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
  46  4     Configuring procfs
  47  4.1   Mount options
  48
  49------------------------------------------------------------------------------
  50Preface
  51------------------------------------------------------------------------------
  52
  530.1 Introduction/Credits
  54------------------------
  55
  56This documentation is  part of a soon (or  so we hope) to be  released book on
  57the SuSE  Linux distribution. As  there is  no complete documentation  for the
  58/proc file system and we've used  many freely available sources to write these
  59chapters, it  seems only fair  to give the work  back to the  Linux community.
  60This work is  based on the 2.2.*  kernel version and the  upcoming 2.4.*. I'm
  61afraid it's still far from complete, but we  hope it will be useful. As far as
  62we know, it is the first 'all-in-one' document about the /proc file system. It
  63is focused  on the Intel  x86 hardware,  so if you  are looking for  PPC, ARM,
  64SPARC, AXP, etc., features, you probably  won't find what you are looking for.
  65It also only covers IPv4 networking, not IPv6 nor other protocols - sorry. But
  66additions and patches  are welcome and will  be added to this  document if you
  67mail them to Bodo.
  68
  69We'd like  to  thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of
  70other people for help compiling this documentation. We'd also like to extend a
  71special thank  you to Andi Kleen for documentation, which we relied on heavily
  72to create  this  document,  as well as the additional information he provided.
  73Thanks to  everybody  else  who contributed source or docs to the Linux kernel
  74and helped create a great piece of software... :)
  75
  76If you  have  any comments, corrections or additions, please don't hesitate to
  77contact Bodo  Bauer  at  bb@ricochet.net.  We'll  be happy to add them to this
  78document.
  79
  80The   latest   version    of   this   document   is    available   online   at
  81http://tldp.org/LDP/Linux-Filesystem-Hierarchy/html/proc.html
  82
  83If  the above  direction does  not works  for you,  you could  try the  kernel
  84mailing  list  at  linux-kernel@vger.kernel.org  and/or try  to  reach  me  at
  85comandante@zaralinux.com.
  86
  870.2 Legal Stuff
  88---------------
  89
  90We don't  guarantee  the  correctness  of this document, and if you come to us
  91complaining about  how  you  screwed  up  your  system  because  of  incorrect
  92documentation, we won't feel responsible...
  93
  94------------------------------------------------------------------------------
  95CHAPTER 1: COLLECTING SYSTEM INFORMATION
  96------------------------------------------------------------------------------
  97
  98------------------------------------------------------------------------------
  99In This Chapter
 100------------------------------------------------------------------------------
 101* Investigating  the  properties  of  the  pseudo  file  system  /proc and its
 102  ability to provide information on the running Linux system
 103* Examining /proc's structure
 104* Uncovering  various  information  about the kernel and the processes running
 105  on the system
 106------------------------------------------------------------------------------
 107
 108
 109The proc  file  system acts as an interface to internal data structures in the
 110kernel. It  can  be  used to obtain information about the system and to change
 111certain kernel parameters at runtime (sysctl).
 112
 113First, we'll  take  a  look  at the read-only parts of /proc. In Chapter 2, we
 114show you how you can use /proc/sys to change settings.
 115
 1161.1 Process-Specific Subdirectories
 117-----------------------------------
 118
 119The directory  /proc  contains  (among other things) one subdirectory for each
 120process running on the system, which is named after the process ID (PID).
 121
 122The link  self  points  to  the  process reading the file system. Each process
 123subdirectory has the entries listed in Table 1-1.
 124
 125
 126Table 1-1: Process specific entries in /proc
 127..............................................................................
 128 File           Content
 129 clear_refs     Clears page referenced bits shown in smaps output
 130 cmdline        Command line arguments
 131 cpu            Current and last cpu in which it was executed   (2.4)(smp)
 132 cwd            Link to the current working directory
 133 environ        Values of environment variables
 134 exe            Link to the executable of this process
 135 fd             Directory, which contains all file descriptors
 136 maps           Memory maps to executables and library files    (2.4)
 137 mem            Memory held by this process
 138 root           Link to the root directory of this process
 139 stat           Process status
 140 statm          Process memory status information
 141 status         Process status in human readable form
 142 wchan          If CONFIG_KALLSYMS is set, a pre-decoded wchan
 143 pagemap        Page table
 144 stack          Report full stack trace, enable via CONFIG_STACKTRACE
 145 smaps          a extension based on maps, showing the memory consumption of
 146                each mapping and flags associated with it
 147..............................................................................
 148
 149For example, to get the status information of a process, all you have to do is
 150read the file /proc/PID/status:
 151
 152  >cat /proc/self/status
 153  Name:   cat
 154  State:  R (running)
 155  Tgid:   5452
 156  Pid:    5452
 157  PPid:   743
 158  TracerPid:      0                                             (2.4)
 159  Uid:    501     501     501     501
 160  Gid:    100     100     100     100
 161  FDSize: 256
 162  Groups: 100 14 16
 163  VmPeak:     5004 kB
 164  VmSize:     5004 kB
 165  VmLck:         0 kB
 166  VmHWM:       476 kB
 167  VmRSS:       476 kB
 168  VmData:      156 kB
 169  VmStk:        88 kB
 170  VmExe:        68 kB
 171  VmLib:      1412 kB
 172  VmPTE:        20 kb
 173  VmSwap:        0 kB
 174  Threads:        1
 175  SigQ:   0/28578
 176  SigPnd: 0000000000000000
 177  ShdPnd: 0000000000000000
 178  SigBlk: 0000000000000000
 179  SigIgn: 0000000000000000
 180  SigCgt: 0000000000000000
 181  CapInh: 00000000fffffeff
 182  CapPrm: 0000000000000000
 183  CapEff: 0000000000000000
 184  CapBnd: ffffffffffffffff
 185  Seccomp:        0
 186  voluntary_ctxt_switches:        0
 187  nonvoluntary_ctxt_switches:     1
 188
 189This shows you nearly the same information you would get if you viewed it with
 190the ps  command.  In  fact,  ps  uses  the  proc  file  system  to  obtain its
 191information.  But you get a more detailed  view of the  process by reading the
 192file /proc/PID/status. It fields are described in table 1-2.
 193
 194The  statm  file  contains  more  detailed  information about the process
 195memory usage. Its seven fields are explained in Table 1-3.  The stat file
 196contains details information about the process itself.  Its fields are
 197explained in Table 1-4.
 198
 199(for SMP CONFIG users)
 200For making accounting scalable, RSS related information are handled in
 201asynchronous manner and the vaule may not be very precise. To see a precise
 202snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
 203It's slow but very precise.
 204
 205Table 1-2: Contents of the status files (as of 2.6.30-rc7)
 206..............................................................................
 207 Field                       Content
 208 Name                        filename of the executable
 209 State                       state (R is running, S is sleeping, D is sleeping
 210                             in an uninterruptible wait, Z is zombie,
 211                             T is traced or stopped)
 212 Tgid                        thread group ID
 213 Pid                         process id
 214 PPid                        process id of the parent process
 215 TracerPid                   PID of process tracing this process (0 if not)
 216 Uid                         Real, effective, saved set, and  file system UIDs
 217 Gid                         Real, effective, saved set, and  file system GIDs
 218 FDSize                      number of file descriptor slots currently allocated
 219 Groups                      supplementary group list
 220 VmPeak                      peak virtual memory size
 221 VmSize                      total program size
 222 VmLck                       locked memory size
 223 VmHWM                       peak resident set size ("high water mark")
 224 VmRSS                       size of memory portions
 225 VmData                      size of data, stack, and text segments
 226 VmStk                       size of data, stack, and text segments
 227 VmExe                       size of text segment
 228 VmLib                       size of shared library code
 229 VmPTE                       size of page table entries
 230 VmSwap                      size of swap usage (the number of referred swapents)
 231 Threads                     number of threads
 232 SigQ                        number of signals queued/max. number for queue
 233 SigPnd                      bitmap of pending signals for the thread
 234 ShdPnd                      bitmap of shared pending signals for the process
 235 SigBlk                      bitmap of blocked signals
 236 SigIgn                      bitmap of ignored signals
 237 SigCgt                      bitmap of catched signals
 238 CapInh                      bitmap of inheritable capabilities
 239 CapPrm                      bitmap of permitted capabilities
 240 CapEff                      bitmap of effective capabilities
 241 CapBnd                      bitmap of capabilities bounding set
 242 Seccomp                     seccomp mode, like prctl(PR_GET_SECCOMP, ...)
 243 Cpus_allowed                mask of CPUs on which this process may run
 244 Cpus_allowed_list           Same as previous, but in "list format"
 245 Mems_allowed                mask of memory nodes allowed to this process
 246 Mems_allowed_list           Same as previous, but in "list format"
 247 voluntary_ctxt_switches     number of voluntary context switches
 248 nonvoluntary_ctxt_switches  number of non voluntary context switches
 249..............................................................................
 250
 251Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
 252..............................................................................
 253 Field    Content
 254 size     total program size (pages)            (same as VmSize in status)
 255 resident size of memory portions (pages)       (same as VmRSS in status)
 256 shared   number of pages that are shared       (i.e. backed by a file)
 257 trs      number of pages that are 'code'       (not including libs; broken,
 258                                                        includes data segment)
 259 lrs      number of pages of library            (always 0 on 2.6)
 260 drs      number of pages of data/stack         (including libs; broken,
 261                                                        includes library text)
 262 dt       number of dirty pages                 (always 0 on 2.6)
 263..............................................................................
