tjh.dev
Linux kernel mirror (for testing)
git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel
os
linux
1------------------------------------------------------------------------------
2 T H E /proc F I L E S Y S T E M
3------------------------------------------------------------------------------
4/proc/sys Terrehon Bowden <terrehon@pacbell.net> October 7 1999
5 Bodo Bauer <bb@ricochet.net>
6
72.4.x update Jorge Nerin <comandante@zaralinux.com> November 14 2000
8move /proc/sys Shen Feng <shen@cn.fujitsu.com> April 1 2009
9------------------------------------------------------------------------------
10Version 1.3 Kernel version 2.2.12
11 Kernel version 2.4.0-test11-pre4
12------------------------------------------------------------------------------
13fixes/update part 1.1 Stefani Seibold <stefani@seibold.net> June 9 2009
14
15Table of Contents
16-----------------
17
18 0 Preface
19 0.1 Introduction/Credits
20 0.2 Legal Stuff
21
22 1 Collecting System Information
23 1.1 Process-Specific Subdirectories
24 1.2 Kernel data
25 1.3 IDE devices in /proc/ide
26 1.4 Networking info in /proc/net
27 1.5 SCSI info
28 1.6 Parallel port info in /proc/parport
29 1.7 TTY info in /proc/tty
30 1.8 Miscellaneous kernel statistics in /proc/stat
31 1.9 Ext4 file system parameters
32
33 2 Modifying System Parameters
34
35 3 Per-Process Parameters
36 3.1 /proc/<pid>/oom_adj - Adjust the oom-killer score
37 3.2 /proc/<pid>/oom_score - Display current oom-killer score
38 3.3 /proc/<pid>/io - Display the IO accounting fields
39 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings
40 3.5 /proc/<pid>/mountinfo - Information about mounts
41 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm
42
43
44------------------------------------------------------------------------------
45Preface
46------------------------------------------------------------------------------
47
480.1 Introduction/Credits
49------------------------
50
51This documentation is part of a soon (or so we hope) to be released book on
52the SuSE Linux distribution. As there is no complete documentation for the
53/proc file system and we've used many freely available sources to write these
54chapters, it seems only fair to give the work back to the Linux community.
55This work is based on the 2.2.* kernel version and the upcoming 2.4.*. I'm
56afraid it's still far from complete, but we hope it will be useful. As far as
57we know, it is the first 'all-in-one' document about the /proc file system. It
58is focused on the Intel x86 hardware, so if you are looking for PPC, ARM,
59SPARC, AXP, etc., features, you probably won't find what you are looking for.
60It also only covers IPv4 networking, not IPv6 nor other protocols - sorry. But
61additions and patches are welcome and will be added to this document if you
62mail them to Bodo.
63
64We'd like to thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of
65other people for help compiling this documentation. We'd also like to extend a
66special thank you to Andi Kleen for documentation, which we relied on heavily
67to create this document, as well as the additional information he provided.
68Thanks to everybody else who contributed source or docs to the Linux kernel
69and helped create a great piece of software... :)
70
71If you have any comments, corrections or additions, please don't hesitate to
72contact Bodo Bauer at bb@ricochet.net. We'll be happy to add them to this
73document.
74
75The latest version of this document is available online at
76http://skaro.nightcrawler.com/~bb/Docs/Proc as HTML version.
77
78If the above direction does not works for you, ypu could try the kernel
79mailing list at linux-kernel@vger.kernel.org and/or try to reach me at
80comandante@zaralinux.com.
81
820.2 Legal Stuff
83---------------
84
85We don't guarantee the correctness of this document, and if you come to us
86complaining about how you screwed up your system because of incorrect
87documentation, we won't feel responsible...
88
89------------------------------------------------------------------------------
90CHAPTER 1: COLLECTING SYSTEM INFORMATION
91------------------------------------------------------------------------------
92
93------------------------------------------------------------------------------
94In This Chapter
95------------------------------------------------------------------------------
96* Investigating the properties of the pseudo file system /proc and its
97 ability to provide information on the running Linux system
98* Examining /proc's structure
99* Uncovering various information about the kernel and the processes running
100 on the system
101------------------------------------------------------------------------------
102
103
104The proc file system acts as an interface to internal data structures in the
105kernel. It can be used to obtain information about the system and to change
106certain kernel parameters at runtime (sysctl).
107
108First, we'll take a look at the read-only parts of /proc. In Chapter 2, we
109show you how you can use /proc/sys to change settings.
110
1111.1 Process-Specific Subdirectories
112-----------------------------------
113
114The directory /proc contains (among other things) one subdirectory for each
115process running on the system, which is named after the process ID (PID).
116
117The link self points to the process reading the file system. Each process
118subdirectory has the entries listed in Table 1-1.
119
120
121Table 1-1: Process specific entries in /proc
122..............................................................................
123 File Content
124 clear_refs Clears page referenced bits shown in smaps output
125 cmdline Command line arguments
126 cpu Current and last cpu in which it was executed (2.4)(smp)
127 cwd Link to the current working directory
128 environ Values of environment variables
129 exe Link to the executable of this process
130 fd Directory, which contains all file descriptors
131 maps Memory maps to executables and library files (2.4)
132 mem Memory held by this process
133 root Link to the root directory of this process
134 stat Process status
135 statm Process memory status information
136 status Process status in human readable form
137 wchan If CONFIG_KALLSYMS is set, a pre-decoded wchan
138 stack Report full stack trace, enable via CONFIG_STACKTRACE
139 smaps a extension based on maps, showing the memory consumption of
140 each mapping
141..............................................................................
142
143For example, to get the status information of a process, all you have to do is
144read the file /proc/PID/status:
145
146 >cat /proc/self/status
147 Name: cat
148 State: R (running)
149 Tgid: 5452
150 Pid: 5452
151 PPid: 743
152 TracerPid: 0 (2.4)
153 Uid: 501 501 501 501
154 Gid: 100 100 100 100
155 FDSize: 256
156 Groups: 100 14 16
157 VmPeak: 5004 kB
158 VmSize: 5004 kB
159 VmLck: 0 kB
160 VmHWM: 476 kB
161 VmRSS: 476 kB
162 VmData: 156 kB
163 VmStk: 88 kB
164 VmExe: 68 kB
165 VmLib: 1412 kB
166 VmPTE: 20 kb
167 VmSwap: 0 kB
168 Threads: 1
169 SigQ: 0/28578
170 SigPnd: 0000000000000000
171 ShdPnd: 0000000000000000
172 SigBlk: 0000000000000000
173 SigIgn: 0000000000000000
174 SigCgt: 0000000000000000
175 CapInh: 00000000fffffeff
176 CapPrm: 0000000000000000
177 CapEff: 0000000000000000
178 CapBnd: ffffffffffffffff
179 voluntary_ctxt_switches: 0
180 nonvoluntary_ctxt_switches: 1
181
182This shows you nearly the same information you would get if you viewed it with
183the ps command. In fact, ps uses the proc file system to obtain its
184information. But you get a more detailed view of the process by reading the
185file /proc/PID/status. It fields are described in table 1-2.
