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
19 0.1 Introduction/Credits
22 1 Collecting System Information
23 1.1 Process-Specific Subdirectories
25 1.3 IDE devices in /proc/ide
26 1.4 Networking info in /proc/net
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
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
45 3.9 /proc/<pid>/map_files - Information about memory mapped files
50 ------------------------------------------------------------------------------
52 ------------------------------------------------------------------------------
54 0.1 Introduction/Credits
55 ------------------------
57 This documentation is part of a soon (or so we hope) to be released book on
58 the SuSE Linux distribution. As there is no complete documentation for the
59 /proc file system and we've used many freely available sources to write these
60 chapters, it seems only fair to give the work back to the Linux community.
61 This work is based on the 2.2.* kernel version and the upcoming 2.4.*. I'm
62 afraid it's still far from complete, but we hope it will be useful. As far as
63 we know, it is the first 'all-in-one' document about the /proc file system. It
64 is focused on the Intel x86 hardware, so if you are looking for PPC, ARM,
65 SPARC, AXP, etc., features, you probably won't find what you are looking for.
66 It also only covers IPv4 networking, not IPv6 nor other protocols - sorry. But
67 additions and patches are welcome and will be added to this document if you
70 We'd like to thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of
71 other people for help compiling this documentation. We'd also like to extend a
72 special thank you to Andi Kleen for documentation, which we relied on heavily
73 to create this document, as well as the additional information he provided.
74 Thanks to everybody else who contributed source or docs to the Linux kernel
75 and helped create a great piece of software... :)
77 If you have any comments, corrections or additions, please don't hesitate to
78 contact Bodo Bauer at bb@ricochet.net. We'll be happy to add them to this
81 The latest version of this document is available online at
82 http://tldp.org/LDP/Linux-Filesystem-Hierarchy/html/proc.html
84 If the above direction does not works for you, you could try the kernel
85 mailing list at linux-kernel@vger.kernel.org and/or try to reach me at
86 comandante@zaralinux.com.
91 We don't guarantee the correctness of this document, and if you come to us
92 complaining about how you screwed up your system because of incorrect
93 documentation, we won't feel responsible...
95 ------------------------------------------------------------------------------
96 CHAPTER 1: COLLECTING SYSTEM INFORMATION
97 ------------------------------------------------------------------------------
99 ------------------------------------------------------------------------------
101 ------------------------------------------------------------------------------
102 * Investigating the properties of the pseudo file system /proc and its
103 ability to provide information on the running Linux system
104 * Examining /proc's structure
105 * Uncovering various information about the kernel and the processes running
107 ------------------------------------------------------------------------------
110 The proc file system acts as an interface to internal data structures in the
111 kernel. It can be used to obtain information about the system and to change
112 certain kernel parameters at runtime (sysctl).
114 First, we'll take a look at the read-only parts of /proc. In Chapter 2, we
115 show you how you can use /proc/sys to change settings.
117 1.1 Process-Specific Subdirectories
118 -----------------------------------
120 The directory /proc contains (among other things) one subdirectory for each
121 process running on the system, which is named after the process ID (PID).
123 The link self points to the process reading the file system. Each process
124 subdirectory has the entries listed in Table 1-1.
127 Table 1-1: Process specific entries in /proc
128 ..............................................................................
130 clear_refs Clears page referenced bits shown in smaps output
131 cmdline Command line arguments
132 cpu Current and last cpu in which it was executed (2.4)(smp)
133 cwd Link to the current working directory
134 environ Values of environment variables
135 exe Link to the executable of this process
136 fd Directory, which contains all file descriptors
137 maps Memory maps to executables and library files (2.4)
138 mem Memory held by this process
139 root Link to the root directory of this process
141 statm Process memory status information
142 status Process status in human readable form
143 wchan Present with CONFIG_KALLSYMS=y: it shows the kernel function
144 symbol the task is blocked in - or "0" if not blocked.
146 stack Report full stack trace, enable via CONFIG_STACKTRACE
147 smaps a extension based on maps, showing the memory consumption of
148 each mapping and flags associated with it
149 numa_maps an extension based on maps, showing the memory locality and
150 binding policy as well as mem usage (in pages) of each mapping.
151 ..............................................................................
153 For example, to get the status information of a process, all you have to do is
154 read the file /proc/PID/status:
156 >cat /proc/self/status
181 SigPnd: 0000000000000000
182 ShdPnd: 0000000000000000
183 SigBlk: 0000000000000000
184 SigIgn: 0000000000000000
185 SigCgt: 0000000000000000
186 CapInh: 00000000fffffeff
187 CapPrm: 0000000000000000
188 CapEff: 0000000000000000
189 CapBnd: ffffffffffffffff
191 voluntary_ctxt_switches: 0
192 nonvoluntary_ctxt_switches: 1
194 This shows you nearly the same information you would get if you viewed it with
195 the ps command. In fact, ps uses the proc file system to obtain its
196 information. But you get a more detailed view of the process by reading the
197 file /proc/PID/status. It fields are described in table 1-2.
199 The statm file contains more detailed information about the process
200 memory usage. Its seven fields are explained in Table 1-3. The stat file
201 contains details information about the process itself. Its fields are
202 explained in Table 1-4.
204 (for SMP CONFIG users)
205 For making accounting scalable, RSS related information are handled in an
206 asynchronous manner and the value may not be very precise. To see a precise
207 snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
208 It's slow but very precise.
210 Table 1-2: Contents of the status files (as of 4.1)
211 ..............................................................................
213 Name filename of the executable
214 State state (R is running, S is sleeping, D is sleeping
215 in an uninterruptible wait, Z is zombie,
216 T is traced or stopped)
218 Ngid NUMA group ID (0 if none)
220 PPid process id of the parent process
221 TracerPid PID of process tracing this process (0 if not)
222 Uid Real, effective, saved set, and file system UIDs
223 Gid Real, effective, saved set, and file system GIDs
224 FDSize number of file descriptor slots currently allocated
225 Groups supplementary group list
226 NStgid descendant namespace thread group ID hierarchy
227 NSpid descendant namespace process ID hierarchy
228 NSpgid descendant namespace process group ID hierarchy
229 NSsid descendant namespace session ID hierarchy
230 VmPeak peak virtual memory size
231 VmSize total program size
232 VmLck locked memory size
233 VmHWM peak resident set size ("high water mark")
234 VmRSS size of memory portions
235 VmData size of data, stack, and text segments
236 VmStk size of data, stack, and text segments
237 VmExe size of text segment
238 VmLib size of shared library code
239 VmPTE size of page table entries
240 VmPMD size of second level page tables
241 VmSwap size of swap usage (the number of referred swapents)
242 HugetlbPages size of hugetlb memory portions
243 Threads number of threads
244 SigQ number of signals queued/max. number for queue
245 SigPnd bitmap of pending signals for the thread
246 ShdPnd bitmap of shared pending signals for the process
247 SigBlk bitmap of blocked signals
248 SigIgn bitmap of ignored signals
249 SigCgt bitmap of caught signals
250 CapInh bitmap of inheritable capabilities
251 CapPrm bitmap of permitted capabilities
252 CapEff bitmap of effective capabilities
253 CapBnd bitmap of capabilities bounding set
254 Seccomp seccomp mode, like prctl(PR_GET_SECCOMP, ...)
255 Cpus_allowed mask of CPUs on which this process may run
256 Cpus_allowed_list Same as previous, but in "list format"
257 Mems_allowed mask of memory nodes allowed to this process
258 Mems_allowed_list Same as previous, but in "list format"
259 voluntary_ctxt_switches number of voluntary context switches
260 nonvoluntary_ctxt_switches number of non voluntary context switches
261 ..............................................................................
263 Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
264 ..............................................................................
266 size total program size (pages) (same as VmSize in status)
267 resident size of memory portions (pages) (same as VmRSS in status)
268 shared number of pages that are shared (i.e. backed by a file)
269 trs number of pages that are 'code' (not including libs; broken,
270 includes data segment)
271 lrs number of pages of library (always 0 on 2.6)
272 drs number of pages of data/stack (including libs; broken,
273 includes library text)
274 dt number of dirty pages (always 0 on 2.6)
275 ..............................................................................
