1 ------------------------------------------------------------------------------
2 T H E /proc F I L E S Y S T E M
3 ------------------------------------------------------------------------------
9 ------------------------------------------------------------------------------
10 Version 1.3 Kernel version 2.2.12
11 Kernel version 2.4.0-test11-pre4
12 ------------------------------------------------------------------------------
19 0.1 Introduction/Credits
22 1 Collecting System Information
23 1.1 Process-Specific Subdirectories
25 1.3 IDE devices in /proc/ide
26 1.4 Networking info in /proc/net
28 1.6 Parallel port info in /proc/parport
29 1.7 TTY info in /proc/tty
30 1.8 Miscellaneous kernel statistics in /proc/stat
31 1.9 Ext4 file system parameters
33 2 Modifying System Parameters
35 3 Per-Process Parameters
36 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj - Adjust the oom-killer
38 3.2 /proc/<pid>/oom_score - Display current oom-killer score
39 3.3 /proc/<pid>/io - Display the IO accounting fields
40 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings
41 3.5 /proc/<pid>/mountinfo - Information about mounts
42 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm
43 3.7 /proc/<pid>/task/<tid>/children - Information about task children
44 3.8 /proc/<pid>/fdinfo/<fd> - Information about opened file
45 3.9 /proc/<pid>/map_files - Information about memory mapped files
50 ------------------------------------------------------------------------------
52 ------------------------------------------------------------------------------
54 0.1 Introduction/Credits
55 ------------------------
57 This documentation is part of a soon (or so we hope) to be released book on
58 the SuSE Linux distribution. As there is no complete documentation for the
59 /proc file system and we've used many freely available sources to write these
60 chapters, it seems only fair to give the work back to the Linux community.
61 This work is based on the 2.2.* kernel version and the upcoming 2.4.*. I'm
62 afraid it's still far from complete, but we hope it will be useful. As far as
63 we know, it is the first 'all-in-one' document about the /proc file system. It
64 is focused on the Intel x86 hardware, so if you are looking for PPC, ARM,
65 SPARC, AXP, etc., features, you probably won't find what you are looking for.
66 It also only covers IPv4 networking, not IPv6 nor other protocols - sorry. But
67 additions and patches are welcome and will be added to this document if you
70 We'd like to thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of
71 other people for help compiling this documentation. We'd also like to extend a
72 special thank you to Andi Kleen for documentation, which we relied on heavily
73 to create this document, as well as the additional information he provided.
74 Thanks to everybody else who contributed source or docs to the Linux kernel
75 and helped create a great piece of software... :)
77 If you have any comments, corrections or additions, please don't hesitate to
81 The latest version of this document is available online at
82 http://tldp.org/LDP/Linux-Filesystem-Hierarchy/html/proc.html
84 If the above direction does not works for you, you could try the kernel
91 We don't guarantee the correctness of this document, and if you come to us
92 complaining about how you screwed up your system because of incorrect
93 documentation, we won't feel responsible...
95 ------------------------------------------------------------------------------
96 CHAPTER 1: COLLECTING SYSTEM INFORMATION
97 ------------------------------------------------------------------------------
99 ------------------------------------------------------------------------------
101 ------------------------------------------------------------------------------
102 * Investigating the properties of the pseudo file system /proc and its
103 ability to provide information on the running Linux system
104 * Examining /proc's structure
105 * Uncovering various information about the kernel and the processes running
107 ------------------------------------------------------------------------------
110 The proc file system acts as an interface to internal data structures in the
111 kernel. It can be used to obtain information about the system and to change
112 certain kernel parameters at runtime (sysctl).
114 First, we'll take a look at the read-only parts of /proc. In Chapter 2, we
115 show you how you can use /proc/sys to change settings.
117 1.1 Process-Specific Subdirectories
118 -----------------------------------
120 The directory /proc contains (among other things) one subdirectory for each
121 process running on the system, which is named after the process ID (PID).
123 The link self points to the process reading the file system. Each process
124 subdirectory has the entries listed in Table 1-1.
127 Table 1-1: Process specific entries in /proc
128 ..............................................................................
130 clear_refs Clears page referenced bits shown in smaps output
131 cmdline Command line arguments
132 cpu Current and last cpu in which it was executed (2.4)(smp)
133 cwd Link to the current working directory
134 environ Values of environment variables
135 exe Link to the executable of this process
136 fd Directory, which contains all file descriptors
137 maps Memory maps to executables and library files (2.4)
138 mem Memory held by this process
139 root Link to the root directory of this process
141 statm Process memory status information
142 status Process status in human readable form
143 wchan If CONFIG_KALLSYMS is set, a pre-decoded wchan
145 stack Report full stack trace, enable via CONFIG_STACKTRACE
146 smaps a extension based on maps, showing the memory consumption of
147 each mapping and flags associated with it
148 numa_maps an extension based on maps, showing the memory locality and
149 binding policy as well as mem usage (in pages) of each mapping.
150 ..............................................................................
152 For example, to get the status information of a process, all you have to do is
153 read the file /proc/PID/status:
155 >cat /proc/self/status
179 SigPnd: 0000000000000000
180 ShdPnd: 0000000000000000
181 SigBlk: 0000000000000000
182 SigIgn: 0000000000000000
183 SigCgt: 0000000000000000
184 CapInh: 00000000fffffeff
185 CapPrm: 0000000000000000
186 CapEff: 0000000000000000
187 CapBnd: ffffffffffffffff
189 voluntary_ctxt_switches: 0
190 nonvoluntary_ctxt_switches: 1
192 This shows you nearly the same information you would get if you viewed it with
193 the ps command. In fact, ps uses the proc file system to obtain its
194 information. But you get a more detailed view of the process by reading the
195 file /proc/PID/status. It fields are described in table 1-2.
197 The statm file contains more detailed information about the process
198 memory usage. Its seven fields are explained in Table 1-3. The stat file
199 contains details information about the process itself. Its fields are
200 explained in Table 1-4.
202 (for SMP CONFIG users)
203 For making accounting scalable, RSS related information are handled in an
204 asynchronous manner and the value may not be very precise. To see a precise
205 snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
206 It's slow but very precise.
208 Table 1-2: Contents of the status files (as of 4.1)
209 ..............................................................................
211 Name filename of the executable
212 State state (R is running, S is sleeping, D is sleeping
213 in an uninterruptible wait, Z is zombie,
214 T is traced or stopped)
216 Ngid NUMA group ID (0 if none)
218 PPid process id of the parent process
219 TracerPid PID of process tracing this process (0 if not)
220 Uid Real, effective, saved set, and file system UIDs
221 Gid Real, effective, saved set, and file system GIDs
222 FDSize number of file descriptor slots currently allocated
223 Groups supplementary group list
224 NStgid descendant namespace thread group ID hierarchy
225 NSpid descendant namespace process ID hierarchy
226 NSpgid descendant namespace process group ID hierarchy
227 NSsid descendant namespace session ID hierarchy
228 VmPeak peak virtual memory size
229 VmSize total program size
230 VmLck locked memory size
231 VmHWM peak resident set size ("high water mark")
232 VmRSS size of memory portions
233 VmData size of data, stack, and text segments
234 VmStk size of data, stack, and text segments
235 VmExe size of text segment
236 VmLib size of shared library code
237 VmPTE size of page table entries
238 VmPMD size of second level page tables
239 VmSwap size of swap usage (the number of referred swapents)
240 Threads number of threads
241 SigQ number of signals queued/max. number for queue
242 SigPnd bitmap of pending signals for the thread
243 ShdPnd bitmap of shared pending signals for the process
244 SigBlk bitmap of blocked signals
245 SigIgn bitmap of ignored signals
246 SigCgt bitmap of caught signals
247 CapInh bitmap of inheritable capabilities
248 CapPrm bitmap of permitted capabilities
249 CapEff bitmap of effective capabilities
250 CapBnd bitmap of capabilities bounding set
251 Seccomp seccomp mode, like prctl(PR_GET_SECCOMP, ...)
252 Cpus_allowed mask of CPUs on which this process may run
253 Cpus_allowed_list Same as previous, but in "list format"
254 Mems_allowed mask of memory nodes allowed to this process
255 Mems_allowed_list Same as previous, but in "list format"
256 voluntary_ctxt_switches number of voluntary context switches
257 nonvoluntary_ctxt_switches number of non voluntary context switches
258 ..............................................................................