 264
 265
 266Table 1-4: Contents of the stat files (as of 2.6.30-rc7)
 267..............................................................................
 268 Field          Content
 269  pid           process id
 270  tcomm         filename of the executable
 271  state         state (R is running, S is sleeping, D is sleeping in an
 272                uninterruptible wait, Z is zombie, T is traced or stopped)
 273  ppid          process id of the parent process
 274  pgrp          pgrp of the process
 275  sid           session id
 276  tty_nr        tty the process uses
 277  tty_pgrp      pgrp of the tty
 278  flags         task flags
 279  min_flt       number of minor faults
 280  cmin_flt      number of minor faults with child's
 281  maj_flt       number of major faults
 282  cmaj_flt      number of major faults with child's
 283  utime         user mode jiffies
 284  stime         kernel mode jiffies
 285  cutime        user mode jiffies with child's
 286  cstime        kernel mode jiffies with child's
 287  priority      priority level
 288  nice          nice level
 289  num_threads   number of threads
 290  it_real_value (obsolete, always 0)
 291  start_time    time the process started after system boot
 292  vsize         virtual memory size
 293  rss           resident set memory size
 294  rsslim        current limit in bytes on the rss
 295  start_code    address above which program text can run
 296  end_code      address below which program text can run
 297  start_stack   address of the start of the main process stack
 298  esp           current value of ESP
 299  eip           current value of EIP
 300  pending       bitmap of pending signals
 301  blocked       bitmap of blocked signals
 302  sigign        bitmap of ignored signals
 303  sigcatch      bitmap of catched signals
 304  wchan         address where process went to sleep
 305  0             (place holder)
 306  0             (place holder)
 307  exit_signal   signal to send to parent thread on exit
 308  task_cpu      which CPU the task is scheduled on
 309  rt_priority   realtime priority
 310  policy        scheduling policy (man sched_setscheduler)
 311  blkio_ticks   time spent waiting for block IO
 312  gtime         guest time of the task in jiffies
 313  cgtime        guest time of the task children in jiffies
 314  start_data    address above which program data+bss is placed
 315  end_data      address below which program data+bss is placed
 316  start_brk     address above which program heap can be expanded with brk()
 317  arg_start     address above which program command line is placed
 318  arg_end       address below which program command line is placed
 319  env_start     address above which program environment is placed
 320  env_end       address below which program environment is placed
 321  exit_code     the thread's exit_code in the form reported by the waitpid system call
 322..............................................................................
 323
 324The /proc/PID/maps file containing the currently mapped memory regions and
 325their access permissions.
 326
 327The format is:
 328
 329address           perms offset  dev   inode      pathname
 330
 33108048000-08049000 r-xp 00000000 03:00 8312       /opt/test
 33208049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
 3330804a000-0806b000 rw-p 00000000 00:00 0          [heap]
 334a7cb1000-a7cb2000 ---p 00000000 00:00 0
 335a7cb2000-a7eb2000 rw-p 00000000 00:00 0
 336a7eb2000-a7eb3000 ---p 00000000 00:00 0
 337a7eb3000-a7ed5000 rw-p 00000000 00:00 0          [stack:1001]
 338a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
 339a8008000-a800a000 r--p 00133000 03:00 4222       /lib/libc.so.6
 340a800a000-a800b000 rw-p 00135000 03:00 4222       /lib/libc.so.6
 341a800b000-a800e000 rw-p 00000000 00:00 0
 342a800e000-a8022000 r-xp 00000000 03:00 14462      /lib/libpthread.so.0
 343a8022000-a8023000 r--p 00013000 03:00 14462      /lib/libpthread.so.0
 344a8023000-a8024000 rw-p 00014000 03:00 14462      /lib/libpthread.so.0
 345a8024000-a8027000 rw-p 00000000 00:00 0
 346a8027000-a8043000 r-xp 00000000 03:00 8317       /lib/ld-linux.so.2
 347a8043000-a8044000 r--p 0001b000 03:00 8317       /lib/ld-linux.so.2
 348a8044000-a8045000 rw-p 0001c000 03:00 8317       /lib/ld-linux.so.2
 349aff35000-aff4a000 rw-p 00000000 00:00 0          [stack]
 350ffffe000-fffff000 r-xp 00000000 00:00 0          [vdso]
 351
 352where "address" is the address space in the process that it occupies, "perms"
 353is a set of permissions:
 354
 355 r = read
 356 w = write
 357 x = execute
 358 s = shared
 359 p = private (copy on write)
 360
 361"offset" is the offset into the mapping, "dev" is the device (major:minor), and
 362"inode" is the inode  on that device.  0 indicates that  no inode is associated
 363with the memory region, as the case would be with BSS (uninitialized data).
 364The "pathname" shows the name associated file for this mapping.  If the mapping
 365is not associated with a file:
 366
 367 [heap]                   = the heap of the program
 368 [stack]                  = the stack of the main process
 369 [stack:1001]             = the stack of the thread with tid 1001
 370 [vdso]                   = the "virtual dynamic shared object",
 371                            the kernel system call handler
 372
 373 or if empty, the mapping is anonymous.
 374
 375The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint
 376of the individual tasks of a process. In this file you will see a mapping marked
 377as [stack] if that task sees it as a stack. This is a key difference from the
 378content of /proc/PID/maps, where you will see all mappings that are being used
 379as stack by all of those tasks. Hence, for the example above, the task-level
 380map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
 381
 38208048000-08049000 r-xp 00000000 03:00 8312       /opt/test
 38308049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
 3840804a000-0806b000 rw-p 00000000 00:00 0          [heap]
 385a7cb1000-a7cb2000 ---p 00000000 00:00 0
 386a7cb2000-a7eb2000 rw-p 00000000 00:00 0
 387a7eb2000-a7eb3000 ---p 00000000 00:00 0
 388a7eb3000-a7ed5000 rw-p 00000000 00:00 0          [stack]
 389a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
 390a8008000-a800a000 r--p 00133000 03:00 4222       /lib/libc.so.6
 391a800a000-a800b000 rw-p 00135000 03:00 4222       /lib/libc.so.6
 392a800b000-a800e000 rw-p 00000000 00:00 0
 393a800e000-a8022000 r-xp 00000000 03:00 14462      /lib/libpthread.so.0
 394a8022000-a8023000 r--p 00013000 03:00 14462      /lib/libpthread.so.0
 395a8023000-a8024000 rw-p 00014000 03:00 14462      /lib/libpthread.so.0
 396a8024000-a8027000 rw-p 00000000 00:00 0
 397a8027000-a8043000 r-xp 00000000 03:00 8317       /lib/ld-linux.so.2
 398a8043000-a8044000 r--p 0001b000 03:00 8317       /lib/ld-linux.so.2
 399a8044000-a8045000 rw-p 0001c000 03:00 8317       /lib/ld-linux.so.2
 400aff35000-aff4a000 rw-p 00000000 00:00 0
 401ffffe000-fffff000 r-xp 00000000 00:00 0          [vdso]
 402
 403The /proc/PID/smaps is an extension based on maps, showing the memory
 404consumption for each of the process's mappings. For each of mappings there
 405is a series of lines such as the following:
 406
 40708048000-080bc000 r-xp 00000000 03:02 13130      /bin/bash
 408Size:               1084 kB
 409Rss:                 892 kB
 410Pss:                 374 kB
 411Shared_Clean:        892 kB
 412Shared_Dirty:          0 kB
 413Private_Clean:         0 kB
 414Private_Dirty:         0 kB
 415Referenced:          892 kB
 416Anonymous:             0 kB
 417Swap:                  0 kB
 418KernelPageSize:        4 kB
 419MMUPageSize:           4 kB
 420Locked:              374 kB
 421VmFlags: rd ex mr mw me de
 422
 423the first of these lines shows the same information as is displayed for the
 424mapping in /proc/PID/maps.  The remaining lines show the size of the mapping
 425(size), the amount of the mapping that is currently resident in RAM (RSS), the
 426process' proportional share of this mapping (PSS), the number of clean and
 427dirty private pages in the mapping.  Note that even a page which is part of a
 428MAP_SHARED mapping, but has only a single pte mapped, i.e.  is currently used
 429by only one process, is accounted as private and not as shared.  "Referenced"
 430indicates the amount of memory currently marked as referenced or accessed.
 431"Anonymous" shows the amount of memory that does not belong to any file.  Even
 432a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
 433and a page is modified, the file page is replaced by a private anonymous copy.
 434"Swap" shows how much would-be-anonymous memory is also used, but out on
 435swap.
