1 ------------------------------------------------------------------------------
2 T H E /proc F I L E S Y S T E M
3 ------------------------------------------------------------------------------
4 /proc/sys Terrehon Bowden <terrehon@pacbell.net> October 7 1999
5 Bodo Bauer <bb@ricochet.net>
7 2.4.x update Jorge Nerin <comandante@zaralinux.com> November 14 2000
8 move /proc/sys Shen Feng <shen@cn.fujitsu.com> April 1 2009
9 ------------------------------------------------------------------------------
10 Version 1.3 Kernel version 2.2.12
11 Kernel version 2.4.0-test11-pre4
12 ------------------------------------------------------------------------------
13 fixes/update part 1.1 Stefani Seibold <stefani@seibold.net> June 9 2009
19 0.1 Introduction/Credits
22 1 Collecting System Information
23 1.1 Process-Specific Subdirectories
25 1.3 IDE devices in /proc/ide
26 1.4 Networking info in /proc/net
28 1.6 Parallel port info in /proc/parport
29 1.7 TTY info in /proc/tty
30 1.8 Miscellaneous kernel statistics in /proc/stat
31 1.9 Ext4 file system parameters
33 2 Modifying System Parameters
35 3 Per-Process Parameters
36 3.1 /proc/<pid>/oom_adj - Adjust the oom-killer score
37 3.2 /proc/<pid>/oom_score - Display current oom-killer score
38 3.3 /proc/<pid>/io - Display the IO accounting fields
39 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings
40 3.5 /proc/<pid>/mountinfo - Information about mounts
43 ------------------------------------------------------------------------------
45 ------------------------------------------------------------------------------
47 0.1 Introduction/Credits
48 ------------------------
50 This documentation is part of a soon (or so we hope) to be released book on
51 the SuSE Linux distribution. As there is no complete documentation for the
52 /proc file system and we've used many freely available sources to write these
53 chapters, it seems only fair to give the work back to the Linux community.
54 This work is based on the 2.2.* kernel version and the upcoming 2.4.*. I'm
55 afraid it's still far from complete, but we hope it will be useful. As far as
56 we know, it is the first 'all-in-one' document about the /proc file system. It
57 is focused on the Intel x86 hardware, so if you are looking for PPC, ARM,
58 SPARC, AXP, etc., features, you probably won't find what you are looking for.
59 It also only covers IPv4 networking, not IPv6 nor other protocols - sorry. But
60 additions and patches are welcome and will be added to this document if you
63 We'd like to thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of
64 other people for help compiling this documentation. We'd also like to extend a
65 special thank you to Andi Kleen for documentation, which we relied on heavily
66 to create this document, as well as the additional information he provided.
67 Thanks to everybody else who contributed source or docs to the Linux kernel
68 and helped create a great piece of software... :)
70 If you have any comments, corrections or additions, please don't hesitate to
71 contact Bodo Bauer at bb@ricochet.net. We'll be happy to add them to this
74 The latest version of this document is available online at
75 http://skaro.nightcrawler.com/~bb/Docs/Proc as HTML version.
77 If the above direction does not works for you, ypu could try the kernel
78 mailing list at linux-kernel@vger.kernel.org and/or try to reach me at
79 comandante@zaralinux.com.
84 We don't guarantee the correctness of this document, and if you come to us
85 complaining about how you screwed up your system because of incorrect
86 documentation, we won't feel responsible...
88 ------------------------------------------------------------------------------
89 CHAPTER 1: COLLECTING SYSTEM INFORMATION
90 ------------------------------------------------------------------------------
92 ------------------------------------------------------------------------------
94 ------------------------------------------------------------------------------
95 * Investigating the properties of the pseudo file system /proc and its
96 ability to provide information on the running Linux system
97 * Examining /proc's structure
98 * Uncovering various information about the kernel and the processes running
100 ------------------------------------------------------------------------------
103 The proc file system acts as an interface to internal data structures in the
104 kernel. It can be used to obtain information about the system and to change
105 certain kernel parameters at runtime (sysctl).
107 First, we'll take a look at the read-only parts of /proc. In Chapter 2, we
108 show you how you can use /proc/sys to change settings.
110 1.1 Process-Specific Subdirectories
111 -----------------------------------
113 The directory /proc contains (among other things) one subdirectory for each
114 process running on the system, which is named after the process ID (PID).
116 The link self points to the process reading the file system. Each process
117 subdirectory has the entries listed in Table 1-1.
120 Table 1-1: Process specific entries in /proc
121 ..............................................................................
123 clear_refs Clears page referenced bits shown in smaps output
124 cmdline Command line arguments
125 cpu Current and last cpu in which it was executed (2.4)(smp)
126 cwd Link to the current working directory
127 environ Values of environment variables
128 exe Link to the executable of this process
129 fd Directory, which contains all file descriptors
130 maps Memory maps to executables and library files (2.4)
131 mem Memory held by this process
132 root Link to the root directory of this process
134 statm Process memory status information
135 status Process status in human readable form
136 wchan If CONFIG_KALLSYMS is set, a pre-decoded wchan
137 stack Report full stack trace, enable via CONFIG_STACKTRACE
138 smaps a extension based on maps, showing the memory consumption of
140 ..............................................................................
142 For example, to get the status information of a process, all you have to do is
143 read the file /proc/PID/status:
145 >cat /proc/self/status
168 SigPnd: 0000000000000000
169 ShdPnd: 0000000000000000
170 SigBlk: 0000000000000000
171 SigIgn: 0000000000000000
172 SigCgt: 0000000000000000
173 CapInh: 00000000fffffeff
174 CapPrm: 0000000000000000
175 CapEff: 0000000000000000
176 CapBnd: ffffffffffffffff
177 voluntary_ctxt_switches: 0
178 nonvoluntary_ctxt_switches: 1
180 This shows you nearly the same information you would get if you viewed it with
181 the ps command. In fact, ps uses the proc file system to obtain its
182 information. But you get a more detailed view of the process by reading the
183 file /proc/PID/status. It fields are described in table 1-2.
