About Kernel Documentation Linux Kernel Contact Linux Resources Linux Blog

Documentation / filesystems / proc.txt




Custom Search

Based on kernel version 4.0. Page generated on 2015-04-14 21:24 EST.

1	------------------------------------------------------------------------------
2	                       T H E  /proc   F I L E S Y S T E M
3	------------------------------------------------------------------------------
4	/proc/sys         Terrehon Bowden <terrehon@pacbell.net>        October 7 1999
5	                  Bodo Bauer <bb@ricochet.net>
6	
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
14	
15	Table of Contents
16	-----------------
17	
18	  0     Preface
19	  0.1	Introduction/Credits
20	  0.2	Legal Stuff
21	
22	  1	Collecting System Information
23	  1.1	Process-Specific Subdirectories
24	  1.2	Kernel data
25	  1.3	IDE devices in /proc/ide
26	  1.4	Networking info in /proc/net
27	  1.5	SCSI info
28	  1.6	Parallel port info in /proc/parport
29	  1.7	TTY info in /proc/tty
30	  1.8	Miscellaneous kernel statistics in /proc/stat
31	  1.9	Ext4 file system parameters
32	
33	  2	Modifying System Parameters
34	
35	  3	Per-Process Parameters
36	  3.1	/proc/<pid>/oom_adj & /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
45	  3.9   /proc/<pid>/map_files - Information about memory mapped files
46	
47	  4	Configuring procfs
48	  4.1	Mount options
49	
50	------------------------------------------------------------------------------
51	Preface
52	------------------------------------------------------------------------------
53	
54	0.1 Introduction/Credits
55	------------------------
56	
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
68	mail them to Bodo.
69	
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... :)
76	
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
79	document.
80	
81	The   latest   version    of   this   document   is    available   online   at
82	http://tldp.org/LDP/Linux-Filesystem-Hierarchy/html/proc.html
83	
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.
87	
88	0.2 Legal Stuff
89	---------------
90	
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...
94	
95	------------------------------------------------------------------------------
96	CHAPTER 1: COLLECTING SYSTEM INFORMATION
97	------------------------------------------------------------------------------
98	
99	------------------------------------------------------------------------------
100	In This Chapter
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
106	  on the system
107	------------------------------------------------------------------------------
108	
109	
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).
113	
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.
116	
117	1.1 Process-Specific Subdirectories
118	-----------------------------------
119	
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).
122	
123	The link  self  points  to  the  process reading the file system. Each process
124	subdirectory has the entries listed in Table 1-1.
125	
126	
127	Table 1-1: Process specific entries in /proc
128	..............................................................................
129	 File		Content
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
140	 stat		Process status
141	 statm		Process memory status information
142	 status		Process status in human readable form
143	 wchan		If CONFIG_KALLSYMS is set, a pre-decoded wchan
144	 pagemap	Page table
145	 stack		Report full stack trace, enable via CONFIG_STACKTRACE
146	 smaps		a extension based on maps, showing the memory consumption of
147			each mapping and flags associated with it
148	 numa_maps	an extension based on maps, showing the memory locality and
149			binding policy as well as mem usage (in pages) of each mapping.
150	..............................................................................
151	
152	For example, to get the status information of a process, all you have to do is
153	read the file /proc/PID/status:
154	
155	  >cat /proc/self/status
156	  Name:   cat
157	  State:  R (running)
158	  Tgid:   5452
159	  Pid:    5452
160	  PPid:   743
161	  TracerPid:      0						(2.4)
162	  Uid:    501     501     501     501
163	  Gid:    100     100     100     100
164	  FDSize: 256
165	  Groups: 100 14 16
166	  VmPeak:     5004 kB
167	  VmSize:     5004 kB
168	  VmLck:         0 kB
169	  VmHWM:       476 kB
170	  VmRSS:       476 kB
171	  VmData:      156 kB
172	  VmStk:        88 kB
173	  VmExe:        68 kB
174	  VmLib:      1412 kB
175	  VmPTE:        20 kb
176	  VmSwap:        0 kB
177	  Threads:        1
178	  SigQ:   0/28578
179	  SigPnd: 0000000000000000
180	  ShdPnd: 0000000000000000
181	  SigBlk: 0000000000000000
182	  SigIgn: 0000000000000000
183	  SigCgt: 0000000000000000
184	  CapInh: 00000000fffffeff
185	  CapPrm: 0000000000000000
186	  CapEff: 0000000000000000
187	  CapBnd: ffffffffffffffff
188	  Seccomp:        0
189	  voluntary_ctxt_switches:        0
190	  nonvoluntary_ctxt_switches:     1
191	
192	This shows you nearly the same information you would get if you viewed it with
193	the ps  command.  In  fact,  ps  uses  the  proc  file  system  to  obtain its
194	information.  But you get a more detailed  view of the  process by reading the
195	file /proc/PID/status. It fields are described in table 1-2.
196	
197	The  statm  file  contains  more  detailed  information about the process
198	memory usage. Its seven fields are explained in Table 1-3.  The stat file
199	contains details information about the process itself.  Its fields are
200	explained in Table 1-4.
201	
202	(for SMP CONFIG users)
203	For making accounting scalable, RSS related information are handled in
204	asynchronous manner and the vaule may not be very precise. To see a precise
205	snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
206	It's slow but very precise.
207	
208	Table 1-2: Contents of the status files (as of 2.6.30-rc7)
209	..............................................................................
210	 Field                       Content
211	 Name                        filename of the executable
212	 State                       state (R is running, S is sleeping, D is sleeping
213	                             in an uninterruptible wait, Z is zombie,
214				     T is traced or stopped)
215	 Tgid                        thread group ID
216	 Pid                         process id
217	 PPid                        process id of the parent process
218	 TracerPid                   PID of process tracing this process (0 if not)
219	 Uid                         Real, effective, saved set, and  file system UIDs
220	 Gid                         Real, effective, saved set, and  file system GIDs
221	 FDSize                      number of file descriptor slots currently allocated
222	 Groups                      supplementary group list
223	 VmPeak                      peak virtual memory size
224	 VmSize                      total program size
225	 VmLck                       locked memory size
226	 VmHWM                       peak resident set size ("high water mark")
227	 VmRSS                       size of memory portions
228	 VmData                      size of data, stack, and text segments
229	 VmStk                       size of data, stack, and text segments
230	 VmExe                       size of text segment
231	 VmLib                       size of shared library code
232	 VmPTE                       size of page table entries
233	 VmSwap                      size of swap usage (the number of referred swapents)
234	 Threads                     number of threads
235	 SigQ                        number of signals queued/max. number for queue
236	 SigPnd                      bitmap of pending signals for the thread
237	 ShdPnd                      bitmap of shared pending signals for the process
238	 SigBlk                      bitmap of blocked signals
239	 SigIgn                      bitmap of ignored signals
240	 SigCgt                      bitmap of caught signals
241	 CapInh                      bitmap of inheritable capabilities
242	 CapPrm                      bitmap of permitted capabilities
243	 CapEff                      bitmap of effective capabilities
244	 CapBnd                      bitmap of capabilities bounding set
245	 Seccomp                     seccomp mode, like prctl(PR_GET_SECCOMP, ...)
246	 Cpus_allowed                mask of CPUs on which this process may run
247	 Cpus_allowed_list           Same as previous, but in "list format"
248	 Mems_allowed                mask of memory nodes allowed to this process
249	 Mems_allowed_list           Same as previous, but in "list format"
250	 voluntary_ctxt_switches     number of voluntary context switches
251	 nonvoluntary_ctxt_switches  number of non voluntary context switches
252	..............................................................................
253	
254	Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
255	..............................................................................
256	 Field    Content
257	 size     total program size (pages)		(same as VmSize in status)
258	 resident size of memory portions (pages)	(same as VmRSS in status)
259	 shared   number of pages that are shared	(i.e. backed by a file)
260	 trs      number of pages that are 'code'	(not including libs; broken,
261								includes data segment)
262	 lrs      number of pages of library		(always 0 on 2.6)
263	 drs      number of pages of data/stack		(including libs; broken,
264								includes library text)
265	 dt       number of dirty pages			(always 0 on 2.6)
266	..............................................................................
267	
268	
269	Table 1-4: Contents of the stat files (as of 2.6.30-rc7)
270	..............................................................................
271	 Field          Content
272	  pid           process id
273	  tcomm         filename of the executable
274	  state         state (R is running, S is sleeping, D is sleeping in an
275	                uninterruptible wait, Z is zombie, T is traced or stopped)
276	  ppid          process id of the parent process
277	  pgrp          pgrp of the process
278	  sid           session id
279	  tty_nr        tty the process uses
280	  tty_pgrp      pgrp of the tty
281	  flags         task flags
282	  min_flt       number of minor faults
283	  cmin_flt      number of minor faults with child's
284	  maj_flt       number of major faults
285	  cmaj_flt      number of major faults with child's
286	  utime         user mode jiffies
287	  stime         kernel mode jiffies
288	  cutime        user mode jiffies with child's
289	  cstime        kernel mode jiffies with child's
290	  priority      priority level
291	  nice          nice level
292	  num_threads   number of threads
293	  it_real_value	(obsolete, always 0)
294	  start_time    time the process started after system boot
295	  vsize         virtual memory size
296	  rss           resident set memory size
297	  rsslim        current limit in bytes on the rss
298	  start_code    address above which program text can run
299	  end_code      address below which program text can run
300	  start_stack   address of the start of the main process stack
301	  esp           current value of ESP
302	  eip           current value of EIP
303	  pending       bitmap of pending signals
304	  blocked       bitmap of blocked signals
305	  sigign        bitmap of ignored signals
306	  sigcatch      bitmap of caught signals
307	  wchan         address where process went to sleep
308	  0             (place holder)
309	  0             (place holder)
310	  exit_signal   signal to send to parent thread on exit
311	  task_cpu      which CPU the task is scheduled on
312	  rt_priority   realtime priority
313	  policy        scheduling policy (man sched_setscheduler)
314	  blkio_ticks   time spent waiting for block IO
315	  gtime         guest time of the task in jiffies
316	  cgtime        guest time of the task children in jiffies
317	  start_data    address above which program data+bss is placed
318	  end_data      address below which program data+bss is placed
319	  start_brk     address above which program heap can be expanded with brk()
320	  arg_start     address above which program command line is placed
321	  arg_end       address below which program command line is placed
322	  env_start     address above which program environment is placed
323	  env_end       address below which program environment is placed
324	  exit_code     the thread's exit_code in the form reported by the waitpid system call
325	..............................................................................
