .BR uptime (1) | |
1377 | and other programs. | |
1378 | The fourth field consists of two numbers separated by a slash (/). | |
1379 | The first of these is the number of currently runnable kernel | |
1380 | scheduling entities (processes, threads). | |
1381 | The value after the slash is the number of kernel scheduling entities | |
1382 | that currently exist on the system. | |
1383 | The fifth field is the PID of the process that was most | |
1384 | recently created on the system. | |
1385 | .TP | |
1386 | .I /proc/locks | |
1387 | This file shows current file locks | |
1388 | .RB ( flock "(2) and " fcntl (2)) | |
1389 | and leases | |
1390 | .RB ( fcntl (2)). | |
1391 | .TP | |
1392 | .IR /proc/malloc " (only up to and including Linux 2.2)" | |
1393 | .\" It looks like this only ever did something back in 1.0 days | |
1394 | This file is only present if | |
1395 | .B CONFIG_DEBUG_MALLOC | |
1396 | was defined during compilation. | |
1397 | .TP | |
1398 | .I /proc/meminfo | |
1399 | This file reports statistics about memory usage on the system. | |
1400 | It is used by | |
1401 | .BR free (1) | |
1402 | to report the amount of free and used memory (both physical and swap) | |
1403 | on the system as well as the shared memory and buffers used by the | |
1404 | kernel. | |
1405 | .TP | |
1406 | .I /proc/modules | |
1407 | A text list of the modules that have been loaded by the system. | |
1408 | See also | |
1409 | .BR lsmod (8). | |
1410 | .TP | |
1411 | .I /proc/mounts | |
1412 | Before kernel 2.4.19, this file was a list | |
1413 | of all the file systems currently mounted on the system. | |
1414 | With the introduction of per-process mount namespaces in | |
1415 | Linux 2.4.19, this file became a link to | |
1416 | .IR /proc/self/mounts , | |
1417 | which lists the mount points of the process's own mount namespace. | |
1418 | The format of this file is documented in | |
1419 | .BR fstab (5). | |
1420 | .TP | |
1421 | .I /proc/mtrr | |
1422 | Memory Type Range Registers. | |
1423 | See the kernel source file | |
1424 | .I Documentation/mtrr.txt | |
1425 | for details. | |
1426 | .TP | |
1427 | .I /proc/net | |
1428 | various net pseudo-files, all of which give the status of some part of | |
1429 | the networking layer. | |
1430 | These files contain ASCII structures and are, | |
1431 | therefore, readable with | |
1432 | .BR cat (1). | |
1433 | However, the standard | |
1434 | .BR netstat (8) | |
1435 | suite provides much cleaner access to these files. | |
1436 | .TP | |
1437 | .I /proc/net/arp | |
1438 | This holds an ASCII readable dump of the kernel ARP table used for | |
1439 | address resolutions. | |
1440 | It will show both dynamically learned and preprogrammed ARP entries. | |
1441 | The format is: | |
1442 | ||
1443 | .nf | |
1444 | .ft CW | |
1445 | .in 8n | |
1446 | IP address HW type Flags HW address Mask Device | |
1447 | 192.168.0.50 0x1 0x2 00:50:BF:25:68:F3 * eth0 | |
1448 | 192.168.0.250 0x1 0xc 00:00:00:00:00:00 * eth0 | |
1449 | .ft | |
1450 | .fi | |
1451 | .in | |
1452 | ||
1453 | Here "IP address" is the IPv4 address of the machine and the "HW type" | |
1454 | is the hardware type of the address from RFC\ 826. | |
1455 | The flags are the internal | |
1456 | flags of the ARP structure (as defined in | |
1457 | .IR /usr/include/linux/if_arp.h ) | |
1458 | and | |
1459 | the "HW address" is the data link layer mapping for that IP address if | |
1460 | it is known. | |
1461 | .TP | |
1462 | .I /proc/net/dev | |
1463 | The dev pseudo-file contains network device status information. | |
1464 | This gives | |
1465 | the number of received and sent packets, the number of errors and | |
1466 | collisions | |
1467 | and other basic statistics. | |
1468 | These are used by the | |
1469 | .BR ifconfig (8) | |
1470 | program to report device status. | |
1471 | The format is: | |
1472 | ||
1473 | .nf | |
1474 | .ft CW | |
1475 | .in 1n | |
1476 | Inter-| Receive | Transmit | |
1477 | face |bytes packets errs drop fifo frame compressed multicast|bytes packets errs drop fifo colls carrier compressed | |
1478 | lo: 2776770 11307 0 0 0 0 0 0 2776770 11307 0 0 0 0 0 0 | |
1479 | eth0: 1215645 2751 0 0 0 0 0 0 1782404 4324 0 0 0 427 0 0 | |
1480 | ppp0: 1622270 5552 1 0 0 0 0 0 354130 5669 0 0 0 0 0 0 | |
1481 | tap0: 7714 81 0 0 0 0 0 0 7714 81 0 0 0 0 0 0 | |
1482 | .in | |
1483 | .ft | |
1484 | .fi | |
1485 | .\" .TP | |
1486 | .\" .I /proc/net/ipx | |
1487 | .\" No information. | |
1488 | .\" .TP | |
1489 | .\" .I /proc/net/ipx_route | |
1490 | .\" No information. | |
1491 | .TP | |
1492 | .I /proc/net/dev_mcast | |
1493 | Defined in | |
1494 | .IR /usr/src/linux/net/core/dev_mcast.c : | |
1495 | .nf | |
1496 | .in +5 | |
1497 | indx interface_name dmi_u dmi_g dmi_address | |
1498 | 2 eth0 1 0 01005e000001 | |
1499 | 3 eth1 1 0 01005e000001 | |
1500 | 4 eth2 1 0 01005e000001 | |
1501 | .in | |
1502 | .fi | |
1503 | .TP | |
1504 | .I /proc/net/igmp | |
1505 | Internet Group Management Protocol. | |
1506 | Defined in | |
1507 | .IR /usr/src/linux/net/core/igmp.c . | |
1508 | .TP | |
1509 | .I /proc/net/rarp | |
1510 | This file uses the same format as the | |
1511 | .I arp | |
1512 | file and contains the current reverse mapping database used to provide | |
1513 | .BR rarp (8) | |
1514 | reverse address lookup services. | |
1515 | If RARP is not configured into the | |
1516 | kernel, | |
1517 | this file will not be present. | |
1518 | .TP | |
1519 | .I /proc/net/raw | |
1520 | Holds a dump of the RAW socket table. | |
1521 | Much of the information is not of | |
1522 | use | |
1523 | apart from debugging. | |
1524 | The "sl" value is the kernel hash slot for the | |
1525 | socket, | |
1526 | the "local_address" is the local address and protocol number pair. | |
1527 | \&"St" is | |
1528 | the internal status of the socket. | |
1529 | The "tx_queue" and "rx_queue" are the | |
1530 | outgoing and incoming data queue in terms of kernel memory usage. | |
1531 | The "tr", "tm\->when", and "rexmits" fields are not used by RAW. | |
1532 | The "uid" | |
1533 | field holds the effective UID of the creator of the socket. | |
1534 | .\" .TP | |
1535 | .\" .I /proc/net/route | |
1536 | .\" No information, but looks similar to | |
1537 | .\" .BR route (8). | |
1538 | .TP | |
1539 | .I /proc/net/snmp | |
1540 | This file holds the ASCII data needed for the IP, ICMP, TCP, and UDP | |
1541 | management | |
1542 | information bases for an SNMP agent. | |
1543 | .TP | |
1544 | .I /proc/net/tcp | |
1545 | Holds a dump of the TCP socket table. | |
1546 | Much of the information is not | |
1547 | of use apart from debugging. | |
1548 | The "sl" value is the kernel hash slot | |
1549 | for the socket, the "local_address" is the local address and port number pair. | |
1550 | The "rem_address" is the remote address and port number pair | |
1551 | (if connected). | |
1552 | \&"St" is the internal status of the socket. | |
1553 | The "tx_queue" and "rx_queue" are the | |
1554 | outgoing and incoming data queue in terms of kernel memory usage. | |
1555 | The "tr", "tm\->when", and "rexmits" fields hold internal information of | |
1556 | the kernel socket state and are only useful for debugging. | |
