linux/Documentation/filesystems/proc.txt
<<
>>
Prefs
   1------------------------------------------------------------------------------
   2                       T H E  /proc   F I L E S Y S T E M
   3------------------------------------------------------------------------------
   4/proc/sys         Terrehon Bowden <terrehon@pacbell.net>        October 7 1999
   5                  Bodo Bauer <bb@ricochet.net>
   6
   72.4.x update      Jorge Nerin <comandante@zaralinux.com>      November 14 2000
   8move /proc/sys    Shen Feng <shen@cn.fujitsu.com>                 April 1 2009
   9------------------------------------------------------------------------------
  10Version 1.3                                              Kernel version 2.2.12
  11                                              Kernel version 2.4.0-test11-pre4
  12------------------------------------------------------------------------------
  13fixes/update part 1.1  Stefani Seibold <stefani@seibold.net>       June 9 2009
  14
  15Table of Contents
  16-----------------
  17
  18  0     Preface
  19  0.1   Introduction/Credits
  20  0.2   Legal Stuff
  21
  22  1     Collecting System Information
  23  1.1   Process-Specific Subdirectories
  24  1.2   Kernel data
  25  1.3   IDE devices in /proc/ide
  26  1.4   Networking info in /proc/net
  27  1.5   SCSI info
  28  1.6   Parallel port info in /proc/parport
  29  1.7   TTY info in /proc/tty
  30  1.8   Miscellaneous kernel statistics in /proc/stat
  31  1.9   Ext4 file system parameters
  32
  33  2     Modifying System Parameters
  34
  35  3     Per-Process Parameters
  36  3.1   /proc/<pid>/oom_adj & /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  3.10  /proc/<pid>/timerslack_ns - Task timerslack value
  47
  48  4     Configuring procfs
  49  4.1   Mount options
  50
  51------------------------------------------------------------------------------
  52Preface
  53------------------------------------------------------------------------------
  54
  550.1 Introduction/Credits
  56------------------------
  57
  58This documentation is  part of a soon (or  so we hope) to be  released book on
  59the SuSE  Linux distribution. As  there is  no complete documentation  for the
  60/proc file system and we've used  many freely available sources to write these
  61chapters, it  seems only fair  to give the work  back to the  Linux community.
  62This work is  based on the 2.2.*  kernel version and the  upcoming 2.4.*. I'm
  63afraid it's still far from complete, but we  hope it will be useful. As far as
  64we know, it is the first 'all-in-one' document about the /proc file system. It
  65is focused  on the Intel  x86 hardware,  so if you  are looking for  PPC, ARM,
  66SPARC, AXP, etc., features, you probably  won't find what you are looking for.
  67It also only covers IPv4 networking, not IPv6 nor other protocols - sorry. But
  68additions and patches  are welcome and will  be added to this  document if you
  69mail them to Bodo.
  70
  71We'd like  to  thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of
  72other people for help compiling this documentation. We'd also like to extend a
  73special thank  you to Andi Kleen for documentation, which we relied on heavily
  74to create  this  document,  as well as the additional information he provided.
  75Thanks to  everybody  else  who contributed source or docs to the Linux kernel
  76and helped create a great piece of software... :)
  77
  78If you  have  any comments, corrections or additions, please don't hesitate to
  79contact Bodo  Bauer  at  bb@ricochet.net.  We'll  be happy to add them to this
  80document.
  81
  82The   latest   version    of   this   document   is    available   online   at
  83http://tldp.org/LDP/Linux-Filesystem-Hierarchy/html/proc.html
  84
  85If  the above  direction does  not works  for you,  you could  try the  kernel
  86mailing  list  at  linux-kernel@vger.kernel.org  and/or try  to  reach  me  at
  87comandante@zaralinux.com.
  88
  890.2 Legal Stuff
  90---------------
  91
  92We don't  guarantee  the  correctness  of this document, and if you come to us
  93complaining about  how  you  screwed  up  your  system  because  of  incorrect
  94documentation, we won't feel responsible...
  95
  96------------------------------------------------------------------------------
  97CHAPTER 1: COLLECTING SYSTEM INFORMATION
  98------------------------------------------------------------------------------
  99
 100------------------------------------------------------------------------------
 101In This Chapter
 102------------------------------------------------------------------------------
 103* Investigating  the  properties  of  the  pseudo  file  system  /proc and its
 104  ability to provide information on the running Linux system
 105* Examining /proc's structure
 106* Uncovering  various  information  about the kernel and the processes running
 107  on the system
 108------------------------------------------------------------------------------
 109
 110
 111The proc  file  system acts as an interface to internal data structures in the
 112kernel. It  can  be  used to obtain information about the system and to change
 113certain kernel parameters at runtime (sysctl).
 114
 115First, we'll  take  a  look  at the read-only parts of /proc. In Chapter 2, we
 116show you how you can use /proc/sys to change settings.
 117
 1181.1 Process-Specific Subdirectories
 119-----------------------------------
 120
 121The directory  /proc  contains  (among other things) one subdirectory for each
 122process running on the system, which is named after the process ID (PID).
 123
 124The link  self  points  to  the  process reading the file system. Each process
 125subdirectory has the entries listed in Table 1-1.
 126
 127
 128Table 1-1: Process specific entries in /proc
 129..............................................................................
 130 File           Content
 131 clear_refs     Clears page referenced bits shown in smaps output
 132 cmdline        Command line arguments
 133 cpu            Current and last cpu in which it was executed   (2.4)(smp)
 134 cwd            Link to the current working directory
 135 environ        Values of environment variables
 136 exe            Link to the executable of this process
 137 fd             Directory, which contains all file descriptors
 138 maps           Memory maps to executables and library files    (2.4)
 139 mem            Memory held by this process
 140 root           Link to the root directory of this process
 141 stat           Process status
 142 statm          Process memory status information
 143 status         Process status in human readable form
 144 wchan          Present with CONFIG_KALLSYMS=y: it shows the kernel function
 145                symbol the task is blocked in - or "0" if not blocked.
 146 pagemap        Page table
 147 stack          Report full stack trace, enable via CONFIG_STACKTRACE
 148 smaps          a extension based on maps, showing the memory consumption of
 149                each mapping and flags associated with it
 150 numa_maps      an extension based on maps, showing the memory locality and
 151                binding policy as well as mem usage (in pages) of each mapping.
 152..............................................................................
 153
 154For example, to get the status information of a process, all you have to do is
 155read the file /proc/PID/status:
 156
 157  >cat /proc/self/status
 158  Name:   cat
 159  State:  R (running)
 160  Tgid:   5452
 161  Pid:    5452
 162  PPid:   743
 163  TracerPid:      0                                             (2.4)
 164  Uid:    501     501     501     501
 165  Gid:    100     100     100     100
 166  FDSize: 256
 167  Groups: 100 14 16
 168  VmPeak:     5004 kB
 169  VmSize:     5004 kB
 170  VmLck:         0 kB
 171  VmHWM:       476 kB
 172  VmRSS:       476 kB
 173  RssAnon:             352 kB
 174  RssFile:             120 kB
 175  RssShmem:              4 kB
 176  VmData:      156 kB
 177  VmStk:        88 kB
 178  VmExe:        68 kB
 179  VmLib:      1412 kB
 180  VmPTE:        20 kb
 181  VmSwap:        0 kB
 182  HugetlbPages:          0 kB
 183  Threads:        1
 184  SigQ:   0/28578
 185  SigPnd: 0000000000000000
 186  ShdPnd: 0000000000000000
 187  SigBlk: 0000000000000000
 188  SigIgn: 0000000000000000
 189  SigCgt: 0000000000000000
 190  CapInh: 00000000fffffeff
 191  CapPrm: 0000000000000000
 192  CapEff: 0000000000000000
 193  CapBnd: ffffffffffffffff
 194  Seccomp:        0
 195  voluntary_ctxt_switches:        0
 196  nonvoluntary_ctxt_switches:     1
 197
 198This shows you nearly the same information you would get if you viewed it with
 199the ps  command.  In  fact,  ps  uses  the  proc  file  system  to  obtain its
 200information.  But you get a more detailed  view of the  process by reading the
 201file /proc/PID/status. It fields are described in table 1-2.
 202
 203The  statm  file  contains  more  detailed  information about the process
 204memory usage. Its seven fields are explained in Table 1-3.  The stat file
 205contains details information about the process itself.  Its fields are
 206explained in Table 1-4.
 207
 208(for SMP CONFIG users)
 209For making accounting scalable, RSS related information are handled in an
 210asynchronous manner and the value may not be very precise. To see a precise
 211snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
 212It's slow but very precise.
 213
 214Table 1-2: Contents of the status files (as of 4.1)
 215..............................................................................
 216 Field                       Content
 217 Name                        filename of the executable
 218 State                       state (R is running, S is sleeping, D is sleeping
 219                             in an uninterruptible wait, Z is zombie,
 220                             T is traced or stopped)
 221 Tgid                        thread group ID
 222 Ngid                        NUMA group ID (0 if none)
 223 Pid                         process id
 224 PPid                        process id of the parent process
 225 TracerPid                   PID of process tracing this process (0 if not)
 226 Uid                         Real, effective, saved set, and  file system UIDs
 227 Gid                         Real, effective, saved set, and  file system GIDs
 228 Umask                       file mode creation mask
 229 FDSize                      number of file descriptor slots currently allocated
 230 Groups                      supplementary group list
 231 NStgid                      descendant namespace thread group ID hierarchy
 232 NSpid                       descendant namespace process ID hierarchy
 233 NSpgid                      descendant namespace process group ID hierarchy
 234 NSsid                       descendant namespace session ID hierarchy
 235 VmPeak                      peak virtual memory size
 236 VmSize                      total program size
 237 VmLck                       locked memory size
 238 VmHWM                       peak resident set size ("high water mark")
 239 VmRSS                       size of memory portions. It contains the three
 240                             following parts (VmRSS = RssAnon + RssFile + RssShmem)
 241 RssAnon                     size of resident anonymous memory
 242 RssFile                     size of resident file mappings
 243 RssShmem                    size of resident shmem memory (includes SysV shm,
 244                             mapping of tmpfs and shared anonymous mappings)
 245 VmData                      size of private data segments
 246 VmStk                       size of stack segments
 247 VmExe                       size of text segment
 248 VmLib                       size of shared library code
 249 VmPTE                       size of page table entries
 250 VmPMD                       size of second level page tables
 251 VmSwap                      amount of swap used by anonymous private data
 252                             (shmem swap usage is not included)
 253 HugetlbPages                size of hugetlb memory portions
 254 Threads                     number of threads
 255 SigQ                        number of signals queued/max. number for queue
 256 SigPnd                      bitmap of pending signals for the thread
 257 ShdPnd                      bitmap of shared pending signals for the process
 258 SigBlk                      bitmap of blocked signals
 259 SigIgn                      bitmap of ignored signals
 260 SigCgt                      bitmap of caught signals
 261 CapInh                      bitmap of inheritable capabilities
 262 CapPrm                      bitmap of permitted capabilities
 263 CapEff                      bitmap of effective capabilities
 264 CapBnd                      bitmap of capabilities bounding set
 265 Seccomp                     seccomp mode, like prctl(PR_GET_SECCOMP, ...)
 266 Cpus_allowed                mask of CPUs on which this process may run
 267 Cpus_allowed_list           Same as previous, but in "list format"
 268 Mems_allowed                mask of memory nodes allowed to this process
 269 Mems_allowed_list           Same as previous, but in "list format"
 270 voluntary_ctxt_switches     number of voluntary context switches
 271 nonvoluntary_ctxt_switches  number of non voluntary context switches
 272..............................................................................
