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 ------------------------------------------------------------------------------
9 Version 1.3 Kernel version 2.2.12
10 Kernel version 2.4.0-test11-pre4
11 ------------------------------------------------------------------------------
17 0.1 Introduction/Credits
20 1 Collecting System Information
21 1.1 Process-Specific Subdirectories
23 1.3 IDE devices in /proc/ide
24 1.4 Networking info in /proc/net
26 1.6 Parallel port info in /proc/parport
27 1.7 TTY info in /proc/tty
28 1.8 Miscellaneous kernel statistics in /proc/stat
30 2 Modifying System Parameters
31 2.1 /proc/sys/fs - File system data
32 2.2 /proc/sys/fs/binfmt_misc - Miscellaneous binary formats
33 2.3 /proc/sys/kernel - general kernel parameters
34 2.4 /proc/sys/vm - The virtual memory subsystem
35 2.5 /proc/sys/dev - Device specific parameters
36 2.6 /proc/sys/sunrpc - Remote procedure calls
37 2.7 /proc/sys/net - Networking stuff
38 2.8 /proc/sys/net/ipv4 - IPV4 settings
41 2.11 /proc/sys/fs/mqueue - POSIX message queues filesystem
42 2.12 /proc/<pid>/oom_adj - Adjust the oom-killer score
43 2.13 /proc/<pid>/oom_score - Display current oom-killer score
44 2.14 /proc/<pid>/io - Display the IO accounting fields
45 2.15 /proc/<pid>/coredump_filter - Core dump filtering settings
46 2.16 /proc/<pid>/mountinfo - Information about mounts
48 ------------------------------------------------------------------------------
50 ------------------------------------------------------------------------------
52 0.1 Introduction/Credits
53 ------------------------
55 This documentation is part of a soon (or so we hope) to be released book on
56 the SuSE Linux distribution. As there is no complete documentation for the
57 /proc file system and we've used many freely available sources to write these
58 chapters, it seems only fair to give the work back to the Linux community.
59 This work is based on the 2.2.* kernel version and the upcoming 2.4.*. I'm
60 afraid it's still far from complete, but we hope it will be useful. As far as
61 we know, it is the first 'all-in-one' document about the /proc file system. It
62 is focused on the Intel x86 hardware, so if you are looking for PPC, ARM,
63 SPARC, AXP, etc., features, you probably won't find what you are looking for.
64 It also only covers IPv4 networking, not IPv6 nor other protocols - sorry. But
65 additions and patches are welcome and will be added to this document if you
68 We'd like to thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of
69 other people for help compiling this documentation. We'd also like to extend a
70 special thank you to Andi Kleen for documentation, which we relied on heavily
71 to create this document, as well as the additional information he provided.
72 Thanks to everybody else who contributed source or docs to the Linux kernel
73 and helped create a great piece of software... :)
75 If you have any comments, corrections or additions, please don't hesitate to
76 contact Bodo Bauer at bb@ricochet.net. We'll be happy to add them to this
79 The latest version of this document is available online at
80 http://skaro.nightcrawler.com/~bb/Docs/Proc as HTML version.
82 If the above direction does not works for you, ypu could try the kernel
83 mailing list at linux-kernel@vger.kernel.org and/or try to reach me at
84 comandante@zaralinux.com.
89 We don't guarantee the correctness of this document, and if you come to us
90 complaining about how you screwed up your system because of incorrect
91 documentation, we won't feel responsible...
93 ------------------------------------------------------------------------------
94 CHAPTER 1: COLLECTING SYSTEM INFORMATION
95 ------------------------------------------------------------------------------
97 ------------------------------------------------------------------------------
99 ------------------------------------------------------------------------------
100 * Investigating the properties of the pseudo file system /proc and its
101 ability to provide information on the running Linux system
102 * Examining /proc's structure
103 * Uncovering various information about the kernel and the processes running
105 ------------------------------------------------------------------------------
108 The proc file system acts as an interface to internal data structures in the
109 kernel. It can be used to obtain information about the system and to change
110 certain kernel parameters at runtime (sysctl).
112 First, we'll take a look at the read-only parts of /proc. In Chapter 2, we
113 show you how you can use /proc/sys to change settings.
115 1.1 Process-Specific Subdirectories
116 -----------------------------------
118 The directory /proc contains (among other things) one subdirectory for each
119 process running on the system, which is named after the process ID (PID).
121 The link self points to the process reading the file system. Each process
122 subdirectory has the entries listed in Table 1-1.
125 Table 1-1: Process specific entries in /proc
126 ..............................................................................
128 clear_refs Clears page referenced bits shown in smaps output
129 cmdline Command line arguments
130 cpu Current and last cpu in which it was executed (2.4)(smp)
131 cwd Link to the current working directory
132 environ Values of environment variables
133 exe Link to the executable of this process
134 fd Directory, which contains all file descriptors
135 maps Memory maps to executables and library files (2.4)
136 mem Memory held by this process
137 root Link to the root directory of this process
139 statm Process memory status information
140 status Process status in human readable form
141 wchan If CONFIG_KALLSYMS is set, a pre-decoded wchan
142 smaps Extension based on maps, the rss size for each mapped file
143 ..............................................................................
145 For example, to get the status information of a process, all you have to do is
146 read the file /proc/PID/status:
148 >cat /proc/self/status
164 SigPnd: 0000000000000000
165 SigBlk: 0000000000000000
166 SigIgn: 0000000000000000
167 SigCgt: 0000000000000000
168 CapInh: 00000000fffffeff
169 CapPrm: 0000000000000000
170 CapEff: 0000000000000000
173 This shows you nearly the same information you would get if you viewed it with
174 the ps command. In fact, ps uses the proc file system to obtain its
175 information. The statm file contains more detailed information about the
176 process memory usage. Its seven fields are explained in Table 1-2. The stat
177 file contains details information about the process itself. Its fields are
178 explained in Table 1-3.
181 Table 1-2: Contents of the statm files (as of 2.6.8-rc3)
182 ..............................................................................
184 size total program size (pages) (same as VmSize in status)
185 resident size of memory portions (pages) (same as VmRSS in status)
186 shared number of pages that are shared (i.e. backed by a file)
187 trs number of pages that are 'code' (not including libs; broken,
188 includes data segment)
189 lrs number of pages of library (always 0 on 2.6)
190 drs number of pages of data/stack (including libs; broken,
191 includes library text)
192 dt number of dirty pages (always 0 on 2.6)
193 ..............................................................................
196 Table 1-3: Contents of the stat files (as of 2.6.22-rc3)
197 ..............................................................................
200 tcomm filename of the executable
201 state state (R is running, S is sleeping, D is sleeping in an
202 uninterruptible wait, Z is zombie, T is traced or stopped)
203 ppid process id of the parent process
204 pgrp pgrp of the process
206 tty_nr tty the process uses
207 tty_pgrp pgrp of the tty
209 min_flt number of minor faults
210 cmin_flt number of minor faults with child's
211 maj_flt number of major faults
212 cmaj_flt number of major faults with child's
213 utime user mode jiffies
214 stime kernel mode jiffies
215 cutime user mode jiffies with child's
216 cstime kernel mode jiffies with child's
217 priority priority level
219 num_threads number of threads
220 it_real_value (obsolete, always 0)
221 start_time time the process started after system boot
222 vsize virtual memory size
223 rss resident set memory size
224 rsslim current limit in bytes on the rss
225 start_code address above which program text can run
226 end_code address below which program text can run
227 start_stack address of the start of the stack
228 esp current value of ESP
229 eip current value of EIP
230 pending bitmap of pending signals (obsolete)
231 blocked bitmap of blocked signals (obsolete)
232 sigign bitmap of ignored signals (obsolete)
233 sigcatch bitmap of catched signals (obsolete)
234 wchan address where process went to sleep
237 exit_signal signal to send to parent thread on exit
238 task_cpu which CPU the task is scheduled on
239 rt_priority realtime priority
240 policy scheduling policy (man sched_setscheduler)
241 blkio_ticks time spent waiting for block IO
242 ..............................................................................
248 Similar to the process entries, the kernel data files give information about
249 the running kernel. The files used to obtain this information are contained in
250 /proc and are listed in Table 1-4. Not all of these will be present in your
251 system. It depends on the kernel configuration and the loaded modules, which
252 files are there, and which are missing.
254 Table 1-4: Kernel info in /proc
255 ..............................................................................
257 apm Advanced power management info
258 buddyinfo Kernel memory allocator information (see text) (2.5)
259 bus Directory containing bus specific information
260 cmdline Kernel command line
261 cpuinfo Info about the CPU
262 devices Available devices (block and character)
263 dma Used DMS channels
264 filesystems Supported filesystems
265 driver Various drivers grouped here, currently rtc (2.4)
266 execdomains Execdomains, related to security (2.4)
267 fb Frame Buffer devices (2.4)
268 fs File system parameters, currently nfs/exports (2.4)
269 ide Directory containing info about the IDE subsystem
270 interrupts Interrupt usage
271 iomem Memory map (2.4)
272 ioports I/O port usage
273 irq Masks for irq to cpu affinity (2.4)(smp?)
274 isapnp ISA PnP (Plug&Play) Info (2.4)
275 kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4))
277 ksyms Kernel symbol table
278 loadavg Load average of last 1, 5 & 15 minutes
282 modules List of loaded modules
283 mounts Mounted filesystems
284 net Networking info (see text)
285 partitions Table of partitions known to the system
286 pci Deprecated info of PCI bus (new way -> /proc/bus/pci/,
287 decoupled by lspci (2.4)
289 scsi SCSI info (see text)
290 slabinfo Slab pool info
291 stat Overall statistics
292 swaps Swap space utilization
294 sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4)
295 tty Info of tty drivers
297 version Kernel version
298 video bttv info of video resources (2.4)
299 vmallocinfo Show vmalloced areas
300 ..............................................................................