 436
 437"VmFlags" field deserves a separate description. This member represents the kernel
 438flags associated with the particular virtual memory area in two letter encoded
 439manner. The codes are the following:
 440    rd  - readable
 441    wr  - writeable
 442    ex  - executable
 443    sh  - shared
 444    mr  - may read
 445    mw  - may write
 446    me  - may execute
 447    ms  - may share
 448    gd  - stack segment growns down
 449    pf  - pure PFN range
 450    dw  - disabled write to the mapped file
 451    lo  - pages are locked in memory
 452    io  - memory mapped I/O area
 453    sr  - sequential read advise provided
 454    rr  - random read advise provided
 455    dc  - do not copy area on fork
 456    de  - do not expand area on remapping
 457    ac  - area is accountable
 458    nr  - swap space is not reserved for the area
 459    ht  - area uses huge tlb pages
 460    nl  - non-linear mapping
 461    ar  - architecture specific flag
 462    dd  - do not include area into core dump
 463    mm  - mixed map area
 464    hg  - huge page advise flag
 465    nh  - no-huge page advise flag
 466    mg  - mergable advise flag
 467
 468Note that there is no guarantee that every flag and associated mnemonic will
 469be present in all further kernel releases. Things get changed, the flags may
 470be vanished or the reverse -- new added.
 471
 472This file is only present if the CONFIG_MMU kernel configuration option is
 473enabled.
 474
 475The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
 476bits on both physical and virtual pages associated with a process, and the
 477soft-dirty bit on pte (see Documentation/vm/soft-dirty.txt for details).
 478To clear the bits for all the pages associated with the process
 479    > echo 1 > /proc/PID/clear_refs
 480
 481To clear the bits for the anonymous pages associated with the process
 482    > echo 2 > /proc/PID/clear_refs
 483
 484To clear the bits for the file mapped pages associated with the process
 485    > echo 3 > /proc/PID/clear_refs
 486
 487To clear the soft-dirty bit
 488    > echo 4 > /proc/PID/clear_refs
 489
 490Any other value written to /proc/PID/clear_refs will have no effect.
 491
 492The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
 493using /proc/kpageflags and number of times a page is mapped using
 494/proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.txt.
 495
 4961.2 Kernel data
 497---------------
 498
 499Similar to  the  process entries, the kernel data files give information about
 500the running kernel. The files used to obtain this information are contained in
 501/proc and  are  listed  in Table 1-5. Not all of these will be present in your
 502system. It  depends  on the kernel configuration and the loaded modules, which
 503files are there, and which are missing.
 504
 505Table 1-5: Kernel info in /proc
 506..............................................................................
 507 File        Content                                           
 508 apm         Advanced power management info                    
 509 buddyinfo   Kernel memory allocator information (see text)     (2.5)
 510 bus         Directory containing bus specific information     
 511 cmdline     Kernel command line                               
 512 cpuinfo     Info about the CPU                                
 513 devices     Available devices (block and character)           
 514 dma         Used DMS channels                                 
 515 filesystems Supported filesystems                             
 516 driver      Various drivers grouped here, currently rtc (2.4)
 517 execdomains Execdomains, related to security                   (2.4)
 518 fb          Frame Buffer devices                               (2.4)
 519 fs          File system parameters, currently nfs/exports      (2.4)
 520 ide         Directory containing info about the IDE subsystem 
 521 interrupts  Interrupt usage                                   
 522 iomem       Memory map                                         (2.4)
 523 ioports     I/O port usage                                    
 524 irq         Masks for irq to cpu affinity                      (2.4)(smp?)
 525 isapnp      ISA PnP (Plug&Play) Info                           (2.4)
 526 kcore       Kernel core image (can be ELF or A.OUT(deprecated in 2.4))   
 527 kmsg        Kernel messages                                   
 528 ksyms       Kernel symbol table                               
 529 loadavg     Load average of last 1, 5 & 15 minutes                
 530 locks       Kernel locks                                      
 531 meminfo     Memory info                                       
 532 misc        Miscellaneous                                     
 533 modules     List of loaded modules                            
 534 mounts      Mounted filesystems                               
 535 net         Networking info (see text)                        
 536 pagetypeinfo Additional page allocator information (see text)  (2.5)
 537 partitions  Table of partitions known to the system           
 538 pci         Deprecated info of PCI bus (new way -> /proc/bus/pci/,
 539             decoupled by lspci                                 (2.4)
 540 rtc         Real time clock                                   
 541 scsi        SCSI info (see text)                              
 542 slabinfo    Slab pool info                                    
 543 softirqs    softirq usage
 544 stat        Overall statistics                                
 545 swaps       Swap space utilization                            
 546 sys         See chapter 2                                     
 547 sysvipc     Info of SysVIPC Resources (msg, sem, shm)          (2.4)
 548 tty         Info of tty drivers
 549 uptime      System uptime                                     
 550 version     Kernel version                                    
 551 video       bttv info of video resources                       (2.4)
 552 vmallocinfo Show vmalloced areas
 553..............................................................................
 554
 555You can,  for  example,  check  which interrupts are currently in use and what
 556they are used for by looking in the file /proc/interrupts:
 557
 558  > cat /proc/interrupts 
 559             CPU0        
 560    0:    8728810          XT-PIC  timer 
 561    1:        895          XT-PIC  keyboard 
 562    2:          0          XT-PIC  cascade 
 563    3:     531695          XT-PIC  aha152x 
 564    4:    2014133          XT-PIC  serial 
 565    5:      44401          XT-PIC  pcnet_cs 
 566    8:          2          XT-PIC  rtc 
 567   11:          8          XT-PIC  i82365 
 568   12:     182918          XT-PIC  PS/2 Mouse 
 569   13:          1          XT-PIC  fpu 
 570   14:    1232265          XT-PIC  ide0 
 571   15:          7          XT-PIC  ide1 
 572  NMI:          0 
 573
 574In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the
 575output of a SMP machine):
 576
 577  > cat /proc/interrupts 
 578
 579             CPU0       CPU1       
 580    0:    1243498    1214548    IO-APIC-edge  timer
 581    1:       8949       8958    IO-APIC-edge  keyboard
 582    2:          0          0          XT-PIC  cascade
 583    5:      11286      10161    IO-APIC-edge  soundblaster
 584    8:          1          0    IO-APIC-edge  rtc
 585    9:      27422      27407    IO-APIC-edge  3c503
 586   12:     113645     113873    IO-APIC-edge  PS/2 Mouse
 587   13:          0          0          XT-PIC  fpu
 588   14:      22491      24012    IO-APIC-edge  ide0
 589   15:       2183       2415    IO-APIC-edge  ide1
 590   17:      30564      30414   IO-APIC-level  eth0
 591   18:        177        164   IO-APIC-level  bttv
 592  NMI:    2457961    2457959 
 593  LOC:    2457882    2457881 
 594  ERR:       2155
 595
 596NMI is incremented in this case because every timer interrupt generates a NMI
 597(Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups.
 598
 599LOC is the local interrupt counter of the internal APIC of every CPU.
 600
 601ERR is incremented in the case of errors in the IO-APIC bus (the bus that
 602connects the CPUs in a SMP system. This means that an error has been detected,
 603the IO-APIC automatically retry the transmission, so it should not be a big
 604problem, but you should read the SMP-FAQ.
 605
 606In 2.6.2* /proc/interrupts was expanded again.  This time the goal was for
 607/proc/interrupts to display every IRQ vector in use by the system, not
 608just those considered 'most important'.  The new vectors are:
 609
 610  THR -- interrupt raised when a machine check threshold counter
 611  (typically counting ECC corrected errors of memory or cache) exceeds
 612  a configurable threshold.  Only available on some systems.
 613
 614  TRM -- a thermal event interrupt occurs when a temperature threshold
 615  has been exceeded for the CPU.  This interrupt may also be generated
 616  when the temperature drops back to normal.
 617
 618  SPU -- a spurious interrupt is some interrupt that was raised then lowered
 619  by some IO device before it could be fully processed by the APIC.  Hence
 620  the APIC sees the interrupt but does not know what device it came from.
 621  For this case the APIC will generate the interrupt with a IRQ vector
 622  of 0xff. This might also be generated by chipset bugs.
 623
 624  RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are
 625  sent from one CPU to another per the needs of the OS.  Typically,
 626  their statistics are used by kernel developers and interested users to
 627  determine the occurrence of interrupts of the given type.
 628
 629The above IRQ vectors are displayed only when relevant.  For example,
 630the threshold vector does not exist on x86_64 platforms.  Others are
 631suppressed when the system is a uniprocessor.  As of this writing, only
 632i386 and x86_64 platforms support the new IRQ vector displays.
 633
 634Of some interest is the introduction of the /proc/irq directory to 2.4.
 635It could be used to set IRQ to CPU affinity, this means that you can "hook" an
 636IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
 637irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and
 638prof_cpu_mask.
 639
 640For example 
 641  > ls /proc/irq/
 642  0  10  12  14  16  18  2  4  6  8  prof_cpu_mask
 643  1  11  13  15  17  19  3  5  7  9  default_smp_affinity
 644  > ls /proc/irq/0/
 645  smp_affinity
 646
 647smp_affinity is a bitmask, in which you can specify which CPUs can handle the
 648IRQ, you can set it by doing:
 649
 650  > echo 1 > /proc/irq/10/smp_affinity
 651
 652This means that only the first CPU will handle the IRQ, but you can also echo
 6535 which means that only the first and fourth CPU can handle the IRQ.
 654
 655The contents of each smp_affinity file is the same by default:
 656
 657  > cat /proc/irq/0/smp_affinity
 658  ffffffff
 659
 660There is an alternate interface, smp_affinity_list which allows specifying
 661a cpu range instead of a bitmask:
 662
 663  > cat /proc/irq/0/smp_affinity_list
 664  1024-1031
 665
 666The default_smp_affinity mask applies to all non-active IRQs, which are the
 667IRQs which have not yet been allocated/activated, and hence which lack a
 668/proc/irq/[0-9]* directory.