326	
327	The /proc/PID/maps file containing the currently mapped memory regions and
328	their access permissions.
329	
330	The format is:
331	
332	address           perms offset  dev   inode      pathname
333	
334	08048000-08049000 r-xp 00000000 03:00 8312       /opt/test
335	08049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
336	0804a000-0806b000 rw-p 00000000 00:00 0          [heap]
337	a7cb1000-a7cb2000 ---p 00000000 00:00 0
338	a7cb2000-a7eb2000 rw-p 00000000 00:00 0
339	a7eb2000-a7eb3000 ---p 00000000 00:00 0
340	a7eb3000-a7ed5000 rw-p 00000000 00:00 0          [stack:1001]
341	a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
342	a8008000-a800a000 r--p 00133000 03:00 4222       /lib/libc.so.6
343	a800a000-a800b000 rw-p 00135000 03:00 4222       /lib/libc.so.6
344	a800b000-a800e000 rw-p 00000000 00:00 0
345	a800e000-a8022000 r-xp 00000000 03:00 14462      /lib/libpthread.so.0
346	a8022000-a8023000 r--p 00013000 03:00 14462      /lib/libpthread.so.0
347	a8023000-a8024000 rw-p 00014000 03:00 14462      /lib/libpthread.so.0
348	a8024000-a8027000 rw-p 00000000 00:00 0
349	a8027000-a8043000 r-xp 00000000 03:00 8317       /lib/ld-linux.so.2
350	a8043000-a8044000 r--p 0001b000 03:00 8317       /lib/ld-linux.so.2
351	a8044000-a8045000 rw-p 0001c000 03:00 8317       /lib/ld-linux.so.2
352	aff35000-aff4a000 rw-p 00000000 00:00 0          [stack]
353	ffffe000-fffff000 r-xp 00000000 00:00 0          [vdso]
354	
355	where "address" is the address space in the process that it occupies, "perms"
356	is a set of permissions:
357	
358	 r = read
359	 w = write
360	 x = execute
361	 s = shared
362	 p = private (copy on write)
363	
364	"offset" is the offset into the mapping, "dev" is the device (major:minor), and
365	"inode" is the inode  on that device.  0 indicates that  no inode is associated
366	with the memory region, as the case would be with BSS (uninitialized data).
367	The "pathname" shows the name associated file for this mapping.  If the mapping
368	is not associated with a file:
369	
370	 [heap]                   = the heap of the program
371	 [stack]                  = the stack of the main process
372	 [stack:1001]             = the stack of the thread with tid 1001
373	 [vdso]                   = the "virtual dynamic shared object",
374	                            the kernel system call handler
375	
376	 or if empty, the mapping is anonymous.
377	
378	The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint
379	of the individual tasks of a process. In this file you will see a mapping marked
380	as [stack] if that task sees it as a stack. This is a key difference from the
381	content of /proc/PID/maps, where you will see all mappings that are being used
382	as stack by all of those tasks. Hence, for the example above, the task-level
383	map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
384	
385	08048000-08049000 r-xp 00000000 03:00 8312       /opt/test
386	08049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
387	0804a000-0806b000 rw-p 00000000 00:00 0          [heap]
388	a7cb1000-a7cb2000 ---p 00000000 00:00 0
389	a7cb2000-a7eb2000 rw-p 00000000 00:00 0
390	a7eb2000-a7eb3000 ---p 00000000 00:00 0
391	a7eb3000-a7ed5000 rw-p 00000000 00:00 0          [stack]
392	a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
393	a8008000-a800a000 r--p 00133000 03:00 4222       /lib/libc.so.6
394	a800a000-a800b000 rw-p 00135000 03:00 4222       /lib/libc.so.6
395	a800b000-a800e000 rw-p 00000000 00:00 0
396	a800e000-a8022000 r-xp 00000000 03:00 14462      /lib/libpthread.so.0
397	a8022000-a8023000 r--p 00013000 03:00 14462      /lib/libpthread.so.0
398	a8023000-a8024000 rw-p 00014000 03:00 14462      /lib/libpthread.so.0
399	a8024000-a8027000 rw-p 00000000 00:00 0
400	a8027000-a8043000 r-xp 00000000 03:00 8317       /lib/ld-linux.so.2
401	a8043000-a8044000 r--p 0001b000 03:00 8317       /lib/ld-linux.so.2
402	a8044000-a8045000 rw-p 0001c000 03:00 8317       /lib/ld-linux.so.2
403	aff35000-aff4a000 rw-p 00000000 00:00 0
404	ffffe000-fffff000 r-xp 00000000 00:00 0          [vdso]
405	
406	The /proc/PID/smaps is an extension based on maps, showing the memory
407	consumption for each of the process's mappings. For each of mappings there
408	is a series of lines such as the following:
409	
410	08048000-080bc000 r-xp 00000000 03:02 13130      /bin/bash
411	Size:               1084 kB
412	Rss:                 892 kB
413	Pss:                 374 kB
414	Shared_Clean:        892 kB
415	Shared_Dirty:          0 kB
416	Private_Clean:         0 kB
417	Private_Dirty:         0 kB
418	Referenced:          892 kB
419	Anonymous:             0 kB
420	Swap:                  0 kB
421	KernelPageSize:        4 kB
422	MMUPageSize:           4 kB
423	Locked:              374 kB
424	VmFlags: rd ex mr mw me de
425	
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.
439	
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
471	
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.
475	
476	This file is only present if the CONFIG_MMU kernel configuration option is
477	enabled.
478	
479	The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
480	bits on both physical and virtual pages associated with a process, and the
481	soft-dirty bit on pte (see Documentation/vm/soft-dirty.txt for details).
482	To clear the bits for all the pages associated with the process
483	    > echo 1 > /proc/PID/clear_refs
484	
485	To clear the bits for the anonymous pages associated with the process
486	    > echo 2 > /proc/PID/clear_refs
487	
488	To clear the bits for the file mapped pages associated with the process
489	    > echo 3 > /proc/PID/clear_refs
490	
491	To clear the soft-dirty bit
492	    > echo 4 > /proc/PID/clear_refs
493	
494	To reset the peak resident set size ("high water mark") to the process's
495	current value:
496	    > echo 5 > /proc/PID/clear_refs
497	
498	Any other value written to /proc/PID/clear_refs will have no effect.
499	
500	The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
501	using /proc/kpageflags and number of times a page is mapped using
502	/proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.txt.
503	
504	The /proc/pid/numa_maps is an extension based on maps, showing the memory
505	locality and binding policy, as well as the memory usage (in pages) of
506	each mapping. The output follows a general format where mapping details get
507	summarized separated by blank spaces, one mapping per each file line:
508	
509	address   policy    mapping details
510	
511	00400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4
512	00600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4
513	3206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4
514	320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
515	3206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
516	3206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4
517	3206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4
518	320698b000 default file=/lib64/libc-2.12.so
519	3206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4
520	3206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
521	3206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4
522	7f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4
523	7f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4
524	7f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048
525	7fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4
526	7fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4
527	
528	Where:
529	"address" is the starting address for the mapping;
530	"policy" reports the NUMA memory policy set for the mapping (see vm/numa_memory_policy.txt);
531	"mapping details" summarizes mapping data such as mapping type, page usage counters,
532	node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page
533	size, in KB, that is backing the mapping up.
534	
535	1.2 Kernel data
536	---------------
537	
538	Similar to  the  process entries, the kernel data files give information about
539	the running kernel. The files used to obtain this information are contained in
540	/proc and  are  listed  in Table 1-5. Not all of these will be present in your
541	system. It  depends  on the kernel configuration and the loaded modules, which
542	files are there, and which are missing.
543	
544	Table 1-5: Kernel info in /proc
545	..............................................................................
546	 File        Content                                           
547	 apm         Advanced power management info                    
548	 buddyinfo   Kernel memory allocator information (see text)	(2.5)
549	 bus         Directory containing bus specific information     
550	 cmdline     Kernel command line                               
551	 cpuinfo     Info about the CPU                                
552	 devices     Available devices (block and character)           
553	 dma         Used DMS channels                                 
554	 filesystems Supported filesystems                             
555	 driver	     Various drivers grouped here, currently rtc (2.4)
556	 execdomains Execdomains, related to security			(2.4)
557	 fb	     Frame Buffer devices				(2.4)
558	 fs	     File system parameters, currently nfs/exports	(2.4)
559	 ide         Directory containing info about the IDE subsystem 
560	 interrupts  Interrupt usage                                   
561	 iomem	     Memory map						(2.4)
562	 ioports     I/O port usage                                    
563	 irq	     Masks for irq to cpu affinity			(2.4)(smp?)
