blob: 2dbff53369d0ea734b7a3c4c446d70d5297c8dc2 [file] [log] [blame]
Linus Torvalds1da177e2005-04-16 15:20:36 -07001Documentation for /proc/sys/kernel/* kernel version 2.2.10
2 (c) 1998, 1999, Rik van Riel <riel@nl.linux.org>
Shen Feng760df932009-04-02 16:57:20 -07003 (c) 2009, Shen Feng<shen@cn.fujitsu.com>
Linus Torvalds1da177e2005-04-16 15:20:36 -07004
5For general info and legal blurb, please look in README.
6
7==============================================================
8
9This file contains documentation for the sysctl files in
10/proc/sys/kernel/ and is valid for Linux kernel version 2.2.
11
12The files in this directory can be used to tune and monitor
13miscellaneous and general things in the operation of the Linux
14kernel. Since some of the files _can_ be used to screw up your
15system, it is advisable to read both documentation and source
16before actually making adjustments.
17
18Currently, these files might (depending on your configuration)
19show up in /proc/sys/kernel:
Pavel Machekc255d842006-02-20 18:27:58 -080020- acpi_video_flags
Linus Torvalds1da177e2005-04-16 15:20:36 -070021- acct
Hans-Joachim Pichtc114728a2009-09-11 10:28:47 +020022- callhome [ S390 only ]
Shen Feng760df932009-04-02 16:57:20 -070023- auto_msgmni
Linus Torvalds1da177e2005-04-16 15:20:36 -070024- core_pattern
25- core_uses_pid
26- ctrl-alt-del
27- dentry-state
28- domainname
29- hostname
30- hotplug
31- java-appletviewer [ binfmt_java, obsolete ]
32- java-interpreter [ binfmt_java, obsolete ]
Chuck Ebbert0741f4d2006-12-07 02:14:11 +010033- kstack_depth_to_print [ X86 only ]
Linus Torvalds1da177e2005-04-16 15:20:36 -070034- l2cr [ PPC only ]
Michael Opdenackerac76cff2008-02-13 15:03:32 -080035- modprobe ==> Documentation/debugging-modules.txt
Kees Cook3d433212009-04-02 15:49:29 -070036- modules_disabled
Linus Torvalds1da177e2005-04-16 15:20:36 -070037- msgmax
38- msgmnb
39- msgmni
Shen Feng760df932009-04-02 16:57:20 -070040- nmi_watchdog
Linus Torvalds1da177e2005-04-16 15:20:36 -070041- osrelease
42- ostype
43- overflowgid
44- overflowuid
45- panic
46- pid_max
47- powersave-nap [ PPC only ]
Shen Feng760df932009-04-02 16:57:20 -070048- panic_on_unrecovered_nmi
Linus Torvalds1da177e2005-04-16 15:20:36 -070049- printk
Jiri Kosina1ec7fd52008-02-09 23:24:08 +010050- randomize_va_space
Linus Torvalds1da177e2005-04-16 15:20:36 -070051- real-root-dev ==> Documentation/initrd.txt
52- reboot-cmd [ SPARC only ]
53- rtsig-max
54- rtsig-nr
55- sem
56- sg-big-buff [ generic SCSI device (sg) ]
57- shmall
58- shmmax [ sysv ipc ]
59- shmmni
60- stop-a [ SPARC only ]
61- sysrq ==> Documentation/sysrq.txt
62- tainted
63- threads-max
Shen Feng760df932009-04-02 16:57:20 -070064- unknown_nmi_panic
Linus Torvalds1da177e2005-04-16 15:20:36 -070065- version
66
67==============================================================
68
Pavel Machekc255d842006-02-20 18:27:58 -080069acpi_video_flags:
70
71flags
72
73See Doc*/kernel/power/video.txt, it allows mode of video boot to be
74set during run time.
75
76==============================================================
77
Linus Torvalds1da177e2005-04-16 15:20:36 -070078acct:
79
80highwater lowwater frequency
81
82If BSD-style process accounting is enabled these values control
83its behaviour. If free space on filesystem where the log lives
84goes below <lowwater>% accounting suspends. If free space gets
85above <highwater>% accounting resumes. <Frequency> determines
86how often do we check the amount of free space (value is in
87seconds). Default:
884 2 30
89That is, suspend accounting if there left <= 2% free; resume it
90if we got >=4%; consider information about amount of free space
91valid for 30 seconds.
