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>
7 2.4.x update Jorge Nerin <comandante@zaralinux.com> November 14 2000
8 move /proc/sys Shen Feng <shen@cn.fujitsu.com> April 1 2009
9 ------------------------------------------------------------------------------
10 Version 1.3 Kernel version 2.2.12
11 Kernel version 2.4.0-test11-pre4
12 ------------------------------------------------------------------------------
13 fixes/update part 1.1 Stefani Seibold <stefani@seibold.net> June 9 2009
15 Table of Contents
16 -----------------
18 0 Preface
19 0.1 Introduction/Credits
20 0.2 Legal Stuff
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
33 2 Modifying System Parameters
35 3 Per-Process Parameters
36 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj - Adjust the oom-killer
37 score
38 3.2 /proc/<pid>/oom_score - Display current oom-killer score
39 3.3 /proc/<pid>/io - Display the IO accounting fields
40 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings
41 3.5 /proc/<pid>/mountinfo - Information about mounts
42 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm
43 3.7 /proc/<pid>/task/<tid>/children - Information about task children
44 3.8 /proc/<pid>/fdinfo/<fd> - Information about opened file
46 4 Configuring procfs
47 4.1 Mount options
49 ------------------------------------------------------------------------------
50 Preface
51 ------------------------------------------------------------------------------
53 0.1 Introduction/Credits
54 ------------------------
56 This documentation is part of a soon (or so we hope) to be released book on
57 the SuSE Linux distribution. As there is no complete documentation for the
58 /proc file system and we've used many freely available sources to write these
59 chapters, it seems only fair to give the work back to the Linux community.
60 This work is based on the 2.2.* kernel version and the upcoming 2.4.*. I'm
61 afraid it's still far from complete, but we hope it will be useful. As far as
62 we know, it is the first 'all-in-one' document about the /proc file system. It
63 is focused on the Intel x86 hardware, so if you are looking for PPC, ARM,
64 SPARC, AXP, etc., features, you probably won't find what you are looking for.
65 It also only covers IPv4 networking, not IPv6 nor other protocols - sorry. But
66 additions and patches are welcome and will be added to this document if you
67 mail them to Bodo.
69 We'd like to thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of
70 other people for help compiling this documentation. We'd also like to extend a
71 special thank you to Andi Kleen for documentation, which we relied on heavily
72 to create this document, as well as the additional information he provided.
73 Thanks to everybody else who contributed source or docs to the Linux kernel
74 and helped create a great piece of software... :)
76 If you have any comments, corrections or additions, please don't hesitate to
77 contact Bodo Bauer at bb@ricochet.net. We'll be happy to add them to this
78 document.
80 The latest version of this document is available online at
81 http://tldp.org/LDP/Linux-Filesystem-Hierarchy/html/proc.html
83 If the above direction does not works for you, you could try the kernel
84 mailing list at linux-kernel@vger.kernel.org and/or try to reach me at
85 comandante@zaralinux.com.
87 0.2 Legal Stuff
88 ---------------
90 We don't guarantee the correctness of this document, and if you come to us
91 complaining about how you screwed up your system because of incorrect
92 documentation, we won't feel responsible...
94 ------------------------------------------------------------------------------
95 CHAPTER 1: COLLECTING SYSTEM INFORMATION
96 ------------------------------------------------------------------------------
98 ------------------------------------------------------------------------------
99 In This Chapter
100 ------------------------------------------------------------------------------
101 * Investigating the properties of the pseudo file system /proc and its
102 ability to provide information on the running Linux system
103 * Examining /proc's structure
104 * Uncovering various information about the kernel and the processes running
105 on the system
106 ------------------------------------------------------------------------------
109 The proc file system acts as an interface to internal data structures in the
110 kernel. It can be used to obtain information about the system and to change
111 certain kernel parameters at runtime (sysctl).
113 First, we'll take a look at the read-only parts of /proc. In Chapter 2, we
114 show you how you can use /proc/sys to change settings.
116 1.1 Process-Specific Subdirectories
117 -----------------------------------
119 The directory /proc contains (among other things) one subdirectory for each
120 process running on the system, which is named after the process ID (PID).
122 The link self points to the process reading the file system. Each process
123 subdirectory has the entries listed in Table 1-1.
126 Table 1-1: Process specific entries in /proc
127 ..............................................................................
128 File Content
129 clear_refs Clears page referenced bits shown in smaps output
130 cmdline Command line arguments
131 cpu Current and last cpu in which it was executed (2.4)(smp)
132 cwd Link to the current working directory
133 environ Values of environment variables
134 exe Link to the executable of this process
135 fd Directory, which contains all file descriptors
136 maps Memory maps to executables and library files (2.4)
137 mem Memory held by this process
138 root Link to the root directory of this process
139 stat Process status
140 statm Process memory status information
141 status Process status in human readable form
142 wchan If CONFIG_KALLSYMS is set, a pre-decoded wchan
143 pagemap Page table
144 stack Report full stack trace, enable via CONFIG_STACKTRACE
145 smaps a extension based on maps, showing the memory consumption of
146 each mapping and flags associated with it
147 ..............................................................................
149 For example, to get the status information of a process, all you have to do is
150 read the file /proc/PID/status:
152 >cat /proc/self/status
153 Name: cat
154 State: R (running)
155 Tgid: 5452
156 Pid: 5452
157 PPid: 743
158 TracerPid: 0 (2.4)
159 Uid: 501 501 501 501
160 Gid: 100 100 100 100
161 FDSize: 256
162 Groups: 100 14 16
163 VmPeak: 5004 kB
164 VmSize: 5004 kB
165 VmLck: 0 kB
166 VmHWM: 476 kB
167 VmRSS: 476 kB
168 VmData: 156 kB
169 VmStk: 88 kB
170 VmExe: 68 kB
171 VmLib: 1412 kB
172 VmPTE: 20 kb
173 VmSwap: 0 kB
174 Threads: 1
175 SigQ: 0/28578
176 SigPnd: 0000000000000000
177 ShdPnd: 0000000000000000
178 SigBlk: 0000000000000000
179 SigIgn: 0000000000000000
180 SigCgt: 0000000000000000
181 CapInh: 00000000fffffeff
182 CapPrm: 0000000000000000
183 CapEff: 0000000000000000
184 CapBnd: ffffffffffffffff
185 Seccomp: 0
186 voluntary_ctxt_switches: 0
187 nonvoluntary_ctxt_switches: 1
189 This shows you nearly the same information you would get if you viewed it with
190 the ps command. In fact, ps uses the proc file system to obtain its
191 information. But you get a more detailed view of the process by reading the
192 file /proc/PID/status. It fields are described in table 1-2.
194 The statm file contains more detailed information about the process
195 memory usage. Its seven fields are explained in Table 1-3. The stat file
196 contains details information about the process itself. Its fields are
197 explained in Table 1-4.
199 (for SMP CONFIG users)
200 For making accounting scalable, RSS related information are handled in
201 asynchronous manner and the vaule may not be very precise. To see a precise
202 snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
203 It's slow but very precise.
205 Table 1-2: Contents of the status files (as of 2.6.30-rc7)
206 ..............................................................................
207 Field Content
208 Name filename of the executable
209 State state (R is running, S is sleeping, D is sleeping
210 in an uninterruptible wait, Z is zombie,
211 T is traced or stopped)
212 Tgid thread group ID
213 Pid process id
214 PPid process id of the parent process
215 TracerPid PID of process tracing this process (0 if not)
216 Uid Real, effective, saved set, and file system UIDs
217 Gid Real, effective, saved set, and file system GIDs
218 FDSize number of file descriptor slots currently allocated
219 Groups supplementary group list
220 VmPeak peak virtual memory size
221 VmSize total program size
222 VmLck locked memory size
223 VmHWM peak resident set size ("high water mark")
224 VmRSS size of memory portions
225 VmData size of data, stack, and text segments
226 VmStk size of data, stack, and text segments
227 VmExe size of text segment
228 VmLib size of shared library code
229 VmPTE size of page table entries
230 VmSwap size of swap usage (the number of referred swapents)
231 Threads number of threads
232 SigQ number of signals queued/max. number for queue
233 SigPnd bitmap of pending signals for the thread
234 ShdPnd bitmap of shared pending signals for the process
235 SigBlk bitmap of blocked signals
236 SigIgn bitmap of ignored signals
237 SigCgt bitmap of catched signals
238 CapInh bitmap of inheritable capabilities
239 CapPrm bitmap of permitted capabilities
240 CapEff bitmap of effective capabilities
241 CapBnd bitmap of capabilities bounding set
242 Seccomp seccomp mode, like prctl(PR_GET_SECCOMP, ...)
243 Cpus_allowed mask of CPUs on which this process may run
244 Cpus_allowed_list Same as previous, but in "list format"
245 Mems_allowed mask of memory nodes allowed to this process
246 Mems_allowed_list Same as previous, but in "list format"
247 voluntary_ctxt_switches number of voluntary context switches
248 nonvoluntary_ctxt_switches number of non voluntary context switches
249 ..............................................................................