278 Table 1-4: Contents of the stat files (as of 2.6.30-rc7)
279 ..............................................................................
282 tcomm filename of the executable
283 state state (R is running, S is sleeping, D is sleeping in an
284 uninterruptible wait, Z is zombie, T is traced or stopped)
285 ppid process id of the parent process
286 pgrp pgrp of the process
288 tty_nr tty the process uses
289 tty_pgrp pgrp of the tty
291 min_flt number of minor faults
292 cmin_flt number of minor faults with child's
293 maj_flt number of major faults
294 cmaj_flt number of major faults with child's
295 utime user mode jiffies
296 stime kernel mode jiffies
297 cutime user mode jiffies with child's
298 cstime kernel mode jiffies with child's
299 priority priority level
301 num_threads number of threads
302 it_real_value (obsolete, always 0)
303 start_time time the process started after system boot
304 vsize virtual memory size
305 rss resident set memory size
306 rsslim current limit in bytes on the rss
307 start_code address above which program text can run
308 end_code address below which program text can run
309 start_stack address of the start of the main process stack
310 esp current value of ESP
311 eip current value of EIP
312 pending bitmap of pending signals
313 blocked bitmap of blocked signals
314 sigign bitmap of ignored signals
315 sigcatch bitmap of caught signals
316 0 (place holder, used to be the wchan address, use /proc/PID/wchan instead)
319 exit_signal signal to send to parent thread on exit
320 task_cpu which CPU the task is scheduled on
321 rt_priority realtime priority
322 policy scheduling policy (man sched_setscheduler)
323 blkio_ticks time spent waiting for block IO
324 gtime guest time of the task in jiffies
325 cgtime guest time of the task children in jiffies
326 start_data address above which program data+bss is placed
327 end_data address below which program data+bss is placed
328 start_brk address above which program heap can be expanded with brk()
329 arg_start address above which program command line is placed
330 arg_end address below which program command line is placed
331 env_start address above which program environment is placed
332 env_end address below which program environment is placed
333 exit_code the thread's exit_code in the form reported by the waitpid system call
334 ..............................................................................
336 The /proc/PID/maps file containing the currently mapped memory regions and
337 their access permissions.
341 address perms offset dev inode pathname
343 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test
344 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test
345 0804a000-0806b000 rw-p 00000000 00:00 0 [heap]
346 a7cb1000-a7cb2000 ---p 00000000 00:00 0
347 a7cb2000-a7eb2000 rw-p 00000000 00:00 0
348 a7eb2000-a7eb3000 ---p 00000000 00:00 0
349 a7eb3000-a7ed5000 rw-p 00000000 00:00 0
350 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6
351 a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6
352 a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6
353 a800b000-a800e000 rw-p 00000000 00:00 0
354 a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0
355 a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0
356 a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0
357 a8024000-a8027000 rw-p 00000000 00:00 0
358 a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2
359 a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2
360 a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2
361 aff35000-aff4a000 rw-p 00000000 00:00 0 [stack]
362 ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso]
364 where "address" is the address space in the process that it occupies, "perms"
365 is a set of permissions:
371 p = private (copy on write)
373 "offset" is the offset into the mapping, "dev" is the device (major:minor), and
374 "inode" is the inode on that device. 0 indicates that no inode is associated
375 with the memory region, as the case would be with BSS (uninitialized data).
376 The "pathname" shows the name associated file for this mapping. If the mapping
377 is not associated with a file:
379 [heap] = the heap of the program
380 [stack] = the stack of the main process
381 [vdso] = the "virtual dynamic shared object",
382 the kernel system call handler
384 or if empty, the mapping is anonymous.
386 The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint
387 of the individual tasks of a process. In this file you will see a mapping marked
388 as [stack] if that task sees it as a stack. Hence, for the example above, the
389 task-level map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
391 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test
392 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test
393 0804a000-0806b000 rw-p 00000000 00:00 0 [heap]
394 a7cb1000-a7cb2000 ---p 00000000 00:00 0
395 a7cb2000-a7eb2000 rw-p 00000000 00:00 0
396 a7eb2000-a7eb3000 ---p 00000000 00:00 0
397 a7eb3000-a7ed5000 rw-p 00000000 00:00 0 [stack]
398 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6
399 a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6
400 a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6
401 a800b000-a800e000 rw-p 00000000 00:00 0
402 a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0
403 a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0
404 a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0
405 a8024000-a8027000 rw-p 00000000 00:00 0
406 a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2
407 a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2
408 a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2
409 aff35000-aff4a000 rw-p 00000000 00:00 0
410 ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso]
412 The /proc/PID/smaps is an extension based on maps, showing the memory
413 consumption for each of the process's mappings. For each of mappings there
414 is a series of lines such as the following:
416 08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash
428 Private_Hugetlb: 0 kB
434 VmFlags: rd ex mr mw me dw
436 the first of these lines shows the same information as is displayed for the
437 mapping in /proc/PID/maps. The remaining lines show the size of the mapping
438 (size), the amount of the mapping that is currently resident in RAM (RSS), the
439 process' proportional share of this mapping (PSS), the number of clean and
440 dirty private pages in the mapping.
442 The "proportional set size" (PSS) of a process is the count of pages it has
443 in memory, where each page is divided by the number of processes sharing it.
444 So if a process has 1000 pages all to itself, and 1000 shared with one other
445 process, its PSS will be 1500.
446 Note that even a page which is part of a MAP_SHARED mapping, but has only
447 a single pte mapped, i.e. is currently used by only one process, is accounted
448 as private and not as shared.
449 "Referenced" indicates the amount of memory currently marked as referenced or
451 "Anonymous" shows the amount of memory that does not belong to any file. Even
452 a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
453 and a page is modified, the file page is replaced by a private anonymous copy.
454 "AnonHugePages" shows the ammount of memory backed by transparent hugepage.
455 "Shared_Hugetlb" and "Private_Hugetlb" show the ammounts of memory backed by
456 hugetlbfs page which is *not* counted in "RSS" or "PSS" field for historical
457 reasons. And these are not included in {Shared,Private}_{Clean,Dirty} field.
458 "Swap" shows how much would-be-anonymous memory is also used, but out on swap.
459 "SwapPss" shows proportional swap share of this mapping.
460 "Locked" indicates whether the mapping is locked in memory or not.
462 "VmFlags" field deserves a separate description. This member represents the kernel
463 flags associated with the particular virtual memory area in two letter encoded
464 manner. The codes are the following:
473 gd - stack segment growns down
475 dw - disabled write to the mapped file
476 lo - pages are locked in memory
477 io - memory mapped I/O area
478 sr - sequential read advise provided
479 rr - random read advise provided
480 dc - do not copy area on fork
481 de - do not expand area on remapping
482 ac - area is accountable
483 nr - swap space is not reserved for the area
484 ht - area uses huge tlb pages
485 ar - architecture specific flag
486 dd - do not include area into core dump
489 hg - huge page advise flag
490 nh - no-huge page advise flag
491 mg - mergable advise flag
493 Note that there is no guarantee that every flag and associated mnemonic will
494 be present in all further kernel releases. Things get changed, the flags may
495 be vanished or the reverse -- new added.
497 This file is only present if the CONFIG_MMU kernel configuration option is
500 The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
501 bits on both physical and virtual pages associated with a process, and the
502 soft-dirty bit on pte (see Documentation/vm/soft-dirty.txt for details).
503 To clear the bits for all the pages associated with the process
504 > echo 1 > /proc/PID/clear_refs
506 To clear the bits for the anonymous pages associated with the process
507 > echo 2 > /proc/PID/clear_refs
509 To clear the bits for the file mapped pages associated with the process
510 > echo 3 > /proc/PID/clear_refs
512 To clear the soft-dirty bit
513 > echo 4 > /proc/PID/clear_refs
515 To reset the peak resident set size ("high water mark") to the process's
517 > echo 5 > /proc/PID/clear_refs
519 Any other value written to /proc/PID/clear_refs will have no effect.
521 The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
522 using /proc/kpageflags and number of times a page is mapped using
523 /proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.txt.