260 Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
261 ..............................................................................
263 size total program size (pages) (same as VmSize in status)
264 resident size of memory portions (pages) (same as VmRSS in status)
265 shared number of pages that are shared (i.e. backed by a file)
266 trs number of pages that are 'code' (not including libs; broken,
267 includes data segment)
268 lrs number of pages of library (always 0 on 2.6)
269 drs number of pages of data/stack (including libs; broken,
270 includes library text)
271 dt number of dirty pages (always 0 on 2.6)
272 ..............................................................................
275 Table 1-4: Contents of the stat files (as of 2.6.30-rc7)
276 ..............................................................................
279 tcomm filename of the executable
280 state state (R is running, S is sleeping, D is sleeping in an
281 uninterruptible wait, Z is zombie, T is traced or stopped)
282 ppid process id of the parent process
283 pgrp pgrp of the process
285 tty_nr tty the process uses
286 tty_pgrp pgrp of the tty
288 min_flt number of minor faults
289 cmin_flt number of minor faults with child's
290 maj_flt number of major faults
291 cmaj_flt number of major faults with child's
292 utime user mode jiffies
293 stime kernel mode jiffies
294 cutime user mode jiffies with child's
295 cstime kernel mode jiffies with child's
296 priority priority level
298 num_threads number of threads
299 it_real_value (obsolete, always 0)
300 start_time time the process started after system boot
301 vsize virtual memory size
302 rss resident set memory size
303 rsslim current limit in bytes on the rss
304 start_code address above which program text can run
305 end_code address below which program text can run
306 start_stack address of the start of the main process stack
307 esp current value of ESP
308 eip current value of EIP
309 pending bitmap of pending signals
310 blocked bitmap of blocked signals
311 sigign bitmap of ignored signals
312 sigcatch bitmap of caught signals
313 wchan address where process went to sleep
316 exit_signal signal to send to parent thread on exit
317 task_cpu which CPU the task is scheduled on
318 rt_priority realtime priority
319 policy scheduling policy (man sched_setscheduler)
320 blkio_ticks time spent waiting for block IO
321 gtime guest time of the task in jiffies
322 cgtime guest time of the task children in jiffies
323 start_data address above which program data+bss is placed
324 end_data address below which program data+bss is placed
325 start_brk address above which program heap can be expanded with brk()
326 arg_start address above which program command line is placed
327 arg_end address below which program command line is placed
328 env_start address above which program environment is placed
329 env_end address below which program environment is placed
330 exit_code the thread's exit_code in the form reported by the waitpid system call
331 ..............................................................................
333 The /proc/PID/maps file containing the currently mapped memory regions and
334 their access permissions.
338 address perms offset dev inode pathname
340 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test
341 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test
342 0804a000-0806b000 rw-p 00000000 00:00 0 [heap]
343 a7cb1000-a7cb2000 ---p 00000000 00:00 0
344 a7cb2000-a7eb2000 rw-p 00000000 00:00 0
345 a7eb2000-a7eb3000 ---p 00000000 00:00 0
346 a7eb3000-a7ed5000 rw-p 00000000 00:00 0 [stack:1001]
347 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6
348 a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6
349 a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6
350 a800b000-a800e000 rw-p 00000000 00:00 0
351 a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0
352 a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0
353 a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0
354 a8024000-a8027000 rw-p 00000000 00:00 0
355 a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2
356 a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2
357 a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2
358 aff35000-aff4a000 rw-p 00000000 00:00 0 [stack]
359 ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso]
361 where "address" is the address space in the process that it occupies, "perms"
362 is a set of permissions:
368 p = private (copy on write)
370 "offset" is the offset into the mapping, "dev" is the device (major:minor), and
371 "inode" is the inode on that device. 0 indicates that no inode is associated
372 with the memory region, as the case would be with BSS (uninitialized data).
373 The "pathname" shows the name associated file for this mapping. If the mapping
374 is not associated with a file:
376 [heap] = the heap of the program
377 [stack] = the stack of the main process
378 [stack:1001] = the stack of the thread with tid 1001
379 [vdso] = the "virtual dynamic shared object",
380 the kernel system call handler
382 or if empty, the mapping is anonymous.
384 The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint
385 of the individual tasks of a process. In this file you will see a mapping marked
386 as [stack] if that task sees it as a stack. This is a key difference from the
387 content of /proc/PID/maps, where you will see all mappings that are being used
388 as stack by all of those tasks. Hence, for the example above, the task-level
389 map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
391 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test
392 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test
393 0804a000-0806b000 rw-p 00000000 00:00 0 [heap]
394 a7cb1000-a7cb2000 ---p 00000000 00:00 0
395 a7cb2000-a7eb2000 rw-p 00000000 00:00 0
396 a7eb2000-a7eb3000 ---p 00000000 00:00 0
397 a7eb3000-a7ed5000 rw-p 00000000 00:00 0 [stack]
398 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6
399 a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6
400 a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6
401 a800b000-a800e000 rw-p 00000000 00:00 0
402 a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0
403 a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0
404 a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0
405 a8024000-a8027000 rw-p 00000000 00:00 0
406 a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2
407 a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2
408 a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2
409 aff35000-aff4a000 rw-p 00000000 00:00 0
410 ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso]
412 The /proc/PID/smaps is an extension based on maps, showing the memory
413 consumption for each of the process's mappings. For each of mappings there
414 is a series of lines such as the following:
416 08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash
431 VmFlags: rd ex mr mw me de
433 the first of these lines shows the same information as is displayed for the
434 mapping in /proc/PID/maps. The remaining lines show the size of the mapping
435 (size), the amount of the mapping that is currently resident in RAM (RSS), the
436 process' proportional share of this mapping (PSS), the number of clean and
437 dirty private pages in the mapping.
439 The "proportional set size" (PSS) of a process is the count of pages it has
440 in memory, where each page is divided by the number of processes sharing it.
441 So if a process has 1000 pages all to itself, and 1000 shared with one other
442 process, its PSS will be 1500.
443 Note that even a page which is part of a MAP_SHARED mapping, but has only
444 a single pte mapped, i.e. is currently used by only one process, is accounted
445 as private and not as shared.
446 "Referenced" indicates the amount of memory currently marked as referenced or
448 "Anonymous" shows the amount of memory that does not belong to any file. Even
449 a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
450 and a page is modified, the file page is replaced by a private anonymous copy.
451 "Swap" shows how much would-be-anonymous memory is also used, but out on
453 "SwapPss" shows proportional swap share of this mapping.
454 "VmFlags" field deserves a separate description. This member represents the kernel
455 flags associated with the particular virtual memory area in two letter encoded
456 manner. The codes are the following:
465 gd - stack segment growns down
467 dw - disabled write to the mapped file
468 lo - pages are locked in memory
469 io - memory mapped I/O area
470 sr - sequential read advise provided
471 rr - random read advise provided
472 dc - do not copy area on fork
473 de - do not expand area on remapping
474 ac - area is accountable
475 nr - swap space is not reserved for the area
476 ht - area uses huge tlb pages
477 nl - non-linear mapping
478 ar - architecture specific flag
479 dd - do not include area into core dump
482 hg - huge page advise flag
483 nh - no-huge page advise flag
484 mg - mergable advise flag
486 Note that there is no guarantee that every flag and associated mnemonic will
487 be present in all further kernel releases. Things get changed, the flags may
488 be vanished or the reverse -- new added.
490 This file is only present if the CONFIG_MMU kernel configuration option is
493 The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
494 bits on both physical and virtual pages associated with a process, and the
495 soft-dirty bit on pte (see Documentation/vm/soft-dirty.txt for details).