186
187The statm file contains more detailed information about the process
188memory usage. Its seven fields are explained in Table 1-3. The stat file
189contains details information about the process itself. Its fields are
190explained in Table 1-4.
191
192(for SMP CONFIG users)
193For making accounting scalable, RSS related information are handled in
194asynchronous manner and the vaule may not be very precise. To see a precise
195snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
196It's slow but very precise.
197
198Table 1-2: Contents of the status files (as of 2.6.30-rc7)
199..............................................................................
200 Field Content
201 Name filename of the executable
202 State state (R is running, S is sleeping, D is sleeping
203 in an uninterruptible wait, Z is zombie,
204 T is traced or stopped)
205 Tgid thread group ID
206 Pid process id
207 PPid process id of the parent process
208 TracerPid PID of process tracing this process (0 if not)
209 Uid Real, effective, saved set, and file system UIDs
210 Gid Real, effective, saved set, and file system GIDs
211 FDSize number of file descriptor slots currently allocated
212 Groups supplementary group list
213 VmPeak peak virtual memory size
214 VmSize total program size
215 VmLck locked memory size
216 VmHWM peak resident set size ("high water mark")
217 VmRSS size of memory portions
218 VmData size of data, stack, and text segments
219 VmStk size of data, stack, and text segments
220 VmExe size of text segment
221 VmLib size of shared library code
222 VmPTE size of page table entries
223 VmSwap size of swap usage (the number of referred swapents)
224 Threads number of threads
225 SigQ number of signals queued/max. number for queue
226 SigPnd bitmap of pending signals for the thread
227 ShdPnd bitmap of shared pending signals for the process
228 SigBlk bitmap of blocked signals
229 SigIgn bitmap of ignored signals
230 SigCgt bitmap of catched signals
231 CapInh bitmap of inheritable capabilities
232 CapPrm bitmap of permitted capabilities
233 CapEff bitmap of effective capabilities
234 CapBnd bitmap of capabilities bounding set
235 Cpus_allowed mask of CPUs on which this process may run
236 Cpus_allowed_list Same as previous, but in "list format"
237 Mems_allowed mask of memory nodes allowed to this process
238 Mems_allowed_list Same as previous, but in "list format"
239 voluntary_ctxt_switches number of voluntary context switches
240 nonvoluntary_ctxt_switches number of non voluntary context switches
241..............................................................................
242
243Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
244..............................................................................
245 Field Content
246 size total program size (pages) (same as VmSize in status)
247 resident size of memory portions (pages) (same as VmRSS in status)
248 shared number of pages that are shared (i.e. backed by a file)
249 trs number of pages that are 'code' (not including libs; broken,
250 includes data segment)
251 lrs number of pages of library (always 0 on 2.6)
252 drs number of pages of data/stack (including libs; broken,
253 includes library text)
254 dt number of dirty pages (always 0 on 2.6)
255..............................................................................
256
257
258Table 1-4: Contents of the stat files (as of 2.6.30-rc7)
259..............................................................................
260 Field Content
261 pid process id
262 tcomm filename of the executable
263 state state (R is running, S is sleeping, D is sleeping in an
264 uninterruptible wait, Z is zombie, T is traced or stopped)
265 ppid process id of the parent process
266 pgrp pgrp of the process
267 sid session id
268 tty_nr tty the process uses
269 tty_pgrp pgrp of the tty
270 flags task flags
271 min_flt number of minor faults
272 cmin_flt number of minor faults with child's
273 maj_flt number of major faults
274 cmaj_flt number of major faults with child's
275 utime user mode jiffies
276 stime kernel mode jiffies
277 cutime user mode jiffies with child's
278 cstime kernel mode jiffies with child's
279 priority priority level
280 nice nice level
281 num_threads number of threads
282 it_real_value (obsolete, always 0)
283 start_time time the process started after system boot
284 vsize virtual memory size
285 rss resident set memory size
286 rsslim current limit in bytes on the rss
287 start_code address above which program text can run
288 end_code address below which program text can run
289 start_stack address of the start of the stack
290 esp current value of ESP
291 eip current value of EIP
292 pending bitmap of pending signals
293 blocked bitmap of blocked signals
294 sigign bitmap of ignored signals
295 sigcatch bitmap of catched signals
296 wchan address where process went to sleep
297 0 (place holder)
298 0 (place holder)
299 exit_signal signal to send to parent thread on exit
300 task_cpu which CPU the task is scheduled on
301 rt_priority realtime priority
302 policy scheduling policy (man sched_setscheduler)
303 blkio_ticks time spent waiting for block IO
304 gtime guest time of the task in jiffies
305 cgtime guest time of the task children in jiffies
306..............................................................................
307
308The /proc/PID/map file containing the currently mapped memory regions and
309their access permissions.
310
311The format is:
312
313address perms offset dev inode pathname
314
31508048000-08049000 r-xp 00000000 03:00 8312 /opt/test
31608049000-0804a000 rw-p 00001000 03:00 8312 /opt/test
3170804a000-0806b000 rw-p 00000000 00:00 0 [heap]
318a7cb1000-a7cb2000 ---p 00000000 00:00 0
319a7cb2000-a7eb2000 rw-p 00000000 00:00 0 [threadstack:001ff4b4]
320a7eb2000-a7eb3000 ---p 00000000 00:00 0
321a7eb3000-a7ed5000 rw-p 00000000 00:00 0
322a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6
323a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6
324a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6
325a800b000-a800e000 rw-p 00000000 00:00 0
326a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0
327a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0
328a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0
329a8024000-a8027000 rw-p 00000000 00:00 0
330a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2
331a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2
332a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2
333aff35000-aff4a000 rw-p 00000000 00:00 0 [stack]
334ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso]
335
336where "address" is the address space in the process that it occupies, "perms"
337is a set of permissions:
338
339 r = read
340 w = write
341 x = execute
342 s = shared
343 p = private (copy on write)
344
345"offset" is the offset into the mapping, "dev" is the device (major:minor), and
346"inode" is the inode on that device. 0 indicates that no inode is associated
347with the memory region, as the case would be with BSS (uninitialized data).
348The "pathname" shows the name associated file for this mapping. If the mapping
349is not associated with a file:
350
351 [heap] = the heap of the program
352 [stack] = the stack of the main process
353 [vdso] = the "virtual dynamic shared object",
354 the kernel system call handler
355 [threadstack:xxxxxxxx] = the stack of the thread, xxxxxxxx is the stack size
356
357 or if empty, the mapping is anonymous.
358
359
360The /proc/PID/smaps is an extension based on maps, showing the memory
361consumption for each of the process's mappings. For each of mappings there
362is a series of lines such as the following:
363
36408048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash
365Size: 1084 kB
366Rss: 892 kB
367Pss: 374 kB
368Shared_Clean: 892 kB
369Shared_Dirty: 0 kB
370Private_Clean: 0 kB
371Private_Dirty: 0 kB
372Referenced: 892 kB
373Swap: 0 kB
374KernelPageSize: 4 kB
375MMUPageSize: 4 kB
376
377The first of these lines shows the same information as is displayed for the
378mapping in /proc/PID/maps. The remaining lines show the size of the mapping,
379the amount of the mapping that is currently resident in RAM, the "proportional
380set size” (divide each shared page by the number of processes sharing it), the
381number of clean and dirty shared pages in the mapping, and the number of clean
382and dirty private pages in the mapping. The "Referenced" indicates the amount
383of memory currently marked as referenced or accessed.