525 The /proc/pid/numa_maps is an extension based on maps, showing the memory
526 locality and binding policy, as well as the memory usage (in pages) of
527 each mapping. The output follows a general format where mapping details get
528 summarized separated by blank spaces, one mapping per each file line:
530 address policy mapping details
532 00400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4
533 00600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4
534 3206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4
535 320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
536 3206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
537 3206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4
538 3206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4
539 320698b000 default file=/lib64/libc-2.12.so
540 3206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4
541 3206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
542 3206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4
543 7f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4
544 7f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4
545 7f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048
546 7fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4
547 7fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4
550 "address" is the starting address for the mapping;
551 "policy" reports the NUMA memory policy set for the mapping (see vm/numa_memory_policy.txt);
552 "mapping details" summarizes mapping data such as mapping type, page usage counters,
553 node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page
554 size, in KB, that is backing the mapping up.
559 Similar to the process entries, the kernel data files give information about
560 the running kernel. The files used to obtain this information are contained in
561 /proc and are listed in Table 1-5. Not all of these will be present in your
562 system. It depends on the kernel configuration and the loaded modules, which
563 files are there, and which are missing.
565 Table 1-5: Kernel info in /proc
566 ..............................................................................
568 apm Advanced power management info
569 buddyinfo Kernel memory allocator information (see text) (2.5)
570 bus Directory containing bus specific information
571 cmdline Kernel command line
572 cpuinfo Info about the CPU
573 devices Available devices (block and character)
574 dma Used DMS channels
575 filesystems Supported filesystems
576 driver Various drivers grouped here, currently rtc (2.4)
577 execdomains Execdomains, related to security (2.4)
578 fb Frame Buffer devices (2.4)
579 fs File system parameters, currently nfs/exports (2.4)
580 ide Directory containing info about the IDE subsystem
581 interrupts Interrupt usage
582 iomem Memory map (2.4)
583 ioports I/O port usage
584 irq Masks for irq to cpu affinity (2.4)(smp?)
585 isapnp ISA PnP (Plug&Play) Info (2.4)
586 kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4))
588 ksyms Kernel symbol table
589 loadavg Load average of last 1, 5 & 15 minutes
593 modules List of loaded modules
594 mounts Mounted filesystems
595 net Networking info (see text)
596 pagetypeinfo Additional page allocator information (see text) (2.5)
597 partitions Table of partitions known to the system
598 pci Deprecated info of PCI bus (new way -> /proc/bus/pci/,
599 decoupled by lspci (2.4)
601 scsi SCSI info (see text)
602 slabinfo Slab pool info
603 softirqs softirq usage
604 stat Overall statistics
605 swaps Swap space utilization
607 sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4)
608 tty Info of tty drivers
609 uptime Wall clock since boot, combined idle time of all cpus
610 version Kernel version
611 video bttv info of video resources (2.4)
612 vmallocinfo Show vmalloced areas
613 ..............................................................................
615 You can, for example, check which interrupts are currently in use and what
616 they are used for by looking in the file /proc/interrupts:
618 > cat /proc/interrupts
620 0: 8728810 XT-PIC timer
621 1: 895 XT-PIC keyboard
623 3: 531695 XT-PIC aha152x
624 4: 2014133 XT-PIC serial
625 5: 44401 XT-PIC pcnet_cs
628 12: 182918 XT-PIC PS/2 Mouse
630 14: 1232265 XT-PIC ide0
634 In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the
635 output of a SMP machine):
637 > cat /proc/interrupts
640 0: 1243498 1214548 IO-APIC-edge timer
641 1: 8949 8958 IO-APIC-edge keyboard
642 2: 0 0 XT-PIC cascade
643 5: 11286 10161 IO-APIC-edge soundblaster
644 8: 1 0 IO-APIC-edge rtc
645 9: 27422 27407 IO-APIC-edge 3c503
646 12: 113645 113873 IO-APIC-edge PS/2 Mouse
648 14: 22491 24012 IO-APIC-edge ide0
649 15: 2183 2415 IO-APIC-edge ide1
650 17: 30564 30414 IO-APIC-level eth0
651 18: 177 164 IO-APIC-level bttv
656 NMI is incremented in this case because every timer interrupt generates a NMI
657 (Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups.
659 LOC is the local interrupt counter of the internal APIC of every CPU.
661 ERR is incremented in the case of errors in the IO-APIC bus (the bus that
662 connects the CPUs in a SMP system. This means that an error has been detected,
663 the IO-APIC automatically retry the transmission, so it should not be a big
664 problem, but you should read the SMP-FAQ.
666 In 2.6.2* /proc/interrupts was expanded again. This time the goal was for
667 /proc/interrupts to display every IRQ vector in use by the system, not
668 just those considered 'most important'. The new vectors are:
670 THR -- interrupt raised when a machine check threshold counter
671 (typically counting ECC corrected errors of memory or cache) exceeds
672 a configurable threshold. Only available on some systems.
674 TRM -- a thermal event interrupt occurs when a temperature threshold
675 has been exceeded for the CPU. This interrupt may also be generated
676 when the temperature drops back to normal.
678 SPU -- a spurious interrupt is some interrupt that was raised then lowered
679 by some IO device before it could be fully processed by the APIC. Hence
680 the APIC sees the interrupt but does not know what device it came from.
681 For this case the APIC will generate the interrupt with a IRQ vector
682 of 0xff. This might also be generated by chipset bugs.
684 RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are
685 sent from one CPU to another per the needs of the OS. Typically,
686 their statistics are used by kernel developers and interested users to
687 determine the occurrence of interrupts of the given type.
689 The above IRQ vectors are displayed only when relevant. For example,
690 the threshold vector does not exist on x86_64 platforms. Others are
691 suppressed when the system is a uniprocessor. As of this writing, only
692 i386 and x86_64 platforms support the new IRQ vector displays.
694 Of some interest is the introduction of the /proc/irq directory to 2.4.
695 It could be used to set IRQ to CPU affinity, this means that you can "hook" an
696 IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
697 irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and
702 0 10 12 14 16 18 2 4 6 8 prof_cpu_mask
703 1 11 13 15 17 19 3 5 7 9 default_smp_affinity
707 smp_affinity is a bitmask, in which you can specify which CPUs can handle the
708 IRQ, you can set it by doing:
710 > echo 1 > /proc/irq/10/smp_affinity
712 This means that only the first CPU will handle the IRQ, but you can also echo
713 5 which means that only the first and fourth CPU can handle the IRQ.
715 The contents of each smp_affinity file is the same by default:
717 > cat /proc/irq/0/smp_affinity
720 There is an alternate interface, smp_affinity_list which allows specifying
721 a cpu range instead of a bitmask:
723 > cat /proc/irq/0/smp_affinity_list
726 The default_smp_affinity mask applies to all non-active IRQs, which are the
727 IRQs which have not yet been allocated/activated, and hence which lack a
728 /proc/irq/[0-9]* directory.
730 The node file on an SMP system shows the node to which the device using the IRQ
731 reports itself as being attached. This hardware locality information does not
732 include information about any possible driver locality preference.
734 prof_cpu_mask specifies which CPUs are to be profiled by the system wide
735 profiler. Default value is ffffffff (all cpus if there are only 32 of them).
737 The way IRQs are routed is handled by the IO-APIC, and it's Round Robin
738 between all the CPUs which are allowed to handle it. As usual the kernel has
739 more info than you and does a better job than you, so the defaults are the
740 best choice for almost everyone. [Note this applies only to those IO-APIC's
741 that support "Round Robin" interrupt distribution.]
743 There are three more important subdirectories in /proc: net, scsi, and sys.
744 The general rule is that the contents, or even the existence of these
745 directories, depend on your kernel configuration. If SCSI is not enabled, the
746 directory scsi may not exist. The same is true with the net, which is there
747 only when networking support is present in the running kernel.