 273
 274Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
 275..............................................................................
 276 Field    Content
 277 size     total program size (pages)            (same as VmSize in status)
 278 resident size of memory portions (pages)       (same as VmRSS in status)
 279 shared   number of pages that are shared       (i.e. backed by a file, same
 280                                                as RssFile+RssShmem in status)
 281 trs      number of pages that are 'code'       (not including libs; broken,
 282                                                        includes data segment)
 283 lrs      number of pages of library            (always 0 on 2.6)
 284 drs      number of pages of data/stack         (including libs; broken,
 285                                                        includes library text)
 286 dt       number of dirty pages                 (always 0 on 2.6)
 287..............................................................................
 288
 289
 290Table 1-4: Contents of the stat files (as of 2.6.30-rc7)
 291..............................................................................
 292 Field          Content
 293  pid           process id
 294  tcomm         filename of the executable
 295  state         state (R is running, S is sleeping, D is sleeping in an
 296                uninterruptible wait, Z is zombie, T is traced or stopped)
 297  ppid          process id of the parent process
 298  pgrp          pgrp of the process
 299  sid           session id
 300  tty_nr        tty the process uses
 301  tty_pgrp      pgrp of the tty
 302  flags         task flags
 303  min_flt       number of minor faults
 304  cmin_flt      number of minor faults with child's
 305  maj_flt       number of major faults
 306  cmaj_flt      number of major faults with child's
 307  utime         user mode jiffies
 308  stime         kernel mode jiffies
 309  cutime        user mode jiffies with child's
 310  cstime        kernel mode jiffies with child's
 311  priority      priority level
 312  nice          nice level
 313  num_threads   number of threads
 314  it_real_value (obsolete, always 0)
 315  start_time    time the process started after system boot
 316  vsize         virtual memory size
 317  rss           resident set memory size
 318  rsslim        current limit in bytes on the rss
 319  start_code    address above which program text can run
 320  end_code      address below which program text can run
 321  start_stack   address of the start of the main process stack
 322  esp           current value of ESP
 323  eip           current value of EIP
 324  pending       bitmap of pending signals
 325  blocked       bitmap of blocked signals
 326  sigign        bitmap of ignored signals
 327  sigcatch      bitmap of caught signals
 328  0             (place holder, used to be the wchan address, use /proc/PID/wchan instead)
 329  0             (place holder)
 330  0             (place holder)
 331  exit_signal   signal to send to parent thread on exit
 332  task_cpu      which CPU the task is scheduled on
 333  rt_priority   realtime priority
 334  policy        scheduling policy (man sched_setscheduler)
 335  blkio_ticks   time spent waiting for block IO
 336  gtime         guest time of the task in jiffies
 337  cgtime        guest time of the task children in jiffies
 338  start_data    address above which program data+bss is placed
 339  end_data      address below which program data+bss is placed
 340  start_brk     address above which program heap can be expanded with brk()
 341  arg_start     address above which program command line is placed
 342  arg_end       address below which program command line is placed
 343  env_start     address above which program environment is placed
 344  env_end       address below which program environment is placed
 345  exit_code     the thread's exit_code in the form reported by the waitpid system call
 346..............................................................................
 347
 348The /proc/PID/maps file containing the currently mapped memory regions and
 349their access permissions.
 350
 351The format is:
 352
 353address           perms offset  dev   inode      pathname
 354
 35508048000-08049000 r-xp 00000000 03:00 8312       /opt/test
 35608049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
 3570804a000-0806b000 rw-p 00000000 00:00 0          [heap]
 358a7cb1000-a7cb2000 ---p 00000000 00:00 0
 359a7cb2000-a7eb2000 rw-p 00000000 00:00 0
 360a7eb2000-a7eb3000 ---p 00000000 00:00 0
 361a7eb3000-a7ed5000 rw-p 00000000 00:00 0
 362a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
 363a8008000-a800a000 r--p 00133000 03:00 4222       /lib/libc.so.6
 364a800a000-a800b000 rw-p 00135000 03:00 4222       /lib/libc.so.6
 365a800b000-a800e000 rw-p 00000000 00:00 0
 366a800e000-a8022000 r-xp 00000000 03:00 14462      /lib/libpthread.so.0
 367a8022000-a8023000 r--p 00013000 03:00 14462      /lib/libpthread.so.0
 368a8023000-a8024000 rw-p 00014000 03:00 14462      /lib/libpthread.so.0
 369a8024000-a8027000 rw-p 00000000 00:00 0
 370a8027000-a8043000 r-xp 00000000 03:00 8317       /lib/ld-linux.so.2
 371a8043000-a8044000 r--p 0001b000 03:00 8317       /lib/ld-linux.so.2
 372a8044000-a8045000 rw-p 0001c000 03:00 8317       /lib/ld-linux.so.2
 373aff35000-aff4a000 rw-p 00000000 00:00 0          [stack]
 374ffffe000-fffff000 r-xp 00000000 00:00 0          [vdso]
 375
 376where "address" is the address space in the process that it occupies, "perms"
 377is a set of permissions:
 378
 379 r = read
 380 w = write
 381 x = execute
 382 s = shared
 383 p = private (copy on write)
 384
 385"offset" is the offset into the mapping, "dev" is the device (major:minor), and
 386"inode" is the inode  on that device.  0 indicates that  no inode is associated
 387with the memory region, as the case would be with BSS (uninitialized data).
 388The "pathname" shows the name associated file for this mapping.  If the mapping
 389is not associated with a file:
 390
 391 [heap]                   = the heap of the program
 392 [stack]                  = the stack of the main process
 393 [vdso]                   = the "virtual dynamic shared object",
 394                            the kernel system call handler
 395
 396 or if empty, the mapping is anonymous.
 397
 398The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint
 399of the individual tasks of a process. In this file you will see a mapping marked
 400as [stack] if that task sees it as a stack. Hence, for the example above, the
 401task-level map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
 402
 40308048000-08049000 r-xp 00000000 03:00 8312       /opt/test
 40408049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
 4050804a000-0806b000 rw-p 00000000 00:00 0          [heap]
 406a7cb1000-a7cb2000 ---p 00000000 00:00 0
 407a7cb2000-a7eb2000 rw-p 00000000 00:00 0
 408a7eb2000-a7eb3000 ---p 00000000 00:00 0
 409a7eb3000-a7ed5000 rw-p 00000000 00:00 0          [stack]
 410a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
 411a8008000-a800a000 r--p 00133000 03:00 4222       /lib/libc.so.6
 412a800a000-a800b000 rw-p 00135000 03:00 4222       /lib/libc.so.6
 413a800b000-a800e000 rw-p 00000000 00:00 0
 414a800e000-a8022000 r-xp 00000000 03:00 14462      /lib/libpthread.so.0
 415a8022000-a8023000 r--p 00013000 03:00 14462      /lib/libpthread.so.0
 416a8023000-a8024000 rw-p 00014000 03:00 14462      /lib/libpthread.so.0
 417a8024000-a8027000 rw-p 00000000 00:00 0
 418a8027000-a8043000 r-xp 00000000 03:00 8317       /lib/ld-linux.so.2
 419a8043000-a8044000 r--p 0001b000 03:00 8317       /lib/ld-linux.so.2
 420a8044000-a8045000 rw-p 0001c000 03:00 8317       /lib/ld-linux.so.2
 421aff35000-aff4a000 rw-p 00000000 00:00 0
 422ffffe000-fffff000 r-xp 00000000 00:00 0          [vdso]
 423
 424The /proc/PID/smaps is an extension based on maps, showing the memory
 425consumption for each of the process's mappings. For each of mappings there
 426is a series of lines such as the following:
 427
 42808048000-080bc000 r-xp 00000000 03:02 13130      /bin/bash
 429Size:               1084 kB
 430Rss:                 892 kB
 431Pss:                 374 kB
 432Shared_Clean:        892 kB
 433Shared_Dirty:          0 kB
 434Private_Clean:         0 kB
 435Private_Dirty:         0 kB
 436Referenced:          892 kB
 437Anonymous:             0 kB
 438AnonHugePages:         0 kB
 439Shared_Hugetlb:        0 kB
 440Private_Hugetlb:       0 kB
 441Swap:                  0 kB
 442SwapPss:               0 kB
 443KernelPageSize:        4 kB
 444MMUPageSize:           4 kB
 445Locked:                0 kB
 446VmFlags: rd ex mr mw me dw
 447
 448the first of these lines shows the same information as is displayed for the
 449mapping in /proc/PID/maps.  The remaining lines show the size of the mapping
 450(size), the amount of the mapping that is currently resident in RAM (RSS), the
 451process' proportional share of this mapping (PSS), the number of clean and
 452dirty private pages in the mapping.
 453
 454The "proportional set size" (PSS) of a process is the count of pages it has
 455in memory, where each page is divided by the number of processes sharing it.
 456So if a process has 1000 pages all to itself, and 1000 shared with one other
 457process, its PSS will be 1500.
 458Note that even a page which is part of a MAP_SHARED mapping, but has only
 459a single pte mapped, i.e.  is currently used by only one process, is accounted
 460as private and not as shared.