302 You can, for example, check which interrupts are currently in use and what
303 they are used for by looking in the file /proc/interrupts:
305 > cat /proc/interrupts
307 0: 8728810 XT-PIC timer
308 1: 895 XT-PIC keyboard
310 3: 531695 XT-PIC aha152x
311 4: 2014133 XT-PIC serial
312 5: 44401 XT-PIC pcnet_cs
315 12: 182918 XT-PIC PS/2 Mouse
317 14: 1232265 XT-PIC ide0
321 In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the
322 output of a SMP machine):
324 > cat /proc/interrupts
327 0: 1243498 1214548 IO-APIC-edge timer
328 1: 8949 8958 IO-APIC-edge keyboard
329 2: 0 0 XT-PIC cascade
330 5: 11286 10161 IO-APIC-edge soundblaster
331 8: 1 0 IO-APIC-edge rtc
332 9: 27422 27407 IO-APIC-edge 3c503
333 12: 113645 113873 IO-APIC-edge PS/2 Mouse
335 14: 22491 24012 IO-APIC-edge ide0
336 15: 2183 2415 IO-APIC-edge ide1
337 17: 30564 30414 IO-APIC-level eth0
338 18: 177 164 IO-APIC-level bttv
343 NMI is incremented in this case because every timer interrupt generates a NMI
344 (Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups.
346 LOC is the local interrupt counter of the internal APIC of every CPU.
348 ERR is incremented in the case of errors in the IO-APIC bus (the bus that
349 connects the CPUs in a SMP system. This means that an error has been detected,
350 the IO-APIC automatically retry the transmission, so it should not be a big
351 problem, but you should read the SMP-FAQ.
353 In 2.6.2* /proc/interrupts was expanded again. This time the goal was for
354 /proc/interrupts to display every IRQ vector in use by the system, not
355 just those considered 'most important'. The new vectors are:
357 THR -- interrupt raised when a machine check threshold counter
358 (typically counting ECC corrected errors of memory or cache) exceeds
359 a configurable threshold. Only available on some systems.
361 TRM -- a thermal event interrupt occurs when a temperature threshold
362 has been exceeded for the CPU. This interrupt may also be generated
363 when the temperature drops back to normal.
365 SPU -- a spurious interrupt is some interrupt that was raised then lowered
366 by some IO device before it could be fully processed by the APIC. Hence
367 the APIC sees the interrupt but does not know what device it came from.
368 For this case the APIC will generate the interrupt with a IRQ vector
369 of 0xff. This might also be generated by chipset bugs.
371 RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are
372 sent from one CPU to another per the needs of the OS. Typically,
373 their statistics are used by kernel developers and interested users to
374 determine the occurance of interrupt of the given type.
376 The above IRQ vectors are displayed only when relevent. For example,
377 the threshold vector does not exist on x86_64 platforms. Others are
378 suppressed when the system is a uniprocessor. As of this writing, only
379 i386 and x86_64 platforms support the new IRQ vector displays.
381 Of some interest is the introduction of the /proc/irq directory to 2.4.
382 It could be used to set IRQ to CPU affinity, this means that you can "hook" an
383 IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
384 irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and
389 0 10 12 14 16 18 2 4 6 8 prof_cpu_mask
390 1 11 13 15 17 19 3 5 7 9 default_smp_affinity
394 smp_affinity is a bitmask, in which you can specify which CPUs can handle the
395 IRQ, you can set it by doing:
397 > echo 1 > /proc/irq/10/smp_affinity
399 This means that only the first CPU will handle the IRQ, but you can also echo
400 5 which means that only the first and fourth CPU can handle the IRQ.
402 The contents of each smp_affinity file is the same by default:
404 > cat /proc/irq/0/smp_affinity
407 The default_smp_affinity mask applies to all non-active IRQs, which are the
408 IRQs which have not yet been allocated/activated, and hence which lack a
409 /proc/irq/[0-9]* directory.
411 prof_cpu_mask specifies which CPUs are to be profiled by the system wide
412 profiler. Default value is ffffffff (all cpus).
414 The way IRQs are routed is handled by the IO-APIC, and it's Round Robin
415 between all the CPUs which are allowed to handle it. As usual the kernel has
416 more info than you and does a better job than you, so the defaults are the
417 best choice for almost everyone.
419 There are three more important subdirectories in /proc: net, scsi, and sys.
420 The general rule is that the contents, or even the existence of these
421 directories, depend on your kernel configuration. If SCSI is not enabled, the
422 directory scsi may not exist. The same is true with the net, which is there
423 only when networking support is present in the running kernel.
425 The slabinfo file gives information about memory usage at the slab level.
426 Linux uses slab pools for memory management above page level in version 2.2.
427 Commonly used objects have their own slab pool (such as network buffers,
428 directory cache, and so on).
430 ..............................................................................
432 > cat /proc/buddyinfo
434 Node 0, zone DMA 0 4 5 4 4 3 ...
435 Node 0, zone Normal 1 0 0 1 101 8 ...
436 Node 0, zone HighMem 2 0 0 1 1 0 ...
438 Memory fragmentation is a problem under some workloads, and buddyinfo is a
439 useful tool for helping diagnose these problems. Buddyinfo will give you a
440 clue as to how big an area you can safely allocate, or why a previous
443 Each column represents the number of pages of a certain order which are
444 available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in
445 ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE
446 available in ZONE_NORMAL, etc...
448 ..............................................................................
452 Provides information about distribution and utilization of memory. This
453 varies by architecture and compile options. The following is from a
454 16GB PIII, which has highmem enabled. You may not have all of these fields.
459 MemTotal: 16344972 kB
466 HighTotal: 15597528 kB
467 HighFree: 13629632 kB
477 SReclaimable: 159856 kB
478 SUnreclaim: 124508 kB
483 CommitLimit: 7669796 kB
484 Committed_AS: 100056 kB
485 VmallocTotal: 112216 kB
487 VmallocChunk: 111088 kB
489 MemTotal: Total usable ram (i.e. physical ram minus a few reserved
490 bits and the kernel binary code)
491 MemFree: The sum of LowFree+HighFree
492 Buffers: Relatively temporary storage for raw disk blocks
493 shouldn't get tremendously large (20MB or so)
494 Cached: in-memory cache for files read from the disk (the
495 pagecache). Doesn't include SwapCached
496 SwapCached: Memory that once was swapped out, is swapped back in but
497 still also is in the swapfile (if memory is needed it
498 doesn't need to be swapped out AGAIN because it is already
499 in the swapfile. This saves I/O)
500 Active: Memory that has been used more recently and usually not
501 reclaimed unless absolutely necessary.
502 Inactive: Memory which has been less recently used. It is more
503 eligible to be reclaimed for other purposes
505 HighFree: Highmem is all memory above ~860MB of physical memory
506 Highmem areas are for use by userspace programs, or
507 for the pagecache. The kernel must use tricks to access
508 this memory, making it slower to access than lowmem.
510 LowFree: Lowmem is memory which can be used for everything that
511 highmem can be used for, but it is also available for the
512 kernel's use for its own data structures. Among many
513 other things, it is where everything from the Slab is
514 allocated. Bad things happen when you're out of lowmem.
515 SwapTotal: total amount of swap space available
516 SwapFree: Memory which has been evicted from RAM, and is temporarily
518 Dirty: Memory which is waiting to get written back to the disk
519 Writeback: Memory which is actively being written back to the disk
520 AnonPages: Non-file backed pages mapped into userspace page tables
521 Mapped: files which have been mmaped, such as libraries
522 Slab: in-kernel data structures cache
523 SReclaimable: Part of Slab, that might be reclaimed, such as caches
524 SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure
525 PageTables: amount of memory dedicated to the lowest level of page
527 NFS_Unstable: NFS pages sent to the server, but not yet committed to stable
529 Bounce: Memory used for block device "bounce buffers"
530 WritebackTmp: Memory used by FUSE for temporary writeback buffers
531 CommitLimit: Based on the overcommit ratio ('vm.overcommit_ratio'),
532 this is the total amount of memory currently available to
533 be allocated on the system. This limit is only adhered to
534 if strict overcommit accounting is enabled (mode 2 in
535 'vm.overcommit_memory').
536 The CommitLimit is calculated with the following formula:
537 CommitLimit = ('vm.overcommit_ratio' * Physical RAM) + Swap
538 For example, on a system with 1G of physical RAM and 7G
539 of swap with a `vm.overcommit_ratio` of 30 it would
540 yield a CommitLimit of 7.3G.
541 For more details, see the memory overcommit documentation
542 in vm/overcommit-accounting.
543 Committed_AS: The amount of memory presently allocated on the system.
544 The committed memory is a sum of all of the memory which
545 has been allocated by processes, even if it has not been
546 "used" by them as of yet. A process which malloc()'s 1G
547 of memory, but only touches 300M of it will only show up
548 as using 300M of memory even if it has the address space
549 allocated for the entire 1G. This 1G is memory which has
550 been "committed" to by the VM and can be used at any time
551 by the allocating application. With strict overcommit
552 enabled on the system (mode 2 in 'vm.overcommit_memory'),
553 allocations which would exceed the CommitLimit (detailed
554 above) will not be permitted. This is useful if one needs
555 to guarantee that processes will not fail due to lack of
556 memory once that memory has been successfully allocated.
557 VmallocTotal: total size of vmalloc memory area
558 VmallocUsed: amount of vmalloc area which is used
559 VmallocChunk: largest contigious block of vmalloc area which is free
561 ..............................................................................
565 Provides information about vmalloced/vmaped areas. One line per area,
566 containing the virtual address range of the area, size in bytes,
567 caller information of the creator, and optional information depending
568 on the kind of area :
570 pages=nr number of pages
571 phys=addr if a physical address was specified
572 ioremap I/O mapping (ioremap() and friends)
573 vmalloc vmalloc() area
576 vpages buffer for pages pointers was vmalloced (huge area)
577 N<node>=nr (Only on NUMA kernels)
578 Number of pages allocated on memory node <node>
580 > cat /proc/vmallocinfo
581 0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ...
