1 ------------------------------------------------------------------------------
2 T H E /proc F I L E S Y S T E M
3 ------------------------------------------------------------------------------
4 /proc/sys Terrehon Bowden <terrehon@pacbell.net> October 7 1999
5 Bodo Bauer <bb@ricochet.net>
6
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 ------------------------------------------------------------------------------
12
13 Table of Contents
14 -----------------
15
16 0 Preface
17 0.1 Introduction/Credits
18 0.2 Legal Stuff
19
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
29 2 Modifying System Parameters
30 2.1 /proc/sys/fs - File system data
31 2.2 /proc/sys/fs/binfmt_misc - Miscellaneous binary formats
32 2.3 /proc/sys/kernel - general kernel parameters
33 2.4 /proc/sys/vm - The virtual memory subsystem
34 2.5 /proc/sys/dev - Device specific parameters
35 2.6 /proc/sys/sunrpc - Remote procedure calls
36 2.7 /proc/sys/net - Networking stuff
37 2.8 /proc/sys/net/ipv4 - IPV4 settings
38 2.9 Appletalk
39 2.10 IPX
40
41 ------------------------------------------------------------------------------
42 Preface
43 ------------------------------------------------------------------------------
44
45 0.1 Introduction/Credits
46 ------------------------
47
48 This documentation is part of a soon (or so we hope) to be released book on
49 the SuSE Linux distribution. As there is no complete documentation for the
50 /proc file system and we've used many freely available sources to write these
51 chapters, it seems only fair to give the work back to the Linux community.
52 This work is based on the 2.2.* kernel version and the upcomming 2.4.*. I'm
53 afraid it's still far from complete, but we hope it will be useful. As far as
54 we know, it is the first 'all-in-one' document about the /proc file system. It
55 is focused on the Intel x86 hardware, so if you are looking for PPC, ARM,
56 SPARC, APX, etc., features, you probably won't find what you are looking for.
57 It also only covers IPv4 networking, not IPv6 nor other protocols - sorry. But
58 additions and patches are welcome and will be added to this document if you
59 mail them to Bodo.
60
61 We'd like to thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of
62 other people for help compiling this documentation. We'd also like to extend a
63 special thank you to Andi Kleen for documentation, which we relied on heavily
64 to create this document, as well as the additional information he provided.
65 Thanks to everybody else who contributed source or docs to the Linux kernel
66 and helped create a great piece of software... :)
67
68 If you have any comments, corrections or additions, please don't hesitate to
69 contact Bodo Bauer at bb@ricochet.net. We'll be happy to add them to this
70 document.
71
72 The latest version of this document is available online at
73 http://skaro.nightcrawler.com/~bb/Docs/Proc as HTML version.
74
75 If the above direction does not works for you, ypu could try the kernel
76 mailing list at linux-kernel@vger.kernel.org and/or try to reach me at
77 comandante@zaralinux.com.
78
79 0.2 Legal Stuff
80 ---------------
81
82 We don't guarantee the correctness of this document, and if you come to us
83 complaining about how you screwed up your system because of incorrect
84 documentation, we won't feel responsible...
85
86 ------------------------------------------------------------------------------
87 CHAPTER 1: COLLECTING SYSTEM INFORMATION
88 ------------------------------------------------------------------------------
89
90 ------------------------------------------------------------------------------
91 In This Chapter
92 ------------------------------------------------------------------------------
93 * Investigating the properties of the pseudo file system /proc and its
94 ability to provide information on the running Linux system
95 * Examining /proc's structure
96 * Uncovering various information about the kernel and the processes running
97 on the system
98 ------------------------------------------------------------------------------
99
100
101 The proc file system acts as an interface to internal data structures in the
102 kernel. It can be used to obtain information about the system and to change
103 certain kernel parameters at runtime (sysctl).
104
105 First, we'll take a look at the read-only parts of /proc. In Chapter 2, we
106 show you how you can use /proc/sys to change settings.
107
108 1.1 Process-Specific Subdirectories
109 -----------------------------------
110
111 The directory /proc contains (among other things) one subdirectory for each
112 process running on the system, which is named after the process ID (PID).
113
114 The link self points to the process reading the file system. Each process
115 subdirectory has the entries listed in Table 1-1.
116
117
118 Table 1-1: Process specific entries in /proc
119 ..............................................................................
120 File Content
121 cmdline Command line arguments
122 cpu Current and last cpu in wich it was executed (2.4)(smp)
123 cwd Link to the current working directory
124 environ Values of environment variables
125 exe Link to the executable of this process
126 fd Directory, which contains all file descriptors
127 maps Memory maps to executables and library files (2.4)
128 mem Memory held by this process
129 root Link to the root directory of this process
130 stat Process status
131 statm Process memory status information
132 status Process status in human readable form
133 ..............................................................................
134
135 For example, to get the status information of a process, all you have to do is
136 read the file /proc/PID/status:
137
138 >cat /proc/self/status
139 Name: cat
140 State: R (running)
141 Pid: 5452
142 PPid: 743
143 TracerPid: 0 (2.4)
144 Uid: 501 501 501 501
145 Gid: 100 100 100 100
146 Groups: 100 14 16
147 VmSize: 1112 kB
148 VmLck: 0 kB
149 VmRSS: 348 kB
150 VmData: 24 kB
151 VmStk: 12 kB
152 VmExe: 8 kB
153 VmLib: 1044 kB
154 SigPnd: 0000000000000000
155 SigBlk: 0000000000000000
156 SigIgn: 0000000000000000
157 SigCgt: 0000000000000000
158 CapInh: 00000000fffffeff
159 CapPrm: 0000000000000000
160 CapEff: 0000000000000000
161
162
163 This shows you nearly the same information you would get if you viewed it with
164 the ps command. In fact, ps uses the proc file system to obtain its
165 information. The statm file contains more detailed information about the
166 process memory usage. Its seven fields are explained in Table 1-2.
167
168
169 Table 1-2: Contents of the statm files
170 ..............................................................................
171 File Content
172 size total program size
173 resident size of memory portions
174 shared number of pages that are shared
175 trs number of pages that are 'code'
176 drs number of pages of data/stack
177 lrs number of pages of library
178 dt number of dirty pages
179 ..............................................................................
180
181 1.2 Kernel data
182 ---------------
183
184 Similar to the process entries, the kernel data files give information about
185 the running kernel. The files used to obtain this information are contained in
186 /proc and are listed in Table 1-3. Not all of these will be present in your
187 system. It depends on the kernel configuration and the loaded modules, which
188 files are there, and which are missing.
189
190 Table 1-3: Kernel info in /proc
191 ..............................................................................
192 File Content
193 apm Advanced power management info
194 bus Directory containing bus specific information
195 cmdline Kernel command line
196 cpuinfo Info about the CPU
197 devices Available devices (block and character)
198 dma Used DMS channels
199 filesystems Supported filesystems
200 driver Various drivers grouped here, currently rtc (2.4)
201 execdomains Execdomains, related to security (2.4)
202 fb Frame Buffer devices (2.4)
203 fs File system parameters, currently nfs/exports (2.4)
204 ide Directory containing info about the IDE subsystem
205 interrupts Interrupt usage
206 iomem Memory map (2.4)
207 ioports I/O port usage
208 irq Masks for irq to cpu affinity (2.4)(smp?)
209 isapnp ISA PnP (Plug&Play) Info (2.4)
210 kcore Kernel core image (can be ELF or A.OUT(deprecated in 2.4))
211 kmsg Kernel messages
212 ksyms Kernel symbol table
213 loadavg Load average of last 1, 5 & 15 minutes
214 locks Kernel locks
215 meminfo Memory info
216 misc Miscellaneous
217 modules List of loaded modules
218 mounts Mounted filesystems
219 net Networking info (see text)
220 partitions Table of partitions known to the system
221 pci Depreciated info of PCI bus (new way -> /proc/bus/pci/,
222 decoupled by lspci (2.4)
223 rtc Real time clock
224 scsi SCSI info (see text)
225 slabinfo Slab pool info
226 stat Overall statistics
227 swaps Swap space utilization
228 sys See chapter 2
229 sysvipc Info of SysVIPC Resources (msg, sem, shm) (2.4)
230 tty Info of tty drivers
231 uptime System uptime
232 version Kernel version
233 video bttv info of video resources (2.4)
234 ..............................................................................