749 The slabinfo file gives information about memory usage at the slab level.
750 Linux uses slab pools for memory management above page level in version 2.2.
751 Commonly used objects have their own slab pool (such as network buffers,
752 directory cache, and so on).
754 ..............................................................................
756 > cat /proc/buddyinfo
758 Node 0, zone DMA 0 4 5 4 4 3 ...
759 Node 0, zone Normal 1 0 0 1 101 8 ...
760 Node 0, zone HighMem 2 0 0 1 1 0 ...
762 External fragmentation is a problem under some workloads, and buddyinfo is a
763 useful tool for helping diagnose these problems. Buddyinfo will give you a
764 clue as to how big an area you can safely allocate, or why a previous
767 Each column represents the number of pages of a certain order which are
768 available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in
769 ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE
770 available in ZONE_NORMAL, etc...
772 More information relevant to external fragmentation can be found in
775 > cat /proc/pagetypeinfo
779 Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
780 Node 0, zone DMA, type Unmovable 0 0 0 1 1 1 1 1 1 1 0
781 Node 0, zone DMA, type Reclaimable 0 0 0 0 0 0 0 0 0 0 0
782 Node 0, zone DMA, type Movable 1 1 2 1 2 1 1 0 1 0 2
783 Node 0, zone DMA, type Reserve 0 0 0 0 0 0 0 0 0 1 0
784 Node 0, zone DMA, type Isolate 0 0 0 0 0 0 0 0 0 0 0
785 Node 0, zone DMA32, type Unmovable 103 54 77 1 1 1 11 8 7 1 9
786 Node 0, zone DMA32, type Reclaimable 0 0 2 1 0 0 0 0 1 0 0
787 Node 0, zone DMA32, type Movable 169 152 113 91 77 54 39 13 6 1 452
788 Node 0, zone DMA32, type Reserve 1 2 2 2 2 0 1 1 1 1 0
789 Node 0, zone DMA32, type Isolate 0 0 0 0 0 0 0 0 0 0 0
791 Number of blocks type Unmovable Reclaimable Movable Reserve Isolate
792 Node 0, zone DMA 2 0 5 1 0
793 Node 0, zone DMA32 41 6 967 2 0
795 Fragmentation avoidance in the kernel works by grouping pages of different
796 migrate types into the same contiguous regions of memory called page blocks.
797 A page block is typically the size of the default hugepage size e.g. 2MB on
798 X86-64. By keeping pages grouped based on their ability to move, the kernel
799 can reclaim pages within a page block to satisfy a high-order allocation.
801 The pagetypinfo begins with information on the size of a page block. It
802 then gives the same type of information as buddyinfo except broken down
803 by migrate-type and finishes with details on how many page blocks of each
806 If min_free_kbytes has been tuned correctly (recommendations made by hugeadm
807 from libhugetlbfs http://sourceforge.net/projects/libhugetlbfs/), one can
808 make an estimate of the likely number of huge pages that can be allocated
809 at a given point in time. All the "Movable" blocks should be allocatable
810 unless memory has been mlock()'d. Some of the Reclaimable blocks should
811 also be allocatable although a lot of filesystem metadata may have to be
812 reclaimed to achieve this.
814 ..............................................................................
818 Provides information about distribution and utilization of memory. This
819 varies by architecture and compile options. The following is from a
820 16GB PIII, which has highmem enabled. You may not have all of these fields.
824 MemTotal: 16344972 kB
826 MemAvailable: 14836172 kB
832 HighTotal: 15597528 kB
833 HighFree: 13629632 kB
843 SReclaimable: 159856 kB
844 SUnreclaim: 124508 kB
849 CommitLimit: 7669796 kB
850 Committed_AS: 100056 kB
851 VmallocTotal: 112216 kB
853 VmallocChunk: 111088 kB
854 AnonHugePages: 49152 kB
856 MemTotal: Total usable ram (i.e. physical ram minus a few reserved
857 bits and the kernel binary code)
858 MemFree: The sum of LowFree+HighFree
859 MemAvailable: An estimate of how much memory is available for starting new
860 applications, without swapping. Calculated from MemFree,
861 SReclaimable, the size of the file LRU lists, and the low
862 watermarks in each zone.
863 The estimate takes into account that the system needs some
864 page cache to function well, and that not all reclaimable
865 slab will be reclaimable, due to items being in use. The
866 impact of those factors will vary from system to system.
867 Buffers: Relatively temporary storage for raw disk blocks
868 shouldn't get tremendously large (20MB or so)
869 Cached: in-memory cache for files read from the disk (the
870 pagecache). Doesn't include SwapCached
871 SwapCached: Memory that once was swapped out, is swapped back in but
872 still also is in the swapfile (if memory is needed it
873 doesn't need to be swapped out AGAIN because it is already
874 in the swapfile. This saves I/O)
875 Active: Memory that has been used more recently and usually not
876 reclaimed unless absolutely necessary.
877 Inactive: Memory which has been less recently used. It is more
878 eligible to be reclaimed for other purposes
880 HighFree: Highmem is all memory above ~860MB of physical memory
881 Highmem areas are for use by userspace programs, or
882 for the pagecache. The kernel must use tricks to access
883 this memory, making it slower to access than lowmem.
885 LowFree: Lowmem is memory which can be used for everything that
886 highmem can be used for, but it is also available for the
887 kernel's use for its own data structures. Among many
888 other things, it is where everything from the Slab is
889 allocated. Bad things happen when you're out of lowmem.
890 SwapTotal: total amount of swap space available
891 SwapFree: Memory which has been evicted from RAM, and is temporarily
893 Dirty: Memory which is waiting to get written back to the disk
894 Writeback: Memory which is actively being written back to the disk
895 AnonPages: Non-file backed pages mapped into userspace page tables
896 AnonHugePages: Non-file backed huge pages mapped into userspace page tables
897 Mapped: files which have been mmaped, such as libraries
898 Slab: in-kernel data structures cache
899 SReclaimable: Part of Slab, that might be reclaimed, such as caches
900 SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure
901 PageTables: amount of memory dedicated to the lowest level of page
903 NFS_Unstable: NFS pages sent to the server, but not yet committed to stable
905 Bounce: Memory used for block device "bounce buffers"
906 WritebackTmp: Memory used by FUSE for temporary writeback buffers
907 CommitLimit: Based on the overcommit ratio ('vm.overcommit_ratio'),
908 this is the total amount of memory currently available to
909 be allocated on the system. This limit is only adhered to
910 if strict overcommit accounting is enabled (mode 2 in
911 'vm.overcommit_memory').
912 The CommitLimit is calculated with the following formula:
913 CommitLimit = ([total RAM pages] - [total huge TLB pages]) *
914 overcommit_ratio / 100 + [total swap pages]
915 For example, on a system with 1G of physical RAM and 7G
916 of swap with a `vm.overcommit_ratio` of 30 it would
917 yield a CommitLimit of 7.3G.
918 For more details, see the memory overcommit documentation
919 in vm/overcommit-accounting.
920 Committed_AS: The amount of memory presently allocated on the system.
921 The committed memory is a sum of all of the memory which
922 has been allocated by processes, even if it has not been
923 "used" by them as of yet. A process which malloc()'s 1G
924 of memory, but only touches 300M of it will show up as
925 using 1G. This 1G is memory which has been "committed" to
926 by the VM and can be used at any time by the allocating
927 application. With strict overcommit enabled on the system
928 (mode 2 in 'vm.overcommit_memory'),allocations which would
929 exceed the CommitLimit (detailed above) will not be permitted.
930 This is useful if one needs to guarantee that processes will
931 not fail due to lack of memory once that memory has been
932 successfully allocated.
933 VmallocTotal: total size of vmalloc memory area
934 VmallocUsed: amount of vmalloc area which is used
935 VmallocChunk: largest contiguous block of vmalloc area which is free
937 ..............................................................................