185 The statm file contains more detailed information about the process
186 memory usage. Its seven fields are explained in Table 1-3. The stat file
187 contains details information about the process itself. Its fields are
188 explained in Table 1-4.
190 Table 1-2: Contents of the statm files (as of 2.6.30-rc7)
191 ..............................................................................
193 Name filename of the executable
194 State state (R is running, S is sleeping, D is sleeping
195 in an uninterruptible wait, Z is zombie,
196 T is traced or stopped)
199 PPid process id of the parent process
200 TracerPid PID of process tracing this process (0 if not)
201 Uid Real, effective, saved set, and file system UIDs
202 Gid Real, effective, saved set, and file system GIDs
203 FDSize number of file descriptor slots currently allocated
204 Groups supplementary group list
205 VmPeak peak virtual memory size
206 VmSize total program size
207 VmLck locked memory size
208 VmHWM peak resident set size ("high water mark")
209 VmRSS size of memory portions
210 VmData size of data, stack, and text segments
211 VmStk size of data, stack, and text segments
212 VmExe size of text segment
213 VmLib size of shared library code
214 VmPTE size of page table entries
215 Threads number of threads
216 SigQ number of signals queued/max. number for queue
217 SigPnd bitmap of pending signals for the thread
218 ShdPnd bitmap of shared pending signals for the process
219 SigBlk bitmap of blocked signals
220 SigIgn bitmap of ignored signals
221 SigCgt bitmap of catched signals
222 CapInh bitmap of inheritable capabilities
223 CapPrm bitmap of permitted capabilities
224 CapEff bitmap of effective capabilities
225 CapBnd bitmap of capabilities bounding set
226 Cpus_allowed mask of CPUs on which this process may run
227 Cpus_allowed_list Same as previous, but in "list format"
228 Mems_allowed mask of memory nodes allowed to this process
229 Mems_allowed_list Same as previous, but in "list format"
230 voluntary_ctxt_switches number of voluntary context switches
231 nonvoluntary_ctxt_switches number of non voluntary context switches
232 ..............................................................................
234 Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
235 ..............................................................................
237 size total program size (pages) (same as VmSize in status)
238 resident size of memory portions (pages) (same as VmRSS in status)
239 shared number of pages that are shared (i.e. backed by a file)
240 trs number of pages that are 'code' (not including libs; broken,
241 includes data segment)
242 lrs number of pages of library (always 0 on 2.6)
243 drs number of pages of data/stack (including libs; broken,
244 includes library text)
245 dt number of dirty pages (always 0 on 2.6)
246 ..............................................................................
249 Table 1-4: Contents of the stat files (as of 2.6.30-rc7)
250 ..............................................................................
253 tcomm filename of the executable
254 state state (R is running, S is sleeping, D is sleeping in an
255 uninterruptible wait, Z is zombie, T is traced or stopped)
256 ppid process id of the parent process
257 pgrp pgrp of the process
259 tty_nr tty the process uses
260 tty_pgrp pgrp of the tty
262 min_flt number of minor faults
263 cmin_flt number of minor faults with child's
264 maj_flt number of major faults
265 cmaj_flt number of major faults with child's
266 utime user mode jiffies
267 stime kernel mode jiffies
268 cutime user mode jiffies with child's
269 cstime kernel mode jiffies with child's
270 priority priority level
272 num_threads number of threads
273 it_real_value (obsolete, always 0)
274 start_time time the process started after system boot
275 vsize virtual memory size
276 rss resident set memory size
277 rsslim current limit in bytes on the rss
278 start_code address above which program text can run
279 end_code address below which program text can run
280 start_stack address of the start of the stack
281 esp current value of ESP
282 eip current value of EIP
283 pending bitmap of pending signals
284 blocked bitmap of blocked signals
285 sigign bitmap of ignored signals
286 sigcatch bitmap of catched signals
287 wchan address where process went to sleep
290 exit_signal signal to send to parent thread on exit
291 task_cpu which CPU the task is scheduled on
292 rt_priority realtime priority
293 policy scheduling policy (man sched_setscheduler)
294 blkio_ticks time spent waiting for block IO
295 gtime guest time of the task in jiffies
296 cgtime guest time of the task children in jiffies
297 ..............................................................................
299 The /proc/PID/map file containing the currently mapped memory regions and
300 their access permissions.
304 address perms offset dev inode pathname
306 08048000-08049000 r-xp 00000000 03:00 8312 /opt/test
307 08049000-0804a000 rw-p 00001000 03:00 8312 /opt/test
308 0804a000-0806b000 rw-p 00000000 00:00 0 [heap]
309 a7cb1000-a7cb2000 ---p 00000000 00:00 0
310 a7cb2000-a7eb2000 rw-p 00000000 00:00 0
311 a7eb2000-a7eb3000 ---p 00000000 00:00 0
312 a7eb3000-a7ed5000 rw-p 00000000 00:00 0
313 a7ed5000-a8008000 r-xp 00000000 03:00 4222 /lib/libc.so.6
314 a8008000-a800a000 r--p 00133000 03:00 4222 /lib/libc.so.6
315 a800a000-a800b000 rw-p 00135000 03:00 4222 /lib/libc.so.6
316 a800b000-a800e000 rw-p 00000000 00:00 0
317 a800e000-a8022000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0
318 a8022000-a8023000 r--p 00013000 03:00 14462 /lib/libpthread.so.0
319 a8023000-a8024000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0
320 a8024000-a8027000 rw-p 00000000 00:00 0
321 a8027000-a8043000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2
322 a8043000-a8044000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2
323 a8044000-a8045000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2
324 aff35000-aff4a000 rw-p 00000000 00:00 0 [stack]
325 ffffe000-fffff000 r-xp 00000000 00:00 0 [vdso]
327 where "address" is the address space in the process that it occupies, "perms"
328 is a set of permissions:
334 p = private (copy on write)
336 "offset" is the offset into the mapping, "dev" is the device (major:minor), and
337 "inode" is the inode on that device. 0 indicates that no inode is associated
338 with the memory region, as the case would be with BSS (uninitialized data).