235
236 You can, for example, check which interrupts are currently in use and what
237 they are used for by looking in the file /proc/interrupts:
238
239 > cat /proc/interrupts
240 CPU0
241 0: 8728810 XT-PIC timer
242 1: 895 XT-PIC keyboard
243 2: 0 XT-PIC cascade
244 3: 531695 XT-PIC aha152x
245 4: 2014133 XT-PIC serial
246 5: 44401 XT-PIC pcnet_cs
247 8: 2 XT-PIC rtc
248 11: 8 XT-PIC i82365
249 12: 182918 XT-PIC PS/2 Mouse
250 13: 1 XT-PIC fpu
251 14: 1232265 XT-PIC ide0
252 15: 7 XT-PIC ide1
253 NMI: 0
254
255 In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the
256 output of a SMP machine):
257
258 > cat /proc/interrupts
259
260 CPU0 CPU1
261 0: 1243498 1214548 IO-APIC-edge timer
262 1: 8949 8958 IO-APIC-edge keyboard
263 2: 0 0 XT-PIC cascade
264 5: 11286 10161 IO-APIC-edge soundblaster
265 8: 1 0 IO-APIC-edge rtc
266 9: 27422 27407 IO-APIC-edge 3c503
267 12: 113645 113873 IO-APIC-edge PS/2 Mouse
268 13: 0 0 XT-PIC fpu
269 14: 22491 24012 IO-APIC-edge ide0
270 15: 2183 2415 IO-APIC-edge ide1
271 17: 30564 30414 IO-APIC-level eth0
272 18: 177 164 IO-APIC-level bttv
273 NMI: 2457961 2457959
274 LOC: 2457882 2457881
275 ERR: 2155
276
277 NMI is incremented in this case because every timer interrupt generates a NMI
278 (Non Maskable Interrupt) which is used by the NMI Watchdog to detect lookups.
279
280 LOC is the local interrupt counter of the internal APIC of every CPU.
281
282 ERR is incremented in the case of errors in the IO-APIC bus (the bus that
283 connects the CPUs in a SMP system. This means that an error has been detected,
284 the IO-APIC automatically retry the transmision, so it should not be a big
285 problem, but you should read the SMP-FAQ.
286
287 In this context it could be interesting to note the new irq directory in 2.4.
288 It could be used to set IRQ to CPU affinity, this means that you can "hook" an
289 IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
290 irq subdir is one subdir for each IRQ, and one file; prof_cpu_mask
291
292 For example
293 > ls /proc/irq/
294 0 10 12 14 16 18 2 4 6 8 prof_cpu_mask
295 1 11 13 15 17 19 3 5 7 9
296 > ls /proc/irq/0/
297 smp_affinity
298
299 The contents of the prof_cpu_mask file and each smp_affinity file for each IRQ
300 is the same by default:
301
302 > cat /proc/irq/0/smp_affinity
303 ffffffff
304
305 It's a bitmask, in wich you can specify wich CPUs can handle the IRQ, you can
306 set it by doing:
307
308 > echo 1 > /proc/irq/prof_cpu_mask
309
310 This means that only the first CPU will handle the IRQ, but you can also echo 5
311 wich means that only the first and fourth CPU can handle the IRQ.
312
313 The way IRQs are routed is handled by the IO-APIC, and it's Round Robin
314 between all the CPUs which are allowed to handle it. As usual the kernel has
315 more info than you and does a better job than you, so the defaults are the
316 best choice for almost everyone.
317
318 There are three more important subdirectories in /proc: net, scsi, and sys.
319 The general rule is that the contents, or even the existence of these
320 directories, depend on your kernel configuration. If SCSI is not enabled, the
321 directory scsi may not exist. The same is true with the net, which is there
322 only when networking support is present in the running kernel.
323
324 The slabinfo file gives information about memory usage at the slab level.
325 Linux uses slab pools for memory management above page level in version 2.2.
326 Commonly used objects have their own slab pool (such as network buffers,
327 directory cache, and so on).
328
329 1.3 IDE devices in /proc/ide
330 ----------------------------
331
332 The subdirectory /proc/ide contains information about all IDE devices of which
333 the kernel is aware. There is one subdirectory for each IDE controller, the
334 file drivers and a link for each IDE device, pointing to the device directory
335 in the controller specific subtree.
336
337 The file drivers contains general information about the drivers used for the
338 IDE devices:
339
340 > cat /proc/ide/drivers
341 ide-cdrom version 4.53
342 ide-disk version 1.08
343
344
345 More detailed information can be found in the controller specific
346 subdirectories. These are named ide0, ide1 and so on. Each of these
347 directories contains the files shown in table 1-4.
348
349
350 Table 1-4: IDE controller info in /proc/ide/ide?
351 ..............................................................................
352 File Content
353 channel IDE channel (0 or 1)
354 config Configuration (only for PCI/IDE bridge)
355 mate Mate name
356 model Type/Chipset of IDE controller
357 ..............................................................................
358
359 Each device connected to a controller has a separate subdirectory in the
360 controllers directory. The files listed in table 1-5 are contained in these
361 directories.
362
363
364 Table 1-5: IDE device information
365 ..............................................................................
366 File Content
367 cache The cache
368 capacity Capacity of the medium (in 512Byte blocks)
369 driver driver and version
370 geometry physical and logical geometry
371 identify device identify block
372 media media type
373 model device identifier
374 settings device setup
375 smart_thresholds IDE disk management thresholds
376 smart_values IDE disk management values
377 ..............................................................................
378
379 The most interesting file is settings. This file contains a nice overview of
380 the drive parameters:
381
382 # cat /proc/ide/ide0/hda/settings
383 name value min max mode
384 ---- ----- --- --- ----
385 bios_cyl 526 0 65535 rw
386 bios_head 255 0 255 rw
387 bios_sect 63 0 63 rw
388 breada_readahead 4 0 127 rw
389 bswap 0 0 1 r
390 file_readahead 72 0 2097151 rw
391 io_32bit 0 0 3 rw
392 keepsettings 0 0 1 rw
393 max_kb_per_request 122 1 127 rw
394 multcount 0 0 8 rw
395 nice1 1 0 1 rw
396 nowerr 0 0 1 rw
397 pio_mode write-only 0 255 w
398 slow 0 0 1 rw
399 unmaskirq 0 0 1 rw
400 using_dma 0 0 1 rw
401
402
403 1.4 Networking info in /proc/net
404 --------------------------------
405
406 The subdirectory /proc/net follows the usual pattern. Table 1-6 shows the
407 additional values you get for IP version 6 if you configure the kernel to
408 support this. Table 1-7 lists the files and their meaning.
409
410
411 Table 1-6: IPv6 info in /proc/net
412 ..............................................................................
413 File Content
414 udp6 UDP sockets (IPv6)
415 tcp6 TCP sockets (IPv6)
416 raw6 Raw device statistics (IPv6)
417 igmp6 IP multicast addresses, which this host joined (IPv6)
418 if_inet6 List of IPv6 interface addresses
419 ipv6_route Kernel routing table for IPv6
420 rt6_stats Global IPv6 routing tables statistics
421 sockstat6 Socket statistics (IPv6)
422 snmp6 Snmp data (IPv6)
423 ..............................................................................
424
425
426 Table 1-7: Network info in /proc/net
427 ..............................................................................
428 File Content
429 arp Kernel ARP table
430 dev network devices with statistics
431 dev_mcast the Layer2 multicast groups a device is listening too
432 (interface index, label, number of references, number of bound
433 addresses).
434 dev_stat network device status
435 ip_fwchains Firewall chain linkage
436 ip_fwnames Firewall chain names
437 ip_masq Directory containing the masquerading tables
438 ip_masquerade Major masquerading table
439 netstat Network statistics
440 raw raw device statistics
441 route Kernel routing table
442 rpc Directory containing rpc info
443 rt_cache Routing cache
444 snmp SNMP data
445 sockstat Socket statistics
446 tcp TCP sockets
447 tr_rif Token ring RIF routing table
448 udp UDP sockets
449 unix UNIX domain sockets
450 wireless Wireless interface data (Wavelan etc)
451 igmp IP multicast addresses, which this host joined
452 psched Global packet scheduler parameters.