941 Provides information about vmalloced/vmaped areas. One line per area,
942 containing the virtual address range of the area, size in bytes,
943 caller information of the creator, and optional information depending
944 on the kind of area :
946 pages=nr number of pages
947 phys=addr if a physical address was specified
948 ioremap I/O mapping (ioremap() and friends)
949 vmalloc vmalloc() area
952 vpages buffer for pages pointers was vmalloced (huge area)
953 N<node>=nr (Only on NUMA kernels)
954 Number of pages allocated on memory node <node>
956 > cat /proc/vmallocinfo
957 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ...
958 /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128
959 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ...
960 /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64
961 0xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f...
962 phys=7fee8000 ioremap
963 0xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f...
964 phys=7fee7000 ioremap
965 0xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210
966 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ...
967 /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3
968 0xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ...
970 0xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ...
971 /0x130 [x_tables] pages=4 vmalloc N0=4
972 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ...
973 pages=14 vmalloc N2=14
974 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ...
976 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ...
978 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ...
979 pages=10 vmalloc N0=10
981 ..............................................................................
985 Provides counts of softirq handlers serviced since boot time, for each cpu.
990 TIMER: 27166 27120 27097 27034
995 SCHED: 27035 26983 26971 26746
997 RCU: 1678 1769 2178 2250
1000 1.3 IDE devices in /proc/ide
1001 ----------------------------
1003 The subdirectory /proc/ide contains information about all IDE devices of which
1004 the kernel is aware. There is one subdirectory for each IDE controller, the
1005 file drivers and a link for each IDE device, pointing to the device directory
1006 in the controller specific subtree.
1008 The file drivers contains general information about the drivers used for the
1011 > cat /proc/ide/drivers
1012 ide-cdrom version 4.53
1013 ide-disk version 1.08
1015 More detailed information can be found in the controller specific
1016 subdirectories. These are named ide0, ide1 and so on. Each of these
1017 directories contains the files shown in table 1-6.
1020 Table 1-6: IDE controller info in /proc/ide/ide?
1021 ..............................................................................
1023 channel IDE channel (0 or 1)
1024 config Configuration (only for PCI/IDE bridge)
1026 model Type/Chipset of IDE controller
1027 ..............................................................................
1029 Each device connected to a controller has a separate subdirectory in the
1030 controllers directory. The files listed in table 1-7 are contained in these
1034 Table 1-7: IDE device information
1035 ..............................................................................
1038 capacity Capacity of the medium (in 512Byte blocks)
1039 driver driver and version
1040 geometry physical and logical geometry
1041 identify device identify block
1043 model device identifier
1044 settings device setup
1045 smart_thresholds IDE disk management thresholds
1046 smart_values IDE disk management values
1047 ..............................................................................
1049 The most interesting file is settings. This file contains a nice overview of
1050 the drive parameters:
1052 # cat /proc/ide/ide0/hda/settings
1053 name value min max mode
1054 ---- ----- --- --- ----
1055 bios_cyl 526 0 65535 rw
1056 bios_head 255 0 255 rw
1057 bios_sect 63 0 63 rw
1058 breada_readahead 4 0 127 rw
1060 file_readahead 72 0 2097151 rw
1062 keepsettings 0 0 1 rw
1063 max_kb_per_request 122 1 127 rw
1067 pio_mode write-only 0 255 w
1073 1.4 Networking info in /proc/net
1074 --------------------------------
1076 The subdirectory /proc/net follows the usual pattern. Table 1-8 shows the
1077 additional values you get for IP version 6 if you configure the kernel to
1078 support this. Table 1-9 lists the files and their meaning.
1081 Table 1-8: IPv6 info in /proc/net
1082 ..............................................................................
1084 udp6 UDP sockets (IPv6)
1085 tcp6 TCP sockets (IPv6)
1086 raw6 Raw device statistics (IPv6)
1087 igmp6 IP multicast addresses, which this host joined (IPv6)
1088 if_inet6 List of IPv6 interface addresses
1089 ipv6_route Kernel routing table for IPv6
1090 rt6_stats Global IPv6 routing tables statistics
1091 sockstat6 Socket statistics (IPv6)
1092 snmp6 Snmp data (IPv6)
1093 ..............................................................................
1096 Table 1-9: Network info in /proc/net
1097 ..............................................................................
1099 arp Kernel ARP table
1100 dev network devices with statistics
1101 dev_mcast the Layer2 multicast groups a device is listening too
1102 (interface index, label, number of references, number of bound
1104 dev_stat network device status
1105 ip_fwchains Firewall chain linkage
1106 ip_fwnames Firewall chain names
1107 ip_masq Directory containing the masquerading tables
1108 ip_masquerade Major masquerading table
1109 netstat Network statistics
1110 raw raw device statistics
1111 route Kernel routing table
1112 rpc Directory containing rpc info
1113 rt_cache Routing cache
1115 sockstat Socket statistics
1118 unix UNIX domain sockets
1119 wireless Wireless interface data (Wavelan etc)
1120 igmp IP multicast addresses, which this host joined
1121 psched Global packet scheduler parameters.
1122 netlink List of PF_NETLINK sockets
1123 ip_mr_vifs List of multicast virtual interfaces
1124 ip_mr_cache List of multicast routing cache
1125 ..............................................................................
1127 You can use this information to see which network devices are available in
1128 your system and how much traffic was routed over those devices:
1131 Inter-|Receive |[...
1132 face |bytes packets errs drop fifo frame compressed multicast|[...
1133 lo: 908188 5596 0 0 0 0 0 0 [...
1134 ppp0:15475140 20721 410 0 0 410 0 0 [...
1135 eth0: 614530 7085 0 0 0 0 0 1 [...
1138 ...] bytes packets errs drop fifo colls carrier compressed
1139 ...] 908188 5596 0 0 0 0 0 0
1140 ...] 1375103 17405 0 0 0 0 0 0
1141 ...] 1703981 5535 0 0 0 3 0 0
1143 In addition, each Channel Bond interface has its own directory. For
1144 example, the bond0 device will have a directory called /proc/net/bond0/.
1145 It will contain information that is specific to that bond, such as the
1146 current slaves of the bond, the link status of the slaves, and how
1147 many times the slaves link has failed.
1152 If you have a SCSI host adapter in your system, you'll find a subdirectory
1153 named after the driver for this adapter in /proc/scsi. You'll also see a list
1154 of all recognized SCSI devices in /proc/scsi:
1156 >cat /proc/scsi/scsi
1158 Host: scsi0 Channel: 00 Id: 00 Lun: 00
1159 Vendor: IBM Model: DGHS09U Rev: 03E0
1160 Type: Direct-Access ANSI SCSI revision: 03
1161 Host: scsi0 Channel: 00 Id: 06 Lun: 00
1162 Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04
1163 Type: CD-ROM ANSI SCSI revision: 02
1166 The directory named after the driver has one file for each adapter found in
1167 the system. These files contain information about the controller, including
1168 the used IRQ and the IO address range. The amount of information shown is
1169 dependent on the adapter you use. The example shows the output for an Adaptec
1170 AHA-2940 SCSI adapter:
1172 > cat /proc/scsi/aic7xxx/0
1174 Adaptec AIC7xxx driver version: 5.1.19/3.2.4
1176 TCQ Enabled By Default : Disabled
1177 AIC7XXX_PROC_STATS : Disabled
1178 AIC7XXX_RESET_DELAY : 5
1179 Adapter Configuration:
1180 SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter
1181 Ultra Wide Controller
1182 PCI MMAPed I/O Base: 0xeb001000
1183 Adapter SEEPROM Config: SEEPROM found and used.
1184 Adaptec SCSI BIOS: Enabled
1186 SCBs: Active 0, Max Active 2,
1187 Allocated 15, HW 16, Page 255
1189 BIOS Control Word: 0x18b6
1190 Adapter Control Word: 0x005b
1191 Extended Translation: Enabled
1192 Disconnect Enable Flags: 0xffff
1193 Ultra Enable Flags: 0x0001
1194 Tag Queue Enable Flags: 0x0000
1195 Ordered Queue Tag Flags: 0x0000
1196 Default Tag Queue Depth: 8
1197 Tagged Queue By Device array for aic7xxx host instance 0:
1198 {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255}
1199 Actual queue depth per device for aic7xxx host instance 0:
1200 {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}
1203 Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8
1204 Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0)
1205 Total transfers 160151 (74577 reads and 85574 writes)
1207 Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15
1208 Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0)
1209 Total transfers 0 (0 reads and 0 writes)
1212 1.6 Parallel port info in /proc/parport
1213 ---------------------------------------
1215 The directory /proc/parport contains information about the parallel ports of
1216 your system. It has one subdirectory for each port, named after the port
1219 These directories contain the four files shown in Table 1-10.
1222 Table 1-10: Files in /proc/parport
1223 ..............................................................................