564	 isapnp	     ISA PnP (Plug&Play) Info				(2.4)
565	 kcore       Kernel core image (can be ELF or A.OUT(deprecated in 2.4))   
566	 kmsg        Kernel messages                                   
567	 ksyms       Kernel symbol table                               
568	 loadavg     Load average of last 1, 5 & 15 minutes                
569	 locks       Kernel locks                                      
570	 meminfo     Memory info                                       
571	 misc        Miscellaneous                                     
572	 modules     List of loaded modules                            
573	 mounts      Mounted filesystems                               
574	 net         Networking info (see text)                        
575	 pagetypeinfo Additional page allocator information (see text)  (2.5)
576	 partitions  Table of partitions known to the system           
577	 pci	     Deprecated info of PCI bus (new way -> /proc/bus/pci/,
578	             decoupled by lspci					(2.4)
579	 rtc         Real time clock                                   
580	 scsi        SCSI info (see text)                              
581	 slabinfo    Slab pool info                                    
582	 softirqs    softirq usage
583	 stat        Overall statistics                                
584	 swaps       Swap space utilization                            
585	 sys         See chapter 2                                     
586	 sysvipc     Info of SysVIPC Resources (msg, sem, shm)		(2.4)
587	 tty	     Info of tty drivers
588	 uptime      Wall clock since boot, combined idle time of all cpus
589	 version     Kernel version                                    
590	 video	     bttv info of video resources			(2.4)
591	 vmallocinfo Show vmalloced areas
592	..............................................................................
593	
594	You can,  for  example,  check  which interrupts are currently in use and what
595	they are used for by looking in the file /proc/interrupts:
596	
597	  > cat /proc/interrupts 
598	             CPU0        
599	    0:    8728810          XT-PIC  timer 
600	    1:        895          XT-PIC  keyboard 
601	    2:          0          XT-PIC  cascade 
602	    3:     531695          XT-PIC  aha152x 
603	    4:    2014133          XT-PIC  serial 
604	    5:      44401          XT-PIC  pcnet_cs 
605	    8:          2          XT-PIC  rtc 
606	   11:          8          XT-PIC  i82365 
607	   12:     182918          XT-PIC  PS/2 Mouse 
608	   13:          1          XT-PIC  fpu 
609	   14:    1232265          XT-PIC  ide0 
610	   15:          7          XT-PIC  ide1 
611	  NMI:          0 
612	
613	In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the
614	output of a SMP machine):
615	
616	  > cat /proc/interrupts 
617	
618	             CPU0       CPU1       
619	    0:    1243498    1214548    IO-APIC-edge  timer
620	    1:       8949       8958    IO-APIC-edge  keyboard
621	    2:          0          0          XT-PIC  cascade
622	    5:      11286      10161    IO-APIC-edge  soundblaster
623	    8:          1          0    IO-APIC-edge  rtc
624	    9:      27422      27407    IO-APIC-edge  3c503
625	   12:     113645     113873    IO-APIC-edge  PS/2 Mouse
626	   13:          0          0          XT-PIC  fpu
627	   14:      22491      24012    IO-APIC-edge  ide0
628	   15:       2183       2415    IO-APIC-edge  ide1
629	   17:      30564      30414   IO-APIC-level  eth0
630	   18:        177        164   IO-APIC-level  bttv
631	  NMI:    2457961    2457959 
632	  LOC:    2457882    2457881 
633	  ERR:       2155
634	
635	NMI is incremented in this case because every timer interrupt generates a NMI
636	(Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups.
637	
638	LOC is the local interrupt counter of the internal APIC of every CPU.
639	
640	ERR is incremented in the case of errors in the IO-APIC bus (the bus that
641	connects the CPUs in a SMP system. This means that an error has been detected,
642	the IO-APIC automatically retry the transmission, so it should not be a big
643	problem, but you should read the SMP-FAQ.
644	
645	In 2.6.2* /proc/interrupts was expanded again.  This time the goal was for
646	/proc/interrupts to display every IRQ vector in use by the system, not
647	just those considered 'most important'.  The new vectors are:
648	
649	  THR -- interrupt raised when a machine check threshold counter
650	  (typically counting ECC corrected errors of memory or cache) exceeds
651	  a configurable threshold.  Only available on some systems.
652	
653	  TRM -- a thermal event interrupt occurs when a temperature threshold
654	  has been exceeded for the CPU.  This interrupt may also be generated
655	  when the temperature drops back to normal.
656	
657	  SPU -- a spurious interrupt is some interrupt that was raised then lowered
658	  by some IO device before it could be fully processed by the APIC.  Hence
659	  the APIC sees the interrupt but does not know what device it came from.
660	  For this case the APIC will generate the interrupt with a IRQ vector
661	  of 0xff. This might also be generated by chipset bugs.
662	
663	  RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are
664	  sent from one CPU to another per the needs of the OS.  Typically,
665	  their statistics are used by kernel developers and interested users to
666	  determine the occurrence of interrupts of the given type.
667	
668	The above IRQ vectors are displayed only when relevant.  For example,
669	the threshold vector does not exist on x86_64 platforms.  Others are
670	suppressed when the system is a uniprocessor.  As of this writing, only
671	i386 and x86_64 platforms support the new IRQ vector displays.
672	
673	Of some interest is the introduction of the /proc/irq directory to 2.4.
674	It could be used to set IRQ to CPU affinity, this means that you can "hook" an
675	IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
676	irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and
677	prof_cpu_mask.
678	
679	For example 
680	  > ls /proc/irq/
681	  0  10  12  14  16  18  2  4  6  8  prof_cpu_mask
682	  1  11  13  15  17  19  3  5  7  9  default_smp_affinity
683	  > ls /proc/irq/0/
684	  smp_affinity
685	
686	smp_affinity is a bitmask, in which you can specify which CPUs can handle the
687	IRQ, you can set it by doing:
688	
689	  > echo 1 > /proc/irq/10/smp_affinity
690	
691	This means that only the first CPU will handle the IRQ, but you can also echo
692	5 which means that only the first and fourth CPU can handle the IRQ.
693	
694	The contents of each smp_affinity file is the same by default:
695	
696	  > cat /proc/irq/0/smp_affinity
697	  ffffffff
698	
699	There is an alternate interface, smp_affinity_list which allows specifying
700	a cpu range instead of a bitmask:
701	
702	  > cat /proc/irq/0/smp_affinity_list
703	  1024-1031
704	
705	The default_smp_affinity mask applies to all non-active IRQs, which are the
706	IRQs which have not yet been allocated/activated, and hence which lack a
707	/proc/irq/[0-9]* directory.
708	
709	The node file on an SMP system shows the node to which the device using the IRQ
710	reports itself as being attached. This hardware locality information does not
711	include information about any possible driver locality preference.
712	
713	prof_cpu_mask specifies which CPUs are to be profiled by the system wide
714	profiler. Default value is ffffffff (all cpus if there are only 32 of them).
715	
716	The way IRQs are routed is handled by the IO-APIC, and it's Round Robin
717	between all the CPUs which are allowed to handle it. As usual the kernel has
718	more info than you and does a better job than you, so the defaults are the
719	best choice for almost everyone.  [Note this applies only to those IO-APIC's
720	that support "Round Robin" interrupt distribution.]
721	
722	There are  three  more  important subdirectories in /proc: net, scsi, and sys.
723	The general  rule  is  that  the  contents,  or  even  the  existence of these
724	directories, depend  on your kernel configuration. If SCSI is not enabled, the
725	directory scsi  may  not  exist. The same is true with the net, which is there
726	only when networking support is present in the running kernel.
727	
728	The slabinfo  file  gives  information  about  memory usage at the slab level.
729	Linux uses  slab  pools for memory management above page level in version 2.2.
730	Commonly used  objects  have  their  own  slab  pool (such as network buffers,
731	directory cache, and so on).
732	
733	..............................................................................
734	
735	> cat /proc/buddyinfo
736	
737	Node 0, zone      DMA      0      4      5      4      4      3 ...
738	Node 0, zone   Normal      1      0      0      1    101      8 ...
739	Node 0, zone  HighMem      2      0      0      1      1      0 ...
740	
741	External fragmentation is a problem under some workloads, and buddyinfo is a
742	useful tool for helping diagnose these problems.  Buddyinfo will give you a 
743	clue as to how big an area you can safely allocate, or why a previous
744	allocation failed.
745	
746	Each column represents the number of pages of a certain order which are 
747	available.  In this case, there are 0 chunks of 2^0*PAGE_SIZE available in 
748	ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE 
749	available in ZONE_NORMAL, etc... 
750	
751	More information relevant to external fragmentation can be found in
752	pagetypeinfo.
753	
754	> cat /proc/pagetypeinfo
755	Page block order: 9
756	Pages per block:  512
757	
758	Free pages count per migrate type at order       0      1      2      3      4      5      6      7      8      9     10
759	Node    0, zone      DMA, type    Unmovable      0      0      0      1      1      1      1      1      1      1      0
760	Node    0, zone      DMA, type  Reclaimable      0      0      0      0      0      0      0      0      0      0      0
761	Node    0, zone      DMA, type      Movable      1      1      2      1      2      1      1      0      1      0      2
762	Node    0, zone      DMA, type      Reserve      0      0      0      0      0      0      0      0      0      1      0
763	Node    0, zone      DMA, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
764	Node    0, zone    DMA32, type    Unmovable    103     54     77      1      1      1     11      8      7      1      9
765	Node    0, zone    DMA32, type  Reclaimable      0      0      2      1      0      0      0      0      1      0      0
766	Node    0, zone    DMA32, type      Movable    169    152    113     91     77     54     39     13      6      1    452
767	Node    0, zone    DMA32, type      Reserve      1      2      2      2      2      0      1      1      1      1      0
768	Node    0, zone    DMA32, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
769	
770	Number of blocks type     Unmovable  Reclaimable      Movable      Reserve      Isolate
771	Node 0, zone      DMA            2            0            5            1            0
772	Node 0, zone    DMA32           41            6          967            2            0
773	
774	Fragmentation avoidance in the kernel works by grouping pages of different
775	migrate types into the same contiguous regions of memory called page blocks.