 461"Referenced" indicates the amount of memory currently marked as referenced or
 462accessed.
 463"Anonymous" shows the amount of memory that does not belong to any file.  Even
 464a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
 465and a page is modified, the file page is replaced by a private anonymous copy.
 466"AnonHugePages" shows the ammount of memory backed by transparent hugepage.
 467"Shared_Hugetlb" and "Private_Hugetlb" show the ammounts of memory backed by
 468hugetlbfs page which is *not* counted in "RSS" or "PSS" field for historical
 469reasons. And these are not included in {Shared,Private}_{Clean,Dirty} field.
 470"Swap" shows how much would-be-anonymous memory is also used, but out on swap.
 471For shmem mappings, "Swap" includes also the size of the mapped (and not
 472replaced by copy-on-write) part of the underlying shmem object out on swap.
 473"SwapPss" shows proportional swap share of this mapping. Unlike "Swap", this
 474does not take into account swapped out page of underlying shmem objects.
 475"Locked" indicates whether the mapping is locked in memory or not.
 476
 477"VmFlags" field deserves a separate description. This member represents the kernel
 478flags associated with the particular virtual memory area in two letter encoded
 479manner. The codes are the following:
 480    rd  - readable
 481    wr  - writeable
 482    ex  - executable
 483    sh  - shared
 484    mr  - may read
 485    mw  - may write
 486    me  - may execute
 487    ms  - may share
 488    gd  - stack segment growns down
 489    pf  - pure PFN range
 490    dw  - disabled write to the mapped file
 491    lo  - pages are locked in memory
 492    io  - memory mapped I/O area
 493    sr  - sequential read advise provided
 494    rr  - random read advise provided
 495    dc  - do not copy area on fork
 496    de  - do not expand area on remapping
 497    ac  - area is accountable
 498    nr  - swap space is not reserved for the area
 499    ht  - area uses huge tlb pages
 500    ar  - architecture specific flag
 501    dd  - do not include area into core dump
 502    sd  - soft-dirty flag
 503    mm  - mixed map area
 504    hg  - huge page advise flag
 505    nh  - no-huge page advise flag
 506    mg  - mergable advise flag
 507
 508Note that there is no guarantee that every flag and associated mnemonic will
 509be present in all further kernel releases. Things get changed, the flags may
 510be vanished or the reverse -- new added.
 511
 512This file is only present if the CONFIG_MMU kernel configuration option is
 513enabled.
 514
 515The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
 516bits on both physical and virtual pages associated with a process, and the
 517soft-dirty bit on pte (see Documentation/vm/soft-dirty.txt for details).
 518To clear the bits for all the pages associated with the process
 519    > echo 1 > /proc/PID/clear_refs
 520
 521To clear the bits for the anonymous pages associated with the process
 522    > echo 2 > /proc/PID/clear_refs
 523
 524To clear the bits for the file mapped pages associated with the process
 525    > echo 3 > /proc/PID/clear_refs
 526
 527To clear the soft-dirty bit
 528    > echo 4 > /proc/PID/clear_refs
 529
 530To reset the peak resident set size ("high water mark") to the process's
 531current value:
 532    > echo 5 > /proc/PID/clear_refs
 533
 534Any other value written to /proc/PID/clear_refs will have no effect.
 535
 536The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
 537using /proc/kpageflags and number of times a page is mapped using
 538/proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.txt.
 539
 540The /proc/pid/numa_maps is an extension based on maps, showing the memory
 541locality and binding policy, as well as the memory usage (in pages) of
 542each mapping. The output follows a general format where mapping details get
 543summarized separated by blank spaces, one mapping per each file line:
 544
 545address   policy    mapping details
 546
 54700400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4
 54800600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4
 5493206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4
 550320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
 5513206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
 5523206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4
 5533206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4
 554320698b000 default file=/lib64/libc-2.12.so
 5553206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4
 5563206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
 5573206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4
 5587f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4
 5597f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4
 5607f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048
 5617fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4
 5627fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4
 563
 564Where:
 565"address" is the starting address for the mapping;
 566"policy" reports the NUMA memory policy set for the mapping (see vm/numa_memory_policy.txt);
 567"mapping details" summarizes mapping data such as mapping type, page usage counters,
 568node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page
 569size, in KB, that is backing the mapping up.
 570
 5711.2 Kernel data
 572---------------
 573
 574Similar to  the  process entries, the kernel data files give information about
 575the running kernel. The files used to obtain this information are contained in
 576/proc and  are  listed  in Table 1-5. Not all of these will be present in your
 577system. It  depends  on the kernel configuration and the loaded modules, which
 578files are there, and which are missing.
 579
 580Table 1-5: Kernel info in /proc
 581..............................................................................
 582 File        Content                                           
 583 apm         Advanced power management info                    
 584 buddyinfo   Kernel memory allocator information (see text)     (2.5)
 585 bus         Directory containing bus specific information     
 586 cmdline     Kernel command line                               
 587 cpuinfo     Info about the CPU                                
 588 devices     Available devices (block and character)           
 589 dma         Used DMS channels                                 
 590 filesystems Supported filesystems                             
 591 driver      Various drivers grouped here, currently rtc (2.4)
 592 execdomains Execdomains, related to security                   (2.4)
 593 fb          Frame Buffer devices                               (2.4)
 594 fs          File system parameters, currently nfs/exports      (2.4)
 595 ide         Directory containing info about the IDE subsystem 
 596 interrupts  Interrupt usage                                   
 597 iomem       Memory map                                         (2.4)
 598 ioports     I/O port usage                                    
 599 irq         Masks for irq to cpu affinity                      (2.4)(smp?)
 600 isapnp      ISA PnP (Plug&Play) Info                           (2.4)
 601 kcore       Kernel core image (can be ELF or A.OUT(deprecated in 2.4))   
 602 kmsg        Kernel messages                                   
 603 ksyms       Kernel symbol table                               
 604 loadavg     Load average of last 1, 5 & 15 minutes                
 605 locks       Kernel locks                                      
 606 meminfo     Memory info                                       
 607 misc        Miscellaneous                                     
 608 modules     List of loaded modules                            
 609 mounts      Mounted filesystems                               
 610 net         Networking info (see text)                        
 611 pagetypeinfo Additional page allocator information (see text)  (2.5)
 612 partitions  Table of partitions known to the system           
 613 pci         Deprecated info of PCI bus (new way -> /proc/bus/pci/,
 614             decoupled by lspci                                 (2.4)
 615 rtc         Real time clock                                   
 616 scsi        SCSI info (see text)                              
 617 slabinfo    Slab pool info                                    
 618 softirqs    softirq usage
 619 stat        Overall statistics                                
 620 swaps       Swap space utilization                            
 621 sys         See chapter 2                                     
 622 sysvipc     Info of SysVIPC Resources (msg, sem, shm)          (2.4)
 623 tty         Info of tty drivers
 624 uptime      Wall clock since boot, combined idle time of all cpus
 625 version     Kernel version                                    
 626 video       bttv info of video resources                       (2.4)
 627 vmallocinfo Show vmalloced areas
 628..............................................................................
 629
 630You can,  for  example,  check  which interrupts are currently in use and what
 631they are used for by looking in the file /proc/interrupts:
 632
 633  > cat /proc/interrupts 
 634             CPU0        
 635    0:    8728810          XT-PIC  timer 
 636    1:        895          XT-PIC  keyboard 
 637    2:          0          XT-PIC  cascade 
 638    3:     531695          XT-PIC  aha152x 
 639    4:    2014133          XT-PIC  serial 
 640    5:      44401          XT-PIC  pcnet_cs 
 641    8:          2          XT-PIC  rtc 
 642   11:          8          XT-PIC  i82365 
 643   12:     182918          XT-PIC  PS/2 Mouse 
 644   13:          1          XT-PIC  fpu 
 645   14:    1232265          XT-PIC  ide0 
 646   15:          7          XT-PIC  ide1 
 647  NMI:          0 
 648
 649In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the
 650output of a SMP machine):
 651
 652  > cat /proc/interrupts 
 653
 654             CPU0       CPU1       
 655    0:    1243498    1214548    IO-APIC-edge  timer
 656    1:       8949       8958    IO-APIC-edge  keyboard
 657    2:          0          0          XT-PIC  cascade
 658    5:      11286      10161    IO-APIC-edge  soundblaster
 659    8:          1          0    IO-APIC-edge  rtc
 660    9:      27422      27407    IO-APIC-edge  3c503
 661   12:     113645     113873    IO-APIC-edge  PS/2 Mouse
 662   13:          0          0          XT-PIC  fpu
 663   14:      22491      24012    IO-APIC-edge  ide0
 664   15:       2183       2415    IO-APIC-edge  ide1
 665   17:      30564      30414   IO-APIC-level  eth0
 666   18:        177        164   IO-APIC-level  bttv
 667  NMI:    2457961    2457959 
 668  LOC:    2457882    2457881 
 669  ERR:       2155
 670
 671NMI is incremented in this case because every timer interrupt generates a NMI
 672(Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups.
 673
 674LOC is the local interrupt counter of the internal APIC of every CPU.
 675
 676ERR is incremented in the case of errors in the IO-APIC bus (the bus that
 677connects the CPUs in a SMP system. This means that an error has been detected,
 678the IO-APIC automatically retry the transmission, so it should not be a big
 679problem, but you should read the SMP-FAQ.
 680
 681In 2.6.2* /proc/interrupts was expanded again.  This time the goal was for
 682/proc/interrupts to display every IRQ vector in use by the system, not
 683just those considered 'most important'.  The new vectors are:
 684
 685  THR -- interrupt raised when a machine check threshold counter
 686  (typically counting ECC corrected errors of memory or cache) exceeds
 687  a configurable threshold.  Only available on some systems.
 688
 689  TRM -- a thermal event interrupt occurs when a temperature threshold
 690  has been exceeded for the CPU.  This interrupt may also be generated
 691  when the temperature drops back to normal.
 692
 693  SPU -- a spurious interrupt is some interrupt that was raised then lowered
 694  by some IO device before it could be fully processed by the APIC.  Hence
 695  the APIC sees the interrupt but does not know what device it came from.
 696  For this case the APIC will generate the interrupt with a IRQ vector
 697  of 0xff. This might also be generated by chipset bugs.
 698
 699  RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are
 700  sent from one CPU to another per the needs of the OS.  Typically,
 701  their statistics are used by kernel developers and interested users to
 702  determine the occurrence of interrupts of the given type.