1557 | The "uid" | |
1558 | field holds the effective UID of the creator of the socket. | |
1559 | .TP | |
1560 | .I /proc/net/udp | |
1561 | Holds a dump of the UDP socket table. | |
1562 | Much of the information is not of | |
1563 | use apart from debugging. | |
1564 | The "sl" value is the kernel hash slot for the | |
1565 | socket, the "local_address" is the local address and port number pair. | |
1566 | The "rem_address" is the remote address and port number pair | |
1567 | (if connected). "St" is the internal status of the socket. | |
1568 | The "tx_queue" and "rx_queue" are the outgoing and incoming data queue | |
1569 | in terms of kernel memory usage. | |
1570 | The "tr", "tm\->when", and "rexmits" fields | |
1571 | are not used by UDP. | |
1572 | The "uid" | |
1573 | field holds the effective UID of the creator of the socket. | |
1574 | The format is: | |
1575 | ||
1576 | .nf | |
1577 | .ft CW | |
1578 | .in 1n | |
1579 | sl local_address rem_address st tx_queue rx_queue tr rexmits tm\->when uid | |
1580 | 1: 01642C89:0201 0C642C89:03FF 01 00000000:00000001 01:000071BA 00000000 0 | |
1581 | 1: 00000000:0801 00000000:0000 0A 00000000:00000000 00:00000000 6F000100 0 | |
1582 | 1: 00000000:0201 00000000:0000 0A 00000000:00000000 00:00000000 00000000 0 | |
1583 | .in | |
1584 | .ft | |
1585 | .fi | |
1586 | .TP | |
1587 | .I /proc/net/unix | |
1588 | Lists the UNIX domain sockets present within the system and their | |
1589 | status. | |
1590 | The format is: | |
1591 | .nf | |
1592 | .sp .5 | |
1593 | .ft CW | |
1594 | Num RefCount Protocol Flags Type St Path | |
1595 | 0: 00000002 00000000 00000000 0001 03 | |
1596 | 1: 00000001 00000000 00010000 0001 01 /dev/printer | |
1597 | .ft | |
1598 | .sp .5 | |
1599 | .fi | |
1600 | ||
1601 | Here "Num" is the kernel table slot number, "RefCount" is the number | |
1602 | of users of the socket, "Protocol" is currently always 0, "Flags" | |
1603 | represent the internal kernel flags holding the status of the | |
1604 | socket. | |
1605 | Currently, type is always "1" (UNIX domain datagram sockets are | |
1606 | not yet supported in the kernel). | |
1607 | \&"St" is the internal state of the | |
1608 | socket and Path is the bound path (if any) of the socket. | |
1609 | .TP | |
1610 | .I /proc/partitions | |
1611 | Contains major and minor numbers of each partition as well as number | |
1612 | of blocks and partition name. | |
1613 | .TP | |
1614 | .I /proc/pci | |
1615 | This is a listing of all PCI devices found during kernel initialization | |
1616 | and their configuration. | |
1617 | ||
1618 | This file has been deprecated in favor of a new | |
1619 | .I /proc | |
1620 | interface for PCI | |
1621 | .RI ( /proc/bus/pci ). | |
1622 | It became optional in Linux 2.2 (available with | |
1623 | .B CONFIG_PCI_OLD_PROC | |
1624 | set at kernel compilation). | |
1625 | It became once more nonoptionally enabled in Linux 2.4. | |
1626 | Next, it was deprecated in Linux 2.6 (still available with | |
1627 | .B CONFIG_PCI_LEGACY_PROC | |
1628 | set), and finally removed altogether since Linux 2.6.17. | |
1629 | .\" FIXME /proc/sched_debug | |
1630 | .\" .TP | |
1631 | .\" .IR /proc/sched_debug " (since Linux 2.6.23)" | |
1632 | .\" See also /proc/[pid]/sched | |
1633 | .TP | |
1634 | .I /proc/scsi | |
1635 | A directory with the | |
1636 | .I scsi | |
1637 | mid-level pseudo-file and various SCSI low-level | |
1638 | driver directories, | |
1639 | which contain a file for each SCSI host in this system, all of | |
1640 | which give the status of some part of the SCSI IO subsystem. | |
1641 | These files contain ASCII structures and are, therefore, readable with | |
1642 | .BR cat (1). | |
1643 | ||
1644 | You can also write to some of the files to reconfigure the subsystem or | |
1645 | switch certain features on or off. | |
1646 | .TP | |
1647 | .I /proc/scsi/scsi | |
1648 | This is a listing of all SCSI devices known to the kernel. | |
1649 | The listing is similar to the one seen during bootup. | |
1650 | scsi currently supports only the \fIadd-single-device\fP command which | |
1651 | allows root to add a hotplugged device to the list of known devices. | |
1652 | ||
1653 | The command | |
1654 | .in +4n | |
1655 | .nf | |
1656 | ||
1657 | echo \(aqscsi add-single-device 1 0 5 0\(aq > /proc/scsi/scsi | |
1658 | ||
1659 | .fi | |
1660 | .in | |
1661 | will cause | |
1662 | host scsi1 to scan on SCSI channel 0 for a device on ID 5 LUN 0. | |
1663 | If there | |
1664 | is already a device known on this address or the address is invalid, an | |
1665 | error will be returned. | |
1666 | .TP | |
1667 | .I /proc/scsi/[drivername] | |
1668 | \fI[drivername]\fP can currently be NCR53c7xx, aha152x, aha1542, aha1740, | |
1669 | aic7xxx, buslogic, eata_dma, eata_pio, fdomain, in2000, pas16, qlogic, | |
1670 | scsi_debug, seagate, t128, u15-24f, ultrastore, or wd7000. | |
1671 | These directories show up for all drivers that registered at least one | |
1672 | SCSI HBA. | |
1673 | Every directory contains one file per registered host. | |
1674 | Every host-file is named after the number the host was assigned during | |
1675 | initialization. | |
1676 | ||
1677 | Reading these files will usually show driver and host configuration, | |
1678 | statistics, etc. | |
1679 | ||
1680 | Writing to these files allows different things on different hosts. | |
1681 | For example, with the \fIlatency\fP and \fInolatency\fP commands, | |
1682 | root can switch on and off command latency measurement code in the | |
1683 | eata_dma driver. | |
1684 | With the \fIlockup\fP and \fIunlock\fP commands, | |
1685 | root can control bus lockups simulated by the scsi_debug driver. | |
1686 | .TP | |
1687 | .I /proc/self | |
1688 | This directory refers to the process accessing the | |
1689 | .I /proc | |
1690 | file system, | |
1691 | and is identical to the | |
1692 | .I /proc | |
1693 | directory named by the process ID of the same process. | |
1694 | .TP | |
1695 | .I /proc/slabinfo | |
1696 | Information about kernel caches. | |
1697 | Since Linux 2.6.16 this file is only present if the | |
1698 | .B CONFIG_SLAB | |
1699 | kernel configuration option is enabled. | |
1700 | The columns in | |
1701 | .I /proc/slabinfo | |
1702 | are: | |
1703 | .in +4n | |
1704 | .nf | |
1705 | ||
1706 | cache-name | |
1707 | num-active-objs | |
1708 | total-objs | |
1709 | object-size | |
1710 | num-active-slabs | |
1711 | total-slabs | |
1712 | num-pages-per-slab | |
1713 | .fi | |
1714 | .in | |
1715 | ||
1716 | See | |
1717 | .BR slabinfo (5) | |
1718 | for details. | |
1719 | .TP | |
1720 | .I /proc/stat | |
1721 | kernel/system statistics. | |
1722 | Varies with architecture. | |
1723 | Common | |
1724 | entries include: | |
1725 | .RS | |
1726 | .TP | |
1727 | \fIcpu 3357 0 4313 1362393\fP | |
1728 | The amount of time, measured in units of | |
1729 | USER_HZ (1/100ths of a second on most architectures, use | |
1730 | .IR sysconf(_SC_CLK_TCK) | |
1731 | to obtain the right value), | |
1732 | .\" 1024 on Alpha and ia64 | |
1733 | that the system spent in user mode, | |
1734 | user mode with low priority (nice), system mode, and the | |
1735 | idle task, respectively. | |
