| blob | 2a99116edc47335f6ab6f50859de0a8284750cdd |
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 ------------------------------------------------------------------------------
13 Table of Contents
14 -----------------
16 0 Preface
17 0.1 Introduction/Credits
18 0.2 Legal Stuff
20 1 Collecting System Information
21 1.1 Process-Specific Subdirectories
22 1.2 Kernel data
23 1.3 IDE devices in /proc/ide
24 1.4 Networking info in /proc/net
25 1.5 SCSI info
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
39 2.9 Appletalk
40 2.10 IPX
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 ------------------------------------------------------------------------------
49 Preface
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
66 mail them to Bodo.
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
77 document.
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.
86 0.2 Legal Stuff
87 ---------------
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 ------------------------------------------------------------------------------
98 In This Chapter
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
104 on the system
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 ..............................................................................
127 File Content
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
138 stat Process status
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
149 Name: cat
150 State: R (running)
151 Pid: 5452
152 PPid: 743
153 TracerPid: 0 (2.4)
154 Uid: 501 501 501 501
155 Gid: 100 100 100 100
156 Groups: 100 14 16
157 VmSize: 1112 kB
158 VmLck: 0 kB
159 VmRSS: 348 kB
160 VmData: 24 kB
161 VmStk: 12 kB
162 VmExe: 8 kB
163 VmLib: 1044 kB
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 ..............................................................................
183 Field Content
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 ..............................................................................
198 Field Content
199 pid process id
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
205 sid session id
206 tty_nr tty the process uses
207 tty_pgrp pgrp of the tty
208 flags task flags
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
218 nice nice 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
235 0 (place holder)
236 0 (place holder)
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 ..............................................................................
245 1.2 Kernel data
246 ---------------
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 ..............................................................................
256 File Content
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))
276 kmsg Kernel messages
277 ksyms Kernel symbol table
278 loadavg Load average of last 1, 5 & 15 minutes
279 locks Kernel locks
280 meminfo Memory info
281 misc Miscellaneous
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)
288 rtc Real time clock
289 scsi SCSI info (see text)
290 slabinfo Slab pool info
291 stat Overall statistics
292 swaps Swap space utilization
293 sys See chapter 2
294 sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4)
295 tty Info of tty drivers
296 uptime System uptime
297 version Kernel version
298 video bttv info of video resources (2.4)
299 ..............................................................................
301 You can, for example, check which interrupts are currently in use and what
302 they are used for by looking in the file /proc/interrupts:
304 > cat /proc/interrupts
305 CPU0
306 0: 8728810 XT-PIC timer
307 1: 895 XT-PIC keyboard
308 2: 0 XT-PIC cascade
309 3: 531695 XT-PIC aha152x
310 4: 2014133 XT-PIC serial
311 5: 44401 XT-PIC pcnet_cs
312 8: 2 XT-PIC rtc
313 11: 8 XT-PIC i82365
314 12: 182918 XT-PIC PS/2 Mouse
315 13: 1 XT-PIC fpu
316 14: 1232265 XT-PIC ide0
317 15: 7 XT-PIC ide1
318 NMI: 0
320 In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the
321 output of a SMP machine):
323 > cat /proc/interrupts
325 CPU0 CPU1
326 0: 1243498 1214548 IO-APIC-edge timer
327 1: 8949 8958 IO-APIC-edge keyboard
328 2: 0 0 XT-PIC cascade
329 5: 11286 10161 IO-APIC-edge soundblaster
330 8: 1 0 IO-APIC-edge rtc
331 9: 27422 27407 IO-APIC-edge 3c503
332 12: 113645 113873 IO-APIC-edge PS/2 Mouse
333 13: 0 0 XT-PIC fpu
334 14: 22491 24012 IO-APIC-edge ide0
335 15: 2183 2415 IO-APIC-edge ide1
336 17: 30564 30414 IO-APIC-level eth0
337 18: 177 164 IO-APIC-level bttv
338 NMI: 2457961 2457959
339 LOC: 2457882 2457881
340 ERR: 2155
342 NMI is incremented in this case because every timer interrupt generates a NMI
343 (Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups.
345 LOC is the local interrupt counter of the internal APIC of every CPU.
347 ERR is incremented in the case of errors in the IO-APIC bus (the bus that
348 connects the CPUs in a SMP system. This means that an error has been detected,
349 the IO-APIC automatically retry the transmission, so it should not be a big
350 problem, but you should read the SMP-FAQ.
352 In 2.6.2* /proc/interrupts was expanded again. This time the goal was for
353 /proc/interrupts to display every IRQ vector in use by the system, not
354 just those considered 'most important'. The new vectors are:
356 THR -- interrupt raised when a machine check threshold counter
357 (typically counting ECC corrected errors of memory or cache) exceeds
358 a configurable threshold. Only available on some systems.
360 TRM -- a thermal event interrupt occurs when a temperature threshold
361 has been exceeded for the CPU. This interrupt may also be generated
362 when the temperature drops back to normal.
364 SPU -- a spurious interrupt is some interrupt that was raised then lowered
365 by some IO device before it could be fully processed by the APIC. Hence
366 the APIC sees the interrupt but does not know what device it came from.
367 For this case the APIC will generate the interrupt with a IRQ vector
368 of 0xff. This might also be generated by chipset bugs.
370 RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are
371 sent from one CPU to another per the needs of the OS. Typically,
372 their statistics are used by kernel developers and interested users to
373 determine the occurance of interrupt of the given type.
375 The above IRQ vectors are displayed only when relevent. For example,
376 the threshold vector does not exist on x86_64 platforms. Others are
377 suppressed when the system is a uniprocessor. As of this writing, only
378 i386 and x86_64 platforms support the new IRQ vector displays.
380 Of some interest is the introduction of the /proc/irq directory to 2.4.
381 It could be used to set IRQ to CPU affinity, this means that you can "hook" an
382 IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
383 irq subdir is one subdir for each IRQ, and one file; prof_cpu_mask
385 For example
386 > ls /proc/irq/
387 0 10 12 14 16 18 2 4 6 8 prof_cpu_mask
388 1 11 13 15 17 19 3 5 7 9
389 > ls /proc/irq/0/
390 smp_affinity
392 The contents of the prof_cpu_mask file and each smp_affinity file for each IRQ
393 is the same by default:
395 > cat /proc/irq/0/smp_affinity
396 ffffffff
398 It's a bitmask, in which you can specify which CPUs can handle the IRQ, you can
399 set it by doing:
401 > echo 1 > /proc/irq/prof_cpu_mask
403 This means that only the first CPU will handle the IRQ, but you can also echo 5
404 which means that only the first and fourth CPU can handle the IRQ.
406 The way IRQs are routed is handled by the IO-APIC, and it's Round Robin
407 between all the CPUs which are allowed to handle it. As usual the kernel has
408 more info than you and does a better job than you, so the defaults are the
409 best choice for almost everyone.
411 There are three more important subdirectories in /proc: net, scsi, and sys.
412 The general rule is that the contents, or even the existence of these
413 directories, depend on your kernel configuration. If SCSI is not enabled, the
414 directory scsi may not exist. The same is true with the net, which is there
415 only when networking support is present in the running kernel.
417 The slabinfo file gives information about memory usage at the slab level.
418 Linux uses slab pools for memory management above page level in version 2.2.
419 Commonly used objects have their own slab pool (such as network buffers,
420 directory cache, and so on).
422 ..............................................................................
424 > cat /proc/buddyinfo
426 Node 0, zone DMA 0 4 5 4 4 3 ...
427 Node 0, zone Normal 1 0 0 1 101 8 ...
428 Node 0, zone HighMem 2 0 0 1 1 0 ...
430 Memory fragmentation is a problem under some workloads, and buddyinfo is a
431 useful tool for helping diagnose these problems. Buddyinfo will give you a
432 clue as to how big an area you can safely allocate, or why a previous
433 allocation failed.
435 Each column represents the number of pages of a certain order which are
436 available. In this case, there are 0 chunks of 2^0*PAGE_SIZE available in
437 ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE
438 available in ZONE_NORMAL, etc...
440 ..............................................................................
442 meminfo:
444 Provides information about distribution and utilization of memory. This
445 varies by architecture and compile options. The following is from a
446 16GB PIII, which has highmem enabled. You may not have all of these fields.
448 > cat /proc/meminfo
451 MemTotal: 16344972 kB
452 MemFree: 13634064 kB
453 Buffers: 3656 kB
454 Cached: 1195708 kB
455 SwapCached: 0 kB
456 Active: 891636 kB
457 Inactive: 1077224 kB
458 HighTotal: 15597528 kB
459 HighFree: 13629632 kB
460 LowTotal: 747444 kB
461 LowFree: 4432 kB
462 SwapTotal: 0 kB
463 SwapFree: 0 kB
464 Dirty: 968 kB
465 Writeback: 0 kB
466 Mapped: 280372 kB
467 Slab: 684068 kB
468 CommitLimit: 7669796 kB
469 Committed_AS: 100056 kB
470 PageTables: 24448 kB
471 VmallocTotal: 112216 kB
472 VmallocUsed: 428 kB
473 VmallocChunk: 111088 kB
475 MemTotal: Total usable ram (i.e. physical ram minus a few reserved
476 bits and the kernel binary code)
477 MemFree: The sum of LowFree+HighFree
478 Buffers: Relatively temporary storage for raw disk blocks
479 shouldn't get tremendously large (20MB or so)
480 Cached: in-memory cache for files read from the disk (the
481 pagecache). Doesn't include SwapCached
482 SwapCached: Memory that once was swapped out, is swapped back in but
483 still also is in the swapfile (if memory is needed it
484 doesn't need to be swapped out AGAIN because it is already
485 in the swapfile. This saves I/O)
486 Active: Memory that has been used more recently and usually not
487 reclaimed unless absolutely necessary.