453 netlink List of PF_NETLINK sockets
454 ip_mr_vifs List of multicast virtual interfaces
455 ip_mr_cache List of multicast routing cache
456 ..............................................................................
457
458 You can use this information to see which network devices are available in
459 your system and how much traffic was routed over those devices:
460
461 > cat /proc/net/dev
462 Inter-|Receive |[...
463 face |bytes packets errs drop fifo frame compressed multicast|[...
464 lo: 908188 5596 0 0 0 0 0 0 [...
465 ppp0:15475140 20721 410 0 0 410 0 0 [...
466 eth0: 614530 7085 0 0 0 0 0 1 [...
467
468 ...] Transmit
469 ...] bytes packets errs drop fifo colls carrier compressed
470 ...] 908188 5596 0 0 0 0 0 0
471 ...] 1375103 17405 0 0 0 0 0 0
472 ...] 1703981 5535 0 0 0 3 0 0
473
474
475 1.5 SCSI info
476 -------------
477
478 If you have a SCSI host adapter in your system, you'll find a subdirectory
479 named after the driver for this adapter in /proc/scsi. You'll also see a list
480 of all recognized SCSI devices in /proc/scsi:
481
482 >cat /proc/scsi/scsi
483 Attached devices:
484 Host: scsi0 Channel: 00 Id: 00 Lun: 00
485 Vendor: IBM Model: DGHS09U Rev: 03E0
486 Type: Direct-Access ANSI SCSI revision: 03
487 Host: scsi0 Channel: 00 Id: 06 Lun: 00
488 Vendor: PIONEER Model: CD-ROM DR-U06S Rev: 1.04
489 Type: CD-ROM ANSI SCSI revision: 02
490
491
492 The directory named after the driver has one file for each adapter found in
493 the system. These files contain information about the controller, including
494 the used IRQ and the IO address range. The amount of information shown is
495 dependent on the adapter you use. The example shows the output for an Adaptec
496 AHA-2940 SCSI adapter:
497
498 > cat /proc/scsi/aic7xxx/0
499
500 Adaptec AIC7xxx driver version: 5.1.19/3.2.4
501 Compile Options:
502 TCQ Enabled By Default : Disabled
503 AIC7XXX_PROC_STATS : Disabled
504 AIC7XXX_RESET_DELAY : 5
505 Adapter Configuration:
506 SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter
507 Ultra Wide Controller
508 PCI MMAPed I/O Base: 0xeb001000
509 Adapter SEEPROM Config: SEEPROM found and used.
510 Adaptec SCSI BIOS: Enabled
511 IRQ: 10
512 SCBs: Active 0, Max Active 2,
513 Allocated 15, HW 16, Page 255
514 Interrupts: 160328
515 BIOS Control Word: 0x18b6
516 Adapter Control Word: 0x005b
517 Extended Translation: Enabled
518 Disconnect Enable Flags: 0xffff
519 Ultra Enable Flags: 0x0001
520 Tag Queue Enable Flags: 0x0000
521 Ordered Queue Tag Flags: 0x0000
522 Default Tag Queue Depth: 8
523 Tagged Queue By Device array for aic7xxx host instance 0:
524 {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255}
525 Actual queue depth per device for aic7xxx host instance 0:
526 {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1}
527 Statistics:
528 (scsi0:0:0:0)
529 Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8
530 Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0)
531 Total transfers 160151 (74577 reads and 85574 writes)
532 (scsi0:0:6:0)
533 Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15
534 Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0)
535 Total transfers 0 (0 reads and 0 writes)
536
537
538 1.6 Parallel port info in /proc/parport
539 ---------------------------------------
540
541 The directory /proc/parport contains information about the parallel ports of
542 your system. It has one subdirectory for each port, named after the port
543 number (0,1,2,...).
544
545 These directories contain the four files shown in Table 1-8.
546
547
548 Table 1-8: Files in /proc/parport
549 ..............................................................................
550 File Content
551 autoprobe Any IEEE-1284 device ID information that has been acquired.
552 devices list of the device drivers using that port. A + will appear by the
553 name of the device currently using the port (it might not appear
554 against any).
555 hardware Parallel port's base address, IRQ line and DMA channel.
556 irq IRQ that parport is using for that port. This is in a separate
557 file to allow you to alter it by writing a new value in (IRQ
558 number or none).
559 ..............................................................................
560
561 1.7 TTY info in /proc/tty
562 -------------------------
563
564 Information about the available and actually used tty's can be found in the
565 directory /proc/tty.You'll find entries for drivers and line disciplines in
566 this directory, as shown in Table 1-9.
567
568
569 Table 1-9: Files in /proc/tty
570 ..............................................................................
571 File Content
572 drivers list of drivers and their usage
573 ldiscs registered line disciplines
574 driver/serial usage statistic and status of single tty lines
575 ..............................................................................
576
577 To see which tty's are currently in use, you can simply look into the file
578 /proc/tty/drivers:
579
580 > cat /proc/tty/drivers
581 pty_slave /dev/pts 136 0-255 pty:slave
582 pty_master /dev/ptm 128 0-255 pty:master
583 pty_slave /dev/ttyp 3 0-255 pty:slave
584 pty_master /dev/pty 2 0-255 pty:master
585 serial /dev/cua 5 64-67 serial:callout
586 serial /dev/ttyS 4 64-67 serial
587 /dev/tty0 /dev/tty0 4 0 system:vtmaster
588 /dev/ptmx /dev/ptmx 5 2 system
589 /dev/console /dev/console 5 1 system:console
590 /dev/tty /dev/tty 5 0 system:/dev/tty
591 unknown /dev/tty 4 1-63 console
592
593
594 ------------------------------------------------------------------------------
595 Summary
596 ------------------------------------------------------------------------------
597 The /proc file system serves information about the running system. It not only
598 allows access to process data but also allows you to request the kernel status
599 by reading files in the hierarchy.
600
601 The directory structure of /proc reflects the types of information and makes
602 it easy, if not obvious, where to look for specific data.
603 ------------------------------------------------------------------------------
604
605 ------------------------------------------------------------------------------
606 CHAPTER 2: MODIFYING SYSTEM PARAMETERS
607 ------------------------------------------------------------------------------
608
609 ------------------------------------------------------------------------------
610 In This Chapter
611 ------------------------------------------------------------------------------
612 * Modifying kernel parameters by writing into files found in /proc/sys
613 * Exploring the files which modify certain parameters
614 * Review of the /proc/sys file tree
615 ------------------------------------------------------------------------------
616
617
618 A very interesting part of /proc is the directory /proc/sys. This is not only
619 a source of information, it also allows you to change parameters within the
620 kernel. Be very careful when attempting this. You can optimize your system,
621 but you can also cause it to crash. Never alter kernel parameters on a
622 production system. Set up a development machine and test to make sure that
623 everything works the way you want it to. You may have no alternative but to
624 reboot the machine once an error has been made.
625
626 To change a value, simply echo the new value into the file. An example is
627 given below in the section on the file system data. You need to be root to do
628 this. You can create your own boot script to perform this every time your
629 system boots.
630
631 The files in /proc/sys can be used to fine tune and monitor miscellaneous and
632 general things in the operation of the Linux kernel. Since some of the files
633 can inadvertently disrupt your system, it is advisable to read both
634 documentation and source before actually making adjustments. In any case, be
635 very careful when writing to any of these files. The entries in /proc may
636 change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt
637 review the kernel documentation in the directory /usr/src/linux/Documentation.
638 This chapter is heavily based on the documentation included in the pre 2.2
639 kernels, and became part of it in version 2.2.1 of the Linux kernel.
640
641 2.1 /proc/sys/fs - File system data
642 -----------------------------------
643
644 This subdirectory contains specific file system, file handle, inode, dentry
645 and quota information.