 669
 670The node file on an SMP system shows the node to which the device using the IRQ
 671reports itself as being attached. This hardware locality information does not
 672include information about any possible driver locality preference.
 673
 674prof_cpu_mask specifies which CPUs are to be profiled by the system wide
 675profiler. Default value is ffffffff (all cpus if there are only 32 of them).
 676
 677The way IRQs are routed is handled by the IO-APIC, and it's Round Robin
 678between all the CPUs which are allowed to handle it. As usual the kernel has
 679more info than you and does a better job than you, so the defaults are the
 680best choice for almost everyone.  [Note this applies only to those IO-APIC's
 681that support "Round Robin" interrupt distribution.]
 682
 683There are  three  more  important subdirectories in /proc: net, scsi, and sys.
 684The general  rule  is  that  the  contents,  or  even  the  existence of these
 685directories, depend  on your kernel configuration. If SCSI is not enabled, the
 686directory scsi  may  not  exist. The same is true with the net, which is there
 687only when networking support is present in the running kernel.
 688
 689The slabinfo  file  gives  information  about  memory usage at the slab level.
 690Linux uses  slab  pools for memory management above page level in version 2.2.
 691Commonly used  objects  have  their  own  slab  pool (such as network buffers,
 692directory cache, and so on).
 693
 694..............................................................................
 695
 696> cat /proc/buddyinfo
 697
 698Node 0, zone      DMA      0      4      5      4      4      3 ...
 699Node 0, zone   Normal      1      0      0      1    101      8 ...
 700Node 0, zone  HighMem      2      0      0      1      1      0 ...
 701
 702External fragmentation is a problem under some workloads, and buddyinfo is a
 703useful tool for helping diagnose these problems.  Buddyinfo will give you a 
 704clue as to how big an area you can safely allocate, or why a previous
 705allocation failed.
 706
 707Each column represents the number of pages of a certain order which are 
 708available.  In this case, there are 0 chunks of 2^0*PAGE_SIZE available in 
 709ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE 
 710available in ZONE_NORMAL, etc... 
 711
 712More information relevant to external fragmentation can be found in
 713pagetypeinfo.
 714
 715> cat /proc/pagetypeinfo
 716Page block order: 9
 717Pages per block:  512
 718
 719Free pages count per migrate type at order       0      1      2      3      4      5      6      7      8      9     10
 720Node    0, zone      DMA, type    Unmovable      0      0      0      1      1      1      1      1      1      1      0
 721Node    0, zone      DMA, type  Reclaimable      0      0      0      0      0      0      0      0      0      0      0
 722Node    0, zone      DMA, type      Movable      1      1      2      1      2      1      1      0      1      0      2
 723Node    0, zone      DMA, type      Reserve      0      0      0      0      0      0      0      0      0      1      0
 724Node    0, zone      DMA, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
 725Node    0, zone    DMA32, type    Unmovable    103     54     77      1      1      1     11      8      7      1      9
 726Node    0, zone    DMA32, type  Reclaimable      0      0      2      1      0      0      0      0      1      0      0
 727Node    0, zone    DMA32, type      Movable    169    152    113     91     77     54     39     13      6      1    452
 728Node    0, zone    DMA32, type      Reserve      1      2      2      2      2      0      1      1      1      1      0
 729Node    0, zone    DMA32, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
 730
 731Number of blocks type     Unmovable  Reclaimable      Movable      Reserve      Isolate
 732Node 0, zone      DMA            2            0            5            1            0
 733Node 0, zone    DMA32           41            6          967            2            0
 734
 735Fragmentation avoidance in the kernel works by grouping pages of different
 736migrate types into the same contiguous regions of memory called page blocks.
 737A page block is typically the size of the default hugepage size e.g. 2MB on
 738X86-64. By keeping pages grouped based on their ability to move, the kernel
 739can reclaim pages within a page block to satisfy a high-order allocation.
 740
 741The pagetypinfo begins with information on the size of a page block. It
 742then gives the same type of information as buddyinfo except broken down
 743by migrate-type and finishes with details on how many page blocks of each
 744type exist.
 745
 746If min_free_kbytes has been tuned correctly (recommendations made by hugeadm
 747from libhugetlbfs http://sourceforge.net/projects/libhugetlbfs/), one can
 748make an estimate of the likely number of huge pages that can be allocated
 749at a given point in time. All the "Movable" blocks should be allocatable
 750unless memory has been mlock()'d. Some of the Reclaimable blocks should
 751also be allocatable although a lot of filesystem metadata may have to be
 752reclaimed to achieve this.
 753
 754..............................................................................
 755
 756meminfo:
 757
 758Provides information about distribution and utilization of memory.  This
 759varies by architecture and compile options.  The following is from a
 76016GB PIII, which has highmem enabled.  You may not have all of these fields.
 761
 762> cat /proc/meminfo
 763
 764The "Locked" indicates whether the mapping is locked in memory or not.
 765
 766
 767MemTotal:     16344972 kB
 768MemFree:      13634064 kB
 769Buffers:          3656 kB
 770Cached:        1195708 kB
 771SwapCached:          0 kB
 772Active:         891636 kB
 773Inactive:      1077224 kB
 774HighTotal:    15597528 kB
 775HighFree:     13629632 kB
 776LowTotal:       747444 kB
 777LowFree:          4432 kB
 778SwapTotal:           0 kB
 779SwapFree:            0 kB
 780Dirty:             968 kB
 781Writeback:           0 kB
 782AnonPages:      861800 kB
 783Mapped:         280372 kB
 784Slab:           284364 kB
 785SReclaimable:   159856 kB
 786SUnreclaim:     124508 kB
 787PageTables:      24448 kB
 788NFS_Unstable:        0 kB
 789Bounce:              0 kB
 790WritebackTmp:        0 kB
 791CommitLimit:   7669796 kB
 792Committed_AS:   100056 kB
 793VmallocTotal:   112216 kB
 794VmallocUsed:       428 kB
 795VmallocChunk:   111088 kB
 796AnonHugePages:   49152 kB
 797
 798    MemTotal: Total usable ram (i.e. physical ram minus a few reserved
 799              bits and the kernel binary code)
 800     MemFree: The sum of LowFree+HighFree
 801     Buffers: Relatively temporary storage for raw disk blocks
 802              shouldn't get tremendously large (20MB or so)
 803      Cached: in-memory cache for files read from the disk (the
 804              pagecache).  Doesn't include SwapCached
 805  SwapCached: Memory that once was swapped out, is swapped back in but
 806              still also is in the swapfile (if memory is needed it
 807              doesn't need to be swapped out AGAIN because it is already
 808              in the swapfile. This saves I/O)
 809      Active: Memory that has been used more recently and usually not
 810              reclaimed unless absolutely necessary.
 811    Inactive: Memory which has been less recently used.  It is more
 812              eligible to be reclaimed for other purposes
 813   HighTotal:
 814    HighFree: Highmem is all memory above ~860MB of physical memory
 815              Highmem areas are for use by userspace programs, or
 816              for the pagecache.  The kernel must use tricks to access
 817              this memory, making it slower to access than lowmem.
 818    LowTotal:
 819     LowFree: Lowmem is memory which can be used for everything that
 820              highmem can be used for, but it is also available for the
 821              kernel's use for its own data structures.  Among many
 822              other things, it is where everything from the Slab is
 823              allocated.  Bad things happen when you're out of lowmem.
 824   SwapTotal: total amount of swap space available
 825    SwapFree: Memory which has been evicted from RAM, and is temporarily
 826              on the disk
 827       Dirty: Memory which is waiting to get written back to the disk
 828   Writeback: Memory which is actively being written back to the disk
 829   AnonPages: Non-file backed pages mapped into userspace page tables
 830AnonHugePages: Non-file backed huge pages mapped into userspace page tables
 831      Mapped: files which have been mmaped, such as libraries
 832        Slab: in-kernel data structures cache
 833SReclaimable: Part of Slab, that might be reclaimed, such as caches
 834  SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure
 835  PageTables: amount of memory dedicated to the lowest level of page
 836              tables.
 837NFS_Unstable: NFS pages sent to the server, but not yet committed to stable
 838              storage
 839      Bounce: Memory used for block device "bounce buffers"
 840WritebackTmp: Memory used by FUSE for temporary writeback buffers
 841 CommitLimit: Based on the overcommit ratio ('vm.overcommit_ratio'),
 842              this is the total amount of  memory currently available to
 843              be allocated on the system. This limit is only adhered to
 844              if strict overcommit accounting is enabled (mode 2 in
 845              'vm.overcommit_memory').
 846              The CommitLimit is calculated with the following formula:
 847              CommitLimit = ('vm.overcommit_ratio' * Physical RAM) + Swap
 848              For example, on a system with 1G of physical RAM and 7G
 849              of swap with a `vm.overcommit_ratio` of 30 it would
 850              yield a CommitLimit of 7.3G.
 851              For more details, see the memory overcommit documentation
 852              in vm/overcommit-accounting.
 853Committed_AS: The amount of memory presently allocated on the system.