488 Inactive: Memory which has been less recently used. It is more
489 eligible to be reclaimed for other purposes
490 HighTotal:
491 HighFree: Highmem is all memory above ~860MB of physical memory
492 Highmem areas are for use by userspace programs, or
493 for the pagecache. The kernel must use tricks to access
494 this memory, making it slower to access than lowmem.
495 LowTotal:
496 LowFree: Lowmem is memory which can be used for everything that
497 highmem can be used for, but it is also available for the
498 kernel's use for its own data structures. Among many
499 other things, it is where everything from the Slab is
500 allocated. Bad things happen when you're out of lowmem.
501 SwapTotal: total amount of swap space available
502 SwapFree: Memory which has been evicted from RAM, and is temporarily
503 on the disk
504 Dirty: Memory which is waiting to get written back to the disk
505 Writeback: Memory which is actively being written back to the disk
506 Mapped: files which have been mmaped, such as libraries
507 Slab: in-kernel data structures cache
508 CommitLimit: Based on the overcommit ratio ('vm.overcommit_ratio'),
509 this is the total amount of memory currently available to
510 be allocated on the system. This limit is only adhered to
511 if strict overcommit accounting is enabled (mode 2 in
512 'vm.overcommit_memory').
513 The CommitLimit is calculated with the following formula:
514 CommitLimit = ('vm.overcommit_ratio' * Physical RAM) + Swap
515 For example, on a system with 1G of physical RAM and 7G
516 of swap with a `vm.overcommit_ratio` of 30 it would
517 yield a CommitLimit of 7.3G.
518 For more details, see the memory overcommit documentation
519 in vm/overcommit-accounting.
520 Committed_AS: The amount of memory presently allocated on the system.
521 The committed memory is a sum of all of the memory which
522 has been allocated by processes, even if it has not been
523 "used" by them as of yet. A process which malloc()'s 1G
524 of memory, but only touches 300M of it will only show up
525 as using 300M of memory even if it has the address space
526 allocated for the entire 1G. This 1G is memory which has
527 been "committed" to by the VM and can be used at any time
528 by the allocating application. With strict overcommit
529 enabled on the system (mode 2 in 'vm.overcommit_memory'),
530 allocations which would exceed the CommitLimit (detailed
531 above) will not be permitted. This is useful if one needs
532 to guarantee that processes will not fail due to lack of
533 memory once that memory has been successfully allocated.
534 PageTables: amount of memory dedicated to the lowest level of page
535 tables.
536 VmallocTotal: total size of vmalloc memory area
537 VmallocUsed: amount of vmalloc area which is used
538 VmallocChunk: largest contigious block of vmalloc area which is free
541 1.3 IDE devices in /proc/ide
542 ----------------------------
544 The subdirectory /proc/ide contains information about all IDE devices of which
545 the kernel is aware. There is one subdirectory for each IDE controller, the
546 file drivers and a link for each IDE device, pointing to the device directory
547 in the controller specific subtree.
549 The file drivers contains general information about the drivers used for the
550 IDE devices:
552 > cat /proc/ide/drivers
553 ide-cdrom version 4.53
554 ide-disk version 1.08
556 More detailed information can be found in the controller specific
557 subdirectories. These are named ide0, ide1 and so on. Each of these
558 directories contains the files shown in table 1-5.
561 Table 1-5: IDE controller info in /proc/ide/ide?
562 ..............................................................................
563 File Content
564 channel IDE channel (0 or 1)
565 config Configuration (only for PCI/IDE bridge)
566 mate Mate name
567 model Type/Chipset of IDE controller
568 ..............................................................................
570 Each device connected to a controller has a separate subdirectory in the
571 controllers directory. The files listed in table 1-6 are contained in these
572 directories.
575 Table 1-6: IDE device information
576 ..............................................................................
577 File Content
578 cache The cache
579 capacity Capacity of the medium (in 512Byte blocks)
580 driver driver and version
581 geometry physical and logical geometry
582 identify device identify block
583 media media type
584 model device identifier
585 settings device setup
586 smart_thresholds IDE disk management thresholds
587 smart_values IDE disk management values
588 ..............................................................................
590 The most interesting file is settings. This file contains a nice overview of
591 the drive parameters:
593 # cat /proc/ide/ide0/hda/settings
594 name value min max mode
595 ---- ----- --- --- ----
596 bios_cyl 526 0 65535 rw
597 bios_head 255 0 255 rw
598 bios_sect 63 0 63 rw
599 breada_readahead 4 0 127 rw
600 bswap 0 0 1 r
601 file_readahead 72 0 2097151 rw
602 io_32bit 0 0 3 rw
603 keepsettings 0 0 1 rw
604 max_kb_per_request 122 1 127 rw
605 multcount 0 0 8 rw
606 nice1 1 0 1 rw
607 nowerr 0 0 1 rw
608 pio_mode write-only 0 255 w
609 slow 0 0 1 rw
610 unmaskirq 0 0 1 rw
611 using_dma 0 0 1 rw
614 1.4 Networking info in /proc/net
615 --------------------------------
617 The subdirectory /proc/net follows the usual pattern. Table 1-6 shows the
618 additional values you get for IP version 6 if you configure the kernel to
619 support this. Table 1-7 lists the files and their meaning.
622 Table 1-6: IPv6 info in /proc/net
623 ..............................................................................
624 File Content
625 udp6 UDP sockets (IPv6)
626 tcp6 TCP sockets (IPv6)
627 raw6 Raw device statistics (IPv6)
628 igmp6 IP multicast addresses, which this host joined (IPv6)
629 if_inet6 List of IPv6 interface addresses
630 ipv6_route Kernel routing table for IPv6
631 rt6_stats Global IPv6 routing tables statistics
632 sockstat6 Socket statistics (IPv6)
633 snmp6 Snmp data (IPv6)
634 ..............................................................................
637 Table 1-7: Network info in /proc/net
638 ..............................................................................
639 File Content
640 arp Kernel ARP table
641 dev network devices with statistics
642 dev_mcast the Layer2 multicast groups a device is listening too
643 (interface index, label, number of references, number of bound
644 addresses).
645 dev_stat network device status
646 ip_fwchains Firewall chain linkage
647 ip_fwnames Firewall chain names
648 ip_masq Directory containing the masquerading tables
649 ip_masquerade Major masquerading table
650 netstat Network statistics
651 raw raw device statistics
652 route Kernel routing table
653 rpc Directory containing rpc info
654 rt_cache Routing cache
655 snmp SNMP data
656 sockstat Socket statistics
657 tcp TCP sockets
658 tr_rif Token ring RIF routing table
659 udp UDP sockets
660 unix UNIX domain sockets
661 wireless Wireless interface data (Wavelan etc)
662 igmp IP multicast addresses, which this host joined
663 psched Global packet scheduler parameters.
664 netlink List of PF_NETLINK sockets
665 ip_mr_vifs List of multicast virtual interfaces
666 ip_mr_cache List of multicast routing cache
667 ..............................................................................
669 You can use this information to see which network devices are available in
670 your system and how much traffic was routed over those devices:
672 > cat /proc/net/dev
673 Inter-|Receive |[...
674 face |bytes packets errs drop fifo frame compressed multicast|[...
675 lo: 908188 5596 0 0 0 0 0 0 [...
676 ppp0:15475140 20721 410 0 0 410 0 0 [...
677 eth0: 614530 7085 0 0 0 0 0 1 [...
679 ...] Transmit
680 ...] bytes packets errs drop fifo colls carrier compressed
681 ...] 908188 5596 0 0 0 0 0 0
682 ...] 1375103 17405 0 0 0 0 0 0
683 ...] 1703981 5535 0 0 0 3 0 0
685 In addition, each Channel Bond interface has it's own directory. For
686 example, the bond0 device will have a directory called /proc/net/bond0/.
687 It will contain information that is specific to that bond, such as the
688 current slaves of the bond, the link status of the slaves, and how
689 many times the slaves link has failed.
691 1.5 SCSI info
692 -------------
694 If you have a SCSI host adapter in your system, you'll find a subdirectory
695 named after the driver for this adapter in /proc/scsi. You'll also see a list
696 of all recognized SCSI devices in /proc/scsi:
698 >cat /proc/scsi/scsi
699 Attached devices:
700 Host: scsi0 Channel: 00 Id: 00 Lun: 00
701 Vendor: IBM Model: DGHS09U Rev: 03E0
702 Type: Direct-Access ANSI SCSI revision: 03
703 Host: scsi0 Channel: 00 Id: 06 Lun: 00
704 Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04
705 Type: CD-ROM ANSI SCSI revision: 02
708 The directory named after the driver has one file for each adapter found in
709 the system. These files contain information about the controller, including
710 the used IRQ and the IO address range. The amount of information shown is
711 dependent on the adapter you use. The example shows the output for an Adaptec
712 AHA-2940 SCSI adapter:
714 > cat /proc/scsi/aic7xxx/0
716 Adaptec AIC7xxx driver version: 5.1.19/3.2.4
717 Compile Options:
718 TCQ Enabled By Default : Disabled
719 AIC7XXX_PROC_STATS : Disabled
720 AIC7XXX_RESET_DELAY : 5
721 Adapter Configuration:
722 SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter
723 Ultra Wide Controller
724 PCI MMAPed I/O Base: 0xeb001000
725 Adapter SEEPROM Config: SEEPROM found and used.
726 Adaptec SCSI BIOS: Enabled
727 IRQ: 10
728 SCBs: Active 0, Max Active 2,
729 Allocated 15, HW 16, Page 255
730 Interrupts: 160328
731 BIOS Control Word: 0x18b6
732 Adapter Control Word: 0x005b
733 Extended Translation: Enabled
734 Disconnect Enable Flags: 0xffff
735 Ultra Enable Flags: 0x0001
736 Tag Queue Enable Flags: 0x0000
737 Ordered Queue Tag Flags: 0x0000
738 Default Tag Queue Depth: 8
739 Tagged Queue By Device array for aic7xxx host instance 0:
740 {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255}
741 Actual queue depth per device for aic7xxx host instance 0:
742 {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}
743 Statistics:
744 (scsi0:0:0:0)
745 Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8
746 Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0)
747 Total transfers 160151 (74577 reads and 85574 writes)
748 (scsi0:0:6:0)
749 Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15
750 Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0)
751 Total transfers 0 (0 reads and 0 writes)
754 1.6 Parallel port info in /proc/parport
755 ---------------------------------------
757 The directory /proc/parport contains information about the parallel ports of
758 your system. It has one subdirectory for each port, named after the port
759 number (0,1,2,...).