646
647 Currently, these files are in /proc/sys/fs:
648
649 dentry-state
650 ------------
651
652 Status of the directory cache. Since directory entries are dynamically
653 allocated and deallocated, this file indicates the current status. It holds
654 six values, in which the last two are not used and are always zero. The others
655 are listed in table 2-1.
656
657
658 Table 2-1: Status files of the directory cache
659 ..............................................................................
660 File Content
661 nr_dentry Almost always zero
662 nr_unused Number of unused cache entries
663 age_limit
664 in seconds after the entry may be reclaimed, when memory is short
665 want_pages internally
666 ..............................................................................
667
668 dquot-nr and dquot-max
669 ----------------------
670
671 The file dquot-max shows the maximum number of cached disk quota entries.
672
673 The file dquot-nr shows the number of allocated disk quota entries and the
674 number of free disk quota entries.
675
676 If the number of available cached disk quotas is very low and you have a large
677 number of simultaneous system users, you might want to raise the limit.
678
679 file-nr and file-max
680 --------------------
681
682 The kernel allocates file handles dynamically, but doesn't free them again at
683 this time.
684
685 The value in file-max denotes the maximum number of file handles that the
686 Linux kernel will allocate. When you get a lot of error messages about running
687 out of file handles, you might want to raise this limit. The default value is
688 4096. To change it, just write the new number into the file:
689
690 # cat /proc/sys/fs/file-max
691 4096
692 # echo 8192 > /proc/sys/fs/file-max
693 # cat /proc/sys/fs/file-max
694 8192
695
696
697 This method of revision is useful for all customizable parameters of the
698 kernel - simply echo the new value to the corresponding file.
699
700 The three values in file-nr denote the number of allocated file handles, the
701 number of used file handles, and the maximum number of file handles. When the
702 allocated file handles come close to the maximum, but the number of actually
703 used ones is far behind, you've encountered a peak in your usage of file
704 handles and you don't need to increase the maximum.
705
706 inode-state, inode-nr and inode-max
707 -----------------------------------
708
709 As with file handles, the kernel allocates the inode structures dynamically,
710 but can't free them yet.
711
712 The value in inode-max denotes the maximum number of inode handlers. This
713 value should be 3 to 4 times larger than the value in file-max, since stdin,
714 stdout, and network sockets also need an inode struct to handle them. If you
715 regularly run out of inodes, you should increase this value.
716
717 The file inode-nr contains the first two items from inode-state, so we'll skip
718 to that file...
719
720 inode-state contains three actual numbers and four dummy values. The numbers
721 are nr_inodes, nr_free_inodes, and preshrink (in order of appearance).
722
723 nr_inodes
724 ~~~~~~~~~
725
726 Denotes the number of inodes the system has allocated. This can be slightly
727 more than inode-max because Linux allocates them one pageful at a time.
728
729 nr_free_inodes
730 --------------
731
732 Represents the number of free inodes and preshrink is nonzero when nr_inodes
733 is greater than inode-max and the system needs to prune the inode list instead
734 of allocating more.
735
736
737 super-nr and super-max
738 ----------------------
739
740 Again, super block structures are allocated by the kernel, but not freed. The
741 file super-max contains the maximum number of super block handlers, where
742 super-nr shows the number of currently allocated ones.
743
744 Every mounted file system needs a super block, so if you plan to mount lots of
745 file systems, you may want to increase these numbers.
746
747 2.2 /proc/sys/fs/binfmt_misc - Miscellaneous binary formats
748 -----------------------------------------------------------
749
750 Besides these files, there is the subdirectory /proc/sys/fs/binfmt_misc. This
751 handles the kernel support for miscellaneous binary formats.
752
753 Binfmt_misc provides the ability to register additional binary formats to the
754 Kernel without compiling an additional module/kernel. Therefore, binfmt_misc
755 needs to know magic numbers at the beginning or the filename extension of the
756 binary.
757
758 It works by maintaining a linked list of structs that contain a description of
759 a binary format, including a magic with size (or the filename extension),
760 offset and mask, and the interpreter name. On request it invokes the given
761 interpreter with the original program as argument, as binfmt_java and
762 binfmt_em86 and binfmt_mz do. Since binfmt_misc does not define any default
763 binary-formats, you have to register an additional binary-format.
764
765 There are two general files in binfmt_misc and one file per registered format.
766 The two general files are register and status.
767
768 Registering a new binary format
769 -------------------------------
770
771 To register a new binary format you have to issue the command
772
773 echo :name:type:offset:magic:mask:interpreter: > /proc/sys/fs/binfmt_misc/register
774
775
776
777 with appropriate name (the name for the /proc-dir entry), offset (defaults to
778 0, if omitted), magic, mask (which can be omitted, defaults to all 0xff) and
779 last but not least, the interpreter that is to be invoked (for example and
780 testing /bin/echo). Type can be M for usual magic matching or E for filename
781 extension matching (give extension in place of magic).
782
783 Check or reset the status of the binary format handler
784 ------------------------------------------------------
785
786 If you do a cat on the file /proc/sys/fs/binfmt_misc/status, you will get the
787 current status (enabled/disabled) of binfmt_misc. Change the status by echoing
788 0 (disables) or 1 (enables) or -1 (caution: this clears all previously
789 registered binary formats) to status. For example echo 0 > status to disable
790 binfmt_misc (temporarily).
791
792 Status of a single handler
793 --------------------------
794
795 Each registered handler has an entry in /proc/sys/fs/binfmt_misc. These files
796 perform the same function as status, but their scope is limited to the actual
797 binary format. By cating this file, you also receive all related information
798 about the interpreter/magic of the binfmt.
799
800 Example usage of binfmt_misc (emulate binfmt_java)
801 --------------------------------------------------
802
803 cd /proc/sys/fs/binfmt_misc
804 echo ':Java:M::\xca\xfe\xba\xbe::/usr/local/java/bin/javawrapper:' > register
805 echo ':HTML:E::html::/usr/local/java/bin/appletviewer:' > register
806 echo ':Applet:M::<!--applet::/usr/local/java/bin/appletviewer:' > register
807 echo ':DEXE:M::\x0eDEX::/usr/bin/dosexec:' > register
808
809
810 These four lines add support for Java executables and Java applets (like
811 binfmt_java, additionally recognizing the .html extension with no need to put
812 <!--applet> to every applet file). You have to install the JDK and the
813 shell-script /usr/local/java/bin/javawrapper too. It works around the
814 brokenness of the Java filename handling. To add a Java binary, just create a
815 link to the class-file somewhere in the path.
816
817 2.3 /proc/sys/kernel - general kernel parameters
818 ------------------------------------------------
819
820 This directory reflects general kernel behaviors. As I've said before, the
821 contents depend on your configuration. Here you'll find the most important
822 files, along with descriptions of what they mean and how to use them.
823
824 acct
825 ----
826
827 The file contains three values; highwater, lowwater, and frequency.
828
829 It exists only when BSD-style process accounting is enabled. These values
830 control its behavior. If the free space on the file system where the log lives
831 goes below lowwater percentage, accounting suspends. If it goes above
832 highwater percentage, accounting resumes. Frequency determines how often you
833 check the amount of free space (value is in seconds). Default settings are: 4,
834 2, and 30. That is, suspend accounting if there is less than 2 percent free;
835 resume it if we have a value of 3 or more percent; consider information about
836 the amount of free space valid for 30 seconds
837
838 ctrl-alt-del
839 ------------
840
841 When the value in this file is 0, ctrl-alt-del is trapped and sent to the init
842 program to handle a graceful restart. However, when the value is greater that
843 zero, Linux's reaction to this key combination will be an immediate reboot,
844 without syncing its dirty buffers.
845
846 [NOTE]
847 When a program (like dosemu) has the keyboard in raw mode, the
848 ctrl-alt-del is intercepted by the program before it ever reaches the
849 kernel tty layer, and it is up to the program to decide what to do with
850 it.