251 Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
252 ..............................................................................
253 Field Content
254 size total program size (pages) (same as VmSize in status)
255 resident size of memory portions (pages) (same as VmRSS in status)
256 shared number of pages that are shared (i.e. backed by a file)
257 trs number of pages that are 'code' (not including libs; broken,
258 includes data segment)
259 lrs number of pages of library (always 0 on 2.6)
260 drs number of pages of data/stack (including libs; broken,
261 includes library text)
262 dt number of dirty pages (always 0 on 2.6)
263 ..............................................................................
266 Table 1-4: Contents of the stat files (as of 2.6.30-rc7)
267 ..............................................................................
268 Field Content
269 pid process id
270 tcomm filename of the executable
271 state state (R is running, S is sleeping, D is sleeping in an
272 uninterruptible wait, Z is zombie, T is traced or stopped)
273 ppid process id of the parent process
274 pgrp pgrp of the process
275 sid session id
276 tty_nr tty the process uses
277 tty_pgrp pgrp of the tty
278 flags task flags
279 min_flt number of minor faults
280 cmin_flt number of minor faults with child's
281 maj_flt number of major faults
282 cmaj_flt number of major faults with child's
283 utime user mode jiffies
284 stime kernel mode jiffies
285 cutime user mode jiffies with child's
286 cstime kernel mode jiffies with child's
287 priority priority level
288 nice nice level
289 num_threads number of threads
290 it_real_value (obsolete, always 0)
291 start_time time the process started after system boot
292 vsize virtual memory size
293 rss resident set memory size
294 rsslim current limit in bytes on the rss
295 start_code address above which program text can run
296 end_code address below which program text can run
297 start_stack address of the start of the main process stack
298 esp current value of ESP
299 eip current value of EIP
300 pending bitmap of pending signals
301 blocked bitmap of blocked signals
302 sigign bitmap of ignored signals
303 sigcatch bitmap of catched signals
304 wchan address where process went to sleep
305 0 (place holder)
306 0 (place holder)
307 exit_signal signal to send to parent thread on exit
308 task_cpu which CPU the task is scheduled on
309 rt_priority realtime priority
310 policy scheduling policy (man sched_setscheduler)
311 blkio_ticks time spent waiting for block IO
312 gtime guest time of the task in jiffies
313 cgtime guest time of the task children in jiffies
314 start_data address above which program data+bss is placed
315 end_data address below which program data+bss is placed
316 start_brk address above which program heap can be expanded with brk()
317 arg_start address above which program command line is placed
318 arg_end address below which program command line is placed
319 env_start address above which program environment is placed
320 env_end address below which program environment is placed
321 exit_code the thread's exit_code in the form reported by the waitpid system call
322 ..............................................................................
324 The /proc/PID/maps file containing the currently mapped memory regions and
325 their access permissions.
327 The format is:
329 address perms offset dev inode pathname
331 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test
332 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test
333 0804a000-0806b000 rw-p 00000000 00:00 0 [heap]
334 a7cb1000-a7cb2000 ---p 00000000 00:00 0
335 a7cb2000-a7eb2000 rw-p 00000000 00:00 0
336 a7eb2000-a7eb3000 ---p 00000000 00:00 0
337 a7eb3000-a7ed5000 rw-p 00000000 00:00 0 [stack:1001]
338 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6
339 a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6
340 a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6
341 a800b000-a800e000 rw-p 00000000 00:00 0
342 a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0
343 a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0
344 a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0
345 a8024000-a8027000 rw-p 00000000 00:00 0
346 a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2
347 a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2
348 a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2
349 aff35000-aff4a000 rw-p 00000000 00:00 0 [stack]
350 ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso]
352 where "address" is the address space in the process that it occupies, "perms"
353 is a set of permissions:
355 r = read
356 w = write
357 x = execute
358 s = shared
359 p = private (copy on write)
361 "offset" is the offset into the mapping, "dev" is the device (major:minor), and
362 "inode" is the inode on that device. 0 indicates that no inode is associated
363 with the memory region, as the case would be with BSS (uninitialized data).
364 The "pathname" shows the name associated file for this mapping. If the mapping
365 is not associated with a file:
367 [heap] = the heap of the program
368 [stack] = the stack of the main process
369 [stack:1001] = the stack of the thread with tid 1001
370 [vdso] = the "virtual dynamic shared object",
371 the kernel system call handler
372 [anon:<name>] = an anonymous mapping that has been
373 named by userspace
375 or if empty, the mapping is anonymous.
377 The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint
378 of the individual tasks of a process. In this file you will see a mapping marked
379 as [stack] if that task sees it as a stack. This is a key difference from the
380 content of /proc/PID/maps, where you will see all mappings that are being used
381 as stack by all of those tasks. Hence, for the example above, the task-level
382 map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
384 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test
385 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test
386 0804a000-0806b000 rw-p 00000000 00:00 0 [heap]
387 a7cb1000-a7cb2000 ---p 00000000 00:00 0
388 a7cb2000-a7eb2000 rw-p 00000000 00:00 0
389 a7eb2000-a7eb3000 ---p 00000000 00:00 0
390 a7eb3000-a7ed5000 rw-p 00000000 00:00 0 [stack]
391 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6
392 a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6
393 a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6
394 a800b000-a800e000 rw-p 00000000 00:00 0
395 a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0
396 a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0
397 a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0
398 a8024000-a8027000 rw-p 00000000 00:00 0
399 a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2
400 a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2
401 a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2
402 aff35000-aff4a000 rw-p 00000000 00:00 0
403 ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso]
405 The /proc/PID/smaps is an extension based on maps, showing the memory
406 consumption for each of the process's mappings. For each of mappings there
407 is a series of lines such as the following:
409 08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash
410 Size: 1084 kB
411 Rss: 892 kB
412 Pss: 374 kB
413 Shared_Clean: 892 kB
414 Shared_Dirty: 0 kB
415 Private_Clean: 0 kB
416 Private_Dirty: 0 kB
417 Referenced: 892 kB
418 Anonymous: 0 kB
419 Swap: 0 kB
420 KernelPageSize: 4 kB
421 MMUPageSize: 4 kB
422 Locked: 374 kB
423 VmFlags: rd ex mr mw me de
424 Name: name from userspace
426 the first of these lines shows the same information as is displayed for the
427 mapping in /proc/PID/maps. The remaining lines show the size of the mapping
428 (size), the amount of the mapping that is currently resident in RAM (RSS), the
429 process' proportional share of this mapping (PSS), the number of clean and
430 dirty private pages in the mapping. Note that even a page which is part of a
431 MAP_SHARED mapping, but has only a single pte mapped, i.e. is currently used
432 by only one process, is accounted as private and not as shared. "Referenced"
433 indicates the amount of memory currently marked as referenced or accessed.
434 "Anonymous" shows the amount of memory that does not belong to any file. Even
435 a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
436 and a page is modified, the file page is replaced by a private anonymous copy.
437 "Swap" shows how much would-be-anonymous memory is also used, but out on
438 swap.
440 "VmFlags" field deserves a separate description. This member represents the kernel
441 flags associated with the particular virtual memory area in two letter encoded
442 manner. The codes are the following:
443 rd - readable
444 wr - writeable
445 ex - executable
446 sh - shared
447 mr - may read
448 mw - may write
449 me - may execute
450 ms - may share
451 gd - stack segment growns down
452 pf - pure PFN range
453 dw - disabled write to the mapped file
454 lo - pages are locked in memory
455 io - memory mapped I/O area
456 sr - sequential read advise provided
457 rr - random read advise provided
458 dc - do not copy area on fork
459 de - do not expand area on remapping
460 ac - area is accountable
461 nr - swap space is not reserved for the area
462 ht - area uses huge tlb pages
463 nl - non-linear mapping
464 ar - architecture specific flag
465 dd - do not include area into core dump
466 sd - soft-dirty flag
467 mm - mixed map area
468 hg - huge page advise flag
469 nh - no-huge page advise flag
470 mg - mergable advise flag
472 Note that there is no guarantee that every flag and associated mnemonic will
473 be present in all further kernel releases. Things get changed, the flags may
474 be vanished or the reverse -- new added.