384
385This file is only present if the CONFIG_MMU kernel configuration option is
386enabled.
387
388The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
389bits on both physical and virtual pages associated with a process.
390To clear the bits for all the pages associated with the process
391 > echo 1 > /proc/PID/clear_refs
392
393To clear the bits for the anonymous pages associated with the process
394 > echo 2 > /proc/PID/clear_refs
395
396To clear the bits for the file mapped pages associated with the process
397 > echo 3 > /proc/PID/clear_refs
398Any other value written to /proc/PID/clear_refs will have no effect.
399
400
4011.2 Kernel data
402---------------
403
404Similar to the process entries, the kernel data files give information about
405the running kernel. The files used to obtain this information are contained in
406/proc and are listed in Table 1-5. Not all of these will be present in your
407system. It depends on the kernel configuration and the loaded modules, which
408files are there, and which are missing.
409
410Table 1-5: Kernel info in /proc
411..............................................................................
412 File Content
413 apm Advanced power management info
414 buddyinfo Kernel memory allocator information (see text) (2.5)
415 bus Directory containing bus specific information
416 cmdline Kernel command line
417 cpuinfo Info about the CPU
418 devices Available devices (block and character)
419 dma Used DMS channels
420 filesystems Supported filesystems
421 driver Various drivers grouped here, currently rtc (2.4)
422 execdomains Execdomains, related to security (2.4)
423 fb Frame Buffer devices (2.4)
424 fs File system parameters, currently nfs/exports (2.4)
425 ide Directory containing info about the IDE subsystem
426 interrupts Interrupt usage
427 iomem Memory map (2.4)
428 ioports I/O port usage
429 irq Masks for irq to cpu affinity (2.4)(smp?)
430 isapnp ISA PnP (Plug&Play) Info (2.4)
431 kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4))
432 kmsg Kernel messages
433 ksyms Kernel symbol table
434 loadavg Load average of last 1, 5 & 15 minutes
435 locks Kernel locks
436 meminfo Memory info
437 misc Miscellaneous
438 modules List of loaded modules
439 mounts Mounted filesystems
440 net Networking info (see text)
441 pagetypeinfo Additional page allocator information (see text) (2.5)
442 partitions Table of partitions known to the system
443 pci Deprecated info of PCI bus (new way -> /proc/bus/pci/,
444 decoupled by lspci (2.4)
445 rtc Real time clock
446 scsi SCSI info (see text)
447 slabinfo Slab pool info
448 softirqs softirq usage
449 stat Overall statistics
450 swaps Swap space utilization
451 sys See chapter 2
452 sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4)
453 tty Info of tty drivers
454 uptime System uptime
455 version Kernel version
456 video bttv info of video resources (2.4)
457 vmallocinfo Show vmalloced areas
458..............................................................................
459
460You can, for example, check which interrupts are currently in use and what
461they are used for by looking in the file /proc/interrupts:
462
463 > cat /proc/interrupts
464 CPU0
465 0: 8728810 XT-PIC timer
466 1: 895 XT-PIC keyboard
467 2: 0 XT-PIC cascade
468 3: 531695 XT-PIC aha152x
469 4: 2014133 XT-PIC serial
470 5: 44401 XT-PIC pcnet_cs
471 8: 2 XT-PIC rtc
472 11: 8 XT-PIC i82365
473 12: 182918 XT-PIC PS/2 Mouse
474 13: 1 XT-PIC fpu
475 14: 1232265 XT-PIC ide0
476 15: 7 XT-PIC ide1
477 NMI: 0
478
479In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the
480output of a SMP machine):
481
482 > cat /proc/interrupts
483
484 CPU0 CPU1
485 0: 1243498 1214548 IO-APIC-edge timer
486 1: 8949 8958 IO-APIC-edge keyboard
487 2: 0 0 XT-PIC cascade
488 5: 11286 10161 IO-APIC-edge soundblaster
489 8: 1 0 IO-APIC-edge rtc
490 9: 27422 27407 IO-APIC-edge 3c503
491 12: 113645 113873 IO-APIC-edge PS/2 Mouse
492 13: 0 0 XT-PIC fpu
493 14: 22491 24012 IO-APIC-edge ide0
494 15: 2183 2415 IO-APIC-edge ide1
495 17: 30564 30414 IO-APIC-level eth0
496 18: 177 164 IO-APIC-level bttv
497 NMI: 2457961 2457959
498 LOC: 2457882 2457881
499 ERR: 2155
500
501NMI is incremented in this case because every timer interrupt generates a NMI
502(Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups.
503
504LOC is the local interrupt counter of the internal APIC of every CPU.
505
506ERR is incremented in the case of errors in the IO-APIC bus (the bus that
507connects the CPUs in a SMP system. This means that an error has been detected,
508the IO-APIC automatically retry the transmission, so it should not be a big
509problem, but you should read the SMP-FAQ.
510
511In 2.6.2* /proc/interrupts was expanded again. This time the goal was for
512/proc/interrupts to display every IRQ vector in use by the system, not
513just those considered 'most important'. The new vectors are:
514
515 THR -- interrupt raised when a machine check threshold counter
516 (typically counting ECC corrected errors of memory or cache) exceeds
517 a configurable threshold. Only available on some systems.
518
519 TRM -- a thermal event interrupt occurs when a temperature threshold
520 has been exceeded for the CPU. This interrupt may also be generated
521 when the temperature drops back to normal.
522
523 SPU -- a spurious interrupt is some interrupt that was raised then lowered
524 by some IO device before it could be fully processed by the APIC. Hence
525 the APIC sees the interrupt but does not know what device it came from.
526 For this case the APIC will generate the interrupt with a IRQ vector
527 of 0xff. This might also be generated by chipset bugs.
528
529 RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are
530 sent from one CPU to another per the needs of the OS. Typically,
531 their statistics are used by kernel developers and interested users to
532 determine the occurrence of interrupts of the given type.
533
534The above IRQ vectors are displayed only when relevent. For example,
535the threshold vector does not exist on x86_64 platforms. Others are
536suppressed when the system is a uniprocessor. As of this writing, only
537i386 and x86_64 platforms support the new IRQ vector displays.
538
539Of some interest is the introduction of the /proc/irq directory to 2.4.
540It could be used to set IRQ to CPU affinity, this means that you can "hook" an
541IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
542irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and
543prof_cpu_mask.
544
545For example
546 > ls /proc/irq/
547 0 10 12 14 16 18 2 4 6 8 prof_cpu_mask
548 1 11 13 15 17 19 3 5 7 9 default_smp_affinity
549 > ls /proc/irq/0/
550 smp_affinity
551
552smp_affinity is a bitmask, in which you can specify which CPUs can handle the
553IRQ, you can set it by doing:
554
555 > echo 1 > /proc/irq/10/smp_affinity
556
557This means that only the first CPU will handle the IRQ, but you can also echo
5585 which means that only the first and fourth CPU can handle the IRQ.