339 The "pathname" shows the name associated file for this mapping. If the mapping
340 is not associated with a file:
342 [heap] = the heap of the program
343 [stack] = the stack of the main process
344 [vdso] = the "virtual dynamic shared object",
345 the kernel system call handler
347 or if empty, the mapping is anonymous.
350 The /proc/PID/smaps is an extension based on maps, showing the memory
351 consumption for each of the process's mappings. For each of mappings there
352 is a series of lines such as the following:
354 08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash
367 The first of these lines shows the same information as is displayed for the
368 mapping in /proc/PID/maps. The remaining lines show the size of the mapping,
369 the amount of the mapping that is currently resident in RAM, the "proportional
370 set size” (divide each shared page by the number of processes sharing it), the
371 number of clean and dirty shared pages in the mapping, and the number of clean
372 and dirty private pages in the mapping. The "Referenced" indicates the amount
373 of memory currently marked as referenced or accessed.
375 This file is only present if the CONFIG_MMU kernel configuration option is
378 The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
379 bits on both physical and virtual pages associated with a process.
380 To clear the bits for all the pages associated with the process
381 > echo 1 > /proc/PID/clear_refs
383 To clear the bits for the anonymous pages associated with the process
384 > echo 2 > /proc/PID/clear_refs
386 To clear the bits for the file mapped pages associated with the process
387 > echo 3 > /proc/PID/clear_refs
388 Any other value written to /proc/PID/clear_refs will have no effect.
394 Similar to the process entries, the kernel data files give information about
395 the running kernel. The files used to obtain this information are contained in
396 /proc and are listed in Table 1-5. Not all of these will be present in your
397 system. It depends on the kernel configuration and the loaded modules, which
398 files are there, and which are missing.
400 Table 1-5: Kernel info in /proc
401 ..............................................................................
403 apm Advanced power management info
404 buddyinfo Kernel memory allocator information (see text) (2.5)
405 bus Directory containing bus specific information
406 cmdline Kernel command line
407 cpuinfo Info about the CPU
408 devices Available devices (block and character)
409 dma Used DMS channels
410 filesystems Supported filesystems
411 driver Various drivers grouped here, currently rtc (2.4)
412 execdomains Execdomains, related to security (2.4)
413 fb Frame Buffer devices (2.4)
414 fs File system parameters, currently nfs/exports (2.4)
415 ide Directory containing info about the IDE subsystem
416 interrupts Interrupt usage
417 iomem Memory map (2.4)
418 ioports I/O port usage
419 irq Masks for irq to cpu affinity (2.4)(smp?)
420 isapnp ISA PnP (Plug&Play) Info (2.4)
421 kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4))
423 ksyms Kernel symbol table
424 loadavg Load average of last 1, 5 & 15 minutes
428 modules List of loaded modules
429 mounts Mounted filesystems
430 net Networking info (see text)
431 partitions Table of partitions known to the system
432 pci Deprecated info of PCI bus (new way -> /proc/bus/pci/,
433 decoupled by lspci (2.4)
435 scsi SCSI info (see text)
436 slabinfo Slab pool info
437 softirqs softirq usage
438 stat Overall statistics
439 swaps Swap space utilization
441 sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4)
442 tty Info of tty drivers
444 version Kernel version
445 video bttv info of video resources (2.4)
446 vmallocinfo Show vmalloced areas
447 ..............................................................................
449 You can, for example, check which interrupts are currently in use and what
450 they are used for by looking in the file /proc/interrupts:
452 > cat /proc/interrupts
454 0: 8728810 XT-PIC timer
455 1: 895 XT-PIC keyboard
457 3: 531695 XT-PIC aha152x
458 4: 2014133 XT-PIC serial
459 5: 44401 XT-PIC pcnet_cs
462 12: 182918 XT-PIC PS/2 Mouse
464 14: 1232265 XT-PIC ide0
468 In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the
469 output of a SMP machine):
471 > cat /proc/interrupts
474 0: 1243498 1214548 IO-APIC-edge timer
475 1: 8949 8958 IO-APIC-edge keyboard
476 2: 0 0 XT-PIC cascade
477 5: 11286 10161 IO-APIC-edge soundblaster
478 8: 1 0 IO-APIC-edge rtc
479 9: 27422 27407 IO-APIC-edge 3c503
480 12: 113645 113873 IO-APIC-edge PS/2 Mouse
482 14: 22491 24012 IO-APIC-edge ide0
483 15: 2183 2415 IO-APIC-edge ide1
484 17: 30564 30414 IO-APIC-level eth0
485 18: 177 164 IO-APIC-level bttv
490 NMI is incremented in this case because every timer interrupt generates a NMI
491 (Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups.
493 LOC is the local interrupt counter of the internal APIC of every CPU.
495 ERR is incremented in the case of errors in the IO-APIC bus (the bus that
496 connects the CPUs in a SMP system. This means that an error has been detected,
497 the IO-APIC automatically retry the transmission, so it should not be a big
498 problem, but you should read the SMP-FAQ.
500 In 2.6.2* /proc/interrupts was expanded again. This time the goal was for
501 /proc/interrupts to display every IRQ vector in use by the system, not
502 just those considered 'most important'. The new vectors are:
504 THR -- interrupt raised when a machine check threshold counter
505 (typically counting ECC corrected errors of memory or cache) exceeds
506 a configurable threshold. Only available on some systems.
508 TRM -- a thermal event interrupt occurs when a temperature threshold
509 has been exceeded for the CPU. This interrupt may also be generated
510 when the temperature drops back to normal.
512 SPU -- a spurious interrupt is some interrupt that was raised then lowered
513 by some IO device before it could be fully processed by the APIC. Hence
514 the APIC sees the interrupt but does not know what device it came from.
515 For this case the APIC will generate the interrupt with a IRQ vector
516 of 0xff. This might also be generated by chipset bugs.
518 RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are
519 sent from one CPU to another per the needs of the OS. Typically,
520 their statistics are used by kernel developers and interested users to
521 determine the occurrence of interrupts of the given type.