582 /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128
583 0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ...
584 /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64
585 0xffffc20000302000-0xffffc20000304000 8192 acpi_tb_verify_table+0x21/0x4f...
586 phys=7fee8000 ioremap
587 0xffffc20000304000-0xffffc20000307000 12288 acpi_tb_verify_table+0x21/0x4f...
588 phys=7fee7000 ioremap
589 0xffffc2000031d000-0xffffc2000031f000 8192 init_vdso_vars+0x112/0x210
590 0xffffc2000031f000-0xffffc2000032b000 49152 cramfs_uncompress_init+0x2e ...
591 /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3
592 0xffffc2000033a000-0xffffc2000033d000 12288 sys_swapon+0x640/0xac0 ...
594 0xffffc20000347000-0xffffc2000034c000 20480 xt_alloc_table_info+0xfe ...
595 /0x130 [x_tables] pages=4 vmalloc N0=4
596 0xffffffffa0000000-0xffffffffa000f000 61440 sys_init_module+0xc27/0x1d00 ...
597 pages=14 vmalloc N2=14
598 0xffffffffa000f000-0xffffffffa0014000 20480 sys_init_module+0xc27/0x1d00 ...
600 0xffffffffa0014000-0xffffffffa0017000 12288 sys_init_module+0xc27/0x1d00 ...
602 0xffffffffa0017000-0xffffffffa0022000 45056 sys_init_module+0xc27/0x1d00 ...
603 pages=10 vmalloc N0=10
605 1.3 IDE devices in /proc/ide
606 ----------------------------
608 The subdirectory /proc/ide contains information about all IDE devices of which
609 the kernel is aware. There is one subdirectory for each IDE controller, the
610 file drivers and a link for each IDE device, pointing to the device directory
611 in the controller specific subtree.
613 The file drivers contains general information about the drivers used for the
616 > cat /proc/ide/drivers
617 ide-cdrom version 4.53
618 ide-disk version 1.08
620 More detailed information can be found in the controller specific
621 subdirectories. These are named ide0, ide1 and so on. Each of these
622 directories contains the files shown in table 1-5.
625 Table 1-5: IDE controller info in /proc/ide/ide?
626 ..............................................................................
628 channel IDE channel (0 or 1)
629 config Configuration (only for PCI/IDE bridge)
631 model Type/Chipset of IDE controller
632 ..............................................................................
634 Each device connected to a controller has a separate subdirectory in the
635 controllers directory. The files listed in table 1-6 are contained in these
639 Table 1-6: IDE device information
640 ..............................................................................
643 capacity Capacity of the medium (in 512Byte blocks)
644 driver driver and version
645 geometry physical and logical geometry
646 identify device identify block
648 model device identifier
649 settings device setup
650 smart_thresholds IDE disk management thresholds
651 smart_values IDE disk management values
652 ..............................................................................
654 The most interesting file is settings. This file contains a nice overview of
655 the drive parameters:
657 # cat /proc/ide/ide0/hda/settings
658 name value min max mode
659 ---- ----- --- --- ----
660 bios_cyl 526 0 65535 rw
661 bios_head 255 0 255 rw
663 breada_readahead 4 0 127 rw
665 file_readahead 72 0 2097151 rw
667 keepsettings 0 0 1 rw
668 max_kb_per_request 122 1 127 rw
672 pio_mode write-only 0 255 w
678 1.4 Networking info in /proc/net
679 --------------------------------
681 The subdirectory /proc/net follows the usual pattern. Table 1-6 shows the
682 additional values you get for IP version 6 if you configure the kernel to
683 support this. Table 1-7 lists the files and their meaning.
686 Table 1-6: IPv6 info in /proc/net
687 ..............................................................................
689 udp6 UDP sockets (IPv6)
690 tcp6 TCP sockets (IPv6)
691 raw6 Raw device statistics (IPv6)
692 igmp6 IP multicast addresses, which this host joined (IPv6)
693 if_inet6 List of IPv6 interface addresses
694 ipv6_route Kernel routing table for IPv6
695 rt6_stats Global IPv6 routing tables statistics
696 sockstat6 Socket statistics (IPv6)
697 snmp6 Snmp data (IPv6)
698 ..............................................................................
701 Table 1-7: Network info in /proc/net
702 ..............................................................................
705 dev network devices with statistics
706 dev_mcast the Layer2 multicast groups a device is listening too
707 (interface index, label, number of references, number of bound
709 dev_stat network device status
710 ip_fwchains Firewall chain linkage
711 ip_fwnames Firewall chain names
712 ip_masq Directory containing the masquerading tables
713 ip_masquerade Major masquerading table
714 netstat Network statistics
715 raw raw device statistics
716 route Kernel routing table
717 rpc Directory containing rpc info
718 rt_cache Routing cache
720 sockstat Socket statistics
722 tr_rif Token ring RIF routing table
724 unix UNIX domain sockets
725 wireless Wireless interface data (Wavelan etc)
726 igmp IP multicast addresses, which this host joined
727 psched Global packet scheduler parameters.
728 netlink List of PF_NETLINK sockets
729 ip_mr_vifs List of multicast virtual interfaces
730 ip_mr_cache List of multicast routing cache
731 ..............................................................................
733 You can use this information to see which network devices are available in
734 your system and how much traffic was routed over those devices:
738 face |bytes packets errs drop fifo frame compressed multicast|[...
739 lo: 908188 5596 0 0 0 0 0 0 [...
740 ppp0:15475140 20721 410 0 0 410 0 0 [...
741 eth0: 614530 7085 0 0 0 0 0 1 [...
744 ...] bytes packets errs drop fifo colls carrier compressed
745 ...] 908188 5596 0 0 0 0 0 0
746 ...] 1375103 17405 0 0 0 0 0 0
747 ...] 1703981 5535 0 0 0 3 0 0
749 In addition, each Channel Bond interface has it's own directory. For
750 example, the bond0 device will have a directory called /proc/net/bond0/.
751 It will contain information that is specific to that bond, such as the
752 current slaves of the bond, the link status of the slaves, and how
753 many times the slaves link has failed.
758 If you have a SCSI host adapter in your system, you'll find a subdirectory
759 named after the driver for this adapter in /proc/scsi. You'll also see a list
760 of all recognized SCSI devices in /proc/scsi:
764 Host: scsi0 Channel: 00 Id: 00 Lun: 00
765 Vendor: IBM Model: DGHS09U Rev: 03E0
766 Type: Direct-Access ANSI SCSI revision: 03
767 Host: scsi0 Channel: 00 Id: 06 Lun: 00
768 Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04
769 Type: CD-ROM ANSI SCSI revision: 02
772 The directory named after the driver has one file for each adapter found in
773 the system. These files contain information about the controller, including
774 the used IRQ and the IO address range. The amount of information shown is
775 dependent on the adapter you use. The example shows the output for an Adaptec
776 AHA-2940 SCSI adapter:
778 > cat /proc/scsi/aic7xxx/0
780 Adaptec AIC7xxx driver version: 5.1.19/3.2.4
782 TCQ Enabled By Default : Disabled
783 AIC7XXX_PROC_STATS : Disabled
784 AIC7XXX_RESET_DELAY : 5
785 Adapter Configuration:
786 SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter
787 Ultra Wide Controller
788 PCI MMAPed I/O Base: 0xeb001000
789 Adapter SEEPROM Config: SEEPROM found and used.
790 Adaptec SCSI BIOS: Enabled
792 SCBs: Active 0, Max Active 2,
793 Allocated 15, HW 16, Page 255
795 BIOS Control Word: 0x18b6
796 Adapter Control Word: 0x005b
797 Extended Translation: Enabled
798 Disconnect Enable Flags: 0xffff
799 Ultra Enable Flags: 0x0001
800 Tag Queue Enable Flags: 0x0000
801 Ordered Queue Tag Flags: 0x0000
802 Default Tag Queue Depth: 8
803 Tagged Queue By Device array for aic7xxx host instance 0:
804 {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255}
805 Actual queue depth per device for aic7xxx host instance 0:
806 {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}
809 Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8
810 Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0)
811 Total transfers 160151 (74577 reads and 85574 writes)
813 Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15
814 Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0)
815 Total transfers 0 (0 reads and 0 writes)
818 1.6 Parallel port info in /proc/parport
819 ---------------------------------------
821 The directory /proc/parport contains information about the parallel ports of
822 your system. It has one subdirectory for each port, named after the port
825 These directories contain the four files shown in Table 1-8.
828 Table 1-8: Files in /proc/parport
829 ..............................................................................
831 autoprobe Any IEEE-1284 device ID information that has been acquired.
832 devices list of the device drivers using that port. A + will appear by the
833 name of the device currently using the port (it might not appear
835 hardware Parallel port's base address, IRQ line and DMA channel.
836 irq IRQ that parport is using for that port. This is in a separate
837 file to allow you to alter it by writing a new value in (IRQ
839 ..............................................................................
841 1.7 TTY info in /proc/tty
842 -------------------------
844 Information about the available and actually used tty's can be found in the
845 directory /proc/tty.You'll find entries for drivers and line disciplines in
846 this directory, as shown in Table 1-9.
849 Table 1-9: Files in /proc/tty
850 ..............................................................................
852 drivers list of drivers and their usage
853 ldiscs registered line disciplines
854 driver/serial usage statistic and status of single tty lines
855 ..............................................................................