776	A page block is typically the size of the default hugepage size e.g. 2MB on
777	X86-64. By keeping pages grouped based on their ability to move, the kernel
778	can reclaim pages within a page block to satisfy a high-order allocation.
779	
780	The pagetypinfo begins with information on the size of a page block. It
781	then gives the same type of information as buddyinfo except broken down
782	by migrate-type and finishes with details on how many page blocks of each
783	type exist.
784	
785	If min_free_kbytes has been tuned correctly (recommendations made by hugeadm
786	from libhugetlbfs http://sourceforge.net/projects/libhugetlbfs/), one can
787	make an estimate of the likely number of huge pages that can be allocated
788	at a given point in time. All the "Movable" blocks should be allocatable
789	unless memory has been mlock()'d. Some of the Reclaimable blocks should
790	also be allocatable although a lot of filesystem metadata may have to be
791	reclaimed to achieve this.
792	
793	..............................................................................
794	
795	meminfo:
796	
797	Provides information about distribution and utilization of memory.  This
798	varies by architecture and compile options.  The following is from a
799	16GB PIII, which has highmem enabled.  You may not have all of these fields.
800	
801	> cat /proc/meminfo
802	
803	The "Locked" indicates whether the mapping is locked in memory or not.
804	
805	
806	MemTotal:     16344972 kB
807	MemFree:      13634064 kB
808	MemAvailable: 14836172 kB
809	Buffers:          3656 kB
810	Cached:        1195708 kB
811	SwapCached:          0 kB
812	Active:         891636 kB
813	Inactive:      1077224 kB
814	HighTotal:    15597528 kB
815	HighFree:     13629632 kB
816	LowTotal:       747444 kB
817	LowFree:          4432 kB
818	SwapTotal:           0 kB
819	SwapFree:            0 kB
820	Dirty:             968 kB
821	Writeback:           0 kB
822	AnonPages:      861800 kB
823	Mapped:         280372 kB
824	Slab:           284364 kB
825	SReclaimable:   159856 kB
826	SUnreclaim:     124508 kB
827	PageTables:      24448 kB
828	NFS_Unstable:        0 kB
829	Bounce:              0 kB
830	WritebackTmp:        0 kB
831	CommitLimit:   7669796 kB
832	Committed_AS:   100056 kB
833	VmallocTotal:   112216 kB
834	VmallocUsed:       428 kB
835	VmallocChunk:   111088 kB
836	AnonHugePages:   49152 kB
837	
838	    MemTotal: Total usable ram (i.e. physical ram minus a few reserved
839	              bits and the kernel binary code)
840	     MemFree: The sum of LowFree+HighFree
841	MemAvailable: An estimate of how much memory is available for starting new
842	              applications, without swapping. Calculated from MemFree,
843	              SReclaimable, the size of the file LRU lists, and the low
844	              watermarks in each zone.
845	              The estimate takes into account that the system needs some
846	              page cache to function well, and that not all reclaimable
847	              slab will be reclaimable, due to items being in use. The
848	              impact of those factors will vary from system to system.
849	     Buffers: Relatively temporary storage for raw disk blocks
850	              shouldn't get tremendously large (20MB or so)
851	      Cached: in-memory cache for files read from the disk (the
852	              pagecache).  Doesn't include SwapCached
853	  SwapCached: Memory that once was swapped out, is swapped back in but
854	              still also is in the swapfile (if memory is needed it
855	              doesn't need to be swapped out AGAIN because it is already
856	              in the swapfile. This saves I/O)
857	      Active: Memory that has been used more recently and usually not
858	              reclaimed unless absolutely necessary.
859	    Inactive: Memory which has been less recently used.  It is more
860	              eligible to be reclaimed for other purposes
861	   HighTotal:
862	    HighFree: Highmem is all memory above ~860MB of physical memory
863	              Highmem areas are for use by userspace programs, or
864	              for the pagecache.  The kernel must use tricks to access
865	              this memory, making it slower to access than lowmem.
866	    LowTotal:
867	     LowFree: Lowmem is memory which can be used for everything that
868	              highmem can be used for, but it is also available for the
869	              kernel's use for its own data structures.  Among many
870	              other things, it is where everything from the Slab is
871	              allocated.  Bad things happen when you're out of lowmem.
872	   SwapTotal: total amount of swap space available
873	    SwapFree: Memory which has been evicted from RAM, and is temporarily
874	              on the disk
875	       Dirty: Memory which is waiting to get written back to the disk
876	   Writeback: Memory which is actively being written back to the disk
877	   AnonPages: Non-file backed pages mapped into userspace page tables
878	AnonHugePages: Non-file backed huge pages mapped into userspace page tables
879	      Mapped: files which have been mmaped, such as libraries
880	        Slab: in-kernel data structures cache
881	SReclaimable: Part of Slab, that might be reclaimed, such as caches
882	  SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure
883	  PageTables: amount of memory dedicated to the lowest level of page
884	              tables.
885	NFS_Unstable: NFS pages sent to the server, but not yet committed to stable
886		      storage
887	      Bounce: Memory used for block device "bounce buffers"
888	WritebackTmp: Memory used by FUSE for temporary writeback buffers
889	 CommitLimit: Based on the overcommit ratio ('vm.overcommit_ratio'),
890	              this is the total amount of  memory currently available to
891	              be allocated on the system. This limit is only adhered to
892	              if strict overcommit accounting is enabled (mode 2 in
893	              'vm.overcommit_memory').
894	              The CommitLimit is calculated with the following formula:
895	              CommitLimit = ([total RAM pages] - [total huge TLB pages]) *
896	                             overcommit_ratio / 100 + [total swap pages]
897	              For example, on a system with 1G of physical RAM and 7G
898	              of swap with a `vm.overcommit_ratio` of 30 it would
899	              yield a CommitLimit of 7.3G.
900	              For more details, see the memory overcommit documentation
901	              in vm/overcommit-accounting.
902	Committed_AS: The amount of memory presently allocated on the system.
903	              The committed memory is a sum of all of the memory which
904	              has been allocated by processes, even if it has not been
905	              "used" by them as of yet. A process which malloc()'s 1G
906	              of memory, but only touches 300M of it will show up as
907		      using 1G. This 1G is memory which has been "committed" to
908	              by the VM and can be used at any time by the allocating
909	              application. With strict overcommit enabled on the system
910	              (mode 2 in 'vm.overcommit_memory'),allocations which would
911	              exceed the CommitLimit (detailed above) will not be permitted.
912	              This is useful if one needs to guarantee that processes will
913	              not fail due to lack of memory once that memory has been
914	              successfully allocated.
915	VmallocTotal: total size of vmalloc memory area
916	 VmallocUsed: amount of vmalloc area which is used
917	VmallocChunk: largest contiguous block of vmalloc area which is free
918	
919	..............................................................................
920	
921	vmallocinfo:
922	
923	Provides information about vmalloced/vmaped areas. One line per area,
924	containing the virtual address range of the area, size in bytes,
925	caller information of the creator, and optional information depending
926	on the kind of area :
927	
928	 pages=nr    number of pages
929	 phys=addr   if a physical address was specified
930	 ioremap     I/O mapping (ioremap() and friends)
931	 vmalloc     vmalloc() area
932	 vmap        vmap()ed pages
933	 user        VM_USERMAP area
934	 vpages      buffer for pages pointers was vmalloced (huge area)
935	 N<node>=nr  (Only on NUMA kernels)
936	             Number of pages allocated on memory node <node>
937	
938	> cat /proc/vmallocinfo
939	0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ...
940	  /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128
941	0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ...
942	  /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64
943	0xffffc20000302000-0xffffc20000304000    8192 acpi_tb_verify_table+0x21/0x4f...
944	  phys=7fee8000 ioremap
945	0xffffc20000304000-0xffffc20000307000   12288 acpi_tb_verify_table+0x21/0x4f...
946	  phys=7fee7000 ioremap
947	0xffffc2000031d000-0xffffc2000031f000    8192 init_vdso_vars+0x112/0x210
948	0xffffc2000031f000-0xffffc2000032b000   49152 cramfs_uncompress_init+0x2e ...
949	  /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3
950	0xffffc2000033a000-0xffffc2000033d000   12288 sys_swapon+0x640/0xac0      ...
951	  pages=2 vmalloc N1=2
952	0xffffc20000347000-0xffffc2000034c000   20480 xt_alloc_table_info+0xfe ...
953	  /0x130 [x_tables] pages=4 vmalloc N0=4
954	0xffffffffa0000000-0xffffffffa000f000   61440 sys_init_module+0xc27/0x1d00 ...
955	   pages=14 vmalloc N2=14
956	0xffffffffa000f000-0xffffffffa0014000   20480 sys_init_module+0xc27/0x1d00 ...
957	   pages=4 vmalloc N1=4
958	0xffffffffa0014000-0xffffffffa0017000   12288 sys_init_module+0xc27/0x1d00 ...
959	   pages=2 vmalloc N1=2
960	0xffffffffa0017000-0xffffffffa0022000   45056 sys_init_module+0xc27/0x1d00 ...
961	   pages=10 vmalloc N0=10
962	
963	..............................................................................