523 The above IRQ vectors are displayed only when relevent. For example,
524 the threshold vector does not exist on x86_64 platforms. Others are
525 suppressed when the system is a uniprocessor. As of this writing, only
526 i386 and x86_64 platforms support the new IRQ vector displays.
528 Of some interest is the introduction of the /proc/irq directory to 2.4.
529 It could be used to set IRQ to CPU affinity, this means that you can "hook" an
530 IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
531 irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and
536 0 10 12 14 16 18 2 4 6 8 prof_cpu_mask
537 1 11 13 15 17 19 3 5 7 9 default_smp_affinity
541 smp_affinity is a bitmask, in which you can specify which CPUs can handle the
542 IRQ, you can set it by doing:
544 > echo 1 > /proc/irq/10/smp_affinity
546 This means that only the first CPU will handle the IRQ, but you can also echo
547 5 which means that only the first and fourth CPU can handle the IRQ.
549 The contents of each smp_affinity file is the same by default:
551 > cat /proc/irq/0/smp_affinity
554 The default_smp_affinity mask applies to all non-active IRQs, which are the
555 IRQs which have not yet been allocated/activated, and hence which lack a
556 /proc/irq/[0-9]* directory.
558 prof_cpu_mask specifies which CPUs are to be profiled by the system wide
559 profiler. Default value is ffffffff (all cpus).
561 The way IRQs are routed is handled by the IO-APIC, and it's Round Robin
562 between all the CPUs which are allowed to handle it. As usual the kernel has
563 more info than you and does a better job than you, so the defaults are the
564 best choice for almost everyone.
566 There are three more important subdirectories in /proc: net, scsi, and sys.
567 The general rule is that the contents, or even the existence of these
568 directories, depend on your kernel configuration. If SCSI is not enabled, the
569 directory scsi may not exist. The same is true with the net, which is there
570 only when networking support is present in the running kernel.
572 The slabinfo file gives information about memory usage at the slab level.
573 Linux uses slab pools for memory management above page level in version 2.2.
574 Commonly used objects have their own slab pool (such as network buffers,
575 directory cache, and so on).
577 ..............................................................................
579 > cat /proc/buddyinfo
581 Node 0, zone DMA 0 4 5 4 4 3 ...
582 Node 0, zone Normal 1 0 0 1 101 8 ...
583 Node 0, zone HighMem 2 0 0 1 1 0 ...
585 Memory fragmentation is a problem under some workloads, and buddyinfo is a
586 useful tool for helping diagnose these problems. Buddyinfo will give you a
587 clue as to how big an area you can safely allocate, or why a previous
590 Each column represents the number of pages of a certain order which are
591 available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in
592 ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE
593 available in ZONE_NORMAL, etc...
595 ..............................................................................
599 Provides information about distribution and utilization of memory. This
600 varies by architecture and compile options. The following is from a
601 16GB PIII, which has highmem enabled. You may not have all of these fields.
606 MemTotal: 16344972 kB
613 HighTotal: 15597528 kB
614 HighFree: 13629632 kB
624 SReclaimable: 159856 kB
625 SUnreclaim: 124508 kB
630 CommitLimit: 7669796 kB
631 Committed_AS: 100056 kB
632 VmallocTotal: 112216 kB
634 VmallocChunk: 111088 kB
636 MemTotal: Total usable ram (i.e. physical ram minus a few reserved
637 bits and the kernel binary code)
638 MemFree: The sum of LowFree+HighFree
639 Buffers: Relatively temporary storage for raw disk blocks
640 shouldn't get tremendously large (20MB or so)
641 Cached: in-memory cache for files read from the disk (the
642 pagecache). Doesn't include SwapCached
643 SwapCached: Memory that once was swapped out, is swapped back in but
644 still also is in the swapfile (if memory is needed it
645 doesn't need to be swapped out AGAIN because it is already
646 in the swapfile. This saves I/O)
647 Active: Memory that has been used more recently and usually not
648 reclaimed unless absolutely necessary.
649 Inactive: Memory which has been less recently used. It is more
650 eligible to be reclaimed for other purposes
652 HighFree: Highmem is all memory above ~860MB of physical memory
653 Highmem areas are for use by userspace programs, or
654 for the pagecache. The kernel must use tricks to access
655 this memory, making it slower to access than lowmem.
657 LowFree: Lowmem is memory which can be used for everything that
658 highmem can be used for, but it is also available for the
659 kernel's use for its own data structures. Among many
660 other things, it is where everything from the Slab is
661 allocated. Bad things happen when you're out of lowmem.
662 SwapTotal: total amount of swap space available
663 SwapFree: Memory which has been evicted from RAM, and is temporarily
665 Dirty: Memory which is waiting to get written back to the disk
666 Writeback: Memory which is actively being written back to the disk
667 AnonPages: Non-file backed pages mapped into userspace page tables
668 Mapped: files which have been mmaped, such as libraries
669 Slab: in-kernel data structures cache
670 SReclaimable: Part of Slab, that might be reclaimed, such as caches
671 SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure
672 PageTables: amount of memory dedicated to the lowest level of page
674 NFS_Unstable: NFS pages sent to the server, but not yet committed to stable
676 Bounce: Memory used for block device "bounce buffers"
677 WritebackTmp: Memory used by FUSE for temporary writeback buffers
678 CommitLimit: Based on the overcommit ratio ('vm.overcommit_ratio'),
679 this is the total amount of memory currently available to
680 be allocated on the system. This limit is only adhered to
681 if strict overcommit accounting is enabled (mode 2 in
682 'vm.overcommit_memory').
683 The CommitLimit is calculated with the following formula:
684 CommitLimit = ('vm.overcommit_ratio' * Physical RAM) + Swap
685 For example, on a system with 1G of physical RAM and 7G
686 of swap with a `vm.overcommit_ratio` of 30 it would
687 yield a CommitLimit of 7.3G.
688 For more details, see the memory overcommit documentation
689 in vm/overcommit-accounting.