559
560The contents of each smp_affinity file is the same by default:
561
562 > cat /proc/irq/0/smp_affinity
563 ffffffff
564
565The default_smp_affinity mask applies to all non-active IRQs, which are the
566IRQs which have not yet been allocated/activated, and hence which lack a
567/proc/irq/[0-9]* directory.
568
569prof_cpu_mask specifies which CPUs are to be profiled by the system wide
570profiler. Default value is ffffffff (all cpus).
571
572The way IRQs are routed is handled by the IO-APIC, and it's Round Robin
573between all the CPUs which are allowed to handle it. As usual the kernel has
574more info than you and does a better job than you, so the defaults are the
575best choice for almost everyone.
576
577There are three more important subdirectories in /proc: net, scsi, and sys.
578The general rule is that the contents, or even the existence of these
579directories, depend on your kernel configuration. If SCSI is not enabled, the
580directory scsi may not exist. The same is true with the net, which is there
581only when networking support is present in the running kernel.
582
583The slabinfo file gives information about memory usage at the slab level.
584Linux uses slab pools for memory management above page level in version 2.2.
585Commonly used objects have their own slab pool (such as network buffers,
586directory cache, and so on).
587
588..............................................................................
589
590> cat /proc/buddyinfo
591
592Node 0, zone DMA 0 4 5 4 4 3 ...
593Node 0, zone Normal 1 0 0 1 101 8 ...
594Node 0, zone HighMem 2 0 0 1 1 0 ...
595
596External fragmentation is a problem under some workloads, and buddyinfo is a
597useful tool for helping diagnose these problems. Buddyinfo will give you a
598clue as to how big an area you can safely allocate, or why a previous
599allocation failed.
600
601Each column represents the number of pages of a certain order which are
602available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in
603ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE
604available in ZONE_NORMAL, etc...
605
606More information relevant to external fragmentation can be found in
607pagetypeinfo.
608
609> cat /proc/pagetypeinfo
610Page block order: 9
611Pages per block: 512
612
613Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
614Node 0, zone DMA, type Unmovable 0 0 0 1 1 1 1 1 1 1 0
615Node 0, zone DMA, type Reclaimable 0 0 0 0 0 0 0 0 0 0 0
616Node 0, zone DMA, type Movable 1 1 2 1 2 1 1 0 1 0 2
617Node 0, zone DMA, type Reserve 0 0 0 0 0 0 0 0 0 1 0
618Node 0, zone DMA, type Isolate 0 0 0 0 0 0 0 0 0 0 0
619Node 0, zone DMA32, type Unmovable 103 54 77 1 1 1 11 8 7 1 9
620Node 0, zone DMA32, type Reclaimable 0 0 2 1 0 0 0 0 1 0 0
621Node 0, zone DMA32, type Movable 169 152 113 91 77 54 39 13 6 1 452
622Node 0, zone DMA32, type Reserve 1 2 2 2 2 0 1 1 1 1 0
623Node 0, zone DMA32, type Isolate 0 0 0 0 0 0 0 0 0 0 0
624
625Number of blocks type Unmovable Reclaimable Movable Reserve Isolate
626Node 0, zone DMA 2 0 5 1 0
627Node 0, zone DMA32 41 6 967 2 0
628
629Fragmentation avoidance in the kernel works by grouping pages of different
630migrate types into the same contiguous regions of memory called page blocks.
631A page block is typically the size of the default hugepage size e.g. 2MB on
632X86-64. By keeping pages grouped based on their ability to move, the kernel
633can reclaim pages within a page block to satisfy a high-order allocation.
634
635The pagetypinfo begins with information on the size of a page block. It
636then gives the same type of information as buddyinfo except broken down
637by migrate-type and finishes with details on how many page blocks of each
638type exist.
639
640If min_free_kbytes has been tuned correctly (recommendations made by hugeadm
641from libhugetlbfs http://sourceforge.net/projects/libhugetlbfs/), one can
642make an estimate of the likely number of huge pages that can be allocated
643at a given point in time. All the "Movable" blocks should be allocatable
644unless memory has been mlock()'d. Some of the Reclaimable blocks should
645also be allocatable although a lot of filesystem metadata may have to be
646reclaimed to achieve this.
647
648..............................................................................
649
650meminfo:
651
652Provides information about distribution and utilization of memory. This
653varies by architecture and compile options. The following is from a
65416GB PIII, which has highmem enabled. You may not have all of these fields.
655
656> cat /proc/meminfo
657
658
659MemTotal: 16344972 kB
660MemFree: 13634064 kB
661Buffers: 3656 kB
662Cached: 1195708 kB
663SwapCached: 0 kB
664Active: 891636 kB
665Inactive: 1077224 kB
666HighTotal: 15597528 kB
667HighFree: 13629632 kB
668LowTotal: 747444 kB
669LowFree: 4432 kB
670SwapTotal: 0 kB
671SwapFree: 0 kB
672Dirty: 968 kB
673Writeback: 0 kB
674AnonPages: 861800 kB
675Mapped: 280372 kB
676Slab: 284364 kB
677SReclaimable: 159856 kB
678SUnreclaim: 124508 kB
679PageTables: 24448 kB
680NFS_Unstable: 0 kB
681Bounce: 0 kB
682WritebackTmp: 0 kB
683CommitLimit: 7669796 kB
684Committed_AS: 100056 kB
685VmallocTotal: 112216 kB
686VmallocUsed: 428 kB
687VmallocChunk: 111088 kB
688
689 MemTotal: Total usable ram (i.e. physical ram minus a few reserved
690 bits and the kernel binary code)
691 MemFree: The sum of LowFree+HighFree
692 Buffers: Relatively temporary storage for raw disk blocks
693 shouldn't get tremendously large (20MB or so)
694 Cached: in-memory cache for files read from the disk (the
695 pagecache). Doesn't include SwapCached
696 SwapCached: Memory that once was swapped out, is swapped back in but
697 still also is in the swapfile (if memory is needed it
698 doesn't need to be swapped out AGAIN because it is already
699 in the swapfile. This saves I/O)
700 Active: Memory that has been used more recently and usually not
701 reclaimed unless absolutely necessary.
702 Inactive: Memory which has been less recently used. It is more
703 eligible to be reclaimed for other purposes
704 HighTotal:
705 HighFree: Highmem is all memory above ~860MB of physical memory
706 Highmem areas are for use by userspace programs, or
707 for the pagecache. The kernel must use tricks to access
708 this memory, making it slower to access than lowmem.
709 LowTotal:
710 LowFree: Lowmem is memory which can be used for everything that
711 highmem can be used for, but it is also available for the
712 kernel's use for its own data structures. Among many
713 other things, it is where everything from the Slab is
714 allocated. Bad things happen when you're out of lowmem.
715 SwapTotal: total amount of swap space available
716 SwapFree: Memory which has been evicted from RAM, and is temporarily
717 on the disk
718 Dirty: Memory which is waiting to get written back to the disk
719 Writeback: Memory which is actively being written back to the disk
720 AnonPages: Non-file backed pages mapped into userspace page tables
721 Mapped: files which have been mmaped, such as libraries
722 Slab: in-kernel data structures cache
723SReclaimable: Part of Slab, that might be reclaimed, such as caches
724 SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure
725 PageTables: amount of memory dedicated to the lowest level of page
726 tables.