761 These directories contain the four files shown in Table 1-8.
764 Table 1-8: Files in /proc/parport
765 ..............................................................................
766 File Content
767 autoprobe Any IEEE-1284 device ID information that has been acquired.
768 devices list of the device drivers using that port. A + will appear by the
769 name of the device currently using the port (it might not appear
770 against any).
771 hardware Parallel port's base address, IRQ line and DMA channel.
772 irq IRQ that parport is using for that port. This is in a separate
773 file to allow you to alter it by writing a new value in (IRQ
774 number or none).
775 ..............................................................................
777 1.7 TTY info in /proc/tty
778 -------------------------
780 Information about the available and actually used tty's can be found in the
781 directory /proc/tty.You'll find entries for drivers and line disciplines in
782 this directory, as shown in Table 1-9.
785 Table 1-9: Files in /proc/tty
786 ..............................................................................
787 File Content
788 drivers list of drivers and their usage
789 ldiscs registered line disciplines
790 driver/serial usage statistic and status of single tty lines
791 ..............................................................................
793 To see which tty's are currently in use, you can simply look into the file
794 /proc/tty/drivers:
796 > cat /proc/tty/drivers
797 pty_slave /dev/pts 136 0-255 pty:slave
798 pty_master /dev/ptm 128 0-255 pty:master
799 pty_slave /dev/ttyp 3 0-255 pty:slave
800 pty_master /dev/pty 2 0-255 pty:master
801 serial /dev/cua 5 64-67 serial:callout
802 serial /dev/ttyS 4 64-67 serial
803 /dev/tty0 /dev/tty0 4 0 system:vtmaster
804 /dev/ptmx /dev/ptmx 5 2 system
805 /dev/console /dev/console 5 1 system:console
806 /dev/tty /dev/tty 5 0 system:/dev/tty
807 unknown /dev/tty 4 1-63 console
810 1.8 Miscellaneous kernel statistics in /proc/stat
811 -------------------------------------------------
813 Various pieces of information about kernel activity are available in the
814 /proc/stat file. All of the numbers reported in this file are aggregates
815 since the system first booted. For a quick look, simply cat the file:
817 > cat /proc/stat
818 cpu 2255 34 2290 22625563 6290 127 456 0
819 cpu0 1132 34 1441 11311718 3675 127 438 0
820 cpu1 1123 0 849 11313845 2614 0 18 0
821 intr 114930548 113199788 3 0 5 263 0 4 [... lots more numbers ...]
822 ctxt 1990473
823 btime 1062191376
824 processes 2915
825 procs_running 1
826 procs_blocked 0
828 The very first "cpu" line aggregates the numbers in all of the other "cpuN"
829 lines. These numbers identify the amount of time the CPU has spent performing
830 different kinds of work. Time units are in USER_HZ (typically hundredths of a
831 second). The meanings of the columns are as follows, from left to right:
833 - user: normal processes executing in user mode
834 - nice: niced processes executing in user mode
835 - system: processes executing in kernel mode
836 - idle: twiddling thumbs
837 - iowait: waiting for I/O to complete
838 - irq: servicing interrupts
839 - softirq: servicing softirqs
840 - steal: involuntary wait
842 The "intr" line gives counts of interrupts serviced since boot time, for each
843 of the possible system interrupts. The first column is the total of all
844 interrupts serviced; each subsequent column is the total for that particular
845 interrupt.
847 The "ctxt" line gives the total number of context switches across all CPUs.
849 The "btime" line gives the time at which the system booted, in seconds since
850 the Unix epoch.
852 The "processes" line gives the number of processes and threads created, which
853 includes (but is not limited to) those created by calls to the fork() and
854 clone() system calls.
856 The "procs_running" line gives the number of processes currently running on
857 CPUs.
859 The "procs_blocked" line gives the number of processes currently blocked,
860 waiting for I/O to complete.
862 1.9 Ext4 file system parameters
863 ------------------------------
864 Ext4 file system have one directory per partition under /proc/fs/ext4/
865 # ls /proc/fs/ext4/hdc/
866 group_prealloc max_to_scan mb_groups mb_history min_to_scan order2_req
867 stats stream_req
869 mb_groups:
870 This file gives the details of mutiblock allocator buddy cache of free blocks
872 mb_history:
873 Multiblock allocation history.
875 stats:
876 This file indicate whether the multiblock allocator should start collecting
877 statistics. The statistics are shown during unmount
879 group_prealloc:
880 The multiblock allocator normalize the block allocation request to
881 group_prealloc filesystem blocks if we don't have strip value set.
882 The stripe value can be specified at mount time or during mke2fs.
884 max_to_scan:
885 How long multiblock allocator can look for a best extent (in found extents)
887 min_to_scan:
888 How long multiblock allocator must look for a best extent
890 order2_req:
891 Multiblock allocator use 2^N search using buddies only for requests greater
892 than or equal to order2_req. The request size is specfied in file system
893 blocks. A value of 2 indicate only if the requests are greater than or equal
894 to 4 blocks.
896 stream_req:
897 Files smaller than stream_req are served by the stream allocator, whose
898 purpose is to pack requests as close each to other as possible to
899 produce smooth I/O traffic. Avalue of 16 indicate that file smaller than 16
900 filesystem block size will use group based preallocation.
902 ------------------------------------------------------------------------------
903 Summary
904 ------------------------------------------------------------------------------
905 The /proc file system serves information about the running system. It not only
906 allows access to process data but also allows you to request the kernel status
907 by reading files in the hierarchy.
909 The directory structure of /proc reflects the types of information and makes
910 it easy, if not obvious, where to look for specific data.
911 ------------------------------------------------------------------------------
913 ------------------------------------------------------------------------------
914 CHAPTER 2: MODIFYING SYSTEM PARAMETERS
915 ------------------------------------------------------------------------------
917 ------------------------------------------------------------------------------
918 In This Chapter
919 ------------------------------------------------------------------------------
920 * Modifying kernel parameters by writing into files found in /proc/sys
921 * Exploring the files which modify certain parameters
922 * Review of the /proc/sys file tree
923 ------------------------------------------------------------------------------
926 A very interesting part of /proc is the directory /proc/sys. This is not only
927 a source of information, it also allows you to change parameters within the
928 kernel. Be very careful when attempting this. You can optimize your system,
929 but you can also cause it to crash. Never alter kernel parameters on a
930 production system. Set up a development machine and test to make sure that
931 everything works the way you want it to. You may have no alternative but to
932 reboot the machine once an error has been made.
934 To change a value, simply echo the new value into the file. An example is
935 given below in the section on the file system data. You need to be root to do
936 this. You can create your own boot script to perform this every time your
937 system boots.
939 The files in /proc/sys can be used to fine tune and monitor miscellaneous and
940 general things in the operation of the Linux kernel. Since some of the files
941 can inadvertently disrupt your system, it is advisable to read both
942 documentation and source before actually making adjustments. In any case, be
943 very careful when writing to any of these files. The entries in /proc may
944 change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt
945 review the kernel documentation in the directory /usr/src/linux/Documentation.
946 This chapter is heavily based on the documentation included in the pre 2.2
947 kernels, and became part of it in version 2.2.1 of the Linux kernel.
949 2.1 /proc/sys/fs - File system data
950 -----------------------------------
952 This subdirectory contains specific file system, file handle, inode, dentry
953 and quota information.
955 Currently, these files are in /proc/sys/fs:
957 dentry-state
958 ------------
960 Status of the directory cache. Since directory entries are dynamically
961 allocated and deallocated, this file indicates the current status. It holds
962 six values, in which the last two are not used and are always zero. The others
963 are listed in table 2-1.
966 Table 2-1: Status files of the directory cache
967 ..............................................................................
968 File Content
969 nr_dentry Almost always zero
970 nr_unused Number of unused cache entries
971 age_limit
972 in seconds after the entry may be reclaimed, when memory is short
973 want_pages internally
974 ..............................................................................
976 dquot-nr and dquot-max
977 ----------------------
979 The file dquot-max shows the maximum number of cached disk quota entries.
981 The file dquot-nr shows the number of allocated disk quota entries and the
982 number of free disk quota entries.
984 If the number of available cached disk quotas is very low and you have a large
985 number of simultaneous system users, you might want to raise the limit.
987 file-nr and file-max
988 --------------------
990 The kernel allocates file handles dynamically, but doesn't free them again at
991 this time.
