blob: c7165f4cb7927a152ec547caeecb393f5ad3c27e [file] [log] [blame]
Linus Torvalds1da177e2005-04-16 15:20:36 -07001/proc/sys/net/ipv4/* Variables:
2
3ip_forward - BOOLEAN
4 0 - disabled (default)
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +00005 not 0 - enabled
Linus Torvalds1da177e2005-04-16 15:20:36 -07006
7 Forward Packets between interfaces.
8
9 This variable is special, its change resets all configuration
10 parameters to their default state (RFC1122 for hosts, RFC1812
11 for routers)
12
13ip_default_ttl - INTEGER
14 default 64
15
16ip_no_pmtu_disc - BOOLEAN
17 Disable Path MTU Discovery.
18 default FALSE
19
20min_pmtu - INTEGER
21 default 562 - minimum discovered Path MTU
22
23mtu_expires - INTEGER
24 Time, in seconds, that cached PMTU information is kept.
25
26min_adv_mss - INTEGER
27 The advertised MSS depends on the first hop route MTU, but will
28 never be lower than this setting.
29
Neil Horman1080d702008-10-27 12:28:25 -070030rt_cache_rebuild_count - INTEGER
31 The per net-namespace route cache emergency rebuild threshold.
32 Any net-namespace having its route cache rebuilt due to
33 a hash bucket chain being too long more than this many times
34 will have its route caching disabled
35
Linus Torvalds1da177e2005-04-16 15:20:36 -070036IP Fragmentation:
37
38ipfrag_high_thresh - INTEGER
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +000039 Maximum memory used to reassemble IP fragments. When
Linus Torvalds1da177e2005-04-16 15:20:36 -070040 ipfrag_high_thresh bytes of memory is allocated for this purpose,
41 the fragment handler will toss packets until ipfrag_low_thresh
42 is reached.
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +000043
Linus Torvalds1da177e2005-04-16 15:20:36 -070044ipfrag_low_thresh - INTEGER
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +000045 See ipfrag_high_thresh
Linus Torvalds1da177e2005-04-16 15:20:36 -070046
47ipfrag_time - INTEGER
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +000048 Time in seconds to keep an IP fragment in memory.
Linus Torvalds1da177e2005-04-16 15:20:36 -070049
50ipfrag_secret_interval - INTEGER
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +000051 Regeneration interval (in seconds) of the hash secret (or lifetime
Linus Torvalds1da177e2005-04-16 15:20:36 -070052 for the hash secret) for IP fragments.
53 Default: 600
54
Herbert Xu89cee8b2005-12-13 23:14:27 -080055ipfrag_max_dist - INTEGER
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +000056 ipfrag_max_dist is a non-negative integer value which defines the
57 maximum "disorder" which is allowed among fragments which share a
58 common IP source address. Note that reordering of packets is
59 not unusual, but if a large number of fragments arrive from a source
60 IP address while a particular fragment queue remains incomplete, it
61 probably indicates that one or more fragments belonging to that queue
62 have been lost. When ipfrag_max_dist is positive, an additional check
63 is done on fragments before they are added to a reassembly queue - if
64 ipfrag_max_dist (or more) fragments have arrived from a particular IP
65 address between additions to any IP fragment queue using that source
66 address, it's presumed that one or more fragments in the queue are
67 lost. The existing fragment queue will be dropped, and a new one
Herbert Xu89cee8b2005-12-13 23:14:27 -080068 started. An ipfrag_max_dist value of zero disables this check.
69
70 Using a very small value, e.g. 1 or 2, for ipfrag_max_dist can
71 result in unnecessarily dropping fragment queues when normal
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +000072 reordering of packets occurs, which could lead to poor application
73 performance. Using a very large value, e.g. 50000, increases the
74 likelihood of incorrectly reassembling IP fragments that originate
Herbert Xu89cee8b2005-12-13 23:14:27 -080075 from different IP datagrams, which could result in data corruption.
76 Default: 64
77
Linus Torvalds1da177e2005-04-16 15:20:36 -070078INET peer storage:
79
80inet_peer_threshold - INTEGER
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +000081 The approximate size of the storage. Starting from this threshold
Linus Torvalds1da177e2005-04-16 15:20:36 -070082 entries will be thrown aggressively. This threshold also determines
83 entries' time-to-live and time intervals between garbage collection
84 passes. More entries, less time-to-live, less GC interval.
85
86inet_peer_minttl - INTEGER
87 Minimum time-to-live of entries. Should be enough to cover fragment
88 time-to-live on the reassembling side. This minimum time-to-live is
89 guaranteed if the pool size is less than inet_peer_threshold.
Stephen Hemminger77a538d2008-07-01 17:22:48 -070090 Measured in seconds.
Linus Torvalds1da177e2005-04-16 15:20:36 -070091
92inet_peer_maxttl - INTEGER
93 Maximum time-to-live of entries. Unused entries will expire after
94 this period of time if there is no memory pressure on the pool (i.e.
95 when the number of entries in the pool is very small).
Stephen Hemminger77a538d2008-07-01 17:22:48 -070096 Measured in seconds.
Linus Torvalds1da177e2005-04-16 15:20:36 -070097
98inet_peer_gc_mintime - INTEGER
99 Minimum interval between garbage collection passes. This interval is
100 in effect under high memory pressure on the pool.
Stephen Hemminger77a538d2008-07-01 17:22:48 -0700101 Measured in seconds.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700102
103inet_peer_gc_maxtime - INTEGER
104 Minimum interval between garbage collection passes. This interval is
105 in effect under low (or absent) memory pressure on the pool.
Stephen Hemminger77a538d2008-07-01 17:22:48 -0700106 Measured in seconds.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700107
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000108TCP variables:
Linus Torvalds1da177e2005-04-16 15:20:36 -0700109
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800110somaxconn - INTEGER
111 Limit of socket listen() backlog, known in userspace as SOMAXCONN.
112 Defaults to 128. See also tcp_max_syn_backlog for additional tuning
113 for TCP sockets.
114
Stephen Hemminger9772efb2005-11-10 17:09:53 -0800115tcp_abc - INTEGER
Stephen Hemmingerb3a8a402006-09-13 19:51:02 -0700116 Controls Appropriate Byte Count (ABC) defined in RFC3465.
117 ABC is a way of increasing congestion window (cwnd) more slowly
118 in response to partial acknowledgments.
119 Possible values are:
120 0 increase cwnd once per acknowledgment (no ABC)
121 1 increase cwnd once per acknowledgment of full sized segment
122 2 allow increase cwnd by two if acknowledgment is
123 of two segments to compensate for delayed acknowledgments.
124 Default: 0 (off)
Stephen Hemminger9772efb2005-11-10 17:09:53 -0800125
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800126tcp_abort_on_overflow - BOOLEAN
127 If listening service is too slow to accept new connections,
128 reset them. Default state is FALSE. It means that if overflow
129 occurred due to a burst, connection will recover. Enable this
130 option _only_ if you are really sure that listening daemon
131 cannot be tuned to accept connections faster. Enabling this
132 option can harm clients of your server.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700133
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800134tcp_adv_win_scale - INTEGER
135 Count buffering overhead as bytes/2^tcp_adv_win_scale
136 (if tcp_adv_win_scale > 0) or bytes-bytes/2^(-tcp_adv_win_scale),
137 if it is <= 0.
138 Default: 2
139
140tcp_allowed_congestion_control - STRING
141 Show/set the congestion control choices available to non-privileged
142 processes. The list is a subset of those listed in
143 tcp_available_congestion_control.
144 Default is "reno" and the default setting (tcp_congestion_control).
145
146tcp_app_win - INTEGER
147 Reserve max(window/2^tcp_app_win, mss) of window for application
148 buffer. Value 0 is special, it means that nothing is reserved.
149 Default: 31
150
151tcp_available_congestion_control - STRING
152 Shows the available congestion control choices that are registered.
153 More congestion control algorithms may be available as modules,
154 but not loaded.
155
John Heffner71599cd2007-02-27 10:03:56 -0800156tcp_base_mss - INTEGER
Stephen Hemminger4edc2f32008-07-10 16:50:26 -0700157 The initial value of search_low to be used by the packetization layer
158 Path MTU discovery (MTU probing). If MTU probing is enabled,
159 this is the initial MSS used by the connection.
John Heffner71599cd2007-02-27 10:03:56 -0800160
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800161tcp_congestion_control - STRING
162 Set the congestion control algorithm to be used for new
163 connections. The algorithm "reno" is always available, but
164 additional choices may be available based on kernel configuration.