 703
 704The above IRQ vectors are displayed only when relevant.  For example,
 705the threshold vector does not exist on x86_64 platforms.  Others are
 706suppressed when the system is a uniprocessor.  As of this writing, only
 707i386 and x86_64 platforms support the new IRQ vector displays.
 708
 709Of some interest is the introduction of the /proc/irq directory to 2.4.
 710It could be used to set IRQ to CPU affinity, this means that you can "hook" an
 711IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
 712irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and
 713prof_cpu_mask.
 714
 715For example 
 716  > ls /proc/irq/
 717  0  10  12  14  16  18  2  4  6  8  prof_cpu_mask
 718  1  11  13  15  17  19  3  5  7  9  default_smp_affinity
 719  > ls /proc/irq/0/
 720  smp_affinity
 721
 722smp_affinity is a bitmask, in which you can specify which CPUs can handle the
 723IRQ, you can set it by doing:
 724
 725  > echo 1 > /proc/irq/10/smp_affinity
 726
 727This means that only the first CPU will handle the IRQ, but you can also echo
 7285 which means that only the first and fourth CPU can handle the IRQ.
 729
 730The contents of each smp_affinity file is the same by default:
 731
 732  > cat /proc/irq/0/smp_affinity
 733  ffffffff
 734
 735There is an alternate interface, smp_affinity_list which allows specifying
 736a cpu range instead of a bitmask:
 737
 738  > cat /proc/irq/0/smp_affinity_list
 739  1024-1031
 740
 741The default_smp_affinity mask applies to all non-active IRQs, which are the
 742IRQs which have not yet been allocated/activated, and hence which lack a
 743/proc/irq/[0-9]* directory.
 744
 745The node file on an SMP system shows the node to which the device using the IRQ
 746reports itself as being attached. This hardware locality information does not
 747include information about any possible driver locality preference.
 748
 749prof_cpu_mask specifies which CPUs are to be profiled by the system wide
 750profiler. Default value is ffffffff (all cpus if there are only 32 of them).
 751
 752The way IRQs are routed is handled by the IO-APIC, and it's Round Robin
 753between all the CPUs which are allowed to handle it. As usual the kernel has
 754more info than you and does a better job than you, so the defaults are the
 755best choice for almost everyone.  [Note this applies only to those IO-APIC's
 756that support "Round Robin" interrupt distribution.]
 757
 758There are  three  more  important subdirectories in /proc: net, scsi, and sys.
 759The general  rule  is  that  the  contents,  or  even  the  existence of these
 760directories, depend  on your kernel configuration. If SCSI is not enabled, the
 761directory scsi  may  not  exist. The same is true with the net, which is there
 762only when networking support is present in the running kernel.
 763
 764The slabinfo  file  gives  information  about  memory usage at the slab level.
 765Linux uses  slab  pools for memory management above page level in version 2.2.
 766Commonly used  objects  have  their  own  slab  pool (such as network buffers,
 767directory cache, and so on).
 768
 769..............................................................................
 770
 771> cat /proc/buddyinfo
 772
 773Node 0, zone      DMA      0      4      5      4      4      3 ...
 774Node 0, zone   Normal      1      0      0      1    101      8 ...
 775Node 0, zone  HighMem      2      0      0      1      1      0 ...
 776
 777External fragmentation is a problem under some workloads, and buddyinfo is a
 778useful tool for helping diagnose these problems.  Buddyinfo will give you a 
 779clue as to how big an area you can safely allocate, or why a previous
 780allocation failed.
 781
 782Each column represents the number of pages of a certain order which are 
 783available.  In this case, there are 0 chunks of 2^0*PAGE_SIZE available in 
 784ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE 
 785available in ZONE_NORMAL, etc... 
 786
 787More information relevant to external fragmentation can be found in
 788pagetypeinfo.
 789
 790> cat /proc/pagetypeinfo
 791Page block order: 9
 792Pages per block:  512
 793
 794Free pages count per migrate type at order       0      1      2      3      4      5      6      7      8      9     10
 795Node    0, zone      DMA, type    Unmovable      0      0      0      1      1      1      1      1      1      1      0
 796Node    0, zone      DMA, type  Reclaimable      0      0      0      0      0      0      0      0      0      0      0
 797Node    0, zone      DMA, type      Movable      1      1      2      1      2      1      1      0      1      0      2
 798Node    0, zone      DMA, type      Reserve      0      0      0      0      0      0      0      0      0      1      0
 799Node    0, zone      DMA, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
 800Node    0, zone    DMA32, type    Unmovable    103     54     77      1      1      1     11      8      7      1      9
 801Node    0, zone    DMA32, type  Reclaimable      0      0      2      1      0      0      0      0      1      0      0
 802Node    0, zone    DMA32, type      Movable    169    152    113     91     77     54     39     13      6      1    452
 803Node    0, zone    DMA32, type      Reserve      1      2      2      2      2      0      1      1      1      1      0
 804Node    0, zone    DMA32, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
 805
 806Number of blocks type     Unmovable  Reclaimable      Movable      Reserve      Isolate
 807Node 0, zone      DMA            2            0            5            1            0
 808Node 0, zone    DMA32           41            6          967            2            0
 809
 810Fragmentation avoidance in the kernel works by grouping pages of different
 811migrate types into the same contiguous regions of memory called page blocks.
 812A page block is typically the size of the default hugepage size e.g. 2MB on
 813X86-64. By keeping pages grouped based on their ability to move, the kernel
 814can reclaim pages within a page block to satisfy a high-order allocation.
 815
 816The pagetypinfo begins with information on the size of a page block. It
 817then gives the same type of information as buddyinfo except broken down
 818by migrate-type and finishes with details on how many page blocks of each
 819type exist.
 820
 821If min_free_kbytes has been tuned correctly (recommendations made by hugeadm
 822from libhugetlbfs https://github.com/libhugetlbfs/libhugetlbfs/), one can
 823make an estimate of the likely number of huge pages that can be allocated
 824at a given point in time. All the "Movable" blocks should be allocatable
 825unless memory has been mlock()'d. Some of the Reclaimable blocks should
 826also be allocatable although a lot of filesystem metadata may have to be
 827reclaimed to achieve this.
 828
 829..............................................................................
 830
 831meminfo:
 832
 833Provides information about distribution and utilization of memory.  This
 834varies by architecture and compile options.  The following is from a
 83516GB PIII, which has highmem enabled.  You may not have all of these fields.
 836
 837> cat /proc/meminfo
 838
 839MemTotal:     16344972 kB
 840MemFree:      13634064 kB
 841MemAvailable: 14836172 kB
 842Buffers:          3656 kB
 843Cached:        1195708 kB
 844SwapCached:          0 kB
 845Active:         891636 kB
 846Inactive:      1077224 kB
 847HighTotal:    15597528 kB
 848HighFree:     13629632 kB
 849LowTotal:       747444 kB
 850LowFree:          4432 kB
 851SwapTotal:           0 kB
 852SwapFree:            0 kB
 853Dirty:             968 kB
 854Writeback:           0 kB
 855AnonPages:      861800 kB
 856Mapped:         280372 kB
 857Shmem:             644 kB
 858Slab:           284364 kB
 859SReclaimable:   159856 kB
 860SUnreclaim:     124508 kB
 861PageTables:      24448 kB
 862NFS_Unstable:        0 kB
 863Bounce:              0 kB
 864WritebackTmp:        0 kB
 865CommitLimit:   7669796 kB
 866Committed_AS:   100056 kB
 867VmallocTotal:   112216 kB
 868VmallocUsed:       428 kB
 869VmallocChunk:   111088 kB
 870AnonHugePages:   49152 kB
 871
 872    MemTotal: Total usable ram (i.e. physical ram minus a few reserved
 873              bits and the kernel binary code)
 874     MemFree: The sum of LowFree+HighFree
 875MemAvailable: An estimate of how much memory is available for starting new
 876              applications, without swapping. Calculated from MemFree,
 877              SReclaimable, the size of the file LRU lists, and the low
 878              watermarks in each zone.
 879              The estimate takes into account that the system needs some
 880              page cache to function well, and that not all reclaimable
 881              slab will be reclaimable, due to items being in use. The
 882              impact of those factors will vary from system to system.
 883     Buffers: Relatively temporary storage for raw disk blocks
 884              shouldn't get tremendously large (20MB or so)
 885      Cached: in-memory cache for files read from the disk (the
 886              pagecache).  Doesn't include SwapCached
 887  SwapCached: Memory that once was swapped out, is swapped back in but
 888              still also is in the swapfile (if memory is needed it
 889              doesn't need to be swapped out AGAIN because it is already
 890              in the swapfile. This saves I/O)
 891      Active: Memory that has been used more recently and usually not
 892              reclaimed unless absolutely necessary.
 893    Inactive: Memory which has been less recently used.  It is more
 894              eligible to be reclaimed for other purposes
 895   HighTotal:
 896    HighFree: Highmem is all memory above ~860MB of physical memory
 897              Highmem areas are for use by userspace programs, or
 898              for the pagecache.  The kernel must use tricks to access
 899              this memory, making it slower to access than lowmem.
 900    LowTotal:
 901     LowFree: Lowmem is memory which can be used for everything that
 902              highmem can be used for, but it is also available for the
 903              kernel's use for its own data structures.  Among many
 904              other things, it is where everything from the Slab is
 905              allocated.  Bad things happen when you're out of lowmem.
 906   SwapTotal: total amount of swap space available
 907    SwapFree: Memory which has been evicted from RAM, and is temporarily
 908              on the disk
 909       Dirty: Memory which is waiting to get written back to the disk
 910   Writeback: Memory which is actively being written back to the disk
 911   AnonPages: Non-file backed pages mapped into userspace page tables
 912AnonHugePages: Non-file backed huge pages mapped into userspace page tables
 913      Mapped: files which have been mmaped, such as libraries
 914       Shmem: Total memory used by shared memory (shmem) and tmpfs
 915        Slab: in-kernel data structures cache
 916SReclaimable: Part of Slab, that might be reclaimed, such as caches
 917  SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure
 918  PageTables: amount of memory dedicated to the lowest level of page
 919              tables.