857 To see which tty's are currently in use, you can simply look into the file
860 > cat /proc/tty/drivers
861 pty_slave /dev/pts 136 0-255 pty:slave
862 pty_master /dev/ptm 128 0-255 pty:master
863 pty_slave /dev/ttyp 3 0-255 pty:slave
864 pty_master /dev/pty 2 0-255 pty:master
865 serial /dev/cua 5 64-67 serial:callout
866 serial /dev/ttyS 4 64-67 serial
867 /dev/tty0 /dev/tty0 4 0 system:vtmaster
868 /dev/ptmx /dev/ptmx 5 2 system
869 /dev/console /dev/console 5 1 system:console
870 /dev/tty /dev/tty 5 0 system:/dev/tty
871 unknown /dev/tty 4 1-63 console
874 1.8 Miscellaneous kernel statistics in /proc/stat
875 -------------------------------------------------
877 Various pieces of information about kernel activity are available in the
878 /proc/stat file. All of the numbers reported in this file are aggregates
879 since the system first booted. For a quick look, simply cat the file:
882 cpu 2255 34 2290 22625563 6290 127 456 0
883 cpu0 1132 34 1441 11311718 3675 127 438 0
884 cpu1 1123 0 849 11313845 2614 0 18 0
885 intr 114930548 113199788 3 0 5 263 0 4 [... lots more numbers ...]
892 The very first "cpu" line aggregates the numbers in all of the other "cpuN"
893 lines. These numbers identify the amount of time the CPU has spent performing
894 different kinds of work. Time units are in USER_HZ (typically hundredths of a
895 second). The meanings of the columns are as follows, from left to right:
897 - user: normal processes executing in user mode
898 - nice: niced processes executing in user mode
899 - system: processes executing in kernel mode
900 - idle: twiddling thumbs
901 - iowait: waiting for I/O to complete
902 - irq: servicing interrupts
903 - softirq: servicing softirqs
904 - steal: involuntary wait
906 The "intr" line gives counts of interrupts serviced since boot time, for each
907 of the possible system interrupts. The first column is the total of all
908 interrupts serviced; each subsequent column is the total for that particular
911 The "ctxt" line gives the total number of context switches across all CPUs.
913 The "btime" line gives the time at which the system booted, in seconds since
916 The "processes" line gives the number of processes and threads created, which
917 includes (but is not limited to) those created by calls to the fork() and
918 clone() system calls.
920 The "procs_running" line gives the number of processes currently running on
923 The "procs_blocked" line gives the number of processes currently blocked,
924 waiting for I/O to complete.
927 1.9 Ext4 file system parameters
928 ------------------------------
930 Information about mounted ext4 file systems can be found in
931 /proc/fs/ext4. Each mounted filesystem will have a directory in
932 /proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or
933 /proc/fs/ext4/dm-0). The files in each per-device directory are shown
934 in Table 1-10, below.
936 Table 1-10: Files in /proc/fs/ext4/<devname>
937 ..............................................................................
939 mb_groups details of multiblock allocator buddy cache of free blocks
940 mb_history multiblock allocation history
941 stats controls whether the multiblock allocator should start
942 collecting statistics, which are shown during the unmount
943 group_prealloc the multiblock allocator will round up allocation
944 requests to a multiple of this tuning parameter if the
945 stripe size is not set in the ext4 superblock
946 max_to_scan The maximum number of extents the multiblock allocator
947 will search to find the best extent
948 min_to_scan The minimum number of extents the multiblock allocator
949 will search to find the best extent
950 order2_req Tuning parameter which controls the minimum size for
951 requests (as a power of 2) where the buddy cache is
953 stream_req Files which have fewer blocks than this tunable
954 parameter will have their blocks allocated out of a
955 block group specific preallocation pool, so that small
956 files are packed closely together. Each large file
957 will have its blocks allocated out of its own unique
959 inode_readahead Tuning parameter which controls the maximum number of
960 inode table blocks that ext4's inode table readahead
961 algorithm will pre-read into the buffer cache
962 ..............................................................................
965 ------------------------------------------------------------------------------
967 ------------------------------------------------------------------------------
968 The /proc file system serves information about the running system. It not only
969 allows access to process data but also allows you to request the kernel status
970 by reading files in the hierarchy.
972 The directory structure of /proc reflects the types of information and makes
973 it easy, if not obvious, where to look for specific data.
974 ------------------------------------------------------------------------------
976 ------------------------------------------------------------------------------
977 CHAPTER 2: MODIFYING SYSTEM PARAMETERS
978 ------------------------------------------------------------------------------
980 ------------------------------------------------------------------------------
982 ------------------------------------------------------------------------------
983 * Modifying kernel parameters by writing into files found in /proc/sys
984 * Exploring the files which modify certain parameters
985 * Review of the /proc/sys file tree
986 ------------------------------------------------------------------------------
989 A very interesting part of /proc is the directory /proc/sys. This is not only
990 a source of information, it also allows you to change parameters within the
991 kernel. Be very careful when attempting this. You can optimize your system,
992 but you can also cause it to crash. Never alter kernel parameters on a
993 production system. Set up a development machine and test to make sure that
994 everything works the way you want it to. You may have no alternative but to
995 reboot the machine once an error has been made.
997 To change a value, simply echo the new value into the file. An example is
998 given below in the section on the file system data. You need to be root to do
999 this. You can create your own boot script to perform this every time your
1002 The files in /proc/sys can be used to fine tune and monitor miscellaneous and
1003 general things in the operation of the Linux kernel. Since some of the files
1004 can inadvertently disrupt your system, it is advisable to read both
1005 documentation and source before actually making adjustments. In any case, be
1006 very careful when writing to any of these files. The entries in /proc may
1007 change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt
1008 review the kernel documentation in the directory /usr/src/linux/Documentation.
1009 This chapter is heavily based on the documentation included in the pre 2.2
1010 kernels, and became part of it in version 2.2.1 of the Linux kernel.
1012 2.1 /proc/sys/fs - File system data
1013 -----------------------------------
1015 This subdirectory contains specific file system, file handle, inode, dentry
1016 and quota information.
1018 Currently, these files are in /proc/sys/fs:
1023 Status of the directory cache. Since directory entries are dynamically
1024 allocated and deallocated, this file indicates the current status. It holds
1025 six values, in which the last two are not used and are always zero. The others
1026 are listed in table 2-1.
1029 Table 2-1: Status files of the directory cache
1030 ..............................................................................
1032 nr_dentry Almost always zero
1033 nr_unused Number of unused cache entries
1035 in seconds after the entry may be reclaimed, when memory is short
1036 want_pages internally
1037 ..............................................................................
1039 dquot-nr and dquot-max
1040 ----------------------
1042 The file dquot-max shows the maximum number of cached disk quota entries.
1044 The file dquot-nr shows the number of allocated disk quota entries and the
1045 number of free disk quota entries.
1047 If the number of available cached disk quotas is very low and you have a large
1048 number of simultaneous system users, you might want to raise the limit.
1050 file-nr and file-max
1051 --------------------
1053 The kernel allocates file handles dynamically, but doesn't free them again at
1056 The value in file-max denotes the maximum number of file handles that the
1057 Linux kernel will allocate. When you get a lot of error messages about running
1058 out of file handles, you might want to raise this limit. The default value is
1059 10% of RAM in kilobytes. To change it, just write the new number into the
1062 # cat /proc/sys/fs/file-max
1064 # echo 8192 > /proc/sys/fs/file-max
1065 # cat /proc/sys/fs/file-max
1069 This method of revision is useful for all customizable parameters of the
1070 kernel - simply echo the new value to the corresponding file.
1072 Historically, the three values in file-nr denoted the number of allocated file
1073 handles, the number of allocated but unused file handles, and the maximum
1074 number of file handles. Linux 2.6 always reports 0 as the number of free file
1075 handles -- this is not an error, it just means that the number of allocated
1076 file handles exactly matches the number of used file handles.
1078 Attempts to allocate more file descriptors than file-max are reported with
1079 printk, look for "VFS: file-max limit <number> reached".
1081 inode-state and inode-nr
1082 ------------------------
1084 The file inode-nr contains the first two items from inode-state, so we'll skip
1087 inode-state contains two actual numbers and five dummy values. The numbers
1088 are nr_inodes and nr_free_inodes (in order of appearance).
1093 Denotes the number of inodes the system has allocated. This number will
1094 grow and shrink dynamically.
1099 Denotes the maximum number of file-handles a process can
1100 allocate. Default value is 1024*1024 (1048576) which should be
1101 enough for most machines. Actual limit depends on RLIMIT_NOFILE
1107 Represents the number of free inodes. Ie. The number of inuse inodes is
1108 (nr_inodes - nr_free_inodes).
1110 aio-nr and aio-max-nr
1111 ---------------------
1113 aio-nr is the running total of the number of events specified on the
1114 io_setup system call for all currently active aio contexts. If aio-nr
1115 reaches aio-max-nr then io_setup will fail with EAGAIN. Note that
1116 raising aio-max-nr does not result in the pre-allocation or re-sizing
1117 of any kernel data structures.
1119 2.2 /proc/sys/fs/binfmt_misc - Miscellaneous binary formats
1120 -----------------------------------------------------------
1122 Besides these files, there is the subdirectory /proc/sys/fs/binfmt_misc. This
1123 handles the kernel support for miscellaneous binary formats.
1125 Binfmt_misc provides the ability to register additional binary formats to the
1126 Kernel without compiling an additional module/kernel. Therefore, binfmt_misc
1127 needs to know magic numbers at the beginning or the filename extension of the
1130 It works by maintaining a linked list of structs that contain a description of
1131 a binary format, including a magic with size (or the filename extension),
1132 offset and mask, and the interpreter name. On request it invokes the given
1133 interpreter with the original program as argument, as binfmt_java and
1134 binfmt_em86 and binfmt_mz do. Since binfmt_misc does not define any default
1135 binary-formats, you have to register an additional binary-format.
1137 There are two general files in binfmt_misc and one file per registered format.
1138 The two general files are register and status.
1140 Registering a new binary format
1141 -------------------------------
1143 To register a new binary format you have to issue the command
1145 echo :name:type:offset:magic:mask:interpreter: > /proc/sys/fs/binfmt_misc/register
1149 with appropriate name (the name for the /proc-dir entry), offset (defaults to
1150 0, if omitted), magic, mask (which can be omitted, defaults to all 0xff) and
1151 last but not least, the interpreter that is to be invoked (for example and
1152 testing /bin/echo). Type can be M for usual magic matching or E for filename
1153 extension matching (give extension in place of magic).