496 To clear the bits for all the pages associated with the process
497 > echo 1 > /proc/PID/clear_refs
499 To clear the bits for the anonymous pages associated with the process
500 > echo 2 > /proc/PID/clear_refs
502 To clear the bits for the file mapped pages associated with the process
503 > echo 3 > /proc/PID/clear_refs
505 To clear the soft-dirty bit
506 > echo 4 > /proc/PID/clear_refs
508 To reset the peak resident set size ("high water mark") to the process's
510 > echo 5 > /proc/PID/clear_refs
512 Any other value written to /proc/PID/clear_refs will have no effect.
514 The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
515 using /proc/kpageflags and number of times a page is mapped using
516 /proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.txt.
518 The /proc/pid/numa_maps is an extension based on maps, showing the memory
519 locality and binding policy, as well as the memory usage (in pages) of
520 each mapping. The output follows a general format where mapping details get
521 summarized separated by blank spaces, one mapping per each file line:
523 address policy mapping details
525 00400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4
526 00600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4
527 3206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4
528 320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
529 3206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
530 3206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4
531 3206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4
532 320698b000 default file=/lib64/libc-2.12.so
533 3206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4
534 3206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
535 3206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4
536 7f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4
537 7f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4
538 7f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048
539 7fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4
540 7fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4
543 "address" is the starting address for the mapping;
544 "policy" reports the NUMA memory policy set for the mapping (see vm/numa_memory_policy.txt);
545 "mapping details" summarizes mapping data such as mapping type, page usage counters,
546 node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page
547 size, in KB, that is backing the mapping up.
552 Similar to the process entries, the kernel data files give information about
553 the running kernel. The files used to obtain this information are contained in
554 /proc and are listed in Table 1-5. Not all of these will be present in your
555 system. It depends on the kernel configuration and the loaded modules, which
556 files are there, and which are missing.
558 Table 1-5: Kernel info in /proc
559 ..............................................................................
561 apm Advanced power management info
562 buddyinfo Kernel memory allocator information (see text) (2.5)
563 bus Directory containing bus specific information
564 cmdline Kernel command line
565 cpuinfo Info about the CPU
566 devices Available devices (block and character)
567 dma Used DMS channels
568 filesystems Supported filesystems
569 driver Various drivers grouped here, currently rtc (2.4)
570 execdomains Execdomains, related to security (2.4)
571 fb Frame Buffer devices (2.4)
572 fs File system parameters, currently nfs/exports (2.4)
573 ide Directory containing info about the IDE subsystem
574 interrupts Interrupt usage
575 iomem Memory map (2.4)
576 ioports I/O port usage
577 irq Masks for irq to cpu affinity (2.4)(smp?)
578 isapnp ISA PnP (Plug&Play) Info (2.4)
579 kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4))
581 ksyms Kernel symbol table
582 loadavg Load average of last 1, 5 & 15 minutes
586 modules List of loaded modules
587 mounts Mounted filesystems
588 net Networking info (see text)
589 pagetypeinfo Additional page allocator information (see text) (2.5)
590 partitions Table of partitions known to the system
591 pci Deprecated info of PCI bus (new way -> /proc/bus/pci/,
592 decoupled by lspci (2.4)
594 scsi SCSI info (see text)
595 slabinfo Slab pool info
596 softirqs softirq usage
597 stat Overall statistics
598 swaps Swap space utilization
600 sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4)
601 tty Info of tty drivers
602 uptime Wall clock since boot, combined idle time of all cpus
603 version Kernel version
604 video bttv info of video resources (2.4)
605 vmallocinfo Show vmalloced areas
606 ..............................................................................
608 You can, for example, check which interrupts are currently in use and what
609 they are used for by looking in the file /proc/interrupts:
611 > cat /proc/interrupts
613 0: 8728810 XT-PIC timer
614 1: 895 XT-PIC keyboard
616 3: 531695 XT-PIC aha152x
617 4: 2014133 XT-PIC serial
618 5: 44401 XT-PIC pcnet_cs
621 12: 182918 XT-PIC PS/2 Mouse
623 14: 1232265 XT-PIC ide0
627 In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the
628 output of a SMP machine):
630 > cat /proc/interrupts
633 0: 1243498 1214548 IO-APIC-edge timer
634 1: 8949 8958 IO-APIC-edge keyboard
635 2: 0 0 XT-PIC cascade
636 5: 11286 10161 IO-APIC-edge soundblaster
637 8: 1 0 IO-APIC-edge rtc
638 9: 27422 27407 IO-APIC-edge 3c503
639 12: 113645 113873 IO-APIC-edge PS/2 Mouse
641 14: 22491 24012 IO-APIC-edge ide0
642 15: 2183 2415 IO-APIC-edge ide1
643 17: 30564 30414 IO-APIC-level eth0
644 18: 177 164 IO-APIC-level bttv
649 NMI is incremented in this case because every timer interrupt generates a NMI
650 (Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups.
652 LOC is the local interrupt counter of the internal APIC of every CPU.
654 ERR is incremented in the case of errors in the IO-APIC bus (the bus that
655 connects the CPUs in a SMP system. This means that an error has been detected,
656 the IO-APIC automatically retry the transmission, so it should not be a big
657 problem, but you should read the SMP-FAQ.
659 In 2.6.2* /proc/interrupts was expanded again. This time the goal was for
660 /proc/interrupts to display every IRQ vector in use by the system, not
661 just those considered 'most important'. The new vectors are:
663 THR -- interrupt raised when a machine check threshold counter
664 (typically counting ECC corrected errors of memory or cache) exceeds
665 a configurable threshold. Only available on some systems.
667 TRM -- a thermal event interrupt occurs when a temperature threshold
668 has been exceeded for the CPU. This interrupt may also be generated
669 when the temperature drops back to normal.
671 SPU -- a spurious interrupt is some interrupt that was raised then lowered
672 by some IO device before it could be fully processed by the APIC. Hence
673 the APIC sees the interrupt but does not know what device it came from.
674 For this case the APIC will generate the interrupt with a IRQ vector
675 of 0xff. This might also be generated by chipset bugs.
677 RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are
678 sent from one CPU to another per the needs of the OS. Typically,
679 their statistics are used by kernel developers and interested users to
680 determine the occurrence of interrupts of the given type.
682 The above IRQ vectors are displayed only when relevant. For example,
683 the threshold vector does not exist on x86_64 platforms. Others are
684 suppressed when the system is a uniprocessor. As of this writing, only
685 i386 and x86_64 platforms support the new IRQ vector displays.
687 Of some interest is the introduction of the /proc/irq directory to 2.4.
688 It could be used to set IRQ to CPU affinity, this means that you can "hook" an
689 IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
690 irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and
695 0 10 12 14 16 18 2 4 6 8 prof_cpu_mask
696 1 11 13 15 17 19 3 5 7 9 default_smp_affinity
700 smp_affinity is a bitmask, in which you can specify which CPUs can handle the
701 IRQ, you can set it by doing:
703 > echo 1 > /proc/irq/10/smp_affinity
705 This means that only the first CPU will handle the IRQ, but you can also echo
706 5 which means that only the first and fourth CPU can handle the IRQ.
708 The contents of each smp_affinity file is the same by default:
710 > cat /proc/irq/0/smp_affinity
713 There is an alternate interface, smp_affinity_list which allows specifying
714 a cpu range instead of a bitmask:
716 > cat /proc/irq/0/smp_affinity_list
719 The default_smp_affinity mask applies to all non-active IRQs, which are the
720 IRQs which have not yet been allocated/activated, and hence which lack a
721 /proc/irq/[0-9]* directory.
723 The node file on an SMP system shows the node to which the device using the IRQ
724 reports itself as being attached. This hardware locality information does not
725 include information about any possible driver locality preference.
727 prof_cpu_mask specifies which CPUs are to be profiled by the system wide
728 profiler. Default value is ffffffff (all cpus if there are only 32 of them).
730 The way IRQs are routed is handled by the IO-APIC, and it's Round Robin
731 between all the CPUs which are allowed to handle it. As usual the kernel has
732 more info than you and does a better job than you, so the defaults are the
733 best choice for almost everyone. [Note this applies only to those IO-APIC's
734 that support "Round Robin" interrupt distribution.]