851
852 domainname and hostname
853 -----------------------
854
855 These files can be controlled to set the NIS domainname and hostname of your
856 box. For the classic darkstar.frop.org a simple:
857
858 # echo "darkstar" > /proc/sys/kernel/hostname
859 # echo "frop.org" > /proc/sys/kernel/domainname
860
861
862 would suffice to set your hostname and NIS domainname.
863
864 osrelease, ostype and version
865 -----------------------------
866
867 The names make it pretty obvious what these fields contain:
868
869 > cat /proc/sys/kernel/osrelease
870 2.2.12
871
872 > cat /proc/sys/kernel/ostype
873 Linux
874
875 > cat /proc/sys/kernel/version
876 #4 Fri Oct 1 12:41:14 PDT 1999
877
878
879 The files osrelease and ostype should be clear enough. Version needs a little
880 more clarification. The #4 means that this is the 4th kernel built from this
881 source base and the date after it indicates the time the kernel was built. The
882 only way to tune these values is to rebuild the kernel.
883
884 panic
885 -----
886
887 The value in this file represents the number of seconds the kernel waits
888 before rebooting on a panic. When you use the software watchdog, the
889 recommended setting is 60. If set to 0, the auto reboot after a kernel panic
890 is disabled, which is the default setting.
891
892 printk
893 ------
894
895 The four values in printk denote
896 * console_loglevel,
897 * default_message_loglevel,
898 * minimum_console_level and
899 * default_console_loglevel
900 respectively.
901
902 These values influence printk() behavior when printing or logging error
903 messages, which come from inside the kernel. See syslog(2) for more
904 information on the different log levels.
905
906 console_loglevel
907 ----------------
908
909 Messages with a higher priority than this will be printed to the console.
910
911 default_message_level
912 ---------------------
913
914 Messages without an explicit priority will be printed with this priority.
915
916 minimum_console_loglevel
917 ------------------------
918
919 Minimum (highest) value to which the console_loglevel can be set.
920
921 default_console_loglevel
922 ------------------------
923
924 Default value for console_loglevel.
925
926 sg-big-buff
927 -----------
928
929 This file shows the size of the generic SCSI (sg) buffer. At this point, you
930 can't tune it yet, but you can change it at compile time by editing
931 include/scsi/sg.h and changing the value of SG_BIG_BUFF.
932
933 If you use a scanner with SANE (Scanner Access Now Easy) you might want to set
934 this to a higher value. Refer to the SANE documentation on this issue.
935
936 modprobe
937 --------
938
939 The location where the modprobe binary is located. The kernel uses this
940 program to load modules on demand.
941
942 2.4 /proc/sys/vm - The virtual memory subsystem
943 -----------------------------------------------
944
945 The files in this directory can be used to tune the operation of the virtual
946 memory (VM) subsystem of the Linux kernel. In addition, one of the files
947 (bdflush) has some influence on disk usage.
948
949 bdflush
950 -------
951
952 This file controls the operation of the bdflush kernel daemon. It currently
953 contains nine integer values, six of which are actually used by the kernel.
954 They are listed in table 2-2.
955
956
957 Table 2-2: Parameters in /proc/sys/vm/bdflush
958 ..............................................................................
959 Value Meaning
960 nfract Percentage of buffer cache dirty to activate bdflush
961 ndirty Maximum number of dirty blocks to write out per wake-cycle
962 nrefill Number of clean buffers to try to obtain each time we call refill
963 nref_dirt buffer threshold for activating bdflush when trying to refill
964 buffers.
965 dummy Unused
966 age_buffer Time for normal buffer to age before we flush it
967 age_super Time for superblock to age before we flush it
968 dummy Unused
969 dummy Unused
970 ..............................................................................
971
972 nfract
973 ------
974
975 This parameter governs the maximum number of dirty buffers in the buffer
976 cache. Dirty means that the contents of the buffer still have to be written to
977 disk (as opposed to a clean buffer, which can just be forgotten about).
978 Setting this to a higher value means that Linux can delay disk writes for a
979 long time, but it also means that it will have to do a lot of I/O at once when
980 memory becomes short. A lower value will spread out disk I/O more evenly.
981
982 ndirty
983 ------
984
985 Ndirty gives the maximum number of dirty buffers that bdflush can write to the
986 disk at one time. A high value will mean delayed, bursty I/O, while a small
987 value can lead to memory shortage when bdflush isn't woken up often enough.
988
989 nrefill
990 -------
991
992 This is the number of buffers that bdflush will add to the list of free
993 buffers when refill_freelist() is called. It is necessary to allocate free
994 buffers beforehand, since the buffers are often different sizes than the
995 memory pages and some bookkeeping needs to be done beforehand. The higher the
996 number, the more memory will be wasted and the less often refill_freelist()
997 will need to run.
998
999 nref_dirt
1000 ---------
1001
1002 When refill_freelist() comes across more than nref_dirt dirty buffers, it will
1003 wake up bdflush.
1004
1005 age_buffer and age_super
1006 ------------------------
1007
1008 Finally, the age_buffer and age_super parameters govern the maximum time Linux
1009 waits before writing out a dirty buffer to disk. The value is expressed in
1010 jiffies (clockticks), the number of jiffies per second is 100. Age_buffer is
1011 the maximum age for data blocks, while age_super is for filesystems meta data.
1012
1013 buffermem
1014 ---------
1015
1016 The three values in this file control how much memory should be used for
1017 buffer memory. The percentage is calculated as a percentage of total system
1018 memory.
1019
1020 The values are:
1021
1022 min_percent
1023 -----------
1024
1025 This is the minimum percentage of memory that should be spent on buffer
1026 memory.
1027
1028 borrow_percent
1029 --------------
1030
1031 When Linux is short on memory, and the buffer cache uses more than it has been
1032 allotted, the memory management (MM) subsystem will prune the buffer cache
1033 more heavily than other memory to compensate.
1034
1035 max_percent
1036 -----------
1037
1038 This is the maximum amount of memory that can be used for buffer memory.
1039
1040 freepages
1041 ---------
1042
1043 This file contains three values: min, low and high:
1044
1045 min
1046 ---
1047 When the number of free pages in the system reaches this number, only the
1048 kernel can allocate more memory.
1049
1050 low
1051 ---
1052 If the number of free pages falls below this point, the kernel starts swapping
1053 aggressively.
1054
1055 high
1056 ----
1057 The kernel tries to keep up to this amount of memory free; if memory falls
1058 below this point, the kernel starts gently swapping in the hopes that it never
1059 has to do really aggressive swapping.
1060
1061 kswapd
1062 ------
1063
1064 Kswapd is the kernel swap out daemon. That is, kswapd is that piece of the
1065 kernel that frees memory when it gets fragmented or full. Since every system
1066 is different, you'll probably want some control over this piece of the system.
1067
1068 The file contains three numbers:
1069
1070 tries_base
1071 ----------
1072
1073 The maximum number of pages kswapd tries to free in one round is calculated
1074 from this number. Usually this number will be divided by 4 or 8 (see
1075 mm/vmscan.c), so it isn't as big as it looks.
1076
1077 When you need to increase the bandwidth to/from swap, you'll want to increase
1078 this number.
1079
1080 tries_min
1081 ---------
1082
1083 This is the minimum number of times kswapd tries to free a page each time it
1084 is called. Basically it's just there to make sure that kswapd frees some pages
1085 even when it's being called with minimum priority.
1086
1087 swap_cluster
1088 ------------
1089
1090 This is probably the greatest influence on system performance.
1091
1092 swap_cluster is the number of pages kswapd writes in one turn. You'll want
1093 this value to be large so that kswapd does its I/O in large chunks and the
1094 disk doesn't have to seek as often, but you don't want it to be too large
1095 since that would flood the request queue.
1096
1097 overcommit_memory
1098 -----------------
1099
1100 This file contains one value. The following algorithm is used to decide if
1101 there's enough memory: if the value of overcommit_memory is positive, then
1102 there's always enough memory. This is a useful feature, since programs often
1103 malloc() huge amounts of memory 'just in case', while they only use a small
1104 part of it. Leaving this value at 0 will lead to the failure of such a huge
1105 malloc(), when in fact the system has enough memory for the program to run.