1225 autoprobe Any IEEE-1284 device ID information that has been acquired.
1226 devices list of the device drivers using that port. A + will appear by the
1227 name of the device currently using the port (it might not appear
1229 hardware Parallel port's base address, IRQ line and DMA channel.
1230 irq IRQ that parport is using for that port. This is in a separate
1231 file to allow you to alter it by writing a new value in (IRQ
1233 ..............................................................................
1235 1.7 TTY info in /proc/tty
1236 -------------------------
1238 Information about the available and actually used tty's can be found in the
1239 directory /proc/tty.You'll find entries for drivers and line disciplines in
1240 this directory, as shown in Table 1-11.
1243 Table 1-11: Files in /proc/tty
1244 ..............................................................................
1246 drivers list of drivers and their usage
1247 ldiscs registered line disciplines
1248 driver/serial usage statistic and status of single tty lines
1249 ..............................................................................
1251 To see which tty's are currently in use, you can simply look into the file
1254 > cat /proc/tty/drivers
1255 pty_slave /dev/pts 136 0-255 pty:slave
1256 pty_master /dev/ptm 128 0-255 pty:master
1257 pty_slave /dev/ttyp 3 0-255 pty:slave
1258 pty_master /dev/pty 2 0-255 pty:master
1259 serial /dev/cua 5 64-67 serial:callout
1260 serial /dev/ttyS 4 64-67 serial
1261 /dev/tty0 /dev/tty0 4 0 system:vtmaster
1262 /dev/ptmx /dev/ptmx 5 2 system
1263 /dev/console /dev/console 5 1 system:console
1264 /dev/tty /dev/tty 5 0 system:/dev/tty
1265 unknown /dev/tty 4 1-63 console
1268 1.8 Miscellaneous kernel statistics in /proc/stat
1269 -------------------------------------------------
1271 Various pieces of information about kernel activity are available in the
1272 /proc/stat file. All of the numbers reported in this file are aggregates
1273 since the system first booted. For a quick look, simply cat the file:
1276 cpu 2255 34 2290 22625563 6290 127 456 0 0 0
1277 cpu0 1132 34 1441 11311718 3675 127 438 0 0 0
1278 cpu1 1123 0 849 11313845 2614 0 18 0 0 0
1279 intr 114930548 113199788 3 0 5 263 0 4 [... lots more numbers ...]
1285 softirq 183433 0 21755 12 39 1137 231 21459 2263
1287 The very first "cpu" line aggregates the numbers in all of the other "cpuN"
1288 lines. These numbers identify the amount of time the CPU has spent performing
1289 different kinds of work. Time units are in USER_HZ (typically hundredths of a
1290 second). The meanings of the columns are as follows, from left to right:
1292 - user: normal processes executing in user mode
1293 - nice: niced processes executing in user mode
1294 - system: processes executing in kernel mode
1295 - idle: twiddling thumbs
1296 - iowait: waiting for I/O to complete
1297 - irq: servicing interrupts
1298 - softirq: servicing softirqs
1299 - steal: involuntary wait
1300 - guest: running a normal guest
1301 - guest_nice: running a niced guest
1303 The "intr" line gives counts of interrupts serviced since boot time, for each
1304 of the possible system interrupts. The first column is the total of all
1305 interrupts serviced including unnumbered architecture specific interrupts;
1306 each subsequent column is the total for that particular numbered interrupt.
1307 Unnumbered interrupts are not shown, only summed into the total.
1309 The "ctxt" line gives the total number of context switches across all CPUs.
1311 The "btime" line gives the time at which the system booted, in seconds since
1314 The "processes" line gives the number of processes and threads created, which
1315 includes (but is not limited to) those created by calls to the fork() and
1316 clone() system calls.
1318 The "procs_running" line gives the total number of threads that are
1319 running or ready to run (i.e., the total number of runnable threads).
1321 The "procs_blocked" line gives the number of processes currently blocked,
1322 waiting for I/O to complete.
1324 The "softirq" line gives counts of softirqs serviced since boot time, for each
1325 of the possible system softirqs. The first column is the total of all
1326 softirqs serviced; each subsequent column is the total for that particular
1330 1.9 Ext4 file system parameters
1331 -------------------------------
1333 Information about mounted ext4 file systems can be found in
1334 /proc/fs/ext4. Each mounted filesystem will have a directory in
1335 /proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or
1336 /proc/fs/ext4/dm-0). The files in each per-device directory are shown
1337 in Table 1-12, below.
1339 Table 1-12: Files in /proc/fs/ext4/<devname>
1340 ..............................................................................
1342 mb_groups details of multiblock allocator buddy cache of free blocks
1343 ..............................................................................
1347 Shows registered system console lines.
1349 To see which character device lines are currently used for the system console
1350 /dev/console, you may simply look into the file /proc/consoles:
1352 > cat /proc/consoles
1358 device name of the device
1359 operations R = can do read operations
1360 W = can do write operations
1362 flags E = it is enabled
1363 C = it is preferred console
1364 B = it is primary boot console
1365 p = it is used for printk buffer
1366 b = it is not a TTY but a Braille device
1367 a = it is safe to use when cpu is offline
1368 major:minor major and minor number of the device separated by a colon
1370 ------------------------------------------------------------------------------
1372 ------------------------------------------------------------------------------
1373 The /proc file system serves information about the running system. It not only
1374 allows access to process data but also allows you to request the kernel status
1375 by reading files in the hierarchy.
1377 The directory structure of /proc reflects the types of information and makes
1378 it easy, if not obvious, where to look for specific data.
1379 ------------------------------------------------------------------------------
1381 ------------------------------------------------------------------------------
1382 CHAPTER 2: MODIFYING SYSTEM PARAMETERS
1383 ------------------------------------------------------------------------------
1385 ------------------------------------------------------------------------------
1387 ------------------------------------------------------------------------------
1388 * Modifying kernel parameters by writing into files found in /proc/sys
1389 * Exploring the files which modify certain parameters
1390 * Review of the /proc/sys file tree
1391 ------------------------------------------------------------------------------
1394 A very interesting part of /proc is the directory /proc/sys. This is not only
1395 a source of information, it also allows you to change parameters within the
1396 kernel. Be very careful when attempting this. You can optimize your system,
1397 but you can also cause it to crash. Never alter kernel parameters on a
1398 production system. Set up a development machine and test to make sure that
1399 everything works the way you want it to. You may have no alternative but to
1400 reboot the machine once an error has been made.
1402 To change a value, simply echo the new value into the file. An example is
1403 given below in the section on the file system data. You need to be root to do
1404 this. You can create your own boot script to perform this every time your
1407 The files in /proc/sys can be used to fine tune and monitor miscellaneous and
1408 general things in the operation of the Linux kernel. Since some of the files
1409 can inadvertently disrupt your system, it is advisable to read both
1410 documentation and source before actually making adjustments. In any case, be
1411 very careful when writing to any of these files. The entries in /proc may
1412 change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt
1413 review the kernel documentation in the directory /usr/src/linux/Documentation.
1414 This chapter is heavily based on the documentation included in the pre 2.2
1415 kernels, and became part of it in version 2.2.1 of the Linux kernel.