165 Default is set as part of kernel configuration.
166
William Allen Simpson519855c2009-12-02 18:14:19 +0000167tcp_cookie_size - INTEGER
168 Default size of TCP Cookie Transactions (TCPCT) option, that may be
169 overridden on a per socket basis by the TCPCT socket option.
170 Values greater than the maximum (16) are interpreted as the maximum.
171 Values greater than zero and less than the minimum (8) are interpreted
172 as the minimum. Odd values are interpreted as the next even value.
173 Default: 0 (off).
174
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800175tcp_dsack - BOOLEAN
176 Allows TCP to send "duplicate" SACKs.
177
178tcp_ecn - BOOLEAN
Ilpo Järvinen255cac92009-05-04 11:07:36 -0700179 Enable Explicit Congestion Notification (ECN) in TCP. ECN is only
180 used when both ends of the TCP flow support it. It is useful to
181 avoid losses due to congestion (when the bottleneck router supports
182 ECN).
183 Possible values are:
184 0 disable ECN
185 1 ECN enabled
186 2 Only server-side ECN enabled. If the other end does
187 not support ECN, behavior is like with ECN disabled.
188 Default: 2
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800189
190tcp_fack - BOOLEAN
191 Enable FACK congestion avoidance and fast retransmission.
192 The value is not used, if tcp_sack is not enabled.
193
194tcp_fin_timeout - INTEGER
195 Time to hold socket in state FIN-WAIT-2, if it was closed
196 by our side. Peer can be broken and never close its side,
197 or even died unexpectedly. Default value is 60sec.
198 Usual value used in 2.2 was 180 seconds, you may restore
199 it, but remember that if your machine is even underloaded WEB server,
200 you risk to overflow memory with kilotons of dead sockets,
201 FIN-WAIT-2 sockets are less dangerous than FIN-WAIT-1,
202 because they eat maximum 1.5K of memory, but they tend
203 to live longer. Cf. tcp_max_orphans.
204
Ilpo Järvinen89808062007-02-27 10:10:55 -0800205tcp_frto - INTEGER
Ilpo Järvinencd998892007-09-20 11:35:26 -0700206 Enables Forward RTO-Recovery (F-RTO) defined in RFC4138.
207 F-RTO is an enhanced recovery algorithm for TCP retransmission
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800208 timeouts. It is particularly beneficial in wireless environments
209 where packet loss is typically due to random radio interference
Ryousei Takano564262c2007-10-25 23:03:52 -0700210 rather than intermediate router congestion. F-RTO is sender-side
Stephen Hemminger4edc2f32008-07-10 16:50:26 -0700211 only modification. Therefore it does not require any support from
212 the peer.
213
Ilpo Järvinencd998892007-09-20 11:35:26 -0700214 If set to 1, basic version is enabled. 2 enables SACK enhanced
215 F-RTO if flow uses SACK. The basic version can be used also when
Ryousei Takano564262c2007-10-25 23:03:52 -0700216 SACK is in use though scenario(s) with it exists where F-RTO
Ilpo Järvinencd998892007-09-20 11:35:26 -0700217 interacts badly with the packet counting of the SACK enabled TCP
218 flow.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700219
Ilpo Järvinen89808062007-02-27 10:10:55 -0800220tcp_frto_response - INTEGER
221 When F-RTO has detected that a TCP retransmission timeout was
222 spurious (i.e, the timeout would have been avoided had TCP set a
223 longer retransmission timeout), TCP has several options what to do
224 next. Possible values are:
225 0 Rate halving based; a smooth and conservative response,
226 results in halved cwnd and ssthresh after one RTT
227 1 Very conservative response; not recommended because even
228 though being valid, it interacts poorly with the rest of
229 Linux TCP, halves cwnd and ssthresh immediately
230 2 Aggressive response; undoes congestion control measures
231 that are now known to be unnecessary (ignoring the
232 possibility of a lost retransmission that would require
233 TCP to be more cautious), cwnd and ssthresh are restored
234 to the values prior timeout
235 Default: 0 (rate halving based)
236
Linus Torvalds1da177e2005-04-16 15:20:36 -0700237tcp_keepalive_time - INTEGER
238 How often TCP sends out keepalive messages when keepalive is enabled.
239 Default: 2hours.
240
241tcp_keepalive_probes - INTEGER
242 How many keepalive probes TCP sends out, until it decides that the
243 connection is broken. Default value: 9.
244
245tcp_keepalive_intvl - INTEGER
246 How frequently the probes are send out. Multiplied by
247 tcp_keepalive_probes it is time to kill not responding connection,
248 after probes started. Default value: 75sec i.e. connection
249 will be aborted after ~11 minutes of retries.
250
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800251tcp_low_latency - BOOLEAN
252 If set, the TCP stack makes decisions that prefer lower
253 latency as opposed to higher throughput. By default, this
254 option is not set meaning that higher throughput is preferred.
255 An example of an application where this default should be
256 changed would be a Beowulf compute cluster.
257 Default: 0
Linus Torvalds1da177e2005-04-16 15:20:36 -0700258
259tcp_max_orphans - INTEGER
260 Maximal number of TCP sockets not attached to any user file handle,
261 held by system. If this number is exceeded orphaned connections are
262 reset immediately and warning is printed. This limit exists
263 only to prevent simple DoS attacks, you _must_ not rely on this
264 or lower the limit artificially, but rather increase it
265 (probably, after increasing installed memory),
266 if network conditions require more than default value,
267 and tune network services to linger and kill such states
268 more aggressively. Let me to remind again: each orphan eats
269 up to ~64K of unswappable memory.
270
Linus Torvalds1da177e2005-04-16 15:20:36 -0700271tcp_max_syn_backlog - INTEGER
272 Maximal number of remembered connection requests, which are
273 still did not receive an acknowledgment from connecting client.
274 Default value is 1024 for systems with more than 128Mb of memory,
275 and 128 for low memory machines. If server suffers of overload,
276 try to increase this number.
277
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800278tcp_max_tw_buckets - INTEGER
279 Maximal number of timewait sockets held by system simultaneously.
280 If this number is exceeded time-wait socket is immediately destroyed
281 and warning is printed. This limit exists only to prevent
282 simple DoS attacks, you _must_ not lower the limit artificially,
283 but rather increase it (probably, after increasing installed memory),
284 if network conditions require more than default value.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700285
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800286tcp_mem - vector of 3 INTEGERs: min, pressure, max
287 min: below this number of pages TCP is not bothered about its
288 memory appetite.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700289
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800290 pressure: when amount of memory allocated by TCP exceeds this number
291 of pages, TCP moderates its memory consumption and enters memory
292 pressure mode, which is exited when memory consumption falls
293 under "min".
Linus Torvalds1da177e2005-04-16 15:20:36 -0700294
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800295 max: number of pages allowed for queueing by all TCP sockets.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700296
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800297 Defaults are calculated at boot time from amount of available
298 memory.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700299
John Heffner71599cd2007-02-27 10:03:56 -0800300tcp_moderate_rcvbuf - BOOLEAN
Stephen Hemminger4edc2f32008-07-10 16:50:26 -0700301 If set, TCP performs receive buffer auto-tuning, attempting to
John Heffner71599cd2007-02-27 10:03:56 -0800302 automatically size the buffer (no greater than tcp_rmem[2]) to
303 match the size required by the path for full throughput. Enabled by
304 default.
305
306tcp_mtu_probing - INTEGER
307 Controls TCP Packetization-Layer Path MTU Discovery. Takes three
308 values:
309 0 - Disabled
310 1 - Disabled by default, enabled when an ICMP black hole detected
311 2 - Always enabled, use initial MSS of tcp_base_mss.
312
313tcp_no_metrics_save - BOOLEAN
314 By default, TCP saves various connection metrics in the route cache
315 when the connection closes, so that connections established in the
316 near future can use these to set initial conditions. Usually, this
317 increases overall performance, but may sometimes cause performance
Simon Arlott0f035b82007-10-20 01:30:25 +0200318 degradation. If set, TCP will not cache metrics on closing
John Heffner71599cd2007-02-27 10:03:56 -0800319 connections.
320
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800321tcp_orphan_retries - INTEGER
Damian Lukowski5d789222009-09-01 10:24:04 +0000322 This value influences the timeout of a locally closed TCP connection,
323 when RTO retransmissions remain unacknowledged.
324 See tcp_retries2 for more details.
325
326 The default value is 7.
327 If your machine is a loaded WEB server,
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800328 you should think about lowering this value, such sockets
329 may consume significant resources. Cf. tcp_max_orphans.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700330
331tcp_reordering - INTEGER
332 Maximal reordering of packets in a TCP stream.
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000333 Default: 3
Linus Torvalds1da177e2005-04-16 15:20:36 -0700334
335tcp_retrans_collapse - BOOLEAN
336 Bug-to-bug compatibility with some broken printers.
337 On retransmit try to send bigger packets to work around bugs in
338 certain TCP stacks.