1155 Check or reset the status of the binary format handler
1156 ------------------------------------------------------
1158 If you do a cat on the file /proc/sys/fs/binfmt_misc/status, you will get the
1159 current status (enabled/disabled) of binfmt_misc. Change the status by echoing
1160 0 (disables) or 1 (enables) or -1 (caution: this clears all previously
1161 registered binary formats) to status. For example echo 0 > status to disable
1162 binfmt_misc (temporarily).
1164 Status of a single handler
1165 --------------------------
1167 Each registered handler has an entry in /proc/sys/fs/binfmt_misc. These files
1168 perform the same function as status, but their scope is limited to the actual
1169 binary format. By cating this file, you also receive all related information
1170 about the interpreter/magic of the binfmt.
1172 Example usage of binfmt_misc (emulate binfmt_java)
1173 --------------------------------------------------
1175 cd /proc/sys/fs/binfmt_misc
1176 echo ':Java:M::\xca\xfe\xba\xbe::/usr/local/java/bin/javawrapper:' > register
1177 echo ':HTML:E::html::/usr/local/java/bin/appletviewer:' > register
1178 echo ':Applet:M::<!--applet::/usr/local/java/bin/appletviewer:' > register
1179 echo ':DEXE:M::\x0eDEX::/usr/bin/dosexec:' > register
1182 These four lines add support for Java executables and Java applets (like
1183 binfmt_java, additionally recognizing the .html extension with no need to put
1184 <!--applet> to every applet file). You have to install the JDK and the
1185 shell-script /usr/local/java/bin/javawrapper too. It works around the
1186 brokenness of the Java filename handling. To add a Java binary, just create a
1187 link to the class-file somewhere in the path.
1189 2.3 /proc/sys/kernel - general kernel parameters
1190 ------------------------------------------------
1192 This directory reflects general kernel behaviors. As I've said before, the
1193 contents depend on your configuration. Here you'll find the most important
1194 files, along with descriptions of what they mean and how to use them.
1199 The file contains three values; highwater, lowwater, and frequency.
1201 It exists only when BSD-style process accounting is enabled. These values
1202 control its behavior. If the free space on the file system where the log lives
1203 goes below lowwater percentage, accounting suspends. If it goes above
1204 highwater percentage, accounting resumes. Frequency determines how often you
1205 check the amount of free space (value is in seconds). Default settings are: 4,
1206 2, and 30. That is, suspend accounting if there is less than 2 percent free;
1207 resume it if we have a value of 3 or more percent; consider information about
1208 the amount of free space valid for 30 seconds
1213 When the value in this file is 0, ctrl-alt-del is trapped and sent to the init
1214 program to handle a graceful restart. However, when the value is greater that
1215 zero, Linux's reaction to this key combination will be an immediate reboot,
1216 without syncing its dirty buffers.
1219 When a program (like dosemu) has the keyboard in raw mode, the
1220 ctrl-alt-del is intercepted by the program before it ever reaches the
1221 kernel tty layer, and it is up to the program to decide what to do with
1224 domainname and hostname
1225 -----------------------
1227 These files can be controlled to set the NIS domainname and hostname of your
1228 box. For the classic darkstar.frop.org a simple:
1230 # echo "darkstar" > /proc/sys/kernel/hostname
1231 # echo "frop.org" > /proc/sys/kernel/domainname
1234 would suffice to set your hostname and NIS domainname.
1236 osrelease, ostype and version
1237 -----------------------------
1239 The names make it pretty obvious what these fields contain:
1241 > cat /proc/sys/kernel/osrelease
1244 > cat /proc/sys/kernel/ostype
1247 > cat /proc/sys/kernel/version
1248 #4 Fri Oct 1 12:41:14 PDT 1999
1251 The files osrelease and ostype should be clear enough. Version needs a little
1252 more clarification. The #4 means that this is the 4th kernel built from this
1253 source base and the date after it indicates the time the kernel was built. The
1254 only way to tune these values is to rebuild the kernel.
1259 The value in this file represents the number of seconds the kernel waits
1260 before rebooting on a panic. When you use the software watchdog, the
1261 recommended setting is 60. If set to 0, the auto reboot after a kernel panic
1262 is disabled, which is the default setting.
1267 The four values in printk denote
1269 * default_message_loglevel,
1270 * minimum_console_loglevel and
1271 * default_console_loglevel
1274 These values influence printk() behavior when printing or logging error
1275 messages, which come from inside the kernel. See syslog(2) for more
1276 information on the different log levels.
1281 Messages with a higher priority than this will be printed to the console.
1283 default_message_level
1284 ---------------------
1286 Messages without an explicit priority will be printed with this priority.
1288 minimum_console_loglevel
1289 ------------------------
1291 Minimum (highest) value to which the console_loglevel can be set.
1293 default_console_loglevel
1294 ------------------------
1296 Default value for console_loglevel.
1301 This file shows the size of the generic SCSI (sg) buffer. At this point, you
1302 can't tune it yet, but you can change it at compile time by editing
1303 include/scsi/sg.h and changing the value of SG_BIG_BUFF.
1305 If you use a scanner with SANE (Scanner Access Now Easy) you might want to set
1306 this to a higher value. Refer to the SANE documentation on this issue.
1311 The location where the modprobe binary is located. The kernel uses this
1312 program to load modules on demand.
1317 The value in this file affects behavior of handling NMI. When the value is
1318 non-zero, unknown NMI is trapped and then panic occurs. At that time, kernel
1319 debugging information is displayed on console.
1321 NMI switch that most IA32 servers have fires unknown NMI up, for example.
1322 If a system hangs up, try pressing the NMI switch.
1327 Enables/Disables the NMI watchdog on x86 systems. When the value is non-zero
1328 the NMI watchdog is enabled and will continuously test all online cpus to
1329 determine whether or not they are still functioning properly.
1331 Because the NMI watchdog shares registers with oprofile, by disabling the NMI
1332 watchdog, oprofile may have more registers to utilize.
1337 Enables/Disables the protection of the per-process proc entries "maps" and
1338 "smaps". When enabled, the contents of these files are visible only to
1339 readers that are allowed to ptrace() the given process.
1344 Maximum number of message queue ids on the system.
1345 This value scales to the amount of lowmem. It is automatically recomputed
1346 upon memory add/remove or ipc namespace creation/removal.
1347 When a value is written into this file, msgmni's value becomes fixed, i.e. it
1348 is not recomputed anymore when one of the above events occurs.
1349 Use auto_msgmni to change this behavior.
1354 Enables/Disables automatic recomputing of msgmni upon memory add/remove or
1355 upon ipc namespace creation/removal (see the msgmni description above).
1356 Echoing "1" into this file enables msgmni automatic recomputing.
1357 Echoing "0" turns it off.
1358 auto_msgmni default value is 1.
1361 2.4 /proc/sys/vm - The virtual memory subsystem
1362 -----------------------------------------------
1364 The files in this directory can be used to tune the operation of the virtual
1365 memory (VM) subsystem of the Linux kernel.
1370 Controls the tendency of the kernel to reclaim the memory which is used for
1371 caching of directory and inode objects.
1373 At the default value of vfs_cache_pressure=100 the kernel will attempt to
1374 reclaim dentries and inodes at a "fair" rate with respect to pagecache and
1375 swapcache reclaim. Decreasing vfs_cache_pressure causes the kernel to prefer
1376 to retain dentry and inode caches. Increasing vfs_cache_pressure beyond 100
1377 causes the kernel to prefer to reclaim dentries and inodes.
1379 dirty_background_ratio
1380 ----------------------
1382 Contains, as a percentage of total system memory, the number of pages at which
1383 the pdflush background writeback daemon will start writing out dirty data.
1388 Contains, as a percentage of total system memory, the number of pages at which
1389 a process which is generating disk writes will itself start writing out dirty
1392 dirty_writeback_centisecs
1393 -------------------------
1395 The pdflush writeback daemons will periodically wake up and write `old' data
1396 out to disk. This tunable expresses the interval between those wakeups, in
1397 100'ths of a second.
1399 Setting this to zero disables periodic writeback altogether.
1401 dirty_expire_centisecs
1402 ----------------------
1404 This tunable is used to define when dirty data is old enough to be eligible
1405 for writeout by the pdflush daemons. It is expressed in 100'ths of a second.
1406 Data which has been dirty in-memory for longer than this interval will be
1407 written out next time a pdflush daemon wakes up.
1409 highmem_is_dirtyable
1410 --------------------
1412 Only present if CONFIG_HIGHMEM is set.
1414 This defaults to 0 (false), meaning that the ratios set above are calculated
1415 as a percentage of lowmem only. This protects against excessive scanning
1416 in page reclaim, swapping and general VM distress.
1418 Setting this to 1 can be useful on 32 bit machines where you want to make
1419 random changes within an MMAPed file that is larger than your available
1420 lowmem without causing large quantities of random IO. Is is safe if the
1421 behavior of all programs running on the machine is known and memory will
1422 not be otherwise stressed.
1427 If non-zero, this sysctl disables the new 32-bit mmap mmap layout - the kernel
1428 will use the legacy (2.4) layout for all processes.
1430 lowmem_reserve_ratio
1431 ---------------------
1433 For some specialised workloads on highmem machines it is dangerous for
1434 the kernel to allow process memory to be allocated from the "lowmem"
1435 zone. This is because that memory could then be pinned via the mlock()
1436 system call, or by unavailability of swapspace.
1438 And on large highmem machines this lack of reclaimable lowmem memory
1441 So the Linux page allocator has a mechanism which prevents allocations
1442 which _could_ use highmem from using too much lowmem. This means that
1443 a certain amount of lowmem is defended from the possibility of being
1444 captured into pinned user memory.