993 The value in file-max denotes the maximum number of file handles that the
994 Linux kernel will allocate. When you get a lot of error messages about running
995 out of file handles, you might want to raise this limit. The default value is
996 10% of RAM in kilobytes. To change it, just write the new number into the
997 file:
999 # cat /proc/sys/fs/file-max
1000 4096
1001 # echo 8192 > /proc/sys/fs/file-max
1002 # cat /proc/sys/fs/file-max
1003 8192
1006 This method of revision is useful for all customizable parameters of the
1007 kernel - simply echo the new value to the corresponding file.
1009 Historically, the three values in file-nr denoted the number of allocated file
1010 handles, the number of allocated but unused file handles, and the maximum
1011 number of file handles. Linux 2.6 always reports 0 as the number of free file
1012 handles -- this is not an error, it just means that the number of allocated
1013 file handles exactly matches the number of used file handles.
1015 Attempts to allocate more file descriptors than file-max are reported with
1016 printk, look for "VFS: file-max limit <number> reached".
1018 inode-state and inode-nr
1019 ------------------------
1021 The file inode-nr contains the first two items from inode-state, so we'll skip
1022 to that file...
1024 inode-state contains two actual numbers and five dummy values. The numbers
1025 are nr_inodes and nr_free_inodes (in order of appearance).
1027 nr_inodes
1028 ~~~~~~~~~
1030 Denotes the number of inodes the system has allocated. This number will
1031 grow and shrink dynamically.
1033 nr_open
1034 -------
1036 Denotes the maximum number of file-handles a process can
1037 allocate. Default value is 1024*1024 (1048576) which should be
1038 enough for most machines. Actual limit depends on RLIMIT_NOFILE
1039 resource limit.
1041 nr_free_inodes
1042 --------------
1044 Represents the number of free inodes. Ie. The number of inuse inodes is
1045 (nr_inodes - nr_free_inodes).
1047 aio-nr and aio-max-nr
1048 ---------------------
1050 aio-nr is the running total of the number of events specified on the
1051 io_setup system call for all currently active aio contexts. If aio-nr
1052 reaches aio-max-nr then io_setup will fail with EAGAIN. Note that
1053 raising aio-max-nr does not result in the pre-allocation or re-sizing
1054 of any kernel data structures.
1056 2.2 /proc/sys/fs/binfmt_misc - Miscellaneous binary formats
1057 -----------------------------------------------------------
1059 Besides these files, there is the subdirectory /proc/sys/fs/binfmt_misc. This
1060 handles the kernel support for miscellaneous binary formats.
1062 Binfmt_misc provides the ability to register additional binary formats to the
1063 Kernel without compiling an additional module/kernel. Therefore, binfmt_misc
1064 needs to know magic numbers at the beginning or the filename extension of the
1065 binary.
1067 It works by maintaining a linked list of structs that contain a description of
1068 a binary format, including a magic with size (or the filename extension),
1069 offset and mask, and the interpreter name. On request it invokes the given
1070 interpreter with the original program as argument, as binfmt_java and
1071 binfmt_em86 and binfmt_mz do. Since binfmt_misc does not define any default
1072 binary-formats, you have to register an additional binary-format.
1074 There are two general files in binfmt_misc and one file per registered format.
1075 The two general files are register and status.
1077 Registering a new binary format
1078 -------------------------------
1080 To register a new binary format you have to issue the command
1082 echo :name:type:offset:magic:mask:interpreter: > /proc/sys/fs/binfmt_misc/register
1086 with appropriate name (the name for the /proc-dir entry), offset (defaults to
1087 0, if omitted), magic, mask (which can be omitted, defaults to all 0xff) and
1088 last but not least, the interpreter that is to be invoked (for example and
1089 testing /bin/echo). Type can be M for usual magic matching or E for filename
1090 extension matching (give extension in place of magic).
1092 Check or reset the status of the binary format handler
1093 ------------------------------------------------------
1095 If you do a cat on the file /proc/sys/fs/binfmt_misc/status, you will get the
1096 current status (enabled/disabled) of binfmt_misc. Change the status by echoing
1097 0 (disables) or 1 (enables) or -1 (caution: this clears all previously
1098 registered binary formats) to status. For example echo 0 > status to disable
1099 binfmt_misc (temporarily).
1101 Status of a single handler
1102 --------------------------
1104 Each registered handler has an entry in /proc/sys/fs/binfmt_misc. These files
1105 perform the same function as status, but their scope is limited to the actual
1106 binary format. By cating this file, you also receive all related information
1107 about the interpreter/magic of the binfmt.
1109 Example usage of binfmt_misc (emulate binfmt_java)
1110 --------------------------------------------------
1112 cd /proc/sys/fs/binfmt_misc
1113 echo ':Java:M::\xca\xfe\xba\xbe::/usr/local/java/bin/javawrapper:' > register
1114 echo ':HTML:E::html::/usr/local/java/bin/appletviewer:' > register
1115 echo ':Applet:M::<!--applet::/usr/local/java/bin/appletviewer:' > register
1116 echo ':DEXE:M::\x0eDEX::/usr/bin/dosexec:' > register
1119 These four lines add support for Java executables and Java applets (like
1120 binfmt_java, additionally recognizing the .html extension with no need to put
1121 <!--applet> to every applet file). You have to install the JDK and the
1122 shell-script /usr/local/java/bin/javawrapper too. It works around the
1123 brokenness of the Java filename handling. To add a Java binary, just create a
1124 link to the class-file somewhere in the path.
1126 2.3 /proc/sys/kernel - general kernel parameters
1127 ------------------------------------------------
1129 This directory reflects general kernel behaviors. As I've said before, the
1130 contents depend on your configuration. Here you'll find the most important
1131 files, along with descriptions of what they mean and how to use them.
1133 acct
1134 ----
1136 The file contains three values; highwater, lowwater, and frequency.
1138 It exists only when BSD-style process accounting is enabled. These values
1139 control its behavior. If the free space on the file system where the log lives
1140 goes below lowwater percentage, accounting suspends. If it goes above
1141 highwater percentage, accounting resumes. Frequency determines how often you
1142 check the amount of free space (value is in seconds). Default settings are: 4,
1143 2, and 30. That is, suspend accounting if there is less than 2 percent free;
1144 resume it if we have a value of 3 or more percent; consider information about
1145 the amount of free space valid for 30 seconds
1147 ctrl-alt-del
1148 ------------
1150 When the value in this file is 0, ctrl-alt-del is trapped and sent to the init
1151 program to handle a graceful restart. However, when the value is greater that
1152 zero, Linux's reaction to this key combination will be an immediate reboot,
1153 without syncing its dirty buffers.
1155 [NOTE]
1156 When a program (like dosemu) has the keyboard in raw mode, the
1157 ctrl-alt-del is intercepted by the program before it ever reaches the
1158 kernel tty layer, and it is up to the program to decide what to do with
1159 it.
1161 domainname and hostname
1162 -----------------------
1164 These files can be controlled to set the NIS domainname and hostname of your
1165 box. For the classic darkstar.frop.org a simple:
1167 # echo "darkstar" > /proc/sys/kernel/hostname
1168 # echo "frop.org" > /proc/sys/kernel/domainname
1171 would suffice to set your hostname and NIS domainname.
1173 osrelease, ostype and version
1174 -----------------------------
1176 The names make it pretty obvious what these fields contain:
1178 > cat /proc/sys/kernel/osrelease
1179 2.2.12
1181 > cat /proc/sys/kernel/ostype
1182 Linux
1184 > cat /proc/sys/kernel/version
1185 #4 Fri Oct 1 12:41:14 PDT 1999
1188 The files osrelease and ostype should be clear enough. Version needs a little
1189 more clarification. The #4 means that this is the 4th kernel built from this
1190 source base and the date after it indicates the time the kernel was built. The
1191 only way to tune these values is to rebuild the kernel.
1193 panic
1194 -----
1196 The value in this file represents the number of seconds the kernel waits
1197 before rebooting on a panic. When you use the software watchdog, the
1198 recommended setting is 60. If set to 0, the auto reboot after a kernel panic
1199 is disabled, which is the default setting.
1201 printk
1202 ------
1204 The four values in printk denote
1205 * console_loglevel,
1206 * default_message_loglevel,
1207 * minimum_console_loglevel and
1208 * default_console_loglevel
1209 respectively.
1211 These values influence printk() behavior when printing or logging error
1212 messages, which come from inside the kernel. See syslog(2) for more
1213 information on the different log levels.
1215 console_loglevel
1216 ----------------
1218 Messages with a higher priority than this will be printed to the console.
1220 default_message_level
1221 ---------------------
1223 Messages without an explicit priority will be printed with this priority.
1225 minimum_console_loglevel
1226 ------------------------
1228 Minimum (highest) value to which the console_loglevel can be set.
1230 default_console_loglevel
1231 ------------------------
1233 Default value for console_loglevel.
1235 sg-big-buff
1236 -----------
1238 This file shows the size of the generic SCSI (sg) buffer. At this point, you
1239 can't tune it yet, but you can change it at compile time by editing
1240 include/scsi/sg.h and changing the value of SG_BIG_BUFF.
1242 If you use a scanner with SANE (Scanner Access Now Easy) you might want to set
1243 this to a higher value. Refer to the SANE documentation on this issue.
1245 modprobe
1246 --------
1248 The location where the modprobe binary is located. The kernel uses this
1249 program to load modules on demand.
1251 unknown_nmi_panic
1252 -----------------
1254 The value in this file affects behavior of handling NMI. When the value is
1255 non-zero, unknown NMI is trapped and then panic occurs. At that time, kernel
1256 debugging information is displayed on console.