339
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800340tcp_retries1 - INTEGER
Damian Lukowski5d789222009-09-01 10:24:04 +0000341 This value influences the time, after which TCP decides, that
342 something is wrong due to unacknowledged RTO retransmissions,
343 and reports this suspicion to the network layer.
344 See tcp_retries2 for more details.
345
346 RFC 1122 recommends at least 3 retransmissions, which is the
347 default.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700348
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800349tcp_retries2 - INTEGER
Damian Lukowski5d789222009-09-01 10:24:04 +0000350 This value influences the timeout of an alive TCP connection,
351 when RTO retransmissions remain unacknowledged.
352 Given a value of N, a hypothetical TCP connection following
353 exponential backoff with an initial RTO of TCP_RTO_MIN would
354 retransmit N times before killing the connection at the (N+1)th RTO.
355
356 The default value of 15 yields a hypothetical timeout of 924.6
357 seconds and is a lower bound for the effective timeout.
358 TCP will effectively time out at the first RTO which exceeds the
359 hypothetical timeout.
360
361 RFC 1122 recommends at least 100 seconds for the timeout,
362 which corresponds to a value of at least 8.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700363
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800364tcp_rfc1337 - BOOLEAN
365 If set, the TCP stack behaves conforming to RFC1337. If unset,
366 we are not conforming to RFC, but prevent TCP TIME_WAIT
367 assassination.
368 Default: 0
Linus Torvalds1da177e2005-04-16 15:20:36 -0700369
370tcp_rmem - vector of 3 INTEGERs: min, default, max
371 min: Minimal size of receive buffer used by TCP sockets.
372 It is guaranteed to each TCP socket, even under moderate memory
373 pressure.
374 Default: 8K
375
J. Bruce Fields53025f52008-07-10 16:47:41 -0700376 default: initial size of receive buffer used by TCP sockets.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700377 This value overrides net.core.rmem_default used by other protocols.
378 Default: 87380 bytes. This value results in window of 65535 with
379 default setting of tcp_adv_win_scale and tcp_app_win:0 and a bit
380 less for default tcp_app_win. See below about these variables.
381
382 max: maximal size of receive buffer allowed for automatically
383 selected receiver buffers for TCP socket. This value does not override
J. Bruce Fields53025f52008-07-10 16:47:41 -0700384 net.core.rmem_max. Calling setsockopt() with SO_RCVBUF disables
385 automatic tuning of that socket's receive buffer size, in which
386 case this value is ignored.
387 Default: between 87380B and 4MB, depending on RAM size.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700388
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800389tcp_sack - BOOLEAN
390 Enable select acknowledgments (SACKS).
Rick Jones15d99e02006-03-20 22:40:29 -0800391
David S. Miller35089bb2006-06-13 22:33:04 -0700392tcp_slow_start_after_idle - BOOLEAN
393 If set, provide RFC2861 behavior and time out the congestion
394 window after an idle period. An idle period is defined at
395 the current RTO. If unset, the congestion window will not
396 be timed out after an idle period.
397 Default: 1
398
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800399tcp_stdurg - BOOLEAN
Stephen Hemminger4edc2f32008-07-10 16:50:26 -0700400 Use the Host requirements interpretation of the TCP urgent pointer field.
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800401 Most hosts use the older BSD interpretation, so if you turn this on
402 Linux might not communicate correctly with them.
403 Default: FALSE
404
405tcp_synack_retries - INTEGER
406 Number of times SYNACKs for a passive TCP connection attempt will
407 be retransmitted. Should not be higher than 255. Default value
408 is 5, which corresponds to ~180seconds.
409
410tcp_syncookies - BOOLEAN
411 Only valid when the kernel was compiled with CONFIG_SYNCOOKIES
412 Send out syncookies when the syn backlog queue of a socket
Stephen Hemminger4edc2f32008-07-10 16:50:26 -0700413 overflows. This is to prevent against the common 'SYN flood attack'
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800414 Default: FALSE
415
416 Note, that syncookies is fallback facility.
417 It MUST NOT be used to help highly loaded servers to stand
Stephen Hemminger4edc2f32008-07-10 16:50:26 -0700418 against legal connection rate. If you see SYN flood warnings
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800419 in your logs, but investigation shows that they occur
420 because of overload with legal connections, you should tune
421 another parameters until this warning disappear.
422 See: tcp_max_syn_backlog, tcp_synack_retries, tcp_abort_on_overflow.
423
424 syncookies seriously violate TCP protocol, do not allow
425 to use TCP extensions, can result in serious degradation
426 of some services (f.e. SMTP relaying), visible not by you,
427 but your clients and relays, contacting you. While you see
Stephen Hemminger4edc2f32008-07-10 16:50:26 -0700428 SYN flood warnings in logs not being really flooded, your server
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800429 is seriously misconfigured.
430
431tcp_syn_retries - INTEGER
432 Number of times initial SYNs for an active TCP connection attempt
433 will be retransmitted. Should not be higher than 255. Default value
434 is 5, which corresponds to ~180seconds.
435
436tcp_timestamps - BOOLEAN
437 Enable timestamps as defined in RFC1323.
438
439tcp_tso_win_divisor - INTEGER
440 This allows control over what percentage of the congestion window
441 can be consumed by a single TSO frame.
442 The setting of this parameter is a choice between burstiness and
443 building larger TSO frames.
444 Default: 3
445
446tcp_tw_recycle - BOOLEAN
447 Enable fast recycling TIME-WAIT sockets. Default value is 0.
448 It should not be changed without advice/request of technical
449 experts.
450
451tcp_tw_reuse - BOOLEAN
452 Allow to reuse TIME-WAIT sockets for new connections when it is
453 safe from protocol viewpoint. Default value is 0.
454 It should not be changed without advice/request of technical
455 experts.
456
457tcp_window_scaling - BOOLEAN
458 Enable window scaling as defined in RFC1323.
459
460tcp_wmem - vector of 3 INTEGERs: min, default, max
J. Bruce Fields53025f52008-07-10 16:47:41 -0700461 min: Amount of memory reserved for send buffers for TCP sockets.
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800462 Each TCP socket has rights to use it due to fact of its birth.
463 Default: 4K
464
J. Bruce Fields53025f52008-07-10 16:47:41 -0700465 default: initial size of send buffer used by TCP sockets. This
466 value overrides net.core.wmem_default used by other protocols.
467 It is usually lower than net.core.wmem_default.
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800468 Default: 16K
469
J. Bruce Fields53025f52008-07-10 16:47:41 -0700470 max: Maximal amount of memory allowed for automatically tuned
471 send buffers for TCP sockets. This value does not override
472 net.core.wmem_max. Calling setsockopt() with SO_SNDBUF disables
473 automatic tuning of that socket's send buffer size, in which case
474 this value is ignored.
475 Default: between 64K and 4MB, depending on RAM size.
Stephen Hemmingeref56e622006-11-09 16:37:26 -0800476
477tcp_workaround_signed_windows - BOOLEAN
478 If set, assume no receipt of a window scaling option means the
479 remote TCP is broken and treats the window as a signed quantity.
480 If unset, assume the remote TCP is not broken even if we do
481 not receive a window scaling option from them.
482 Default: 0
483
Chris Leech72d0b7a2007-03-08 09:57:35 -0800484tcp_dma_copybreak - INTEGER
485 Lower limit, in bytes, of the size of socket reads that will be
486 offloaded to a DMA copy engine, if one is present in the system
487 and CONFIG_NET_DMA is enabled.
488 Default: 4096
489
Andreas Petlund36e31b0a2010-02-18 02:47:01 +0000490tcp_thin_linear_timeouts - BOOLEAN
491 Enable dynamic triggering of linear timeouts for thin streams.
492 If set, a check is performed upon retransmission by timeout to
493 determine if the stream is thin (less than 4 packets in flight).
494 As long as the stream is found to be thin, up to 6 linear
495 timeouts may be performed before exponential backoff mode is
496 initiated. This improves retransmission latency for
497 non-aggressive thin streams, often found to be time-dependent.
498 For more information on thin streams, see
499 Documentation/networking/tcp-thin.txt
500 Default: 0
501
Andreas Petlund7e380172010-02-18 04:48:19 +0000502tcp_thin_dupack - BOOLEAN
503 Enable dynamic triggering of retransmissions after one dupACK
504 for thin streams. If set, a check is performed upon reception
505 of a dupACK to determine if the stream is thin (less than 4
506 packets in flight). As long as the stream is found to be thin,
507 data is retransmitted on the first received dupACK. This
508 improves retransmission latency for non-aggressive thin
509 streams, often found to be time-dependent.