690 Committed_AS: The amount of memory presently allocated on the system.
691 The committed memory is a sum of all of the memory which
692 has been allocated by processes, even if it has not been
693 "used" by them as of yet. A process which malloc()'s 1G
694 of memory, but only touches 300M of it will only show up
695 as using 300M of memory even if it has the address space
696 allocated for the entire 1G. This 1G is memory which has
697 been "committed" to by the VM and can be used at any time
698 by the allocating application. With strict overcommit
699 enabled on the system (mode 2 in 'vm.overcommit_memory'),
700 allocations which would exceed the CommitLimit (detailed
701 above) will not be permitted. This is useful if one needs
702 to guarantee that processes will not fail due to lack of
703 memory once that memory has been successfully allocated.
704 VmallocTotal: total size of vmalloc memory area
705 VmallocUsed: amount of vmalloc area which is used
706 VmallocChunk: largest contiguous block of vmalloc area which is free
708 ..............................................................................
712 Provides information about vmalloced/vmaped areas. One line per area,
713 containing the virtual address range of the area, size in bytes,
714 caller information of the creator, and optional information depending
715 on the kind of area :
717 pages=nr number of pages
718 phys=addr if a physical address was specified
719 ioremap I/O mapping (ioremap() and friends)
720 vmalloc vmalloc() area
723 vpages buffer for pages pointers was vmalloced (huge area)
724 N<node>=nr (Only on NUMA kernels)
725 Number of pages allocated on memory node <node>
727 > cat /proc/vmallocinfo
728 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ...
729 /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128
730 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ...
731 /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64
732 0xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f...
733 phys=7fee8000 ioremap
734 0xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f...
735 phys=7fee7000 ioremap
736 0xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210
737 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ...
738 /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3
739 0xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ...
741 0xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ...
742 /0x130 [x_tables] pages=4 vmalloc N0=4
743 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ...
744 pages=14 vmalloc N2=14
745 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ...
747 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ...
749 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ...
750 pages=10 vmalloc N0=10
752 ..............................................................................
756 Provides counts of softirq handlers serviced since boot time, for each cpu.
761 TIMER: 27166 27120 27097 27034
766 SCHED: 27035 26983 26971 26746
768 RCU: 1678 1769 2178 2250
771 1.3 IDE devices in /proc/ide
772 ----------------------------
774 The subdirectory /proc/ide contains information about all IDE devices of which
775 the kernel is aware. There is one subdirectory for each IDE controller, the
776 file drivers and a link for each IDE device, pointing to the device directory
777 in the controller specific subtree.
779 The file drivers contains general information about the drivers used for the
782 > cat /proc/ide/drivers
783 ide-cdrom version 4.53
784 ide-disk version 1.08
786 More detailed information can be found in the controller specific
787 subdirectories. These are named ide0, ide1 and so on. Each of these
788 directories contains the files shown in table 1-6.
791 Table 1-6: IDE controller info in /proc/ide/ide?
792 ..............................................................................
794 channel IDE channel (0 or 1)
795 config Configuration (only for PCI/IDE bridge)
797 model Type/Chipset of IDE controller
798 ..............................................................................
800 Each device connected to a controller has a separate subdirectory in the
801 controllers directory. The files listed in table 1-7 are contained in these
805 Table 1-7: IDE device information
806 ..............................................................................
809 capacity Capacity of the medium (in 512Byte blocks)
810 driver driver and version
811 geometry physical and logical geometry
812 identify device identify block
814 model device identifier
815 settings device setup
816 smart_thresholds IDE disk management thresholds
817 smart_values IDE disk management values
818 ..............................................................................
820 The most interesting file is settings. This file contains a nice overview of
821 the drive parameters:
823 # cat /proc/ide/ide0/hda/settings
824 name value min max mode
825 ---- ----- --- --- ----
826 bios_cyl 526 0 65535 rw
827 bios_head 255 0 255 rw
829 breada_readahead 4 0 127 rw
831 file_readahead 72 0 2097151 rw
833 keepsettings 0 0 1 rw
834 max_kb_per_request 122 1 127 rw
838 pio_mode write-only 0 255 w
844 1.4 Networking info in /proc/net
845 --------------------------------
847 The subdirectory /proc/net follows the usual pattern. Table 1-8 shows the
848 additional values you get for IP version 6 if you configure the kernel to
849 support this. Table 1-9 lists the files and their meaning.
852 Table 1-8: IPv6 info in /proc/net
853 ..............................................................................
855 udp6 UDP sockets (IPv6)
856 tcp6 TCP sockets (IPv6)
857 raw6 Raw device statistics (IPv6)
858 igmp6 IP multicast addresses, which this host joined (IPv6)
859 if_inet6 List of IPv6 interface addresses
860 ipv6_route Kernel routing table for IPv6
861 rt6_stats Global IPv6 routing tables statistics
862 sockstat6 Socket statistics (IPv6)
863 snmp6 Snmp data (IPv6)
864 ..............................................................................
867 Table 1-9: Network info in /proc/net
868 ..............................................................................
871 dev network devices with statistics
872 dev_mcast the Layer2 multicast groups a device is listening too
873 (interface index, label, number of references, number of bound
875 dev_stat network device status
876 ip_fwchains Firewall chain linkage
877 ip_fwnames Firewall chain names
878 ip_masq Directory containing the masquerading tables
879 ip_masquerade Major masquerading table
880 netstat Network statistics
881 raw raw device statistics
882 route Kernel routing table
883 rpc Directory containing rpc info
884 rt_cache Routing cache
886 sockstat Socket statistics
888 tr_rif Token ring RIF routing table
890 unix UNIX domain sockets
891 wireless Wireless interface data (Wavelan etc)
892 igmp IP multicast addresses, which this host joined
893 psched Global packet scheduler parameters.
894 netlink List of PF_NETLINK sockets
895 ip_mr_vifs List of multicast virtual interfaces
896 ip_mr_cache List of multicast routing cache
897 ..............................................................................
899 You can use this information to see which network devices are available in
900 your system and how much traffic was routed over those devices:
904 face |bytes packets errs drop fifo frame compressed multicast|[...
905 lo: 908188 5596 0 0 0 0 0 0 [...