1258 NMI switch that most IA32 servers have fires unknown NMI up, for example.
1259 If a system hangs up, try pressing the NMI switch.
1261 nmi_watchdog
1262 ------------
1264 Enables/Disables the NMI watchdog on x86 systems. When the value is non-zero
1265 the NMI watchdog is enabled and will continuously test all online cpus to
1266 determine whether or not they are still functioning properly.
1268 Because the NMI watchdog shares registers with oprofile, by disabling the NMI
1269 watchdog, oprofile may have more registers to utilize.
1271 maps_protect
1272 ------------
1274 Enables/Disables the protection of the per-process proc entries "maps" and
1275 "smaps". When enabled, the contents of these files are visible only to
1276 readers that are allowed to ptrace() the given process.
1279 2.4 /proc/sys/vm - The virtual memory subsystem
1280 -----------------------------------------------
1282 The files in this directory can be used to tune the operation of the virtual
1283 memory (VM) subsystem of the Linux kernel.
1285 vfs_cache_pressure
1286 ------------------
1288 Controls the tendency of the kernel to reclaim the memory which is used for
1289 caching of directory and inode objects.
1291 At the default value of vfs_cache_pressure=100 the kernel will attempt to
1292 reclaim dentries and inodes at a "fair" rate with respect to pagecache and
1293 swapcache reclaim. Decreasing vfs_cache_pressure causes the kernel to prefer
1294 to retain dentry and inode caches. Increasing vfs_cache_pressure beyond 100
1295 causes the kernel to prefer to reclaim dentries and inodes.
1297 dirty_background_ratio
1298 ----------------------
1300 Contains, as a percentage of total system memory, the number of pages at which
1301 the pdflush background writeback daemon will start writing out dirty data.
1303 dirty_ratio
1304 -----------------
1306 Contains, as a percentage of total system memory, the number of pages at which
1307 a process which is generating disk writes will itself start writing out dirty
1308 data.
1310 dirty_writeback_centisecs
1311 -------------------------
1313 The pdflush writeback daemons will periodically wake up and write `old' data
1314 out to disk. This tunable expresses the interval between those wakeups, in
1315 100'ths of a second.
1317 Setting this to zero disables periodic writeback altogether.
1319 dirty_expire_centisecs
1320 ----------------------
1322 This tunable is used to define when dirty data is old enough to be eligible
1323 for writeout by the pdflush daemons. It is expressed in 100'ths of a second.
1324 Data which has been dirty in-memory for longer than this interval will be
1325 written out next time a pdflush daemon wakes up.
1327 highmem_is_dirtyable
1328 --------------------
1330 Only present if CONFIG_HIGHMEM is set.
1332 This defaults to 0 (false), meaning that the ratios set above are calculated
1333 as a percentage of lowmem only. This protects against excessive scanning
1334 in page reclaim, swapping and general VM distress.
1336 Setting this to 1 can be useful on 32 bit machines where you want to make
1337 random changes within an MMAPed file that is larger than your available
1338 lowmem without causing large quantities of random IO. Is is safe if the
1339 behavior of all programs running on the machine is known and memory will
1340 not be otherwise stressed.
1342 legacy_va_layout
1343 ----------------
1345 If non-zero, this sysctl disables the new 32-bit mmap mmap layout - the kernel
1346 will use the legacy (2.4) layout for all processes.
1348 lowmem_reserve_ratio
1349 ---------------------
1351 For some specialised workloads on highmem machines it is dangerous for
1352 the kernel to allow process memory to be allocated from the "lowmem"
1353 zone. This is because that memory could then be pinned via the mlock()
1354 system call, or by unavailability of swapspace.
1356 And on large highmem machines this lack of reclaimable lowmem memory
1357 can be fatal.
1359 So the Linux page allocator has a mechanism which prevents allocations
1360 which _could_ use highmem from using too much lowmem. This means that
1361 a certain amount of lowmem is defended from the possibility of being
1362 captured into pinned user memory.
1364 (The same argument applies to the old 16 megabyte ISA DMA region. This
1365 mechanism will also defend that region from allocations which could use
1366 highmem or lowmem).
1368 The `lowmem_reserve_ratio' tunable determines how aggressive the kernel is
1369 in defending these lower zones.
1371 If you have a machine which uses highmem or ISA DMA and your
1372 applications are using mlock(), or if you are running with no swap then
1373 you probably should change the lowmem_reserve_ratio setting.
1375 The lowmem_reserve_ratio is an array. You can see them by reading this file.
1376 -
1377 % cat /proc/sys/vm/lowmem_reserve_ratio
1378 256 256 32
1379 -
1380 Note: # of this elements is one fewer than number of zones. Because the highest
1381 zone's value is not necessary for following calculation.
1383 But, these values are not used directly. The kernel calculates # of protection
1384 pages for each zones from them. These are shown as array of protection pages
1385 in /proc/zoneinfo like followings. (This is an example of x86-64 box).
1386 Each zone has an array of protection pages like this.
1388 -
1389 Node 0, zone DMA
1390 pages free 1355
1391 min 3
1392 low 3
1393 high 4
1394 :
1395 :
1396 numa_other 0
1397 protection: (0, 2004, 2004, 2004)
1398 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1399 pagesets
1400 cpu: 0 pcp: 0
1401 :
1402 -
1403 These protections are added to score to judge whether this zone should be used
1404 for page allocation or should be reclaimed.
1406 In this example, if normal pages (index=2) are required to this DMA zone and
1407 pages_high is used for watermark, the kernel judges this zone should not be
1408 used because pages_free(1355) is smaller than watermark + protection[2]
1409 (4 + 2004 = 2008). If this protection value is 0, this zone would be used for
1410 normal page requirement. If requirement is DMA zone(index=0), protection[0]
1411 (=0) is used.
1413 zone[i]'s protection[j] is calculated by following exprssion.
1415 (i < j):
1416 zone[i]->protection[j]
1417 = (total sums of present_pages from zone[i+1] to zone[j] on the node)
1418 / lowmem_reserve_ratio[i];
1419 (i = j):
1420 (should not be protected. = 0;
1421 (i > j):
1422 (not necessary, but looks 0)
1424 The default values of lowmem_reserve_ratio[i] are
1425 256 (if zone[i] means DMA or DMA32 zone)
1426 32 (others).
1427 As above expression, they are reciprocal number of ratio.
1428 256 means 1/256. # of protection pages becomes about "0.39%" of total present
1429 pages of higher zones on the node.
1431 If you would like to protect more pages, smaller values are effective.
1432 The minimum value is 1 (1/1 -> 100%).
1434 page-cluster
1435 ------------
1437 page-cluster controls the number of pages which are written to swap in
1438 a single attempt. The swap I/O size.
1440 It is a logarithmic value - setting it to zero means "1 page", setting
1441 it to 1 means "2 pages", setting it to 2 means "4 pages", etc.
1443 The default value is three (eight pages at a time). There may be some
1444 small benefits in tuning this to a different value if your workload is
1445 swap-intensive.
1447 overcommit_memory
1448 -----------------
1450 Controls overcommit of system memory, possibly allowing processes
1451 to allocate (but not use) more memory than is actually available.
1454 0 - Heuristic overcommit handling. Obvious overcommits of
1455 address space are refused. Used for a typical system. It
1456 ensures a seriously wild allocation fails while allowing
1457 overcommit to reduce swap usage. root is allowed to
1458 allocate slightly more memory in this mode. This is the
1459 default.
1461 1 - Always overcommit. Appropriate for some scientific
1462 applications.
1464 2 - Don't overcommit. The total address space commit
1465 for the system is not permitted to exceed swap plus a
1466 configurable percentage (default is 50) of physical RAM.
1467 Depending on the percentage you use, in most situations
1468 this means a process will not be killed while attempting
1469 to use already-allocated memory but will receive errors
1470 on memory allocation as appropriate.
1472 overcommit_ratio
1473 ----------------
1475 Percentage of physical memory size to include in overcommit calculations
1476 (see above.)
1478 Memory allocation limit = swapspace + physmem * (overcommit_ratio / 100)
1480 swapspace = total size of all swap areas
1481 physmem = size of physical memory in system
1483 nr_hugepages and hugetlb_shm_group
1484 ----------------------------------
1486 nr_hugepages configures number of hugetlb page reserved for the system.
1488 hugetlb_shm_group contains group id that is allowed to create SysV shared
1489 memory segment using hugetlb page.
1491 hugepages_treat_as_movable
1492 --------------------------
1494 This parameter is only useful when kernelcore= is specified at boot time to
1495 create ZONE_MOVABLE for pages that may be reclaimed or migrated. Huge pages
1496 are not movable so are not normally allocated from ZONE_MOVABLE. A non-zero
1497 value written to hugepages_treat_as_movable allows huge pages to be allocated
1498 from ZONE_MOVABLE.
1500 Once enabled, the ZONE_MOVABLE is treated as an area of memory the huge
1501 pages pool can easily grow or shrink within. Assuming that applications are
1502 not running that mlock() a lot of memory, it is likely the huge pages pool
1503 can grow to the size of ZONE_MOVABLE by repeatedly entering the desired value
1504 into nr_hugepages and triggering page reclaim.
1506 laptop_mode
1507 -----------
1509 laptop_mode is a knob that controls "laptop mode". All the things that are
1510 controlled by this knob are discussed in Documentation/laptops/laptop-mode.txt.
1512 block_dump
1513 ----------
1515 block_dump enables block I/O debugging when set to a nonzero value. More
1516 information on block I/O debugging is in Documentation/laptops/laptop-mode.txt.
1518 swap_token_timeout
1519 ------------------
1521 This file contains valid hold time of swap out protection token. The Linux
1522 VM has token based thrashing control mechanism and uses the token to prevent
1523 unnecessary page faults in thrashing situation. The unit of the value is
1524 second. The value would be useful to tune thrashing behavior.