510 For more information on thin streams, see
511 Documentation/networking/tcp-thin.txt
512 Default: 0
513
Hideo Aoki95766ff2007-12-31 00:29:24 -0800514UDP variables:
515
516udp_mem - vector of 3 INTEGERs: min, pressure, max
517 Number of pages allowed for queueing by all UDP sockets.
518
519 min: Below this number of pages UDP is not bothered about its
520 memory appetite. When amount of memory allocated by UDP exceeds
521 this number, UDP starts to moderate memory usage.
522
523 pressure: This value was introduced to follow format of tcp_mem.
524
525 max: Number of pages allowed for queueing by all UDP sockets.
526
527 Default is calculated at boot time from amount of available memory.
528
529udp_rmem_min - INTEGER
530 Minimal size of receive buffer used by UDP sockets in moderation.
531 Each UDP socket is able to use the size for receiving data, even if
532 total pages of UDP sockets exceed udp_mem pressure. The unit is byte.
533 Default: 4096
534
535udp_wmem_min - INTEGER
536 Minimal size of send buffer used by UDP sockets in moderation.
537 Each UDP socket is able to use the size for sending data, even if
538 total pages of UDP sockets exceed udp_mem pressure. The unit is byte.
539 Default: 4096
540
Paul Moore8802f612006-08-03 16:45:49 -0700541CIPSOv4 Variables:
542
543cipso_cache_enable - BOOLEAN
544 If set, enable additions to and lookups from the CIPSO label mapping
545 cache. If unset, additions are ignored and lookups always result in a
546 miss. However, regardless of the setting the cache is still
547 invalidated when required when means you can safely toggle this on and
548 off and the cache will always be "safe".
549 Default: 1
550
551cipso_cache_bucket_size - INTEGER
552 The CIPSO label cache consists of a fixed size hash table with each
553 hash bucket containing a number of cache entries. This variable limits
554 the number of entries in each hash bucket; the larger the value the
555 more CIPSO label mappings that can be cached. When the number of
556 entries in a given hash bucket reaches this limit adding new entries
557 causes the oldest entry in the bucket to be removed to make room.
558 Default: 10
559
560cipso_rbm_optfmt - BOOLEAN
561 Enable the "Optimized Tag 1 Format" as defined in section 3.4.2.6 of
562 the CIPSO draft specification (see Documentation/netlabel for details).
563 This means that when set the CIPSO tag will be padded with empty
564 categories in order to make the packet data 32-bit aligned.
565 Default: 0
566
567cipso_rbm_structvalid - BOOLEAN
568 If set, do a very strict check of the CIPSO option when
569 ip_options_compile() is called. If unset, relax the checks done during
570 ip_options_compile(). Either way is "safe" as errors are caught else
571 where in the CIPSO processing code but setting this to 0 (False) should
572 result in less work (i.e. it should be faster) but could cause problems
573 with other implementations that require strict checking.
574 Default: 0
575
Linus Torvalds1da177e2005-04-16 15:20:36 -0700576IP Variables:
577
578ip_local_port_range - 2 INTEGERS
579 Defines the local port range that is used by TCP and UDP to
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000580 choose the local port. The first number is the first, the
Linus Torvalds1da177e2005-04-16 15:20:36 -0700581 second the last local port number. Default value depends on
582 amount of memory available on the system:
583 > 128Mb 32768-61000
584 < 128Mb 1024-4999 or even less.
585 This number defines number of active connections, which this
586 system can issue simultaneously to systems not supporting
587 TCP extensions (timestamps). With tcp_tw_recycle enabled
588 (i.e. by default) range 1024-4999 is enough to issue up to
589 2000 connections per second to systems supporting timestamps.
590
Amerigo Wange3826f12010-05-05 00:27:06 +0000591ip_local_reserved_ports - list of comma separated ranges
592 Specify the ports which are reserved for known third-party
593 applications. These ports will not be used by automatic port
594 assignments (e.g. when calling connect() or bind() with port
595 number 0). Explicit port allocation behavior is unchanged.
596
597 The format used for both input and output is a comma separated
598 list of ranges (e.g. "1,2-4,10-10" for ports 1, 2, 3, 4 and
599 10). Writing to the file will clear all previously reserved
600 ports and update the current list with the one given in the
601 input.
602
603 Note that ip_local_port_range and ip_local_reserved_ports
604 settings are independent and both are considered by the kernel
605 when determining which ports are available for automatic port
606 assignments.
607
608 You can reserve ports which are not in the current
609 ip_local_port_range, e.g.:
610
611 $ cat /proc/sys/net/ipv4/ip_local_port_range
612 32000 61000
613 $ cat /proc/sys/net/ipv4/ip_local_reserved_ports
614 8080,9148
615
616 although this is redundant. However such a setting is useful
617 if later the port range is changed to a value that will
618 include the reserved ports.
619
620 Default: Empty
621
Linus Torvalds1da177e2005-04-16 15:20:36 -0700622ip_nonlocal_bind - BOOLEAN
623 If set, allows processes to bind() to non-local IP addresses,
624 which can be quite useful - but may break some applications.
625 Default: 0
626
627ip_dynaddr - BOOLEAN
628 If set non-zero, enables support for dynamic addresses.
629 If set to a non-zero value larger than 1, a kernel log
630 message will be printed when dynamic address rewriting
631 occurs.
632 Default: 0
633
634icmp_echo_ignore_all - BOOLEAN
David S. Miller7ce312462005-10-03 16:07:30 -0700635 If set non-zero, then the kernel will ignore all ICMP ECHO
636 requests sent to it.
637 Default: 0
638
Linus Torvalds1da177e2005-04-16 15:20:36 -0700639icmp_echo_ignore_broadcasts - BOOLEAN
David S. Miller7ce312462005-10-03 16:07:30 -0700640 If set non-zero, then the kernel will ignore all ICMP ECHO and
641 TIMESTAMP requests sent to it via broadcast/multicast.
642 Default: 1
Linus Torvalds1da177e2005-04-16 15:20:36 -0700643
644icmp_ratelimit - INTEGER
645 Limit the maximal rates for sending ICMP packets whose type matches
646 icmp_ratemask (see below) to specific targets.
Stephen Hemminger6dbf4bc2008-07-01 19:29:07 -0700647 0 to disable any limiting,
648 otherwise the minimal space between responses in milliseconds.
649 Default: 1000
Linus Torvalds1da177e2005-04-16 15:20:36 -0700650
651icmp_ratemask - INTEGER
652 Mask made of ICMP types for which rates are being limited.
653 Significant bits: IHGFEDCBA9876543210
654 Default mask: 0000001100000011000 (6168)
655
656 Bit definitions (see include/linux/icmp.h):
657 0 Echo Reply
658 3 Destination Unreachable *
659 4 Source Quench *
660 5 Redirect
661 8 Echo Request
662 B Time Exceeded *
663 C Parameter Problem *
664 D Timestamp Request
665 E Timestamp Reply
666 F Info Request
667 G Info Reply
668 H Address Mask Request
669 I Address Mask Reply
670
671 * These are rate limited by default (see default mask above)
672
673icmp_ignore_bogus_error_responses - BOOLEAN
674 Some routers violate RFC1122 by sending bogus responses to broadcast
675 frames. Such violations are normally logged via a kernel warning.
676 If this is set to TRUE, the kernel will not give such warnings, which
677 will avoid log file clutter.
678 Default: FALSE
679
Horms95f7daf2006-02-02 17:02:25 -0800680icmp_errors_use_inbound_ifaddr - BOOLEAN
681
682 If zero, icmp error messages are sent with the primary address of
683 the exiting interface.
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000684
Horms95f7daf2006-02-02 17:02:25 -0800685 If non-zero, the message will be sent with the primary address of
686 the interface that received the packet that caused the icmp error.
687 This is the behaviour network many administrators will expect from
688 a router. And it can make debugging complicated network layouts
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000689 much easier.
Horms95f7daf2006-02-02 17:02:25 -0800690
691 Note that if no primary address exists for the interface selected,
692 then the primary address of the first non-loopback interface that
Matt LaPlanted6bc8ac2006-10-03 22:54:15 +0200693 has one will be used regardless of this setting.