1736 | .\" FIXME Actually, the following info about the /proc/stat 'cpu' field | |
1737 | .\" does not seem to be quite right (at least in 2.6.12) | |
1738 | The last value should be USER_HZ times the | |
1739 | second entry in the uptime pseudo-file. | |
1740 | ||
1741 | In Linux 2.6 this line includes three additional columns: | |
1742 | .I iowait | |
1743 | \- time waiting for I/O to complete (since 2.5.41); | |
1744 | .I irq | |
1745 | \- time servicing interrupts (since 2.6.0-test4); | |
1746 | .I softirq | |
1747 | \- time servicing softirqs (since 2.6.0-test4). | |
1748 | ||
1749 | Since Linux 2.6.11, there is an eighth column, | |
1750 | .I steal | |
1751 | \- stolen time, which is the time spent in other operating systems when | |
1752 | running in a virtualized environment | |
1753 | ||
1754 | Since Linux 2.6.24, there is a ninth column, | |
1755 | .IR guest , | |
1756 | which is the time spent running a virtual CPU for guest | |
1757 | operating systems under the control of the Linux kernel. | |
1758 | .\" See Changelog entry for 5e84cfde51cf303d368fcb48f22059f37b3872de | |
1759 | .TP | |
1760 | \fIpage 5741 1808\fP | |
1761 | The number of pages the system paged in and the number that were paged | |
1762 | out (from disk). | |
1763 | .TP | |
1764 | \fIswap 1 0\fP | |
1765 | The number of swap pages that have been brought in and out. | |
1766 | .TP | |
1767 | .\" FIXME The following is not the full picture for the 'intr' of | |
1768 | .\" /proc/stat on 2.6: | |
1769 | \fIintr 1462898\fP | |
1770 | This line shows counts of interrupts serviced since boot time, | |
1771 | for each of the possible system interrupts. | |
1772 | The first column is the total of all interrupts serviced; | |
1773 | each subsequent column is the total for a particular interrupt. | |
1774 | .TP | |
1775 | \fIdisk_io: (2,0):(31,30,5764,1,2) (3,0):\fP... | |
1776 | (major,disk_idx):(noinfo, read_io_ops, blks_read, write_io_ops, blks_written) | |
1777 | .br | |
1778 | (Linux 2.4 only) | |
1779 | .TP | |
1780 | \fIctxt 115315\fP | |
1781 | The number of context switches that the system underwent. | |
1782 | .TP | |
1783 | \fIbtime 769041601\fP | |
1784 | boot time, in seconds since the Epoch, 1970-01-01 00:00:00 +0000 (UTC). | |
1785 | .TP | |
1786 | \fIprocesses 86031\fP | |
1787 | Number of forks since boot. | |
1788 | .TP | |
1789 | \fIprocs_running 6\fP | |
1790 | Number of processes in runnable state. | |
1791 | (Linux 2.5.45 onward.) | |
1792 | .TP | |
1793 | \fIprocs_blocked 2\fP | |
1794 | Number of processes blocked waiting for I/O to complete. | |
1795 | (Linux 2.5.45 onward.) | |
1796 | .RE | |
1797 | .TP | |
1798 | .I /proc/swaps | |
1799 | Swap areas in use. | |
1800 | See also | |
1801 | .BR swapon (8). | |
1802 | .TP | |
1803 | .I /proc/sys | |
1804 | This directory (present since 1.3.57) contains a number of files | |
1805 | and subdirectories corresponding to kernel variables. | |
1806 | These variables can be read and sometimes modified using | |
1807 | the \fI/proc\fP file system, and the (deprecated) | |
1808 | .BR sysctl (2) | |
1809 | system call. | |
1810 | .TP | |
1811 | .IR /proc/sys/abi " (since Linux 2.4.10)" | |
1812 | This directory may contain files with application binary information. | |
1813 | .\" On some systems, it is not present. | |
1814 | See the kernel source file | |
1815 | .I Documentation/sysctl/abi.txt | |
1816 | for more information. | |
1817 | .TP | |
1818 | .I /proc/sys/debug | |
1819 | This directory may be empty. | |
1820 | .TP | |
1821 | .I /proc/sys/dev | |
1822 | This directory contains device-specific information (e.g., | |
1823 | .IR dev/cdrom/info ). | |
1824 | On | |
1825 | some systems, it may be empty. | |
1826 | .TP | |
1827 | .I /proc/sys/fs | |
1828 | This directory contains the files and subdirectories for kernel variables | |
1829 | related to file systems. | |
1830 | .TP | |
1831 | .I /proc/sys/fs/binfmt_misc | |
1832 | Documentation for files in this directory can be found | |
1833 | in the kernel sources in | |
1834 | .IR Documentation/binfmt_misc.txt . | |
1835 | .TP | |
1836 | .IR /proc/sys/fs/dentry-state " (since Linux 2.2)" | |
1837 | This file contains information about the status of the | |
1838 | directory cache (dcache). | |
1839 | The file contains six numbers, | |
1840 | .IR nr_dentry ", " nr_unused ", " age_limit " (age in seconds), " | |
1841 | .I want_pages | |
1842 | (pages requested by system) and two dummy values. | |
1843 | .RS | |
1844 | .IP * 2 | |
1845 | .I nr_dentry | |
1846 | is the number of allocated dentries (dcache entries). | |
1847 | This field is unused in Linux 2.2. | |
1848 | .IP * | |
1849 | .I nr_unused | |
1850 | is the number of unused dentries. | |
1851 | .IP * | |
1852 | .I age_limit | |
1853 | .\" looks like this is unused in kernels 2.2 to 2.6 | |
1854 | is the age in seconds after which dcache entries | |
1855 | can be reclaimed when memory is short. | |
1856 | .IP * | |
1857 | .I want_pages | |
1858 | .\" looks like this is unused in kernels 2.2 to 2.6 | |
1859 | is nonzero when the kernel has called shrink_dcache_pages() and the | |
1860 | dcache isn't pruned yet. | |
1861 | .RE | |
1862 | .TP | |
1863 | .I /proc/sys/fs/dir-notify-enable | |
1864 | This file can be used to disable or enable the | |
1865 | .I dnotify | |
1866 | interface described in | |
1867 | .BR fcntl (2) | |
1868 | on a system-wide basis. | |
1869 | A value of 0 in this file disables the interface, | |
1870 | and a value of 1 enables it. | |
1871 | .TP | |
1872 | .I /proc/sys/fs/dquot-max | |
1873 | This file shows the maximum number of cached disk quota entries. | |
1874 | On some (2.4) systems, it is not present. | |
1875 | If the number of free cached disk quota entries is very low and | |
1876 | you have some awesome number of simultaneous system users, | |
1877 | you might want to raise the limit. | |
1878 | .TP | |
1879 | .I /proc/sys/fs/dquot-nr | |
1880 | This file shows the number of allocated disk quota | |
1881 | entries and the number of free disk quota entries. | |
1882 | .TP | |
1883 | .IR /proc/sys/fs/epoll " (since Linux 2.6.28)" | |
1884 | This directory contains the file | |
1885 | .IR max_user_watches , | |
1886 | which can be used to limit the amount of kernel memory consumed by the | |
1887 | .I epoll | |
1888 | interface. | |
1889 | For further details, see | |
1890 | .BR epoll (7). | |
1891 | .TP | |
1892 | .I /proc/sys/fs/file-max | |
1893 | This file defines | |
1894 | a system-wide limit on the number of open files for all processes. | |
1895 | (See also | |
1896 | .BR setrlimit (2), | |
1897 | which can be used by a process to set the per-process limit, | |
1898 | .BR RLIMIT_NOFILE , | |
1899 | on the number of files it may open.) | |
1900 | If you get lots | |
1901 | of error messages about running out of file handles, | |
1902 | try increasing this value: | |
1903 | .br | |
1904 | ||
1905 | .br | |
1906 | .nf | |
1907 | .ft CW | |
1908 | echo 100000 > /proc/sys/fs/file-max | |
1909 | .fi | |
1910 | .ft | |
1911 | ||
1912 | The kernel constant | |
1913 | .B NR_OPEN | |
1914 | imposes an upper limit on the value that may be placed in | |
1915 | .IR file-max . | |
1916 | ||
1917 | If you increase | |
1918 | .IR /proc/sys/fs/file-max "," | |