1526 drop_caches
1527 -----------
1529 Writing to this will cause the kernel to drop clean caches, dentries and
1530 inodes from memory, causing that memory to become free.
1532 To free pagecache:
1533 echo 1 > /proc/sys/vm/drop_caches
1534 To free dentries and inodes:
1535 echo 2 > /proc/sys/vm/drop_caches
1536 To free pagecache, dentries and inodes:
1537 echo 3 > /proc/sys/vm/drop_caches
1539 As this is a non-destructive operation and dirty objects are not freeable, the
1540 user should run `sync' first.
1543 2.5 /proc/sys/dev - Device specific parameters
1544 ----------------------------------------------
1546 Currently there is only support for CDROM drives, and for those, there is only
1547 one read-only file containing information about the CD-ROM drives attached to
1548 the system:
1550 >cat /proc/sys/dev/cdrom/info
1551 CD-ROM information, Id: cdrom.c 2.55 1999/04/25
1553 drive name: sr0 hdb
1554 drive speed: 32 40
1555 drive # of slots: 1 0
1556 Can close tray: 1 1
1557 Can open tray: 1 1
1558 Can lock tray: 1 1
1559 Can change speed: 1 1
1560 Can select disk: 0 1
1561 Can read multisession: 1 1
1562 Can read MCN: 1 1
1563 Reports media changed: 1 1
1564 Can play audio: 1 1
1567 You see two drives, sr0 and hdb, along with a list of their features.
1569 2.6 /proc/sys/sunrpc - Remote procedure calls
1570 ---------------------------------------------
1572 This directory contains four files, which enable or disable debugging for the
1573 RPC functions NFS, NFS-daemon, RPC and NLM. The default values are 0. They can
1574 be set to one to turn debugging on. (The default value is 0 for each)
1576 2.7 /proc/sys/net - Networking stuff
1577 ------------------------------------
1579 The interface to the networking parts of the kernel is located in
1580 /proc/sys/net. Table 2-3 shows all possible subdirectories. You may see only
1581 some of them, depending on your kernel's configuration.
1584 Table 2-3: Subdirectories in /proc/sys/net
1585 ..............................................................................
1586 Directory Content Directory Content
1587 core General parameter appletalk Appletalk protocol
1588 unix Unix domain sockets netrom NET/ROM
1589 802 E802 protocol ax25 AX25
1590 ethernet Ethernet protocol rose X.25 PLP layer
1591 ipv4 IP version 4 x25 X.25 protocol
1592 ipx IPX token-ring IBM token ring
1593 bridge Bridging decnet DEC net
1594 ipv6 IP version 6
1595 ..............................................................................
1597 We will concentrate on IP networking here. Since AX15, X.25, and DEC Net are
1598 only minor players in the Linux world, we'll skip them in this chapter. You'll
1599 find some short info on Appletalk and IPX further on in this chapter. Review
1600 the online documentation and the kernel source to get a detailed view of the
1601 parameters for those protocols. In this section we'll discuss the
1602 subdirectories printed in bold letters in the table above. As default values
1603 are suitable for most needs, there is no need to change these values.
1605 /proc/sys/net/core - Network core options
1606 -----------------------------------------
1608 rmem_default
1609 ------------
1611 The default setting of the socket receive buffer in bytes.
1613 rmem_max
1614 --------
1616 The maximum receive socket buffer size in bytes.
1618 wmem_default
1619 ------------
1621 The default setting (in bytes) of the socket send buffer.
1623 wmem_max
1624 --------
1626 The maximum send socket buffer size in bytes.
1628 message_burst and message_cost
1629 ------------------------------
1631 These parameters are used to limit the warning messages written to the kernel
1632 log from the networking code. They enforce a rate limit to make a
1633 denial-of-service attack impossible. A higher message_cost factor, results in
1634 fewer messages that will be written. Message_burst controls when messages will
1635 be dropped. The default settings limit warning messages to one every five
1636 seconds.
1638 warnings
1639 --------
1641 This controls console messages from the networking stack that can occur because
1642 of problems on the network like duplicate address or bad checksums. Normally,
1643 this should be enabled, but if the problem persists the messages can be
1644 disabled.
1647 netdev_max_backlog
1648 ------------------
1650 Maximum number of packets, queued on the INPUT side, when the interface
1651 receives packets faster than kernel can process them.
1653 optmem_max
1654 ----------
1656 Maximum ancillary buffer size allowed per socket. Ancillary data is a sequence
1657 of struct cmsghdr structures with appended data.
1659 /proc/sys/net/unix - Parameters for Unix domain sockets
1660 -------------------------------------------------------
1662 There are only two files in this subdirectory. They control the delays for
1663 deleting and destroying socket descriptors.
1665 2.8 /proc/sys/net/ipv4 - IPV4 settings
1666 --------------------------------------
1668 IP version 4 is still the most used protocol in Unix networking. It will be
1669 replaced by IP version 6 in the next couple of years, but for the moment it's
1670 the de facto standard for the internet and is used in most networking
1671 environments around the world. Because of the importance of this protocol,
1672 we'll have a deeper look into the subtree controlling the behavior of the IPv4
1673 subsystem of the Linux kernel.
1675 Let's start with the entries in /proc/sys/net/ipv4.
1677 ICMP settings
1678 -------------
1680 icmp_echo_ignore_all and icmp_echo_ignore_broadcasts
1681 ----------------------------------------------------
1683 Turn on (1) or off (0), if the kernel should ignore all ICMP ECHO requests, or
1684 just those to broadcast and multicast addresses.
1686 Please note that if you accept ICMP echo requests with a broadcast/multi\-cast
1687 destination address your network may be used as an exploder for denial of
1688 service packet flooding attacks to other hosts.
1690 icmp_destunreach_rate, icmp_echoreply_rate, icmp_paramprob_rate and icmp_timeexeed_rate
1691 ---------------------------------------------------------------------------------------
1693 Sets limits for sending ICMP packets to specific targets. A value of zero
1694 disables all limiting. Any positive value sets the maximum package rate in
1695 hundredth of a second (on Intel systems).
1697 IP settings
1698 -----------
1700 ip_autoconfig
1701 -------------
1703 This file contains the number one if the host received its IP configuration by
1704 RARP, BOOTP, DHCP or a similar mechanism. Otherwise it is zero.
1706 ip_default_ttl
1707 --------------
1709 TTL (Time To Live) for IPv4 interfaces. This is simply the maximum number of
1710 hops a packet may travel.
1712 ip_dynaddr
1713 ----------
1715 Enable dynamic socket address rewriting on interface address change. This is
1716 useful for dialup interface with changing IP addresses.
1718 ip_forward
1719 ----------
1721 Enable or disable forwarding of IP packages between interfaces. Changing this
1722 value resets all other parameters to their default values. They differ if the
1723 kernel is configured as host or router.
1725 ip_local_port_range
1726 -------------------
1728 Range of ports used by TCP and UDP to choose the local port. Contains two
1729 numbers, the first number is the lowest port, the second number the highest
1730 local port. Default is 1024-4999. Should be changed to 32768-61000 for
1731 high-usage systems.
1733 ip_no_pmtu_disc
1734 ---------------
1736 Global switch to turn path MTU discovery off. It can also be set on a per
1737 socket basis by the applications or on a per route basis.
1739 ip_masq_debug
1740 -------------
1742 Enable/disable debugging of IP masquerading.
1744 IP fragmentation settings
1745 -------------------------
1747 ipfrag_high_trash and ipfrag_low_trash
1748 --------------------------------------
1750 Maximum memory used to reassemble IP fragments. When ipfrag_high_thresh bytes
1751 of memory is allocated for this purpose, the fragment handler will toss
1752 packets until ipfrag_low_thresh is reached.
1754 ipfrag_time
1755 -----------
1757 Time in seconds to keep an IP fragment in memory.
1759 TCP settings
1760 ------------
1762 tcp_ecn
1763 -------
1765 This file controls the use of the ECN bit in the IPv4 headers. This is a new
1766 feature about Explicit Congestion Notification, but some routers and firewalls
1767 block traffic that has this bit set, so it could be necessary to echo 0 to
1768 /proc/sys/net/ipv4/tcp_ecn if you want to talk to these sites. For more info
1769 you could read RFC2481.
1771 tcp_retrans_collapse
1772 --------------------
1774 Bug-to-bug compatibility with some broken printers. On retransmit, try to send
1775 larger packets to work around bugs in certain TCP stacks. Can be turned off by
1776 setting it to zero.
1778 tcp_keepalive_probes
1779 --------------------
1781 Number of keep alive probes TCP sends out, until it decides that the
1782 connection is broken.
1784 tcp_keepalive_time
1785 ------------------
1787 How often TCP sends out keep alive messages, when keep alive is enabled. The
1788 default is 2 hours.
1790 tcp_syn_retries
1791 ---------------
1793 Number of times initial SYNs for a TCP connection attempt will be
1794 retransmitted. Should not be higher than 255. This is only the timeout for
1795 outgoing connections, for incoming connections the number of retransmits is
1796 defined by tcp_retries1.
1798 tcp_sack
1799 --------
1801 Enable select acknowledgments after RFC2018.
1803 tcp_timestamps
1804 --------------
1806 Enable timestamps as defined in RFC1323.
1808 tcp_stdurg
1809 ----------
1811 Enable the strict RFC793 interpretation of the TCP urgent pointer field. The
1812 default is to use the BSD compatible interpretation of the urgent pointer
1813 pointing to the first byte after the urgent data. The RFC793 interpretation is
1814 to have it point to the last byte of urgent data. Enabling this option may
1815 lead to interoperability problems. Disabled by default.