 854              The committed memory is a sum of all of the memory which
 855              has been allocated by processes, even if it has not been
 856              "used" by them as of yet. A process which malloc()'s 1G
 857              of memory, but only touches 300M of it will only show up
 858              as using 300M of memory even if it has the address space
 859              allocated for the entire 1G. This 1G is memory which has
 860              been "committed" to by the VM and can be used at any time
 861              by the allocating application. With strict overcommit
 862              enabled on the system (mode 2 in 'vm.overcommit_memory'),
 863              allocations which would exceed the CommitLimit (detailed
 864              above) will not be permitted. This is useful if one needs
 865              to guarantee that processes will not fail due to lack of
 866              memory once that memory has been successfully allocated.
 867VmallocTotal: total size of vmalloc memory area
 868 VmallocUsed: amount of vmalloc area which is used
 869VmallocChunk: largest contiguous block of vmalloc area which is free
 870
 871..............................................................................
 872
 873vmallocinfo:
 874
 875Provides information about vmalloced/vmaped areas. One line per area,
 876containing the virtual address range of the area, size in bytes,
 877caller information of the creator, and optional information depending
 878on the kind of area :
 879
 880 pages=nr    number of pages
 881 phys=addr   if a physical address was specified
 882 ioremap     I/O mapping (ioremap() and friends)
 883 vmalloc     vmalloc() area
 884 vmap        vmap()ed pages
 885 user        VM_USERMAP area
 886 vpages      buffer for pages pointers was vmalloced (huge area)
 887 N<node>=nr  (Only on NUMA kernels)
 888             Number of pages allocated on memory node <node>
 889
 890> cat /proc/vmallocinfo
 8910xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ...
 892  /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128
 8930xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ...
 894  /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64
 8950xffffc20000302000-0xffffc20000304000    8192 acpi_tb_verify_table+0x21/0x4f...
 896  phys=7fee8000 ioremap
 8970xffffc20000304000-0xffffc20000307000   12288 acpi_tb_verify_table+0x21/0x4f...
 898  phys=7fee7000 ioremap
 8990xffffc2000031d000-0xffffc2000031f000    8192 init_vdso_vars+0x112/0x210
 9000xffffc2000031f000-0xffffc2000032b000   49152 cramfs_uncompress_init+0x2e ...
 901  /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3
 9020xffffc2000033a000-0xffffc2000033d000   12288 sys_swapon+0x640/0xac0      ...
 903  pages=2 vmalloc N1=2
 9040xffffc20000347000-0xffffc2000034c000   20480 xt_alloc_table_info+0xfe ...
 905  /0x130 [x_tables] pages=4 vmalloc N0=4
 9060xffffffffa0000000-0xffffffffa000f000   61440 sys_init_module+0xc27/0x1d00 ...
 907   pages=14 vmalloc N2=14
 9080xffffffffa000f000-0xffffffffa0014000   20480 sys_init_module+0xc27/0x1d00 ...
 909   pages=4 vmalloc N1=4
 9100xffffffffa0014000-0xffffffffa0017000   12288 sys_init_module+0xc27/0x1d00 ...
 911   pages=2 vmalloc N1=2
 9120xffffffffa0017000-0xffffffffa0022000   45056 sys_init_module+0xc27/0x1d00 ...
 913   pages=10 vmalloc N0=10
 914
 915..............................................................................
 916
 917softirqs:
 918
 919Provides counts of softirq handlers serviced since boot time, for each cpu.
 920
 921> cat /proc/softirqs
 922                CPU0       CPU1       CPU2       CPU3
 923      HI:          0          0          0          0
 924   TIMER:      27166      27120      27097      27034
 925  NET_TX:          0          0          0         17
 926  NET_RX:         42          0          0         39
 927   BLOCK:          0          0        107       1121
 928 TASKLET:          0          0          0        290
 929   SCHED:      27035      26983      26971      26746
 930 HRTIMER:          0          0          0          0
 931     RCU:       1678       1769       2178       2250
 932
 933
 9341.3 IDE devices in /proc/ide
 935----------------------------
 936
 937The subdirectory /proc/ide contains information about all IDE devices of which
 938the kernel  is  aware.  There is one subdirectory for each IDE controller, the
 939file drivers  and a link for each IDE device, pointing to the device directory
 940in the controller specific subtree.
 941
 942The file  drivers  contains general information about the drivers used for the
 943IDE devices:
 944
 945  > cat /proc/ide/drivers
 946  ide-cdrom version 4.53
 947  ide-disk version 1.08
 948
 949More detailed  information  can  be  found  in  the  controller  specific
 950subdirectories. These  are  named  ide0,  ide1  and  so  on.  Each  of  these
 951directories contains the files shown in table 1-6.
 952
 953
 954Table 1-6: IDE controller info in  /proc/ide/ide?
 955..............................................................................
 956 File    Content                                 
 957 channel IDE channel (0 or 1)                    
 958 config  Configuration (only for PCI/IDE bridge) 
 959 mate    Mate name                               
 960 model   Type/Chipset of IDE controller          
 961..............................................................................
 962
 963Each device  connected  to  a  controller  has  a separate subdirectory in the
 964controllers directory.  The  files  listed in table 1-7 are contained in these
 965directories.
 966
 967
 968Table 1-7: IDE device information
 969..............................................................................
 970 File             Content                                    
 971 cache            The cache                                  
 972 capacity         Capacity of the medium (in 512Byte blocks) 
 973 driver           driver and version                         
 974 geometry         physical and logical geometry              
 975 identify         device identify block                      
 976 media            media type                                 
 977 model            device identifier                          
 978 settings         device setup                               
 979 smart_thresholds IDE disk management thresholds             
 980 smart_values     IDE disk management values                 
 981..............................................................................
 982
 983The most  interesting  file is settings. This file contains a nice overview of
 984the drive parameters:
 985
 986  # cat /proc/ide/ide0/hda/settings 
 987  name                    value           min             max             mode 
 988  ----                    -----           ---             ---             ---- 
 989  bios_cyl                526             0               65535           rw 
 990  bios_head               255             0               255             rw 
 991  bios_sect               63              0               63              rw 
 992  breada_readahead        4               0               127             rw 
 993  bswap                   0               0               1               r 
 994  file_readahead          72              0               2097151         rw 
 995  io_32bit                0               0               3               rw 
 996  keepsettings            0               0               1               rw 
 997  max_kb_per_request      122             1               127             rw 
 998  multcount               0               0               8               rw 
 999  nice1                   1               0               1               rw 
1000  nowerr                  0               0               1               rw 
1001  pio_mode                write-only      0               255             w 
1002  slow                    0               0               1               rw 
1003  unmaskirq               0               0               1               rw 
1004  using_dma               0               0               1               rw 
1005
1006
10071.4 Networking info in /proc/net
1008--------------------------------
1009
1010The subdirectory  /proc/net  follows  the  usual  pattern. Table 1-8 shows the
1011additional values  you  get  for  IP  version 6 if you configure the kernel to
1012support this. Table 1-9 lists the files and their meaning.
1013
1014
1015Table 1-8: IPv6 info in /proc/net
1016..............................................................................
1017 File       Content                                               
1018 udp6       UDP sockets (IPv6)                                    
1019 tcp6       TCP sockets (IPv6)                                    
1020 raw6       Raw device statistics (IPv6)                          
1021 igmp6      IP multicast addresses, which this host joined (IPv6) 
1022 if_inet6   List of IPv6 interface addresses                      
1023 ipv6_route Kernel routing table for IPv6                         
1024 rt6_stats  Global IPv6 routing tables statistics                 
1025 sockstat6  Socket statistics (IPv6)                              
1026 snmp6      Snmp data (IPv6)                                      
1027..............................................................................
1028
1029
1030Table 1-9: Network info in /proc/net
1031..............................................................................
1032 File          Content                                                         
1033 arp           Kernel  ARP table                                               
1034 dev           network devices with statistics                                 
1035 dev_mcast     the Layer2 multicast groups a device is listening too
1036               (interface index, label, number of references, number of bound
1037               addresses). 
1038 dev_stat      network device status                                           
1039 ip_fwchains   Firewall chain linkage                                          
1040 ip_fwnames    Firewall chain names                                            
1041 ip_masq       Directory containing the masquerading tables                    
1042 ip_masquerade Major masquerading table                                        
1043 netstat       Network statistics                                              
1044 raw           raw device statistics                                           
1045 route         Kernel routing table                                            
1046 rpc           Directory containing rpc info                                   
1047 rt_cache      Routing cache                                                   
1048 snmp          SNMP data                                                       
1049 sockstat      Socket statistics                                               
1050 tcp           TCP  sockets                                                    
1051 udp           UDP sockets                                                     
1052 unix          UNIX domain sockets                                             
1053 wireless      Wireless interface data (Wavelan etc)                           
1054 igmp          IP multicast addresses, which this host joined                  
1055 psched        Global packet scheduler parameters.                             
1056 netlink       List of PF_NETLINK sockets                                      
1057 ip_mr_vifs    List of multicast virtual interfaces                            
1058 ip_mr_cache   List of multicast routing cache                                 
1059..............................................................................
1060
1061You can  use  this  information  to see which network devices are available in
1062your system and how much traffic was routed over those devices:
1063
1064  > cat /proc/net/dev 
1065  Inter-|Receive                                                   |[... 
1066   face |bytes    packets errs drop fifo frame compressed multicast|[... 