736 There are three more important subdirectories in /proc: net, scsi, and sys.
737 The general rule is that the contents, or even the existence of these
738 directories, depend on your kernel configuration. If SCSI is not enabled, the
739 directory scsi may not exist. The same is true with the net, which is there
740 only when networking support is present in the running kernel.
742 The slabinfo file gives information about memory usage at the slab level.
743 Linux uses slab pools for memory management above page level in version 2.2.
744 Commonly used objects have their own slab pool (such as network buffers,
745 directory cache, and so on).
747 ..............................................................................
749 > cat /proc/buddyinfo
751 Node 0, zone DMA 0 4 5 4 4 3 ...
752 Node 0, zone Normal 1 0 0 1 101 8 ...
753 Node 0, zone HighMem 2 0 0 1 1 0 ...
755 External fragmentation is a problem under some workloads, and buddyinfo is a
756 useful tool for helping diagnose these problems. Buddyinfo will give you a
757 clue as to how big an area you can safely allocate, or why a previous
760 Each column represents the number of pages of a certain order which are
761 available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in
762 ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE
763 available in ZONE_NORMAL, etc...
765 More information relevant to external fragmentation can be found in
768 > cat /proc/pagetypeinfo
772 Free pages count per migrate type at order 0 1 2 3 4 5 6 7 8 9 10
773 Node 0, zone DMA, type Unmovable 0 0 0 1 1 1 1 1 1 1 0
774 Node 0, zone DMA, type Reclaimable 0 0 0 0 0 0 0 0 0 0 0
775 Node 0, zone DMA, type Movable 1 1 2 1 2 1 1 0 1 0 2
776 Node 0, zone DMA, type Reserve 0 0 0 0 0 0 0 0 0 1 0
777 Node 0, zone DMA, type Isolate 0 0 0 0 0 0 0 0 0 0 0
778 Node 0, zone DMA32, type Unmovable 103 54 77 1 1 1 11 8 7 1 9
779 Node 0, zone DMA32, type Reclaimable 0 0 2 1 0 0 0 0 1 0 0
780 Node 0, zone DMA32, type Movable 169 152 113 91 77 54 39 13 6 1 452
781 Node 0, zone DMA32, type Reserve 1 2 2 2 2 0 1 1 1 1 0
782 Node 0, zone DMA32, type Isolate 0 0 0 0 0 0 0 0 0 0 0
784 Number of blocks type Unmovable Reclaimable Movable Reserve Isolate
785 Node 0, zone DMA 2 0 5 1 0
786 Node 0, zone DMA32 41 6 967 2 0
788 Fragmentation avoidance in the kernel works by grouping pages of different
789 migrate types into the same contiguous regions of memory called page blocks.
790 A page block is typically the size of the default hugepage size e.g. 2MB on
791 X86-64. By keeping pages grouped based on their ability to move, the kernel
792 can reclaim pages within a page block to satisfy a high-order allocation.
794 The pagetypinfo begins with information on the size of a page block. It
795 then gives the same type of information as buddyinfo except broken down
796 by migrate-type and finishes with details on how many page blocks of each
799 If min_free_kbytes has been tuned correctly (recommendations made by hugeadm
800 from libhugetlbfs http://sourceforge.net/projects/libhugetlbfs/), one can
801 make an estimate of the likely number of huge pages that can be allocated
802 at a given point in time. All the "Movable" blocks should be allocatable
803 unless memory has been mlock()'d. Some of the Reclaimable blocks should
804 also be allocatable although a lot of filesystem metadata may have to be
805 reclaimed to achieve this.
807 ..............................................................................
811 Provides information about distribution and utilization of memory. This
812 varies by architecture and compile options. The following is from a
813 16GB PIII, which has highmem enabled. You may not have all of these fields.
817 The "Locked" indicates whether the mapping is locked in memory or not.
820 MemTotal: 16344972 kB
822 MemAvailable: 14836172 kB
828 HighTotal: 15597528 kB
829 HighFree: 13629632 kB
839 SReclaimable: 159856 kB
840 SUnreclaim: 124508 kB
845 CommitLimit: 7669796 kB
846 Committed_AS: 100056 kB
847 VmallocTotal: 112216 kB
849 VmallocChunk: 111088 kB
850 AnonHugePages: 49152 kB
852 MemTotal: Total usable ram (i.e. physical ram minus a few reserved
853 bits and the kernel binary code)
854 MemFree: The sum of LowFree+HighFree
855 MemAvailable: An estimate of how much memory is available for starting new
856 applications, without swapping. Calculated from MemFree,
857 SReclaimable, the size of the file LRU lists, and the low
858 watermarks in each zone.
859 The estimate takes into account that the system needs some
860 page cache to function well, and that not all reclaimable
861 slab will be reclaimable, due to items being in use. The
862 impact of those factors will vary from system to system.
863 Buffers: Relatively temporary storage for raw disk blocks
864 shouldn't get tremendously large (20MB or so)
865 Cached: in-memory cache for files read from the disk (the
866 pagecache). Doesn't include SwapCached
867 SwapCached: Memory that once was swapped out, is swapped back in but
868 still also is in the swapfile (if memory is needed it
869 doesn't need to be swapped out AGAIN because it is already
870 in the swapfile. This saves I/O)
871 Active: Memory that has been used more recently and usually not
872 reclaimed unless absolutely necessary.
873 Inactive: Memory which has been less recently used. It is more
874 eligible to be reclaimed for other purposes
876 HighFree: Highmem is all memory above ~860MB of physical memory
877 Highmem areas are for use by userspace programs, or
878 for the pagecache. The kernel must use tricks to access
879 this memory, making it slower to access than lowmem.
881 LowFree: Lowmem is memory which can be used for everything that
882 highmem can be used for, but it is also available for the
883 kernel's use for its own data structures. Among many
884 other things, it is where everything from the Slab is
885 allocated. Bad things happen when you're out of lowmem.
886 SwapTotal: total amount of swap space available
887 SwapFree: Memory which has been evicted from RAM, and is temporarily
889 Dirty: Memory which is waiting to get written back to the disk
890 Writeback: Memory which is actively being written back to the disk
891 AnonPages: Non-file backed pages mapped into userspace page tables
892 AnonHugePages: Non-file backed huge pages mapped into userspace page tables
893 Mapped: files which have been mmaped, such as libraries
894 Slab: in-kernel data structures cache
895 SReclaimable: Part of Slab, that might be reclaimed, such as caches
896 SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure
897 PageTables: amount of memory dedicated to the lowest level of page
899 NFS_Unstable: NFS pages sent to the server, but not yet committed to stable
901 Bounce: Memory used for block device "bounce buffers"
902 WritebackTmp: Memory used by FUSE for temporary writeback buffers
903 CommitLimit: Based on the overcommit ratio ('vm.overcommit_ratio'),
904 this is the total amount of memory currently available to
905 be allocated on the system. This limit is only adhered to
906 if strict overcommit accounting is enabled (mode 2 in
907 'vm.overcommit_memory').
908 The CommitLimit is calculated with the following formula:
909 CommitLimit = ([total RAM pages] - [total huge TLB pages]) *
910 overcommit_ratio / 100 + [total swap pages]
911 For example, on a system with 1G of physical RAM and 7G
912 of swap with a `vm.overcommit_ratio` of 30 it would
913 yield a CommitLimit of 7.3G.
914 For more details, see the memory overcommit documentation
915 in vm/overcommit-accounting.
916 Committed_AS: The amount of memory presently allocated on the system.
917 The committed memory is a sum of all of the memory which
918 has been allocated by processes, even if it has not been
919 "used" by them as of yet. A process which malloc()'s 1G
920 of memory, but only touches 300M of it will show up as
921 using 1G. This 1G is memory which has been "committed" to
922 by the VM and can be used at any time by the allocating
923 application. With strict overcommit enabled on the system
924 (mode 2 in 'vm.overcommit_memory'),allocations which would
925 exceed the CommitLimit (detailed above) will not be permitted.
926 This is useful if one needs to guarantee that processes will
927 not fail due to lack of memory once that memory has been
928 successfully allocated.