727NFS_Unstable: NFS pages sent to the server, but not yet committed to stable
728 storage
729 Bounce: Memory used for block device "bounce buffers"
730WritebackTmp: Memory used by FUSE for temporary writeback buffers
731 CommitLimit: Based on the overcommit ratio ('vm.overcommit_ratio'),
732 this is the total amount of memory currently available to
733 be allocated on the system. This limit is only adhered to
734 if strict overcommit accounting is enabled (mode 2 in
735 'vm.overcommit_memory').
736 The CommitLimit is calculated with the following formula:
737 CommitLimit = ('vm.overcommit_ratio' * Physical RAM) + Swap
738 For example, on a system with 1G of physical RAM and 7G
739 of swap with a `vm.overcommit_ratio` of 30 it would
740 yield a CommitLimit of 7.3G.
741 For more details, see the memory overcommit documentation
742 in vm/overcommit-accounting.
743Committed_AS: The amount of memory presently allocated on the system.
744 The committed memory is a sum of all of the memory which
745 has been allocated by processes, even if it has not been
746 "used" by them as of yet. A process which malloc()'s 1G
747 of memory, but only touches 300M of it will only show up
748 as using 300M of memory even if it has the address space
749 allocated for the entire 1G. This 1G is memory which has
750 been "committed" to by the VM and can be used at any time
751 by the allocating application. With strict overcommit
752 enabled on the system (mode 2 in 'vm.overcommit_memory'),
753 allocations which would exceed the CommitLimit (detailed
754 above) will not be permitted. This is useful if one needs
755 to guarantee that processes will not fail due to lack of
756 memory once that memory has been successfully allocated.
757VmallocTotal: total size of vmalloc memory area
758 VmallocUsed: amount of vmalloc area which is used
759VmallocChunk: largest contiguous block of vmalloc area which is free
760
761..............................................................................
762
763vmallocinfo:
764
765Provides information about vmalloced/vmaped areas. One line per area,
766containing the virtual address range of the area, size in bytes,
767caller information of the creator, and optional information depending
768on the kind of area :
769
770 pages=nr number of pages
771 phys=addr if a physical address was specified
772 ioremap I/O mapping (ioremap() and friends)
773 vmalloc vmalloc() area
774 vmap vmap()ed pages
775 user VM_USERMAP area
776 vpages buffer for pages pointers was vmalloced (huge area)
777 N<node>=nr (Only on NUMA kernels)
778 Number of pages allocated on memory node <node>
779
780> cat /proc/vmallocinfo
7810xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ...
782 /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128
7830xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ...
784 /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64
7850xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f...
786 phys=7fee8000 ioremap
7870xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f...
788 phys=7fee7000 ioremap
7890xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210
7900xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ...
791 /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3
7920xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ...
793 pages=2 vmalloc N1=2
7940xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ...
795 /0x130 [x_tables] pages=4 vmalloc N0=4
7960xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ...
797 pages=14 vmalloc N2=14
7980xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ...
799 pages=4 vmalloc N1=4
8000xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ...
801 pages=2 vmalloc N1=2
8020xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ...
803 pages=10 vmalloc N0=10
804
805..............................................................................
806
807softirqs:
808
809Provides counts of softirq handlers serviced since boot time, for each cpu.
810
811> cat /proc/softirqs
812 CPU0 CPU1 CPU2 CPU3
813 HI: 0 0 0 0
814 TIMER: 27166 27120 27097 27034
815 NET_TX: 0 0 0 17
816 NET_RX: 42 0 0 39
817 BLOCK: 0 0 107 1121
818 TASKLET: 0 0 0 290
819 SCHED: 27035 26983 26971 26746
820 HRTIMER: 0 0 0 0
821 RCU: 1678 1769 2178 2250
822
823
8241.3 IDE devices in /proc/ide
825----------------------------
826
827The subdirectory /proc/ide contains information about all IDE devices of which
828the kernel is aware. There is one subdirectory for each IDE controller, the
829file drivers and a link for each IDE device, pointing to the device directory
830in the controller specific subtree.
831
832The file drivers contains general information about the drivers used for the
833IDE devices:
834
835 > cat /proc/ide/drivers
836 ide-cdrom version 4.53
837 ide-disk version 1.08
838
839More detailed information can be found in the controller specific
840subdirectories. These are named ide0, ide1 and so on. Each of these
841directories contains the files shown in table 1-6.
842
843
844Table 1-6: IDE controller info in /proc/ide/ide?
845..............................................................................
846 File Content
847 channel IDE channel (0 or 1)
848 config Configuration (only for PCI/IDE bridge)
849 mate Mate name
850 model Type/Chipset of IDE controller
851..............................................................................
852
853Each device connected to a controller has a separate subdirectory in the
854controllers directory. The files listed in table 1-7 are contained in these
855directories.
856
857
858Table 1-7: IDE device information
859..............................................................................
860 File Content
861 cache The cache
862 capacity Capacity of the medium (in 512Byte blocks)
863 driver driver and version
864 geometry physical and logical geometry
865 identify device identify block
866 media media type
867 model device identifier
868 settings device setup
869 smart_thresholds IDE disk management thresholds
870 smart_values IDE disk management values
871..............................................................................
872
873The most interesting file is settings. This file contains a nice overview of
874the drive parameters:
875
876 # cat /proc/ide/ide0/hda/settings
877 name value min max mode
878 ---- ----- --- --- ----
879 bios_cyl 526 0 65535 rw
880 bios_head 255 0 255 rw
881 bios_sect 63 0 63 rw
882 breada_readahead 4 0 127 rw
883 bswap 0 0 1 r
884 file_readahead 72 0 2097151 rw
885 io_32bit 0 0 3 rw
886 keepsettings 0 0 1 rw
887 max_kb_per_request 122 1 127 rw
888 multcount 0 0 8 rw
889 nice1 1 0 1 rw
890 nowerr 0 0 1 rw
891 pio_mode write-only 0 255 w
892 slow 0 0 1 rw
893 unmaskirq 0 0 1 rw
894 using_dma 0 0 1 rw
895
896
8971.4 Networking info in /proc/net
898--------------------------------
899
900The subdirectory /proc/net follows the usual pattern. Table 1-8 shows the
901additional values you get for IP version 6 if you configure the kernel to
902support this. Table 1-9 lists the files and their meaning.
903
904
905Table 1-8: IPv6 info in /proc/net
906..............................................................................
907 File Content
908 udp6 UDP sockets (IPv6)
909 tcp6 TCP sockets (IPv6)
910 raw6 Raw device statistics (IPv6)
911 igmp6 IP multicast addresses, which this host joined (IPv6)
912 if_inet6 List of IPv6 interface addresses
913 ipv6_route Kernel routing table for IPv6
914 rt6_stats Global IPv6 routing tables statistics
915 sockstat6 Socket statistics (IPv6)
916 snmp6 Snmp data (IPv6)
917..............................................................................
