linux/Documentation/sysctl/kernel.txt
<<
>>
Prefs
   1Documentation for /proc/sys/kernel/*    kernel version 2.2.10
   2        (c) 1998, 1999,  Rik van Riel <riel@nl.linux.org>
   3        (c) 2009,        Shen Feng<shen@cn.fujitsu.com>
   4
   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:
  20
  21- acct
  22- acpi_video_flags
  23- auto_msgmni
  24- bootloader_type            [ X86 only ]
  25- bootloader_version         [ X86 only ]
  26- callhome                   [ S390 only ]
  27- cap_last_cap
  28- core_pattern
  29- core_pipe_limit
  30- core_uses_pid
  31- ctrl-alt-del
  32- dmesg_restrict
  33- domainname
  34- hostname
  35- hotplug
  36- kptr_restrict
  37- kstack_depth_to_print       [ X86 only ]
  38- l2cr                        [ PPC only ]
  39- modprobe                    ==> Documentation/debugging-modules.txt
  40- modules_disabled
  41- msgmax
  42- msgmnb
  43- msgmni
  44- nmi_watchdog
  45- osrelease
  46- ostype
  47- overflowgid
  48- overflowuid
  49- panic
  50- panic_on_oops
  51- panic_on_unrecovered_nmi
  52- panic_on_stackoverflow
  53- pid_max
  54- powersave-nap               [ PPC only ]
  55- printk
  56- printk_delay
  57- printk_ratelimit
  58- printk_ratelimit_burst
  59- randomize_va_space
  60- real-root-dev               ==> Documentation/initrd.txt
  61- reboot-cmd                  [ SPARC only ]
  62- rtsig-max
  63- rtsig-nr
  64- sem
  65- sg-big-buff                 [ generic SCSI device (sg) ]
  66- shm_rmid_forced
  67- shmall
  68- shmmax                      [ sysv ipc ]
  69- shmmni
  70- softlockup_thresh
  71- stop-a                      [ SPARC only ]
  72- sysrq                       ==> Documentation/sysrq.txt
  73- tainted
  74- threads-max
  75- unknown_nmi_panic
  76- version
  77
  78==============================================================
  79
  80acct:
  81
  82highwater lowwater frequency
  83
  84If BSD-style process accounting is enabled these values control
  85its behaviour. If free space on filesystem where the log lives
  86goes below <lowwater>% accounting suspends. If free space gets
  87above <highwater>% accounting resumes. <Frequency> determines
  88how often do we check the amount of free space (value is in
  89seconds). Default:
  904 2 30
  91That is, suspend accounting if there left <= 2% free; resume it
  92if we got >=4%; consider information about amount of free space
  93valid for 30 seconds.
  94
  95==============================================================
  96
  97acpi_video_flags:
  98
  99flags
 100
 101See Doc*/kernel/power/video.txt, it allows mode of video boot to be
 102set during run time.
 103
 104==============================================================
 105
 106auto_msgmni:
 107
 108Enables/Disables automatic recomputing of msgmni upon memory add/remove
 109or upon ipc namespace creation/removal (see the msgmni description
 110above). Echoing "1" into this file enables msgmni automatic recomputing.
 111Echoing "0" turns it off. auto_msgmni default value is 1.
 112
 113
 114==============================================================
 115
 116bootloader_type:
 117
 118x86 bootloader identification
 119
 120This gives the bootloader type number as indicated by the bootloader,
 121shifted left by 4, and OR'd with the low four bits of the bootloader
 122version.  The reason for this encoding is that this used to match the
 123type_of_loader field in the kernel header; the encoding is kept for
 124backwards compatibility.  That is, if the full bootloader type number
 125is 0x15 and the full version number is 0x234, this file will contain
 126the value 340 = 0x154.
 127
 128See the type_of_loader and ext_loader_type fields in
 129Documentation/x86/boot.txt for additional information.
 130
 131==============================================================
 132
 133bootloader_version:
 134
 135x86 bootloader version
 136
 137The complete bootloader version number.  In the example above, this
 138file will contain the value 564 = 0x234.
 139
 140See the type_of_loader and ext_loader_ver fields in
 141Documentation/x86/boot.txt for additional information.