929 VmallocTotal: total size of vmalloc memory area
930 VmallocUsed: amount of vmalloc area which is used
931 VmallocChunk: largest contiguous block of vmalloc area which is free
933 ..............................................................................
937 Provides information about vmalloced/vmaped areas. One line per area,
938 containing the virtual address range of the area, size in bytes,
939 caller information of the creator, and optional information depending
940 on the kind of area :
942 pages=nr number of pages
943 phys=addr if a physical address was specified
944 ioremap I/O mapping (ioremap() and friends)
945 vmalloc vmalloc() area
948 vpages buffer for pages pointers was vmalloced (huge area)
949 N<node>=nr (Only on NUMA kernels)
950 Number of pages allocated on memory node <node>
952 > cat /proc/vmallocinfo
953 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ...
954 /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128
955 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ...
956 /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64
957 0xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f...
958 phys=7fee8000 ioremap
959 0xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f...
960 phys=7fee7000 ioremap
961 0xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210
962 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ...
963 /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3
964 0xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ...
966 0xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ...
967 /0x130 [x_tables] pages=4 vmalloc N0=4
968 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ...
969 pages=14 vmalloc N2=14
970 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ...
972 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ...
974 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ...
975 pages=10 vmalloc N0=10
977 ..............................................................................
981 Provides counts of softirq handlers serviced since boot time, for each cpu.
986 TIMER: 27166 27120 27097 27034
991 SCHED: 27035 26983 26971 26746
993 RCU: 1678 1769 2178 2250
996 1.3 IDE devices in /proc/ide
997 ----------------------------
999 The subdirectory /proc/ide contains information about all IDE devices of which
1000 the kernel is aware. There is one subdirectory for each IDE controller, the
1001 file drivers and a link for each IDE device, pointing to the device directory
1002 in the controller specific subtree.
1004 The file drivers contains general information about the drivers used for the
1007 > cat /proc/ide/drivers
1008 ide-cdrom version 4.53
1009 ide-disk version 1.08
1011 More detailed information can be found in the controller specific
1012 subdirectories. These are named ide0, ide1 and so on. Each of these
1013 directories contains the files shown in table 1-6.
1016 Table 1-6: IDE controller info in /proc/ide/ide?
1017 ..............................................................................
1019 channel IDE channel (0 or 1)
1020 config Configuration (only for PCI/IDE bridge)
1022 model Type/Chipset of IDE controller
1023 ..............................................................................
1025 Each device connected to a controller has a separate subdirectory in the
1026 controllers directory. The files listed in table 1-7 are contained in these
1030 Table 1-7: IDE device information
1031 ..............................................................................
1034 capacity Capacity of the medium (in 512Byte blocks)
1035 driver driver and version
1036 geometry physical and logical geometry
1037 identify device identify block
1039 model device identifier
1040 settings device setup
1041 smart_thresholds IDE disk management thresholds
1042 smart_values IDE disk management values
1043 ..............................................................................
1045 The most interesting file is settings. This file contains a nice overview of
1046 the drive parameters:
1048 # cat /proc/ide/ide0/hda/settings
1049 name value min max mode
1050 ---- ----- --- --- ----
1051 bios_cyl 526 0 65535 rw
1052 bios_head 255 0 255 rw
1053 bios_sect 63 0 63 rw
1054 breada_readahead 4 0 127 rw
1056 file_readahead 72 0 2097151 rw
1058 keepsettings 0 0 1 rw
1059 max_kb_per_request 122 1 127 rw
1063 pio_mode write-only 0 255 w
1069 1.4 Networking info in /proc/net
1070 --------------------------------
1072 The subdirectory /proc/net follows the usual pattern. Table 1-8 shows the
1073 additional values you get for IP version 6 if you configure the kernel to
1074 support this. Table 1-9 lists the files and their meaning.
1077 Table 1-8: IPv6 info in /proc/net
1078 ..............................................................................
1080 udp6 UDP sockets (IPv6)
1081 tcp6 TCP sockets (IPv6)
1082 raw6 Raw device statistics (IPv6)
1083 igmp6 IP multicast addresses, which this host joined (IPv6)
1084 if_inet6 List of IPv6 interface addresses
1085 ipv6_route Kernel routing table for IPv6
1086 rt6_stats Global IPv6 routing tables statistics
1087 sockstat6 Socket statistics (IPv6)
1088 snmp6 Snmp data (IPv6)
1089 ..............................................................................
1092 Table 1-9: Network info in /proc/net
1093 ..............................................................................
1095 arp Kernel ARP table
1096 dev network devices with statistics
1097 dev_mcast the Layer2 multicast groups a device is listening too
1098 (interface index, label, number of references, number of bound
1100 dev_stat network device status
1101 ip_fwchains Firewall chain linkage
1102 ip_fwnames Firewall chain names
1103 ip_masq Directory containing the masquerading tables
1104 ip_masquerade Major masquerading table
1105 netstat Network statistics
1106 raw raw device statistics
1107 route Kernel routing table
1108 rpc Directory containing rpc info
1109 rt_cache Routing cache
1111 sockstat Socket statistics
1114 unix UNIX domain sockets
1115 wireless Wireless interface data (Wavelan etc)
1116 igmp IP multicast addresses, which this host joined
1117 psched Global packet scheduler parameters.
1118 netlink List of PF_NETLINK sockets
1119 ip_mr_vifs List of multicast virtual interfaces
1120 ip_mr_cache List of multicast routing cache
1121 ..............................................................................
1123 You can use this information to see which network devices are available in
1124 your system and how much traffic was routed over those devices:
1127 Inter-|Receive |[...
1128 face |bytes packets errs drop fifo frame compressed multicast|[...
1129 lo: 908188 5596 0 0 0 0 0 0 [...
1130 ppp0:15475140 20721 410 0 0 410 0 0 [...
1131 eth0: 614530 7085 0 0 0 0 0 1 [...
1134 ...] bytes packets errs drop fifo colls carrier compressed
1135 ...] 908188 5596 0 0 0 0 0 0
1136 ...] 1375103 17405 0 0 0 0 0 0
1137 ...] 1703981 5535 0 0 0 3 0 0
1139 In addition, each Channel Bond interface has its own directory. For
1140 example, the bond0 device will have a directory called /proc/net/bond0/.
1141 It will contain information that is specific to that bond, such as the
1142 current slaves of the bond, the link status of the slaves, and how
1143 many times the slaves link has failed.
1148 If you have a SCSI host adapter in your system, you'll find a subdirectory
1149 named after the driver for this adapter in /proc/scsi. You'll also see a list
1150 of all recognized SCSI devices in /proc/scsi:
1152 >cat /proc/scsi/scsi
1154 Host: scsi0 Channel: 00 Id: 00 Lun: 00
1155 Vendor: IBM Model: DGHS09U Rev: 03E0
1156 Type: Direct-Access ANSI SCSI revision: 03
1157 Host: scsi0 Channel: 00 Id: 06 Lun: 00
1158 Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04
1159 Type: CD-ROM ANSI SCSI revision: 02
1162 The directory named after the driver has one file for each adapter found in
1163 the system. These files contain information about the controller, including
1164 the used IRQ and the IO address range. The amount of information shown is
1165 dependent on the adapter you use. The example shows the output for an Adaptec
1166 AHA-2940 SCSI adapter:
1168 > cat /proc/scsi/aic7xxx/0
1170 Adaptec AIC7xxx driver version: 5.1.19/3.2.4
1172 TCQ Enabled By Default : Disabled
1173 AIC7XXX_PROC_STATS : Disabled
1174 AIC7XXX_RESET_DELAY : 5
1175 Adapter Configuration:
1176 SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter
1177 Ultra Wide Controller
1178 PCI MMAPed I/O Base: 0xeb001000
1179 Adapter SEEPROM Config: SEEPROM found and used.
1180 Adaptec SCSI BIOS: Enabled
1182 SCBs: Active 0, Max Active 2,
1183 Allocated 15, HW 16, Page 255
1185 BIOS Control Word: 0x18b6
1186 Adapter Control Word: 0x005b
1187 Extended Translation: Enabled
1188 Disconnect Enable Flags: 0xffff
1189 Ultra Enable Flags: 0x0001
1190 Tag Queue Enable Flags: 0x0000
1191 Ordered Queue Tag Flags: 0x0000
1192 Default Tag Queue Depth: 8
1193 Tagged Queue By Device array for aic7xxx host instance 0:
1194 {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255}
1195 Actual queue depth per device for aic7xxx host instance 0:
1196 {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}
1199 Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8
1200 Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0)
1201 Total transfers 160151 (74577 reads and 85574 writes)
1203 Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15
1204 Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0)
1205 Total transfers 0 (0 reads and 0 writes)
1208 1.6 Parallel port info in /proc/parport
1209 ---------------------------------------
1211 The directory /proc/parport contains information about the parallel ports of
1212 your system. It has one subdirectory for each port, named after the port
1215 These directories contain the four files shown in Table 1-10.
1218 Table 1-10: Files in /proc/parport
1219 ..............................................................................