476 The "Name" field will only be present on a mapping that has been named by
477 userspace, and will show the name passed in by userspace.
479 This file is only present if the CONFIG_MMU kernel configuration option is
480 enabled.
482 The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
483 bits on both physical and virtual pages associated with a process, and the
484 soft-dirty bit on pte (see Documentation/vm/soft-dirty.txt for details).
485 To clear the bits for all the pages associated with the process
486 > echo 1 > /proc/PID/clear_refs
488 To clear the bits for the anonymous pages associated with the process
489 > echo 2 > /proc/PID/clear_refs
491 To clear the bits for the file mapped pages associated with the process
492 > echo 3 > /proc/PID/clear_refs
494 To clear the soft-dirty bit
495 > echo 4 > /proc/PID/clear_refs
497 Any other value written to /proc/PID/clear_refs will have no effect.
499 The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
500 using /proc/kpageflags and number of times a page is mapped using
501 /proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.txt.
503 1.2 Kernel data
504 ---------------
506 Similar to the process entries, the kernel data files give information about
507 the running kernel. The files used to obtain this information are contained in
508 /proc and are listed in Table 1-5. Not all of these will be present in your
509 system. It depends on the kernel configuration and the loaded modules, which
510 files are there, and which are missing.
512 Table 1-5: Kernel info in /proc
513 ..............................................................................
514 File Content
515 apm Advanced power management info
516 buddyinfo Kernel memory allocator information (see text) (2.5)
517 bus Directory containing bus specific information
518 cmdline Kernel command line
519 cpuinfo Info about the CPU
520 devices Available devices (block and character)
521 dma Used DMS channels
522 filesystems Supported filesystems
523 driver Various drivers grouped here, currently rtc (2.4)
524 execdomains Execdomains, related to security (2.4)
525 fb Frame Buffer devices (2.4)
526 fs File system parameters, currently nfs/exports (2.4)
527 ide Directory containing info about the IDE subsystem
528 interrupts Interrupt usage
529 iomem Memory map (2.4)
530 ioports I/O port usage
531 irq Masks for irq to cpu affinity (2.4)(smp?)
532 isapnp ISA PnP (Plug&Play) Info (2.4)
533 kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4))
534 kmsg Kernel messages
535 ksyms Kernel symbol table
536 loadavg Load average of last 1, 5 & 15 minutes
537 locks Kernel locks
538 meminfo Memory info
539 misc Miscellaneous
540 modules List of loaded modules
541 mounts Mounted filesystems
542 net Networking info (see text)
543 pagetypeinfo Additional page allocator information (see text) (2.5)
544 partitions Table of partitions known to the system
545 pci Deprecated info of PCI bus (new way -> /proc/bus/pci/,
546 decoupled by lspci (2.4)
547 rtc Real time clock
548 scsi SCSI info (see text)
549 slabinfo Slab pool info
550 softirqs softirq usage
551 stat Overall statistics
552 swaps Swap space utilization
553 sys See chapter 2
554 sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4)
555 tty Info of tty drivers
556 uptime Wall clock since boot, combined idle time of all cpus
557 version Kernel version
558 video bttv info of video resources (2.4)
559 vmallocinfo Show vmalloced areas
560 ..............................................................................
562 You can, for example, check which interrupts are currently in use and what
563 they are used for by looking in the file /proc/interrupts:
565 > cat /proc/interrupts
566 CPU0
567 0: 8728810 XT-PIC timer
568 1: 895 XT-PIC keyboard
569 2: 0 XT-PIC cascade
570 3: 531695 XT-PIC aha152x
571 4: 2014133 XT-PIC serial
572 5: 44401 XT-PIC pcnet_cs
573 8: 2 XT-PIC rtc
574 11: 8 XT-PIC i82365
575 12: 182918 XT-PIC PS/2 Mouse
576 13: 1 XT-PIC fpu
577 14: 1232265 XT-PIC ide0
578 15: 7 XT-PIC ide1
579 NMI: 0
581 In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the
582 output of a SMP machine):
584 > cat /proc/interrupts
586 CPU0 CPU1
587 0: 1243498 1214548 IO-APIC-edge timer
588 1: 8949 8958 IO-APIC-edge keyboard
589 2: 0 0 XT-PIC cascade
590 5: 11286 10161 IO-APIC-edge soundblaster
591 8: 1 0 IO-APIC-edge rtc
592 9: 27422 27407 IO-APIC-edge 3c503
593 12: 113645 113873 IO-APIC-edge PS/2 Mouse
594 13: 0 0 XT-PIC fpu
595 14: 22491 24012 IO-APIC-edge ide0
596 15: 2183 2415 IO-APIC-edge ide1
597 17: 30564 30414 IO-APIC-level eth0
598 18: 177 164 IO-APIC-level bttv
599 NMI: 2457961 2457959
600 LOC: 2457882 2457881
601 ERR: 2155
603 NMI is incremented in this case because every timer interrupt generates a NMI
604 (Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups.
606 LOC is the local interrupt counter of the internal APIC of every CPU.
608 ERR is incremented in the case of errors in the IO-APIC bus (the bus that
609 connects the CPUs in a SMP system. This means that an error has been detected,
610 the IO-APIC automatically retry the transmission, so it should not be a big
611 problem, but you should read the SMP-FAQ.
613 In 2.6.2* /proc/interrupts was expanded again. This time the goal was for
614 /proc/interrupts to display every IRQ vector in use by the system, not
615 just those considered 'most important'. The new vectors are:
617 THR -- interrupt raised when a machine check threshold counter
618 (typically counting ECC corrected errors of memory or cache) exceeds
619 a configurable threshold. Only available on some systems.
621 TRM -- a thermal event interrupt occurs when a temperature threshold
622 has been exceeded for the CPU. This interrupt may also be generated
623 when the temperature drops back to normal.
625 SPU -- a spurious interrupt is some interrupt that was raised then lowered
626 by some IO device before it could be fully processed by the APIC. Hence
627 the APIC sees the interrupt but does not know what device it came from.
628 For this case the APIC will generate the interrupt with a IRQ vector
629 of 0xff. This might also be generated by chipset bugs.
631 RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are
632 sent from one CPU to another per the needs of the OS. Typically,
633 their statistics are used by kernel developers and interested users to
634 determine the occurrence of interrupts of the given type.
636 The above IRQ vectors are displayed only when relevant. For example,
637 the threshold vector does not exist on x86_64 platforms. Others are
638 suppressed when the system is a uniprocessor. As of this writing, only
639 i386 and x86_64 platforms support the new IRQ vector displays.
641 Of some interest is the introduction of the /proc/irq directory to 2.4.
642 It could be used to set IRQ to CPU affinity, this means that you can "hook" an
643 IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
644 irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and
645 prof_cpu_mask.
647 For example
648 > ls /proc/irq/
649 0 10 12 14 16 18 2 4 6 8 prof_cpu_mask
650 1 11 13 15 17 19 3 5 7 9 default_smp_affinity
651 > ls /proc/irq/0/
652 smp_affinity
654 smp_affinity is a bitmask, in which you can specify which CPUs can handle the
655 IRQ, you can set it by doing:
657 > echo 1 > /proc/irq/10/smp_affinity
659 This means that only the first CPU will handle the IRQ, but you can also echo
660 5 which means that only the first and fourth CPU can handle the IRQ.
662 The contents of each smp_affinity file is the same by default:
664 > cat /proc/irq/0/smp_affinity
665 ffffffff
667 There is an alternate interface, smp_affinity_list which allows specifying
668 a cpu range instead of a bitmask:
670 > cat /proc/irq/0/smp_affinity_list
671 1024-1031
673 The default_smp_affinity mask applies to all non-active IRQs, which are the
674 IRQs which have not yet been allocated/activated, and hence which lack a
675 /proc/irq/[0-9]* directory.
677 The node file on an SMP system shows the node to which the device using the IRQ
678 reports itself as being attached. This hardware locality information does not
679 include information about any possible driver locality preference.
681 prof_cpu_mask specifies which CPUs are to be profiled by the system wide
682 profiler. Default value is ffffffff (all cpus if there are only 32 of them).
684 The way IRQs are routed is handled by the IO-APIC, and it's Round Robin
685 between all the CPUs which are allowed to handle it. As usual the kernel has
686 more info than you and does a better job than you, so the defaults are the
687 best choice for almost everyone. [Note this applies only to those IO-APIC's
688 that support "Round Robin" interrupt distribution.]