Horms95f7daf2006-02-02 17:02:25 -0800694
695 Default: 0
696
Linus Torvalds1da177e2005-04-16 15:20:36 -0700697igmp_max_memberships - INTEGER
698 Change the maximum number of multicast groups we can subscribe to.
699 Default: 20
700
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000701conf/interface/* changes special settings per interface (where "interface" is
Linus Torvalds1da177e2005-04-16 15:20:36 -0700702 the name of your network interface)
703conf/all/* is special, changes the settings for all interfaces
704
705
706log_martians - BOOLEAN
707 Log packets with impossible addresses to kernel log.
708 log_martians for the interface will be enabled if at least one of
709 conf/{all,interface}/log_martians is set to TRUE,
710 it will be disabled otherwise
711
712accept_redirects - BOOLEAN
713 Accept ICMP redirect messages.
714 accept_redirects for the interface will be enabled if:
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000715 - both conf/{all,interface}/accept_redirects are TRUE in the case
716 forwarding for the interface is enabled
Linus Torvalds1da177e2005-04-16 15:20:36 -0700717 or
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000718 - at least one of conf/{all,interface}/accept_redirects is TRUE in the
719 case forwarding for the interface is disabled
Linus Torvalds1da177e2005-04-16 15:20:36 -0700720 accept_redirects for the interface will be disabled otherwise
721 default TRUE (host)
722 FALSE (router)
723
724forwarding - BOOLEAN
725 Enable IP forwarding on this interface.
726
727mc_forwarding - BOOLEAN
728 Do multicast routing. The kernel needs to be compiled with CONFIG_MROUTE
729 and a multicast routing daemon is required.
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000730 conf/all/mc_forwarding must also be set to TRUE to enable multicast
731 routing for the interface
Linus Torvalds1da177e2005-04-16 15:20:36 -0700732
733medium_id - INTEGER
734 Integer value used to differentiate the devices by the medium they
735 are attached to. Two devices can have different id values when
736 the broadcast packets are received only on one of them.
737 The default value 0 means that the device is the only interface
738 to its medium, value of -1 means that medium is not known.
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000739
Linus Torvalds1da177e2005-04-16 15:20:36 -0700740 Currently, it is used to change the proxy_arp behavior:
741 the proxy_arp feature is enabled for packets forwarded between
742 two devices attached to different media.
743
744proxy_arp - BOOLEAN
745 Do proxy arp.
746 proxy_arp for the interface will be enabled if at least one of
747 conf/{all,interface}/proxy_arp is set to TRUE,
748 it will be disabled otherwise
749
Jesper Dangaard Brouer65324142010-01-05 05:50:47 +0000750proxy_arp_pvlan - BOOLEAN
751 Private VLAN proxy arp.
752 Basically allow proxy arp replies back to the same interface
753 (from which the ARP request/solicitation was received).
754
755 This is done to support (ethernet) switch features, like RFC
756 3069, where the individual ports are NOT allowed to
757 communicate with each other, but they are allowed to talk to
758 the upstream router. As described in RFC 3069, it is possible
759 to allow these hosts to communicate through the upstream
760 router by proxy_arp'ing. Don't need to be used together with
761 proxy_arp.
762
763 This technology is known by different names:
764 In RFC 3069 it is called VLAN Aggregation.
765 Cisco and Allied Telesyn call it Private VLAN.
766 Hewlett-Packard call it Source-Port filtering or port-isolation.
767 Ericsson call it MAC-Forced Forwarding (RFC Draft).
768
Linus Torvalds1da177e2005-04-16 15:20:36 -0700769shared_media - BOOLEAN
770 Send(router) or accept(host) RFC1620 shared media redirects.
771 Overrides ip_secure_redirects.
772 shared_media for the interface will be enabled if at least one of
773 conf/{all,interface}/shared_media is set to TRUE,
774 it will be disabled otherwise
775 default TRUE
776
777secure_redirects - BOOLEAN
778 Accept ICMP redirect messages only for gateways,
779 listed in default gateway list.
780 secure_redirects for the interface will be enabled if at least one of
781 conf/{all,interface}/secure_redirects is set to TRUE,
782 it will be disabled otherwise
783 default TRUE
784
785send_redirects - BOOLEAN
786 Send redirects, if router.
787 send_redirects for the interface will be enabled if at least one of
788 conf/{all,interface}/send_redirects is set to TRUE,
789 it will be disabled otherwise
790 Default: TRUE
791
792bootp_relay - BOOLEAN
793 Accept packets with source address 0.b.c.d destined
794 not to this host as local ones. It is supposed, that
795 BOOTP relay daemon will catch and forward such packets.
796 conf/all/bootp_relay must also be set to TRUE to enable BOOTP relay
797 for the interface
798 default FALSE
799 Not Implemented Yet.
800
801accept_source_route - BOOLEAN
802 Accept packets with SRR option.
803 conf/all/accept_source_route must also be set to TRUE to accept packets
804 with SRR option on the interface
805 default TRUE (router)
806 FALSE (host)
807
Patrick McHardy8153a102009-12-03 01:25:58 +0000808accept_local - BOOLEAN
809 Accept packets with local source addresses. In combination with
810 suitable routing, this can be used to direct packets between two
811 local interfaces over the wire and have them accepted properly.
812 default FALSE
813
Stephen Hemmingerc1cf8422009-02-20 08:25:36 +0000814rp_filter - INTEGER
Linus Torvalds1da177e2005-04-16 15:20:36 -0700815 0 - No source validation.
Stephen Hemmingerc1cf8422009-02-20 08:25:36 +0000816 1 - Strict mode as defined in RFC3704 Strict Reverse Path
817 Each incoming packet is tested against the FIB and if the interface
818 is not the best reverse path the packet check will fail.
819 By default failed packets are discarded.
820 2 - Loose mode as defined in RFC3704 Loose Reverse Path
821 Each incoming packet's source address is also tested against the FIB
822 and if the source address is not reachable via any interface
823 the packet check will fail.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700824
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000825 Current recommended practice in RFC3704 is to enable strict mode
Jesper Dangaard Brouerbf869c32009-02-23 04:37:55 +0000826 to prevent IP spoofing from DDos attacks. If using asymmetric routing
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000827 or other complicated routing, then loose mode is recommended.
Stephen Hemmingerc1cf8422009-02-20 08:25:36 +0000828
Shan Wei1f5865e2009-12-02 15:39:04 -0800829 The max value from conf/{all,interface}/rp_filter is used
830 when doing source validation on the {interface}.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700831
832 Default value is 0. Note that some distributions enable it
833 in startup scripts.
834
835arp_filter - BOOLEAN
836 1 - Allows you to have multiple network interfaces on the same
837 subnet, and have the ARPs for each interface be answered
838 based on whether or not the kernel would route a packet from
839 the ARP'd IP out that interface (therefore you must use source
840 based routing for this to work). In other words it allows control
841 of which cards (usually 1) will respond to an arp request.
842
843 0 - (default) The kernel can respond to arp requests with addresses
844 from other interfaces. This may seem wrong but it usually makes
845 sense, because it increases the chance of successful communication.
846 IP addresses are owned by the complete host on Linux, not by
847 particular interfaces. Only for more complex setups like load-
848 balancing, does this behaviour cause problems.
849
850 arp_filter for the interface will be enabled if at least one of
851 conf/{all,interface}/arp_filter is set to TRUE,
852 it will be disabled otherwise
853
854arp_announce - INTEGER
855 Define different restriction levels for announcing the local
856 source IP address from IP packets in ARP requests sent on
857 interface:
858 0 - (default) Use any local address, configured on any interface
859 1 - Try to avoid local addresses that are not in the target's
860 subnet for this interface. This mode is useful when target
861 hosts reachable via this interface require the source IP
862 address in ARP requests to be part of their logical network
863 configured on the receiving interface. When we generate the
864 request we will check all our subnets that include the
865 target IP and will preserve the source address if it is from
866 such subnet. If there is no such subnet we select source
867 address according to the rules for level 2.
868 2 - Always use the best local address for this target.
869 In this mode we ignore the source address in the IP packet
870 and try to select local address that we prefer for talks with
871 the target host. Such local address is selected by looking
872 for primary IP addresses on all our subnets on the outgoing
873 interface that include the target IP address. If no suitable
874 local address is found we select the first local address
875 we have on the outgoing interface or on all other interfaces,
876 with the hope we will receive reply for our request and
877 even sometimes no matter the source IP address we announce.
878
879 The max value from conf/{all,interface}/arp_announce is used.
880
881 Increasing the restriction level gives more chance for
882 receiving answer from the resolved target while decreasing
883 the level announces more valid sender's information.