906 ppp0:15475140 20721 410 0 0 410 0 0 [...
907 eth0: 614530 7085 0 0 0 0 0 1 [...
910 ...] bytes packets errs drop fifo colls carrier compressed
911 ...] 908188 5596 0 0 0 0 0 0
912 ...] 1375103 17405 0 0 0 0 0 0
913 ...] 1703981 5535 0 0 0 3 0 0
915 In addition, each Channel Bond interface has it's own directory. For
916 example, the bond0 device will have a directory called /proc/net/bond0/.
917 It will contain information that is specific to that bond, such as the
918 current slaves of the bond, the link status of the slaves, and how
919 many times the slaves link has failed.
924 If you have a SCSI host adapter in your system, you'll find a subdirectory
925 named after the driver for this adapter in /proc/scsi. You'll also see a list
926 of all recognized SCSI devices in /proc/scsi:
930 Host: scsi0 Channel: 00 Id: 00 Lun: 00
931 Vendor: IBM Model: DGHS09U Rev: 03E0
932 Type: Direct-Access ANSI SCSI revision: 03
933 Host: scsi0 Channel: 00 Id: 06 Lun: 00
934 Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04
935 Type: CD-ROM ANSI SCSI revision: 02
938 The directory named after the driver has one file for each adapter found in
939 the system. These files contain information about the controller, including
940 the used IRQ and the IO address range. The amount of information shown is
941 dependent on the adapter you use. The example shows the output for an Adaptec
942 AHA-2940 SCSI adapter:
944 > cat /proc/scsi/aic7xxx/0
946 Adaptec AIC7xxx driver version: 5.1.19/3.2.4
948 TCQ Enabled By Default : Disabled
949 AIC7XXX_PROC_STATS : Disabled
950 AIC7XXX_RESET_DELAY : 5
951 Adapter Configuration:
952 SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter
953 Ultra Wide Controller
954 PCI MMAPed I/O Base: 0xeb001000
955 Adapter SEEPROM Config: SEEPROM found and used.
956 Adaptec SCSI BIOS: Enabled
958 SCBs: Active 0, Max Active 2,
959 Allocated 15, HW 16, Page 255
961 BIOS Control Word: 0x18b6
962 Adapter Control Word: 0x005b
963 Extended Translation: Enabled
964 Disconnect Enable Flags: 0xffff
965 Ultra Enable Flags: 0x0001
966 Tag Queue Enable Flags: 0x0000
967 Ordered Queue Tag Flags: 0x0000
968 Default Tag Queue Depth: 8
969 Tagged Queue By Device array for aic7xxx host instance 0:
970 {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255}
971 Actual queue depth per device for aic7xxx host instance 0:
972 {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}
975 Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8
976 Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0)
977 Total transfers 160151 (74577 reads and 85574 writes)
979 Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15
980 Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0)
981 Total transfers 0 (0 reads and 0 writes)
984 1.6 Parallel port info in /proc/parport
985 ---------------------------------------
987 The directory /proc/parport contains information about the parallel ports of
988 your system. It has one subdirectory for each port, named after the port
991 These directories contain the four files shown in Table 1-10.
994 Table 1-10: Files in /proc/parport
995 ..............................................................................
997 autoprobe Any IEEE-1284 device ID information that has been acquired.
998 devices list of the device drivers using that port. A + will appear by the
999 name of the device currently using the port (it might not appear
1001 hardware Parallel port's base address, IRQ line and DMA channel.
1002 irq IRQ that parport is using for that port. This is in a separate
1003 file to allow you to alter it by writing a new value in (IRQ
1005 ..............................................................................
1007 1.7 TTY info in /proc/tty
1008 -------------------------
1010 Information about the available and actually used tty's can be found in the
1011 directory /proc/tty.You'll find entries for drivers and line disciplines in
1012 this directory, as shown in Table 1-11.
1015 Table 1-11: Files in /proc/tty
1016 ..............................................................................
1018 drivers list of drivers and their usage
1019 ldiscs registered line disciplines
1020 driver/serial usage statistic and status of single tty lines
1021 ..............................................................................
1023 To see which tty's are currently in use, you can simply look into the file
1026 > cat /proc/tty/drivers
1027 pty_slave /dev/pts 136 0-255 pty:slave
1028 pty_master /dev/ptm 128 0-255 pty:master
1029 pty_slave /dev/ttyp 3 0-255 pty:slave
1030 pty_master /dev/pty 2 0-255 pty:master
1031 serial /dev/cua 5 64-67 serial:callout
1032 serial /dev/ttyS 4 64-67 serial
1033 /dev/tty0 /dev/tty0 4 0 system:vtmaster
1034 /dev/ptmx /dev/ptmx 5 2 system
1035 /dev/console /dev/console 5 1 system:console
1036 /dev/tty /dev/tty 5 0 system:/dev/tty
1037 unknown /dev/tty 4 1-63 console
1040 1.8 Miscellaneous kernel statistics in /proc/stat
1041 -------------------------------------------------
1043 Various pieces of information about kernel activity are available in the
1044 /proc/stat file. All of the numbers reported in this file are aggregates
1045 since the system first booted. For a quick look, simply cat the file:
1048 cpu 2255 34 2290 22625563 6290 127 456 0 0
1049 cpu0 1132 34 1441 11311718 3675 127 438 0 0
1050 cpu1 1123 0 849 11313845 2614 0 18 0 0
1051 intr 114930548 113199788 3 0 5 263 0 4 [... lots more numbers ...]