1106
1107 On the other hand, enabling this feature can cause you to run out of memory
1108 and thrash the system to death, so large and/or important servers will want to
1109 set this value to 0.
1110
1111 pagecache
1112 ---------
1113
1114 This file does exactly the same job as buffermem, only this file controls the
1115 amount of memory allowed for memory mapping and generic caching of files.
1116
1117 You don't want the minimum level to be too low, otherwise your system might
1118 thrash when memory is tight or fragmentation is high.
1119
1120 pagetable_cache
1121 ---------------
1122
1123 The kernel keeps a number of page tables in a per-processor cache (this helps
1124 a lot on SMP systems). The cache size for each processor will be between the
1125 low and the high value.
1126
1127 On a low-memory, single CPU system, you can safely set these values to 0 so
1128 you don't waste memory. It is used on SMP systems so that the system can
1129 perform fast pagetable allocations without having to acquire the kernel memory
1130 lock.
1131
1132 For large systems, the settings are probably fine. For normal systems they
1133 won't hurt a bit. For small systems ( less than 16MB ram) it might be
1134 advantageous to set both values to 0.
1135
1136 swapctl
1137 -------
1138
1139 This file contains no less than 8 variables. All of these values are used by
1140 kswapd.
1141
1142 The first four variables
1143 * sc_max_page_age,
1144 * sc_page_advance,
1145 * sc_page_decline and
1146 * sc_page_initial_age
1147 are used to keep track of Linux's page aging. Page aging is a bookkeeping
1148 method to track which pages of memory are often used, and which pages can be
1149 swapped out without consequences.
1150
1151 When a page is swapped in, it starts at sc_page_initial_age (default 3) and
1152 when the page is scanned by kswapd, its age is adjusted according to the
1153 following scheme:
1154
1155 * If the page was used since the last time we scanned, its age is increased
1156 by sc_page_advance (default 3). Where the maximum value is given by
1157 sc_max_page_age (default 20).
1158 * Otherwise (meaning it wasn't used) its age is decreased by sc_page_decline
1159 (default 1).
1160
1161 When a page reaches age 0, it's ready to be swapped out.
1162
1163 The variables sc_age_cluster_fract, sc_age_cluster_min, sc_pageout_weight and
1164 sc_bufferout_weight, can be used to control kswapd's aggressiveness in
1165 swapping out pages.
1166
1167 Sc_age_cluster_fract is used to calculate how many pages from a process are to
1168 be scanned by kswapd. The formula used is
1169
1170 (sc_age_cluster_fract divided by 1024) times resident set size
1171
1172 So if you want kswapd to scan the whole process, sc_age_cluster_fract needs to
1173 have a value of 1024. The minimum number of pages kswapd will scan is
1174 represented by sc_age_cluster_min, which is done so that kswapd will also scan
1175 small processes.
1176
1177 The values of sc_pageout_weight and sc_bufferout_weight are used to control
1178 how many tries kswapd will make in order to swap out one page/buffer. These
1179 values can be used to fine-tune the ratio between user pages and buffer/cache
1180 memory. When you find that your Linux system is swapping out too many process
1181 pages in order to satisfy buffer memory demands, you may want to either
1182 increase sc_bufferout_weight, or decrease the value of sc_pageout_weight.
1183
1184 2.5 /proc/sys/dev - Device specific parameters
1185 ----------------------------------------------
1186
1187 Currently there is only support for CDROM drives, and for those, there is only
1188 one read-only file containing information about the CD-ROM drives attached to
1189 the system:
1190
1191 >cat /proc/sys/dev/cdrom/info
1192 CD-ROM information, Id: cdrom.c 2.55 1999/04/25
1193
1194 drive name: sr0 hdb
1195 drive speed: 32 40
1196 drive # of slots: 1 0
1197 Can close tray: 1 1
1198 Can open tray: 1 1
1199 Can lock tray: 1 1
1200 Can change speed: 1 1
1201 Can select disk: 0 1
1202 Can read multisession: 1 1
1203 Can read MCN: 1 1
1204 Reports media changed: 1 1
1205 Can play audio: 1 1
1206
1207
1208 You see two drives, sr0 and hdb, along with a list of their features.
1209
1210 2.6 /proc/sys/sunrpc - Remote procedure calls
1211 ---------------------------------------------
1212
1213 This directory contains four files, which enable or disable debugging for the
1214 RPC functions NFS, NFS-daemon, RPC and NLM. The default values are 0. They can
1215 be set to one to turn debugging on. (The default value is 0 for each)
1216
1217 2.7 /proc/sys/net - Networking stuff
1218 ------------------------------------
1219
1220 The interface to the networking parts of the kernel is located in
1221 /proc/sys/net. Table 2-3 shows all possible subdirectories. You may see only
1222 some of them, depending on your kernel's configuration.
1223
1224
1225 Table 2-3: Subdirectories in /proc/sys/net
1226 ..............................................................................
1227 Directory Content Directory Content
1228 core General parameter appletalk Appletalk protocol
1229 unix Unix domain sockets netrom NET/ROM
1230 802 E802 protocol ax25 AX25
1231 ethernet Ethernet protocol rose X.25 PLP layer
1232 ipv4 IP version 4 x25 X.25 protocol
1233 ipx IPX token-ring IBM token ring
1234 bridge Bridging decnet DEC net
1235 ipv6 IP version 6
1236 ..............................................................................
1237
1238 We will concentrate on IP networking here. Since AX15, X.25, and DEC Net are
1239 only minor players in the Linux world, we'll skip them in this chapter. You'll
1240 find some short info on Appletalk and IPX further on in this chapter. Review
1241 the online documentation and the kernel source to get a detailed view of the
1242 parameters for those protocols. In this section we'll discuss the
1243 subdirectories printed in bold letters in the table above. As default values
1244 are suitable for most needs, there is no need to change these values.
1245
1246 /proc/sys/net/core - Network core options
1247 -----------------------------------------
1248
1249 rmem_default
1250 ------------
1251
1252 The default setting of the socket receive buffer in bytes.
1253
1254 rmem_max
1255 --------
1256
1257 The maximum receive socket buffer size in bytes.
1258
1259 wmem_default
1260 ------------
1261
1262 The default setting (in bytes) of the socket send buffer.
1263
1264 wmem_max
1265 --------
1266
1267 The maximum send socket buffer size in bytes.
1268
1269 message_burst and message_cost
1270 ------------------------------
1271
1272 These parameters are used to limit the warning messages written to the kernel
1273 log from the networking code. They enforce a rate limit to make a
1274 denial-of-service attack impossible. A higher message_cost factor, results in
1275 fewer messages that will be written. Message_burst controls when messages will
1276 be dropped. The default settings limit warning messages to one every five
1277 seconds.
1278
1279 netdev_max_backlog
1280 ------------------
1281
1282 Maximum number of packets, queued on the INPUT side, when the interface
1283 receives packets faster than kernel can process them.
1284
1285 optmem_max
1286 ----------
1287
1288 Maximum ancillary buffer size allowed per socket. Ancillary data is a sequence
1289 of struct cmsghdr structures with appended data.
1290
1291 /proc/sys/net/unix - Parameters for Unix domain sockets
1292 -------------------------------------------------------
1293
1294 There are only two files in this subdirectory. They control the delays for
1295 deleting and destroying socket descriptors.
1296
1297 2.8 /proc/sys/net/ipv4 - IPV4 settings
1298 --------------------------------------
1299
1300 IP version 4 is still the most used protocol in Unix networking. It will be
1301 replaced by IP version 6 in the next couple of years, but for the moment it's
1302 the de facto standard for the internet and is used in most networking
1303 environments around the world. Because of the importance of this protocol,
1304 we'll have a deeper look into the subtree controlling the behavior of the IPv4
1305 subsystem of the Linux kernel.
1306
1307 Let's start with the entries in /proc/sys/net/ipv4.
1308
1309 ICMP settings
1310 -------------
1311
1312 icmp_echo_ignore_all and icmp_echo_ignore_broadcasts
1313 ----------------------------------------------------
1314
1315 Turn on (1) or off (0), if the kernel should ignore all ICMP ECHO requests, or
1316 just those to broadcast and multicast addresses.