1221 autoprobe Any IEEE-1284 device ID information that has been acquired.
1222 devices list of the device drivers using that port. A + will appear by the
1223 name of the device currently using the port (it might not appear
1225 hardware Parallel port's base address, IRQ line and DMA channel.
1226 irq IRQ that parport is using for that port. This is in a separate
1227 file to allow you to alter it by writing a new value in (IRQ
1229 ..............................................................................
1231 1.7 TTY info in /proc/tty
1232 -------------------------
1234 Information about the available and actually used tty's can be found in the
1235 directory /proc/tty.You'll find entries for drivers and line disciplines in
1236 this directory, as shown in Table 1-11.
1239 Table 1-11: Files in /proc/tty
1240 ..............................................................................
1242 drivers list of drivers and their usage
1243 ldiscs registered line disciplines
1244 driver/serial usage statistic and status of single tty lines
1245 ..............................................................................
1247 To see which tty's are currently in use, you can simply look into the file
1250 > cat /proc/tty/drivers
1251 pty_slave /dev/pts 136 0-255 pty:slave
1252 pty_master /dev/ptm 128 0-255 pty:master
1253 pty_slave /dev/ttyp 3 0-255 pty:slave
1254 pty_master /dev/pty 2 0-255 pty:master
1255 serial /dev/cua 5 64-67 serial:callout
1256 serial /dev/ttyS 4 64-67 serial
1257 /dev/tty0 /dev/tty0 4 0 system:vtmaster
1258 /dev/ptmx /dev/ptmx 5 2 system
1259 /dev/console /dev/console 5 1 system:console
1260 /dev/tty /dev/tty 5 0 system:/dev/tty
1261 unknown /dev/tty 4 1-63 console
1264 1.8 Miscellaneous kernel statistics in /proc/stat
1265 -------------------------------------------------
1267 Various pieces of information about kernel activity are available in the
1268 /proc/stat file. All of the numbers reported in this file are aggregates
1269 since the system first booted. For a quick look, simply cat the file:
1272 cpu 2255 34 2290 22625563 6290 127 456 0 0 0
1273 cpu0 1132 34 1441 11311718 3675 127 438 0 0 0
1274 cpu1 1123 0 849 11313845 2614 0 18 0 0 0
1275 intr 114930548 113199788 3 0 5 263 0 4 [... lots more numbers ...]
1281 softirq 183433 0 21755 12 39 1137 231 21459 2263
1283 The very first "cpu" line aggregates the numbers in all of the other "cpuN"
1284 lines. These numbers identify the amount of time the CPU has spent performing
1285 different kinds of work. Time units are in USER_HZ (typically hundredths of a
1286 second). The meanings of the columns are as follows, from left to right:
1288 - user: normal processes executing in user mode
1289 - nice: niced processes executing in user mode
1290 - system: processes executing in kernel mode
1291 - idle: twiddling thumbs
1292 - iowait: waiting for I/O to complete
1293 - irq: servicing interrupts
1294 - softirq: servicing softirqs
1295 - steal: involuntary wait
1296 - guest: running a normal guest
1297 - guest_nice: running a niced guest
1299 The "intr" line gives counts of interrupts serviced since boot time, for each
1300 of the possible system interrupts. The first column is the total of all
1301 interrupts serviced including unnumbered architecture specific interrupts;
1302 each subsequent column is the total for that particular numbered interrupt.
1303 Unnumbered interrupts are not shown, only summed into the total.
1305 The "ctxt" line gives the total number of context switches across all CPUs.
1307 The "btime" line gives the time at which the system booted, in seconds since
1310 The "processes" line gives the number of processes and threads created, which
1311 includes (but is not limited to) those created by calls to the fork() and
1312 clone() system calls.
1314 The "procs_running" line gives the total number of threads that are
1315 running or ready to run (i.e., the total number of runnable threads).
1317 The "procs_blocked" line gives the number of processes currently blocked,
1318 waiting for I/O to complete.
1320 The "softirq" line gives counts of softirqs serviced since boot time, for each
1321 of the possible system softirqs. The first column is the total of all
1322 softirqs serviced; each subsequent column is the total for that particular
1326 1.9 Ext4 file system parameters
1327 -------------------------------
1329 Information about mounted ext4 file systems can be found in
1330 /proc/fs/ext4. Each mounted filesystem will have a directory in
1331 /proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or
1332 /proc/fs/ext4/dm-0). The files in each per-device directory are shown
1333 in Table 1-12, below.
1335 Table 1-12: Files in /proc/fs/ext4/<devname>
1336 ..............................................................................
1338 mb_groups details of multiblock allocator buddy cache of free blocks
1339 ..............................................................................
1343 Shows registered system console lines.
1345 To see which character device lines are currently used for the system console
1346 /dev/console, you may simply look into the file /proc/consoles:
1348 > cat /proc/consoles
1354 device name of the device
1355 operations R = can do read operations
1356 W = can do write operations
1358 flags E = it is enabled
1359 C = it is preferred console
1360 B = it is primary boot console
1361 p = it is used for printk buffer
1362 b = it is not a TTY but a Braille device
1363 a = it is safe to use when cpu is offline
1364 major:minor major and minor number of the device separated by a colon
1366 ------------------------------------------------------------------------------
1368 ------------------------------------------------------------------------------
1369 The /proc file system serves information about the running system. It not only
1370 allows access to process data but also allows you to request the kernel status
1371 by reading files in the hierarchy.
1373 The directory structure of /proc reflects the types of information and makes
1374 it easy, if not obvious, where to look for specific data.
1375 ------------------------------------------------------------------------------
1377 ------------------------------------------------------------------------------
1378 CHAPTER 2: MODIFYING SYSTEM PARAMETERS
1379 ------------------------------------------------------------------------------
1381 ------------------------------------------------------------------------------
1383 ------------------------------------------------------------------------------
1384 * Modifying kernel parameters by writing into files found in /proc/sys
1385 * Exploring the files which modify certain parameters
1386 * Review of the /proc/sys file tree
1387 ------------------------------------------------------------------------------
1390 A very interesting part of /proc is the directory /proc/sys. This is not only
1391 a source of information, it also allows you to change parameters within the
1392 kernel. Be very careful when attempting this. You can optimize your system,
1393 but you can also cause it to crash. Never alter kernel parameters on a
1394 production system. Set up a development machine and test to make sure that
1395 everything works the way you want it to. You may have no alternative but to
1396 reboot the machine once an error has been made.
1398 To change a value, simply echo the new value into the file. An example is
1399 given below in the section on the file system data. You need to be root to do
1400 this. You can create your own boot script to perform this every time your
1403 The files in /proc/sys can be used to fine tune and monitor miscellaneous and
1404 general things in the operation of the Linux kernel. Since some of the files
1405 can inadvertently disrupt your system, it is advisable to read both
1406 documentation and source before actually making adjustments. In any case, be
1407 very careful when writing to any of these files. The entries in /proc may
1408 change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt
1409 review the kernel documentation in the directory /usr/src/linux/Documentation.
1410 This chapter is heavily based on the documentation included in the pre 2.2
1411 kernels, and became part of it in version 2.2.1 of the Linux kernel.