964	
965	softirqs:
966	
967	Provides counts of softirq handlers serviced since boot time, for each cpu.
968	
969	> cat /proc/softirqs
970	                CPU0       CPU1       CPU2       CPU3
971	      HI:          0          0          0          0
972	   TIMER:      27166      27120      27097      27034
973	  NET_TX:          0          0          0         17
974	  NET_RX:         42          0          0         39
975	   BLOCK:          0          0        107       1121
976	 TASKLET:          0          0          0        290
977	   SCHED:      27035      26983      26971      26746
978	 HRTIMER:          0          0          0          0
979	     RCU:       1678       1769       2178       2250
980	
981	
982	1.3 IDE devices in /proc/ide
983	----------------------------
984	
985	The subdirectory /proc/ide contains information about all IDE devices of which
986	the kernel  is  aware.  There is one subdirectory for each IDE controller, the
987	file drivers  and a link for each IDE device, pointing to the device directory
988	in the controller specific subtree.
989	
990	The file  drivers  contains general information about the drivers used for the
991	IDE devices:
992	
993	  > cat /proc/ide/drivers
994	  ide-cdrom version 4.53
995	  ide-disk version 1.08
996	
997	More detailed  information  can  be  found  in  the  controller  specific
998	subdirectories. These  are  named  ide0,  ide1  and  so  on.  Each  of  these
999	directories contains the files shown in table 1-6.
1000	
1001	
1002	Table 1-6: IDE controller info in  /proc/ide/ide?
1003	..............................................................................
1004	 File    Content                                 
1005	 channel IDE channel (0 or 1)                    
1006	 config  Configuration (only for PCI/IDE bridge) 
1007	 mate    Mate name                               
1008	 model   Type/Chipset of IDE controller          
1009	..............................................................................
1010	
1011	Each device  connected  to  a  controller  has  a separate subdirectory in the
1012	controllers directory.  The  files  listed in table 1-7 are contained in these
1013	directories.
1014	
1015	
1016	Table 1-7: IDE device information
1017	..............................................................................
1018	 File             Content                                    
1019	 cache            The cache                                  
1020	 capacity         Capacity of the medium (in 512Byte blocks) 
1021	 driver           driver and version                         
1022	 geometry         physical and logical geometry              
1023	 identify         device identify block                      
1024	 media            media type                                 
1025	 model            device identifier                          
1026	 settings         device setup                               
1027	 smart_thresholds IDE disk management thresholds             
1028	 smart_values     IDE disk management values                 
1029	..............................................................................
1030	
1031	The most  interesting  file is settings. This file contains a nice overview of
1032	the drive parameters:
1033	
1034	  # cat /proc/ide/ide0/hda/settings 
1035	  name                    value           min             max             mode 
1036	  ----                    -----           ---             ---             ---- 
1037	  bios_cyl                526             0               65535           rw 
1038	  bios_head               255             0               255             rw 
1039	  bios_sect               63              0               63              rw 
1040	  breada_readahead        4               0               127             rw 
1041	  bswap                   0               0               1               r 
1042	  file_readahead          72              0               2097151         rw 
1043	  io_32bit                0               0               3               rw 
1044	  keepsettings            0               0               1               rw 
1045	  max_kb_per_request      122             1               127             rw 
1046	  multcount               0               0               8               rw 
1047	  nice1                   1               0               1               rw 
1048	  nowerr                  0               0               1               rw 
1049	  pio_mode                write-only      0               255             w 
1050	  slow                    0               0               1               rw 
1051	  unmaskirq               0               0               1               rw 
1052	  using_dma               0               0               1               rw 
1053	
1054	
1055	1.4 Networking info in /proc/net
1056	--------------------------------
1057	
1058	The subdirectory  /proc/net  follows  the  usual  pattern. Table 1-8 shows the
1059	additional values  you  get  for  IP  version 6 if you configure the kernel to
1060	support this. Table 1-9 lists the files and their meaning.
1061	
1062	
1063	Table 1-8: IPv6 info in /proc/net
1064	..............................................................................
1065	 File       Content                                               
1066	 udp6       UDP sockets (IPv6)                                    
1067	 tcp6       TCP sockets (IPv6)                                    
1068	 raw6       Raw device statistics (IPv6)                          
1069	 igmp6      IP multicast addresses, which this host joined (IPv6) 
1070	 if_inet6   List of IPv6 interface addresses                      
1071	 ipv6_route Kernel routing table for IPv6                         
1072	 rt6_stats  Global IPv6 routing tables statistics                 
1073	 sockstat6  Socket statistics (IPv6)                              
1074	 snmp6      Snmp data (IPv6)                                      
1075	..............................................................................
1076	
1077	
1078	Table 1-9: Network info in /proc/net
1079	..............................................................................
1080	 File          Content                                                         
1081	 arp           Kernel  ARP table                                               
1082	 dev           network devices with statistics                                 
1083	 dev_mcast     the Layer2 multicast groups a device is listening too
1084	               (interface index, label, number of references, number of bound
1085	               addresses). 
1086	 dev_stat      network device status                                           
1087	 ip_fwchains   Firewall chain linkage                                          
1088	 ip_fwnames    Firewall chain names                                            
1089	 ip_masq       Directory containing the masquerading tables                    
1090	 ip_masquerade Major masquerading table                                        
1091	 netstat       Network statistics                                              
1092	 raw           raw device statistics                                           
1093	 route         Kernel routing table                                            
1094	 rpc           Directory containing rpc info                                   
1095	 rt_cache      Routing cache                                                   
1096	 snmp          SNMP data                                                       
1097	 sockstat      Socket statistics                                               
1098	 tcp           TCP  sockets                                                    
1099	 udp           UDP sockets                                                     
1100	 unix          UNIX domain sockets                                             
1101	 wireless      Wireless interface data (Wavelan etc)                           
1102	 igmp          IP multicast addresses, which this host joined                  
1103	 psched        Global packet scheduler parameters.                             
1104	 netlink       List of PF_NETLINK sockets                                      
1105	 ip_mr_vifs    List of multicast virtual interfaces                            
1106	 ip_mr_cache   List of multicast routing cache                                 
1107	..............................................................................
1108	
1109	You can  use  this  information  to see which network devices are available in
1110	your system and how much traffic was routed over those devices:
1111	
1112	  > cat /proc/net/dev 
1113	  Inter-|Receive                                                   |[... 
1114	   face |bytes    packets errs drop fifo frame compressed multicast|[... 
1115	      lo:  908188   5596     0    0    0     0          0         0 [...         
1116	    ppp0:15475140  20721   410    0    0   410          0         0 [...  
1117	    eth0:  614530   7085     0    0    0     0          0         1 [... 
1118	   
1119	  ...] Transmit 
1120	  ...] bytes    packets errs drop fifo colls carrier compressed 
1121	  ...]  908188     5596    0    0    0     0       0          0 
1122	  ...] 1375103    17405    0    0    0     0       0          0 
1123	  ...] 1703981     5535    0    0    0     3       0          0 
1124	
1125	In addition, each Channel Bond interface has its own directory.  For
1126	example, the bond0 device will have a directory called /proc/net/bond0/.
1127	It will contain information that is specific to that bond, such as the
1128	current slaves of the bond, the link status of the slaves, and how
1129	many times the slaves link has failed.
1130	
1131	1.5 SCSI info
1132	-------------
1133	
1134	If you  have  a  SCSI  host adapter in your system, you'll find a subdirectory
1135	named after  the driver for this adapter in /proc/scsi. You'll also see a list
1136	of all recognized SCSI devices in /proc/scsi:
1137	
1138	  >cat /proc/scsi/scsi 
1139	  Attached devices: 
1140	  Host: scsi0 Channel: 00 Id: 00 Lun: 00 
1141	    Vendor: IBM      Model: DGHS09U          Rev: 03E0 
1142	    Type:   Direct-Access                    ANSI SCSI revision: 03 
1143	  Host: scsi0 Channel: 00 Id: 06 Lun: 00 
1144	    Vendor: PIONEER  Model: CD-ROM DR-U06S   Rev: 1.04 
1145	    Type:   CD-ROM                           ANSI SCSI revision: 02 
1146	
1147	
1148	The directory  named  after  the driver has one file for each adapter found in
1149	the system.  These  files  contain information about the controller, including
1150	the used  IRQ  and  the  IO  address range. The amount of information shown is
1151	dependent on  the adapter you use. The example shows the output for an Adaptec
1152	AHA-2940 SCSI adapter:
1153	
1154	  > cat /proc/scsi/aic7xxx/0 
1155	   
1156	  Adaptec AIC7xxx driver version: 5.1.19/3.2.4 
1157	  Compile Options: 
1158	    TCQ Enabled By Default : Disabled 
1159	    AIC7XXX_PROC_STATS     : Disabled 
1160	    AIC7XXX_RESET_DELAY    : 5 
1161	  Adapter Configuration: 
1162	             SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter 
1163	                             Ultra Wide Controller 
1164	      PCI MMAPed I/O Base: 0xeb001000 
1165	   Adapter SEEPROM Config: SEEPROM found and used. 
1166	        Adaptec SCSI BIOS: Enabled 
1167	                      IRQ: 10 
1168	                     SCBs: Active 0, Max Active 2, 
1169	                           Allocated 15, HW 16, Page 255 
1170	               Interrupts: 160328 
1171	        BIOS Control Word: 0x18b6 
1172	     Adapter Control Word: 0x005b 
1173	     Extended Translation: Enabled 
1174	  Disconnect Enable Flags: 0xffff 
1175	       Ultra Enable Flags: 0x0001 
1176	   Tag Queue Enable Flags: 0x0000 
1177	  Ordered Queue Tag Flags: 0x0000 
1178	  Default Tag Queue Depth: 8 
1179	      Tagged Queue By Device array for aic7xxx host instance 0: 
1180	        {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255} 
1181	      Actual queue depth per device for aic7xxx host instance 0: 
1182	        {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1} 
1183	  Statistics: 
1184	  (scsi0:0:0:0) 
1185	    Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8 
1186	    Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0) 
1187	    Total transfers 160151 (74577 reads and 85574 writes) 
1188	  (scsi0:0:6:0) 
1189	    Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15 
1190	    Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0) 
1191	    Total transfers 0 (0 reads and 0 writes) 
1192	
1193	
1194	1.6 Parallel port info in /proc/parport
1195	---------------------------------------
1196	
1197	The directory  /proc/parport  contains information about the parallel ports of
1198	your system.  It  has  one  subdirectory  for  each port, named after the port
1199	number (0,1,2,...).