1919 | be sure to increase | |
1920 | .I /proc/sys/fs/inode-max | |
1921 | to 3-4 times the new | |
1922 | value of | |
1923 | .IR /proc/sys/fs/file-max "," | |
1924 | or you will run out of inodes. | |
1925 | ||
1926 | Privileged processes | |
1927 | .RB ( CAP_SYS_ADMIN ) | |
1928 | can override the | |
1929 | .I file-max | |
1930 | limit. | |
1931 | .TP | |
1932 | .I /proc/sys/fs/file-nr | |
1933 | This (read-only) file gives the number of files presently opened. | |
1934 | It contains three numbers: the number of allocated file handles; | |
1935 | the number of free file handles; and the maximum number of file handles. | |
1936 | The kernel allocates file handles dynamically, but it | |
1937 | doesn't free them again. | |
1938 | If the number of allocated files is close to the | |
1939 | maximum, you should consider increasing the maximum. | |
1940 | When the number of free file handles is | |
1941 | large, you've encountered a peak in your usage of file | |
1942 | handles and you probably don't need to increase the maximum. | |
1943 | .TP | |
1944 | .I /proc/sys/fs/inode-max | |
1945 | This file contains the maximum number of in-memory inodes. | |
1946 | On some (2.4) systems, it may not be present. | |
1947 | This value should be 3-4 times larger | |
1948 | than the value in | |
1949 | .IR file-max , | |
1950 | since \fIstdin\fP, \fIstdout\fP | |
1951 | and network sockets also need an inode to handle them. | |
1952 | When you regularly run out of inodes, you need to increase this value. | |
1953 | .TP | |
1954 | .I /proc/sys/fs/inode-nr | |
1955 | This file contains the first two values from | |
1956 | .IR inode-state . | |
1957 | .TP | |
1958 | .I /proc/sys/fs/inode-state | |
1959 | This file | |
1960 | contains seven numbers: | |
1961 | .IR nr_inodes , | |
1962 | .IR nr_free_inodes , | |
1963 | .IR preshrink , | |
1964 | and four dummy values. | |
1965 | .I nr_inodes | |
1966 | is the number of inodes the system has allocated. | |
1967 | This can be slightly more than | |
1968 | .I inode-max | |
1969 | because Linux allocates them one page full at a time. | |
1970 | .I nr_free_inodes | |
1971 | represents the number of free inodes. | |
1972 | .I preshrink | |
1973 | is nonzero when the | |
1974 | .I nr_inodes | |
1975 | > | |
1976 | .I inode-max | |
1977 | and the system needs to prune the inode list instead of allocating more. | |
1978 | .TP | |
1979 | .IR /proc/sys/fs/inotify " (since Linux 2.6.13)" | |
1980 | This directory contains files | |
1981 | .IR max_queued_events ", " max_user_instances ", and " max_user_watches , | |
1982 | that can be used to limit the amount of kernel memory consumed by the | |
1983 | .I inotify | |
1984 | interface. | |
1985 | For further details, see | |
1986 | .BR inotify (7). | |
1987 | .TP | |
1988 | .I /proc/sys/fs/lease-break-time | |
1989 | This file specifies the grace period that the kernel grants to a process | |
1990 | holding a file lease | |
1991 | .RB ( fcntl (2)) | |
1992 | after it has sent a signal to that process notifying it | |
1993 | that another process is waiting to open the file. | |
1994 | If the lease holder does not remove or downgrade the lease within | |
1995 | this grace period, the kernel forcibly breaks the lease. | |
1996 | .TP | |
1997 | .I /proc/sys/fs/leases-enable | |
1998 | This file can be used to enable or disable file leases | |
1999 | .RB ( fcntl (2)) | |
2000 | on a system-wide basis. | |
2001 | If this file contains the value 0, leases are disabled. | |
2002 | A nonzero value enables leases. | |
2003 | .TP | |
2004 | .IR /proc/sys/fs/mqueue " (since Linux 2.6.6)" | |
2005 | This directory contains files | |
2006 | .IR msg_max ", " msgsize_max ", and " queues_max , | |
2007 | controlling the resources used by POSIX message queues. | |
2008 | See | |
2009 | .BR mq_overview (7) | |
2010 | for details. | |
2011 | .TP | |
2012 | .IR /proc/sys/fs/overflowgid " and " /proc/sys/fs/overflowuid | |
2013 | These files | |
2014 | allow you to change the value of the fixed UID and GID. | |
2015 | The default is 65534. | |
2016 | Some file systems only support 16-bit UIDs and GIDs, although in Linux | |
2017 | UIDs and GIDs are 32 bits. | |
2018 | When one of these file systems is mounted | |
2019 | with writes enabled, any UID or GID that would exceed 65535 is translated | |
2020 | to the overflow value before being written to disk. | |
2021 | .TP | |
2022 | .IR /proc/sys/fs/pipe-max-size " (since Linux 2.6.35)" | |
2023 | The value in this file defines an upper limit for raising the capacity | |
2024 | of a pipe using the | |
2025 | .BR fcntl (2) | |
2026 | .B F_SETPIPE_SZ | |
2027 | operation. | |
2028 | This limit applies only to unprivileged processes. | |
2029 | The default value for this file is 1,048,576. | |
2030 | The value assigned to this file may be rounded upward, | |
2031 | to reflect the value actually employed for a convenient implementation. | |
2032 | To determine the rounded-up value, | |
2033 | display the contents of this file after assigning a value to it. | |
2034 | The minimum value that can be assigned to this file is the system page size. | |
2035 | .TP | |
2036 | .IR /proc/sys/fs/suid_dumpable " (since Linux 2.6.13)" | |
2037 | .\" The following is based on text from Documentation/sysctl/kernel.txt | |
2038 | The value in this file determines whether core dump files are | |
2039 | produced for set-user-ID or otherwise protected/tainted binaries. | |
2040 | Three different integer values can be specified: | |
2041 | .sp | |
2042 | \fI0\ (default)\fP | |
2043 | This provides the traditional (pre-Linux 2.6.13) behavior. | |
2044 | A core dump will not be produced for a process which has | |
2045 | changed credentials (by calling | |
2046 | .BR seteuid (2), | |
2047 | .BR setgid (2), | |
2048 | or similar, or by executing a set-user-ID or set-group-ID program) | |
2049 | or whose binary does not have read permission enabled. | |
2050 | .sp | |
2051 | \fI1\ ("debug")\fP | |
2052 | All processes dump core when possible. | |
2053 | The core dump is owned by the file system user ID of the dumping process | |
2054 | and no security is applied. | |
2055 | This is intended for system debugging situations only. | |
2056 | Ptrace is unchecked. | |
2057 | .sp | |
2058 | \fI2\ ("suidsafe")\fP | |
2059 | Any binary which normally would not be dumped (see "0" above) | |
2060 | is dumped readable by root only. | |
2061 | This allows the user to remove the core dump file but not to read it. | |
2062 | For security reasons core dumps in this mode will not overwrite one | |
2063 | another or other files. | |
2064 | This mode is appropriate when administrators are | |
2065 | attempting to debug problems in a normal environment. | |
2066 | .TP | |
2067 | .I /proc/sys/fs/super-max | |
2068 | This file | |
2069 | controls the maximum number of superblocks, and | |
2070 | thus the maximum number of mounted file systems the kernel | |
2071 | can have. | |
2072 | You only need to increase | |
2073 | .I super-max | |
2074 | if you need to mount more file systems than the current value in | |
2075 | .I super-max | |
2076 | allows you to. | |
2077 | .TP | |
2078 | .I /proc/sys/fs/super-nr | |
2079 | This file | |