884
885arp_ignore - INTEGER
886 Define different modes for sending replies in response to
887 received ARP requests that resolve local target IP addresses:
888 0 - (default): reply for any local target IP address, configured
889 on any interface
890 1 - reply only if the target IP address is local address
891 configured on the incoming interface
892 2 - reply only if the target IP address is local address
893 configured on the incoming interface and both with the
894 sender's IP address are part from same subnet on this interface
895 3 - do not reply for local addresses configured with scope host,
896 only resolutions for global and link addresses are replied
897 4-7 - reserved
898 8 - do not reply for all local addresses
899
900 The max value from conf/{all,interface}/arp_ignore is used
901 when ARP request is received on the {interface}
902
Stephen Hemmingereefef1c2009-02-01 01:04:33 -0800903arp_notify - BOOLEAN
904 Define mode for notification of address and device changes.
905 0 - (default): do nothing
Ian Campbell3f8dc232010-05-26 00:09:41 +0000906 1 - Generate gratuitous arp requests when device is brought up
Stephen Hemmingereefef1c2009-02-01 01:04:33 -0800907 or hardware address changes.
908
Neil Hormanc1b1bce2006-03-20 22:40:03 -0800909arp_accept - BOOLEAN
Octavian Purdila6d955182010-01-18 12:58:44 +0000910 Define behavior for gratuitous ARP frames who's IP is not
911 already present in the ARP table:
912 0 - don't create new entries in the ARP table
913 1 - create new entries in the ARP table
914
915 Both replies and requests type gratuitous arp will trigger the
916 ARP table to be updated, if this setting is on.
917
918 If the ARP table already contains the IP address of the
919 gratuitous arp frame, the arp table will be updated regardless
920 if this setting is on or off.
921
Neil Hormanc1b1bce2006-03-20 22:40:03 -0800922
Linus Torvalds1da177e2005-04-16 15:20:36 -0700923app_solicit - INTEGER
924 The maximum number of probes to send to the user space ARP daemon
925 via netlink before dropping back to multicast probes (see
926 mcast_solicit). Defaults to 0.
927
928disable_policy - BOOLEAN
929 Disable IPSEC policy (SPD) for this interface
930
931disable_xfrm - BOOLEAN
932 Disable IPSEC encryption on this interface, whatever the policy
933
934
935
936tag - INTEGER
937 Allows you to write a number, which can be used as required.
938 Default value is 0.
939
Linus Torvalds1da177e2005-04-16 15:20:36 -0700940Alexey Kuznetsov.
941kuznet@ms2.inr.ac.ru
942
943Updated by:
944Andi Kleen
945ak@muc.de
946Nicolas Delon
947delon.nicolas@wanadoo.fr
948
949
950
951
952/proc/sys/net/ipv6/* Variables:
953
954IPv6 has no global variables such as tcp_*. tcp_* settings under ipv4/ also
955apply to IPv6 [XXX?].
956
957bindv6only - BOOLEAN
958 Default value for IPV6_V6ONLY socket option,
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000959 which restricts use of the IPv6 socket to IPv6 communication
Linus Torvalds1da177e2005-04-16 15:20:36 -0700960 only.
961 TRUE: disable IPv4-mapped address feature
962 FALSE: enable IPv4-mapped address feature
963
964 Default: FALSE (as specified in RFC2553bis)
965
966IPv6 Fragmentation:
967
968ip6frag_high_thresh - INTEGER
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000969 Maximum memory used to reassemble IPv6 fragments. When
Linus Torvalds1da177e2005-04-16 15:20:36 -0700970 ip6frag_high_thresh bytes of memory is allocated for this purpose,
971 the fragment handler will toss packets until ip6frag_low_thresh
972 is reached.
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000973
Linus Torvalds1da177e2005-04-16 15:20:36 -0700974ip6frag_low_thresh - INTEGER
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000975 See ip6frag_high_thresh
Linus Torvalds1da177e2005-04-16 15:20:36 -0700976
977ip6frag_time - INTEGER
978 Time in seconds to keep an IPv6 fragment in memory.
979
980ip6frag_secret_interval - INTEGER
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000981 Regeneration interval (in seconds) of the hash secret (or lifetime
Linus Torvalds1da177e2005-04-16 15:20:36 -0700982 for the hash secret) for IPv6 fragments.
983 Default: 600
984
985conf/default/*:
986 Change the interface-specific default settings.
987
988
989conf/all/*:
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000990 Change all the interface-specific settings.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700991
992 [XXX: Other special features than forwarding?]
993
994conf/all/forwarding - BOOLEAN
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000995 Enable global IPv6 forwarding between all interfaces.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700996
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +0000997 IPv4 and IPv6 work differently here; e.g. netfilter must be used
Linus Torvalds1da177e2005-04-16 15:20:36 -0700998 to control which interfaces may forward packets and which not.
999
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +00001000 This also sets all interfaces' Host/Router setting
Linus Torvalds1da177e2005-04-16 15:20:36 -07001001 'forwarding' to the specified value. See below for details.
1002
1003 This referred to as global forwarding.
1004
YOSHIFUJI Hideakifbea49e2006-09-22 14:43:49 -07001005proxy_ndp - BOOLEAN
1006 Do proxy ndp.
1007
Linus Torvalds1da177e2005-04-16 15:20:36 -07001008conf/interface/*:
1009 Change special settings per interface.
1010
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +00001011 The functional behaviour for certain settings is different
Linus Torvalds1da177e2005-04-16 15:20:36 -07001012 depending on whether local forwarding is enabled or not.
1013
1014accept_ra - BOOLEAN
1015 Accept Router Advertisements; autoconfigure using them.
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +00001016
Thomas Grafae8abfa2010-09-03 05:47:30 +00001017 Possible values are:
1018 0 Do not accept Router Advertisements.
1019 1 Accept Router Advertisements if forwarding is disabled.
1020 2 Overrule forwarding behaviour. Accept Router Advertisements
1021 even if forwarding is enabled.
1022
Linus Torvalds1da177e2005-04-16 15:20:36 -07001023 Functional default: enabled if local forwarding is disabled.
1024 disabled if local forwarding is enabled.
1025
YOSHIFUJI Hideaki65f5c7c2006-03-20 16:55:08 -08001026accept_ra_defrtr - BOOLEAN
1027 Learn default router in Router Advertisement.
1028
1029 Functional default: enabled if accept_ra is enabled.
1030 disabled if accept_ra is disabled.
1031
YOSHIFUJI Hideakic4fd30e2006-03-20 16:55:26 -08001032accept_ra_pinfo - BOOLEAN
Matt LaPlante2fe0ae72006-10-03 22:50:39 +02001033 Learn Prefix Information in Router Advertisement.
YOSHIFUJI Hideakic4fd30e2006-03-20 16:55:26 -08001034
1035 Functional default: enabled if accept_ra is enabled.
1036 disabled if accept_ra is disabled.
1037
YOSHIFUJI Hideaki09c884d2006-03-20 17:07:03 -08001038accept_ra_rt_info_max_plen - INTEGER
1039 Maximum prefix length of Route Information in RA.
1040
1041 Route Information w/ prefix larger than or equal to this
1042 variable shall be ignored.
1043
1044 Functional default: 0 if accept_ra_rtr_pref is enabled.
1045 -1 if accept_ra_rtr_pref is disabled.
1046
YOSHIFUJI Hideaki930d6ff2006-03-20 17:05:30 -08001047accept_ra_rtr_pref - BOOLEAN
1048 Accept Router Preference in RA.
1049
1050 Functional default: enabled if accept_ra is enabled.
1051 disabled if accept_ra is disabled.
1052
Linus Torvalds1da177e2005-04-16 15:20:36 -07001053accept_redirects - BOOLEAN
1054 Accept Redirects.
1055
1056 Functional default: enabled if local forwarding is disabled.
1057 disabled if local forwarding is enabled.
1058
YOSHIFUJI Hideaki0bcbc922007-04-24 14:58:30 -07001059accept_source_route - INTEGER
1060 Accept source routing (routing extension header).
1061
YOSHIFUJI Hideakibb4dbf92007-07-10 22:55:49 -07001062 >= 0: Accept only routing header type 2.
YOSHIFUJI Hideaki0bcbc922007-04-24 14:58:30 -07001063 < 0: Do not accept routing header.
1064
1065 Default: 0
1066
Linus Torvalds1da177e2005-04-16 15:20:36 -07001067autoconf - BOOLEAN
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +00001068 Autoconfigure addresses using Prefix Information in Router
Linus Torvalds1da177e2005-04-16 15:20:36 -07001069 Advertisements.
1070
YOSHIFUJI Hideakic4fd30e2006-03-20 16:55:26 -08001071 Functional default: enabled if accept_ra_pinfo is enabled.