92
93==============================================================
94
Hans-Joachim Pichtc114728a2009-09-11 10:28:47 +020095callhome:
96
97Controls the kernel's callhome behavior in case of a kernel panic.
98
99The s390 hardware allows an operating system to send a notification
100to a service organization (callhome) in case of an operating system panic.
101
102When the value in this file is 0 (which is the default behavior)
103nothing happens in case of a kernel panic. If this value is set to "1"
104the complete kernel oops message is send to the IBM customer service
105organization in case the mainframe the Linux operating system is running
106on has a service contract with IBM.
107
108==============================================================
109
Linus Torvalds1da177e2005-04-16 15:20:36 -0700110core_pattern:
111
112core_pattern is used to specify a core dumpfile pattern name.
Matthias Urlichscd081042006-10-11 01:21:57 -0700113. max length 128 characters; default value is "core"
Linus Torvalds1da177e2005-04-16 15:20:36 -0700114. core_pattern is used as a pattern template for the output filename;
115 certain string patterns (beginning with '%') are substituted with
116 their actual values.
117. backward compatibility with core_uses_pid:
118 If core_pattern does not include "%p" (default does not)
119 and core_uses_pid is set, then .PID will be appended to
120 the filename.
121. corename format specifiers:
122 %<NUL> '%' is dropped
123 %% output one '%'
124 %p pid
125 %u uid
126 %g gid
127 %s signal number
128 %t UNIX time of dump
129 %h hostname
130 %e executable filename
131 %<OTHER> both are dropped
Matthias Urlichscd081042006-10-11 01:21:57 -0700132. If the first character of the pattern is a '|', the kernel will treat
133 the rest of the pattern as a command to run. The core dump will be
134 written to the standard input of that program instead of to a file.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700135
136==============================================================
137
138core_uses_pid:
139
140The default coredump filename is "core". By setting
141core_uses_pid to 1, the coredump filename becomes core.PID.
142If core_pattern does not include "%p" (default does not)
143and core_uses_pid is set, then .PID will be appended to
144the filename.
145
146==============================================================
147
148ctrl-alt-del:
149
150When the value in this file is 0, ctrl-alt-del is trapped and
151sent to the init(1) program to handle a graceful restart.
152When, however, the value is > 0, Linux's reaction to a Vulcan
153Nerve Pinch (tm) will be an immediate reboot, without even
154syncing its dirty buffers.
155
156Note: when a program (like dosemu) has the keyboard in 'raw'
157mode, the ctrl-alt-del is intercepted by the program before it
158ever reaches the kernel tty layer, and it's up to the program
159to decide what to do with it.
160
161==============================================================
162
163domainname & hostname:
164
165These files can be used to set the NIS/YP domainname and the
166hostname of your box in exactly the same way as the commands
167domainname and hostname, i.e.:
168# echo "darkstar" > /proc/sys/kernel/hostname
169# echo "mydomain" > /proc/sys/kernel/domainname
170has the same effect as
171# hostname "darkstar"
172# domainname "mydomain"
173
174Note, however, that the classic darkstar.frop.org has the
175hostname "darkstar" and DNS (Internet Domain Name Server)
176domainname "frop.org", not to be confused with the NIS (Network
177Information Service) or YP (Yellow Pages) domainname. These two
178domain names are in general different. For a detailed discussion
179see the hostname(1) man page.
180
181==============================================================
182
183hotplug:
184
185Path for the hotplug policy agent.
186Default value is "/sbin/hotplug".
187
188==============================================================
189
190l2cr: (PPC only)
191
192This flag controls the L2 cache of G3 processor boards. If
1930, the cache is disabled. Enabled if nonzero.
194
195==============================================================
196
Chuck Ebbert0741f4d2006-12-07 02:14:11 +0100197kstack_depth_to_print: (X86 only)
198
199Controls the number of words to print when dumping the raw
200kernel stack.
201
202==============================================================
203
Kees Cook3d433212009-04-02 15:49:29 -0700204modules_disabled:
205
206A toggle value indicating if modules are allowed to be loaded
207in an otherwise modular kernel. This toggle defaults to off
208(0), but can be set true (1). Once true, modules can be
209neither loaded nor unloaded, and the toggle cannot be set back
210to false.