1057 softirq 183433 0 21755 12 39 1137 231 21459 2263
1059 The very first "cpu" line aggregates the numbers in all of the other "cpuN"
1060 lines. These numbers identify the amount of time the CPU has spent performing
1061 different kinds of work. Time units are in USER_HZ (typically hundredths of a
1062 second). The meanings of the columns are as follows, from left to right:
1064 - user: normal processes executing in user mode
1065 - nice: niced processes executing in user mode
1066 - system: processes executing in kernel mode
1067 - idle: twiddling thumbs
1068 - iowait: waiting for I/O to complete
1069 - irq: servicing interrupts
1070 - softirq: servicing softirqs
1071 - steal: involuntary wait
1072 - guest: running a guest
1074 The "intr" line gives counts of interrupts serviced since boot time, for each
1075 of the possible system interrupts. The first column is the total of all
1076 interrupts serviced; each subsequent column is the total for that particular
1079 The "ctxt" line gives the total number of context switches across all CPUs.
1081 The "btime" line gives the time at which the system booted, in seconds since
1084 The "processes" line gives the number of processes and threads created, which
1085 includes (but is not limited to) those created by calls to the fork() and
1086 clone() system calls.
1088 The "procs_running" line gives the number of processes currently running on
1091 The "procs_blocked" line gives the number of processes currently blocked,
1092 waiting for I/O to complete.
1094 The "softirq" line gives counts of softirqs serviced since boot time, for each
1095 of the possible system softirqs. The first column is the total of all
1096 softirqs serviced; each subsequent column is the total for that particular
1100 1.9 Ext4 file system parameters
1101 ------------------------------
1103 Information about mounted ext4 file systems can be found in
1104 /proc/fs/ext4. Each mounted filesystem will have a directory in
1105 /proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or
1106 /proc/fs/ext4/dm-0). The files in each per-device directory are shown
1107 in Table 1-12, below.
1109 Table 1-12: Files in /proc/fs/ext4/<devname>
1110 ..............................................................................
1112 mb_groups details of multiblock allocator buddy cache of free blocks
1113 mb_history multiblock allocation history
1114 ..............................................................................
1117 ------------------------------------------------------------------------------
1119 ------------------------------------------------------------------------------
1120 The /proc file system serves information about the running system. It not only
1121 allows access to process data but also allows you to request the kernel status
1122 by reading files in the hierarchy.
1124 The directory structure of /proc reflects the types of information and makes
1125 it easy, if not obvious, where to look for specific data.
1126 ------------------------------------------------------------------------------
1128 ------------------------------------------------------------------------------
1129 CHAPTER 2: MODIFYING SYSTEM PARAMETERS
1130 ------------------------------------------------------------------------------
1132 ------------------------------------------------------------------------------
1134 ------------------------------------------------------------------------------
1135 * Modifying kernel parameters by writing into files found in /proc/sys
1136 * Exploring the files which modify certain parameters
1137 * Review of the /proc/sys file tree
1138 ------------------------------------------------------------------------------
1141 A very interesting part of /proc is the directory /proc/sys. This is not only
1142 a source of information, it also allows you to change parameters within the
1143 kernel. Be very careful when attempting this. You can optimize your system,
1144 but you can also cause it to crash. Never alter kernel parameters on a
1145 production system. Set up a development machine and test to make sure that
1146 everything works the way you want it to. You may have no alternative but to
1147 reboot the machine once an error has been made.
1149 To change a value, simply echo the new value into the file. An example is
1150 given below in the section on the file system data. You need to be root to do
1151 this. You can create your own boot script to perform this every time your
1154 The files in /proc/sys can be used to fine tune and monitor miscellaneous and
1155 general things in the operation of the Linux kernel. Since some of the files
1156 can inadvertently disrupt your system, it is advisable to read both
1157 documentation and source before actually making adjustments. In any case, be
1158 very careful when writing to any of these files. The entries in /proc may
1159 change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt
1160 review the kernel documentation in the directory /usr/src/linux/Documentation.
1161 This chapter is heavily based on the documentation included in the pre 2.2
1162 kernels, and became part of it in version 2.2.1 of the Linux kernel.
1164 Please see: Documentation/sysctls/ directory for descriptions of these
1167 ------------------------------------------------------------------------------
1169 ------------------------------------------------------------------------------
1170 Certain aspects of kernel behavior can be modified at runtime, without the
1171 need to recompile the kernel, or even to reboot the system. The files in the
1172 /proc/sys tree can not only be read, but also modified. You can use the echo
1173 command to write value into these files, thereby changing the default settings
1175 ------------------------------------------------------------------------------
1177 ------------------------------------------------------------------------------
1178 CHAPTER 3: PER-PROCESS PARAMETERS
1179 ------------------------------------------------------------------------------
1181 3.1 /proc/<pid>/oom_adj - Adjust the oom-killer score
1182 ------------------------------------------------------
1184 This file can be used to adjust the score used to select which processes
1185 should be killed in an out-of-memory situation. Giving it a high score will
1186 increase the likelihood of this process being killed by the oom-killer. Valid
1187 values are in the range -16 to +15, plus the special value -17, which disables
1188 oom-killing altogether for this process.
1190 The process to be killed in an out-of-memory situation is selected among all others
1191 based on its badness score. This value equals the original memory size of the process
1192 and is then updated according to its CPU time (utime + stime) and the
1193 run time (uptime - start time). The longer it runs the smaller is the score.
1194 Badness score is divided by the square root of the CPU time and then by
1195 the double square root of the run time.
1197 Swapped out tasks are killed first. Half of each child's memory size is added to
1198 the parent's score if they do not share the same memory. Thus forking servers
1199 are the prime candidates to be killed. Having only one 'hungry' child will make
1200 parent less preferable than the child.
1202 /proc/<pid>/oom_score shows process' current badness score.
1204 The following heuristics are then applied:
1205 * if the task was reniced, its score doubles
1206 * superuser or direct hardware access tasks (CAP_SYS_ADMIN, CAP_SYS_RESOURCE
1207 or CAP_SYS_RAWIO) have their score divided by 4
1208 * if oom condition happened in one cpuset and checked task does not belong
1209 to it, its score is divided by 8
1210 * the resulting score is multiplied by two to the power of oom_adj, i.e.
1211 points <<= oom_adj when it is positive and
1212 points >>= -(oom_adj) otherwise
1214 The task with the highest badness score is then selected and its children
1215 are killed, process itself will be killed in an OOM situation when it does
1216 not have children or some of them disabled oom like described above.