 920NFS_Unstable: NFS pages sent to the server, but not yet committed to stable
 921              storage
 922      Bounce: Memory used for block device "bounce buffers"
 923WritebackTmp: Memory used by FUSE for temporary writeback buffers
 924 CommitLimit: Based on the overcommit ratio ('vm.overcommit_ratio'),
 925              this is the total amount of  memory currently available to
 926              be allocated on the system. This limit is only adhered to
 927              if strict overcommit accounting is enabled (mode 2 in
 928              'vm.overcommit_memory').
 929              The CommitLimit is calculated with the following formula:
 930              CommitLimit = ([total RAM pages] - [total huge TLB pages]) *
 931                             overcommit_ratio / 100 + [total swap pages]
 932              For example, on a system with 1G of physical RAM and 7G
 933              of swap with a `vm.overcommit_ratio` of 30 it would
 934              yield a CommitLimit of 7.3G.
 935              For more details, see the memory overcommit documentation
 936              in vm/overcommit-accounting.
 937Committed_AS: The amount of memory presently allocated on the system.
 938              The committed memory is a sum of all of the memory which
 939              has been allocated by processes, even if it has not been
 940              "used" by them as of yet. A process which malloc()'s 1G
 941              of memory, but only touches 300M of it will show up as
 942              using 1G. This 1G is memory which has been "committed" to
 943              by the VM and can be used at any time by the allocating
 944              application. With strict overcommit enabled on the system
 945              (mode 2 in 'vm.overcommit_memory'),allocations which would
 946              exceed the CommitLimit (detailed above) will not be permitted.
 947              This is useful if one needs to guarantee that processes will
 948              not fail due to lack of memory once that memory has been
 949              successfully allocated.
 950VmallocTotal: total size of vmalloc memory area
 951 VmallocUsed: amount of vmalloc area which is used
 952VmallocChunk: largest contiguous block of vmalloc area which is free
 953
 954..............................................................................
 955
 956vmallocinfo:
 957
 958Provides information about vmalloced/vmaped areas. One line per area,
 959containing the virtual address range of the area, size in bytes,
 960caller information of the creator, and optional information depending
 961on the kind of area :
 962
 963 pages=nr    number of pages
 964 phys=addr   if a physical address was specified
 965 ioremap     I/O mapping (ioremap() and friends)
 966 vmalloc     vmalloc() area
 967 vmap        vmap()ed pages
 968 user        VM_USERMAP area
 969 vpages      buffer for pages pointers was vmalloced (huge area)
 970 N<node>=nr  (Only on NUMA kernels)
 971             Number of pages allocated on memory node <node>
 972
 973> cat /proc/vmallocinfo
 9740xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ...
 975  /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128
 9760xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ...
 977  /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64
 9780xffffc20000302000-0xffffc20000304000    8192 acpi_tb_verify_table+0x21/0x4f...
 979  phys=7fee8000 ioremap
 9800xffffc20000304000-0xffffc20000307000   12288 acpi_tb_verify_table+0x21/0x4f...
 981  phys=7fee7000 ioremap
 9820xffffc2000031d000-0xffffc2000031f000    8192 init_vdso_vars+0x112/0x210
 9830xffffc2000031f000-0xffffc2000032b000   49152 cramfs_uncompress_init+0x2e ...
 984  /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3
 9850xffffc2000033a000-0xffffc2000033d000   12288 sys_swapon+0x640/0xac0      ...
 986  pages=2 vmalloc N1=2
 9870xffffc20000347000-0xffffc2000034c000   20480 xt_alloc_table_info+0xfe ...
 988  /0x130 [x_tables] pages=4 vmalloc N0=4
 9890xffffffffa0000000-0xffffffffa000f000   61440 sys_init_module+0xc27/0x1d00 ...
 990   pages=14 vmalloc N2=14
 9910xffffffffa000f000-0xffffffffa0014000   20480 sys_init_module+0xc27/0x1d00 ...
 992   pages=4 vmalloc N1=4
 9930xffffffffa0014000-0xffffffffa0017000   12288 sys_init_module+0xc27/0x1d00 ...
 994   pages=2 vmalloc N1=2
 9950xffffffffa0017000-0xffffffffa0022000   45056 sys_init_module+0xc27/0x1d00 ...
 996   pages=10 vmalloc N0=10
 997
 998..............................................................................
 999
1000softirqs:
1001
1002Provides counts of softirq handlers serviced since boot time, for each cpu.
1003
1004> cat /proc/softirqs
1005                CPU0       CPU1       CPU2       CPU3
1006      HI:          0          0          0          0
1007   TIMER:      27166      27120      27097      27034
1008  NET_TX:          0          0          0         17
1009  NET_RX:         42          0          0         39
1010   BLOCK:          0          0        107       1121
1011 TASKLET:          0          0          0        290
1012   SCHED:      27035      26983      26971      26746
1013 HRTIMER:          0          0          0          0
1014     RCU:       1678       1769       2178       2250
1015
1016
10171.3 IDE devices in /proc/ide
1018----------------------------
1019
1020The subdirectory /proc/ide contains information about all IDE devices of which
1021the kernel  is  aware.  There is one subdirectory for each IDE controller, the
1022file drivers  and a link for each IDE device, pointing to the device directory
1023in the controller specific subtree.
1024
1025The file  drivers  contains general information about the drivers used for the
1026IDE devices:
1027
1028  > cat /proc/ide/drivers
1029  ide-cdrom version 4.53
1030  ide-disk version 1.08
1031
1032More detailed  information  can  be  found  in  the  controller  specific
1033subdirectories. These  are  named  ide0,  ide1  and  so  on.  Each  of  these
1034directories contains the files shown in table 1-6.
1035
1036
1037Table 1-6: IDE controller info in  /proc/ide/ide?
1038..............................................................................
1039 File    Content                                 
1040 channel IDE channel (0 or 1)                    
1041 config  Configuration (only for PCI/IDE bridge) 
1042 mate    Mate name                               
1043 model   Type/Chipset of IDE controller          
1044..............................................................................
1045
1046Each device  connected  to  a  controller  has  a separate subdirectory in the
1047controllers directory.  The  files  listed in table 1-7 are contained in these
1048directories.
1049
1050
1051Table 1-7: IDE device information
1052..............................................................................
1053 File             Content                                    
1054 cache            The cache                                  
1055 capacity         Capacity of the medium (in 512Byte blocks) 
1056 driver           driver and version                         
1057 geometry         physical and logical geometry              
1058 identify         device identify block                      
1059 media            media type                                 
1060 model            device identifier                          
1061 settings         device setup                               
1062 smart_thresholds IDE disk management thresholds             
1063 smart_values     IDE disk management values                 
1064..............................................................................
1065
1066The most  interesting  file is settings. This file contains a nice overview of
1067the drive parameters:
1068
1069  # cat /proc/ide/ide0/hda/settings 
1070  name                    value           min             max             mode 
1071  ----                    -----           ---             ---             ---- 
1072  bios_cyl                526             0               65535           rw 
1073  bios_head               255             0               255             rw 
1074  bios_sect               63              0               63              rw 
1075  breada_readahead        4               0               127             rw 
1076  bswap                   0               0               1               r 
1077  file_readahead          72              0               2097151         rw 
1078  io_32bit                0               0               3               rw 
1079  keepsettings            0               0               1               rw 
1080  max_kb_per_request      122             1               127             rw 
1081  multcount               0               0               8               rw 
1082  nice1                   1               0               1               rw 
1083  nowerr                  0               0               1               rw 
1084  pio_mode                write-only      0               255             w 
1085  slow                    0               0               1               rw 
1086  unmaskirq               0               0               1               rw 
1087  using_dma               0               0               1               rw 
1088
1089
10901.4 Networking info in /proc/net
1091--------------------------------
1092
1093The subdirectory  /proc/net  follows  the  usual  pattern. Table 1-8 shows the
1094additional values  you  get  for  IP  version 6 if you configure the kernel to
1095support this. Table 1-9 lists the files and their meaning.
1096
1097
1098Table 1-8: IPv6 info in /proc/net
1099..............................................................................
1100 File       Content                                               
1101 udp6       UDP sockets (IPv6)                                    
1102 tcp6       TCP sockets (IPv6)                                    
1103 raw6       Raw device statistics (IPv6)                          
1104 igmp6      IP multicast addresses, which this host joined (IPv6) 
1105 if_inet6   List of IPv6 interface addresses                      
1106 ipv6_route Kernel routing table for IPv6                         
1107 rt6_stats  Global IPv6 routing tables statistics                 
1108 sockstat6  Socket statistics (IPv6)                              
1109 snmp6      Snmp data (IPv6)                                      
1110..............................................................................
1111
1112
1113Table 1-9: Network info in /proc/net
1114..............................................................................
1115 File          Content                                                         
1116 arp           Kernel  ARP table                                               
1117 dev           network devices with statistics                                 
1118 dev_mcast     the Layer2 multicast groups a device is listening too
1119               (interface index, label, number of references, number of bound
1120               addresses). 
1121 dev_stat      network device status                                           
1122 ip_fwchains   Firewall chain linkage                                          
1123 ip_fwnames    Firewall chain names                                            
1124 ip_masq       Directory containing the masquerading tables                    
1125 ip_masquerade Major masquerading table                                        
1126 netstat       Network statistics                                              
1127 raw           raw device statistics                                           
1128 route         Kernel routing table                                            
1129 rpc           Directory containing rpc info                                   
1130 rt_cache      Routing cache                                                   
1131 snmp          SNMP data                                                       
1132 sockstat      Socket statistics                                               
1133 tcp           TCP  sockets                                                    
1134 udp           UDP sockets                                                     
1135 unix          UNIX domain sockets                                             
1136 wireless      Wireless interface data (Wavelan etc)                           
1137 igmp          IP multicast addresses, which this host joined                  
1138 psched        Global packet scheduler parameters.                             
1139 netlink       List of PF_NETLINK sockets                                      
1140 ip_mr_vifs    List of multicast virtual interfaces                            
1141 ip_mr_cache   List of multicast routing cache                                 
1142..............................................................................
1143
1144You can  use  this  information  to see which network devices are available in
1145your system and how much traffic was routed over those devices:
1146
1147  > cat /proc/net/dev 
1148  Inter-|Receive                                                   |[... 
1149   face |bytes    packets errs drop fifo frame compressed multicast|[... 
1150      lo:  908188   5596     0    0    0     0          0         0 [...         
1151    ppp0:15475140  20721   410    0    0   410          0         0 [...  
1152    eth0:  614530   7085     0    0    0     0          0         1 [... 