 142
 143==============================================================
 144
 145callhome:
 146
 147Controls the kernel's callhome behavior in case of a kernel panic.
 148
 149The s390 hardware allows an operating system to send a notification
 150to a service organization (callhome) in case of an operating system panic.
 151
 152When the value in this file is 0 (which is the default behavior)
 153nothing happens in case of a kernel panic. If this value is set to "1"
 154the complete kernel oops message is send to the IBM customer service
 155organization in case the mainframe the Linux operating system is running
 156on has a service contract with IBM.
 157
 158==============================================================
 159
 160cap_last_cap
 161
 162Highest valid capability of the running kernel.  Exports
 163CAP_LAST_CAP from the kernel.
 164
 165==============================================================
 166
 167core_pattern:
 168
 169core_pattern is used to specify a core dumpfile pattern name.
 170. max length 128 characters; default value is "core"
 171. core_pattern is used as a pattern template for the output filename;
 172  certain string patterns (beginning with '%') are substituted with
 173  their actual values.
 174. backward compatibility with core_uses_pid:
 175        If core_pattern does not include "%p" (default does not)
 176        and core_uses_pid is set, then .PID will be appended to
 177        the filename.
 178. corename format specifiers:
 179        %<NUL>  '%' is dropped
 180        %%      output one '%'
 181        %p      pid
 182        %u      uid
 183        %g      gid
 184        %s      signal number
 185        %t      UNIX time of dump
 186        %h      hostname
 187        %e      executable filename (may be shortened)
 188        %E      executable path
 189        %<OTHER> both are dropped
 190. If the first character of the pattern is a '|', the kernel will treat
 191  the rest of the pattern as a command to run.  The core dump will be
 192  written to the standard input of that program instead of to a file.
 193
 194==============================================================
 195
 196core_pipe_limit:
 197
 198This sysctl is only applicable when core_pattern is configured to pipe
 199core files to a user space helper (when the first character of
 200core_pattern is a '|', see above).  When collecting cores via a pipe
 201to an application, it is occasionally useful for the collecting
 202application to gather data about the crashing process from its
 203/proc/pid directory.  In order to do this safely, the kernel must wait
 204for the collecting process to exit, so as not to remove the crashing
 205processes proc files prematurely.  This in turn creates the
 206possibility that a misbehaving userspace collecting process can block
 207the reaping of a crashed process simply by never exiting.  This sysctl
 208defends against that.  It defines how many concurrent crashing
 209processes may be piped to user space applications in parallel.  If
 210this value is exceeded, then those crashing processes above that value
 211are noted via the kernel log and their cores are skipped.  0 is a
 212special value, indicating that unlimited processes may be captured in
 213parallel, but that no waiting will take place (i.e. the collecting
 214process is not guaranteed access to /proc/<crashing pid>/).  This
 215value defaults to 0.
 216
 217==============================================================
 218
 219core_uses_pid:
 220
 221The default coredump filename is "core".  By setting
 222core_uses_pid to 1, the coredump filename becomes core.PID.
 223If core_pattern does not include "%p" (default does not)
 224and core_uses_pid is set, then .PID will be appended to
 225the filename.
 226
 227==============================================================
 228
 229ctrl-alt-del:
 230
 231When the value in this file is 0, ctrl-alt-del is trapped and
 232sent to the init(1) program to handle a graceful restart.
 233When, however, the value is > 0, Linux's reaction to a Vulcan
 234Nerve Pinch (tm) will be an immediate reboot, without even
 235syncing its dirty buffers.
 236
 237Note: when a program (like dosemu) has the keyboard in 'raw'
 238mode, the ctrl-alt-del is intercepted by the program before it
 239ever reaches the kernel tty layer, and it's up to the program
 240to decide what to do with it.
 241
 242==============================================================
 243
 244dmesg_restrict:
 245
 246This toggle indicates whether unprivileged users are prevented
 247from using dmesg(8) to view messages from the kernel's log buffer.
 248When dmesg_restrict is set to (0) there are no restrictions. When
 249dmesg_restrict is set set to (1), users must have CAP_SYSLOG to use
 250dmesg(8).
 251
 252The kernel config option CONFIG_SECURITY_DMESG_RESTRICT sets the
 253default value of dmesg_restrict.