1317
1318 Please note that if you accept ICMP echo requests with a broadcast/multi\-cast
1319 destination address your network may be used as an exploder for denial of
1320 service packet flooding attacks to other hosts.
1321
1322 icmp_destunreach_rate, icmp_echoreply_rate, icmp_paramprob_rate and icmp_timeexeed_rate
1323 ---------------------------------------------------------------------------------------
1324
1325 Sets limits for sending ICMP packets to specific targets. A value of zero
1326 disables all limiting. Any positive value sets the maximum package rate in
1327 hundredth of a second (on Intel systems).
1328
1329 IP settings
1330 -----------
1331
1332 ip_autoconfig
1333 -------------
1334
1335 This file contains the number one if the host received its IP configuration by
1336 RARP, BOOTP, DHCP or a similar mechanism. Otherwise it is zero.
1337
1338 ip_default_ttl
1339 --------------
1340
1341 TTL (Time To Live) for IPv4 interfaces. This is simply the maximum number of
1342 hops a packet may travel.
1343
1344 ip_dynaddr
1345 ----------
1346
1347 Enable dynamic socket address rewriting on interface address change. This is
1348 useful for dialup interface with changing IP addresses.
1349
1350 ip_forward
1351 ----------
1352
1353 Enable or disable forwarding of IP packages between interfaces. Changing this
1354 value resets all other parameters to their default values. They differ if the
1355 kernel is configured as host or router.
1356
1357 ip_local_port_range
1358 -------------------
1359
1360 Range of ports used by TCP and UDP to choose the local port. Contains two
1361 numbers, the first number is the lowest port, the second number the highest
1362 local port. Default is 1024-4999. Should be changed to 32768-61000 for
1363 high-usage systems.
1364
1365 ip_no_pmtu_disc
1366 ---------------
1367
1368 Global switch to turn path MTU discovery off. It can also be set on a per
1369 socket basis by the applications or on a per route basis.
1370
1371 ip_masq_debug
1372 -------------
1373
1374 Enable/disable debugging of IP masquerading.
1375
1376 IP fragmentation settings
1377 -------------------------
1378
1379 ipfrag_high_trash and ipfrag_low_trash
1380 --------------------------------------
1381
1382 Maximum memory used to reassemble IP fragments. When ipfrag_high_thresh bytes
1383 of memory is allocated for this purpose, the fragment handler will toss
1384 packets until ipfrag_low_thresh is reached.
1385
1386 ipfrag_time
1387 -----------
1388
1389 Time in seconds to keep an IP fragment in memory.
1390
1391 TCP settings
1392 ------------
1393
1394 tcp_ecn
1395 -------
1396
1397 This file controls the use of the ECN bit in the IPv4 headers, this is a new
1398 feature about Explicit Congestion Notification, but some routers and firewalls
1399 block trafic that has this bit set, so it could be necessary to echo 0 to
1400 /proc/sys/net/ipv4/tcp_ecn, if you want to talk to this sites. For more info
1401 you could read RFC2481.
1402
1403 tcp_retrans_collapse
1404 --------------------
1405
1406 Bug-to-bug compatibility with some broken printers. On retransmit, try to send
1407 larger packets to work around bugs in certain TCP stacks. Can be turned off by
1408 setting it to zero.
1409
1410 tcp_keepalive_probes
1411 --------------------
1412
1413 Number of keep alive probes TCP sends out, until it decides that the
1414 connection is broken.
1415
1416 tcp_keepalive_time
1417 ------------------
1418
1419 How often TCP sends out keep alive messages, when keep alive is enabled. The
1420 default is 2 hours.
1421
1422 tcp_syn_retries
1423 ---------------
1424
1425 Number of times initial SYNs for a TCP connection attempt will be
1426 retransmitted. Should not be higher than 255. This is only the timeout for
1427 outgoing connections, for incoming connections the number of retransmits is
1428 defined by tcp_retries1.
1429
1430 tcp_sack
1431 --------
1432
1433 Enable select acknowledgments after RFC2018.
1434
1435 tcp_timestamps
1436 --------------
1437
1438 Enable timestamps as defined in RFC1323.
1439
1440 tcp_stdurg
1441 ----------
1442
1443 Enable the strict RFC793 interpretation of the TCP urgent pointer field. The
1444 default is to use the BSD compatible interpretation of the urgent pointer
1445 pointing to the first byte after the urgent data. The RFC793 interpretation is
1446 to have it point to the last byte of urgent data. Enabling this option may
1447 lead to interoperatibility problems. Disabled by default.
1448
1449 tcp_syncookies
1450 --------------
1451
1452 Only valid when the kernel was compiled with CONFIG_SYNCOOKIES. Send out
1453 syncookies when the syn backlog queue of a socket overflows. This is to ward
1454 off the common 'syn flood attack'. Disabled by default.
1455
1456 Note that the concept of a socket backlog is abandoned. This means the peer
1457 may not receive reliable error messages from an over loaded server with
1458 syncookies enabled.
1459
1460 tcp_window_scaling
1461 ------------------
1462
1463 Enable window scaling as defined in RFC1323.
1464
1465 tcp_fin_timeout
1466 ---------------
1467
1468 The length of time in seconds it takes to receive a final FIN before the
1469 socket is always closed. This is strictly a violation of the TCP
1470 specification, but required to prevent denial-of-service attacks.
1471
1472 tcp_max_ka_probes
1473 -----------------
1474
1475 Indicates how many keep alive probes are sent per slow timer run. Should not
1476 be set too high to prevent bursts.
1477
1478 tcp_max_syn_backlog
1479 -------------------
1480
1481 Length of the per socket backlog queue. Since Linux 2.2 the backlog specified
1482 in listen(2) only specifies the length of the backlog queue of already
1483 established sockets. When more connection requests arrive Linux starts to drop
1484 packets. When syncookies are enabled the packets are still answered and the
1485 maximum queue is effectively ignored.
1486
1487 tcp_retries1
1488 ------------
1489
1490 Defines how often an answer to a TCP connection request is retransmitted
1491 before giving up.
1492
1493 tcp_retries2
1494 ------------
1495
1496 Defines how often a TCP packet is retransmitted before giving up.
1497
1498 Interface specific settings
1499 ---------------------------
1500
1501 In the directory /proc/sys/net/ipv4/conf you'll find one subdirectory for each
1502 interface the system knows about and one directory calls all. Changes in the
1503 all subdirectory affect all interfaces, whereas changes in the other
1504 subdirectories affect only one interface. All directories have the same
1505 entries:
1506
1507 accept_redirects
1508 ----------------
1509
1510 This switch decides if the kernel accepts ICMP redirect messages or not. The
1511 default is 'yes' if the kernel is configured for a regular host and 'no' for a
1512 router configuration.
1513
1514 accept_source_route
1515 -------------------
1516
1517 Should source routed packages be accepted or declined. The default is
1518 dependent on the kernel configuration. It's 'yes' for routers and 'no' for
1519 hosts.
1520
1521 bootp_relay
1522 ~~~~~~~~~~~
1523
1524 Accept packets with source address 0.b.c.d with destinations not to this host
1525 as local ones. It is supposed that a BOOTP relay daemon will catch and forward
1526 such packets.
1527
1528 The default is 0, since this feature is not implemented yet (kernel version
1529 2.2.12).
1530
1531 forwarding
1532 ----------
1533
1534 Enable or disable IP forwarding on this interface.
1535
1536 log_martians
1537 ------------
1538
1539 Log packets with source addresses with no known route to kernel log.
1540
1541 mc_forwarding
1542 -------------
1543
1544 Do multicast routing. The kernel needs to be compiled with CONFIG_MROUTE and a
1545 multicast routing daemon is required.
1546
1547 proxy_arp
1548 ---------
1549
1550 Does (1) or does not (0) perform proxy ARP.
1551
1552 rp_filter
1553 ---------
1554
1555 Integer value determines if a source validation should be made. 1 means yes, 0
1556 means no. Disabled by default, but local/broadcast address spoofing is always
1557 on.