1200	
1201	These directories contain the four files shown in Table 1-10.
1202	
1203	
1204	Table 1-10: Files in /proc/parport
1205	..............................................................................
1206	 File      Content                                                             
1207	 autoprobe Any IEEE-1284 device ID information that has been acquired.         
1208	 devices   list of the device drivers using that port. A + will appear by the
1209	           name of the device currently using the port (it might not appear
1210	           against any). 
1211	 hardware  Parallel port's base address, IRQ line and DMA channel.             
1212	 irq       IRQ that parport is using for that port. This is in a separate
1213	           file to allow you to alter it by writing a new value in (IRQ
1214	           number or none). 
1215	..............................................................................
1216	
1217	1.7 TTY info in /proc/tty
1218	-------------------------
1219	
1220	Information about  the  available  and actually used tty's can be found in the
1221	directory /proc/tty.You'll  find  entries  for drivers and line disciplines in
1222	this directory, as shown in Table 1-11.
1223	
1224	
1225	Table 1-11: Files in /proc/tty
1226	..............................................................................
1227	 File          Content                                        
1228	 drivers       list of drivers and their usage                
1229	 ldiscs        registered line disciplines                    
1230	 driver/serial usage statistic and status of single tty lines 
1231	..............................................................................
1232	
1233	To see  which  tty's  are  currently in use, you can simply look into the file
1234	/proc/tty/drivers:
1235	
1236	  > cat /proc/tty/drivers 
1237	  pty_slave            /dev/pts      136   0-255 pty:slave 
1238	  pty_master           /dev/ptm      128   0-255 pty:master 
1239	  pty_slave            /dev/ttyp       3   0-255 pty:slave 
1240	  pty_master           /dev/pty        2   0-255 pty:master 
1241	  serial               /dev/cua        5   64-67 serial:callout 
1242	  serial               /dev/ttyS       4   64-67 serial 
1243	  /dev/tty0            /dev/tty0       4       0 system:vtmaster 
1244	  /dev/ptmx            /dev/ptmx       5       2 system 
1245	  /dev/console         /dev/console    5       1 system:console 
1246	  /dev/tty             /dev/tty        5       0 system:/dev/tty 
1247	  unknown              /dev/tty        4    1-63 console 
1248	
1249	
1250	1.8 Miscellaneous kernel statistics in /proc/stat
1251	-------------------------------------------------
1252	
1253	Various pieces   of  information about  kernel activity  are  available in the
1254	/proc/stat file.  All  of  the numbers reported  in  this file are  aggregates
1255	since the system first booted.  For a quick look, simply cat the file:
1256	
1257	  > cat /proc/stat
1258	  cpu  2255 34 2290 22625563 6290 127 456 0 0
1259	  cpu0 1132 34 1441 11311718 3675 127 438 0 0
1260	  cpu1 1123 0 849 11313845 2614 0 18 0 0
1261	  intr 114930548 113199788 3 0 5 263 0 4 [... lots more numbers ...]
1262	  ctxt 1990473
1263	  btime 1062191376
1264	  processes 2915
1265	  procs_running 1
1266	  procs_blocked 0
1267	  softirq 183433 0 21755 12 39 1137 231 21459 2263
1268	
1269	The very first  "cpu" line aggregates the  numbers in all  of the other "cpuN"
1270	lines.  These numbers identify the amount of time the CPU has spent performing
1271	different kinds of work.  Time units are in USER_HZ (typically hundredths of a
1272	second).  The meanings of the columns are as follows, from left to right:
1273	
1274	- user: normal processes executing in user mode
1275	- nice: niced processes executing in user mode
1276	- system: processes executing in kernel mode
1277	- idle: twiddling thumbs
1278	- iowait: waiting for I/O to complete
1279	- irq: servicing interrupts
1280	- softirq: servicing softirqs
1281	- steal: involuntary wait
1282	- guest: running a normal guest
1283	- guest_nice: running a niced guest
1284	
1285	The "intr" line gives counts of interrupts  serviced since boot time, for each
1286	of the  possible system interrupts.   The first  column  is the  total of  all
1287	interrupts serviced  including  unnumbered  architecture specific  interrupts;
1288	each  subsequent column is the  total for that particular numbered interrupt.
1289	Unnumbered interrupts are not shown, only summed into the total.
1290	
1291	The "ctxt" line gives the total number of context switches across all CPUs.
1292	
1293	The "btime" line gives  the time at which the  system booted, in seconds since
1294	the Unix epoch.
1295	
1296	The "processes" line gives the number  of processes and threads created, which
1297	includes (but  is not limited  to) those  created by  calls to the  fork() and
1298	clone() system calls.
1299	
1300	The "procs_running" line gives the total number of threads that are
1301	running or ready to run (i.e., the total number of runnable threads).
1302	
1303	The   "procs_blocked" line gives  the  number of  processes currently blocked,
1304	waiting for I/O to complete.
1305	
1306	The "softirq" line gives counts of softirqs serviced since boot time, for each
1307	of the possible system softirqs. The first column is the total of all
1308	softirqs serviced; each subsequent column is the total for that particular
1309	softirq.
1310	
1311	
1312	1.9 Ext4 file system parameters
1313	-------------------------------
1314	
1315	Information about mounted ext4 file systems can be found in
1316	/proc/fs/ext4.  Each mounted filesystem will have a directory in
1317	/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or
1318	/proc/fs/ext4/dm-0).   The files in each per-device directory are shown
1319	in Table 1-12, below.
1320	
1321	Table 1-12: Files in /proc/fs/ext4/<devname>
1322	..............................................................................
1323	 File            Content                                        
1324	 mb_groups       details of multiblock allocator buddy cache of free blocks
1325	..............................................................................
1326	
1327	2.0 /proc/consoles
1328	------------------
1329	Shows registered system console lines.
1330	
1331	To see which character device lines are currently used for the system console
1332	/dev/console, you may simply look into the file /proc/consoles:
1333	
1334	  > cat /proc/consoles
1335	  tty0                 -WU (ECp)       4:7
1336	  ttyS0                -W- (Ep)        4:64
1337	
1338	The columns are:
1339	
1340	  device               name of the device
1341	  operations           R = can do read operations
1342	                       W = can do write operations
1343	                       U = can do unblank
1344	  flags                E = it is enabled
1345	                       C = it is preferred console
1346	                       B = it is primary boot console
1347	                       p = it is used for printk buffer
1348	                       b = it is not a TTY but a Braille device
1349	                       a = it is safe to use when cpu is offline
1350	  major:minor          major and minor number of the device separated by a colon
1351	
1352	------------------------------------------------------------------------------
1353	Summary
1354	------------------------------------------------------------------------------
1355	The /proc file system serves information about the running system. It not only
1356	allows access to process data but also allows you to request the kernel status
1357	by reading files in the hierarchy.
1358	
1359	The directory  structure  of /proc reflects the types of information and makes
1360	it easy, if not obvious, where to look for specific data.
1361	------------------------------------------------------------------------------
1362	
1363	------------------------------------------------------------------------------
1364	CHAPTER 2: MODIFYING SYSTEM PARAMETERS
1365	------------------------------------------------------------------------------
1366	
1367	------------------------------------------------------------------------------
1368	In This Chapter
1369	------------------------------------------------------------------------------
1370	* Modifying kernel parameters by writing into files found in /proc/sys
1371	* Exploring the files which modify certain parameters
1372	* Review of the /proc/sys file tree
1373	------------------------------------------------------------------------------
1374	
1375	
1376	A very  interesting part of /proc is the directory /proc/sys. This is not only
1377	a source  of  information,  it also allows you to change parameters within the
1378	kernel. Be  very  careful  when attempting this. You can optimize your system,
1379	but you  can  also  cause  it  to  crash.  Never  alter kernel parameters on a
1380	production system.  Set  up  a  development machine and test to make sure that
1381	everything works  the  way  you want it to. You may have no alternative but to
1382	reboot the machine once an error has been made.
1383	
1384	To change  a  value,  simply  echo  the new value into the file. An example is
1385	given below  in the section on the file system data. You need to be root to do
1386	this. You  can  create  your  own  boot script to perform this every time your
1387	system boots.
1388	
1389	The files  in /proc/sys can be used to fine tune and monitor miscellaneous and
1390	general things  in  the operation of the Linux kernel. Since some of the files
1391	can inadvertently  disrupt  your  system,  it  is  advisable  to  read  both
1392	documentation and  source  before actually making adjustments. In any case, be
1393	very careful  when  writing  to  any  of these files. The entries in /proc may
1394	change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt
1395	review the kernel documentation in the directory /usr/src/linux/Documentation.
1396	This chapter  is  heavily  based  on the documentation included in the pre 2.2
1397	kernels, and became part of it in version 2.2.1 of the Linux kernel.
1398	
1399	Please see: Documentation/sysctl/ directory for descriptions of these
1400	entries.