1072 disabled if accept_ra_pinfo is disabled.
Linus Torvalds1da177e2005-04-16 15:20:36 -07001073
1074dad_transmits - INTEGER
1075 The amount of Duplicate Address Detection probes to send.
1076 Default: 1
Linus Torvalds1da177e2005-04-16 15:20:36 -07001077
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +00001078forwarding - BOOLEAN
1079 Configure interface-specific Host/Router behaviour.
1080
1081 Note: It is recommended to have the same setting on all
Linus Torvalds1da177e2005-04-16 15:20:36 -07001082 interfaces; mixed router/host scenarios are rather uncommon.
1083
Thomas Grafae8abfa2010-09-03 05:47:30 +00001084 Possible values are:
1085 0 Forwarding disabled
1086 1 Forwarding enabled
1087 2 Forwarding enabled (Hybrid Mode)
1088
1089 FALSE (0):
Linus Torvalds1da177e2005-04-16 15:20:36 -07001090
1091 By default, Host behaviour is assumed. This means:
1092
1093 1. IsRouter flag is not set in Neighbour Advertisements.
1094 2. Router Solicitations are being sent when necessary.
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +00001095 3. If accept_ra is TRUE (default), accept Router
Linus Torvalds1da177e2005-04-16 15:20:36 -07001096 Advertisements (and do autoconfiguration).
1097 4. If accept_redirects is TRUE (default), accept Redirects.
1098
Thomas Grafae8abfa2010-09-03 05:47:30 +00001099 TRUE (1):
Linus Torvalds1da177e2005-04-16 15:20:36 -07001100
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +00001101 If local forwarding is enabled, Router behaviour is assumed.
Linus Torvalds1da177e2005-04-16 15:20:36 -07001102 This means exactly the reverse from the above:
1103
1104 1. IsRouter flag is set in Neighbour Advertisements.
1105 2. Router Solicitations are not sent.
Thomas Grafae8abfa2010-09-03 05:47:30 +00001106 3. Router Advertisements are ignored unless accept_ra is 2.
Linus Torvalds1da177e2005-04-16 15:20:36 -07001107 4. Redirects are ignored.
1108
Thomas Grafae8abfa2010-09-03 05:47:30 +00001109 TRUE (2):
1110
1111 Hybrid mode. Same behaviour as TRUE, except for:
1112
1113 2. Router Solicitations are being sent when necessary.
1114
1115 Default: 0 (disabled) if global forwarding is disabled (default),
1116 otherwise 1 (enabled).
Linus Torvalds1da177e2005-04-16 15:20:36 -07001117
1118hop_limit - INTEGER
1119 Default Hop Limit to set.
1120 Default: 64
1121
1122mtu - INTEGER
1123 Default Maximum Transfer Unit
1124 Default: 1280 (IPv6 required minimum)
1125
YOSHIFUJI Hideaki52e163562006-03-20 17:05:47 -08001126router_probe_interval - INTEGER
1127 Minimum interval (in seconds) between Router Probing described
1128 in RFC4191.
1129
1130 Default: 60
1131
Linus Torvalds1da177e2005-04-16 15:20:36 -07001132router_solicitation_delay - INTEGER
1133 Number of seconds to wait after interface is brought up
1134 before sending Router Solicitations.
1135 Default: 1
1136
1137router_solicitation_interval - INTEGER
1138 Number of seconds to wait between Router Solicitations.
1139 Default: 4
1140
1141router_solicitations - INTEGER
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +00001142 Number of Router Solicitations to send until assuming no
Linus Torvalds1da177e2005-04-16 15:20:36 -07001143 routers are present.
1144 Default: 3
1145
1146use_tempaddr - INTEGER
1147 Preference for Privacy Extensions (RFC3041).
1148 <= 0 : disable Privacy Extensions
1149 == 1 : enable Privacy Extensions, but prefer public
1150 addresses over temporary addresses.
1151 > 1 : enable Privacy Extensions and prefer temporary
1152 addresses over public addresses.
1153 Default: 0 (for most devices)
1154 -1 (for point-to-point devices and loopback devices)
1155
1156temp_valid_lft - INTEGER
1157 valid lifetime (in seconds) for temporary addresses.
1158 Default: 604800 (7 days)
1159
1160temp_prefered_lft - INTEGER
1161 Preferred lifetime (in seconds) for temporary addresses.
1162 Default: 86400 (1 day)
1163
1164max_desync_factor - INTEGER
1165 Maximum value for DESYNC_FACTOR, which is a random value
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +00001166 that ensures that clients don't synchronize with each
Linus Torvalds1da177e2005-04-16 15:20:36 -07001167 other and generate new addresses at exactly the same time.
1168 value is in seconds.
1169 Default: 600
Jesper Dangaard Brouere18f5fe2009-02-23 04:39:04 +00001170
Linus Torvalds1da177e2005-04-16 15:20:36 -07001171regen_max_retry - INTEGER
1172 Number of attempts before give up attempting to generate
1173 valid temporary addresses.
1174 Default: 5
1175
1176max_addresses - INTEGER
Brian Haleye79dc482010-02-22 12:27:21 +00001177 Maximum number of autoconfigured addresses per interface. Setting
1178 to zero disables the limitation. It is not recommended to set this
1179 value too large (or to zero) because it would be an easy way to
1180 crash the kernel by allowing too many addresses to be created.
Linus Torvalds1da177e2005-04-16 15:20:36 -07001181 Default: 16
1182
YOSHIFUJI Hideaki778d80b2008-06-28 14:17:11 +09001183disable_ipv6 - BOOLEAN
Brian Haley9bdd8d42009-03-18 18:22:48 -07001184 Disable IPv6 operation. If accept_dad is set to 2, this value
1185 will be dynamically set to TRUE if DAD fails for the link-local
1186 address.
YOSHIFUJI Hideaki778d80b2008-06-28 14:17:11 +09001187 Default: FALSE (enable IPv6 operation)
1188
Brian Haley56d417b2009-06-01 03:07:33 -07001189 When this value is changed from 1 to 0 (IPv6 is being enabled),
1190 it will dynamically create a link-local address on the given
1191 interface and start Duplicate Address Detection, if necessary.
1192
1193 When this value is changed from 0 to 1 (IPv6 is being disabled),
1194 it will dynamically delete all address on the given interface.
1195
YOSHIFUJI Hideaki1b34be72008-06-28 14:18:38 +09001196accept_dad - INTEGER
1197 Whether to accept DAD (Duplicate Address Detection).
1198 0: Disable DAD
1199 1: Enable DAD (default)
1200 2: Enable DAD, and disable IPv6 operation if MAC-based duplicate
1201 link-local address has been found.
1202
Octavian Purdilaf7734fd2009-10-02 11:39:15 +00001203force_tllao - BOOLEAN
1204 Enable sending the target link-layer address option even when
1205 responding to a unicast neighbor solicitation.
1206 Default: FALSE
1207
1208 Quoting from RFC 2461, section 4.4, Target link-layer address:
1209
1210 "The option MUST be included for multicast solicitations in order to
1211 avoid infinite Neighbor Solicitation "recursion" when the peer node
1212 does not have a cache entry to return a Neighbor Advertisements
1213 message. When responding to unicast solicitations, the option can be
1214 omitted since the sender of the solicitation has the correct link-
1215 layer address; otherwise it would not have be able to send the unicast
1216 solicitation in the first place. However, including the link-layer
1217 address in this case adds little overhead and eliminates a potential
1218 race condition where the sender deletes the cached link-layer address
1219 prior to receiving a response to a previous solicitation."
1220
Linus Torvalds1da177e2005-04-16 15:20:36 -07001221icmp/*:
1222ratelimit - INTEGER
1223 Limit the maximal rates for sending ICMPv6 packets.
Stephen Hemminger6dbf4bc2008-07-01 19:29:07 -07001224 0 to disable any limiting,
1225 otherwise the minimal space between responses in milliseconds.
1226 Default: 1000
Linus Torvalds1da177e2005-04-16 15:20:36 -07001227
1228
1229IPv6 Update by:
1230Pekka Savola <pekkas@netcore.fi>
1231YOSHIFUJI Hideaki / USAGI Project <yoshfuji@linux-ipv6.org>
1232
1233
1234/proc/sys/net/bridge/* Variables:
1235
1236bridge-nf-call-arptables - BOOLEAN
1237 1 : pass bridged ARP traffic to arptables' FORWARD chain.
1238 0 : disable this.
1239 Default: 1
1240
1241bridge-nf-call-iptables - BOOLEAN
1242 1 : pass bridged IPv4 traffic to iptables' chains.
1243 0 : disable this.