1558
1559 If you set this to 1 on a router that is the only connection for a network to
1560 the net, it will prevent spoofing attacks against your internal networks
1561 (external addresses can still be spoofed), without the need for additional
1562 firewall rules.
1563
1564 secure_redirects
1565 ----------------
1566
1567 Accept ICMP redirect messages only for gateways, listed in default gateway
1568 list. Enabled by default.
1569
1570 shared_media
1571 ------------
1572
1573 If it is not set the kernel does not assume that different subnets on this
1574 device can communicate directly. Default setting is 'yes'.
1575
1576 send_redirects
1577 --------------
1578
1579 Determines whether to send ICMP redirects to other hosts.
1580
1581 Routing settings
1582 ----------------
1583
1584 The directory /proc/sys/net/ipv4/route contains several file to control
1585 routing issues.
1586
1587 error_burst and error_cost
1588 --------------------------
1589
1590 These parameters are used to limit the warning messages written to the kernel
1591 log from the routing code. The higher the error_cost factor is, the fewer
1592 messages will be written. Error_burst controls when messages will be dropped.
1593 The default settings limit warning messages to one every five seconds.
1594
1595 flush
1596 -----
1597
1598 Writing to this file results in a flush of the routing cache.
1599
1600 gc_elastic, gc_interval, gc_min_interval, gc_tresh, gc_timeout
1601 --------------------------------------------------------------
1602
1603 Values to control the frequency and behavior of the garbage collection
1604 algorithm for the routing cache.
1605
1606 max_size
1607 --------
1608
1609 Maximum size of the routing cache. Old entries will be purged once the cache
1610 reached has this size.
1611
1612 max_delay, min_delay
1613 --------------------
1614
1615 Delays for flushing the routing cache.
1616
1617 redirect_load, redirect_number
1618 ------------------------------
1619
1620 Factors which determine if more ICPM redirects should be sent to a specific
1621 host. No redirects will be sent once the load limit or the maximum number of
1622 redirects has been reached.
1623
1624 redirect_silence
1625 ----------------
1626
1627 Timeout for redirects. After this period redirects will be sent again, even if
1628 this has been stopped, because the load or number limit has been reached.
1629
1630 Network Neighbor handling
1631 -------------------------
1632
1633 Settings about how to handle connections with direct neighbors (nodes attached
1634 to the same link) can be found in the directory /proc/sys/net/ipv4/neigh.
1635
1636 As we saw it in the conf directory, there is a default subdirectory which
1637 holds the default values, and one directory for each interface. The contents
1638 of the directories are identical, with the single exception that the default
1639 settings contain additional options to set garbage collection parameters.
1640
1641 In the interface directories you'll find the following entries:
1642
1643 base_reachable_time
1644 -------------------
1645
1646 A base value used for computing the random reachable time value as specified
1647 in RFC2461.
1648
1649 retrans_time
1650 ------------
1651
1652 The time, expressed in jiffies (1/100 sec), between retransmitted Neighbor
1653 Solicitation messages. Used for address resolution and to determine if a
1654 neighbor is unreachable.
1655
1656 unres_qlen
1657 ----------
1658
1659 Maximum queue length for a pending arp request - the number of packets which
1660 are accepted from other layers while the ARP address is still resolved.
1661
1662 anycast_delay
1663 -------------
1664
1665 Maximum for random delay of answers to neighbor solicitation messages in
1666 jiffies (1/100 sec). Not yet implemented (Linux does not have anycast support
1667 yet).
1668
1669 ucast_solicit
1670 -------------
1671
1672 Maximum number of retries for unicast solicitation.
1673
1674 mcast_solicit
1675 -------------
1676
1677 Maximum number of retries for multicast solicitation.
1678
1679 delay_first_probe_time
1680 ----------------------
1681
1682 Delay for the first time probe if the neighbor is reachable. (see
1683 gc_stale_time)
1684
1685 locktime
1686 --------
1687
1688 An ARP/neighbor entry is only replaced with a new one if the old is at least
1689 locktime old. This prevents ARP cache thrashing.
1690
1691 proxy_delay
1692 -----------
1693
1694 Maximum time (real time is random [0..proxytime]) before answering to an ARP
1695 request for which we have an proxy ARP entry. In some cases, this is used to
1696 prevent network flooding.
1697
1698 proxy_qlen
1699 ----------
1700
1701 Maximum queue length of the delayed proxy arp timer. (see proxy_delay).
1702
1703 app_solcit
1704 ----------
1705
1706 Determines the number of requests to send to the user level ARP daemon. Use 0
1707 to turn off.
1708
1709 gc_stale_time
1710 -------------
1711
1712 Determines how often to check for stale ARP entries. After an ARP entry is
1713 stale it will be resolved again (which is useful when an IP address migrates
1714 to another machine). When ucast_solicit is greater than 0 it first tries to
1715 send an ARP packet directly to the known host When that fails and
1716 mcast_solicit is greater than 0, an ARP request is broadcasted.
1717
1718 2.9 Appletalk
1719 -------------
1720
1721 The /proc/sys/net/appletalk directory holds the Appletalk configuration data
1722 when Appletalk is loaded. The configurable parameters are:
1723
1724 aarp-expiry-time
1725 ----------------
1726
1727 The amount of time we keep an ARP entry before expiring it. Used to age out
1728 old hosts.
1729
1730 aarp-resolve-time
1731 -----------------
1732
1733 The amount of time we will spend trying to resolve an Appletalk address.
1734
1735 aarp-retransmit-limit
1736 ---------------------
1737
1738 The number of times we will retransmit a query before giving up.
1739
1740 aarp-tick-time
1741 --------------
1742
1743 Controls the rate at which expires are checked.
1744
1745 The directory /proc/net/appletalk holds the list of active Appletalk sockets
1746 on a machine.
1747
1748 The fields indicate the DDP type, the local address (in network:node format)
1749 the remote address, the size of the transmit pending queue, the size of the
1750 received queue (bytes waiting for applications to read) the state and the uid
1751 owning the socket.
1752
1753 /proc/net/atalk_iface lists all the interfaces configured for appletalk.It
1754 shows the name of the interface, its Appletalk address, the network range on
1755 that address (or network number for phase 1 networks), and the status of the
1756 interface.
1757
1758 /proc/net/atalk_route lists each known network route. It lists the target
1759 (network) that the route leads to, the router (may be directly connected), the
1760 route flags, and the device the route is using.
1761
1762 2.10 IPX
1763 --------
1764
1765 The IPX protocol has no tunable values in proc/sys/net.
1766
1767 The IPX protocol does, however, provide proc/net/ipx. This lists each IPX
1768 socket giving the local and remote addresses in Novell format (that is
1769 network:node:port). In accordance with the strange Novell tradition,
1770 everything but the port is in hex. Not_Connected is displayed for sockets that
1771 are not tied to a specific remote address. The Tx and Rx queue sizes indicate
1772 the number of bytes pending for transmission and reception. The state
1773 indicates the state the socket is in and the uid is the owning uid of the
1774 socket.
1775
1776 The /proc/net/ipx_interface file lists all IPX interfaces. For each interface
1777 it gives the network number, the node number, and indicates if the network is
1778 the primary network. It also indicates which device it is bound to (or
1779 Internal for internal networks) and the Frame Type if appropriate. Linux
1780 supports 802.3, 802.2, 802.2 SNAP and DIX (Blue Book) ethernet framing for
1781 IPX.
1782
1783 The /proc/net/ipx_route table holds a list of IPX routes. For each route it
1784 gives the destination network, the router node (or Directly) and the network
1785 address of the router (or Connected) for internal networks.
1786
1787 ------------------------------------------------------------------------------
1788 Summary
1789 ------------------------------------------------------------------------------
1790 Certain aspects of kernel behavior can be modified at runtime, without the
1791 need to recompile the kernel, or even to reboot the system. The files in the
1792 /proc/sys tree can not only be read, but also modified. You can use the echo
1793 command to write value into these files, thereby changing the default settings
1794 of the kernel.
1795 ------------------------------------------------------------------------------
1796
1797
1798
1799
1800
1801
1802
This page was automatically generated by the
LXR engine.
Visit the LXR main site for more
information.