690 There are three more important subdirectories in /proc: net, scsi, and sys.
691 The general rule is that the contents, or even the existence of these
692 directories, depend on your kernel configuration. If SCSI is not enabled, the
693 directory scsi may not exist. The same is true with the net, which is there
694 only when networking support is present in the running kernel.
696 The slabinfo file gives information about memory usage at the slab level.
697 Linux uses slab pools for memory management above page level in version 2.2.
698 Commonly used objects have their own slab pool (such as network buffers,
699 directory cache, and so on).
701 ..............................................................................
703 > cat /proc/buddyinfo
705 Node 0, zone DMA 0 4 5 4 4 3 ...
706 Node 0, zone Normal 1 0 0 1 101 8 ...
707 Node 0, zone HighMem 2 0 0 1 1 0 ...
709 External fragmentation is a problem under some workloads, and buddyinfo is a
710 useful tool for helping diagnose these problems. Buddyinfo will give you a
711 clue as to how big an area you can safely allocate, or why a previous
712 allocation failed.
714 Each column represents the number of pages of a certain order which are
715 available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in
716 ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE
717 available in ZONE_NORMAL, etc...
719 More information relevant to external fragmentation can be found in
720 pagetypeinfo.
722 > cat /proc/pagetypeinfo
723 Page block order: 9
724 Pages per block: 512
726 Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
727 Node 0, zone DMA, type Unmovable 0 0 0 1 1 1 1 1 1 1 0
728 Node 0, zone DMA, type Reclaimable 0 0 0 0 0 0 0 0 0 0 0
729 Node 0, zone DMA, type Movable 1 1 2 1 2 1 1 0 1 0 2
730 Node 0, zone DMA, type Reserve 0 0 0 0 0 0 0 0 0 1 0
731 Node 0, zone DMA, type Isolate 0 0 0 0 0 0 0 0 0 0 0
732 Node 0, zone DMA32, type Unmovable 103 54 77 1 1 1 11 8 7 1 9
733 Node 0, zone DMA32, type Reclaimable 0 0 2 1 0 0 0 0 1 0 0
734 Node 0, zone DMA32, type Movable 169 152 113 91 77 54 39 13 6 1 452
735 Node 0, zone DMA32, type Reserve 1 2 2 2 2 0 1 1 1 1 0
736 Node 0, zone DMA32, type Isolate 0 0 0 0 0 0 0 0 0 0 0
738 Number of blocks type Unmovable Reclaimable Movable Reserve Isolate
739 Node 0, zone DMA 2 0 5 1 0
740 Node 0, zone DMA32 41 6 967 2 0
742 Fragmentation avoidance in the kernel works by grouping pages of different
743 migrate types into the same contiguous regions of memory called page blocks.
744 A page block is typically the size of the default hugepage size e.g. 2MB on
745 X86-64. By keeping pages grouped based on their ability to move, the kernel
746 can reclaim pages within a page block to satisfy a high-order allocation.
748 The pagetypinfo begins with information on the size of a page block. It
749 then gives the same type of information as buddyinfo except broken down
750 by migrate-type and finishes with details on how many page blocks of each
751 type exist.
753 If min_free_kbytes has been tuned correctly (recommendations made by hugeadm
754 from libhugetlbfs http://sourceforge.net/projects/libhugetlbfs/), one can
755 make an estimate of the likely number of huge pages that can be allocated
756 at a given point in time. All the "Movable" blocks should be allocatable
757 unless memory has been mlock()'d. Some of the Reclaimable blocks should
758 also be allocatable although a lot of filesystem metadata may have to be
759 reclaimed to achieve this.
761 ..............................................................................
763 meminfo:
765 Provides information about distribution and utilization of memory. This
766 varies by architecture and compile options. The following is from a
767 16GB PIII, which has highmem enabled. You may not have all of these fields.
769 > cat /proc/meminfo
771 The "Locked" indicates whether the mapping is locked in memory or not.
774 MemTotal: 16344972 kB
775 MemFree: 13634064 kB
776 MemAvailable: 14836172 kB
777 Buffers: 3656 kB
778 Cached: 1195708 kB
779 SwapCached: 0 kB
780 Active: 891636 kB
781 Inactive: 1077224 kB
782 HighTotal: 15597528 kB
783 HighFree: 13629632 kB
784 LowTotal: 747444 kB
785 LowFree: 4432 kB
786 SwapTotal: 0 kB
787 SwapFree: 0 kB
788 Dirty: 968 kB
789 Writeback: 0 kB
790 AnonPages: 861800 kB
791 Mapped: 280372 kB
792 Slab: 284364 kB
793 SReclaimable: 159856 kB
794 SUnreclaim: 124508 kB
795 PageTables: 24448 kB
796 NFS_Unstable: 0 kB
797 Bounce: 0 kB
798 WritebackTmp: 0 kB
799 CommitLimit: 7669796 kB
800 Committed_AS: 100056 kB
801 VmallocTotal: 112216 kB
802 VmallocUsed: 428 kB
803 VmallocChunk: 111088 kB
804 AnonHugePages: 49152 kB
806 MemTotal: Total usable ram (i.e. physical ram minus a few reserved
807 bits and the kernel binary code)
808 MemFree: The sum of LowFree+HighFree
809 MemAvailable: An estimate of how much memory is available for starting new
810 applications, without swapping. Calculated from MemFree,
811 SReclaimable, the size of the file LRU lists, and the low
812 watermarks in each zone.
813 The estimate takes into account that the system needs some
814 page cache to function well, and that not all reclaimable
815 slab will be reclaimable, due to items being in use. The
816 impact of those factors will vary from system to system.
817 Buffers: Relatively temporary storage for raw disk blocks
818 shouldn't get tremendously large (20MB or so)
819 Cached: in-memory cache for files read from the disk (the
820 pagecache). Doesn't include SwapCached
821 SwapCached: Memory that once was swapped out, is swapped back in but
822 still also is in the swapfile (if memory is needed it
823 doesn't need to be swapped out AGAIN because it is already
824 in the swapfile. This saves I/O)
825 Active: Memory that has been used more recently and usually not
826 reclaimed unless absolutely necessary.
827 Inactive: Memory which has been less recently used. It is more
828 eligible to be reclaimed for other purposes
829 HighTotal:
830 HighFree: Highmem is all memory above ~860MB of physical memory
831 Highmem areas are for use by userspace programs, or
832 for the pagecache. The kernel must use tricks to access
833 this memory, making it slower to access than lowmem.
834 LowTotal:
835 LowFree: Lowmem is memory which can be used for everything that
836 highmem can be used for, but it is also available for the
837 kernel's use for its own data structures. Among many
838 other things, it is where everything from the Slab is
839 allocated. Bad things happen when you're out of lowmem.
840 SwapTotal: total amount of swap space available
841 SwapFree: Memory which has been evicted from RAM, and is temporarily
842 on the disk
843 Dirty: Memory which is waiting to get written back to the disk
844 Writeback: Memory which is actively being written back to the disk
845 AnonPages: Non-file backed pages mapped into userspace page tables
846 AnonHugePages: Non-file backed huge pages mapped into userspace page tables
847 Mapped: files which have been mmaped, such as libraries
848 Slab: in-kernel data structures cache
849 SReclaimable: Part of Slab, that might be reclaimed, such as caches
850 SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure
851 PageTables: amount of memory dedicated to the lowest level of page
852 tables.
853 NFS_Unstable: NFS pages sent to the server, but not yet committed to stable
854 storage
855 Bounce: Memory used for block device "bounce buffers"
856 WritebackTmp: Memory used by FUSE for temporary writeback buffers
857 CommitLimit: Based on the overcommit ratio ('vm.overcommit_ratio'),
858 this is the total amount of memory currently available to
859 be allocated on the system. This limit is only adhered to
860 if strict overcommit accounting is enabled (mode 2 in
861 'vm.overcommit_memory').
862 The CommitLimit is calculated with the following formula:
863 CommitLimit = ('vm.overcommit_ratio' * Physical RAM) + Swap
864 For example, on a system with 1G of physical RAM and 7G
865 of swap with a `vm.overcommit_ratio` of 30 it would
866 yield a CommitLimit of 7.3G.
867 For more details, see the memory overcommit documentation
868 in vm/overcommit-accounting.