211
212==============================================================
213
Linus Torvalds1da177e2005-04-16 15:20:36 -0700214osrelease, ostype & version:
215
216# cat osrelease
2172.1.88
218# cat ostype
219Linux
220# cat version
221#5 Wed Feb 25 21:49:24 MET 1998
222
223The files osrelease and ostype should be clear enough. Version
224needs a little more clarification however. The '#5' means that
225this is the fifth kernel built from this source base and the
226date behind it indicates the time the kernel was built.
227The only way to tune these values is to rebuild the kernel :-)
228
229==============================================================
230
231overflowgid & overflowuid:
232
233if your architecture did not always support 32-bit UIDs (i.e. arm, i386,
234m68k, sh, and sparc32), a fixed UID and GID will be returned to
235applications that use the old 16-bit UID/GID system calls, if the actual
236UID or GID would exceed 65535.
237
238These sysctls allow you to change the value of the fixed UID and GID.
239The default is 65534.
240
241==============================================================
242
243panic:
244
245The value in this file represents the number of seconds the
246kernel waits before rebooting on a panic. When you use the
247software watchdog, the recommended setting is 60.
248
249==============================================================
250
251panic_on_oops:
252
253Controls the kernel's behaviour when an oops or BUG is encountered.
254
2550: try to continue operation
256
Matt LaPlantea982ac02007-05-09 07:35:06 +02002571: panic immediately. If the `panic' sysctl is also non-zero then the
Maxime Bizon8b23d04d2006-08-05 12:14:32 -0700258 machine will be rebooted.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700259
260==============================================================
261
262pid_max:
263
Robert P. J. Daybeb7dd82007-05-09 07:14:03 +0200264PID allocation wrap value. When the kernel's next PID value
Linus Torvalds1da177e2005-04-16 15:20:36 -0700265reaches this value, it wraps back to a minimum PID value.
266PIDs of value pid_max or larger are not allocated.
267
268==============================================================
269
270powersave-nap: (PPC only)
271
272If set, Linux-PPC will use the 'nap' mode of powersaving,
273otherwise the 'doze' mode will be used.
274
275==============================================================
276
277printk:
278
279The four values in printk denote: console_loglevel,
280default_message_loglevel, minimum_console_loglevel and
281default_console_loglevel respectively.
282
283These values influence printk() behavior when printing or
284logging error messages. See 'man 2 syslog' for more info on
285the different loglevels.
286
287- console_loglevel: messages with a higher priority than
288 this will be printed to the console
289- default_message_level: messages without an explicit priority
290 will be printed with this priority
291- minimum_console_loglevel: minimum (highest) value to which
292 console_loglevel can be set
293- default_console_loglevel: default value for console_loglevel
294
295==============================================================
296
297printk_ratelimit:
298
299Some warning messages are rate limited. printk_ratelimit specifies
300the minimum length of time between these messages (in jiffies), by
301default we allow one every 5 seconds.
302
303A value of 0 will disable rate limiting.
304
305==============================================================
306
307printk_ratelimit_burst:
308
309While long term we enforce one message per printk_ratelimit
310seconds, we do allow a burst of messages to pass through.
311printk_ratelimit_burst specifies the number of messages we can
312send before ratelimiting kicks in.
313
314==============================================================
315
Jiri Kosina1ec7fd52008-02-09 23:24:08 +0100316randomize-va-space:
317
318This option can be used to select the type of process address
319space randomization that is used in the system, for architectures
320that support this feature.
321
3220 - Turn the process address space randomization off by default.
323
3241 - Make the addresses of mmap base, stack and VDSO page randomized.
325 This, among other things, implies that shared libraries will be
326 loaded to random addresses. Also for PIE-linked binaries, the location
327 of code start is randomized.
328
329 With heap randomization, the situation is a little bit more
330 complicated.
331 There a few legacy applications out there (such as some ancient
332 versions of libc.so.5 from 1996) that assume that brk area starts
333 just after the end of the code+bss. These applications break when
334 start of the brk area is randomized. There are however no known
335 non-legacy applications that would be broken this way, so for most
336 systems it is safe to choose full randomization. However there is
337 a CONFIG_COMPAT_BRK option for systems with ancient and/or broken
338 binaries, that makes heap non-randomized, but keeps all other
339 parts of process address space randomized if randomize_va_space
340 sysctl is turned on.
341
342==============================================================
343
Linus Torvalds1da177e2005-04-16 15:20:36 -0700344reboot-cmd: (Sparc only)
345
346??? This seems to be a way to give an argument to the Sparc
347ROM/Flash boot loader. Maybe to tell it what to do after
348rebooting. ???