1067      lo:  908188   5596     0    0    0     0          0         0 [...         
1068    ppp0:15475140  20721   410    0    0   410          0         0 [...  
1069    eth0:  614530   7085     0    0    0     0          0         1 [... 
1070   
1071  ...] Transmit 
1072  ...] bytes    packets errs drop fifo colls carrier compressed 
1073  ...]  908188     5596    0    0    0     0       0          0 
1074  ...] 1375103    17405    0    0    0     0       0          0 
1075  ...] 1703981     5535    0    0    0     3       0          0 
1076
1077In addition, each Channel Bond interface has its own directory.  For
1078example, the bond0 device will have a directory called /proc/net/bond0/.
1079It will contain information that is specific to that bond, such as the
1080current slaves of the bond, the link status of the slaves, and how
1081many times the slaves link has failed.
1082
10831.5 SCSI info
1084-------------
1085
1086If you  have  a  SCSI  host adapter in your system, you'll find a subdirectory
1087named after  the driver for this adapter in /proc/scsi. You'll also see a list
1088of all recognized SCSI devices in /proc/scsi:
1089
1090  >cat /proc/scsi/scsi 
1091  Attached devices: 
1092  Host: scsi0 Channel: 00 Id: 00 Lun: 00 
1093    Vendor: IBM      Model: DGHS09U          Rev: 03E0 
1094    Type:   Direct-Access                    ANSI SCSI revision: 03 
1095  Host: scsi0 Channel: 00 Id: 06 Lun: 00 
1096    Vendor: PIONEER  Model: CD-ROM DR-U06S   Rev: 1.04 
1097    Type:   CD-ROM                           ANSI SCSI revision: 02 
1098
1099
1100The directory  named  after  the driver has one file for each adapter found in
1101the system.  These  files  contain information about the controller, including
1102the used  IRQ  and  the  IO  address range. The amount of information shown is
1103dependent on  the adapter you use. The example shows the output for an Adaptec
1104AHA-2940 SCSI adapter:
1105
1106  > cat /proc/scsi/aic7xxx/0 
1107   
1108  Adaptec AIC7xxx driver version: 5.1.19/3.2.4 
1109  Compile Options: 
1110    TCQ Enabled By Default : Disabled 
1111    AIC7XXX_PROC_STATS     : Disabled 
1112    AIC7XXX_RESET_DELAY    : 5 
1113  Adapter Configuration: 
1114             SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter 
1115                             Ultra Wide Controller 
1116      PCI MMAPed I/O Base: 0xeb001000 
1117   Adapter SEEPROM Config: SEEPROM found and used. 
1118        Adaptec SCSI BIOS: Enabled 
1119                      IRQ: 10 
1120                     SCBs: Active 0, Max Active 2, 
1121                           Allocated 15, HW 16, Page 255 
1122               Interrupts: 160328 
1123        BIOS Control Word: 0x18b6 
1124     Adapter Control Word: 0x005b 
1125     Extended Translation: Enabled 
1126  Disconnect Enable Flags: 0xffff 
1127       Ultra Enable Flags: 0x0001 
1128   Tag Queue Enable Flags: 0x0000 
1129  Ordered Queue Tag Flags: 0x0000 
1130  Default Tag Queue Depth: 8 
1131      Tagged Queue By Device array for aic7xxx host instance 0: 
1132        {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255} 
1133      Actual queue depth per device for aic7xxx host instance 0: 
1134        {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1} 
1135  Statistics: 
1136  (scsi0:0:0:0) 
1137    Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8 
1138    Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0) 
1139    Total transfers 160151 (74577 reads and 85574 writes) 
1140  (scsi0:0:6:0) 
1141    Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15 
1142    Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0) 
1143    Total transfers 0 (0 reads and 0 writes) 
1144
1145
11461.6 Parallel port info in /proc/parport
1147---------------------------------------
1148
1149The directory  /proc/parport  contains information about the parallel ports of
1150your system.  It  has  one  subdirectory  for  each port, named after the port
1151number (0,1,2,...).
1152
1153These directories contain the four files shown in Table 1-10.
1154
1155
1156Table 1-10: Files in /proc/parport
1157..............................................................................
1158 File      Content                                                             
1159 autoprobe Any IEEE-1284 device ID information that has been acquired.         
1160 devices   list of the device drivers using that port. A + will appear by the
1161           name of the device currently using the port (it might not appear
1162           against any). 
1163 hardware  Parallel port's base address, IRQ line and DMA channel.             
1164 irq       IRQ that parport is using for that port. This is in a separate
1165           file to allow you to alter it by writing a new value in (IRQ
1166           number or none). 
1167..............................................................................
1168
11691.7 TTY info in /proc/tty
1170-------------------------
1171
1172Information about  the  available  and actually used tty's can be found in the
1173directory /proc/tty.You'll  find  entries  for drivers and line disciplines in
1174this directory, as shown in Table 1-11.
1175
1176
1177Table 1-11: Files in /proc/tty
1178..............................................................................
1179 File          Content                                        
1180 drivers       list of drivers and their usage                
1181 ldiscs        registered line disciplines                    
1182 driver/serial usage statistic and status of single tty lines 
1183..............................................................................
1184
1185To see  which  tty's  are  currently in use, you can simply look into the file
1186/proc/tty/drivers:
1187
1188  > cat /proc/tty/drivers 
1189  pty_slave            /dev/pts      136   0-255 pty:slave 
1190  pty_master           /dev/ptm      128   0-255 pty:master 
1191  pty_slave            /dev/ttyp       3   0-255 pty:slave 
1192  pty_master           /dev/pty        2   0-255 pty:master 
1193  serial               /dev/cua        5   64-67 serial:callout 
1194  serial               /dev/ttyS       4   64-67 serial 
1195  /dev/tty0            /dev/tty0       4       0 system:vtmaster 
1196  /dev/ptmx            /dev/ptmx       5       2 system 
1197  /dev/console         /dev/console    5       1 system:console 
1198  /dev/tty             /dev/tty        5       0 system:/dev/tty 
1199  unknown              /dev/tty        4    1-63 console 
1200
1201
12021.8 Miscellaneous kernel statistics in /proc/stat
1203-------------------------------------------------
1204
1205Various pieces   of  information about  kernel activity  are  available in the
1206/proc/stat file.  All  of  the numbers reported  in  this file are  aggregates
1207since the system first booted.  For a quick look, simply cat the file:
1208
1209  > cat /proc/stat
1210  cpu  2255 34 2290 22625563 6290 127 456 0 0
1211  cpu0 1132 34 1441 11311718 3675 127 438 0 0
1212  cpu1 1123 0 849 11313845 2614 0 18 0 0
1213  intr 114930548 113199788 3 0 5 263 0 4 [... lots more numbers ...]
1214  ctxt 1990473
1215  btime 1062191376
1216  processes 2915
1217  procs_running 1
1218  procs_blocked 0
1219  softirq 183433 0 21755 12 39 1137 231 21459 2263
1220
1221The very first  "cpu" line aggregates the  numbers in all  of the other "cpuN"
1222lines.  These numbers identify the amount of time the CPU has spent performing
1223different kinds of work.  Time units are in USER_HZ (typically hundredths of a
1224second).  The meanings of the columns are as follows, from left to right:
1225
1226- user: normal processes executing in user mode
1227- nice: niced processes executing in user mode
1228- system: processes executing in kernel mode
1229- idle: twiddling thumbs
1230- iowait: waiting for I/O to complete
1231- irq: servicing interrupts
1232- softirq: servicing softirqs
1233- steal: involuntary wait
1234- guest: running a normal guest
1235- guest_nice: running a niced guest
1236
1237The "intr" line gives counts of interrupts  serviced since boot time, for each
1238of the  possible system interrupts.   The first  column  is the  total of  all
1239interrupts serviced; each  subsequent column is the  total for that particular
1240interrupt.
1241
1242The "ctxt" line gives the total number of context switches across all CPUs.
1243
1244The "btime" line gives  the time at which the  system booted, in seconds since
1245the Unix epoch.
1246
1247The "processes" line gives the number  of processes and threads created, which
1248includes (but  is not limited  to) those  created by  calls to the  fork() and
1249clone() system calls.
1250
1251The "procs_running" line gives the total number of threads that are
1252running or ready to run (i.e., the total number of runnable threads).
1253
1254The   "procs_blocked" line gives  the  number of  processes currently blocked,
1255waiting for I/O to complete.
1256
1257The "softirq" line gives counts of softirqs serviced since boot time, for each
1258of the possible system softirqs. The first column is the total of all
1259softirqs serviced; each subsequent column is the total for that particular
1260softirq.
1261
1262
12631.9 Ext4 file system parameters
1264------------------------------
1265
1266Information about mounted ext4 file systems can be found in
1267/proc/fs/ext4.  Each mounted filesystem will have a directory in
1268/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or
1269/proc/fs/ext4/dm-0).   The files in each per-device directory are shown
1270in Table 1-12, below.
1271
1272Table 1-12: Files in /proc/fs/ext4/<devname>
1273..............................................................................
1274 File            Content                                        
1275 mb_groups       details of multiblock allocator buddy cache of free blocks
1276..............................................................................
1277
12782.0 /proc/consoles
1279------------------
1280Shows registered system console lines.