1413 Please see: Documentation/sysctl/ directory for descriptions of these
1416 ------------------------------------------------------------------------------
1418 ------------------------------------------------------------------------------
1419 Certain aspects of kernel behavior can be modified at runtime, without the
1420 need to recompile the kernel, or even to reboot the system. The files in the
1421 /proc/sys tree can not only be read, but also modified. You can use the echo
1422 command to write value into these files, thereby changing the default settings
1424 ------------------------------------------------------------------------------
1426 ------------------------------------------------------------------------------
1427 CHAPTER 3: PER-PROCESS PARAMETERS
1428 ------------------------------------------------------------------------------
1430 3.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score
1431 --------------------------------------------------------------------------------
1433 These file can be used to adjust the badness heuristic used to select which
1434 process gets killed in out of memory conditions.
1436 The badness heuristic assigns a value to each candidate task ranging from 0
1437 (never kill) to 1000 (always kill) to determine which process is targeted. The
1438 units are roughly a proportion along that range of allowed memory the process
1439 may allocate from based on an estimation of its current memory and swap use.
1440 For example, if a task is using all allowed memory, its badness score will be
1441 1000. If it is using half of its allowed memory, its score will be 500.
1443 There is an additional factor included in the badness score: the current memory
1444 and swap usage is discounted by 3% for root processes.
1446 The amount of "allowed" memory depends on the context in which the oom killer
1447 was called. If it is due to the memory assigned to the allocating task's cpuset
1448 being exhausted, the allowed memory represents the set of mems assigned to that
1449 cpuset. If it is due to a mempolicy's node(s) being exhausted, the allowed
1450 memory represents the set of mempolicy nodes. If it is due to a memory
1451 limit (or swap limit) being reached, the allowed memory is that configured
1452 limit. Finally, if it is due to the entire system being out of memory, the
1453 allowed memory represents all allocatable resources.
1455 The value of /proc/<pid>/oom_score_adj is added to the badness score before it
1456 is used to determine which task to kill. Acceptable values range from -1000
1457 (OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX). This allows userspace to
1458 polarize the preference for oom killing either by always preferring a certain
1459 task or completely disabling it. The lowest possible value, -1000, is
1460 equivalent to disabling oom killing entirely for that task since it will always
1461 report a badness score of 0.
1463 Consequently, it is very simple for userspace to define the amount of memory to
1464 consider for each task. Setting a /proc/<pid>/oom_score_adj value of +500, for
1465 example, is roughly equivalent to allowing the remainder of tasks sharing the
1466 same system, cpuset, mempolicy, or memory controller resources to use at least
1467 50% more memory. A value of -500, on the other hand, would be roughly
1468 equivalent to discounting 50% of the task's allowed memory from being considered
1469 as scoring against the task.
1471 For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also
1472 be used to tune the badness score. Its acceptable values range from -16
1473 (OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17
1474 (OOM_DISABLE) to disable oom killing entirely for that task. Its value is
1475 scaled linearly with /proc/<pid>/oom_score_adj.
1477 The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last
1478 value set by a CAP_SYS_RESOURCE process. To reduce the value any lower
1479 requires CAP_SYS_RESOURCE.
1481 Caveat: when a parent task is selected, the oom killer will sacrifice any first
1482 generation children with separate address spaces instead, if possible. This
1483 avoids servers and important system daemons from being killed and loses the
1484 minimal amount of work.
1487 3.2 /proc/<pid>/oom_score - Display current oom-killer score
1488 -------------------------------------------------------------
1490 This file can be used to check the current score used by the oom-killer is for
1491 any given <pid>. Use it together with /proc/<pid>/oom_score_adj to tune which
1492 process should be killed in an out-of-memory situation.
1495 3.3 /proc/<pid>/io - Display the IO accounting fields
1496 -------------------------------------------------------
1498 This file contains IO statistics for each running process
1503 test:/tmp # dd if=/dev/zero of=/tmp/test.dat &
1506 test:/tmp # cat /proc/3828/io
1512 write_bytes: 323932160
1513 cancelled_write_bytes: 0
1522 I/O counter: chars read
1523 The number of bytes which this task has caused to be read from storage. This
1524 is simply the sum of bytes which this process passed to read() and pread().
1525 It includes things like tty IO and it is unaffected by whether or not actual
1526 physical disk IO was required (the read might have been satisfied from
1533 I/O counter: chars written
1534 The number of bytes which this task has caused, or shall cause to be written
1535 to disk. Similar caveats apply here as with rchar.
1541 I/O counter: read syscalls
1542 Attempt to count the number of read I/O operations, i.e. syscalls like read()
1549 I/O counter: write syscalls
1550 Attempt to count the number of write I/O operations, i.e. syscalls like
1551 write() and pwrite().
1557 I/O counter: bytes read
1558 Attempt to count the number of bytes which this process really did cause to
1559 be fetched from the storage layer. Done at the submit_bio() level, so it is
1560 accurate for block-backed filesystems. <please add status regarding NFS and
1561 CIFS at a later time>
1567 I/O counter: bytes written
1568 Attempt to count the number of bytes which this process caused to be sent to
1569 the storage layer. This is done at page-dirtying time.
1572 cancelled_write_bytes
1573 ---------------------
1575 The big inaccuracy here is truncate. If a process writes 1MB to a file and
1576 then deletes the file, it will in fact perform no writeout. But it will have
1577 been accounted as having caused 1MB of write.
1578 In other words: The number of bytes which this process caused to not happen,
1579 by truncating pagecache. A task can cause "negative" IO too. If this task
1580 truncates some dirty pagecache, some IO which another task has been accounted
1581 for (in its write_bytes) will not be happening. We _could_ just subtract that
1582 from the truncating task's write_bytes, but there is information loss in doing
1589 At its current implementation state, this is a bit racy on 32-bit machines: if
1590 process A reads process B's /proc/pid/io while process B is updating one of
1591 those 64-bit counters, process A could see an intermediate result.
1594 More information about this can be found within the taskstats documentation in
1595 Documentation/accounting.
1597 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings
1598 ---------------------------------------------------------------
1599 When a process is dumped, all anonymous memory is written to a core file as
1600 long as the size of the core file isn't limited. But sometimes we don't want
1601 to dump some memory segments, for example, huge shared memory. Conversely,
1602 sometimes we want to save file-backed memory segments into a core file, not
1603 only the individual files.
1605 /proc/<pid>/coredump_filter allows you to customize which memory segments
1606 will be dumped when the <pid> process is dumped. coredump_filter is a bitmask
1607 of memory types. If a bit of the bitmask is set, memory segments of the
1608 corresponding memory type are dumped, otherwise they are not dumped.
1610 The following 7 memory types are supported:
1611 - (bit 0) anonymous private memory
1612 - (bit 1) anonymous shared memory
1613 - (bit 2) file-backed private memory
1614 - (bit 3) file-backed shared memory
1615 - (bit 4) ELF header pages in file-backed private memory areas (it is
1616 effective only if the bit 2 is cleared)
1617 - (bit 5) hugetlb private memory
1618 - (bit 6) hugetlb shared memory
1620 Note that MMIO pages such as frame buffer are never dumped and vDSO pages
1621 are always dumped regardless of the bitmask status.
1623 Note bit 0-4 doesn't effect any hugetlb memory. hugetlb memory are only
1624 effected by bit 5-6.
1626 Default value of coredump_filter is 0x23; this means all anonymous memory
1627 segments and hugetlb private memory are dumped.
1629 If you don't want to dump all shared memory segments attached to pid 1234,
1630 write 0x21 to the process's proc file.
1632 $ echo 0x21 > /proc/1234/coredump_filter
1634 When a new process is created, the process inherits the bitmask status from its
1635 parent. It is useful to set up coredump_filter before the program runs.