2080 | contains the number of file systems currently mounted. | |
2081 | .TP | |
2082 | .I /proc/sys/kernel | |
2083 | This directory contains files controlling a range of kernel parameters, | |
2084 | as described below. | |
2085 | .TP | |
2086 | .I /proc/sys/kernel/acct | |
2087 | This file | |
2088 | contains three numbers: | |
2089 | .IR highwater , | |
2090 | .IR lowwater , | |
2091 | and | |
2092 | .IR frequency . | |
2093 | If BSD-style process accounting is enabled these values control | |
2094 | its behavior. | |
2095 | If free space on file system where the log lives goes below | |
2096 | .I lowwater | |
2097 | percent accounting suspends. | |
2098 | If free space gets above | |
2099 | .I highwater | |
2100 | percent accounting resumes. | |
2101 | .I frequency | |
2102 | determines | |
2103 | how often the kernel checks the amount of free space (value is in | |
2104 | seconds). | |
2105 | Default values are 4, 2 and 30. | |
2106 | That is, suspend accounting if 2% or less space is free; resume it | |
2107 | if 4% or more space is free; consider information about amount of free space | |
2108 | valid for 30 seconds. | |
2109 | .TP | |
2110 | .IR /proc/sys/kernel/cap-bound " (from Linux 2.2 to 2.6.24)" | |
2111 | This file holds the value of the kernel | |
2112 | .I "capability bounding set" | |
2113 | (expressed as a signed decimal number). | |
2114 | This set is ANDed against the capabilities permitted to a process | |
2115 | during | |
2116 | .BR execve (2). | |
2117 | Starting with Linux 2.6.25, | |
2118 | the system-wide capability bounding set disappeared, | |
2119 | and was replaced by a per-thread bounding set; see | |
2120 | .BR capabilities (7). | |
2121 | .TP | |
2122 | .I /proc/sys/kernel/core_pattern | |
2123 | See | |
2124 | .BR core (5). | |
2125 | .TP | |
2126 | .I /proc/sys/kernel/core_uses_pid | |
2127 | See | |
2128 | .BR core (5). | |
2129 | .TP | |
2130 | .I /proc/sys/kernel/ctrl-alt-del | |
2131 | This file | |
2132 | controls the handling of Ctrl-Alt-Del from the keyboard. | |
2133 | When the value in this file is 0, Ctrl-Alt-Del is trapped and | |
2134 | sent to the | |
2135 | .BR init (8) | |
2136 | program to handle a graceful restart. | |
2137 | When the value is greater than zero, Linux's reaction to a Vulcan | |
2138 | Nerve Pinch (tm) will be an immediate reboot, without even | |
2139 | syncing its dirty buffers. | |
2140 | Note: when a program (like dosemu) has the keyboard in "raw" | |
2141 | mode, the ctrl-alt-del is intercepted by the program before it | |
2142 | ever reaches the kernel tty layer, and it's up to the program | |
2143 | to decide what to do with it. | |
2144 | .TP | |
2145 | .I /proc/sys/kernel/hotplug | |
2146 | This file | |
2147 | contains the path for the hotplug policy agent. | |
2148 | The default value in this file is | |
2149 | .IR /sbin/hotplug . | |
2150 | .TP | |
2151 | .IR /proc/sys/kernel/domainname " and " /proc/sys/kernel/hostname | |
2152 | can be used to set the NIS/YP domainname and the | |
2153 | hostname of your box in exactly the same way as the commands | |
2154 | .BR domainname (1) | |
2155 | and | |
2156 | .BR hostname (1), | |
2157 | that is: | |
2158 | ||
2159 | .in +4n | |
2160 | .nf | |
2161 | .RB "#" " echo \(aqdarkstar\(aq > /proc/sys/kernel/hostname" | |
2162 | .RB "#" " echo \(aqmydomain\(aq > /proc/sys/kernel/domainname" | |
2163 | .fi | |
2164 | .in | |
2165 | ||
2166 | has the same effect as | |
2167 | ||
2168 | .in +4n | |
2169 | .nf | |
2170 | .RB "#" " hostname \(aqdarkstar\(aq" | |
2171 | .RB "#" " domainname \(aqmydomain\(aq" | |
2172 | .fi | |
2173 | .in | |
2174 | ||
2175 | Note, however, that the classic darkstar.frop.org has the | |
2176 | hostname "darkstar" and DNS (Internet Domain Name Server) | |
2177 | domainname "frop.org", not to be confused with the NIS (Network | |
2178 | Information Service) or YP (Yellow Pages) domainname. | |
2179 | These two | |
2180 | domain names are in general different. | |
2181 | For a detailed discussion | |
2182 | see the | |
2183 | .BR hostname (1) | |
2184 | man page. | |
2185 | .TP | |
2186 | .I /proc/sys/kernel/htab-reclaim | |
2187 | (PowerPC only) If this file is set to a nonzero value, | |
2188 | the PowerPC htab | |
2189 | (see kernel file | |
2190 | .IR Documentation/powerpc/ppc_htab.txt ) | |
2191 | is pruned | |
2192 | each time the system hits the idle loop. | |
2193 | .TP | |
2194 | .I /proc/sys/kernel/l2cr | |
2195 | (PowerPC only) This file | |
2196 | contains a flag that controls the L2 cache of G3 processor | |
2197 | boards. | |
2198 | If 0, the cache is disabled. | |
2199 | Enabled if nonzero. | |
2200 | .TP | |
2201 | .I /proc/sys/kernel/modprobe | |
2202 | This file contains the path for the kernel module loader. | |
2203 | The default value is | |
2204 | .IR /sbin/modprobe . | |
2205 | The file is only present if the kernel is built with the | |
2206 | .B CONFIG_KMOD | |
2207 | option enabled. | |
2208 | It is described by the kernel source file | |
2209 | .I Documentation/kmod.txt | |
2210 | (only present in kernel 2.4 and earlier). | |
2211 | .TP | |
2212 | .I /proc/sys/kernel/msgmax | |
2213 | This file defines | |
2214 | a system-wide limit specifying the maximum number of bytes in | |
2215 | a single message written on a System V message queue. | |
2216 | .TP | |
2217 | .I /proc/sys/kernel/msgmni | |
2218 | This file defines the system-wide limit on the number of | |
2219 | message queue identifiers. | |
2220 | (This file is only present in Linux 2.4 onward.) | |
2221 | .TP | |
2222 | .I /proc/sys/kernel/msgmnb | |
2223 | This file defines a system-wide parameter used to initialize the | |
2224 | .I msg_qbytes | |
2225 | setting for subsequently created message queues. | |
2226 | The | |
2227 | .I msg_qbytes | |
2228 | setting specifies the maximum number of bytes that may be written to the | |
2229 | message queue. | |
2230 | .TP | |
2231 | .IR /proc/sys/kernel/ostype " and " /proc/sys/kernel/osrelease | |
2232 | These files | |
2233 | give substrings of | |
2234 | .IR /proc/version . | |
2235 | .TP | |
2236 | .IR /proc/sys/kernel/overflowgid " and " /proc/sys/kernel/overflowuid | |
2237 | These files duplicate the files | |
2238 | .I /proc/sys/fs/overflowgid | |
2239 | and | |
2240 | .IR /proc/sys/fs/overflowuid . | |
2241 | .TP | |
2242 | .I /proc/sys/kernel/panic | |
2243 | This file gives read/write access to the kernel variable | |
2244 | .IR panic_timeout . | |
2245 | If this is zero, the kernel will loop on a panic; if nonzero | |
2246 | it indicates that the kernel should autoreboot after this number | |
2247 | of seconds. | |
2248 | When you use the | |
2249 | software watchdog device driver, the recommended setting is 60. | |
2250 | .TP | |
2251 | .IR /proc/sys/kernel/panic_on_oops " (since Linux 2.5.68)" | |
2252 | This file controls the kernel's behavior when an oops | |
2253 | or BUG is encountered. | |
2254 | If this file contains 0, then the system | |
2255 | tries to continue operation. | |
2256 | If it contains 1, then the system | |
2257 | delays a few seconds (to give klogd time to record the oops output) | |
2258 | and then panics. | |
2259 | If the | |
2260 | .I /proc/sys/kernel/panic | |
2261 | file is also nonzero then the machine will be rebooted. | |