1281
1282To see which character device lines are currently used for the system console
1283/dev/console, you may simply look into the file /proc/consoles:
1284
1285  > cat /proc/consoles
1286  tty0                 -WU (ECp)       4:7
1287  ttyS0                -W- (Ep)        4:64
1288
1289The columns are:
1290
1291  device               name of the device
1292  operations           R = can do read operations
1293                       W = can do write operations
1294                       U = can do unblank
1295  flags                E = it is enabled
1296                       C = it is preferred console
1297                       B = it is primary boot console
1298                       p = it is used for printk buffer
1299                       b = it is not a TTY but a Braille device
1300                       a = it is safe to use when cpu is offline
1301  major:minor          major and minor number of the device separated by a colon
1302
1303------------------------------------------------------------------------------
1304Summary
1305------------------------------------------------------------------------------
1306The /proc file system serves information about the running system. It not only
1307allows access to process data but also allows you to request the kernel status
1308by reading files in the hierarchy.
1309
1310The directory  structure  of /proc reflects the types of information and makes
1311it easy, if not obvious, where to look for specific data.
1312------------------------------------------------------------------------------
1313
1314------------------------------------------------------------------------------
1315CHAPTER 2: MODIFYING SYSTEM PARAMETERS
1316------------------------------------------------------------------------------
1317
1318------------------------------------------------------------------------------
1319In This Chapter
1320------------------------------------------------------------------------------
1321* Modifying kernel parameters by writing into files found in /proc/sys
1322* Exploring the files which modify certain parameters
1323* Review of the /proc/sys file tree
1324------------------------------------------------------------------------------
1325
1326
1327A very  interesting part of /proc is the directory /proc/sys. This is not only
1328a source  of  information,  it also allows you to change parameters within the
1329kernel. Be  very  careful  when attempting this. You can optimize your system,
1330but you  can  also  cause  it  to  crash.  Never  alter kernel parameters on a
1331production system.  Set  up  a  development machine and test to make sure that
1332everything works  the  way  you want it to. You may have no alternative but to
1333reboot the machine once an error has been made.
1334
1335To change  a  value,  simply  echo  the new value into the file. An example is
1336given below  in the section on the file system data. You need to be root to do
1337this. You  can  create  your  own  boot script to perform this every time your
1338system boots.
1339
1340The files  in /proc/sys can be used to fine tune and monitor miscellaneous and
1341general things  in  the operation of the Linux kernel. Since some of the files
1342can inadvertently  disrupt  your  system,  it  is  advisable  to  read  both
1343documentation and  source  before actually making adjustments. In any case, be
1344very careful  when  writing  to  any  of these files. The entries in /proc may
1345change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt
1346review the kernel documentation in the directory /usr/src/linux/Documentation.
1347This chapter  is  heavily  based  on the documentation included in the pre 2.2
1348kernels, and became part of it in version 2.2.1 of the Linux kernel.
1349
1350Please see: Documentation/sysctl/ directory for descriptions of these
1351entries.
1352
1353------------------------------------------------------------------------------
1354Summary
1355------------------------------------------------------------------------------
1356Certain aspects  of  kernel  behavior  can be modified at runtime, without the
1357need to  recompile  the kernel, or even to reboot the system. The files in the
1358/proc/sys tree  can  not only be read, but also modified. You can use the echo
1359command to write value into these files, thereby changing the default settings
1360of the kernel.
1361------------------------------------------------------------------------------
1362
1363------------------------------------------------------------------------------
1364CHAPTER 3: PER-PROCESS PARAMETERS
1365------------------------------------------------------------------------------
1366
13673.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score
1368--------------------------------------------------------------------------------
1369
1370These file can be used to adjust the badness heuristic used to select which
1371process gets killed in out of memory conditions.
1372
1373The badness heuristic assigns a value to each candidate task ranging from 0
1374(never kill) to 1000 (always kill) to determine which process is targeted.  The
1375units are roughly a proportion along that range of allowed memory the process
1376may allocate from based on an estimation of its current memory and swap use.
1377For example, if a task is using all allowed memory, its badness score will be
13781000.  If it is using half of its allowed memory, its score will be 500.
1379
1380There is an additional factor included in the badness score: root
1381processes are given 3% extra memory over other tasks.
1382
1383The amount of "allowed" memory depends on the context in which the oom killer
1384was called.  If it is due to the memory assigned to the allocating task's cpuset
1385being exhausted, the allowed memory represents the set of mems assigned to that
1386cpuset.  If it is due to a mempolicy's node(s) being exhausted, the allowed
1387memory represents the set of mempolicy nodes.  If it is due to a memory
1388limit (or swap limit) being reached, the allowed memory is that configured
1389limit.  Finally, if it is due to the entire system being out of memory, the
1390allowed memory represents all allocatable resources.
1391
1392The value of /proc/<pid>/oom_score_adj is added to the badness score before it
1393is used to determine which task to kill.  Acceptable values range from -1000
1394(OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX).  This allows userspace to
1395polarize the preference for oom killing either by always preferring a certain
1396task or completely disabling it.  The lowest possible value, -1000, is
1397equivalent to disabling oom killing entirely for that task since it will always
1398report a badness score of 0.
1399
1400Consequently, it is very simple for userspace to define the amount of memory to
1401consider for each task.  Setting a /proc/<pid>/oom_score_adj value of +500, for
1402example, is roughly equivalent to allowing the remainder of tasks sharing the
1403same system, cpuset, mempolicy, or memory controller resources to use at least
140450% more memory.  A value of -500, on the other hand, would be roughly
1405equivalent to discounting 50% of the task's allowed memory from being considered
1406as scoring against the task.
1407
1408For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also
1409be used to tune the badness score.  Its acceptable values range from -16
1410(OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17
1411(OOM_DISABLE) to disable oom killing entirely for that task.  Its value is
1412scaled linearly with /proc/<pid>/oom_score_adj.
1413
1414The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last
1415value set by a CAP_SYS_RESOURCE process. To reduce the value any lower
1416requires CAP_SYS_RESOURCE.
1417
1418Caveat: when a parent task is selected, the oom killer will sacrifice any first
1419generation children with separate address spaces instead, if possible.  This
1420avoids servers and important system daemons from being killed and loses the
1421minimal amount of work.
1422
1423
14243.2 /proc/<pid>/oom_score - Display current oom-killer score
1425-------------------------------------------------------------
1426
1427This file can be used to check the current score used by the oom-killer is for
1428any given <pid>. Use it together with /proc/<pid>/oom_score_adj to tune which
1429process should be killed in an out-of-memory situation.
1430
1431
14323.3  /proc/<pid>/io - Display the IO accounting fields
1433-------------------------------------------------------
1434
1435This file contains IO statistics for each running process
1436
1437Example
1438-------
1439
1440test:/tmp # dd if=/dev/zero of=/tmp/test.dat &
1441[1] 3828
1442
1443test:/tmp # cat /proc/3828/io
1444rchar: 323934931
1445wchar: 323929600
1446syscr: 632687
1447syscw: 632675
1448read_bytes: 0
1449write_bytes: 323932160
1450cancelled_write_bytes: 0
1451
1452
1453Description
1454-----------
1455
1456rchar
1457-----
1458
1459I/O counter: chars read
1460The number of bytes which this task has caused to be read from storage. This
1461is simply the sum of bytes which this process passed to read() and pread().
1462It includes things like tty IO and it is unaffected by whether or not actual
1463physical disk IO was required (the read might have been satisfied from
1464pagecache)
1465
1466
1467wchar
1468-----
1469
1470I/O counter: chars written
1471The number of bytes which this task has caused, or shall cause to be written
1472to disk. Similar caveats apply here as with rchar.
1473
1474
1475syscr
1476-----
1477
1478I/O counter: read syscalls
1479Attempt to count the number of read I/O operations, i.e. syscalls like read()
1480and pread().
1481
1482
1483syscw
1484-----
1485
1486I/O counter: write syscalls
1487Attempt to count the number of write I/O operations, i.e. syscalls like
1488write() and pwrite().
1489
1490
1491read_bytes
1492----------
1493
1494I/O counter: bytes read
1495Attempt to count the number of bytes which this process really did cause to
1496be fetched from the storage layer. Done at the submit_bio() level, so it is
1497accurate for block-backed filesystems. <please add status regarding NFS and
1498CIFS at a later time>
1499
1500
1501write_bytes
1502-----------
1503
1504I/O counter: bytes written
1505Attempt to count the number of bytes which this process caused to be sent to
1506the storage layer. This is done at page-dirtying time.
1507
1508
1509cancelled_write_bytes
1510---------------------
1511
1512The big inaccuracy here is truncate. If a process writes 1MB to a file and
1513then deletes the file, it will in fact perform no writeout. But it will have
1514been accounted as having caused 1MB of write.
1515In other words: The number of bytes which this process caused to not happen,
1516by truncating pagecache. A task can cause "negative" IO too. If this task
1517truncates some dirty pagecache, some IO which another task has been accounted
1518for (in its write_bytes) will not be happening. We _could_ just subtract that
1519from the truncating task's write_bytes, but there is information loss in doing
1520that.
1521
1522
1523Note
1524----
1525
1526At its current implementation state, this is a bit racy on 32-bit machines: if
1527process A reads process B's /proc/pid/io while process B is updating one of
1528those 64-bit counters, process A could see an intermediate result.