1446 (The same argument applies to the old 16 megabyte ISA DMA region. This
1447 mechanism will also defend that region from allocations which could use
1450 The `lowmem_reserve_ratio' tunable determines how aggressive the kernel is
1451 in defending these lower zones.
1453 If you have a machine which uses highmem or ISA DMA and your
1454 applications are using mlock(), or if you are running with no swap then
1455 you probably should change the lowmem_reserve_ratio setting.
1457 The lowmem_reserve_ratio is an array. You can see them by reading this file.
1459 % cat /proc/sys/vm/lowmem_reserve_ratio
1462 Note: # of this elements is one fewer than number of zones. Because the highest
1463 zone's value is not necessary for following calculation.
1465 But, these values are not used directly. The kernel calculates # of protection
1466 pages for each zones from them. These are shown as array of protection pages
1467 in /proc/zoneinfo like followings. (This is an example of x86-64 box).
1468 Each zone has an array of protection pages like this.
1479 protection: (0, 2004, 2004, 2004)
1480 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1485 These protections are added to score to judge whether this zone should be used
1486 for page allocation or should be reclaimed.
1488 In this example, if normal pages (index=2) are required to this DMA zone and
1489 pages_high is used for watermark, the kernel judges this zone should not be
1490 used because pages_free(1355) is smaller than watermark + protection[2]
1491 (4 + 2004 = 2008). If this protection value is 0, this zone would be used for
1492 normal page requirement. If requirement is DMA zone(index=0), protection[0]
1495 zone[i]'s protection[j] is calculated by following expression.
1498 zone[i]->protection[j]
1499 = (total sums of present_pages from zone[i+1] to zone[j] on the node)
1500 / lowmem_reserve_ratio[i];
1502 (should not be protected. = 0;
1504 (not necessary, but looks 0)
1506 The default values of lowmem_reserve_ratio[i] are
1507 256 (if zone[i] means DMA or DMA32 zone)
1509 As above expression, they are reciprocal number of ratio.
1510 256 means 1/256. # of protection pages becomes about "0.39%" of total present
1511 pages of higher zones on the node.
1513 If you would like to protect more pages, smaller values are effective.
1514 The minimum value is 1 (1/1 -> 100%).
1519 page-cluster controls the number of pages which are written to swap in
1520 a single attempt. The swap I/O size.
1522 It is a logarithmic value - setting it to zero means "1 page", setting
1523 it to 1 means "2 pages", setting it to 2 means "4 pages", etc.
1525 The default value is three (eight pages at a time). There may be some
1526 small benefits in tuning this to a different value if your workload is
1532 Controls overcommit of system memory, possibly allowing processes
1533 to allocate (but not use) more memory than is actually available.
1536 0 - Heuristic overcommit handling. Obvious overcommits of
1537 address space are refused. Used for a typical system. It
1538 ensures a seriously wild allocation fails while allowing
1539 overcommit to reduce swap usage. root is allowed to
1540 allocate slightly more memory in this mode. This is the
1543 1 - Always overcommit. Appropriate for some scientific
1546 2 - Don't overcommit. The total address space commit
1547 for the system is not permitted to exceed swap plus a
1548 configurable percentage (default is 50) of physical RAM.
1549 Depending on the percentage you use, in most situations
1550 this means a process will not be killed while attempting
1551 to use already-allocated memory but will receive errors
1552 on memory allocation as appropriate.
1557 Percentage of physical memory size to include in overcommit calculations
1560 Memory allocation limit = swapspace + physmem * (overcommit_ratio / 100)
1562 swapspace = total size of all swap areas
1563 physmem = size of physical memory in system
1565 nr_hugepages and hugetlb_shm_group
1566 ----------------------------------
1568 nr_hugepages configures number of hugetlb page reserved for the system.
1570 hugetlb_shm_group contains group id that is allowed to create SysV shared
1571 memory segment using hugetlb page.
1573 hugepages_treat_as_movable
1574 --------------------------
1576 This parameter is only useful when kernelcore= is specified at boot time to
1577 create ZONE_MOVABLE for pages that may be reclaimed or migrated. Huge pages
1578 are not movable so are not normally allocated from ZONE_MOVABLE. A non-zero
1579 value written to hugepages_treat_as_movable allows huge pages to be allocated
1582 Once enabled, the ZONE_MOVABLE is treated as an area of memory the huge
1583 pages pool can easily grow or shrink within. Assuming that applications are
1584 not running that mlock() a lot of memory, it is likely the huge pages pool
1585 can grow to the size of ZONE_MOVABLE by repeatedly entering the desired value
1586 into nr_hugepages and triggering page reclaim.
1591 laptop_mode is a knob that controls "laptop mode". All the things that are
1592 controlled by this knob are discussed in Documentation/laptops/laptop-mode.txt.
1597 block_dump enables block I/O debugging when set to a nonzero value. More
1598 information on block I/O debugging is in Documentation/laptops/laptop-mode.txt.
1603 This file contains valid hold time of swap out protection token. The Linux
1604 VM has token based thrashing control mechanism and uses the token to prevent
1605 unnecessary page faults in thrashing situation. The unit of the value is
1606 second. The value would be useful to tune thrashing behavior.
1611 Writing to this will cause the kernel to drop clean caches, dentries and
1612 inodes from memory, causing that memory to become free.
1615 echo 1 > /proc/sys/vm/drop_caches
1616 To free dentries and inodes:
1617 echo 2 > /proc/sys/vm/drop_caches
1618 To free pagecache, dentries and inodes:
1619 echo 3 > /proc/sys/vm/drop_caches
1621 As this is a non-destructive operation and dirty objects are not freeable, the
1622 user should run `sync' first.
1625 2.5 /proc/sys/dev - Device specific parameters
1626 ----------------------------------------------
1628 Currently there is only support for CDROM drives, and for those, there is only
1629 one read-only file containing information about the CD-ROM drives attached to
1632 >cat /proc/sys/dev/cdrom/info
1633 CD-ROM information, Id: cdrom.c 2.55 1999/04/25
1637 drive # of slots: 1 0
1641 Can change speed: 1 1
1642 Can select disk: 0 1
1643 Can read multisession: 1 1
1645 Reports media changed: 1 1
1649 You see two drives, sr0 and hdb, along with a list of their features.
1651 2.6 /proc/sys/sunrpc - Remote procedure calls
1652 ---------------------------------------------
1654 This directory contains four files, which enable or disable debugging for the
1655 RPC functions NFS, NFS-daemon, RPC and NLM. The default values are 0. They can
1656 be set to one to turn debugging on. (The default value is 0 for each)
1658 2.7 /proc/sys/net - Networking stuff
1659 ------------------------------------
1661 The interface to the networking parts of the kernel is located in
1662 /proc/sys/net. Table 2-3 shows all possible subdirectories. You may see only
1663 some of them, depending on your kernel's configuration.
1666 Table 2-3: Subdirectories in /proc/sys/net
1667 ..............................................................................
1668 Directory Content Directory Content
1669 core General parameter appletalk Appletalk protocol
1670 unix Unix domain sockets netrom NET/ROM
1671 802 E802 protocol ax25 AX25
1672 ethernet Ethernet protocol rose X.25 PLP layer
1673 ipv4 IP version 4 x25 X.25 protocol
1674 ipx IPX token-ring IBM token ring
1675 bridge Bridging decnet DEC net
1677 ..............................................................................
1679 We will concentrate on IP networking here. Since AX15, X.25, and DEC Net are
1680 only minor players in the Linux world, we'll skip them in this chapter. You'll
1681 find some short info on Appletalk and IPX further on in this chapter. Review
1682 the online documentation and the kernel source to get a detailed view of the
1683 parameters for those protocols. In this section we'll discuss the
1684 subdirectories printed in bold letters in the table above. As default values
1685 are suitable for most needs, there is no need to change these values.
1687 /proc/sys/net/core - Network core options
1688 -----------------------------------------
1693 The default setting of the socket receive buffer in bytes.
1698 The maximum receive socket buffer size in bytes.
1703 The default setting (in bytes) of the socket send buffer.
1708 The maximum send socket buffer size in bytes.
1710 message_burst and message_cost
1711 ------------------------------
1713 These parameters are used to limit the warning messages written to the kernel
1714 log from the networking code. They enforce a rate limit to make a
1715 denial-of-service attack impossible. A higher message_cost factor, results in
1716 fewer messages that will be written. Message_burst controls when messages will
1717 be dropped. The default settings limit warning messages to one every five
1723 This controls console messages from the networking stack that can occur because
1724 of problems on the network like duplicate address or bad checksums. Normally,
1725 this should be enabled, but if the problem persists the messages can be
1732 Maximum number of packets, queued on the INPUT side, when the interface
1733 receives packets faster than kernel can process them.
1738 Maximum ancillary buffer size allowed per socket. Ancillary data is a sequence
1739 of struct cmsghdr structures with appended data.
1741 /proc/sys/net/unix - Parameters for Unix domain sockets
1742 -------------------------------------------------------
1744 There are only two files in this subdirectory. They control the delays for
1745 deleting and destroying socket descriptors.
1747 2.8 /proc/sys/net/ipv4 - IPV4 settings
1748 --------------------------------------
1750 IP version 4 is still the most used protocol in Unix networking. It will be
1751 replaced by IP version 6 in the next couple of years, but for the moment it's
1752 the de facto standard for the internet and is used in most networking
1753 environments around the world. Because of the importance of this protocol,
1754 we'll have a deeper look into the subtree controlling the behavior of the IPv4
1755 subsystem of the Linux kernel.
1757 Let's start with the entries in /proc/sys/net/ipv4.
1762 icmp_echo_ignore_all and icmp_echo_ignore_broadcasts
1763 ----------------------------------------------------
1765 Turn on (1) or off (0), if the kernel should ignore all ICMP ECHO requests, or
1766 just those to broadcast and multicast addresses.
1768 Please note that if you accept ICMP echo requests with a broadcast/multi\-cast
1769 destination address your network may be used as an exploder for denial of
1770 service packet flooding attacks to other hosts.