918
919
920Table 1-9: Network info in /proc/net
921..............................................................................
922 File Content
923 arp Kernel ARP table
924 dev network devices with statistics
925 dev_mcast the Layer2 multicast groups a device is listening too
926 (interface index, label, number of references, number of bound
927 addresses).
928 dev_stat network device status
929 ip_fwchains Firewall chain linkage
930 ip_fwnames Firewall chain names
931 ip_masq Directory containing the masquerading tables
932 ip_masquerade Major masquerading table
933 netstat Network statistics
934 raw raw device statistics
935 route Kernel routing table
936 rpc Directory containing rpc info
937 rt_cache Routing cache
938 snmp SNMP data
939 sockstat Socket statistics
940 tcp TCP sockets
941 tr_rif Token ring RIF routing table
942 udp UDP sockets
943 unix UNIX domain sockets
944 wireless Wireless interface data (Wavelan etc)
945 igmp IP multicast addresses, which this host joined
946 psched Global packet scheduler parameters.
947 netlink List of PF_NETLINK sockets
948 ip_mr_vifs List of multicast virtual interfaces
949 ip_mr_cache List of multicast routing cache
950..............................................................................
951
952You can use this information to see which network devices are available in
953your system and how much traffic was routed over those devices:
954
955 > cat /proc/net/dev
956 Inter-|Receive |[...
957 face |bytes packets errs drop fifo frame compressed multicast|[...
958 lo: 908188 5596 0 0 0 0 0 0 [...
959 ppp0:15475140 20721 410 0 0 410 0 0 [...
960 eth0: 614530 7085 0 0 0 0 0 1 [...
961
962 ...] Transmit
963 ...] bytes packets errs drop fifo colls carrier compressed
964 ...] 908188 5596 0 0 0 0 0 0
965 ...] 1375103 17405 0 0 0 0 0 0
966 ...] 1703981 5535 0 0 0 3 0 0
967
968In addition, each Channel Bond interface has it's own directory. For
969example, the bond0 device will have a directory called /proc/net/bond0/.
970It will contain information that is specific to that bond, such as the
971current slaves of the bond, the link status of the slaves, and how
972many times the slaves link has failed.
973
9741.5 SCSI info
975-------------
976
977If you have a SCSI host adapter in your system, you'll find a subdirectory
978named after the driver for this adapter in /proc/scsi. You'll also see a list
979of all recognized SCSI devices in /proc/scsi:
980
981 >cat /proc/scsi/scsi
982 Attached devices:
983 Host: scsi0 Channel: 00 Id: 00 Lun: 00
984 Vendor: IBM Model: DGHS09U Rev: 03E0
985 Type: Direct-Access ANSI SCSI revision: 03
986 Host: scsi0 Channel: 00 Id: 06 Lun: 00
987 Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04
988 Type: CD-ROM ANSI SCSI revision: 02
989
990
991The directory named after the driver has one file for each adapter found in
992the system. These files contain information about the controller, including
993the used IRQ and the IO address range. The amount of information shown is
994dependent on the adapter you use. The example shows the output for an Adaptec
995AHA-2940 SCSI adapter:
996
997 > cat /proc/scsi/aic7xxx/0
998
999 Adaptec AIC7xxx driver version: 5.1.19/3.2.4
1000 Compile Options:
1001 TCQ Enabled By Default : Disabled
1002 AIC7XXX_PROC_STATS : Disabled
1003 AIC7XXX_RESET_DELAY : 5
1004 Adapter Configuration:
1005 SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter
1006 Ultra Wide Controller
1007 PCI MMAPed I/O Base: 0xeb001000
1008 Adapter SEEPROM Config: SEEPROM found and used.
1009 Adaptec SCSI BIOS: Enabled
1010 IRQ: 10
1011 SCBs: Active 0, Max Active 2,
1012 Allocated 15, HW 16, Page 255
1013 Interrupts: 160328
1014 BIOS Control Word: 0x18b6
1015 Adapter Control Word: 0x005b
1016 Extended Translation: Enabled
1017 Disconnect Enable Flags: 0xffff
1018 Ultra Enable Flags: 0x0001
1019 Tag Queue Enable Flags: 0x0000
1020 Ordered Queue Tag Flags: 0x0000
1021 Default Tag Queue Depth: 8
1022 Tagged Queue By Device array for aic7xxx host instance 0:
1023 {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255}
1024 Actual queue depth per device for aic7xxx host instance 0:
1025 {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}
1026 Statistics:
1027 (scsi0:0:0:0)
1028 Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8
1029 Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0)
1030 Total transfers 160151 (74577 reads and 85574 writes)
1031 (scsi0:0:6:0)
1032 Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15
1033 Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0)
1034 Total transfers 0 (0 reads and 0 writes)
1035
1036
10371.6 Parallel port info in /proc/parport
1038---------------------------------------
1039
1040The directory /proc/parport contains information about the parallel ports of
1041your system. It has one subdirectory for each port, named after the port
1042number (0,1,2,...).
1043
1044These directories contain the four files shown in Table 1-10.
1045
1046
1047Table 1-10: Files in /proc/parport
1048..............................................................................
1049 File Content
1050 autoprobe Any IEEE-1284 device ID information that has been acquired.
1051 devices list of the device drivers using that port. A + will appear by the
1052 name of the device currently using the port (it might not appear
1053 against any).
1054 hardware Parallel port's base address, IRQ line and DMA channel.
1055 irq IRQ that parport is using for that port. This is in a separate
1056 file to allow you to alter it by writing a new value in (IRQ
1057 number or none).
1058..............................................................................
1059
10601.7 TTY info in /proc/tty
1061-------------------------
1062
1063Information about the available and actually used tty's can be found in the
1064directory /proc/tty.You'll find entries for drivers and line disciplines in
1065this directory, as shown in Table 1-11.
1066
1067
1068Table 1-11: Files in /proc/tty
1069..............................................................................
1070 File Content
1071 drivers list of drivers and their usage
1072 ldiscs registered line disciplines
1073 driver/serial usage statistic and status of single tty lines
1074..............................................................................
1075
1076To see which tty's are currently in use, you can simply look into the file
1077/proc/tty/drivers:
1078
1079 > cat /proc/tty/drivers
1080 pty_slave /dev/pts 136 0-255 pty:slave
1081 pty_master /dev/ptm 128 0-255 pty:master
1082 pty_slave /dev/ttyp 3 0-255 pty:slave
1083 pty_master /dev/pty 2 0-255 pty:master
1084 serial /dev/cua 5 64-67 serial:callout
1085 serial /dev/ttyS 4 64-67 serial
1086 /dev/tty0 /dev/tty0 4 0 system:vtmaster
1087 /dev/ptmx /dev/ptmx 5 2 system
1088 /dev/console /dev/console 5 1 system:console
1089 /dev/tty /dev/tty 5 0 system:/dev/tty
1090 unknown /dev/tty 4 1-63 console
1091
1092
10931.8 Miscellaneous kernel statistics in /proc/stat
1094-------------------------------------------------
1095
1096Various pieces of information about kernel activity are available in the
1097/proc/stat file. All of the numbers reported in this file are aggregates
1098since the system first booted. For a quick look, simply cat the file:
1099
1100 > cat /proc/stat
1101 cpu 2255 34 2290 22625563 6290 127 456 0 0
1102 cpu0 1132 34 1441 11311718 3675 127 438 0 0
1103 cpu1 1123 0 849 11313845 2614 0 18 0 0
1104 intr 114930548 113199788 3 0 5 263 0 4 [... lots more numbers ...]