869 Committed_AS: The amount of memory presently allocated on the system.
870 The committed memory is a sum of all of the memory which
871 has been allocated by processes, even if it has not been
872 "used" by them as of yet. A process which malloc()'s 1G
873 of memory, but only touches 300M of it will show up as
874 using 1G. This 1G is memory which has been "committed" to
875 by the VM and can be used at any time by the allocating
876 application. With strict overcommit enabled on the system
877 (mode 2 in 'vm.overcommit_memory'),allocations which would
878 exceed the CommitLimit (detailed above) will not be permitted.
879 This is useful if one needs to guarantee that processes will
880 not fail due to lack of memory once that memory has been
881 successfully allocated.
882 VmallocTotal: total size of vmalloc memory area
883 VmallocUsed: amount of vmalloc area which is used
884 VmallocChunk: largest contiguous block of vmalloc area which is free
886 ..............................................................................
888 vmallocinfo:
890 Provides information about vmalloced/vmaped areas. One line per area,
891 containing the virtual address range of the area, size in bytes,
892 caller information of the creator, and optional information depending
893 on the kind of area :
895 pages=nr number of pages
896 phys=addr if a physical address was specified
897 ioremap I/O mapping (ioremap() and friends)
898 vmalloc vmalloc() area
899 vmap vmap()ed pages
900 user VM_USERMAP area
901 vpages buffer for pages pointers was vmalloced (huge area)
902 N<node>=nr (Only on NUMA kernels)
903 Number of pages allocated on memory node <node>
905 > cat /proc/vmallocinfo
906 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ...
907 /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128
908 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ...
909 /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64
910 0xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f...
911 phys=7fee8000 ioremap
912 0xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f...
913 phys=7fee7000 ioremap
914 0xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210
915 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ...
916 /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3
917 0xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ...
918 pages=2 vmalloc N1=2
919 0xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ...
920 /0x130 [x_tables] pages=4 vmalloc N0=4
921 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ...
922 pages=14 vmalloc N2=14
923 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ...
924 pages=4 vmalloc N1=4
925 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ...
926 pages=2 vmalloc N1=2
927 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ...
928 pages=10 vmalloc N0=10
930 ..............................................................................
932 softirqs:
934 Provides counts of softirq handlers serviced since boot time, for each cpu.
936 > cat /proc/softirqs
937 CPU0 CPU1 CPU2 CPU3
938 HI: 0 0 0 0
939 TIMER: 27166 27120 27097 27034
940 NET_TX: 0 0 0 17
941 NET_RX: 42 0 0 39
942 BLOCK: 0 0 107 1121
943 TASKLET: 0 0 0 290
944 SCHED: 27035 26983 26971 26746
945 HRTIMER: 0 0 0 0
946 RCU: 1678 1769 2178 2250
949 1.3 IDE devices in /proc/ide
950 ----------------------------
952 The subdirectory /proc/ide contains information about all IDE devices of which
953 the kernel is aware. There is one subdirectory for each IDE controller, the
954 file drivers and a link for each IDE device, pointing to the device directory
955 in the controller specific subtree.
957 The file drivers contains general information about the drivers used for the
958 IDE devices:
960 > cat /proc/ide/drivers
961 ide-cdrom version 4.53
962 ide-disk version 1.08
964 More detailed information can be found in the controller specific
965 subdirectories. These are named ide0, ide1 and so on. Each of these
966 directories contains the files shown in table 1-6.
969 Table 1-6: IDE controller info in /proc/ide/ide?
970 ..............................................................................
971 File Content
972 channel IDE channel (0 or 1)
973 config Configuration (only for PCI/IDE bridge)
974 mate Mate name
975 model Type/Chipset of IDE controller
976 ..............................................................................
978 Each device connected to a controller has a separate subdirectory in the
979 controllers directory. The files listed in table 1-7 are contained in these
980 directories.
983 Table 1-7: IDE device information
984 ..............................................................................
985 File Content
986 cache The cache
987 capacity Capacity of the medium (in 512Byte blocks)
988 driver driver and version
989 geometry physical and logical geometry
990 identify device identify block
991 media media type
992 model device identifier
993 settings device setup
994 smart_thresholds IDE disk management thresholds
995 smart_values IDE disk management values
996 ..............................................................................
998 The most interesting file is settings. This file contains a nice overview of
999 the drive parameters:
1001 # cat /proc/ide/ide0/hda/settings
1002 name value min max mode
1003 ---- ----- --- --- ----
1004 bios_cyl 526 0 65535 rw
1005 bios_head 255 0 255 rw
1006 bios_sect 63 0 63 rw
1007 breada_readahead 4 0 127 rw
1008 bswap 0 0 1 r
1009 file_readahead 72 0 2097151 rw
1010 io_32bit 0 0 3 rw
1011 keepsettings 0 0 1 rw
1012 max_kb_per_request 122 1 127 rw
1013 multcount 0 0 8 rw
1014 nice1 1 0 1 rw
1015 nowerr 0 0 1 rw
1016 pio_mode write-only 0 255 w
1017 slow 0 0 1 rw
1018 unmaskirq 0 0 1 rw
1019 using_dma 0 0 1 rw
1022 1.4 Networking info in /proc/net
1023 --------------------------------
1025 The subdirectory /proc/net follows the usual pattern. Table 1-8 shows the
1026 additional values you get for IP version 6 if you configure the kernel to
1027 support this. Table 1-9 lists the files and their meaning.
1030 Table 1-8: IPv6 info in /proc/net
1031 ..............................................................................
1032 File Content
1033 udp6 UDP sockets (IPv6)
1034 tcp6 TCP sockets (IPv6)
1035 raw6 Raw device statistics (IPv6)
1036 igmp6 IP multicast addresses, which this host joined (IPv6)
1037 if_inet6 List of IPv6 interface addresses
1038 ipv6_route Kernel routing table for IPv6
1039 rt6_stats Global IPv6 routing tables statistics
1040 sockstat6 Socket statistics (IPv6)
1041 snmp6 Snmp data (IPv6)
1042 ..............................................................................
1045 Table 1-9: Network info in /proc/net
1046 ..............................................................................
1047 File Content
1048 arp Kernel ARP table
1049 dev network devices with statistics
1050 dev_mcast the Layer2 multicast groups a device is listening too
1051 (interface index, label, number of references, number of bound
1052 addresses).
1053 dev_stat network device status
1054 ip_fwchains Firewall chain linkage
1055 ip_fwnames Firewall chain names
1056 ip_masq Directory containing the masquerading tables
1057 ip_masquerade Major masquerading table
1058 netstat Network statistics
1059 raw raw device statistics
1060 route Kernel routing table
1061 rpc Directory containing rpc info
1062 rt_cache Routing cache
1063 snmp SNMP data
1064 sockstat Socket statistics
1065 tcp TCP sockets
1066 udp UDP sockets
1067 unix UNIX domain sockets
1068 wireless Wireless interface data (Wavelan etc)
1069 igmp IP multicast addresses, which this host joined
1070 psched Global packet scheduler parameters.
1071 netlink List of PF_NETLINK sockets
1072 ip_mr_vifs List of multicast virtual interfaces
1073 ip_mr_cache List of multicast routing cache
1074 ..............................................................................
1076 You can use this information to see which network devices are available in
1077 your system and how much traffic was routed over those devices:
1079 > cat /proc/net/dev
1080 Inter-|Receive |[...
1081 face |bytes packets errs drop fifo frame compressed multicast|[...
1082 lo: 908188 5596 0 0 0 0 0 0 [...
1083 ppp0:15475140 20721 410 0 0 410 0 0 [...
1084 eth0: 614530 7085 0 0 0 0 0 1 [...
1086 ...] Transmit
1087 ...] bytes packets errs drop fifo colls carrier compressed
1088 ...] 908188 5596 0 0 0 0 0 0
1089 ...] 1375103 17405 0 0 0 0 0 0
1090 ...] 1703981 5535 0 0 0 3 0 0
1092 In addition, each Channel Bond interface has its own directory. For
1093 example, the bond0 device will have a directory called /proc/net/bond0/.
1094 It will contain information that is specific to that bond, such as the
1095 current slaves of the bond, the link status of the slaves, and how
1096 many times the slaves link has failed.