1401	
1402	------------------------------------------------------------------------------
1403	Summary
1404	------------------------------------------------------------------------------
1405	Certain aspects  of  kernel  behavior  can be modified at runtime, without the
1406	need to  recompile  the kernel, or even to reboot the system. The files in the
1407	/proc/sys tree  can  not only be read, but also modified. You can use the echo
1408	command to write value into these files, thereby changing the default settings
1409	of the kernel.
1410	------------------------------------------------------------------------------
1411	
1412	------------------------------------------------------------------------------
1413	CHAPTER 3: PER-PROCESS PARAMETERS
1414	------------------------------------------------------------------------------
1415	
1416	3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score
1417	--------------------------------------------------------------------------------
1418	
1419	These file can be used to adjust the badness heuristic used to select which
1420	process gets killed in out of memory conditions.
1421	
1422	The badness heuristic assigns a value to each candidate task ranging from 0
1423	(never kill) to 1000 (always kill) to determine which process is targeted.  The
1424	units are roughly a proportion along that range of allowed memory the process
1425	may allocate from based on an estimation of its current memory and swap use.
1426	For example, if a task is using all allowed memory, its badness score will be
1427	1000.  If it is using half of its allowed memory, its score will be 500.
1428	
1429	There is an additional factor included in the badness score: the current memory
1430	and swap usage is discounted by 3% for root processes.
1431	
1432	The amount of "allowed" memory depends on the context in which the oom killer
1433	was called.  If it is due to the memory assigned to the allocating task's cpuset
1434	being exhausted, the allowed memory represents the set of mems assigned to that
1435	cpuset.  If it is due to a mempolicy's node(s) being exhausted, the allowed
1436	memory represents the set of mempolicy nodes.  If it is due to a memory
1437	limit (or swap limit) being reached, the allowed memory is that configured
1438	limit.  Finally, if it is due to the entire system being out of memory, the
1439	allowed memory represents all allocatable resources.
1440	
1441	The value of /proc/<pid>/oom_score_adj is added to the badness score before it
1442	is used to determine which task to kill.  Acceptable values range from -1000
1443	(OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX).  This allows userspace to
1444	polarize the preference for oom killing either by always preferring a certain
1445	task or completely disabling it.  The lowest possible value, -1000, is
1446	equivalent to disabling oom killing entirely for that task since it will always
1447	report a badness score of 0.
1448	
1449	Consequently, it is very simple for userspace to define the amount of memory to
1450	consider for each task.  Setting a /proc/<pid>/oom_score_adj value of +500, for
1451	example, is roughly equivalent to allowing the remainder of tasks sharing the
1452	same system, cpuset, mempolicy, or memory controller resources to use at least
1453	50% more memory.  A value of -500, on the other hand, would be roughly
1454	equivalent to discounting 50% of the task's allowed memory from being considered
1455	as scoring against the task.
1456	
1457	For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also
1458	be used to tune the badness score.  Its acceptable values range from -16
1459	(OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17
1460	(OOM_DISABLE) to disable oom killing entirely for that task.  Its value is
1461	scaled linearly with /proc/<pid>/oom_score_adj.
1462	
1463	The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last
1464	value set by a CAP_SYS_RESOURCE process. To reduce the value any lower
1465	requires CAP_SYS_RESOURCE.
1466	
1467	Caveat: when a parent task is selected, the oom killer will sacrifice any first
1468	generation children with separate address spaces instead, if possible.  This
1469	avoids servers and important system daemons from being killed and loses the
1470	minimal amount of work.
1471	
1472	
1473	3.2 /proc/<pid>/oom_score - Display current oom-killer score
1474	-------------------------------------------------------------
1475	
1476	This file can be used to check the current score used by the oom-killer is for
1477	any given <pid>. Use it together with /proc/<pid>/oom_score_adj to tune which
1478	process should be killed in an out-of-memory situation.
1479	
1480	
1481	3.3  /proc/<pid>/io - Display the IO accounting fields
1482	-------------------------------------------------------
1483	
1484	This file contains IO statistics for each running process
1485	
1486	Example
1487	-------
1488	
1489	test:/tmp # dd if=/dev/zero of=/tmp/test.dat &
1490	[1] 3828
1491	
1492	test:/tmp # cat /proc/3828/io
1493	rchar: 323934931
1494	wchar: 323929600
1495	syscr: 632687
1496	syscw: 632675
1497	read_bytes: 0
1498	write_bytes: 323932160
1499	cancelled_write_bytes: 0
1500	
1501	
1502	Description
1503	-----------
1504	
1505	rchar
1506	-----
1507	
1508	I/O counter: chars read
1509	The number of bytes which this task has caused to be read from storage. This
1510	is simply the sum of bytes which this process passed to read() and pread().
1511	It includes things like tty IO and it is unaffected by whether or not actual
1512	physical disk IO was required (the read might have been satisfied from
1513	pagecache)
1514	
1515	
1516	wchar
1517	-----
1518	
1519	I/O counter: chars written
1520	The number of bytes which this task has caused, or shall cause to be written
1521	to disk. Similar caveats apply here as with rchar.
1522	
1523	
1524	syscr
1525	-----
1526	
1527	I/O counter: read syscalls
1528	Attempt to count the number of read I/O operations, i.e. syscalls like read()
1529	and pread().
1530	
1531	
1532	syscw
1533	-----
1534	
1535	I/O counter: write syscalls
1536	Attempt to count the number of write I/O operations, i.e. syscalls like
1537	write() and pwrite().
1538	
1539	
1540	read_bytes
1541	----------
1542	
1543	I/O counter: bytes read
1544	Attempt to count the number of bytes which this process really did cause to
1545	be fetched from the storage layer. Done at the submit_bio() level, so it is
1546	accurate for block-backed filesystems. <please add status regarding NFS and
1547	CIFS at a later time>
1548	
1549	
1550	write_bytes
1551	-----------
1552	
1553	I/O counter: bytes written
1554	Attempt to count the number of bytes which this process caused to be sent to
1555	the storage layer. This is done at page-dirtying time.
1556	
1557	
1558	cancelled_write_bytes
1559	---------------------
1560	
1561	The big inaccuracy here is truncate. If a process writes 1MB to a file and
1562	then deletes the file, it will in fact perform no writeout. But it will have
1563	been accounted as having caused 1MB of write.
1564	In other words: The number of bytes which this process caused to not happen,
1565	by truncating pagecache. A task can cause "negative" IO too. If this task
1566	truncates some dirty pagecache, some IO which another task has been accounted
1567	for (in its write_bytes) will not be happening. We _could_ just subtract that
1568	from the truncating task's write_bytes, but there is information loss in doing
1569	that.
1570	
1571	
1572	Note
1573	----
1574	
1575	At its current implementation state, this is a bit racy on 32-bit machines: if
1576	process A reads process B's /proc/pid/io while process B is updating one of
1577	those 64-bit counters, process A could see an intermediate result.
1578	
1579	
1580	More information about this can be found within the taskstats documentation in
1581	Documentation/accounting.
1582	
1583	3.4 /proc/<pid>/coredump_filter - Core dump filtering settings
1584	---------------------------------------------------------------
1585	When a process is dumped, all anonymous memory is written to a core file as
1586	long as the size of the core file isn't limited. But sometimes we don't want
1587	to dump some memory segments, for example, huge shared memory. Conversely,
1588	sometimes we want to save file-backed memory segments into a core file, not
1589	only the individual files.
1590	
1591	/proc/<pid>/coredump_filter allows you to customize which memory segments
1592	will be dumped when the <pid> process is dumped. coredump_filter is a bitmask
1593	of memory types. If a bit of the bitmask is set, memory segments of the
1594	corresponding memory type are dumped, otherwise they are not dumped.
1595	
1596	The following 7 memory types are supported:
1597	  - (bit 0) anonymous private memory
1598	  - (bit 1) anonymous shared memory
1599	  - (bit 2) file-backed private memory
1600	  - (bit 3) file-backed shared memory
1601	  - (bit 4) ELF header pages in file-backed private memory areas (it is
1602	            effective only if the bit 2 is cleared)
1603	  - (bit 5) hugetlb private memory
1604	  - (bit 6) hugetlb shared memory
1605	
1606	  Note that MMIO pages such as frame buffer are never dumped and vDSO pages
1607	  are always dumped regardless of the bitmask status.
1608	
1609	  Note bit 0-4 doesn't effect any hugetlb memory. hugetlb memory are only
1610	  effected by bit 5-6.
1611	
1612	Default value of coredump_filter is 0x23; this means all anonymous memory
1613	segments and hugetlb private memory are dumped.
1614	
1615	If you don't want to dump all shared memory segments attached to pid 1234,
1616	write 0x21 to the process's proc file.
1617	
1618	  $ echo 0x21 > /proc/1234/coredump_filter
1619	
1620	When a new process is created, the process inherits the bitmask status from its
1621	parent. It is useful to set up coredump_filter before the program runs.