349
350==============================================================
351
352rtsig-max & rtsig-nr:
353
354The file rtsig-max can be used to tune the maximum number
355of POSIX realtime (queued) signals that can be outstanding
356in the system.
357
358rtsig-nr shows the number of RT signals currently queued.
359
360==============================================================
361
362sg-big-buff:
363
364This file shows the size of the generic SCSI (sg) buffer.
365You can't tune it just yet, but you could change it on
366compile time by editing include/scsi/sg.h and changing
367the value of SG_BIG_BUFF.
368
369There shouldn't be any reason to change this value. If
370you can come up with one, you probably know what you
371are doing anyway :)
372
373==============================================================
374
375shmmax:
376
377This value can be used to query and set the run time limit
378on the maximum shared memory segment size that can be created.
379Shared memory segments up to 1Gb are now supported in the
380kernel. This value defaults to SHMMAX.
381
382==============================================================
383
Ravikiran G Thirumalaic4f3b632007-10-16 23:26:09 -0700384softlockup_thresh:
385
Andrew Mortonb4d19cc2008-09-22 13:57:51 -0700386This value can be used to lower the softlockup tolerance threshold. The
387default threshold is 60 seconds. If a cpu is locked up for 60 seconds,
388the kernel complains. Valid values are 1-60 seconds. Setting this
389tunable to zero will disable the softlockup detection altogether.
Ravikiran G Thirumalaic4f3b632007-10-16 23:26:09 -0700390
391==============================================================
392
Linus Torvalds1da177e2005-04-16 15:20:36 -0700393tainted:
394
395Non-zero if the kernel has been tainted. Numeric values, which
396can be ORed together:
397
Greg Kroah-Hartmanbb206982008-10-17 15:01:07 -0700398 1 - A module with a non-GPL license has been loaded, this
399 includes modules with no license.
400 Set by modutils >= 2.4.9 and module-init-tools.
401 2 - A module was force loaded by insmod -f.
402 Set by modutils >= 2.4.9 and module-init-tools.
403 4 - Unsafe SMP processors: SMP with CPUs not designed for SMP.
404 8 - A module was forcibly unloaded from the system by rmmod -f.
405 16 - A hardware machine check error occurred on the system.
406 32 - A bad page was discovered on the system.
407 64 - The user has asked that the system be marked "tainted". This
408 could be because they are running software that directly modifies
409 the hardware, or for other reasons.
410 128 - The system has died.
411 256 - The ACPI DSDT has been overridden with one supplied by the user
412 instead of using the one provided by the hardware.
413 512 - A kernel warning has occurred.
4141024 - A module from drivers/staging was loaded.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700415
Shen Feng760df932009-04-02 16:57:20 -0700416==============================================================
417
418auto_msgmni:
419
420Enables/Disables automatic recomputing of msgmni upon memory add/remove or
421upon ipc namespace creation/removal (see the msgmni description above).
422Echoing "1" into this file enables msgmni automatic recomputing.
423Echoing "0" turns it off.
424auto_msgmni default value is 1.
425
426==============================================================
427
428nmi_watchdog:
429
430Enables/Disables the NMI watchdog on x86 systems. When the value is non-zero
431the NMI watchdog is enabled and will continuously test all online cpus to
432determine whether or not they are still functioning properly. Currently,
433passing "nmi_watchdog=" parameter at boot time is required for this function
434to work.
435
436If LAPIC NMI watchdog method is in use (nmi_watchdog=2 kernel parameter), the
437NMI watchdog shares registers with oprofile. By disabling the NMI watchdog,
438oprofile may have more registers to utilize.
439
440==============================================================
441
442unknown_nmi_panic:
443
444The value in this file affects behavior of handling NMI. When the value is
445non-zero, unknown NMI is trapped and then panic occurs. At that time, kernel
446debugging information is displayed on console.
447
448NMI switch that most IA32 servers have fires unknown NMI up, for example.
449If a system hangs up, try pressing the NMI switch.
450
451==============================================================
452
453panic_on_unrecovered_nmi:
454
455The default Linux behaviour on an NMI of either memory or unknown is to continue
456operation. For many environments such as scientific computing it is preferable
457that the box is taken out and the error dealt with than an uncorrected
458parity/ECC error get propogated.
459
460A small number of systems do generate NMI's for bizarre random reasons such as
461power management so the default is off. That sysctl works like the existing
462panic controls already in that directory.
463