1098 1.5 SCSI info
1099 -------------
1101 If you have a SCSI host adapter in your system, you'll find a subdirectory
1102 named after the driver for this adapter in /proc/scsi. You'll also see a list
1103 of all recognized SCSI devices in /proc/scsi:
1105 >cat /proc/scsi/scsi
1106 Attached devices:
1107 Host: scsi0 Channel: 00 Id: 00 Lun: 00
1108 Vendor: IBM Model: DGHS09U Rev: 03E0
1109 Type: Direct-Access ANSI SCSI revision: 03
1110 Host: scsi0 Channel: 00 Id: 06 Lun: 00
1111 Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04
1112 Type: CD-ROM ANSI SCSI revision: 02
1115 The directory named after the driver has one file for each adapter found in
1116 the system. These files contain information about the controller, including
1117 the used IRQ and the IO address range. The amount of information shown is
1118 dependent on the adapter you use. The example shows the output for an Adaptec
1119 AHA-2940 SCSI adapter:
1121 > cat /proc/scsi/aic7xxx/0
1123 Adaptec AIC7xxx driver version: 5.1.19/3.2.4
1124 Compile Options:
1125 TCQ Enabled By Default : Disabled
1126 AIC7XXX_PROC_STATS : Disabled
1127 AIC7XXX_RESET_DELAY : 5
1128 Adapter Configuration:
1129 SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter
1130 Ultra Wide Controller
1131 PCI MMAPed I/O Base: 0xeb001000
1132 Adapter SEEPROM Config: SEEPROM found and used.
1133 Adaptec SCSI BIOS: Enabled
1134 IRQ: 10
1135 SCBs: Active 0, Max Active 2,
1136 Allocated 15, HW 16, Page 255
1137 Interrupts: 160328
1138 BIOS Control Word: 0x18b6
1139 Adapter Control Word: 0x005b
1140 Extended Translation: Enabled
1141 Disconnect Enable Flags: 0xffff
1142 Ultra Enable Flags: 0x0001
1143 Tag Queue Enable Flags: 0x0000
1144 Ordered Queue Tag Flags: 0x0000
1145 Default Tag Queue Depth: 8
1146 Tagged Queue By Device array for aic7xxx host instance 0:
1147 {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255}
1148 Actual queue depth per device for aic7xxx host instance 0:
1149 {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}
1150 Statistics:
1151 (scsi0:0:0:0)
1152 Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8
1153 Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0)
1154 Total transfers 160151 (74577 reads and 85574 writes)
1155 (scsi0:0:6:0)
1156 Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15
1157 Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0)
1158 Total transfers 0 (0 reads and 0 writes)
1161 1.6 Parallel port info in /proc/parport
1162 ---------------------------------------
1164 The directory /proc/parport contains information about the parallel ports of
1165 your system. It has one subdirectory for each port, named after the port
1166 number (0,1,2,...).
1168 These directories contain the four files shown in Table 1-10.
1171 Table 1-10: Files in /proc/parport
1172 ..............................................................................
1173 File Content
1174 autoprobe Any IEEE-1284 device ID information that has been acquired.
1175 devices list of the device drivers using that port. A + will appear by the
1176 name of the device currently using the port (it might not appear
1177 against any).
1178 hardware Parallel port's base address, IRQ line and DMA channel.
1179 irq IRQ that parport is using for that port. This is in a separate
1180 file to allow you to alter it by writing a new value in (IRQ
1181 number or none).
1182 ..............................................................................
1184 1.7 TTY info in /proc/tty
1185 -------------------------
1187 Information about the available and actually used tty's can be found in the
1188 directory /proc/tty.You'll find entries for drivers and line disciplines in
1189 this directory, as shown in Table 1-11.
1192 Table 1-11: Files in /proc/tty
1193 ..............................................................................
1194 File Content
1195 drivers list of drivers and their usage
1196 ldiscs registered line disciplines
1197 driver/serial usage statistic and status of single tty lines
1198 ..............................................................................
1200 To see which tty's are currently in use, you can simply look into the file
1201 /proc/tty/drivers:
1203 > cat /proc/tty/drivers
1204 pty_slave /dev/pts 136 0-255 pty:slave
1205 pty_master /dev/ptm 128 0-255 pty:master
1206 pty_slave /dev/ttyp 3 0-255 pty:slave
1207 pty_master /dev/pty 2 0-255 pty:master
1208 serial /dev/cua 5 64-67 serial:callout
1209 serial /dev/ttyS 4 64-67 serial
1210 /dev/tty0 /dev/tty0 4 0 system:vtmaster
1211 /dev/ptmx /dev/ptmx 5 2 system
1212 /dev/console /dev/console 5 1 system:console
1213 /dev/tty /dev/tty 5 0 system:/dev/tty
1214 unknown /dev/tty 4 1-63 console
1217 1.8 Miscellaneous kernel statistics in /proc/stat
1218 -------------------------------------------------
1220 Various pieces of information about kernel activity are available in the
1221 /proc/stat file. All of the numbers reported in this file are aggregates
1222 since the system first booted. For a quick look, simply cat the file:
1224 > cat /proc/stat
1225 cpu 2255 34 2290 22625563 6290 127 456 0 0
1226 cpu0 1132 34 1441 11311718 3675 127 438 0 0
1227 cpu1 1123 0 849 11313845 2614 0 18 0 0
1228 intr 114930548 113199788 3 0 5 263 0 4 [... lots more numbers ...]
1229 ctxt 1990473
1230 btime 1062191376
1231 processes 2915
1232 procs_running 1
1233 procs_blocked 0
1234 softirq 183433 0 21755 12 39 1137 231 21459 2263
1236 The very first "cpu" line aggregates the numbers in all of the other "cpuN"
1237 lines. These numbers identify the amount of time the CPU has spent performing
1238 different kinds of work. Time units are in USER_HZ (typically hundredths of a
1239 second). The meanings of the columns are as follows, from left to right:
1241 - user: normal processes executing in user mode
1242 - nice: niced processes executing in user mode
1243 - system: processes executing in kernel mode
1244 - idle: twiddling thumbs
1245 - iowait: waiting for I/O to complete
1246 - irq: servicing interrupts
1247 - softirq: servicing softirqs
1248 - steal: involuntary wait
1249 - guest: running a normal guest
1250 - guest_nice: running a niced guest
1252 The "intr" line gives counts of interrupts serviced since boot time, for each
1253 of the possible system interrupts. The first column is the total of all
1254 interrupts serviced; each subsequent column is the total for that particular
1255 interrupt.
1257 The "ctxt" line gives the total number of context switches across all CPUs.
1259 The "btime" line gives the time at which the system booted, in seconds since
1260 the Unix epoch.
1262 The "processes" line gives the number of processes and threads created, which
1263 includes (but is not limited to) those created by calls to the fork() and
1264 clone() system calls.
1266 The "procs_running" line gives the total number of threads that are
1267 running or ready to run (i.e., the total number of runnable threads).
1269 The "procs_blocked" line gives the number of processes currently blocked,
1270 waiting for I/O to complete.
1272 The "softirq" line gives counts of softirqs serviced since boot time, for each
1273 of the possible system softirqs. The first column is the total of all
1274 softirqs serviced; each subsequent column is the total for that particular
1275 softirq.
1278 1.9 Ext4 file system parameters
1279 ------------------------------
1281 Information about mounted ext4 file systems can be found in
1282 /proc/fs/ext4. Each mounted filesystem will have a directory in
1283 /proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or
1284 /proc/fs/ext4/dm-0). The files in each per-device directory are shown
1285 in Table 1-12, below.
1287 Table 1-12: Files in /proc/fs/ext4/<devname>
1288 ..............................................................................
1289 File Content
1290 mb_groups details of multiblock allocator buddy cache of free blocks
1291 ..............................................................................
1293 2.0 /proc/consoles
1294 ------------------
1295 Shows registered system console lines.
1297 To see which character device lines are currently used for the system console
1298 /dev/console, you may simply look into the file /proc/consoles:
1300 > cat /proc/consoles
1301 tty0 -WU (ECp) 4:7
1302 ttyS0 -W- (Ep) 4:64
1304 The columns are:
1306 device name of the device
1307 operations R = can do read operations
1308 W = can do write operations
1309 U = can do unblank
1310 flags E = it is enabled
1311 C = it is preferred console
1312 B = it is primary boot console
1313 p = it is used for printk buffer
1314 b = it is not a TTY but a Braille device
1315 a = it is safe to use when cpu is offline
1316 major:minor major and minor number of the device separated by a colon
1318 ------------------------------------------------------------------------------
1319 Summary
1320 ------------------------------------------------------------------------------
1321 The /proc file system serves information about the running system. It not only
1322 allows access to process data but also allows you to request the kernel status
1323 by reading files in the hierarchy.
1325 The directory structure of /proc reflects the types of information and makes
1326 it easy, if not obvious, where to look for specific data.