1622	For example:
1623	
1624	  $ echo 0x7 > /proc/self/coredump_filter
1625	  $ ./some_program
1626	
1627	3.5	/proc/<pid>/mountinfo - Information about mounts
1628	--------------------------------------------------------
1629	
1630	This file contains lines of the form:
1631	
1632	36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue
1633	(1)(2)(3)   (4)   (5)      (6)      (7)   (8) (9)   (10)         (11)
1634	
1635	(1) mount ID:  unique identifier of the mount (may be reused after umount)
1636	(2) parent ID:  ID of parent (or of self for the top of the mount tree)
1637	(3) major:minor:  value of st_dev for files on filesystem
1638	(4) root:  root of the mount within the filesystem
1639	(5) mount point:  mount point relative to the process's root
1640	(6) mount options:  per mount options
1641	(7) optional fields:  zero or more fields of the form "tag[:value]"
1642	(8) separator:  marks the end of the optional fields
1643	(9) filesystem type:  name of filesystem of the form "type[.subtype]"
1644	(10) mount source:  filesystem specific information or "none"
1645	(11) super options:  per super block options
1646	
1647	Parsers should ignore all unrecognised optional fields.  Currently the
1648	possible optional fields are:
1649	
1650	shared:X  mount is shared in peer group X
1651	master:X  mount is slave to peer group X
1652	propagate_from:X  mount is slave and receives propagation from peer group X (*)
1653	unbindable  mount is unbindable
1654	
1655	(*) X is the closest dominant peer group under the process's root.  If
1656	X is the immediate master of the mount, or if there's no dominant peer
1657	group under the same root, then only the "master:X" field is present
1658	and not the "propagate_from:X" field.
1659	
1660	For more information on mount propagation see:
1661	
1662	  Documentation/filesystems/sharedsubtree.txt
1663	
1664	
1665	3.6	/proc/<pid>/comm  & /proc/<pid>/task/<tid>/comm
1666	--------------------------------------------------------
1667	These files provide a method to access a tasks comm value. It also allows for
1668	a task to set its own or one of its thread siblings comm value. The comm value
1669	is limited in size compared to the cmdline value, so writing anything longer
1670	then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated
1671	comm value.
1672	
1673	
1674	3.7	/proc/<pid>/task/<tid>/children - Information about task children
1675	-------------------------------------------------------------------------
1676	This file provides a fast way to retrieve first level children pids
1677	of a task pointed by <pid>/<tid> pair. The format is a space separated
1678	stream of pids.
1679	
1680	Note the "first level" here -- if a child has own children they will
1681	not be listed here, one needs to read /proc/<children-pid>/task/<tid>/children
1682	to obtain the descendants.
1683	
1684	Since this interface is intended to be fast and cheap it doesn't
1685	guarantee to provide precise results and some children might be
1686	skipped, especially if they've exited right after we printed their
1687	pids, so one need to either stop or freeze processes being inspected
1688	if precise results are needed.
1689	
1690	
1691	3.8	/proc/<pid>/fdinfo/<fd> - Information about opened file
1692	---------------------------------------------------------------
1693	This file provides information associated with an opened file. The regular
1694	files have at least three fields -- 'pos', 'flags' and mnt_id. The 'pos'
1695	represents the current offset of the opened file in decimal form [see lseek(2)
1696	for details], 'flags' denotes the octal O_xxx mask the file has been
1697	created with [see open(2) for details] and 'mnt_id' represents mount ID of
1698	the file system containing the opened file [see 3.5 /proc/<pid>/mountinfo
1699	for details].
1700	
1701	A typical output is
1702	
1703		pos:	0
1704		flags:	0100002
1705		mnt_id:	19
1706	
1707	The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags
1708	pair provide additional information particular to the objects they represent.
1709	
1710		Eventfd files
1711		~~~~~~~~~~~~~
1712		pos:	0
1713		flags:	04002
1714		mnt_id:	9
1715		eventfd-count:	5a
1716	
1717		where 'eventfd-count' is hex value of a counter.
1718	
1719		Signalfd files
1720		~~~~~~~~~~~~~~
1721		pos:	0
1722		flags:	04002
1723		mnt_id:	9
1724		sigmask:	0000000000000200
1725	
1726		where 'sigmask' is hex value of the signal mask associated
1727		with a file.
1728	
1729		Epoll files
1730		~~~~~~~~~~~
1731		pos:	0
1732		flags:	02
1733		mnt_id:	9
1734		tfd:        5 events:       1d data: ffffffffffffffff
1735	
1736		where 'tfd' is a target file descriptor number in decimal form,
1737		'events' is events mask being watched and the 'data' is data
1738		associated with a target [see epoll(7) for more details].
1739	
1740		Fsnotify files
1741		~~~~~~~~~~~~~~
1742		For inotify files the format is the following
1743	
1744		pos:	0
1745		flags:	02000000
1746		inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d
1747	
1748		where 'wd' is a watch descriptor in decimal form, ie a target file
1749		descriptor number, 'ino' and 'sdev' are inode and device where the
1750		target file resides and the 'mask' is the mask of events, all in hex
1751		form [see inotify(7) for more details].
1752	
1753		If the kernel was built with exportfs support, the path to the target
1754		file is encoded as a file handle.  The file handle is provided by three
1755		fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex
1756		format.
1757	
1758		If the kernel is built without exportfs support the file handle won't be
1759		printed out.
1760	
1761		If there is no inotify mark attached yet the 'inotify' line will be omitted.
1762	
1763		For fanotify files the format is
1764	
1765		pos:	0
1766		flags:	02
1767		mnt_id:	9
1768		fanotify flags:10 event-flags:0
1769		fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003
1770		fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4
1771	
1772		where fanotify 'flags' and 'event-flags' are values used in fanotify_init
1773		call, 'mnt_id' is the mount point identifier, 'mflags' is the value of
1774		flags associated with mark which are tracked separately from events
1775		mask. 'ino', 'sdev' are target inode and device, 'mask' is the events
1776		mask and 'ignored_mask' is the mask of events which are to be ignored.
1777		All in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask'
1778		does provide information about flags and mask used in fanotify_mark
1779		call [see fsnotify manpage for details].
1780	
1781		While the first three lines are mandatory and always printed, the rest is
1782		optional and may be omitted if no marks created yet.
1783	
1784		Timerfd files
1785		~~~~~~~~~~~~~
1786	
1787		pos:	0
1788		flags:	02
1789		mnt_id:	9
1790		clockid: 0
1791		ticks: 0
1792		settime flags: 01
1793		it_value: (0, 49406829)
1794		it_interval: (1, 0)
1795	
1796		where 'clockid' is the clock type and 'ticks' is the number of the timer expirations
1797		that have occurred [see timerfd_create(2) for details]. 'settime flags' are
1798		flags in octal form been used to setup the timer [see timerfd_settime(2) for
1799		details]. 'it_value' is remaining time until the timer exiration.
1800		'it_interval' is the interval for the timer. Note the timer might be set up
1801		with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value'
1802		still exhibits timer's remaining time.
1803	
1804	3.9	/proc/<pid>/map_files - Information about memory mapped files
1805	---------------------------------------------------------------------
1806	This directory contains symbolic links which represent memory mapped files
1807	the process is maintaining.  Example output:
1808	
1809	     | lr-------- 1 root root 64 Jan 27 11:24 333c600000-333c620000 -> /usr/lib64/ld-2.18.so
1810	     | lr-------- 1 root root 64 Jan 27 11:24 333c81f000-333c820000 -> /usr/lib64/ld-2.18.so
1811	     | lr-------- 1 root root 64 Jan 27 11:24 333c820000-333c821000 -> /usr/lib64/ld-2.18.so
1812	     | ...
1813	     | lr-------- 1 root root 64 Jan 27 11:24 35d0421000-35d0422000 -> /usr/lib64/libselinux.so.1
1814	     | lr-------- 1 root root 64 Jan 27 11:24 400000-41a000 -> /usr/bin/ls
1815	
1816	The name of a link represents the virtual memory bounds of a mapping, i.e.
1817	vm_area_struct::vm_start-vm_area_struct::vm_end.
1818	
1819	The main purpose of the map_files is to retrieve a set of memory mapped
1820	files in a fast way instead of parsing /proc/<pid>/maps or
1821	/proc/<pid>/smaps, both of which contain many more records.  At the same
1822	time one can open(2) mappings from the listings of two processes and
1823	comparing their inode numbers to figure out which anonymous memory areas
1824	are actually shared.
1825	
1826	------------------------------------------------------------------------------
1827	Configuring procfs
1828	------------------------------------------------------------------------------
1829	
1830	4.1	Mount options
1831	---------------------
1832	
1833	The following mount options are supported:
1834	
1835		hidepid=	Set /proc/<pid>/ access mode.
1836		gid=		Set the group authorized to learn processes information.
1837	
1838	hidepid=0 means classic mode - everybody may access all /proc/<pid>/ directories
1839	(default).
1840	
1841	hidepid=1 means users may not access any /proc/<pid>/ directories but their
1842	own.  Sensitive files like cmdline, sched*, status are now protected against
1843	other users.  This makes it impossible to learn whether any user runs
1844	specific program (given the program doesn't reveal itself by its behaviour).
1845	As an additional bonus, as /proc/<pid>/cmdline is unaccessible for other users,
1846	poorly written programs passing sensitive information via program arguments are
1847	now protected against local eavesdroppers.
1848	
1849	hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be fully invisible to other
1850	users.  It doesn't mean that it hides a fact whether a process with a specific
1851	pid value exists (it can be learned by other means, e.g. by "kill -0 $PID"),
1852	but it hides process' uid and gid, which may be learned by stat()'ing
1853	/proc/<pid>/ otherwise.  It greatly complicates an intruder's task of gathering
1854	information about running processes, whether some daemon runs with elevated
1855	privileges, whether other user runs some sensitive program, whether other users
1856	run any program at all, etc.
1857	
1858	gid= defines a group authorized to learn processes information otherwise
1859	prohibited by hidepid=.  If you use some daemon like identd which needs to learn
1860	information about processes information, just add identd to this group.
Hide Line Numbers
About Kernel Documentation Linux Kernel Contact Linux Resources Linux Blog

Information is copyright its respective author. All material is available from the Linux Kernel Source distributed under a GPL License. This page is provided as a free service by mjmwired.net.