1417 Please see: Documentation/sysctl/ directory for descriptions of these
1420 ------------------------------------------------------------------------------
1422 ------------------------------------------------------------------------------
1423 Certain aspects of kernel behavior can be modified at runtime, without the
1424 need to recompile the kernel, or even to reboot the system. The files in the
1425 /proc/sys tree can not only be read, but also modified. You can use the echo
1426 command to write value into these files, thereby changing the default settings
1428 ------------------------------------------------------------------------------
1430 ------------------------------------------------------------------------------
1431 CHAPTER 3: PER-PROCESS PARAMETERS
1432 ------------------------------------------------------------------------------
1434 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score
1435 --------------------------------------------------------------------------------
1437 These file can be used to adjust the badness heuristic used to select which
1438 process gets killed in out of memory conditions.
1440 The badness heuristic assigns a value to each candidate task ranging from 0
1441 (never kill) to 1000 (always kill) to determine which process is targeted. The
1442 units are roughly a proportion along that range of allowed memory the process
1443 may allocate from based on an estimation of its current memory and swap use.
1444 For example, if a task is using all allowed memory, its badness score will be
1445 1000. If it is using half of its allowed memory, its score will be 500.
1447 There is an additional factor included in the badness score: the current memory
1448 and swap usage is discounted by 3% for root processes.
1450 The amount of "allowed" memory depends on the context in which the oom killer
1451 was called. If it is due to the memory assigned to the allocating task's cpuset
1452 being exhausted, the allowed memory represents the set of mems assigned to that
1453 cpuset. If it is due to a mempolicy's node(s) being exhausted, the allowed
1454 memory represents the set of mempolicy nodes. If it is due to a memory
1455 limit (or swap limit) being reached, the allowed memory is that configured
1456 limit. Finally, if it is due to the entire system being out of memory, the
1457 allowed memory represents all allocatable resources.
1459 The value of /proc/<pid>/oom_score_adj is added to the badness score before it
1460 is used to determine which task to kill. Acceptable values range from -1000
1461 (OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX). This allows userspace to
1462 polarize the preference for oom killing either by always preferring a certain
1463 task or completely disabling it. The lowest possible value, -1000, is
1464 equivalent to disabling oom killing entirely for that task since it will always
1465 report a badness score of 0.
1467 Consequently, it is very simple for userspace to define the amount of memory to
1468 consider for each task. Setting a /proc/<pid>/oom_score_adj value of +500, for
1469 example, is roughly equivalent to allowing the remainder of tasks sharing the
1470 same system, cpuset, mempolicy, or memory controller resources to use at least
1471 50% more memory. A value of -500, on the other hand, would be roughly
1472 equivalent to discounting 50% of the task's allowed memory from being considered
1473 as scoring against the task.
1475 For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also
1476 be used to tune the badness score. Its acceptable values range from -16
1477 (OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17
1478 (OOM_DISABLE) to disable oom killing entirely for that task. Its value is
1479 scaled linearly with /proc/<pid>/oom_score_adj.
1481 The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last
1482 value set by a CAP_SYS_RESOURCE process. To reduce the value any lower
1483 requires CAP_SYS_RESOURCE.
1485 Caveat: when a parent task is selected, the oom killer will sacrifice any first
1486 generation children with separate address spaces instead, if possible. This
1487 avoids servers and important system daemons from being killed and loses the
1488 minimal amount of work.
1491 3.2 /proc/<pid>/oom_score - Display current oom-killer score
1492 -------------------------------------------------------------
1494 This file can be used to check the current score used by the oom-killer is for
1495 any given <pid>. Use it together with /proc/<pid>/oom_score_adj to tune which
1496 process should be killed in an out-of-memory situation.
1499 3.3 /proc/<pid>/io - Display the IO accounting fields
1500 -------------------------------------------------------
1502 This file contains IO statistics for each running process
1507 test:/tmp # dd if=/dev/zero of=/tmp/test.dat &
1510 test:/tmp # cat /proc/3828/io
1516 write_bytes: 323932160
1517 cancelled_write_bytes: 0
1526 I/O counter: chars read
1527 The number of bytes which this task has caused to be read from storage. This
1528 is simply the sum of bytes which this process passed to read() and pread().
1529 It includes things like tty IO and it is unaffected by whether or not actual
1530 physical disk IO was required (the read might have been satisfied from
1537 I/O counter: chars written
1538 The number of bytes which this task has caused, or shall cause to be written
1539 to disk. Similar caveats apply here as with rchar.
1545 I/O counter: read syscalls
1546 Attempt to count the number of read I/O operations, i.e. syscalls like read()
1553 I/O counter: write syscalls
1554 Attempt to count the number of write I/O operations, i.e. syscalls like
1555 write() and pwrite().
1561 I/O counter: bytes read
1562 Attempt to count the number of bytes which this process really did cause to
1563 be fetched from the storage layer. Done at the submit_bio() level, so it is
1564 accurate for block-backed filesystems. <please add status regarding NFS and
1565 CIFS at a later time>
1571 I/O counter: bytes written
1572 Attempt to count the number of bytes which this process caused to be sent to
1573 the storage layer. This is done at page-dirtying time.
1576 cancelled_write_bytes
1577 ---------------------
1579 The big inaccuracy here is truncate. If a process writes 1MB to a file and
1580 then deletes the file, it will in fact perform no writeout. But it will have
1581 been accounted as having caused 1MB of write.
1582 In other words: The number of bytes which this process caused to not happen,
1583 by truncating pagecache. A task can cause "negative" IO too. If this task
1584 truncates some dirty pagecache, some IO which another task has been accounted
1585 for (in its write_bytes) will not be happening. We _could_ just subtract that
1586 from the truncating task's write_bytes, but there is information loss in doing
1593 At its current implementation state, this is a bit racy on 32-bit machines: if
1594 process A reads process B's /proc/pid/io while process B is updating one of
1595 those 64-bit counters, process A could see an intermediate result.
1598 More information about this can be found within the taskstats documentation in
1599 Documentation/accounting.
1601 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings
1602 ---------------------------------------------------------------
1603 When a process is dumped, all anonymous memory is written to a core file as
1604 long as the size of the core file isn't limited. But sometimes we don't want
1605 to dump some memory segments, for example, huge shared memory or DAX.
1606 Conversely, sometimes we want to save file-backed memory segments into a core
1607 file, not only the individual files.
1609 /proc/<pid>/coredump_filter allows you to customize which memory segments
1610 will be dumped when the <pid> process is dumped. coredump_filter is a bitmask
1611 of memory types. If a bit of the bitmask is set, memory segments of the
1612 corresponding memory type are dumped, otherwise they are not dumped.
1614 The following 9 memory types are supported:
1615 - (bit 0) anonymous private memory
1616 - (bit 1) anonymous shared memory
1617 - (bit 2) file-backed private memory
1618 - (bit 3) file-backed shared memory
1619 - (bit 4) ELF header pages in file-backed private memory areas (it is
1620 effective only if the bit 2 is cleared)
1621 - (bit 5) hugetlb private memory
1622 - (bit 6) hugetlb shared memory
1623 - (bit 7) DAX private memory
1624 - (bit 8) DAX shared memory
1626 Note that MMIO pages such as frame buffer are never dumped and vDSO pages
1627 are always dumped regardless of the bitmask status.
1629 Note that bits 0-4 don't affect hugetlb or DAX memory. hugetlb memory is
1630 only affected by bit 5-6, and DAX is only affected by bits 7-8.
1632 The default value of coredump_filter is 0x33; this means all anonymous memory
1633 segments, ELF header pages and hugetlb private memory are dumped.
1635 If you don't want to dump all shared memory segments attached to pid 1234,
1636 write 0x31 to the process's proc file.
1638 $ echo 0x31 > /proc/1234/coredump_filter
1640 When a new process is created, the process inherits the bitmask status from its
1641 parent. It is useful to set up coredump_filter before the program runs.