1153   
1154  ...] Transmit 
1155  ...] bytes    packets errs drop fifo colls carrier compressed 
1156  ...]  908188     5596    0    0    0     0       0          0 
1157  ...] 1375103    17405    0    0    0     0       0          0 
1158  ...] 1703981     5535    0    0    0     3       0          0 
1159
1160In addition, each Channel Bond interface has its own directory.  For
1161example, the bond0 device will have a directory called /proc/net/bond0/.
1162It will contain information that is specific to that bond, such as the
1163current slaves of the bond, the link status of the slaves, and how
1164many times the slaves link has failed.
1165
11661.5 SCSI info
1167-------------
1168
1169If you  have  a  SCSI  host adapter in your system, you'll find a subdirectory
1170named after  the driver for this adapter in /proc/scsi. You'll also see a list
1171of all recognized SCSI devices in /proc/scsi:
1172
1173  >cat /proc/scsi/scsi 
1174  Attached devices: 
1175  Host: scsi0 Channel: 00 Id: 00 Lun: 00 
1176    Vendor: IBM      Model: DGHS09U          Rev: 03E0 
1177    Type:   Direct-Access                    ANSI SCSI revision: 03 
1178  Host: scsi0 Channel: 00 Id: 06 Lun: 00 
1179    Vendor: PIONEER  Model: CD-ROM DR-U06S   Rev: 1.04 
1180    Type:   CD-ROM                           ANSI SCSI revision: 02 
1181
1182
1183The directory  named  after  the driver has one file for each adapter found in
1184the system.  These  files  contain information about the controller, including
1185the used  IRQ  and  the  IO  address range. The amount of information shown is
1186dependent on  the adapter you use. The example shows the output for an Adaptec
1187AHA-2940 SCSI adapter:
1188
1189  > cat /proc/scsi/aic7xxx/0 
1190   
1191  Adaptec AIC7xxx driver version: 5.1.19/3.2.4 
1192  Compile Options: 
1193    TCQ Enabled By Default : Disabled 
1194    AIC7XXX_PROC_STATS     : Disabled 
1195    AIC7XXX_RESET_DELAY    : 5 
1196  Adapter Configuration: 
1197             SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter 
1198                             Ultra Wide Controller 
1199      PCI MMAPed I/O Base: 0xeb001000 
1200   Adapter SEEPROM Config: SEEPROM found and used. 
1201        Adaptec SCSI BIOS: Enabled 
1202                      IRQ: 10 
1203                     SCBs: Active 0, Max Active 2, 
1204                           Allocated 15, HW 16, Page 255 
1205               Interrupts: 160328 
1206        BIOS Control Word: 0x18b6 
1207     Adapter Control Word: 0x005b 
1208     Extended Translation: Enabled 
1209  Disconnect Enable Flags: 0xffff 
1210       Ultra Enable Flags: 0x0001 
1211   Tag Queue Enable Flags: 0x0000 
1212  Ordered Queue Tag Flags: 0x0000 
1213  Default Tag Queue Depth: 8 
1214      Tagged Queue By Device array for aic7xxx host instance 0: 
1215        {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255} 
1216      Actual queue depth per device for aic7xxx host instance 0: 
1217        {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1} 
1218  Statistics: 
1219  (scsi0:0:0:0) 
1220    Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8 
1221    Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0) 
1222    Total transfers 160151 (74577 reads and 85574 writes) 
1223  (scsi0:0:6:0) 
1224    Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15 
1225    Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0) 
1226    Total transfers 0 (0 reads and 0 writes) 
1227
1228
12291.6 Parallel port info in /proc/parport
1230---------------------------------------
1231
1232The directory  /proc/parport  contains information about the parallel ports of
1233your system.  It  has  one  subdirectory  for  each port, named after the port
1234number (0,1,2,...).
1235
1236These directories contain the four files shown in Table 1-10.
1237
1238
1239Table 1-10: Files in /proc/parport
1240..............................................................................
1241 File      Content                                                             
1242 autoprobe Any IEEE-1284 device ID information that has been acquired.         
1243 devices   list of the device drivers using that port. A + will appear by the
1244           name of the device currently using the port (it might not appear
1245           against any). 
1246 hardware  Parallel port's base address, IRQ line and DMA channel.             
1247 irq       IRQ that parport is using for that port. This is in a separate
1248           file to allow you to alter it by writing a new value in (IRQ
1249           number or none). 
1250..............................................................................
1251
12521.7 TTY info in /proc/tty
1253-------------------------
1254
1255Information about  the  available  and actually used tty's can be found in the
1256directory /proc/tty.You'll  find  entries  for drivers and line disciplines in
1257this directory, as shown in Table 1-11.
1258
1259
1260Table 1-11: Files in /proc/tty
1261..............................................................................
1262 File          Content                                        
1263 drivers       list of drivers and their usage                
1264 ldiscs        registered line disciplines                    
1265 driver/serial usage statistic and status of single tty lines 
1266..............................................................................
1267
1268To see  which  tty's  are  currently in use, you can simply look into the file
1269/proc/tty/drivers:
1270
1271  > cat /proc/tty/drivers 
1272  pty_slave            /dev/pts      136   0-255 pty:slave 
1273  pty_master           /dev/ptm      128   0-255 pty:master 
1274  pty_slave            /dev/ttyp       3   0-255 pty:slave 
1275  pty_master           /dev/pty        2   0-255 pty:master 
1276  serial               /dev/cua        5   64-67 serial:callout 
1277  serial               /dev/ttyS       4   64-67 serial 
1278  /dev/tty0            /dev/tty0       4       0 system:vtmaster 
1279  /dev/ptmx            /dev/ptmx       5       2 system 
1280  /dev/console         /dev/console    5       1 system:console 
1281  /dev/tty             /dev/tty        5       0 system:/dev/tty 
1282  unknown              /dev/tty        4    1-63 console 
1283
1284
12851.8 Miscellaneous kernel statistics in /proc/stat
1286-------------------------------------------------
1287
1288Various pieces   of  information about  kernel activity  are  available in the
1289/proc/stat file.  All  of  the numbers reported  in  this file are  aggregates
1290since the system first booted.  For a quick look, simply cat the file:
1291
1292  > cat /proc/stat
1293  cpu  2255 34 2290 22625563 6290 127 456 0 0 0
1294  cpu0 1132 34 1441 11311718 3675 127 438 0 0 0
1295  cpu1 1123 0 849 11313845 2614 0 18 0 0 0
1296  intr 114930548 113199788 3 0 5 263 0 4 [... lots more numbers ...]
1297  ctxt 1990473
1298  btime 1062191376
1299  processes 2915
1300  procs_running 1
1301  procs_blocked 0
1302  softirq 183433 0 21755 12 39 1137 231 21459 2263
1303
1304The very first  "cpu" line aggregates the  numbers in all  of the other "cpuN"
1305lines.  These numbers identify the amount of time the CPU has spent performing
1306different kinds of work.  Time units are in USER_HZ (typically hundredths of a
1307second).  The meanings of the columns are as follows, from left to right:
1308
1309- user: normal processes executing in user mode
1310- nice: niced processes executing in user mode
1311- system: processes executing in kernel mode
1312- idle: twiddling thumbs
1313- iowait: waiting for I/O to complete
1314- irq: servicing interrupts
1315- softirq: servicing softirqs
1316- steal: involuntary wait
1317- guest: running a normal guest
1318- guest_nice: running a niced guest
1319
1320The "intr" line gives counts of interrupts  serviced since boot time, for each
1321of the  possible system interrupts.   The first  column  is the  total of  all
1322interrupts serviced  including  unnumbered  architecture specific  interrupts;
1323each  subsequent column is the  total for that particular numbered interrupt.
1324Unnumbered interrupts are not shown, only summed into the total.
1325
1326The "ctxt" line gives the total number of context switches across all CPUs.
1327
1328The "btime" line gives  the time at which the  system booted, in seconds since
1329the Unix epoch.
1330
1331The "processes" line gives the number  of processes and threads created, which
1332includes (but  is not limited  to) those  created by  calls to the  fork() and
1333clone() system calls.
1334
1335The "procs_running" line gives the total number of threads that are
1336running or ready to run (i.e., the total number of runnable threads).
1337
1338The   "procs_blocked" line gives  the  number of  processes currently blocked,
1339waiting for I/O to complete.
1340
1341The "softirq" line gives counts of softirqs serviced since boot time, for each
1342of the possible system softirqs. The first column is the total of all
1343softirqs serviced; each subsequent column is the total for that particular
1344softirq.
1345
1346
13471.9 Ext4 file system parameters
1348-------------------------------
1349
1350Information about mounted ext4 file systems can be found in
1351/proc/fs/ext4.  Each mounted filesystem will have a directory in
1352/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or
1353/proc/fs/ext4/dm-0).   The files in each per-device directory are shown
1354in Table 1-12, below.
1355
1356Table 1-12: Files in /proc/fs/ext4/<devname>
1357..............................................................................
1358 File            Content                                        
1359 mb_groups       details of multiblock allocator buddy cache of free blocks
1360..............................................................................
1361
13622.0 /proc/consoles
1363------------------
1364Shows registered system console lines.
1365
1366To see which character device lines are currently used for the system console
1367/dev/console, you may simply look into the file /proc/consoles:
1368
1369  > cat /proc/consoles
1370  tty0                 -WU (ECp)       4:7
1371  ttyS0                -W- (Ep)        4:64
1372
1373The columns are:
1374
1375  device               name of the device
1376  operations           R = can do read operations
1377                       W = can do write operations
1378                       U = can do unblank
1379  flags                E = it is enabled
1380                       C = it is preferred console
1381                       B = it is primary boot console
1382                       p = it is used for printk buffer
1383                       b = it is not a TTY but a Braille device
1384                       a = it is safe to use when cpu is offline
1385  major:minor          major and minor number of the device separated by a colon
1386
1387------------------------------------------------------------------------------
1388Summary
1389------------------------------------------------------------------------------
1390The /proc file system serves information about the running system. It not only
1391allows access to process data but also allows you to request the kernel status
1392by reading files in the hierarchy.
1393
1394The directory  structure  of /proc reflects the types of information and makes
1395it easy, if not obvious, where to look for specific data.