2262 | .TP | |
2263 | .IR /proc/sys/kernel/pid_max " (since Linux 2.5.34)" | |
2264 | This file specifies the value at which PIDs wrap around | |
2265 | (i.e., the value in this file is one greater than the maximum PID). | |
2266 | The default value for this file, 32768, | |
2267 | results in the same range of PIDs as on earlier kernels. | |
2268 | On 32-bit platforms, 32768 is the maximum value for | |
2269 | .IR pid_max . | |
2270 | On 64-bit systems, | |
2271 | .I pid_max | |
2272 | can be set to any value up to 2^22 | |
2273 | .RB ( PID_MAX_LIMIT , | |
2274 | approximately 4 million). | |
2275 | .\" Prior to 2.6.10, pid_max could also be raised above 32768 on 32-bit | |
2276 | .\" platforms, but this broke /proc/[pid] | |
2277 | .\" See http://marc.theaimsgroup.com/?l=linux-kernel&m=109513010926152&w=2 | |
2278 | .TP | |
2279 | .IR /proc/sys/kernel/powersave-nap " (PowerPC only)" | |
2280 | This file contains a flag. | |
2281 | If set, Linux-PPC will use the "nap" mode of | |
2282 | powersaving, | |
2283 | otherwise the "doze" mode will be used. | |
2284 | .TP | |
2285 | .I /proc/sys/kernel/printk | |
2286 | The four values in this file are | |
2287 | .IR console_loglevel , | |
2288 | .IR default_message_loglevel , | |
2289 | .IR minimum_console_level , | |
2290 | and | |
2291 | .IR default_console_loglevel . | |
2292 | These values influence | |
2293 | .I printk() | |
2294 | behavior when printing or logging error messages. | |
2295 | See | |
2296 | .BR syslog (2) | |
2297 | for more info on the different loglevels. | |
2298 | Messages with a higher priority than | |
2299 | .I console_loglevel | |
2300 | will be printed to the console. | |
2301 | Messages without an explicit priority will be printed with priority | |
2302 | .IR default_message_level . | |
2303 | .I minimum_console_loglevel | |
2304 | is the minimum (highest) value to which | |
2305 | .I console_loglevel | |
2306 | can be set. | |
2307 | .I default_console_loglevel | |
2308 | is the default value for | |
2309 | .IR console_loglevel . | |
2310 | .TP | |
2311 | .IR /proc/sys/kernel/pty " (since Linux 2.6.4)" | |
2312 | This directory contains two files relating to the number of UNIX 98 | |
2313 | pseudoterminals (see | |
2314 | .BR pts (4)) | |
2315 | on the system. | |
2316 | .TP | |
2317 | .I /proc/sys/kernel/pty/max | |
2318 | This file defines the maximum number of pseudoterminals. | |
2319 | .TP | |
2320 | .I /proc/sys/kernel/pty/nr | |
2321 | This read-only file | |
2322 | indicates how many pseudoterminals are currently in use. | |
2323 | .TP | |
2324 | .I /proc/sys/kernel/random | |
2325 | This directory | |
2326 | contains various parameters controlling the operation of the file | |
2327 | .IR /dev/random . | |
2328 | See | |
2329 | .BR random (4) | |
2330 | for further information. | |
2331 | .TP | |
2332 | .I /proc/sys/kernel/real-root-dev | |
2333 | This file is documented in the kernel source file | |
2334 | .IR Documentation/initrd.txt . | |
2335 | .TP | |
2336 | .IR /proc/sys/kernel/reboot-cmd " (Sparc only) " | |
2337 | This file seems to be a way to give an argument to the SPARC | |
2338 | ROM/Flash boot loader. | |
2339 | Maybe to tell it what to do after | |
2340 | rebooting? | |
2341 | .TP | |
2342 | .I /proc/sys/kernel/rtsig-max | |
2343 | (Only in kernels up to and including 2.6.7; see | |
2344 | .BR setrlimit (2)) | |
2345 | This file can be used to tune the maximum number | |
2346 | of POSIX real-time (queued) signals that can be outstanding | |
2347 | in the system. | |
2348 | .TP | |
2349 | .I /proc/sys/kernel/rtsig-nr | |
2350 | (Only in kernels up to and including 2.6.7.) | |
2351 | This file shows the number POSIX real-time signals currently queued. | |
2352 | .TP | |
2353 | .IR /proc/sys/kernel/sem " (since Linux 2.4)" | |
2354 | This file contains 4 numbers defining limits for System V IPC semaphores. | |
2355 | These fields are, in order: | |
2356 | .RS | |
2357 | .IP SEMMSL 8 | |
2358 | The maximum semaphores per semaphore set. | |
2359 | .IP SEMMNS 8 | |
2360 | A system-wide limit on the number of semaphores in all semaphore sets. | |
2361 | .IP SEMOPM 8 | |
2362 | The maximum number of operations that may be specified in a | |
2363 | .BR semop (2) | |
2364 | call. | |
2365 | .IP SEMMNI 8 | |
2366 | A system-wide limit on the maximum number of semaphore identifiers. | |
2367 | .RE | |
2368 | .TP | |
2369 | .I /proc/sys/kernel/sg-big-buff | |
2370 | This file | |
2371 | shows the size of the generic SCSI device (sg) buffer. | |
2372 | You can't tune it just yet, but you could change it at | |
2373 | compile time by editing | |
2374 | .I include/scsi/sg.h | |
2375 | and changing | |
2376 | the value of | |
2377 | .BR SG_BIG_BUFF . | |
2378 | However, there shouldn't be any reason to change this value. | |
2379 | .TP | |
2380 | .I /proc/sys/kernel/shmall | |
2381 | This file | |
2382 | contains the system-wide limit on the total number of pages of | |
2383 | System V shared memory. | |
2384 | .TP | |
2385 | .I /proc/sys/kernel/shmmax | |
2386 | This file | |
2387 | can be used to query and set the run-time limit | |
2388 | on the maximum (System V IPC) shared memory segment size that can be | |
2389 | created. | |
2390 | Shared memory segments up to 1GB are now supported in the | |
2391 | kernel. | |
2392 | This value defaults to | |
2393 | .BR SHMMAX . | |
2394 | .TP | |
2395 | .I /proc/sys/kernel/shmmni | |
2396 | (available in Linux 2.4 and onward) | |
2397 | This file | |
2398 | specifies the system-wide maximum number of System V shared memory | |
2399 | segments that can be created. | |
2400 | .TP | |
2401 | .I /proc/sys/kernel/sysrq | |
2402 | This file controls the functions allowed to be invoked by the SysRq key. | |
2403 | By default, | |
2404 | the file contains 1 meaning that every possible SysRq request is allowed | |
2405 | (in older kernel versions, SysRq was disabled by default, | |
2406 | and you were required to specifically enable it at run-time, | |
2407 | but this is not the case any more). | |
2408 | Possible values in this file are: | |
2409 | ||
2410 | 0 - disable sysrq completely | |
2411 | 1 - enable all functions of sysrq | |
2412 | >1 - bitmask of allowed sysrq functions, as follows: | |
2413 | 2 - enable control of console logging level | |
2414 | 4 - enable control of keyboard (SAK, unraw) | |
2415 | 8 - enable debugging dumps of processes etc. | |
2416 | 16 - enable sync command | |
2417 | 32 - enable remount read-only | |
2418 | 64 - enable signalling of processes (term, kill, oom-kill) | |
2419 | 128 - allow reboot/poweroff | |
2420 | 256 - allow nicing of all real-time tasks | |
2421 | ||
2422 | This file is only present if the | |
2423 | .B CONFIG_MAGIC_SYSRQ | |
2424 | kernel configuration option is enabled. | |
2425 | For further details see the kernel source file | |
2426 | .IR Documentation/sysrq.txt . | |
2427 | .TP | |
2428 | .I /proc/sys/kernel/version | |
2429 | This file contains a string like: | |
2430 | ||
2431 | #5 Wed Feb 25 21:49:24 MET 1998 | |
2432 | ||
2433 | The "#5" means that | |
2434 | this is the fifth kernel built from this source base and the | |
2435 | date behind it indicates the time the kernel was built. | |