 254
 255==============================================================
 256
 257domainname & hostname:
 258
 259These files can be used to set the NIS/YP domainname and the
 260hostname of your box in exactly the same way as the commands
 261domainname and hostname, i.e.:
 262# echo "darkstar" > /proc/sys/kernel/hostname
 263# echo "mydomain" > /proc/sys/kernel/domainname
 264has the same effect as
 265# hostname "darkstar"
 266# domainname "mydomain"
 267
 268Note, however, that the classic darkstar.frop.org has the
 269hostname "darkstar" and DNS (Internet Domain Name Server)
 270domainname "frop.org", not to be confused with the NIS (Network
 271Information Service) or YP (Yellow Pages) domainname. These two
 272domain names are in general different. For a detailed discussion
 273see the hostname(1) man page.
 274
 275==============================================================
 276
 277hotplug:
 278
 279Path for the hotplug policy agent.
 280Default value is "/sbin/hotplug".
 281
 282==============================================================
 283
 284kptr_restrict:
 285
 286This toggle indicates whether restrictions are placed on
 287exposing kernel addresses via /proc and other interfaces.  When
 288kptr_restrict is set to (0), there are no restrictions.  When
 289kptr_restrict is set to (1), the default, kernel pointers
 290printed using the %pK format specifier will be replaced with 0's
 291unless the user has CAP_SYSLOG.  When kptr_restrict is set to
 292(2), kernel pointers printed using %pK will be replaced with 0's
 293regardless of privileges.
 294
 295==============================================================
 296
 297kstack_depth_to_print: (X86 only)
 298
 299Controls the number of words to print when dumping the raw
 300kernel stack.
 301
 302==============================================================
 303
 304l2cr: (PPC only)
 305
 306This flag controls the L2 cache of G3 processor boards. If
 3070, the cache is disabled. Enabled if nonzero.
 308
 309==============================================================
 310
 311modules_disabled:
 312
 313A toggle value indicating if modules are allowed to be loaded
 314in an otherwise modular kernel.  This toggle defaults to off
 315(0), but can be set true (1).  Once true, modules can be
 316neither loaded nor unloaded, and the toggle cannot be set back
 317to false.
 318
 319==============================================================
 320
 321nmi_watchdog:
 322
 323Enables/Disables the NMI watchdog on x86 systems. When the value is
 324non-zero the NMI watchdog is enabled and will continuously test all
 325online cpus to determine whether or not they are still functioning
 326properly. Currently, passing "nmi_watchdog=" parameter at boot time is
 327required for this function to work.
 328
 329If LAPIC NMI watchdog method is in use (nmi_watchdog=2 kernel
 330parameter), the NMI watchdog shares registers with oprofile. By
 331disabling the NMI watchdog, oprofile may have more registers to
 332utilize.
 333
 334==============================================================
 335
 336osrelease, ostype & version:
 337
 338# cat osrelease
 3392.1.88
 340# cat ostype
 341Linux
 342# cat version
 343#5 Wed Feb 25 21:49:24 MET 1998
 344
 345The files osrelease and ostype should be clear enough. Version
 346needs a little more clarification however. The '#5' means that
 347this is the fifth kernel built from this source base and the
 348date behind it indicates the time the kernel was built.
 349The only way to tune these values is to rebuild the kernel :-)
 350
 351==============================================================
 352
 353overflowgid & overflowuid:
 354
 355if your architecture did not always support 32-bit UIDs (i.e. arm,
 356i386, m68k, sh, and sparc32), a fixed UID and GID will be returned to
 357applications that use the old 16-bit UID/GID system calls, if the
 358actual UID or GID would exceed 65535.
 359
 360These sysctls allow you to change the value of the fixed UID and GID.
 361The default is 65534.
 362
 363==============================================================
 364
 365panic:
 366
 367The value in this file represents the number of seconds the kernel
 368waits before rebooting on a panic. When you use the software watchdog,
 369the recommended setting is 60.
 370
 371==============================================================
 372
 373panic_on_unrecovered_nmi:
 374
 375The default Linux behaviour on an NMI of either memory or unknown is
 376to continue operation. For many environments such as scientific
 377computing it is preferable that the box is taken out and the error
 378dealt with than an uncorrected parity/ECC error get propagated.