1638 $ echo 0x7 > /proc/self/coredump_filter
1641 3.5 /proc/<pid>/mountinfo - Information about mounts
1642 --------------------------------------------------------
1644 This file contains lines of the form:
1646 36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue
1647 (1)(2)(3) (4) (5) (6) (7) (8) (9) (10) (11)
1649 (1) mount ID: unique identifier of the mount (may be reused after umount)
1650 (2) parent ID: ID of parent (or of self for the top of the mount tree)
1651 (3) major:minor: value of st_dev for files on filesystem
1652 (4) root: root of the mount within the filesystem
1653 (5) mount point: mount point relative to the process's root
1654 (6) mount options: per mount options
1655 (7) optional fields: zero or more fields of the form "tag[:value]"
1656 (8) separator: marks the end of the optional fields
1657 (9) filesystem type: name of filesystem of the form "type[.subtype]"
1658 (10) mount source: filesystem specific information or "none"
1659 (11) super options: per super block options
1661 Parsers should ignore all unrecognised optional fields. Currently the
1662 possible optional fields are:
1664 shared:X mount is shared in peer group X
1665 master:X mount is slave to peer group X
1666 propagate_from:X mount is slave and receives propagation from peer group X (*)
1667 unbindable mount is unbindable
1669 (*) X is the closest dominant peer group under the process's root. If
1670 X is the immediate master of the mount, or if there's no dominant peer
1671 group under the same root, then only the "master:X" field is present
1672 and not the "propagate_from:X" field.
1674 For more information on mount propagation see:
1676 Documentation/filesystems/sharedsubtree.txt
1679 3.6 /proc/<pid>/comm & /proc/<pid>/task/<tid>/comm
1680 --------------------------------------------------------
1681 These files provide a method to access a tasks comm value. It also allows for
1682 a task to set its own or one of its thread siblings comm value. The comm value
1683 is limited in size compared to the cmdline value, so writing anything longer
1684 then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated
1688 3.7 /proc/<pid>/task/<tid>/children - Information about task children
1689 -------------------------------------------------------------------------
1690 This file provides a fast way to retrieve first level children pids
1691 of a task pointed by <pid>/<tid> pair. The format is a space separated
1694 Note the "first level" here -- if a child has own children they will
1695 not be listed here, one needs to read /proc/<children-pid>/task/<tid>/children
1696 to obtain the descendants.
1698 Since this interface is intended to be fast and cheap it doesn't
1699 guarantee to provide precise results and some children might be
1700 skipped, especially if they've exited right after we printed their
1701 pids, so one need to either stop or freeze processes being inspected
1702 if precise results are needed.
1705 3.8 /proc/<pid>/fdinfo/<fd> - Information about opened file
1706 ---------------------------------------------------------------
1707 This file provides information associated with an opened file. The regular
1708 files have at least three fields -- 'pos', 'flags' and mnt_id. The 'pos'
1709 represents the current offset of the opened file in decimal form [see lseek(2)
1710 for details], 'flags' denotes the octal O_xxx mask the file has been
1711 created with [see open(2) for details] and 'mnt_id' represents mount ID of
1712 the file system containing the opened file [see 3.5 /proc/<pid>/mountinfo
1721 All locks associated with a file descriptor are shown in its fdinfo too.
1723 lock: 1: FLOCK ADVISORY WRITE 359 00:13:11691 0 EOF
1725 The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags
1726 pair provide additional information particular to the objects they represent.
1735 where 'eventfd-count' is hex value of a counter.
1742 sigmask: 0000000000000200
1744 where 'sigmask' is hex value of the signal mask associated
1752 tfd: 5 events: 1d data: ffffffffffffffff
1754 where 'tfd' is a target file descriptor number in decimal form,
1755 'events' is events mask being watched and the 'data' is data
1756 associated with a target [see epoll(7) for more details].
1760 For inotify files the format is the following
1764 inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d
1766 where 'wd' is a watch descriptor in decimal form, ie a target file
1767 descriptor number, 'ino' and 'sdev' are inode and device where the
1768 target file resides and the 'mask' is the mask of events, all in hex
1769 form [see inotify(7) for more details].
1771 If the kernel was built with exportfs support, the path to the target
1772 file is encoded as a file handle. The file handle is provided by three
1773 fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex
1776 If the kernel is built without exportfs support the file handle won't be
1779 If there is no inotify mark attached yet the 'inotify' line will be omitted.
1781 For fanotify files the format is
1786 fanotify flags:10 event-flags:0
1787 fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003
1788 fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4
1790 where fanotify 'flags' and 'event-flags' are values used in fanotify_init
1791 call, 'mnt_id' is the mount point identifier, 'mflags' is the value of
1792 flags associated with mark which are tracked separately from events
1793 mask. 'ino', 'sdev' are target inode and device, 'mask' is the events
1794 mask and 'ignored_mask' is the mask of events which are to be ignored.
1795 All in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask'
1796 does provide information about flags and mask used in fanotify_mark
1797 call [see fsnotify manpage for details].
1799 While the first three lines are mandatory and always printed, the rest is
1800 optional and may be omitted if no marks created yet.
1811 it_value: (0, 49406829)
1814 where 'clockid' is the clock type and 'ticks' is the number of the timer expirations
1815 that have occurred [see timerfd_create(2) for details]. 'settime flags' are
1816 flags in octal form been used to setup the timer [see timerfd_settime(2) for
1817 details]. 'it_value' is remaining time until the timer exiration.
1818 'it_interval' is the interval for the timer. Note the timer might be set up
1819 with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value'
1820 still exhibits timer's remaining time.
1822 3.9 /proc/<pid>/map_files - Information about memory mapped files
1823 ---------------------------------------------------------------------
1824 This directory contains symbolic links which represent memory mapped files
1825 the process is maintaining. Example output:
1827 | lr-------- 1 root root 64 Jan 27 11:24 333c600000-333c620000 -> /usr/lib64/ld-2.18.so
1828 | lr-------- 1 root root 64 Jan 27 11:24 333c81f000-333c820000 -> /usr/lib64/ld-2.18.so
1829 | lr-------- 1 root root 64 Jan 27 11:24 333c820000-333c821000 -> /usr/lib64/ld-2.18.so
1831 | lr-------- 1 root root 64 Jan 27 11:24 35d0421000-35d0422000 -> /usr/lib64/libselinux.so.1
1832 | lr-------- 1 root root 64 Jan 27 11:24 400000-41a000 -> /usr/bin/ls
1834 The name of a link represents the virtual memory bounds of a mapping, i.e.
1835 vm_area_struct::vm_start-vm_area_struct::vm_end.
1837 The main purpose of the map_files is to retrieve a set of memory mapped
1838 files in a fast way instead of parsing /proc/<pid>/maps or
1839 /proc/<pid>/smaps, both of which contain many more records. At the same
1840 time one can open(2) mappings from the listings of two processes and
1841 comparing their inode numbers to figure out which anonymous memory areas
1842 are actually shared.
1844 ------------------------------------------------------------------------------
1846 ------------------------------------------------------------------------------
1849 ---------------------
1851 The following mount options are supported:
1853 hidepid= Set /proc/<pid>/ access mode.
1854 gid= Set the group authorized to learn processes information.
1856 hidepid=0 means classic mode - everybody may access all /proc/<pid>/ directories
1859 hidepid=1 means users may not access any /proc/<pid>/ directories but their
1860 own. Sensitive files like cmdline, sched*, status are now protected against
1861 other users. This makes it impossible to learn whether any user runs
1862 specific program (given the program doesn't reveal itself by its behaviour).
1863 As an additional bonus, as /proc/<pid>/cmdline is unaccessible for other users,
1864 poorly written programs passing sensitive information via program arguments are
1865 now protected against local eavesdroppers.
1867 hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be fully invisible to other
1868 users. It doesn't mean that it hides a fact whether a process with a specific
1869 pid value exists (it can be learned by other means, e.g. by "kill -0 $PID"),
1870 but it hides process' uid and gid, which may be learned by stat()'ing
1871 /proc/<pid>/ otherwise. It greatly complicates an intruder's task of gathering
1872 information about running processes, whether some daemon runs with elevated
1873 privileges, whether other user runs some sensitive program, whether other users
1874 run any program at all, etc.
1876 gid= defines a group authorized to learn processes information otherwise
1877 prohibited by hidepid=. If you use some daemon like identd which needs to learn
1878 information about processes information, just add identd to this group.
projects / linux.git / blob