2436 | .TP | |
2437 | .IR /proc/sys/kernel/threads-max " (since Linux 2.3.11)" | |
2438 | This file specifies the system-wide limit on the number of | |
2439 | threads (tasks) that can be created on the system. | |
2440 | .TP | |
2441 | .IR /proc/sys/kernel/zero-paged " (PowerPC only) " | |
2442 | This file | |
2443 | contains a flag. | |
2444 | When enabled (nonzero), Linux-PPC will pre-zero pages in | |
2445 | the idle loop, possibly speeding up get_free_pages. | |
2446 | .TP | |
2447 | .I /proc/sys/net | |
2448 | This directory contains networking stuff. | |
2449 | Explanations for some of the files under this directory can be found in | |
2450 | .BR tcp (7) | |
2451 | and | |
2452 | .BR ip (7). | |
2453 | .TP | |
2454 | .I /proc/sys/net/core/somaxconn | |
2455 | This file defines a ceiling value for the | |
2456 | .I backlog | |
2457 | argument of | |
2458 | .BR listen (2); | |
2459 | see the | |
2460 | .BR listen (2) | |
2461 | manual page for details. | |
2462 | .TP | |
2463 | .I /proc/sys/proc | |
2464 | This directory may be empty. | |
2465 | .TP | |
2466 | .I /proc/sys/sunrpc | |
2467 | This directory supports Sun remote procedure call for network file system | |
2468 | (NFS). | |
2469 | On some systems, it is not present. | |
2470 | .TP | |
2471 | .I /proc/sys/vm | |
2472 | This directory contains files for memory management tuning, buffer and | |
2473 | cache management. | |
2474 | .TP | |
2475 | .IR /proc/sys/vm/drop_caches " (since Linux 2.6.16)" | |
2476 | Writing to this file causes the kernel to drop clean caches, dentries and | |
2477 | inodes from memory, causing that memory to become free. | |
2478 | ||
2479 | To free pagecache, use | |
2480 | .IR "echo 1 > /proc/sys/vm/drop_caches" ; | |
2481 | to free dentries and inodes, use | |
2482 | .IR "echo 2 > /proc/sys/vm/drop_caches" ; | |
2483 | to free pagecache, dentries and inodes, use | |
2484 | .IR "echo 3 > /proc/sys/vm/drop_caches" . | |
2485 | ||
2486 | Because this is a nondestructive operation and dirty objects | |
2487 | are not freeable, the | |
2488 | user should run | |
2489 | .BR sync (8) | |
2490 | first. | |
2491 | .TP | |
2492 | .IR /proc/sys/vm/legacy_va_layout " (since Linux 2.6.9)" | |
2493 | .\" The following is from Documentation/filesystems/proc.txt | |
2494 | If nonzero, this disables the new 32-bit memory-mapping layout; | |
2495 | the kernel will use the legacy (2.4) layout for all processes. | |
2496 | .TP | |
2497 | .IR /proc/sys/vm/memory_failure_early_kill " (since Linux 2.6.32)" | |
2498 | .\" The following is based on the text in Documentation/sysctl/vm.txt | |
2499 | Control how to kill processes when an uncorrected memory error | |
2500 | (typically a 2-bit error in a memory module) | |
2501 | that cannot be handled by the kernel | |
2502 | is detected in the background by hardware. | |
2503 | In some cases (like the page still having a valid copy on disk), | |
2504 | the kernel will handle the failure | |
2505 | transparently without affecting any applications. | |
2506 | But if there is no other up-to-date copy of the data, | |
2507 | it will kill processes to prevent any data corruptions from propagating. | |
2508 | ||
2509 | The file has one of the following values: | |
2510 | .RS | |
2511 | .IP 1: 4 | |
2512 | Kill all processes that have the corrupted-and-not-reloadable page mapped | |
2513 | as soon as the corruption is detected. | |
2514 | Note this is not supported for a few types of pages, like kernel internally | |
2515 | allocated data or the swap cache, but works for the majority of user pages. | |
2516 | .IP 0: 4 | |
2517 | Only unmap the corrupted page from all processes and only kill a process | |
2518 | who tries to access it. | |
2519 | .RE | |
2520 | .IP | |
2521 | The kill is performed using a | |
2522 | .B SIGBUS | |
2523 | signal with | |
2524 | .I si_code | |
2525 | set to | |
2526 | .BR BUS_MCEERR_AO . | |
2527 | Processes can handle this if they want to; see | |
2528 | .BR sigaction (2) | |
2529 | for more details. | |
2530 | ||
2531 | This feature is only active on architectures/platforms with advanced machine | |
2532 | check handling and depends on the hardware capabilities. | |
2533 | ||
2534 | Applications can override the | |
2535 | .I memory_failure_early_kill | |
2536 | setting individually with the | |
2537 | .BR prctl (2) | |
2538 | .B PR_MCE_KILL | |
2539 | operation. | |
2540 | .IP | |
2541 | Only present if the kernel was configured with | |
2542 | .BR CONFIG_MEMORY_FAILURE . | |
2543 | .TP | |
2544 | .IR /proc/sys/vm/memory_failure_recovery " (since Linux 2.6.32)" | |
2545 | .\" The following is based on the text in Documentation/sysctl/vm.txt | |
2546 | Enable memory failure recovery (when supported by the platform) | |
2547 | .RS | |
2548 | .IP 1: 4 | |
2549 | Attempt recovery. | |
2550 | .IP 0: 4 | |
2551 | Always panic on a memory failure. | |
2552 | .RE | |
2553 | .IP | |
2554 | Only present if the kernel was configured with | |
2555 | .BR CONFIG_MEMORY_FAILURE . | |
2556 | .TP | |
2557 | .IR /proc/sys/vm/oom_dump_tasks " (since Linux 2.6.25)" | |
2558 | .\" The following is from Documentation/sysctl/vm.txt | |
2559 | Enables a system-wide task dump (excluding kernel threads) to be | |
2560 | produced when the kernel performs an OOM-killing. | |
2561 | The dump includes the following information | |
2562 | for each task (thread, process): | |
2563 | thread ID, real user ID, thread group ID (process ID), | |
2564 | virtual memory size, resident set size, | |
2565 | the CPU that the task is scheduled on, | |
2566 | oom_adj score (see the description of | |
2567 | .IR /proc/[pid]/oom_adj ), | |
2568 | and command name. | |
2569 | This is helpful to determine why the OOM-killer was invoked | |
2570 | and to identify the rogue task that caused it. | |
2571 | ||
2572 | If this contains the value zero, this information is suppressed. | |
2573 | On very large systems with thousands of tasks, | |
2574 | it may not be feasible to dump the memory state information for each one. | |
2575 | Such systems should not be forced to incur a performance penalty in | |
2576 | OOM situations when the information may not be desired. | |
2577 | ||
2578 | If this is set to nonzero, this information is shown whenever the | |
2579 | OOM-killer actually kills a memory-hogging task. | |
2580 | ||
2581 | The default value is 0. | |
2582 | .TP | |
2583 | .IR /proc/sys/vm/oom_kill_allocating_task " (since Linux 2.6.24)" | |
2584 | .\" The following is from Documentation/sysctl/vm.txt | |
2585 | This enables or disables killing the OOM-triggering task in | |
2586 | out-of-memory situations. | |
2587 | ||
2588 | If this is set to zero, the OOM-killer will scan through the entire | |
2589 | tasklist and select a task based on heuristics to kill. | |
2590 | This normally selects a rogue memory-hogging task that | |
2591 | frees up a large amount of memory when killed. | |
2592 | ||
2593 | If this is set to nonzero, the OOM-killer simply kills the task that | |
2594 | triggered the out-of-memory condition. | |
2595 | This avoids a possibly expensive tasklist scan. | |
2596 | ||
2597 | If | |
2598 | .I /proc/sys/vm/panic_on_oom | |
2599 | is nonzero, it takes precedence over whatever value is used in | |