1105 ctxt 1990473
1106 btime 1062191376
1107 processes 2915
1108 procs_running 1
1109 procs_blocked 0
1110 softirq 183433 0 21755 12 39 1137 231 21459 2263
1111
1112The very first "cpu" line aggregates the numbers in all of the other "cpuN"
1113lines. These numbers identify the amount of time the CPU has spent performing
1114different kinds of work. Time units are in USER_HZ (typically hundredths of a
1115second). The meanings of the columns are as follows, from left to right:
1116
1117- user: normal processes executing in user mode
1118- nice: niced processes executing in user mode
1119- system: processes executing in kernel mode
1120- idle: twiddling thumbs
1121- iowait: waiting for I/O to complete
1122- irq: servicing interrupts
1123- softirq: servicing softirqs
1124- steal: involuntary wait
1125- guest: running a normal guest
1126- guest_nice: running a niced guest
1127
1128The "intr" line gives counts of interrupts serviced since boot time, for each
1129of the possible system interrupts. The first column is the total of all
1130interrupts serviced; each subsequent column is the total for that particular
1131interrupt.
1132
1133The "ctxt" line gives the total number of context switches across all CPUs.
1134
1135The "btime" line gives the time at which the system booted, in seconds since
1136the Unix epoch.
1137
1138The "processes" line gives the number of processes and threads created, which
1139includes (but is not limited to) those created by calls to the fork() and
1140clone() system calls.
1141
1142The "procs_running" line gives the total number of threads that are
1143running or ready to run (i.e., the total number of runnable threads).
1144
1145The "procs_blocked" line gives the number of processes currently blocked,
1146waiting for I/O to complete.
1147
1148The "softirq" line gives counts of softirqs serviced since boot time, for each
1149of the possible system softirqs. The first column is the total of all
1150softirqs serviced; each subsequent column is the total for that particular
1151softirq.
1152
1153
11541.9 Ext4 file system parameters
1155------------------------------
1156
1157Information about mounted ext4 file systems can be found in
1158/proc/fs/ext4. Each mounted filesystem will have a directory in
1159/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or
1160/proc/fs/ext4/dm-0). The files in each per-device directory are shown
1161in Table 1-12, below.
1162
1163Table 1-12: Files in /proc/fs/ext4/<devname>
1164..............................................................................
1165 File Content
1166 mb_groups details of multiblock allocator buddy cache of free blocks
1167..............................................................................
1168
1169
1170------------------------------------------------------------------------------
1171Summary
1172------------------------------------------------------------------------------
1173The /proc file system serves information about the running system. It not only
1174allows access to process data but also allows you to request the kernel status
1175by reading files in the hierarchy.
1176
1177The directory structure of /proc reflects the types of information and makes
1178it easy, if not obvious, where to look for specific data.
1179------------------------------------------------------------------------------
1180
1181------------------------------------------------------------------------------
1182CHAPTER 2: MODIFYING SYSTEM PARAMETERS
1183------------------------------------------------------------------------------
1184
1185------------------------------------------------------------------------------
1186In This Chapter
1187------------------------------------------------------------------------------
1188* Modifying kernel parameters by writing into files found in /proc/sys
1189* Exploring the files which modify certain parameters
1190* Review of the /proc/sys file tree
1191------------------------------------------------------------------------------
1192
1193
1194A very interesting part of /proc is the directory /proc/sys. This is not only
1195a source of information, it also allows you to change parameters within the
1196kernel. Be very careful when attempting this. You can optimize your system,
1197but you can also cause it to crash. Never alter kernel parameters on a
1198production system. Set up a development machine and test to make sure that
1199everything works the way you want it to. You may have no alternative but to
1200reboot the machine once an error has been made.
1201
1202To change a value, simply echo the new value into the file. An example is
1203given below in the section on the file system data. You need to be root to do
1204this. You can create your own boot script to perform this every time your
1205system boots.
1206
1207The files in /proc/sys can be used to fine tune and monitor miscellaneous and
1208general things in the operation of the Linux kernel. Since some of the files
1209can inadvertently disrupt your system, it is advisable to read both
1210documentation and source before actually making adjustments. In any case, be
1211very careful when writing to any of these files. The entries in /proc may
1212change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt
1213review the kernel documentation in the directory /usr/src/linux/Documentation.
1214This chapter is heavily based on the documentation included in the pre 2.2
1215kernels, and became part of it in version 2.2.1 of the Linux kernel.
1216
1217Please see: Documentation/sysctls/ directory for descriptions of these
1218entries.
1219
1220------------------------------------------------------------------------------
1221Summary
1222------------------------------------------------------------------------------
1223Certain aspects of kernel behavior can be modified at runtime, without the
1224need to recompile the kernel, or even to reboot the system. The files in the
1225/proc/sys tree can not only be read, but also modified. You can use the echo
1226command to write value into these files, thereby changing the default settings
1227of the kernel.
1228------------------------------------------------------------------------------
1229
1230------------------------------------------------------------------------------
1231CHAPTER 3: PER-PROCESS PARAMETERS
1232------------------------------------------------------------------------------
1233
12343.1 /proc/<pid>/oom_adj - Adjust the oom-killer score
1235------------------------------------------------------
1236
1237This file can be used to adjust the score used to select which processes
1238should be killed in an out-of-memory situation. Giving it a high score will
1239increase the likelihood of this process being killed by the oom-killer. Valid
1240values are in the range -16 to +15, plus the special value -17, which disables
1241oom-killing altogether for this process.
1242
1243The process to be killed in an out-of-memory situation is selected among all others
1244based on its badness score. This value equals the original memory size of the process
1245and is then updated according to its CPU time (utime + stime) and the
1246run time (uptime - start time). The longer it runs the smaller is the score.
1247Badness score is divided by the square root of the CPU time and then by
1248the double square root of the run time.
1249
1250Swapped out tasks are killed first. Half of each child's memory size is added to
1251the parent's score if they do not share the same memory. Thus forking servers
1252are the prime candidates to be killed. Having only one 'hungry' child will make
1253parent less preferable than the child.
1254
1255/proc/<pid>/oom_score shows process' current badness score.
1256
1257The following heuristics are then applied:
1258 * if the task was reniced, its score doubles
1259 * superuser or direct hardware access tasks (CAP_SYS_ADMIN, CAP_SYS_RESOURCE
1260 or CAP_SYS_RAWIO) have their score divided by 4
1261 * if oom condition happened in one cpuset and checked process does not belong
1262 to it, its score is divided by 8
1263 * the resulting score is multiplied by two to the power of oom_adj, i.e.
1264 points <<= oom_adj when it is positive and
1265 points >>= -(oom_adj) otherwise
1266
1267The task with the highest badness score is then selected and its children
1268are killed, process itself will be killed in an OOM situation when it does
1269not have children or some of them disabled oom like described above.