1327 ------------------------------------------------------------------------------
1329 ------------------------------------------------------------------------------
1330 CHAPTER 2: MODIFYING SYSTEM PARAMETERS
1331 ------------------------------------------------------------------------------
1333 ------------------------------------------------------------------------------
1334 In This Chapter
1335 ------------------------------------------------------------------------------
1336 * Modifying kernel parameters by writing into files found in /proc/sys
1337 * Exploring the files which modify certain parameters
1338 * Review of the /proc/sys file tree
1339 ------------------------------------------------------------------------------
1342 A very interesting part of /proc is the directory /proc/sys. This is not only
1343 a source of information, it also allows you to change parameters within the
1344 kernel. Be very careful when attempting this. You can optimize your system,
1345 but you can also cause it to crash. Never alter kernel parameters on a
1346 production system. Set up a development machine and test to make sure that
1347 everything works the way you want it to. You may have no alternative but to
1348 reboot the machine once an error has been made.
1350 To change a value, simply echo the new value into the file. An example is
1351 given below in the section on the file system data. You need to be root to do
1352 this. You can create your own boot script to perform this every time your
1353 system boots.
1355 The files in /proc/sys can be used to fine tune and monitor miscellaneous and
1356 general things in the operation of the Linux kernel. Since some of the files
1357 can inadvertently disrupt your system, it is advisable to read both
1358 documentation and source before actually making adjustments. In any case, be
1359 very careful when writing to any of these files. The entries in /proc may
1360 change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt
1361 review the kernel documentation in the directory /usr/src/linux/Documentation.
1362 This chapter is heavily based on the documentation included in the pre 2.2
1363 kernels, and became part of it in version 2.2.1 of the Linux kernel.
1365 Please see: Documentation/sysctl/ directory for descriptions of these
1366 entries.
1368 ------------------------------------------------------------------------------
1369 Summary
1370 ------------------------------------------------------------------------------
1371 Certain aspects of kernel behavior can be modified at runtime, without the
1372 need to recompile the kernel, or even to reboot the system. The files in the
1373 /proc/sys tree can not only be read, but also modified. You can use the echo
1374 command to write value into these files, thereby changing the default settings
1375 of the kernel.
1376 ------------------------------------------------------------------------------
1378 ------------------------------------------------------------------------------
1379 CHAPTER 3: PER-PROCESS PARAMETERS
1380 ------------------------------------------------------------------------------
1382 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score
1383 --------------------------------------------------------------------------------
1385 These file can be used to adjust the badness heuristic used to select which
1386 process gets killed in out of memory conditions.
1388 The badness heuristic assigns a value to each candidate task ranging from 0
1389 (never kill) to 1000 (always kill) to determine which process is targeted. The
1390 units are roughly a proportion along that range of allowed memory the process
1391 may allocate from based on an estimation of its current memory and swap use.
1392 For example, if a task is using all allowed memory, its badness score will be
1393 1000. If it is using half of its allowed memory, its score will be 500.
1395 There is an additional factor included in the badness score: the current memory
1396 and swap usage is discounted by 3% for root processes.
1398 The amount of "allowed" memory depends on the context in which the oom killer
1399 was called. If it is due to the memory assigned to the allocating task's cpuset
1400 being exhausted, the allowed memory represents the set of mems assigned to that
1401 cpuset. If it is due to a mempolicy's node(s) being exhausted, the allowed
1402 memory represents the set of mempolicy nodes. If it is due to a memory
1403 limit (or swap limit) being reached, the allowed memory is that configured
1404 limit. Finally, if it is due to the entire system being out of memory, the
1405 allowed memory represents all allocatable resources.
1407 The value of /proc/<pid>/oom_score_adj is added to the badness score before it
1408 is used to determine which task to kill. Acceptable values range from -1000
1409 (OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX). This allows userspace to
1410 polarize the preference for oom killing either by always preferring a certain
1411 task or completely disabling it. The lowest possible value, -1000, is
1412 equivalent to disabling oom killing entirely for that task since it will always
1413 report a badness score of 0.
1415 Consequently, it is very simple for userspace to define the amount of memory to
1416 consider for each task. Setting a /proc/<pid>/oom_score_adj value of +500, for
1417 example, is roughly equivalent to allowing the remainder of tasks sharing the
1418 same system, cpuset, mempolicy, or memory controller resources to use at least
1419 50% more memory. A value of -500, on the other hand, would be roughly
1420 equivalent to discounting 50% of the task's allowed memory from being considered
1421 as scoring against the task.
1423 For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also
1424 be used to tune the badness score. Its acceptable values range from -16
1425 (OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17
1426 (OOM_DISABLE) to disable oom killing entirely for that task. Its value is
1427 scaled linearly with /proc/<pid>/oom_score_adj.
1429 The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last
1430 value set by a CAP_SYS_RESOURCE process. To reduce the value any lower
1431 requires CAP_SYS_RESOURCE.
1433 Caveat: when a parent task is selected, the oom killer will sacrifice any first
1434 generation children with separate address spaces instead, if possible. This
1435 avoids servers and important system daemons from being killed and loses the
1436 minimal amount of work.
1439 3.2 /proc/<pid>/oom_score - Display current oom-killer score
1440 -------------------------------------------------------------
1442 This file can be used to check the current score used by the oom-killer is for
1443 any given <pid>. Use it together with /proc/<pid>/oom_score_adj to tune which
1444 process should be killed in an out-of-memory situation.
1447 3.3 /proc/<pid>/io - Display the IO accounting fields
1448 -------------------------------------------------------
1450 This file contains IO statistics for each running process
1452 Example
1453 -------
1455 test:/tmp # dd if=/dev/zero of=/tmp/test.dat &
1456 [1] 3828
1458 test:/tmp # cat /proc/3828/io
1459 rchar: 323934931
1460 wchar: 323929600
1461 syscr: 632687
1462 syscw: 632675
1463 read_bytes: 0
1464 write_bytes: 323932160
1465 cancelled_write_bytes: 0
1468 Description
1469 -----------
1471 rchar
1472 -----
1474 I/O counter: chars read
1475 The number of bytes which this task has caused to be read from storage. This
1476 is simply the sum of bytes which this process passed to read() and pread().
1477 It includes things like tty IO and it is unaffected by whether or not actual
1478 physical disk IO was required (the read might have been satisfied from
1479 pagecache)
1482 wchar
1483 -----
1485 I/O counter: chars written
1486 The number of bytes which this task has caused, or shall cause to be written
1487 to disk. Similar caveats apply here as with rchar.
1490 syscr
1491 -----
1493 I/O counter: read syscalls
1494 Attempt to count the number of read I/O operations, i.e. syscalls like read()
1495 and pread().
1498 syscw
1499 -----
1501 I/O counter: write syscalls
1502 Attempt to count the number of write I/O operations, i.e. syscalls like
1503 write() and pwrite().
1506 read_bytes
1507 ----------
1509 I/O counter: bytes read
1510 Attempt to count the number of bytes which this process really did cause to
1511 be fetched from the storage layer. Done at the submit_bio() level, so it is
1512 accurate for block-backed filesystems. <please add status regarding NFS and
1513 CIFS at a later time>
1516 write_bytes
1517 -----------
1519 I/O counter: bytes written
1520 Attempt to count the number of bytes which this process caused to be sent to
1521 the storage layer. This is done at page-dirtying time.
1524 cancelled_write_bytes
1525 ---------------------
1527 The big inaccuracy here is truncate. If a process writes 1MB to a file and
1528 then deletes the file, it will in fact perform no writeout. But it will have
1529 been accounted as having caused 1MB of write.
1530 In other words: The number of bytes which this process caused to not happen,
1531 by truncating pagecache. A task can cause "negative" IO too. If this task
1532 truncates some dirty pagecache, some IO which another task has been accounted
1533 for (in its write_bytes) will not be happening. We _could_ just subtract that
1534 from the truncating task's write_bytes, but there is information loss in doing
1535 that.
1538 Note
1539 ----
1541 At its current implementation state, this is a bit racy on 32-bit machines: if
1542 process A reads process B's /proc/pid/io while process B is updating one of
1543 those 64-bit counters, process A could see an intermediate result.
1546 More information about this can be found within the taskstats documentation in
1547 Documentation/accounting.
1549 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings
1550 ---------------------------------------------------------------
1551 When a process is dumped, all anonymous memory is written to a core file as
1552 long as the size of the core file isn't limited. But sometimes we don't want
1553 to dump some memory segments, for example, huge shared memory. Conversely,
1554 sometimes we want to save file-backed memory segments into a core file, not
1555 only the individual files.