1817 tcp_syncookies
1818 --------------
1820 Only valid when the kernel was compiled with CONFIG_SYNCOOKIES. Send out
1821 syncookies when the syn backlog queue of a socket overflows. This is to ward
1822 off the common 'syn flood attack'. Disabled by default.
1824 Note that the concept of a socket backlog is abandoned. This means the peer
1825 may not receive reliable error messages from an over loaded server with
1826 syncookies enabled.
1828 tcp_window_scaling
1829 ------------------
1831 Enable window scaling as defined in RFC1323.
1833 tcp_fin_timeout
1834 ---------------
1836 The length of time in seconds it takes to receive a final FIN before the
1837 socket is always closed. This is strictly a violation of the TCP
1838 specification, but required to prevent denial-of-service attacks.
1840 tcp_max_ka_probes
1841 -----------------
1843 Indicates how many keep alive probes are sent per slow timer run. Should not
1844 be set too high to prevent bursts.
1846 tcp_max_syn_backlog
1847 -------------------
1849 Length of the per socket backlog queue. Since Linux 2.2 the backlog specified
1850 in listen(2) only specifies the length of the backlog queue of already
1851 established sockets. When more connection requests arrive Linux starts to drop
1852 packets. When syncookies are enabled the packets are still answered and the
1853 maximum queue is effectively ignored.
1855 tcp_retries1
1856 ------------
1858 Defines how often an answer to a TCP connection request is retransmitted
1859 before giving up.
1861 tcp_retries2
1862 ------------
1864 Defines how often a TCP packet is retransmitted before giving up.
1866 Interface specific settings
1867 ---------------------------
1869 In the directory /proc/sys/net/ipv4/conf you'll find one subdirectory for each
1870 interface the system knows about and one directory calls all. Changes in the
1871 all subdirectory affect all interfaces, whereas changes in the other
1872 subdirectories affect only one interface. All directories have the same
1873 entries:
1875 accept_redirects
1876 ----------------
1878 This switch decides if the kernel accepts ICMP redirect messages or not. The
1879 default is 'yes' if the kernel is configured for a regular host and 'no' for a
1880 router configuration.
1882 accept_source_route
1883 -------------------
1885 Should source routed packages be accepted or declined. The default is
1886 dependent on the kernel configuration. It's 'yes' for routers and 'no' for
1887 hosts.
1889 bootp_relay
1890 ~~~~~~~~~~~
1892 Accept packets with source address 0.b.c.d with destinations not to this host
1893 as local ones. It is supposed that a BOOTP relay daemon will catch and forward
1894 such packets.
1896 The default is 0, since this feature is not implemented yet (kernel version
1897 2.2.12).
1899 forwarding
1900 ----------
1902 Enable or disable IP forwarding on this interface.
1904 log_martians
1905 ------------
1907 Log packets with source addresses with no known route to kernel log.
1909 mc_forwarding
1910 -------------
1912 Do multicast routing. The kernel needs to be compiled with CONFIG_MROUTE and a
1913 multicast routing daemon is required.
1915 proxy_arp
1916 ---------
1918 Does (1) or does not (0) perform proxy ARP.
1920 rp_filter
1921 ---------
1923 Integer value determines if a source validation should be made. 1 means yes, 0
1924 means no. Disabled by default, but local/broadcast address spoofing is always
1925 on.
1927 If you set this to 1 on a router that is the only connection for a network to
1928 the net, it will prevent spoofing attacks against your internal networks
1929 (external addresses can still be spoofed), without the need for additional
1930 firewall rules.
1932 secure_redirects
1933 ----------------
1935 Accept ICMP redirect messages only for gateways, listed in default gateway
1936 list. Enabled by default.
1938 shared_media
1939 ------------
1941 If it is not set the kernel does not assume that different subnets on this
1942 device can communicate directly. Default setting is 'yes'.
1944 send_redirects
1945 --------------
1947 Determines whether to send ICMP redirects to other hosts.
1949 Routing settings
1950 ----------------
1952 The directory /proc/sys/net/ipv4/route contains several file to control
1953 routing issues.
1955 error_burst and error_cost
1956 --------------------------
1958 These parameters are used to limit how many ICMP destination unreachable to
1959 send from the host in question. ICMP destination unreachable messages are
1960 sent when we cannot reach the next hop while trying to transmit a packet.
1961 It will also print some error messages to kernel logs if someone is ignoring
1962 our ICMP redirects. The higher the error_cost factor is, the fewer
1963 destination unreachable and error messages will be let through. Error_burst
1964 controls when destination unreachable messages and error messages will be
1965 dropped. The default settings limit warning messages to five every second.
1967 flush
1968 -----
1970 Writing to this file results in a flush of the routing cache.
1972 gc_elasticity, gc_interval, gc_min_interval_ms, gc_timeout, gc_thresh
1973 ---------------------------------------------------------------------
1975 Values to control the frequency and behavior of the garbage collection
1976 algorithm for the routing cache. gc_min_interval is deprecated and replaced
1977 by gc_min_interval_ms.
1980 max_size
1981 --------
1983 Maximum size of the routing cache. Old entries will be purged once the cache
1984 reached has this size.
1986 redirect_load, redirect_number
1987 ------------------------------
1989 Factors which determine if more ICPM redirects should be sent to a specific
1990 host. No redirects will be sent once the load limit or the maximum number of
1991 redirects has been reached.
1993 redirect_silence
1994 ----------------
1996 Timeout for redirects. After this period redirects will be sent again, even if
1997 this has been stopped, because the load or number limit has been reached.
1999 Network Neighbor handling
2000 -------------------------
2002 Settings about how to handle connections with direct neighbors (nodes attached
2003 to the same link) can be found in the directory /proc/sys/net/ipv4/neigh.
2005 As we saw it in the conf directory, there is a default subdirectory which
2006 holds the default values, and one directory for each interface. The contents
2007 of the directories are identical, with the single exception that the default
2008 settings contain additional options to set garbage collection parameters.
2010 In the interface directories you'll find the following entries:
2012 base_reachable_time, base_reachable_time_ms
2013 -------------------------------------------
2015 A base value used for computing the random reachable time value as specified
2016 in RFC2461.
2018 Expression of base_reachable_time, which is deprecated, is in seconds.
2019 Expression of base_reachable_time_ms is in milliseconds.
2021 retrans_time, retrans_time_ms
2022 -----------------------------
2024 The time between retransmitted Neighbor Solicitation messages.
2025 Used for address resolution and to determine if a neighbor is
2026 unreachable.
2028 Expression of retrans_time, which is deprecated, is in 1/100 seconds (for
2029 IPv4) or in jiffies (for IPv6).
2030 Expression of retrans_time_ms is in milliseconds.
2032 unres_qlen
2033 ----------
2035 Maximum queue length for a pending arp request - the number of packets which
2036 are accepted from other layers while the ARP address is still resolved.
2038 anycast_delay
2039 -------------
2041 Maximum for random delay of answers to neighbor solicitation messages in
2042 jiffies (1/100 sec). Not yet implemented (Linux does not have anycast support
2043 yet).
2045 ucast_solicit
2046 -------------
2048 Maximum number of retries for unicast solicitation.
2050 mcast_solicit
2051 -------------
2053 Maximum number of retries for multicast solicitation.
2055 delay_first_probe_time
2056 ----------------------
2058 Delay for the first time probe if the neighbor is reachable. (see
2059 gc_stale_time)
2061 locktime
2062 --------
2064 An ARP/neighbor entry is only replaced with a new one if the old is at least
2065 locktime old. This prevents ARP cache thrashing.
2067 proxy_delay
2068 -----------
2070 Maximum time (real time is random [0..proxytime]) before answering to an ARP
2071 request for which we have an proxy ARP entry. In some cases, this is used to
2072 prevent network flooding.
2074 proxy_qlen
2075 ----------
2077 Maximum queue length of the delayed proxy arp timer. (see proxy_delay).
2079 app_solicit
2080 ----------
2082 Determines the number of requests to send to the user level ARP daemon. Use 0
2083 to turn off.
2085 gc_stale_time
2086 -------------
2088 Determines how often to check for stale ARP entries. After an ARP entry is
2089 stale it will be resolved again (which is useful when an IP address migrates
2090 to another machine). When ucast_solicit is greater than 0 it first tries to
2091 send an ARP packet directly to the known host When that fails and
2092 mcast_solicit is greater than 0, an ARP request is broadcasted.
2094 2.9 Appletalk
2095 -------------
2097 The /proc/sys/net/appletalk directory holds the Appletalk configuration data
2098 when Appletalk is loaded. The configurable parameters are:
2100 aarp-expiry-time
2101 ----------------
2103 The amount of time we keep an ARP entry before expiring it. Used to age out
2104 old hosts.
2106 aarp-resolve-time
2107 -----------------
2109 The amount of time we will spend trying to resolve an Appletalk address.
2111 aarp-retransmit-limit
2112 ---------------------
2114 The number of times we will retransmit a query before giving up.
2116 aarp-tick-time
2117 --------------
2119 Controls the rate at which expires are checked.
2121 The directory /proc/net/appletalk holds the list of active Appletalk sockets
2122 on a machine.
2124 The fields indicate the DDP type, the local address (in network:node format)
2125 the remote address, the size of the transmit pending queue, the size of the
2126 received queue (bytes waiting for applications to read) the state and the uid
2127 owning the socket.
2129 /proc/net/atalk_iface lists all the interfaces configured for appletalk.It
2130 shows the name of the interface, its Appletalk address, the network range on
2131 that address (or network number for phase 1 networks), and the status of the
2132 interface.