 379
 380A small number of systems do generate NMI's for bizarre random reasons
 381such as power management so the default is off. That sysctl works like
 382the existing panic controls already in that directory.
 383
 384==============================================================
 385
 386panic_on_oops:
 387
 388Controls the kernel's behaviour when an oops or BUG is encountered.
 389
 3900: try to continue operation
 391
 3921: panic immediately.  If the `panic' sysctl is also non-zero then the
 393   machine will be rebooted.
 394
 395==============================================================
 396
 397panic_on_stackoverflow:
 398
 399Controls the kernel's behavior when detecting the overflows of
 400kernel, IRQ and exception stacks except a user stack.
 401This file shows up if CONFIG_DEBUG_STACKOVERFLOW is enabled.
 402
 4030: try to continue operation.
 404
 4051: panic immediately.
 406
 407==============================================================
 408
 409
 410pid_max:
 411
 412PID allocation wrap value.  When the kernel's next PID value
 413reaches this value, it wraps back to a minimum PID value.
 414PIDs of value pid_max or larger are not allocated.
 415
 416==============================================================
 417
 418ns_last_pid:
 419
 420The last pid allocated in the current (the one task using this sysctl
 421lives in) pid namespace. When selecting a pid for a next task on fork
 422kernel tries to allocate a number starting from this one.
 423
 424==============================================================
 425
 426powersave-nap: (PPC only)
 427
 428If set, Linux-PPC will use the 'nap' mode of powersaving,
 429otherwise the 'doze' mode will be used.
 430
 431==============================================================
 432
 433printk:
 434
 435The four values in printk denote: console_loglevel,
 436default_message_loglevel, minimum_console_loglevel and
 437default_console_loglevel respectively.
 438
 439These values influence printk() behavior when printing or
 440logging error messages. See 'man 2 syslog' for more info on
 441the different loglevels.
 442
 443- console_loglevel: messages with a higher priority than
 444  this will be printed to the console
 445- default_message_loglevel: messages without an explicit priority
 446  will be printed with this priority
 447- minimum_console_loglevel: minimum (highest) value to which
 448  console_loglevel can be set
 449- default_console_loglevel: default value for console_loglevel
 450
 451==============================================================
 452
 453printk_delay:
 454
 455Delay each printk message in printk_delay milliseconds
 456
 457Value from 0 - 10000 is allowed.
 458
 459==============================================================
 460
 461printk_ratelimit:
 462
 463Some warning messages are rate limited. printk_ratelimit specifies
 464the minimum length of time between these messages (in jiffies), by
 465default we allow one every 5 seconds.
 466
 467A value of 0 will disable rate limiting.
 468
 469==============================================================
 470
 471printk_ratelimit_burst:
 472
 473While long term we enforce one message per printk_ratelimit
 474seconds, we do allow a burst of messages to pass through.
 475printk_ratelimit_burst specifies the number of messages we can
 476send before ratelimiting kicks in.
 477
 478==============================================================
 479
 480randomize_va_space:
 481
 482This option can be used to select the type of process address
 483space randomization that is used in the system, for architectures
 484that support this feature.
 485
 4860 - Turn the process address space randomization off.  This is the
 487    default for architectures that do not support this feature anyways,
 488    and kernels that are booted with the "norandmaps" parameter.
 489
 4901 - Make the addresses of mmap base, stack and VDSO page randomized.
 491    This, among other things, implies that shared libraries will be
 492    loaded to random addresses.  Also for PIE-linked binaries, the
 493    location of code start is randomized.  This is the default if the
 494    CONFIG_COMPAT_BRK option is enabled.
 495
 4962 - Additionally enable heap randomization.  This is the default if
 497    CONFIG_COMPAT_BRK is disabled.
 498
 499    There are a few legacy applications out there (such as some ancient
 500    versions of libc.so.5 from 1996) that assume that brk area starts
 501    just after the end of the code+bss.  These applications break when
 502    start of the brk area is randomized.  There are however no known
 503    non-legacy applications that would be broken this way, so for most
 504    systems it is safe to choose full randomization.
 505
 506    Systems with ancient and/or broken binaries should be configured
 507    with CONFIG_COMPAT_BRK enabled, which excludes the heap from process
 508    address space randomization.