1244 Default: 1
1245
1246bridge-nf-call-ip6tables - BOOLEAN
1247 1 : pass bridged IPv6 traffic to ip6tables' chains.
1248 0 : disable this.
1249 Default: 1
1250
1251bridge-nf-filter-vlan-tagged - BOOLEAN
Michael Milner516299d2007-04-12 22:14:23 -07001252 1 : pass bridged vlan-tagged ARP/IP/IPv6 traffic to {arp,ip,ip6}tables.
1253 0 : disable this.
1254 Default: 1
1255
1256bridge-nf-filter-pppoe-tagged - BOOLEAN
1257 1 : pass bridged pppoe-tagged IP/IPv6 traffic to {ip,ip6}tables.
Linus Torvalds1da177e2005-04-16 15:20:36 -07001258 0 : disable this.
1259 Default: 1
1260
1261
Vlad Yasevich32e8d492008-07-08 16:43:29 -07001262proc/sys/net/sctp/* Variables:
1263
1264addip_enable - BOOLEAN
1265 Enable or disable extension of Dynamic Address Reconfiguration
1266 (ADD-IP) functionality specified in RFC5061. This extension provides
1267 the ability to dynamically add and remove new addresses for the SCTP
1268 associations.
1269
1270 1: Enable extension.
1271
1272 0: Disable extension.
1273
1274 Default: 0
1275
1276addip_noauth_enable - BOOLEAN
1277 Dynamic Address Reconfiguration (ADD-IP) requires the use of
1278 authentication to protect the operations of adding or removing new
1279 addresses. This requirement is mandated so that unauthorized hosts
1280 would not be able to hijack associations. However, older
1281 implementations may not have implemented this requirement while
1282 allowing the ADD-IP extension. For reasons of interoperability,
1283 we provide this variable to control the enforcement of the
1284 authentication requirement.
1285
1286 1: Allow ADD-IP extension to be used without authentication. This
1287 should only be set in a closed environment for interoperability
1288 with older implementations.
1289
1290 0: Enforce the authentication requirement
1291
1292 Default: 0
1293
1294auth_enable - BOOLEAN
1295 Enable or disable Authenticated Chunks extension. This extension
1296 provides the ability to send and receive authenticated chunks and is
1297 required for secure operation of Dynamic Address Reconfiguration
1298 (ADD-IP) extension.
1299
1300 1: Enable this extension.
1301 0: Disable this extension.
1302
1303 Default: 0
1304
1305prsctp_enable - BOOLEAN
1306 Enable or disable the Partial Reliability extension (RFC3758) which
1307 is used to notify peers that a given DATA should no longer be expected.
1308
1309 1: Enable extension
1310 0: Disable
1311
1312 Default: 1
1313
1314max_burst - INTEGER
1315 The limit of the number of new packets that can be initially sent. It
1316 controls how bursty the generated traffic can be.
1317
1318 Default: 4
1319
1320association_max_retrans - INTEGER
1321 Set the maximum number for retransmissions that an association can
1322 attempt deciding that the remote end is unreachable. If this value
1323 is exceeded, the association is terminated.
1324
1325 Default: 10
1326
1327max_init_retransmits - INTEGER
1328 The maximum number of retransmissions of INIT and COOKIE-ECHO chunks
1329 that an association will attempt before declaring the destination
1330 unreachable and terminating.
1331
1332 Default: 8
1333
1334path_max_retrans - INTEGER
1335 The maximum number of retransmissions that will be attempted on a given
1336 path. Once this threshold is exceeded, the path is considered
1337 unreachable, and new traffic will use a different path when the
1338 association is multihomed.
1339
1340 Default: 5
1341
1342rto_initial - INTEGER
1343 The initial round trip timeout value in milliseconds that will be used
1344 in calculating round trip times. This is the initial time interval
1345 for retransmissions.
1346
1347 Default: 3000
1348
1349rto_max - INTEGER
1350 The maximum value (in milliseconds) of the round trip timeout. This
1351 is the largest time interval that can elapse between retransmissions.
1352
1353 Default: 60000
1354
1355rto_min - INTEGER
1356 The minimum value (in milliseconds) of the round trip timeout. This
1357 is the smallest time interval the can elapse between retransmissions.
1358
1359 Default: 1000
1360
1361hb_interval - INTEGER
1362 The interval (in milliseconds) between HEARTBEAT chunks. These chunks
1363 are sent at the specified interval on idle paths to probe the state of
1364 a given path between 2 associations.
1365
1366 Default: 30000
1367
1368sack_timeout - INTEGER
1369 The amount of time (in milliseconds) that the implementation will wait
1370 to send a SACK.
1371
1372 Default: 200
1373
1374valid_cookie_life - INTEGER
1375 The default lifetime of the SCTP cookie (in milliseconds). The cookie
1376 is used during association establishment.
1377
1378 Default: 60000
1379
1380cookie_preserve_enable - BOOLEAN
1381 Enable or disable the ability to extend the lifetime of the SCTP cookie
1382 that is used during the establishment phase of SCTP association
1383
1384 1: Enable cookie lifetime extension.
1385 0: Disable
1386
1387 Default: 1
1388
1389rcvbuf_policy - INTEGER
1390 Determines if the receive buffer is attributed to the socket or to
1391 association. SCTP supports the capability to create multiple
1392 associations on a single socket. When using this capability, it is
1393 possible that a single stalled association that's buffering a lot
1394 of data may block other associations from delivering their data by
1395 consuming all of the receive buffer space. To work around this,
1396 the rcvbuf_policy could be set to attribute the receiver buffer space
1397 to each association instead of the socket. This prevents the described
1398 blocking.
1399
1400 1: rcvbuf space is per association
1401 0: recbuf space is per socket
1402
1403 Default: 0
1404
1405sndbuf_policy - INTEGER
1406 Similar to rcvbuf_policy above, this applies to send buffer space.
1407
1408 1: Send buffer is tracked per association
1409 0: Send buffer is tracked per socket.
1410
1411 Default: 0
1412
1413sctp_mem - vector of 3 INTEGERs: min, pressure, max
1414 Number of pages allowed for queueing by all SCTP sockets.
1415
1416 min: Below this number of pages SCTP is not bothered about its
1417 memory appetite. When amount of memory allocated by SCTP exceeds
1418 this number, SCTP starts to moderate memory usage.
1419
1420 pressure: This value was introduced to follow format of tcp_mem.
1421
1422 max: Number of pages allowed for queueing by all SCTP sockets.
1423
1424 Default is calculated at boot time from amount of available memory.
1425
1426sctp_rmem - vector of 3 INTEGERs: min, default, max
1427 See tcp_rmem for a description.
1428
1429sctp_wmem - vector of 3 INTEGERs: min, default, max
1430 See tcp_wmem for a description.
1431
Bhaskar Dutta72388432009-09-03 17:25:47 +05301432addr_scope_policy - INTEGER
1433 Control IPv4 address scoping - draft-stewart-tsvwg-sctp-ipv4-00
1434
1435 0 - Disable IPv4 address scoping
1436 1 - Enable IPv4 address scoping
1437 2 - Follow draft but allow IPv4 private addresses
1438 3 - Follow draft but allow IPv4 link local addresses
1439
1440 Default: 1
1441
Linus Torvalds1da177e2005-04-16 15:20:36 -07001442
Stephen Hemminger4edc2f32008-07-10 16:50:26 -07001443/proc/sys/net/core/*
Wang Tinggong705efc32009-05-14 22:49:36 +00001444dev_weight - INTEGER
1445 The maximum number of packets that kernel can handle on a NAPI
1446 interrupt, it's a Per-CPU variable.
1447
1448 Default: 64
Linus Torvalds1da177e2005-04-16 15:20:36 -07001449
Stephen Hemminger4edc2f32008-07-10 16:50:26 -07001450/proc/sys/net/unix/*
Wang Tinggong705efc32009-05-14 22:49:36 +00001451max_dgram_qlen - INTEGER
1452 The maximum length of dgram socket receive queue
1453
1454 Default: 10
1455
1456
1457UNDOCUMENTED:
Stephen Hemminger4edc2f32008-07-10 16:50:26 -07001458
1459/proc/sys/net/irda/*
1460 fast_poll_increase FIXME
1461 warn_noreply_time FIXME
1462 discovery_slots FIXME
1463 slot_timeout FIXME
1464 max_baud_rate FIXME
1465 discovery_timeout FIXME
1466 lap_keepalive_time FIXME
1467 max_noreply_time FIXME
1468 max_tx_data_size FIXME
1469 max_tx_window FIXME
1470 min_tx_turn_time FIXME