1270
12713.2 /proc/<pid>/oom_score - Display current oom-killer score
1272-------------------------------------------------------------
1273
1274This file can be used to check the current score used by the oom-killer is for
1275any given <pid>. Use it together with /proc/<pid>/oom_adj to tune which
1276process should be killed in an out-of-memory situation.
1277
1278
12793.3 /proc/<pid>/io - Display the IO accounting fields
1280-------------------------------------------------------
1281
1282This file contains IO statistics for each running process
1283
1284Example
1285-------
1286
1287test:/tmp # dd if=/dev/zero of=/tmp/test.dat &
1288[1] 3828
1289
1290test:/tmp # cat /proc/3828/io
1291rchar: 323934931
1292wchar: 323929600
1293syscr: 632687
1294syscw: 632675
1295read_bytes: 0
1296write_bytes: 323932160
1297cancelled_write_bytes: 0
1298
1299
1300Description
1301-----------
1302
1303rchar
1304-----
1305
1306I/O counter: chars read
1307The number of bytes which this task has caused to be read from storage. This
1308is simply the sum of bytes which this process passed to read() and pread().
1309It includes things like tty IO and it is unaffected by whether or not actual
1310physical disk IO was required (the read might have been satisfied from
1311pagecache)
1312
1313
1314wchar
1315-----
1316
1317I/O counter: chars written
1318The number of bytes which this task has caused, or shall cause to be written
1319to disk. Similar caveats apply here as with rchar.
1320
1321
1322syscr
1323-----
1324
1325I/O counter: read syscalls
1326Attempt to count the number of read I/O operations, i.e. syscalls like read()
1327and pread().
1328
1329
1330syscw
1331-----
1332
1333I/O counter: write syscalls
1334Attempt to count the number of write I/O operations, i.e. syscalls like
1335write() and pwrite().
1336
1337
1338read_bytes
1339----------
1340
1341I/O counter: bytes read
1342Attempt to count the number of bytes which this process really did cause to
1343be fetched from the storage layer. Done at the submit_bio() level, so it is
1344accurate for block-backed filesystems. <please add status regarding NFS and
1345CIFS at a later time>
1346
1347
1348write_bytes
1349-----------
1350
1351I/O counter: bytes written
1352Attempt to count the number of bytes which this process caused to be sent to
1353the storage layer. This is done at page-dirtying time.
1354
1355
1356cancelled_write_bytes
1357---------------------
1358
1359The big inaccuracy here is truncate. If a process writes 1MB to a file and
1360then deletes the file, it will in fact perform no writeout. But it will have
1361been accounted as having caused 1MB of write.
1362In other words: The number of bytes which this process caused to not happen,
1363by truncating pagecache. A task can cause "negative" IO too. If this task
1364truncates some dirty pagecache, some IO which another task has been accounted
1365for (in it's write_bytes) will not be happening. We _could_ just subtract that
1366from the truncating task's write_bytes, but there is information loss in doing
1367that.
1368
1369
1370Note
1371----
1372
1373At its current implementation state, this is a bit racy on 32-bit machines: if
1374process A reads process B's /proc/pid/io while process B is updating one of
1375those 64-bit counters, process A could see an intermediate result.
1376
1377
1378More information about this can be found within the taskstats documentation in
1379Documentation/accounting.
1380
13813.4 /proc/<pid>/coredump_filter - Core dump filtering settings
1382---------------------------------------------------------------
1383When a process is dumped, all anonymous memory is written to a core file as
1384long as the size of the core file isn't limited. But sometimes we don't want
1385to dump some memory segments, for example, huge shared memory. Conversely,
1386sometimes we want to save file-backed memory segments into a core file, not
1387only the individual files.
1388
1389/proc/<pid>/coredump_filter allows you to customize which memory segments
1390will be dumped when the <pid> process is dumped. coredump_filter is a bitmask
1391of memory types. If a bit of the bitmask is set, memory segments of the
1392corresponding memory type are dumped, otherwise they are not dumped.
1393
1394The following 7 memory types are supported:
1395 - (bit 0) anonymous private memory
1396 - (bit 1) anonymous shared memory
1397 - (bit 2) file-backed private memory
1398 - (bit 3) file-backed shared memory
1399 - (bit 4) ELF header pages in file-backed private memory areas (it is
1400 effective only if the bit 2 is cleared)
1401 - (bit 5) hugetlb private memory
1402 - (bit 6) hugetlb shared memory
1403
1404 Note that MMIO pages such as frame buffer are never dumped and vDSO pages
1405 are always dumped regardless of the bitmask status.
1406
1407 Note bit 0-4 doesn't effect any hugetlb memory. hugetlb memory are only
1408 effected by bit 5-6.
1409
1410Default value of coredump_filter is 0x23; this means all anonymous memory
1411segments and hugetlb private memory are dumped.
1412
1413If you don't want to dump all shared memory segments attached to pid 1234,
1414write 0x21 to the process's proc file.
1415
1416 $ echo 0x21 > /proc/1234/coredump_filter
1417
1418When a new process is created, the process inherits the bitmask status from its
1419parent. It is useful to set up coredump_filter before the program runs.
1420For example:
1421
1422 $ echo 0x7 > /proc/self/coredump_filter
1423 $ ./some_program
1424
14253.5 /proc/<pid>/mountinfo - Information about mounts
1426--------------------------------------------------------
1427
1428This file contains lines of the form:
1429
143036 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue
1431(1)(2)(3) (4) (5) (6) (7) (8) (9) (10) (11)
1432
1433(1) mount ID: unique identifier of the mount (may be reused after umount)
1434(2) parent ID: ID of parent (or of self for the top of the mount tree)
1435(3) major:minor: value of st_dev for files on filesystem
1436(4) root: root of the mount within the filesystem
1437(5) mount point: mount point relative to the process's root
1438(6) mount options: per mount options
1439(7) optional fields: zero or more fields of the form "tag[:value]"
1440(8) separator: marks the end of the optional fields
1441(9) filesystem type: name of filesystem of the form "type[.subtype]"
1442(10) mount source: filesystem specific information or "none"
1443(11) super options: per super block options
1444
1445Parsers should ignore all unrecognised optional fields. Currently the
1446possible optional fields are:
1447
1448shared:X mount is shared in peer group X
1449master:X mount is slave to peer group X
1450propagate_from:X mount is slave and receives propagation from peer group X (*)
1451unbindable mount is unbindable
1452
1453(*) X is the closest dominant peer group under the process's root. If
1454X is the immediate master of the mount, or if there's no dominant peer
1455group under the same root, then only the "master:X" field is present
1456and not the "propagate_from:X" field.
1457
1458For more information on mount propagation see:
1459
1460 Documentation/filesystems/sharedsubtree.txt
1461
1462
14633.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm
1464--------------------------------------------------------
1465These files provide a method to access a tasks comm value. It also allows for
1466a task to set its own or one of its thread siblings comm value. The comm value
1467is limited in size compared to the cmdline value, so writing anything longer
1468then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated
1469comm value.