 509
 510==============================================================
 511
 512reboot-cmd: (Sparc only)
 513
 514??? This seems to be a way to give an argument to the Sparc
 515ROM/Flash boot loader. Maybe to tell it what to do after
 516rebooting. ???
 517
 518==============================================================
 519
 520rtsig-max & rtsig-nr:
 521
 522The file rtsig-max can be used to tune the maximum number
 523of POSIX realtime (queued) signals that can be outstanding
 524in the system.
 525
 526rtsig-nr shows the number of RT signals currently queued.
 527
 528==============================================================
 529
 530sg-big-buff:
 531
 532This file shows the size of the generic SCSI (sg) buffer.
 533You can't tune it just yet, but you could change it on
 534compile time by editing include/scsi/sg.h and changing
 535the value of SG_BIG_BUFF.
 536
 537There shouldn't be any reason to change this value. If
 538you can come up with one, you probably know what you
 539are doing anyway :)
 540
 541==============================================================
 542
 543shmmax:
 544
 545This value can be used to query and set the run time limit
 546on the maximum shared memory segment size that can be created.
 547Shared memory segments up to 1Gb are now supported in the
 548kernel.  This value defaults to SHMMAX.
 549
 550==============================================================
 551
 552shm_rmid_forced:
 553
 554Linux lets you set resource limits, including how much memory one
 555process can consume, via setrlimit(2).  Unfortunately, shared memory
 556segments are allowed to exist without association with any process, and
 557thus might not be counted against any resource limits.  If enabled,
 558shared memory segments are automatically destroyed when their attach
 559count becomes zero after a detach or a process termination.  It will
 560also destroy segments that were created, but never attached to, on exit
 561from the process.  The only use left for IPC_RMID is to immediately
 562destroy an unattached segment.  Of course, this breaks the way things are
 563defined, so some applications might stop working.  Note that this
 564feature will do you no good unless you also configure your resource
 565limits (in particular, RLIMIT_AS and RLIMIT_NPROC).  Most systems don't
 566need this.
 567
 568Note that if you change this from 0 to 1, already created segments
 569without users and with a dead originative process will be destroyed.
 570
 571==============================================================
 572
 573softlockup_thresh:
 574
 575This value can be used to lower the softlockup tolerance threshold.  The
 576default threshold is 60 seconds.  If a cpu is locked up for 60 seconds,
 577the kernel complains.  Valid values are 1-60 seconds.  Setting this
 578tunable to zero will disable the softlockup detection altogether.
 579
 580==============================================================
 581
 582tainted:
 583
 584Non-zero if the kernel has been tainted.  Numeric values, which
 585can be ORed together:
 586
 587   1 - A module with a non-GPL license has been loaded, this
 588       includes modules with no license.
 589       Set by modutils >= 2.4.9 and module-init-tools.
 590   2 - A module was force loaded by insmod -f.
 591       Set by modutils >= 2.4.9 and module-init-tools.
 592   4 - Unsafe SMP processors: SMP with CPUs not designed for SMP.
 593   8 - A module was forcibly unloaded from the system by rmmod -f.
 594  16 - A hardware machine check error occurred on the system.
 595  32 - A bad page was discovered on the system.
 596  64 - The user has asked that the system be marked "tainted".  This
 597       could be because they are running software that directly modifies
 598       the hardware, or for other reasons.
 599 128 - The system has died.
 600 256 - The ACPI DSDT has been overridden with one supplied by the user
 601        instead of using the one provided by the hardware.
 602 512 - A kernel warning has occurred.
 6031024 - A module from drivers/staging was loaded.
 6042048 - The system is working around a severe firmware bug.
 6054096 - An out-of-tree module has been loaded.
 606
 607==============================================================
 608
 609unknown_nmi_panic:
 610
 611The value in this file affects behavior of handling NMI. When the
 612value is non-zero, unknown NMI is trapped and then panic occurs. At
 613that time, kernel debugging information is displayed on console.
 614
 615NMI switch that most IA32 servers have fires unknown NMI up, for
 616example.  If a system hangs up, try pressing the NMI switch.
 617
lxr.linux.no kindly hosted by Redpill Linpro AS, provider of Linux consulting and operations services since 1995.