1396------------------------------------------------------------------------------
1397
1398------------------------------------------------------------------------------
1399CHAPTER 2: MODIFYING SYSTEM PARAMETERS
1400------------------------------------------------------------------------------
1401
1402------------------------------------------------------------------------------
1403In This Chapter
1404------------------------------------------------------------------------------
1405* Modifying kernel parameters by writing into files found in /proc/sys
1406* Exploring the files which modify certain parameters
1407* Review of the /proc/sys file tree
1408------------------------------------------------------------------------------
1409
1410
1411A very  interesting part of /proc is the directory /proc/sys. This is not only
1412a source  of  information,  it also allows you to change parameters within the
1413kernel. Be  very  careful  when attempting this. You can optimize your system,
1414but you  can  also  cause  it  to  crash.  Never  alter kernel parameters on a
1415production system.  Set  up  a  development machine and test to make sure that
1416everything works  the  way  you want it to. You may have no alternative but to
1417reboot the machine once an error has been made.
1418
1419To change  a  value,  simply  echo  the new value into the file. An example is
1420given below  in the section on the file system data. You need to be root to do
1421this. You  can  create  your  own  boot script to perform this every time your
1422system boots.
1423
1424The files  in /proc/sys can be used to fine tune and monitor miscellaneous and
1425general things  in  the operation of the Linux kernel. Since some of the files
1426can inadvertently  disrupt  your  system,  it  is  advisable  to  read  both
1427documentation and  source  before actually making adjustments. In any case, be
1428very careful  when  writing  to  any  of these files. The entries in /proc may
1429change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt
1430review the kernel documentation in the directory /usr/src/linux/Documentation.
1431This chapter  is  heavily  based  on the documentation included in the pre 2.2
1432kernels, and became part of it in version 2.2.1 of the Linux kernel.
1433
1434Please see: Documentation/sysctl/ directory for descriptions of these
1435entries.
1436
1437------------------------------------------------------------------------------
1438Summary
1439------------------------------------------------------------------------------
1440Certain aspects  of  kernel  behavior  can be modified at runtime, without the
1441need to  recompile  the kernel, or even to reboot the system. The files in the
1442/proc/sys tree  can  not only be read, but also modified. You can use the echo
1443command to write value into these files, thereby changing the default settings
1444of the kernel.
1445------------------------------------------------------------------------------
1446
1447------------------------------------------------------------------------------
1448CHAPTER 3: PER-PROCESS PARAMETERS
1449------------------------------------------------------------------------------
1450
14513.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score
1452--------------------------------------------------------------------------------
1453
1454These file can be used to adjust the badness heuristic used to select which
1455process gets killed in out of memory conditions.
1456
1457The badness heuristic assigns a value to each candidate task ranging from 0
1458(never kill) to 1000 (always kill) to determine which process is targeted.  The
1459units are roughly a proportion along that range of allowed memory the process
1460may allocate from based on an estimation of its current memory and swap use.
1461For example, if a task is using all allowed memory, its badness score will be
14621000.  If it is using half of its allowed memory, its score will be 500.
1463
1464There is an additional factor included in the badness score: the current memory
1465and swap usage is discounted by 3% for root processes.
1466
1467The amount of "allowed" memory depends on the context in which the oom killer
1468was called.  If it is due to the memory assigned to the allocating task's cpuset
1469being exhausted, the allowed memory represents the set of mems assigned to that
1470cpuset.  If it is due to a mempolicy's node(s) being exhausted, the allowed
1471memory represents the set of mempolicy nodes.  If it is due to a memory
1472limit (or swap limit) being reached, the allowed memory is that configured
1473limit.  Finally, if it is due to the entire system being out of memory, the
1474allowed memory represents all allocatable resources.
1475
1476The value of /proc/<pid>/oom_score_adj is added to the badness score before it
1477is used to determine which task to kill.  Acceptable values range from -1000
1478(OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX).  This allows userspace to
1479polarize the preference for oom killing either by always preferring a certain
1480task or completely disabling it.  The lowest possible value, -1000, is
1481equivalent to disabling oom killing entirely for that task since it will always
1482report a badness score of 0.
1483
1484Consequently, it is very simple for userspace to define the amount of memory to
1485consider for each task.  Setting a /proc/<pid>/oom_score_adj value of +500, for
1486example, is roughly equivalent to allowing the remainder of tasks sharing the
1487same system, cpuset, mempolicy, or memory controller resources to use at least
148850% more memory.  A value of -500, on the other hand, would be roughly
1489equivalent to discounting 50% of the task's allowed memory from being considered
1490as scoring against the task.
1491
1492For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also
1493be used to tune the badness score.  Its acceptable values range from -16
1494(OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17
1495(OOM_DISABLE) to disable oom killing entirely for that task.  Its value is
1496scaled linearly with /proc/<pid>/oom_score_adj.
1497
1498The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last
1499value set by a CAP_SYS_RESOURCE process. To reduce the value any lower
1500requires CAP_SYS_RESOURCE.
1501
1502Caveat: when a parent task is selected, the oom killer will sacrifice any first
1503generation children with separate address spaces instead, if possible.  This
1504avoids servers and important system daemons from being killed and loses the
1505minimal amount of work.
1506
1507
15083.2 /proc/<pid>/oom_score - Display current oom-killer score
1509-------------------------------------------------------------
1510
1511This file can be used to check the current score used by the oom-killer is for
1512any given <pid>. Use it together with /proc/<pid>/oom_score_adj to tune which
1513process should be killed in an out-of-memory situation.
1514
1515
15163.3  /proc/<pid>/io - Display the IO accounting fields
1517-------------------------------------------------------
1518
1519This file contains IO statistics for each running process
1520
1521Example
1522-------
1523
1524test:/tmp # dd if=/dev/zero of=/tmp/test.dat &
1525[1] 3828
1526
1527test:/tmp # cat /proc/3828/io
1528rchar: 323934931
1529wchar: 323929600
1530syscr: 632687
1531syscw: 632675
1532read_bytes: 0
1533write_bytes: 323932160
1534cancelled_write_bytes: 0
1535
1536
1537Description
1538-----------
1539
1540rchar
1541-----
1542
1543I/O counter: chars read
1544The number of bytes which this task has caused to be read from storage. This
1545is simply the sum of bytes which this process passed to read() and pread().
1546It includes things like tty IO and it is unaffected by whether or not actual
1547physical disk IO was required (the read might have been satisfied from
1548pagecache)
1549
1550
1551wchar
1552-----
1553
1554I/O counter: chars written
1555The number of bytes which this task has caused, or shall cause to be written
1556to disk. Similar caveats apply here as with rchar.
1557
1558
1559syscr
1560-----
1561
1562I/O counter: read syscalls
1563Attempt to count the number of read I/O operations, i.e. syscalls like read()
1564and pread().
1565
1566
1567syscw
1568-----
1569
1570I/O counter: write syscalls
1571Attempt to count the number of write I/O operations, i.e. syscalls like
1572write() and pwrite().
1573
1574
1575read_bytes
1576----------
1577
1578I/O counter: bytes read
1579Attempt to count the number of bytes which this process really did cause to
1580be fetched from the storage layer. Done at the submit_bio() level, so it is
1581accurate for block-backed filesystems. <please add status regarding NFS and
1582CIFS at a later time>
1583
1584
1585write_bytes
1586-----------
1587
1588I/O counter: bytes written
1589Attempt to count the number of bytes which this process caused to be sent to
1590the storage layer. This is done at page-dirtying time.
1591
1592
1593cancelled_write_bytes
1594---------------------
1595
1596The big inaccuracy here is truncate. If a process writes 1MB to a file and
1597then deletes the file, it will in fact perform no writeout. But it will have
1598been accounted as having caused 1MB of write.
1599In other words: The number of bytes which this process caused to not happen,
1600by truncating pagecache. A task can cause "negative" IO too. If this task
1601truncates some dirty pagecache, some IO which another task has been accounted
1602for (in its write_bytes) will not be happening. We _could_ just subtract that
1603from the truncating task's write_bytes, but there is information loss in doing
1604that.
1605
1606
1607Note
1608----
1609
1610At its current implementation state, this is a bit racy on 32-bit machines: if
1611process A reads process B's /proc/pid/io while process B is updating one of
1612those 64-bit counters, process A could see an intermediate result.
1613
1614
1615More information about this can be found within the taskstats documentation in
1616Documentation/accounting.
1617
16183.4 /proc/<pid>/coredump_filter - Core dump filtering settings
1619---------------------------------------------------------------
1620When a process is dumped, all anonymous memory is written to a core file as
1621long as the size of the core file isn't limited. But sometimes we don't want
1622to dump some memory segments, for example, huge shared memory or DAX.
1623Conversely, sometimes we want to save file-backed memory segments into a core
1624file, not only the individual files.
1625
1626/proc/<pid>/coredump_filter allows you to customize which memory segments
1627will be dumped when the <pid> process is dumped. coredump_filter is a bitmask
1628of memory types. If a bit of the bitmask is set, memory segments of the
1629corresponding memory type are dumped, otherwise they are not dumped.
1630
1631The following 9 memory types are supported:
1632  - (bit 0) anonymous private memory
1633  - (bit 1) anonymous shared memory
1634  - (bit 2) file-backed private memory
1635  - (bit 3) file-backed shared memory
1636  - (bit 4) ELF header pages in file-backed private memory areas (it is
1637            effective only if the bit 2 is cleared)
1638  - (bit 5) hugetlb private memory
1639  - (bit 6) hugetlb shared memory
1640  - (bit 7) DAX private memory
1641  - (bit 8) DAX shared memory
1642
1643  Note that MMIO pages such as frame buffer are never dumped and vDSO pages
1644  are always dumped regardless of the bitmask status.
1645
1646  Note that bits 0-4 don't affect hugetlb or DAX memory. hugetlb memory is
1647  only affected by bit 5-6, and DAX is only affected by bits 7-8.
1648
1649The default value of coredump_filter is 0x33; this means all anonymous memory
1650segments, ELF header pages and hugetlb private memory are dumped.
1651
1652If you don't want to dump all shared memory segments attached to pid 1234,
1653write 0x31 to the process's proc file.
1654
1655  $ echo 0x31 > /proc/1234/coredump_filter
1656
1657When a new process is created, the process inherits the bitmask status from its
1658parent. It is useful to set up coredump_filter before the program runs.