1772 icmp_destunreach_rate, icmp_echoreply_rate, icmp_paramprob_rate and icmp_timeexeed_rate
1773 ---------------------------------------------------------------------------------------
1775 Sets limits for sending ICMP packets to specific targets. A value of zero
1776 disables all limiting. Any positive value sets the maximum package rate in
1777 hundredth of a second (on Intel systems).
1785 This file contains the number one if the host received its IP configuration by
1786 RARP, BOOTP, DHCP or a similar mechanism. Otherwise it is zero.
1791 TTL (Time To Live) for IPv4 interfaces. This is simply the maximum number of
1792 hops a packet may travel.
1797 Enable dynamic socket address rewriting on interface address change. This is
1798 useful for dialup interface with changing IP addresses.
1803 Enable or disable forwarding of IP packages between interfaces. Changing this
1804 value resets all other parameters to their default values. They differ if the
1805 kernel is configured as host or router.
1810 Range of ports used by TCP and UDP to choose the local port. Contains two
1811 numbers, the first number is the lowest port, the second number the highest
1812 local port. Default is 1024-4999. Should be changed to 32768-61000 for
1818 Global switch to turn path MTU discovery off. It can also be set on a per
1819 socket basis by the applications or on a per route basis.
1824 Enable/disable debugging of IP masquerading.
1826 IP fragmentation settings
1827 -------------------------
1829 ipfrag_high_trash and ipfrag_low_trash
1830 --------------------------------------
1832 Maximum memory used to reassemble IP fragments. When ipfrag_high_thresh bytes
1833 of memory is allocated for this purpose, the fragment handler will toss
1834 packets until ipfrag_low_thresh is reached.
1839 Time in seconds to keep an IP fragment in memory.
1847 This file controls the use of the ECN bit in the IPv4 headers. This is a new
1848 feature about Explicit Congestion Notification, but some routers and firewalls
1849 block traffic that has this bit set, so it could be necessary to echo 0 to
1850 /proc/sys/net/ipv4/tcp_ecn if you want to talk to these sites. For more info
1851 you could read RFC2481.
1853 tcp_retrans_collapse
1854 --------------------
1856 Bug-to-bug compatibility with some broken printers. On retransmit, try to send
1857 larger packets to work around bugs in certain TCP stacks. Can be turned off by
1860 tcp_keepalive_probes
1861 --------------------
1863 Number of keep alive probes TCP sends out, until it decides that the
1864 connection is broken.
1869 How often TCP sends out keep alive messages, when keep alive is enabled. The
1875 Number of times initial SYNs for a TCP connection attempt will be
1876 retransmitted. Should not be higher than 255. This is only the timeout for
1877 outgoing connections, for incoming connections the number of retransmits is
1878 defined by tcp_retries1.
1883 Enable select acknowledgments after RFC2018.
1888 Enable timestamps as defined in RFC1323.
1893 Enable the strict RFC793 interpretation of the TCP urgent pointer field. The
1894 default is to use the BSD compatible interpretation of the urgent pointer
1895 pointing to the first byte after the urgent data. The RFC793 interpretation is
1896 to have it point to the last byte of urgent data. Enabling this option may
1897 lead to interoperability problems. Disabled by default.
1902 Only valid when the kernel was compiled with CONFIG_SYNCOOKIES. Send out
1903 syncookies when the syn backlog queue of a socket overflows. This is to ward
1904 off the common 'syn flood attack'. Disabled by default.
1906 Note that the concept of a socket backlog is abandoned. This means the peer
1907 may not receive reliable error messages from an over loaded server with
1913 Enable window scaling as defined in RFC1323.
1918 The length of time in seconds it takes to receive a final FIN before the
1919 socket is always closed. This is strictly a violation of the TCP
1920 specification, but required to prevent denial-of-service attacks.
1925 Indicates how many keep alive probes are sent per slow timer run. Should not
1926 be set too high to prevent bursts.
1931 Length of the per socket backlog queue. Since Linux 2.2 the backlog specified
1932 in listen(2) only specifies the length of the backlog queue of already
1933 established sockets. When more connection requests arrive Linux starts to drop
1934 packets. When syncookies are enabled the packets are still answered and the
1935 maximum queue is effectively ignored.
1940 Defines how often an answer to a TCP connection request is retransmitted
1946 Defines how often a TCP packet is retransmitted before giving up.
1948 Interface specific settings
1949 ---------------------------
1951 In the directory /proc/sys/net/ipv4/conf you'll find one subdirectory for each
1952 interface the system knows about and one directory calls all. Changes in the
1953 all subdirectory affect all interfaces, whereas changes in the other
1954 subdirectories affect only one interface. All directories have the same
1960 This switch decides if the kernel accepts ICMP redirect messages or not. The
1961 default is 'yes' if the kernel is configured for a regular host and 'no' for a
1962 router configuration.
1967 Should source routed packages be accepted or declined. The default is
1968 dependent on the kernel configuration. It's 'yes' for routers and 'no' for
1974 Accept packets with source address 0.b.c.d with destinations not to this host
1975 as local ones. It is supposed that a BOOTP relay daemon will catch and forward
1978 The default is 0, since this feature is not implemented yet (kernel version
1984 Enable or disable IP forwarding on this interface.
1989 Log packets with source addresses with no known route to kernel log.
1994 Do multicast routing. The kernel needs to be compiled with CONFIG_MROUTE and a
1995 multicast routing daemon is required.
2000 Does (1) or does not (0) perform proxy ARP.
2005 Integer value determines if a source validation should be made. 1 means yes, 0
2006 means no. Disabled by default, but local/broadcast address spoofing is always
2009 If you set this to 1 on a router that is the only connection for a network to
2010 the net, it will prevent spoofing attacks against your internal networks
2011 (external addresses can still be spoofed), without the need for additional
2017 Accept ICMP redirect messages only for gateways, listed in default gateway
2018 list. Enabled by default.
2023 If it is not set the kernel does not assume that different subnets on this
2024 device can communicate directly. Default setting is 'yes'.
2029 Determines whether to send ICMP redirects to other hosts.
2034 The directory /proc/sys/net/ipv4/route contains several file to control
2037 error_burst and error_cost
2038 --------------------------
2040 These parameters are used to limit how many ICMP destination unreachable to
2041 send from the host in question. ICMP destination unreachable messages are
2042 sent when we cannot reach the next hop while trying to transmit a packet.
2043 It will also print some error messages to kernel logs if someone is ignoring
2044 our ICMP redirects. The higher the error_cost factor is, the fewer
2045 destination unreachable and error messages will be let through. Error_burst
2046 controls when destination unreachable messages and error messages will be
2047 dropped. The default settings limit warning messages to five every second.
2052 Writing to this file results in a flush of the routing cache.
2054 gc_elasticity, gc_interval, gc_min_interval_ms, gc_timeout, gc_thresh
2055 ---------------------------------------------------------------------
2057 Values to control the frequency and behavior of the garbage collection
2058 algorithm for the routing cache. gc_min_interval is deprecated and replaced
2059 by gc_min_interval_ms.
2065 Maximum size of the routing cache. Old entries will be purged once the cache
2066 reached has this size.
2068 redirect_load, redirect_number
2069 ------------------------------
2071 Factors which determine if more ICPM redirects should be sent to a specific
2072 host. No redirects will be sent once the load limit or the maximum number of
2073 redirects has been reached.
2078 Timeout for redirects. After this period redirects will be sent again, even if
2079 this has been stopped, because the load or number limit has been reached.
2081 Network Neighbor handling
2082 -------------------------
2084 Settings about how to handle connections with direct neighbors (nodes attached
2085 to the same link) can be found in the directory /proc/sys/net/ipv4/neigh.
2087 As we saw it in the conf directory, there is a default subdirectory which
2088 holds the default values, and one directory for each interface. The contents
2089 of the directories are identical, with the single exception that the default
2090 settings contain additional options to set garbage collection parameters.
2092 In the interface directories you'll find the following entries:
2094 base_reachable_time, base_reachable_time_ms
2095 -------------------------------------------
2097 A base value used for computing the random reachable time value as specified
2100 Expression of base_reachable_time, which is deprecated, is in seconds.
2101 Expression of base_reachable_time_ms is in milliseconds.
2103 retrans_time, retrans_time_ms
2104 -----------------------------
2106 The time between retransmitted Neighbor Solicitation messages.
2107 Used for address resolution and to determine if a neighbor is
2110 Expression of retrans_time, which is deprecated, is in 1/100 seconds (for
2111 IPv4) or in jiffies (for IPv6).
2112 Expression of retrans_time_ms is in milliseconds.
2117 Maximum queue length for a pending arp request - the number of packets which
2118 are accepted from other layers while the ARP address is still resolved.
2123 Maximum for random delay of answers to neighbor solicitation messages in
2124 jiffies (1/100 sec). Not yet implemented (Linux does not have anycast support
2130 Maximum number of retries for unicast solicitation.
2135 Maximum number of retries for multicast solicitation.
2137 delay_first_probe_time
2138 ----------------------
2140 Delay for the first time probe if the neighbor is reachable. (see
2146 An ARP/neighbor entry is only replaced with a new one if the old is at least
2147 locktime old. This prevents ARP cache thrashing.
2152 Maximum time (real time is random [0..proxytime]) before answering to an ARP
2153 request for which we have an proxy ARP entry. In some cases, this is used to
2154 prevent network flooding.
2159 Maximum queue length of the delayed proxy arp timer. (see proxy_delay).
2164 Determines the number of requests to send to the user level ARP daemon. Use 0
2170 Determines how often to check for stale ARP entries. After an ARP entry is
2171 stale it will be resolved again (which is useful when an IP address migrates
2172 to another machine). When ucast_solicit is greater than 0 it first tries to
2173 send an ARP packet directly to the known host When that fails and
2174 mcast_solicit is greater than 0, an ARP request is broadcasted.