1644 $ echo 0x7 > /proc/self/coredump_filter
1647 3.5 /proc/<pid>/mountinfo - Information about mounts
1648 --------------------------------------------------------
1650 This file contains lines of the form:
1652 36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue
1653 (1)(2)(3) (4) (5) (6) (7) (8) (9) (10) (11)
1655 (1) mount ID: unique identifier of the mount (may be reused after umount)
1656 (2) parent ID: ID of parent (or of self for the top of the mount tree)
1657 (3) major:minor: value of st_dev for files on filesystem
1658 (4) root: root of the mount within the filesystem
1659 (5) mount point: mount point relative to the process's root
1660 (6) mount options: per mount options
1661 (7) optional fields: zero or more fields of the form "tag[:value]"
1662 (8) separator: marks the end of the optional fields
1663 (9) filesystem type: name of filesystem of the form "type[.subtype]"
1664 (10) mount source: filesystem specific information or "none"
1665 (11) super options: per super block options
1667 Parsers should ignore all unrecognised optional fields. Currently the
1668 possible optional fields are:
1670 shared:X mount is shared in peer group X
1671 master:X mount is slave to peer group X
1672 propagate_from:X mount is slave and receives propagation from peer group X (*)
1673 unbindable mount is unbindable
1675 (*) X is the closest dominant peer group under the process's root. If
1676 X is the immediate master of the mount, or if there's no dominant peer
1677 group under the same root, then only the "master:X" field is present
1678 and not the "propagate_from:X" field.
1680 For more information on mount propagation see:
1682 Documentation/filesystems/sharedsubtree.txt
1685 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm
1686 --------------------------------------------------------
1687 These files provide a method to access a tasks comm value. It also allows for
1688 a task to set its own or one of its thread siblings comm value. The comm value
1689 is limited in size compared to the cmdline value, so writing anything longer
1690 then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated
1694 3.7 /proc/<pid>/task/<tid>/children - Information about task children
1695 -------------------------------------------------------------------------
1696 This file provides a fast way to retrieve first level children pids
1697 of a task pointed by <pid>/<tid> pair. The format is a space separated
1700 Note the "first level" here -- if a child has own children they will
1701 not be listed here, one needs to read /proc/<children-pid>/task/<tid>/children
1702 to obtain the descendants.
1704 Since this interface is intended to be fast and cheap it doesn't
1705 guarantee to provide precise results and some children might be
1706 skipped, especially if they've exited right after we printed their
1707 pids, so one need to either stop or freeze processes being inspected
1708 if precise results are needed.
1711 3.8 /proc/<pid>/fdinfo/<fd> - Information about opened file
1712 ---------------------------------------------------------------
1713 This file provides information associated with an opened file. The regular
1714 files have at least three fields -- 'pos', 'flags' and mnt_id. The 'pos'
1715 represents the current offset of the opened file in decimal form [see lseek(2)
1716 for details], 'flags' denotes the octal O_xxx mask the file has been
1717 created with [see open(2) for details] and 'mnt_id' represents mount ID of
1718 the file system containing the opened file [see 3.5 /proc/<pid>/mountinfo
1727 All locks associated with a file descriptor are shown in its fdinfo too.
1729 lock: 1: FLOCK ADVISORY WRITE 359 00:13:11691 0 EOF
1731 The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags
1732 pair provide additional information particular to the objects they represent.
1741 where 'eventfd-count' is hex value of a counter.
1748 sigmask: 0000000000000200
1750 where 'sigmask' is hex value of the signal mask associated
1758 tfd: 5 events: 1d data: ffffffffffffffff
1760 where 'tfd' is a target file descriptor number in decimal form,
1761 'events' is events mask being watched and the 'data' is data
1762 associated with a target [see epoll(7) for more details].
1766 For inotify files the format is the following
1770 inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d
1772 where 'wd' is a watch descriptor in decimal form, ie a target file
1773 descriptor number, 'ino' and 'sdev' are inode and device where the
1774 target file resides and the 'mask' is the mask of events, all in hex
1775 form [see inotify(7) for more details].
1777 If the kernel was built with exportfs support, the path to the target
1778 file is encoded as a file handle. The file handle is provided by three
1779 fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex
1782 If the kernel is built without exportfs support the file handle won't be
1785 If there is no inotify mark attached yet the 'inotify' line will be omitted.
1787 For fanotify files the format is
1792 fanotify flags:10 event-flags:0
1793 fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003
1794 fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4
1796 where fanotify 'flags' and 'event-flags' are values used in fanotify_init
1797 call, 'mnt_id' is the mount point identifier, 'mflags' is the value of
1798 flags associated with mark which are tracked separately from events
1799 mask. 'ino', 'sdev' are target inode and device, 'mask' is the events
1800 mask and 'ignored_mask' is the mask of events which are to be ignored.
1801 All in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask'
1802 does provide information about flags and mask used in fanotify_mark
1803 call [see fsnotify manpage for details].
1805 While the first three lines are mandatory and always printed, the rest is
1806 optional and may be omitted if no marks created yet.
1817 it_value: (0, 49406829)
1820 where 'clockid' is the clock type and 'ticks' is the number of the timer expirations
1821 that have occurred [see timerfd_create(2) for details]. 'settime flags' are
1822 flags in octal form been used to setup the timer [see timerfd_settime(2) for
1823 details]. 'it_value' is remaining time until the timer exiration.
1824 'it_interval' is the interval for the timer. Note the timer might be set up
1825 with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value'
1826 still exhibits timer's remaining time.
1828 3.9 /proc/<pid>/map_files - Information about memory mapped files
1829 ---------------------------------------------------------------------
1830 This directory contains symbolic links which represent memory mapped files
1831 the process is maintaining. Example output:
1833 | lr-------- 1 root root 64 Jan 27 11:24 333c600000-333c620000 -> /usr/lib64/ld-2.18.so
1834 | lr-------- 1 root root 64 Jan 27 11:24 333c81f000-333c820000 -> /usr/lib64/ld-2.18.so
1835 | lr-------- 1 root root 64 Jan 27 11:24 333c820000-333c821000 -> /usr/lib64/ld-2.18.so
1837 | lr-------- 1 root root 64 Jan 27 11:24 35d0421000-35d0422000 -> /usr/lib64/libselinux.so.1
1838 | lr-------- 1 root root 64 Jan 27 11:24 400000-41a000 -> /usr/bin/ls
1840 The name of a link represents the virtual memory bounds of a mapping, i.e.
1841 vm_area_struct::vm_start-vm_area_struct::vm_end.
1843 The main purpose of the map_files is to retrieve a set of memory mapped
1844 files in a fast way instead of parsing /proc/<pid>/maps or
1845 /proc/<pid>/smaps, both of which contain many more records. At the same
1846 time one can open(2) mappings from the listings of two processes and
1847 comparing their inode numbers to figure out which anonymous memory areas
1848 are actually shared.
1850 ------------------------------------------------------------------------------
1852 ------------------------------------------------------------------------------
1855 ---------------------
1857 The following mount options are supported:
1859 hidepid= Set /proc/<pid>/ access mode.
1860 gid= Set the group authorized to learn processes information.
1862 hidepid=0 means classic mode - everybody may access all /proc/<pid>/ directories
1865 hidepid=1 means users may not access any /proc/<pid>/ directories but their
1866 own. Sensitive files like cmdline, sched*, status are now protected against
1867 other users. This makes it impossible to learn whether any user runs
1868 specific program (given the program doesn't reveal itself by its behaviour).
1869 As an additional bonus, as /proc/<pid>/cmdline is unaccessible for other users,
1870 poorly written programs passing sensitive information via program arguments are
1871 now protected against local eavesdroppers.
1873 hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be fully invisible to other
1874 users. It doesn't mean that it hides a fact whether a process with a specific
1875 pid value exists (it can be learned by other means, e.g. by "kill -0 $PID"),
1876 but it hides process' uid and gid, which may be learned by stat()'ing
1877 /proc/<pid>/ otherwise. It greatly complicates an intruder's task of gathering
1878 information about running processes, whether some daemon runs with elevated
1879 privileges, whether other user runs some sensitive program, whether other users
1880 run any program at all, etc.
1882 gid= defines a group authorized to learn processes information otherwise
1883 prohibited by hidepid=. If you use some daemon like identd which needs to learn
1884 information about processes information, just add identd to this group.