2134 /proc/net/atalk_route lists each known network route. It lists the target
2135 (network) that the route leads to, the router (may be directly connected), the
2136 route flags, and the device the route is using.
2138 2.10 IPX
2139 --------
2141 The IPX protocol has no tunable values in proc/sys/net.
2143 The IPX protocol does, however, provide proc/net/ipx. This lists each IPX
2144 socket giving the local and remote addresses in Novell format (that is
2145 network:node:port). In accordance with the strange Novell tradition,
2146 everything but the port is in hex. Not_Connected is displayed for sockets that
2147 are not tied to a specific remote address. The Tx and Rx queue sizes indicate
2148 the number of bytes pending for transmission and reception. The state
2149 indicates the state the socket is in and the uid is the owning uid of the
2150 socket.
2152 The /proc/net/ipx_interface file lists all IPX interfaces. For each interface
2153 it gives the network number, the node number, and indicates if the network is
2154 the primary network. It also indicates which device it is bound to (or
2155 Internal for internal networks) and the Frame Type if appropriate. Linux
2156 supports 802.3, 802.2, 802.2 SNAP and DIX (Blue Book) ethernet framing for
2157 IPX.
2159 The /proc/net/ipx_route table holds a list of IPX routes. For each route it
2160 gives the destination network, the router node (or Directly) and the network
2161 address of the router (or Connected) for internal networks.
2163 2.11 /proc/sys/fs/mqueue - POSIX message queues filesystem
2164 ----------------------------------------------------------
2166 The "mqueue" filesystem provides the necessary kernel features to enable the
2167 creation of a user space library that implements the POSIX message queues
2168 API (as noted by the MSG tag in the POSIX 1003.1-2001 version of the System
2169 Interfaces specification.)
2171 The "mqueue" filesystem contains values for determining/setting the amount of
2172 resources used by the file system.
2174 /proc/sys/fs/mqueue/queues_max is a read/write file for setting/getting the
2175 maximum number of message queues allowed on the system.
2177 /proc/sys/fs/mqueue/msg_max is a read/write file for setting/getting the
2178 maximum number of messages in a queue value. In fact it is the limiting value
2179 for another (user) limit which is set in mq_open invocation. This attribute of
2180 a queue must be less or equal then msg_max.
2182 /proc/sys/fs/mqueue/msgsize_max is a read/write file for setting/getting the
2183 maximum message size value (it is every message queue's attribute set during
2184 its creation).
2186 2.12 /proc/<pid>/oom_adj - Adjust the oom-killer score
2187 ------------------------------------------------------
2189 This file can be used to adjust the score used to select which processes
2190 should be killed in an out-of-memory situation. Giving it a high score will
2191 increase the likelihood of this process being killed by the oom-killer. Valid
2192 values are in the range -16 to +15, plus the special value -17, which disables
2193 oom-killing altogether for this process.
2195 2.13 /proc/<pid>/oom_score - Display current oom-killer score
2196 -------------------------------------------------------------
2198 ------------------------------------------------------------------------------
2199 This file can be used to check the current score used by the oom-killer is for
2200 any given <pid>. Use it together with /proc/<pid>/oom_adj to tune which
2201 process should be killed in an out-of-memory situation.
2203 ------------------------------------------------------------------------------
2204 Summary
2205 ------------------------------------------------------------------------------
2206 Certain aspects of kernel behavior can be modified at runtime, without the
2207 need to recompile the kernel, or even to reboot the system. The files in the
2208 /proc/sys tree can not only be read, but also modified. You can use the echo
2209 command to write value into these files, thereby changing the default settings
2210 of the kernel.
2211 ------------------------------------------------------------------------------
2213 2.14 /proc/<pid>/io - Display the IO accounting fields
2214 -------------------------------------------------------
2216 This file contains IO statistics for each running process
2218 Example
2219 -------
2221 test:/tmp # dd if=/dev/zero of=/tmp/test.dat &
2222 [1] 3828
2224 test:/tmp # cat /proc/3828/io
2225 rchar: 323934931
2226 wchar: 323929600
2227 syscr: 632687
2228 syscw: 632675
2229 read_bytes: 0
2230 write_bytes: 323932160
2231 cancelled_write_bytes: 0
2234 Description
2235 -----------
2237 rchar
2238 -----
2240 I/O counter: chars read
2241 The number of bytes which this task has caused to be read from storage. This
2242 is simply the sum of bytes which this process passed to read() and pread().
2243 It includes things like tty IO and it is unaffected by whether or not actual
2244 physical disk IO was required (the read might have been satisfied from
2245 pagecache)
2248 wchar
2249 -----
2251 I/O counter: chars written
2252 The number of bytes which this task has caused, or shall cause to be written
2253 to disk. Similar caveats apply here as with rchar.
2256 syscr
2257 -----
2259 I/O counter: read syscalls
2260 Attempt to count the number of read I/O operations, i.e. syscalls like read()
2261 and pread().
2264 syscw
2265 -----
2267 I/O counter: write syscalls
2268 Attempt to count the number of write I/O operations, i.e. syscalls like
2269 write() and pwrite().
2272 read_bytes
2273 ----------
2275 I/O counter: bytes read
2276 Attempt to count the number of bytes which this process really did cause to
2277 be fetched from the storage layer. Done at the submit_bio() level, so it is
2278 accurate for block-backed filesystems. <please add status regarding NFS and
2279 CIFS at a later time>
2282 write_bytes
2283 -----------
2285 I/O counter: bytes written
2286 Attempt to count the number of bytes which this process caused to be sent to
2287 the storage layer. This is done at page-dirtying time.
2290 cancelled_write_bytes
2291 ---------------------
2293 The big inaccuracy here is truncate. If a process writes 1MB to a file and
2294 then deletes the file, it will in fact perform no writeout. But it will have
2295 been accounted as having caused 1MB of write.
2296 In other words: The number of bytes which this process caused to not happen,
2297 by truncating pagecache. A task can cause "negative" IO too. If this task
2298 truncates some dirty pagecache, some IO which another task has been accounted
2299 for (in it's write_bytes) will not be happening. We _could_ just subtract that
2300 from the truncating task's write_bytes, but there is information loss in doing
2301 that.
2304 Note
2305 ----
2307 At its current implementation state, this is a bit racy on 32-bit machines: if
2308 process A reads process B's /proc/pid/io while process B is updating one of
2309 those 64-bit counters, process A could see an intermediate result.
2312 More information about this can be found within the taskstats documentation in
2313 Documentation/accounting.
2315 2.15 /proc/<pid>/coredump_filter - Core dump filtering settings
2316 ---------------------------------------------------------------
2317 When a process is dumped, all anonymous memory is written to a core file as
2318 long as the size of the core file isn't limited. But sometimes we don't want
2319 to dump some memory segments, for example, huge shared memory. Conversely,
2320 sometimes we want to save file-backed memory segments into a core file, not
2321 only the individual files.
2323 /proc/<pid>/coredump_filter allows you to customize which memory segments
2324 will be dumped when the <pid> process is dumped. coredump_filter is a bitmask
2325 of memory types. If a bit of the bitmask is set, memory segments of the
2326 corresponding memory type are dumped, otherwise they are not dumped.
2328 The following 4 memory types are supported:
2329 - (bit 0) anonymous private memory
2330 - (bit 1) anonymous shared memory
2331 - (bit 2) file-backed private memory
2332 - (bit 3) file-backed shared memory
2334 Note that MMIO pages such as frame buffer are never dumped and vDSO pages
2335 are always dumped regardless of the bitmask status.
2337 Default value of coredump_filter is 0x3; this means all anonymous memory
2338 segments are dumped.
2340 If you don't want to dump all shared memory segments attached to pid 1234,
2341 write 1 to the process's proc file.
2343 $ echo 0x1 > /proc/1234/coredump_filter
2345 When a new process is created, the process inherits the bitmask status from its
2346 parent. It is useful to set up coredump_filter before the program runs.
2347 For example:
2349 $ echo 0x7 > /proc/self/coredump_filter
2350 $ ./some_program
2352 2.16 /proc/<pid>/mountinfo - Information about mounts
2353 --------------------------------------------------------
2355 This file contains lines of the form:
2357 36 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue
2358 (1)(2)(3) (4) (5) (6) (7) (8) (9) (10) (11)
2360 (1) mount ID: unique identifier of the mount (may be reused after umount)
2361 (2) parent ID: ID of parent (or of self for the top of the mount tree)
2362 (3) major:minor: value of st_dev for files on filesystem
2363 (4) root: root of the mount within the filesystem
2364 (5) mount point: mount point relative to the process's root
2365 (6) mount options: per mount options
2366 (7) optional fields: zero or more fields of the form "tag[:value]"
2367 (8) separator: marks the end of the optional fields
2368 (9) filesystem type: name of filesystem of the form "type[.subtype]"
2369 (10) mount source: filesystem specific information or "none"
2370 (11) super options: per super block options
2372 Parsers should ignore all unrecognised optional fields. Currently the
2373 possible optional fields are:
2375 shared:X mount is shared in peer group X
2376 master:X mount is slave to peer group X
2377 propagate_from:X mount is slave and receives propagation from peer group X (*)
2378 unbindable mount is unbindable
2380 (*) X is the closest dominant peer group under the process's root. If
2381 X is the immediate master of the mount, or if there's no dominant peer
2382 group under the same root, then only the "master:X" field is present
2383 and not the "propagate_from:X" field.
2385 For more information on mount propagation see:
2387 Documentation/filesystems/sharedsubtree.txt
2389 ------------------------------------------------------------------------------