1557 /proc/<pid>/coredump_filter allows you to customize which memory segments
1558 will be dumped when the <pid> process is dumped. coredump_filter is a bitmask
1559 of memory types. If a bit of the bitmask is set, memory segments of the
1560 corresponding memory type are dumped, otherwise they are not dumped.
1562 The following 7 memory types are supported:
1563 - (bit 0) anonymous private memory
1564 - (bit 1) anonymous shared memory
1565 - (bit 2) file-backed private memory
1566 - (bit 3) file-backed shared memory
1567 - (bit 4) ELF header pages in file-backed private memory areas (it is
1568 effective only if the bit 2 is cleared)
1569 - (bit 5) hugetlb private memory
1570 - (bit 6) hugetlb shared memory
1572 Note that MMIO pages such as frame buffer are never dumped and vDSO pages
1573 are always dumped regardless of the bitmask status.
1575 Note bit 0-4 doesn't effect any hugetlb memory. hugetlb memory are only
1576 effected by bit 5-6.
1578 Default value of coredump_filter is 0x23; this means all anonymous memory
1579 segments and hugetlb private memory are dumped.
1581 If you don't want to dump all shared memory segments attached to pid 1234,
1582 write 0x21 to the process's proc file.
1584 $ echo 0x21 > /proc/1234/coredump_filter
1586 When a new process is created, the process inherits the bitmask status from its
1587 parent. It is useful to set up coredump_filter before the program runs.
1588 For example:
1590 $ echo 0x7 > /proc/self/coredump_filter
1591 $ ./some_program
1593 3.5 /proc/<pid>/mountinfo - Information about mounts
1594 --------------------------------------------------------
1596 This file contains lines of the form:
1598 36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue
1599 (1)(2)(3) (4) (5) (6) (7) (8) (9) (10) (11)
1601 (1) mount ID: unique identifier of the mount (may be reused after umount)
1602 (2) parent ID: ID of parent (or of self for the top of the mount tree)
1603 (3) major:minor: value of st_dev for files on filesystem
1604 (4) root: root of the mount within the filesystem
1605 (5) mount point: mount point relative to the process's root
1606 (6) mount options: per mount options
1607 (7) optional fields: zero or more fields of the form "tag[:value]"
1608 (8) separator: marks the end of the optional fields
1609 (9) filesystem type: name of filesystem of the form "type[.subtype]"
1610 (10) mount source: filesystem specific information or "none"
1611 (11) super options: per super block options
1613 Parsers should ignore all unrecognised optional fields. Currently the
1614 possible optional fields are:
1616 shared:X mount is shared in peer group X
1617 master:X mount is slave to peer group X
1618 propagate_from:X mount is slave and receives propagation from peer group X (*)
1619 unbindable mount is unbindable
1621 (*) X is the closest dominant peer group under the process's root. If
1622 X is the immediate master of the mount, or if there's no dominant peer
1623 group under the same root, then only the "master:X" field is present
1624 and not the "propagate_from:X" field.
1626 For more information on mount propagation see:
1628 Documentation/filesystems/sharedsubtree.txt
1631 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm
1632 --------------------------------------------------------
1633 These files provide a method to access a tasks comm value. It also allows for
1634 a task to set its own or one of its thread siblings comm value. The comm value
1635 is limited in size compared to the cmdline value, so writing anything longer
1636 then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated
1637 comm value.
1640 3.7 /proc/<pid>/task/<tid>/children - Information about task children
1641 -------------------------------------------------------------------------
1642 This file provides a fast way to retrieve first level children pids
1643 of a task pointed by <pid>/<tid> pair. The format is a space separated
1644 stream of pids.
1646 Note the "first level" here -- if a child has own children they will
1647 not be listed here, one needs to read /proc/<children-pid>/task/<tid>/children
1648 to obtain the descendants.
1650 Since this interface is intended to be fast and cheap it doesn't
1651 guarantee to provide precise results and some children might be
1652 skipped, especially if they've exited right after we printed their
1653 pids, so one need to either stop or freeze processes being inspected
1654 if precise results are needed.
1657 3.7 /proc/<pid>/fdinfo/<fd> - Information about opened file
1658 ---------------------------------------------------------------
1659 This file provides information associated with an opened file. The regular
1660 files have at least two fields -- 'pos' and 'flags'. The 'pos' represents
1661 the current offset of the opened file in decimal form [see lseek(2) for
1662 details] and 'flags' denotes the octal O_xxx mask the file has been
1663 created with [see open(2) for details].
1665 A typical output is
1667 pos: 0
1668 flags: 0100002
1670 The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags
1671 pair provide additional information particular to the objects they represent.
1673 Eventfd files
1674 ~~~~~~~~~~~~~
1675 pos: 0
1676 flags: 04002
1677 eventfd-count: 5a
1679 where 'eventfd-count' is hex value of a counter.
1681 Signalfd files
1682 ~~~~~~~~~~~~~~
1683 pos: 0
1684 flags: 04002
1685 sigmask: 0000000000000200
1687 where 'sigmask' is hex value of the signal mask associated
1688 with a file.
1690 Epoll files
1691 ~~~~~~~~~~~
1692 pos: 0
1693 flags: 02
1694 tfd: 5 events: 1d data: ffffffffffffffff
1696 where 'tfd' is a target file descriptor number in decimal form,
1697 'events' is events mask being watched and the 'data' is data
1698 associated with a target [see epoll(7) for more details].
1700 Fsnotify files
1701 ~~~~~~~~~~~~~~
1702 For inotify files the format is the following
1704 pos: 0
1705 flags: 02000000
1706 inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d
1708 where 'wd' is a watch descriptor in decimal form, ie a target file
1709 descriptor number, 'ino' and 'sdev' are inode and device where the
1710 target file resides and the 'mask' is the mask of events, all in hex
1711 form [see inotify(7) for more details].
1713 If the kernel was built with exportfs support, the path to the target
1714 file is encoded as a file handle. The file handle is provided by three
1715 fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex
1716 format.
1718 If the kernel is built without exportfs support the file handle won't be
1719 printed out.
1721 If there is no inotify mark attached yet the 'inotify' line will be omitted.
1723 For fanotify files the format is
1725 pos: 0
1726 flags: 02
1727 fanotify flags:10 event-flags:0
1728 fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003
1729 fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4
1731 where fanotify 'flags' and 'event-flags' are values used in fanotify_init
1732 call, 'mnt_id' is the mount point identifier, 'mflags' is the value of
1733 flags associated with mark which are tracked separately from events
1734 mask. 'ino', 'sdev' are target inode and device, 'mask' is the events
1735 mask and 'ignored_mask' is the mask of events which are to be ignored.
1736 All in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask'
1737 does provide information about flags and mask used in fanotify_mark
1738 call [see fsnotify manpage for details].
1740 While the first three lines are mandatory and always printed, the rest is
1741 optional and may be omitted if no marks created yet.
1744 ------------------------------------------------------------------------------
1745 Configuring procfs
1746 ------------------------------------------------------------------------------
1748 4.1 Mount options
1749 ---------------------
1751 The following mount options are supported:
1753 hidepid= Set /proc/<pid>/ access mode.
1754 gid= Set the group authorized to learn processes information.
1756 hidepid=0 means classic mode - everybody may access all /proc/<pid>/ directories
1757 (default).
1759 hidepid=1 means users may not access any /proc/<pid>/ directories but their
1760 own. Sensitive files like cmdline, sched*, status are now protected against
1761 other users. This makes it impossible to learn whether any user runs
1762 specific program (given the program doesn't reveal itself by its behaviour).
1763 As an additional bonus, as /proc/<pid>/cmdline is unaccessible for other users,
1764 poorly written programs passing sensitive information via program arguments are
1765 now protected against local eavesdroppers.
1767 hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be fully invisible to other
1768 users. It doesn't mean that it hides a fact whether a process with a specific
1769 pid value exists (it can be learned by other means, e.g. by "kill -0 $PID"),
1770 but it hides process' uid and gid, which may be learned by stat()'ing
1771 /proc/<pid>/ otherwise. It greatly complicates an intruder's task of gathering
1772 information about running processes, whether some daemon runs with elevated
1773 privileges, whether other user runs some sensitive program, whether other users
1774 run any program at all, etc.
1776 gid= defines a group authorized to learn processes information otherwise
1777 prohibited by hidepid=. If you use some daemon like identd which needs to learn
1778 information about processes information, just add identd to this group.