1659For example:
1660
1661  $ echo 0x7 > /proc/self/coredump_filter
1662  $ ./some_program
1663
16643.5     /proc/<pid>/mountinfo - Information about mounts
1665--------------------------------------------------------
1666
1667This file contains lines of the form:
1668
166936 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue
1670(1)(2)(3)   (4)   (5)      (6)      (7)   (8) (9)   (10)         (11)
1671
1672(1) mount ID:  unique identifier of the mount (may be reused after umount)
1673(2) parent ID:  ID of parent (or of self for the top of the mount tree)
1674(3) major:minor:  value of st_dev for files on filesystem
1675(4) root:  root of the mount within the filesystem
1676(5) mount point:  mount point relative to the process's root
1677(6) mount options:  per mount options
1678(7) optional fields:  zero or more fields of the form "tag[:value]"
1679(8) separator:  marks the end of the optional fields
1680(9) filesystem type:  name of filesystem of the form "type[.subtype]"
1681(10) mount source:  filesystem specific information or "none"
1682(11) super options:  per super block options
1683
1684Parsers should ignore all unrecognised optional fields.  Currently the
1685possible optional fields are:
1686
1687shared:X  mount is shared in peer group X
1688master:X  mount is slave to peer group X
1689propagate_from:X  mount is slave and receives propagation from peer group X (*)
1690unbindable  mount is unbindable
1691
1692(*) X is the closest dominant peer group under the process's root.  If
1693X is the immediate master of the mount, or if there's no dominant peer
1694group under the same root, then only the "master:X" field is present
1695and not the "propagate_from:X" field.
1696
1697For more information on mount propagation see:
1698
1699  Documentation/filesystems/sharedsubtree.txt
1700
1701
17023.6     /proc/<pid>/comm  & /proc/<pid>/task/<tid>/comm
1703--------------------------------------------------------
1704These files provide a method to access a tasks comm value. It also allows for
1705a task to set its own or one of its thread siblings comm value. The comm value
1706is limited in size compared to the cmdline value, so writing anything longer
1707then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated
1708comm value.
1709
1710
17113.7     /proc/<pid>/task/<tid>/children - Information about task children
1712-------------------------------------------------------------------------
1713This file provides a fast way to retrieve first level children pids
1714of a task pointed by <pid>/<tid> pair. The format is a space separated
1715stream of pids.
1716
1717Note the "first level" here -- if a child has own children they will
1718not be listed here, one needs to read /proc/<children-pid>/task/<tid>/children
1719to obtain the descendants.
1720
1721Since this interface is intended to be fast and cheap it doesn't
1722guarantee to provide precise results and some children might be
1723skipped, especially if they've exited right after we printed their
1724pids, so one need to either stop or freeze processes being inspected
1725if precise results are needed.
1726
1727
17283.8     /proc/<pid>/fdinfo/<fd> - Information about opened file
1729---------------------------------------------------------------
1730This file provides information associated with an opened file. The regular
1731files have at least three fields -- 'pos', 'flags' and mnt_id. The 'pos'
1732represents the current offset of the opened file in decimal form [see lseek(2)
1733for details], 'flags' denotes the octal O_xxx mask the file has been
1734created with [see open(2) for details] and 'mnt_id' represents mount ID of
1735the file system containing the opened file [see 3.5 /proc/<pid>/mountinfo
1736for details].
1737
1738A typical output is
1739
1740        pos:    0
1741        flags:  0100002
1742        mnt_id: 19
1743
1744All locks associated with a file descriptor are shown in its fdinfo too.
1745
1746lock:       1: FLOCK  ADVISORY  WRITE 359 00:13:11691 0 EOF
1747
1748The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags
1749pair provide additional information particular to the objects they represent.
1750
1751        Eventfd files
1752        ~~~~~~~~~~~~~
1753        pos:    0
1754        flags:  04002
1755        mnt_id: 9
1756        eventfd-count:  5a
1757
1758        where 'eventfd-count' is hex value of a counter.
1759
1760        Signalfd files
1761        ~~~~~~~~~~~~~~
1762        pos:    0
1763        flags:  04002
1764        mnt_id: 9
1765        sigmask:        0000000000000200
1766
1767        where 'sigmask' is hex value of the signal mask associated
1768        with a file.
1769
1770        Epoll files
1771        ~~~~~~~~~~~
1772        pos:    0
1773        flags:  02
1774        mnt_id: 9
1775        tfd:        5 events:       1d data: ffffffffffffffff
1776
1777        where 'tfd' is a target file descriptor number in decimal form,
1778        'events' is events mask being watched and the 'data' is data
1779        associated with a target [see epoll(7) for more details].
1780
1781        Fsnotify files
1782        ~~~~~~~~~~~~~~
1783        For inotify files the format is the following
1784
1785        pos:    0
1786        flags:  02000000
1787        inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d
1788
1789        where 'wd' is a watch descriptor in decimal form, ie a target file
1790        descriptor number, 'ino' and 'sdev' are inode and device where the
1791        target file resides and the 'mask' is the mask of events, all in hex
1792        form [see inotify(7) for more details].
1793
1794        If the kernel was built with exportfs support, the path to the target
1795        file is encoded as a file handle.  The file handle is provided by three
1796        fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex
1797        format.
1798
1799        If the kernel is built without exportfs support the file handle won't be
1800        printed out.
1801
1802        If there is no inotify mark attached yet the 'inotify' line will be omitted.
1803
1804        For fanotify files the format is
1805
1806        pos:    0
1807        flags:  02
1808        mnt_id: 9
1809        fanotify flags:10 event-flags:0
1810        fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003
1811        fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4
1812
1813        where fanotify 'flags' and 'event-flags' are values used in fanotify_init
1814        call, 'mnt_id' is the mount point identifier, 'mflags' is the value of
1815        flags associated with mark which are tracked separately from events
1816        mask. 'ino', 'sdev' are target inode and device, 'mask' is the events
1817        mask and 'ignored_mask' is the mask of events which are to be ignored.
1818        All in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask'
1819        does provide information about flags and mask used in fanotify_mark
1820        call [see fsnotify manpage for details].
1821
1822        While the first three lines are mandatory and always printed, the rest is
1823        optional and may be omitted if no marks created yet.
1824
1825        Timerfd files
1826        ~~~~~~~~~~~~~
1827
1828        pos:    0
1829        flags:  02
1830        mnt_id: 9
1831        clockid: 0
1832        ticks: 0
1833        settime flags: 01
1834        it_value: (0, 49406829)
1835        it_interval: (1, 0)
1836
1837        where 'clockid' is the clock type and 'ticks' is the number of the timer expirations
1838        that have occurred [see timerfd_create(2) for details]. 'settime flags' are
1839        flags in octal form been used to setup the timer [see timerfd_settime(2) for
1840        details]. 'it_value' is remaining time until the timer exiration.
1841        'it_interval' is the interval for the timer. Note the timer might be set up
1842        with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value'
1843        still exhibits timer's remaining time.
1844
18453.9     /proc/<pid>/map_files - Information about memory mapped files
1846---------------------------------------------------------------------
1847This directory contains symbolic links which represent memory mapped files
1848the process is maintaining.  Example output:
1849
1850     | lr-------- 1 root root 64 Jan 27 11:24 333c600000-333c620000 -> /usr/lib64/ld-2.18.so
1851     | lr-------- 1 root root 64 Jan 27 11:24 333c81f000-333c820000 -> /usr/lib64/ld-2.18.so
1852     | lr-------- 1 root root 64 Jan 27 11:24 333c820000-333c821000 -> /usr/lib64/ld-2.18.so
1853     | ...
1854     | lr-------- 1 root root 64 Jan 27 11:24 35d0421000-35d0422000 -> /usr/lib64/libselinux.so.1
1855     | lr-------- 1 root root 64 Jan 27 11:24 400000-41a000 -> /usr/bin/ls
1856
1857The name of a link represents the virtual memory bounds of a mapping, i.e.
1858vm_area_struct::vm_start-vm_area_struct::vm_end.
1859
1860The main purpose of the map_files is to retrieve a set of memory mapped
1861files in a fast way instead of parsing /proc/<pid>/maps or
1862/proc/<pid>/smaps, both of which contain many more records.  At the same
1863time one can open(2) mappings from the listings of two processes and
1864comparing their inode numbers to figure out which anonymous memory areas
1865are actually shared.
1866
18673.10    /proc/<pid>/timerslack_ns - Task timerslack value
1868---------------------------------------------------------
1869This file provides the value of the task's timerslack value in nanoseconds.
1870This value specifies a amount of time that normal timers may be deferred
1871in order to coalesce timers and avoid unnecessary wakeups.
1872
1873This allows a task's interactivity vs power consumption trade off to be
1874adjusted.
1875
1876Writing 0 to the file will set the tasks timerslack to the default value.
1877
1878Valid values are from 0 - ULLONG_MAX
1879
1880An application setting the value must have PTRACE_MODE_ATTACH_FSCREDS level
1881permissions on the task specified to change its timerslack_ns value.
1882
1883
1884------------------------------------------------------------------------------
1885Configuring procfs
1886------------------------------------------------------------------------------
1887
18884.1     Mount options
1889---------------------
1890
1891The following mount options are supported:
1892
1893        hidepid=        Set /proc/<pid>/ access mode.
1894        gid=            Set the group authorized to learn processes information.
1895
1896hidepid=0 means classic mode - everybody may access all /proc/<pid>/ directories
1897(default).
1898
1899hidepid=1 means users may not access any /proc/<pid>/ directories but their
1900own.  Sensitive files like cmdline, sched*, status are now protected against
1901other users.  This makes it impossible to learn whether any user runs
1902specific program (given the program doesn't reveal itself by its behaviour).
1903As an additional bonus, as /proc/<pid>/cmdline is unaccessible for other users,
1904poorly written programs passing sensitive information via program arguments are
1905now protected against local eavesdroppers.
1906
1907hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be fully invisible to other
1908users.  It doesn't mean that it hides a fact whether a process with a specific
1909pid value exists (it can be learned by other means, e.g. by "kill -0 $PID"),
1910but it hides process' uid and gid, which may be learned by stat()'ing
1911/proc/<pid>/ otherwise.  It greatly complicates an intruder's task of gathering
1912information about running processes, whether some daemon runs with elevated
1913privileges, whether other user runs some sensitive program, whether other users
1914run any program at all, etc.
1915
1916gid= defines a group authorized to learn processes information otherwise
1917prohibited by hidepid=.  If you use some daemon like identd which needs to learn
1918information about processes information, just add identd to this group.
1919
lxr.linux.no kindly hosted by Redpill Linpro AS, provider of Linux consulting and operations services since 1995.