1529
1530
1531More information about this can be found within the taskstats documentation in
1532Documentation/accounting.
1533
15343.4 /proc/<pid>/coredump_filter - Core dump filtering settings
1535---------------------------------------------------------------
1536When a process is dumped, all anonymous memory is written to a core file as
1537long as the size of the core file isn't limited. But sometimes we don't want
1538to dump some memory segments, for example, huge shared memory. Conversely,
1539sometimes we want to save file-backed memory segments into a core file, not
1540only the individual files.
1541
1542/proc/<pid>/coredump_filter allows you to customize which memory segments
1543will be dumped when the <pid> process is dumped. coredump_filter is a bitmask
1544of memory types. If a bit of the bitmask is set, memory segments of the
1545corresponding memory type are dumped, otherwise they are not dumped.
1546
1547The following 7 memory types are supported:
1548  - (bit 0) anonymous private memory
1549  - (bit 1) anonymous shared memory
1550  - (bit 2) file-backed private memory
1551  - (bit 3) file-backed shared memory
1552  - (bit 4) ELF header pages in file-backed private memory areas (it is
1553            effective only if the bit 2 is cleared)
1554  - (bit 5) hugetlb private memory
1555  - (bit 6) hugetlb shared memory
1556
1557  Note that MMIO pages such as frame buffer are never dumped and vDSO pages
1558  are always dumped regardless of the bitmask status.
1559
1560  Note bit 0-4 doesn't effect any hugetlb memory. hugetlb memory are only
1561  effected by bit 5-6.
1562
1563Default value of coredump_filter is 0x23; this means all anonymous memory
1564segments and hugetlb private memory are dumped.
1565
1566If you don't want to dump all shared memory segments attached to pid 1234,
1567write 0x21 to the process's proc file.
1568
1569  $ echo 0x21 > /proc/1234/coredump_filter
1570
1571When a new process is created, the process inherits the bitmask status from its
1572parent. It is useful to set up coredump_filter before the program runs.
1573For example:
1574
1575  $ echo 0x7 > /proc/self/coredump_filter
1576  $ ./some_program
1577
15783.5     /proc/<pid>/mountinfo - Information about mounts
1579--------------------------------------------------------
1580
1581This file contains lines of the form:
1582
158336 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue
1584(1)(2)(3)   (4)   (5)      (6)      (7)   (8) (9)   (10)         (11)
1585
1586(1) mount ID:  unique identifier of the mount (may be reused after umount)
1587(2) parent ID:  ID of parent (or of self for the top of the mount tree)
1588(3) major:minor:  value of st_dev for files on filesystem
1589(4) root:  root of the mount within the filesystem
1590(5) mount point:  mount point relative to the process's root
1591(6) mount options:  per mount options
1592(7) optional fields:  zero or more fields of the form "tag[:value]"
1593(8) separator:  marks the end of the optional fields
1594(9) filesystem type:  name of filesystem of the form "type[.subtype]"
1595(10) mount source:  filesystem specific information or "none"
1596(11) super options:  per super block options
1597
1598Parsers should ignore all unrecognised optional fields.  Currently the
1599possible optional fields are:
1600
1601shared:X  mount is shared in peer group X
1602master:X  mount is slave to peer group X
1603propagate_from:X  mount is slave and receives propagation from peer group X (*)
1604unbindable  mount is unbindable
1605
1606(*) X is the closest dominant peer group under the process's root.  If
1607X is the immediate master of the mount, or if there's no dominant peer
1608group under the same root, then only the "master:X" field is present
1609and not the "propagate_from:X" field.
1610
1611For more information on mount propagation see:
1612
1613  Documentation/filesystems/sharedsubtree.txt
1614
1615
16163.6     /proc/<pid>/comm  & /proc/<pid>/task/<tid>/comm
1617--------------------------------------------------------
1618These files provide a method to access a tasks comm value. It also allows for
1619a task to set its own or one of its thread siblings comm value. The comm value
1620is limited in size compared to the cmdline value, so writing anything longer
1621then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated
1622comm value.
1623
1624
16253.7     /proc/<pid>/task/<tid>/children - Information about task children
1626-------------------------------------------------------------------------
1627This file provides a fast way to retrieve first level children pids
1628of a task pointed by <pid>/<tid> pair. The format is a space separated
1629stream of pids.
1630
1631Note the "first level" here -- if a child has own children they will
1632not be listed here, one needs to read /proc/<children-pid>/task/<tid>/children
1633to obtain the descendants.
1634
1635Since this interface is intended to be fast and cheap it doesn't
1636guarantee to provide precise results and some children might be
1637skipped, especially if they've exited right after we printed their
1638pids, so one need to either stop or freeze processes being inspected
1639if precise results are needed.
1640
1641
16423.7     /proc/<pid>/fdinfo/<fd> - Information about opened file
1643---------------------------------------------------------------
1644This file provides information associated with an opened file. The regular
1645files have at least two fields -- 'pos' and 'flags'. The 'pos' represents
1646the current offset of the opened file in decimal form [see lseek(2) for
1647details] and 'flags' denotes the octal O_xxx mask the file has been
1648created with [see open(2) for details].
1649
1650A typical output is
1651
1652        pos:    0
1653        flags:  0100002
1654
1655The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags
1656pair provide additional information particular to the objects they represent.
1657
1658        Eventfd files
1659        ~~~~~~~~~~~~~
1660        pos:    0
1661        flags:  04002
1662        eventfd-count:  5a
1663
1664        where 'eventfd-count' is hex value of a counter.
1665
1666        Signalfd files
1667        ~~~~~~~~~~~~~~
1668        pos:    0
1669        flags:  04002
1670        sigmask:        0000000000000200
1671
1672        where 'sigmask' is hex value of the signal mask associated
1673        with a file.
1674
1675        Epoll files
1676        ~~~~~~~~~~~
1677        pos:    0
1678        flags:  02
1679        tfd:        5 events:       1d data: ffffffffffffffff
1680
1681        where 'tfd' is a target file descriptor number in decimal form,
1682        'events' is events mask being watched and the 'data' is data
1683        associated with a target [see epoll(7) for more details].
1684
1685        Fsnotify files
1686        ~~~~~~~~~~~~~~
1687        For inotify files the format is the following
1688
1689        pos:    0
1690        flags:  02000000
1691        inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d
1692
1693        where 'wd' is a watch descriptor in decimal form, ie a target file
1694        descriptor number, 'ino' and 'sdev' are inode and device where the
1695        target file resides and the 'mask' is the mask of events, all in hex
1696        form [see inotify(7) for more details].
1697
1698        If the kernel was built with exportfs support, the path to the target
1699        file is encoded as a file handle.  The file handle is provided by three
1700        fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex
1701        format.
1702
1703        If the kernel is built without exportfs support the file handle won't be
1704        printed out.
1705
1706        If there is no inotify mark attached yet the 'inotify' line will be omitted.
1707
1708        For fanotify files the format is
1709
1710        pos:    0
1711        flags:  02
1712        fanotify flags:10 event-flags:0
1713        fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003
1714        fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4
1715
1716        where fanotify 'flags' and 'event-flags' are values used in fanotify_init
1717        call, 'mnt_id' is the mount point identifier, 'mflags' is the value of
1718        flags associated with mark which are tracked separately from events
1719        mask. 'ino', 'sdev' are target inode and device, 'mask' is the events
1720        mask and 'ignored_mask' is the mask of events which are to be ignored.
1721        All in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask'
1722        does provide information about flags and mask used in fanotify_mark
1723        call [see fsnotify manpage for details].
1724
1725        While the first three lines are mandatory and always printed, the rest is
1726        optional and may be omitted if no marks created yet.
1727
1728
1729------------------------------------------------------------------------------
1730Configuring procfs
1731------------------------------------------------------------------------------
1732
17334.1     Mount options
1734---------------------
1735
1736The following mount options are supported:
1737
1738        hidepid=        Set /proc/<pid>/ access mode.
1739        gid=            Set the group authorized to learn processes information.
1740
1741hidepid=0 means classic mode - everybody may access all /proc/<pid>/ directories
1742(default).
1743
1744hidepid=1 means users may not access any /proc/<pid>/ directories but their
1745own.  Sensitive files like cmdline, sched*, status are now protected against
1746other users.  This makes it impossible to learn whether any user runs
1747specific program (given the program doesn't reveal itself by its behaviour).
1748As an additional bonus, as /proc/<pid>/cmdline is unaccessible for other users,
1749poorly written programs passing sensitive information via program arguments are
1750now protected against local eavesdroppers.
1751
1752hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be fully invisible to other
1753users.  It doesn't mean that it hides a fact whether a process with a specific
1754pid value exists (it can be learned by other means, e.g. by "kill -0 $PID"),
1755but it hides process' uid and gid, which may be learned by stat()'ing
1756/proc/<pid>/ otherwise.  It greatly complicates an intruder's task of gathering
1757information about running processes, whether some daemon runs with elevated
1758privileges, whether other user runs some sensitive program, whether other users
1759run any program at all, etc.
1760
1761gid= defines a group authorized to learn processes information otherwise
1762prohibited by hidepid=.  If you use some daemon like identd which needs to learn
1763information about processes information, just add identd to this group.
1764
lxr.linux.no kindly hosted by Redpill Linpro AS, provider of Linux consulting and operations services since 1995.