2179 The /proc/sys/net/appletalk directory holds the Appletalk configuration data
2180 when Appletalk is loaded. The configurable parameters are:
2185 The amount of time we keep an ARP entry before expiring it. Used to age out
2191 The amount of time we will spend trying to resolve an Appletalk address.
2193 aarp-retransmit-limit
2194 ---------------------
2196 The number of times we will retransmit a query before giving up.
2201 Controls the rate at which expires are checked.
2203 The directory /proc/net/appletalk holds the list of active Appletalk sockets
2206 The fields indicate the DDP type, the local address (in network:node format)
2207 the remote address, the size of the transmit pending queue, the size of the
2208 received queue (bytes waiting for applications to read) the state and the uid
2211 /proc/net/atalk_iface lists all the interfaces configured for appletalk.It
2212 shows the name of the interface, its Appletalk address, the network range on
2213 that address (or network number for phase 1 networks), and the status of the
2216 /proc/net/atalk_route lists each known network route. It lists the target
2217 (network) that the route leads to, the router (may be directly connected), the
2218 route flags, and the device the route is using.
2223 The IPX protocol has no tunable values in proc/sys/net.
2225 The IPX protocol does, however, provide proc/net/ipx. This lists each IPX
2226 socket giving the local and remote addresses in Novell format (that is
2227 network:node:port). In accordance with the strange Novell tradition,
2228 everything but the port is in hex. Not_Connected is displayed for sockets that
2229 are not tied to a specific remote address. The Tx and Rx queue sizes indicate
2230 the number of bytes pending for transmission and reception. The state
2231 indicates the state the socket is in and the uid is the owning uid of the
2234 The /proc/net/ipx_interface file lists all IPX interfaces. For each interface
2235 it gives the network number, the node number, and indicates if the network is
2236 the primary network. It also indicates which device it is bound to (or
2237 Internal for internal networks) and the Frame Type if appropriate. Linux
2238 supports 802.3, 802.2, 802.2 SNAP and DIX (Blue Book) ethernet framing for
2241 The /proc/net/ipx_route table holds a list of IPX routes. For each route it
2242 gives the destination network, the router node (or Directly) and the network
2243 address of the router (or Connected) for internal networks.
2245 2.11 /proc/sys/fs/mqueue - POSIX message queues filesystem
2246 ----------------------------------------------------------
2248 The "mqueue" filesystem provides the necessary kernel features to enable the
2249 creation of a user space library that implements the POSIX message queues
2250 API (as noted by the MSG tag in the POSIX 1003.1-2001 version of the System
2251 Interfaces specification.)
2253 The "mqueue" filesystem contains values for determining/setting the amount of
2254 resources used by the file system.
2256 /proc/sys/fs/mqueue/queues_max is a read/write file for setting/getting the
2257 maximum number of message queues allowed on the system.
2259 /proc/sys/fs/mqueue/msg_max is a read/write file for setting/getting the
2260 maximum number of messages in a queue value. In fact it is the limiting value
2261 for another (user) limit which is set in mq_open invocation. This attribute of
2262 a queue must be less or equal then msg_max.
2264 /proc/sys/fs/mqueue/msgsize_max is a read/write file for setting/getting the
2265 maximum message size value (it is every message queue's attribute set during
2268 2.12 /proc/<pid>/oom_adj - Adjust the oom-killer score
2269 ------------------------------------------------------
2271 This file can be used to adjust the score used to select which processes
2272 should be killed in an out-of-memory situation. Giving it a high score will
2273 increase the likelihood of this process being killed by the oom-killer. Valid
2274 values are in the range -16 to +15, plus the special value -17, which disables
2275 oom-killing altogether for this process.
2277 2.13 /proc/<pid>/oom_score - Display current oom-killer score
2278 -------------------------------------------------------------
2280 ------------------------------------------------------------------------------
2281 This file can be used to check the current score used by the oom-killer is for
2282 any given <pid>. Use it together with /proc/<pid>/oom_adj to tune which
2283 process should be killed in an out-of-memory situation.
2285 ------------------------------------------------------------------------------
2287 ------------------------------------------------------------------------------
2288 Certain aspects of kernel behavior can be modified at runtime, without the
2289 need to recompile the kernel, or even to reboot the system. The files in the
2290 /proc/sys tree can not only be read, but also modified. You can use the echo
2291 command to write value into these files, thereby changing the default settings
2293 ------------------------------------------------------------------------------
2295 2.14 /proc/<pid>/io - Display the IO accounting fields
2296 -------------------------------------------------------
2298 This file contains IO statistics for each running process
2303 test:/tmp # dd if=/dev/zero of=/tmp/test.dat &
2306 test:/tmp # cat /proc/3828/io
2312 write_bytes: 323932160
2313 cancelled_write_bytes: 0
2322 I/O counter: chars read
2323 The number of bytes which this task has caused to be read from storage. This
2324 is simply the sum of bytes which this process passed to read() and pread().
2325 It includes things like tty IO and it is unaffected by whether or not actual
2326 physical disk IO was required (the read might have been satisfied from
2333 I/O counter: chars written
2334 The number of bytes which this task has caused, or shall cause to be written
2335 to disk. Similar caveats apply here as with rchar.
2341 I/O counter: read syscalls
2342 Attempt to count the number of read I/O operations, i.e. syscalls like read()
2349 I/O counter: write syscalls
2350 Attempt to count the number of write I/O operations, i.e. syscalls like
2351 write() and pwrite().
2357 I/O counter: bytes read
2358 Attempt to count the number of bytes which this process really did cause to
2359 be fetched from the storage layer. Done at the submit_bio() level, so it is
2360 accurate for block-backed filesystems. <please add status regarding NFS and
2361 CIFS at a later time>
2367 I/O counter: bytes written
2368 Attempt to count the number of bytes which this process caused to be sent to
2369 the storage layer. This is done at page-dirtying time.
2372 cancelled_write_bytes
2373 ---------------------
2375 The big inaccuracy here is truncate. If a process writes 1MB to a file and
2376 then deletes the file, it will in fact perform no writeout. But it will have
2377 been accounted as having caused 1MB of write.
2378 In other words: The number of bytes which this process caused to not happen,
2379 by truncating pagecache. A task can cause "negative" IO too. If this task
2380 truncates some dirty pagecache, some IO which another task has been accounted
2381 for (in it's write_bytes) will not be happening. We _could_ just subtract that
2382 from the truncating task's write_bytes, but there is information loss in doing
2389 At its current implementation state, this is a bit racy on 32-bit machines: if
2390 process A reads process B's /proc/pid/io while process B is updating one of
2391 those 64-bit counters, process A could see an intermediate result.
2394 More information about this can be found within the taskstats documentation in
2395 Documentation/accounting.
2397 2.15 /proc/<pid>/coredump_filter - Core dump filtering settings
2398 ---------------------------------------------------------------
2399 When a process is dumped, all anonymous memory is written to a core file as
2400 long as the size of the core file isn't limited. But sometimes we don't want
2401 to dump some memory segments, for example, huge shared memory. Conversely,
2402 sometimes we want to save file-backed memory segments into a core file, not
2403 only the individual files.
2405 /proc/<pid>/coredump_filter allows you to customize which memory segments
2406 will be dumped when the <pid> process is dumped. coredump_filter is a bitmask
2407 of memory types. If a bit of the bitmask is set, memory segments of the
2408 corresponding memory type are dumped, otherwise they are not dumped.
2410 The following 4 memory types are supported:
2411 - (bit 0) anonymous private memory
2412 - (bit 1) anonymous shared memory
2413 - (bit 2) file-backed private memory
2414 - (bit 3) file-backed shared memory
2415 - (bit 4) ELF header pages in file-backed private memory areas (it is
2416 effective only if the bit 2 is cleared)
2418 Note that MMIO pages such as frame buffer are never dumped and vDSO pages
2419 are always dumped regardless of the bitmask status.
2421 Default value of coredump_filter is 0x3; this means all anonymous memory
2422 segments are dumped.
2424 If you don't want to dump all shared memory segments attached to pid 1234,
2425 write 1 to the process's proc file.
2427 $ echo 0x1 > /proc/1234/coredump_filter
2429 When a new process is created, the process inherits the bitmask status from its
2430 parent. It is useful to set up coredump_filter before the program runs.
2433 $ echo 0x7 > /proc/self/coredump_filter
2436 2.16 /proc/<pid>/mountinfo - Information about mounts
2437 --------------------------------------------------------
2439 This file contains lines of the form:
2441 36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue
2442 (1)(2)(3) (4) (5) (6) (7) (8) (9) (10) (11)
2444 (1) mount ID: unique identifier of the mount (may be reused after umount)
2445 (2) parent ID: ID of parent (or of self for the top of the mount tree)
2446 (3) major:minor: value of st_dev for files on filesystem
2447 (4) root: root of the mount within the filesystem
2448 (5) mount point: mount point relative to the process's root
2449 (6) mount options: per mount options
2450 (7) optional fields: zero or more fields of the form "tag[:value]"
2451 (8) separator: marks the end of the optional fields
2452 (9) filesystem type: name of filesystem of the form "type[.subtype]"
2453 (10) mount source: filesystem specific information or "none"
2454 (11) super options: per super block options
2456 Parsers should ignore all unrecognised optional fields. Currently the
2457 possible optional fields are:
2459 shared:X mount is shared in peer group X
2460 master:X mount is slave to peer group X
2461 propagate_from:X mount is slave and receives propagation from peer group X (*)
2462 unbindable mount is unbindable
2464 (*) X is the closest dominant peer group under the process's root. If
2465 X is the immediate master of the mount, or if there's no dominant peer
2466 group under the same root, then only the "master:X" field is present
2467 and not the "propagate_from:X" field.
2469 For more information on mount propagation see:
2471 Documentation/filesystems/sharedsubtree.txt
2473 ------------------------------------------------------------------------------
Code Review / linux-2.6.git / blob