1 /proc/sys/net/ipv4/* Variables:
7 Forward Packets between interfaces.
9 This variable is special, its change resets all configuration
10 parameters to their default state (RFC1122 for hosts, RFC1812
13 ip_default_ttl - INTEGER
14 Default value of TTL field (Time To Live) for outgoing (but not
15 forwarded) IP packets. Should be between 1 and 255 inclusive.
16 Default: 64 (as recommended by RFC1700)
18 ip_no_pmtu_disc - BOOLEAN
19 Disable Path MTU Discovery.
23 default 552 - minimum discovered Path MTU
25 route/max_size - INTEGER
26 Maximum number of routes allowed in the kernel. Increase
27 this when using large numbers of interfaces and/or routes.
29 neigh/default/gc_thresh1 - INTEGER
30 Minimum number of entries to keep. Garbage collector will not
31 purge entries if there are fewer than this number.
34 neigh/default/gc_thresh3 - INTEGER
35 Maximum number of neighbor entries allowed. Increase this
36 when using large numbers of interfaces and when communicating
37 with large numbers of directly-connected peers.
40 neigh/default/unres_qlen_bytes - INTEGER
41 The maximum number of bytes which may be used by packets
42 queued for each unresolved address by other network layers.
44 Setting negative value is meaningless and will return error.
45 Default: 65536 Bytes(64KB)
47 neigh/default/unres_qlen - INTEGER
48 The maximum number of packets which may be queued for each
49 unresolved address by other network layers.
50 (deprecated in linux 3.3) : use unres_qlen_bytes instead.
51 Prior to linux 3.3, the default value is 3 which may cause
52 unexpected packet loss. The current default value is calculated
53 according to default value of unres_qlen_bytes and true size of
58 Time, in seconds, that cached PMTU information is kept.
61 The advertised MSS depends on the first hop route MTU, but will
62 never be lower than this setting.
66 ipfrag_high_thresh - INTEGER
67 Maximum memory used to reassemble IP fragments. When
68 ipfrag_high_thresh bytes of memory is allocated for this purpose,
69 the fragment handler will toss packets until ipfrag_low_thresh
72 ipfrag_low_thresh - INTEGER
73 See ipfrag_high_thresh
76 Time in seconds to keep an IP fragment in memory.
78 ipfrag_secret_interval - INTEGER
79 Regeneration interval (in seconds) of the hash secret (or lifetime
80 for the hash secret) for IP fragments.
83 ipfrag_max_dist - INTEGER
84 ipfrag_max_dist is a non-negative integer value which defines the
85 maximum "disorder" which is allowed among fragments which share a
86 common IP source address. Note that reordering of packets is
87 not unusual, but if a large number of fragments arrive from a source
88 IP address while a particular fragment queue remains incomplete, it
89 probably indicates that one or more fragments belonging to that queue
90 have been lost. When ipfrag_max_dist is positive, an additional check
91 is done on fragments before they are added to a reassembly queue - if
92 ipfrag_max_dist (or more) fragments have arrived from a particular IP
93 address between additions to any IP fragment queue using that source
94 address, it's presumed that one or more fragments in the queue are
95 lost. The existing fragment queue will be dropped, and a new one
96 started. An ipfrag_max_dist value of zero disables this check.
98 Using a very small value, e.g. 1 or 2, for ipfrag_max_dist can
99 result in unnecessarily dropping fragment queues when normal
100 reordering of packets occurs, which could lead to poor application
101 performance. Using a very large value, e.g. 50000, increases the
102 likelihood of incorrectly reassembling IP fragments that originate
103 from different IP datagrams, which could result in data corruption.
108 inet_peer_threshold - INTEGER
109 The approximate size of the storage. Starting from this threshold
110 entries will be thrown aggressively. This threshold also determines
111 entries' time-to-live and time intervals between garbage collection
112 passes. More entries, less time-to-live, less GC interval.
114 inet_peer_minttl - INTEGER
115 Minimum time-to-live of entries. Should be enough to cover fragment
116 time-to-live on the reassembling side. This minimum time-to-live is
117 guaranteed if the pool size is less than inet_peer_threshold.