2600 | .IR /proc/sys/vm/oom_kill_allocating_task . | |
2601 | ||
2602 | The default value is 0. | |
2603 | .TP | |
2604 | .I /proc/sys/vm/overcommit_memory | |
2605 | This file contains the kernel virtual memory accounting mode. | |
2606 | Values are: | |
2607 | .RS | |
2608 | .IP | |
2609 | 0: heuristic overcommit (this is the default) | |
2610 | .br | |
2611 | 1: always overcommit, never check | |
2612 | .br | |
2613 | 2: always check, never overcommit | |
2614 | .RE | |
2615 | .IP | |
2616 | In mode 0, calls of | |
2617 | .BR mmap (2) | |
2618 | with | |
2619 | .B MAP_NORESERVE | |
2620 | are not checked, and the default check is very weak, | |
2621 | leading to the risk of getting a process "OOM-killed". | |
2622 | Under Linux 2.4 any nonzero value implies mode 1. | |
2623 | In mode 2 (available since Linux 2.6), the total virtual address space | |
2624 | on the system is limited to (SS + RAM*(r/100)), | |
2625 | where SS is the size of the swap space, and RAM | |
2626 | is the size of the physical memory, and r is the contents of the file | |
2627 | .IR /proc/sys/vm/overcommit_ratio . | |
2628 | .TP | |
2629 | .I /proc/sys/vm/overcommit_ratio | |
2630 | See the description of | |
2631 | .IR /proc/sys/vm/overcommit_memory . | |
2632 | .TP | |
2633 | .IR /proc/sys/vm/panic_on_oom " (since Linux 2.6.18)" | |
2634 | .\" The following is adapted from Documentation/sysctl/vm.txt | |
2635 | This enables or disables a kernel panic in | |
2636 | an out-of-memory situation. | |
2637 | ||
2638 | If this file is set to the value 0, | |
2639 | the kernel's OOM-killer will kill some rogue process. | |
2640 | Usually, the OOM-killer is able to kill a rogue process and the | |
2641 | system will survive. | |
2642 | ||
2643 | If this file is set to the value 1, | |
2644 | then the kernel normally panics when out-of-memory happens. | |
2645 | However, if a process limits allocations to certain nodes | |
2646 | using memory policies | |
2647 | .RB ( mbind (2) | |
2648 | .BR MPOL_BIND ) | |
2649 | or cpusets | |
2650 | .RB ( cpuset (7)) | |
2651 | and those nodes reach memory exhaustion status, | |
2652 | one process may be killed by the OOM-killer. | |
2653 | No panic occurs in this case: | |
2654 | because other nodes' memory may be free, | |
2655 | this means the system as a whole may not have reached | |
2656 | an out-of-memory situation yet. | |
2657 | ||
2658 | If this file is set to the value 2, | |
2659 | the kernel always panics when an out-of-memory condition occurs. | |
2660 | ||
2661 | The default value is 0. | |
2662 | 1 and 2 are for failover of clustering. | |
2663 | Select either according to your policy of failover. | |
2664 | .TP | |
2665 | .IR /proc/sys/vm/swappiness | |
2666 | .\" The following is from Documentation/sysctl/vm.txt | |
2667 | The value in this file controls how aggressively the kernel will swap | |
2668 | memory pages. | |
2669 | Higher values increase aggressiveness, lower values | |
2670 | decrease aggressiveness. | |
2671 | The default value is 60. | |
2672 | .TP | |
2673 | .IR /proc/sysrq-trigger " (since Linux 2.4.21)" | |
2674 | Writing a character to this file triggers the same SysRq function as | |
2675 | typing ALT-SysRq-<character> (see the description of | |
2676 | .IR /proc/sys/kernel/sysrq ). | |
2677 | This file is normally only writable by | |
2678 | .IR root . | |
2679 | For further details see the kernel source file | |
2680 | .IR Documentation/sysrq.txt . | |
2681 | .TP | |
2682 | .I /proc/sysvipc | |
2683 | Subdirectory containing the pseudo-files | |
2684 | .IR msg ", " sem " and " shm "." | |
2685 | These files list the System V Interprocess Communication (IPC) objects | |
2686 | (respectively: message queues, semaphores, and shared memory) | |
2687 | that currently exist on the system, | |
2688 | providing similar information to that available via | |
2689 | .BR ipcs (1). | |
2690 | These files have headers and are formatted (one IPC object per line) | |
2691 | for easy understanding. | |
2692 | .BR svipc (7) | |
2693 | provides further background on the information shown by these files. | |
2694 | .TP | |
2695 | .I /proc/tty | |
2696 | Subdirectory containing the pseudo-files and subdirectories for | |
2697 | tty drivers and line disciplines. | |
2698 | .TP | |
2699 | .I /proc/uptime | |
2700 | This file contains two numbers: the uptime of the system (seconds), | |
2701 | and the amount of time spent in idle process (seconds). | |
2702 | .TP | |
2703 | .I /proc/version | |
2704 | This string identifies the kernel version that is currently running. | |
2705 | It includes the contents of | |
2706 | .IR /proc/sys/kernel/ostype , | |
2707 | .I /proc/sys/kernel/osrelease | |
2708 | and | |
2709 | .IR /proc/sys/kernel/version . | |
2710 | For example: | |
2711 | .nf | |
2712 | .in -2 | |
2713 | .ft CW | |
2714 | Linux version 1.0.9 (quinlan@phaze) #1 Sat May 14 01:51:54 EDT 1994 | |
2715 | .ft | |
2716 | .in +2 | |
2717 | .fi | |
2718 | .\" FIXME Document /proc/timer_list | |
2719 | .\" .TP | |
2720 | .\" .IR /proc/timer_list " (since Linux 2.6.21)" | |
2721 | .\" See the 2.6.21 Change log | |
2722 | .\" FIXME Document /proc/timer_stats | |
2723 | .\" .TP | |
2724 | .\" .IR /proc/timer_stats " (since Linux 2.6.21)" | |
2725 | .\" See the 2.6.21 Change log | |
2726 | .TP | |
2727 | .IR /proc/vmstat " (since Linux 2.6)" | |
2728 | This file displays various virtual memory statistics. | |
2729 | .TP | |
2730 | .IR /proc/zoneinfo " (since Linux 2.6.13)" | |
2731 | This file display information about memory zones. | |
2732 | This is useful for analyzing virtual memory behavior. | |
2733 | .\" FIXME more should be said about /proc/zoneinfo | |
2734 | .SH NOTES | |
2735 | Many strings (i.e., the environment and command line) are in | |
2736 | the internal format, with subfields terminated by null bytes (\(aq\\0\(aq), | |
2737 | so you | |
2738 | may find that things are more readable if you use \fIod \-c\fP or \fItr | |
2739 | "\\000" "\\n"\fP to read them. | |
2740 | Alternatively, \fIecho \`cat <file>\`\fP works well. | |
2741 | ||
2742 | This manual page is incomplete, possibly inaccurate, and is the kind | |
2743 | of thing that needs to be updated very often. | |
2744 | .\" .SH ACKNOWLEDGEMENTS | |
2745 | .\" The material on /proc/sys/fs and /proc/sys/kernel is closely based on | |
2746 | .\" kernel source documentation files written by Rik van Riel. | |
2747 | .SH "SEE ALSO" | |
2748 | .BR cat (1), | |
2749 | .BR dmesg (1), | |
2750 | .BR find (1), | |
2751 | .BR free (1), | |
2752 | .BR ps (1), | |
2753 | .BR tr (1), | |
2754 | .BR uptime (1), | |
2755 | .BR chroot (2), | |
2756 | .BR mmap (2), | |
2757 | .BR readlink (2), | |
2758 | .BR syslog (2), | |
2759 | .BR slabinfo (5), | |
2760 | .BR hier (7), | |
2761 | .BR time (7), | |
2762 | .BR arp (8), | |
2763 | .BR hdparm (8), | |
2764 | .BR ifconfig (8), | |
2765 | .BR init (8), | |
2766 | .BR lsmod (8), | |
2767 | .BR lspci (8), | |
2768 | .BR mount (8), | |
2769 | .BR netstat (8), | |
2770 | .BR procinfo (8), | |
2771 | .BR route (8) | |
2772 | .br | |
2773 | The kernel source files: | |
2774 | .IR Documentation/filesystems/proc.txt , | |
2775 | .IR Documentation/sysctl/vm.txt |