1218 3.2 /proc/<pid>/oom_score - Display current oom-killer score
1219 -------------------------------------------------------------
1221 This file can be used to check the current score used by the oom-killer is for
1222 any given <pid>. Use it together with /proc/<pid>/oom_adj to tune which
1223 process should be killed in an out-of-memory situation.
1226 3.3 /proc/<pid>/io - Display the IO accounting fields
1227 -------------------------------------------------------
1229 This file contains IO statistics for each running process
1234 test:/tmp # dd if=/dev/zero of=/tmp/test.dat &
1237 test:/tmp # cat /proc/3828/io
1243 write_bytes: 323932160
1244 cancelled_write_bytes: 0
1253 I/O counter: chars read
1254 The number of bytes which this task has caused to be read from storage. This
1255 is simply the sum of bytes which this process passed to read() and pread().
1256 It includes things like tty IO and it is unaffected by whether or not actual
1257 physical disk IO was required (the read might have been satisfied from
1264 I/O counter: chars written
1265 The number of bytes which this task has caused, or shall cause to be written
1266 to disk. Similar caveats apply here as with rchar.
1272 I/O counter: read syscalls
1273 Attempt to count the number of read I/O operations, i.e. syscalls like read()
1280 I/O counter: write syscalls
1281 Attempt to count the number of write I/O operations, i.e. syscalls like
1282 write() and pwrite().
1288 I/O counter: bytes read
1289 Attempt to count the number of bytes which this process really did cause to
1290 be fetched from the storage layer. Done at the submit_bio() level, so it is
1291 accurate for block-backed filesystems. <please add status regarding NFS and
1292 CIFS at a later time>
1298 I/O counter: bytes written
1299 Attempt to count the number of bytes which this process caused to be sent to
1300 the storage layer. This is done at page-dirtying time.
1303 cancelled_write_bytes
1304 ---------------------
1306 The big inaccuracy here is truncate. If a process writes 1MB to a file and
1307 then deletes the file, it will in fact perform no writeout. But it will have
1308 been accounted as having caused 1MB of write.
1309 In other words: The number of bytes which this process caused to not happen,
1310 by truncating pagecache. A task can cause "negative" IO too. If this task
1311 truncates some dirty pagecache, some IO which another task has been accounted
1312 for (in it's write_bytes) will not be happening. We _could_ just subtract that
1313 from the truncating task's write_bytes, but there is information loss in doing
1320 At its current implementation state, this is a bit racy on 32-bit machines: if
1321 process A reads process B's /proc/pid/io while process B is updating one of
1322 those 64-bit counters, process A could see an intermediate result.
1325 More information about this can be found within the taskstats documentation in
1326 Documentation/accounting.
1328 3.4 /proc/<pid>/coredump_filter - Core dump filtering settings
1329 ---------------------------------------------------------------
1330 When a process is dumped, all anonymous memory is written to a core file as
1331 long as the size of the core file isn't limited. But sometimes we don't want
1332 to dump some memory segments, for example, huge shared memory. Conversely,
1333 sometimes we want to save file-backed memory segments into a core file, not
1334 only the individual files.
1336 /proc/<pid>/coredump_filter allows you to customize which memory segments
1337 will be dumped when the <pid> process is dumped. coredump_filter is a bitmask
1338 of memory types. If a bit of the bitmask is set, memory segments of the
1339 corresponding memory type are dumped, otherwise they are not dumped.
1341 The following 7 memory types are supported:
1342 - (bit 0) anonymous private memory
1343 - (bit 1) anonymous shared memory
1344 - (bit 2) file-backed private memory
1345 - (bit 3) file-backed shared memory
1346 - (bit 4) ELF header pages in file-backed private memory areas (it is
1347 effective only if the bit 2 is cleared)
1348 - (bit 5) hugetlb private memory
1349 - (bit 6) hugetlb shared memory
1351 Note that MMIO pages such as frame buffer are never dumped and vDSO pages
1352 are always dumped regardless of the bitmask status.
1354 Note bit 0-4 doesn't effect any hugetlb memory. hugetlb memory are only
1355 effected by bit 5-6.
1357 Default value of coredump_filter is 0x23; this means all anonymous memory
1358 segments and hugetlb private memory are dumped.
1360 If you don't want to dump all shared memory segments attached to pid 1234,
1361 write 0x21 to the process's proc file.
1363 $ echo 0x21 > /proc/1234/coredump_filter
1365 When a new process is created, the process inherits the bitmask status from its
1366 parent. It is useful to set up coredump_filter before the program runs.
1369 $ echo 0x7 > /proc/self/coredump_filter
1372 3.5 /proc/<pid>/mountinfo - Information about mounts
1373 --------------------------------------------------------
1375 This file contains lines of the form:
1377 36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue
1378 (1)(2)(3) (4) (5) (6) (7) (8) (9) (10) (11)
1380 (1) mount ID: unique identifier of the mount (may be reused after umount)
1381 (2) parent ID: ID of parent (or of self for the top of the mount tree)
1382 (3) major:minor: value of st_dev for files on filesystem
1383 (4) root: root of the mount within the filesystem
1384 (5) mount point: mount point relative to the process's root
1385 (6) mount options: per mount options
1386 (7) optional fields: zero or more fields of the form "tag[:value]"
1387 (8) separator: marks the end of the optional fields
1388 (9) filesystem type: name of filesystem of the form "type[.subtype]"
1389 (10) mount source: filesystem specific information or "none"
1390 (11) super options: per super block options
1392 Parsers should ignore all unrecognised optional fields. Currently the
1393 possible optional fields are:
1395 shared:X mount is shared in peer group X
1396 master:X mount is slave to peer group X
1397 propagate_from:X mount is slave and receives propagation from peer group X (*)
1398 unbindable mount is unbindable
1400 (*) X is the closest dominant peer group under the process's root. If
1401 X is the immediate master of the mount, or if there's no dominant peer
1402 group under the same root, then only the "master:X" field is present
1403 and not the "propagate_from:X" field.
1405 For more information on mount propagation see:
1407 Documentation/filesystems/sharedsubtree.txt
git://bbs.cooldavid.org / net-next-2.6.git / blob