120 inet_peer_maxttl - INTEGER
121 Maximum time-to-live of entries. Unused entries will expire after
122 this period of time if there is no memory pressure on the pool (i.e.
123 when the number of entries in the pool is very small).
129 Limit of socket listen() backlog, known in userspace as SOMAXCONN.
130 Defaults to 128. See also tcp_max_syn_backlog for additional tuning
133 tcp_abort_on_overflow - BOOLEAN
134 If listening service is too slow to accept new connections,
135 reset them. Default state is FALSE. It means that if overflow
136 occurred due to a burst, connection will recover. Enable this
137 option _only_ if you are really sure that listening daemon
138 cannot be tuned to accept connections faster. Enabling this
139 option can harm clients of your server.
141 tcp_adv_win_scale - INTEGER
142 Count buffering overhead as bytes/2^tcp_adv_win_scale
143 (if tcp_adv_win_scale > 0) or bytes-bytes/2^(-tcp_adv_win_scale),
145 Possible values are [-31, 31], inclusive.
148 tcp_allowed_congestion_control - STRING
149 Show/set the congestion control choices available to non-privileged
150 processes. The list is a subset of those listed in
151 tcp_available_congestion_control.
152 Default is "reno" and the default setting (tcp_congestion_control).
154 tcp_app_win - INTEGER
155 Reserve max(window/2^tcp_app_win, mss) of window for application
156 buffer. Value 0 is special, it means that nothing is reserved.
159 tcp_available_congestion_control - STRING
160 Shows the available congestion control choices that are registered.
161 More congestion control algorithms may be available as modules,
164 tcp_base_mss - INTEGER
165 The initial value of search_low to be used by the packetization layer
166 Path MTU discovery (MTU probing). If MTU probing is enabled,
167 this is the initial MSS used by the connection.
169 tcp_congestion_control - STRING
170 Set the congestion control algorithm to be used for new
171 connections. The algorithm "reno" is always available, but
172 additional choices may be available based on kernel configuration.
173 Default is set as part of kernel configuration.
174 For passive connections, the listener congestion control choice
176 [see setsockopt(listenfd, SOL_TCP, TCP_CONGESTION, "name" ...) ]
179 Allows TCP to send "duplicate" SACKs.
181 tcp_early_retrans - INTEGER
182 Enable Early Retransmit (ER), per RFC 5827. ER lowers the threshold
183 for triggering fast retransmit when the amount of outstanding data is
184 small and when no previously unsent data can be transmitted (such
185 that limited transmit could be used). Also controls the use of
186 Tail loss probe (TLP) that converts RTOs occurring due to tail
187 losses into fast recovery (draft-dukkipati-tcpm-tcp-loss-probe-01).
191 2 enables ER but delays fast recovery and fast retransmit
192 by a fourth of RTT. This mitigates connection falsely
193 recovers when network has a small degree of reordering
194 (less than 3 packets).
195 3 enables delayed ER and TLP.
200 Control use of Explicit Congestion Notification (ECN) by TCP.
201 ECN is used only when both ends of the TCP connection indicate
202 support for it. This feature is useful in avoiding losses due
203 to congestion by allowing supporting routers to signal
204 congestion before having to drop packets.
206 0 Disable ECN. Neither initiate nor accept ECN.
207 1 Enable ECN when requested by incoming connections and
208 also request ECN on outgoing connection attempts.
209 2 Enable ECN when requested by incoming connections
210 but do not request ECN on outgoing connections.
214 Enable FACK congestion avoidance and fast retransmission.
215 The value is not used, if tcp_sack is not enabled.
217 tcp_fin_timeout - INTEGER
218 The length of time an orphaned (no longer referenced by any
219 application) connection will remain in the FIN_WAIT_2 state
220 before it is aborted at the local end. While a perfectly
221 valid "receive only" state for an un-orphaned connection, an
222 orphaned connection in FIN_WAIT_2 state could otherwise wait
223 forever for the remote to close its end of the connection.
228 Enables Forward RTO-Recovery (F-RTO) defined in RFC5682.
229 F-RTO is an enhanced recovery algorithm for TCP retransmission
230 timeouts. It is particularly beneficial in networks where the
231 RTT fluctuates (e.g., wireless). F-RTO is sender-side only
232 modification. It does not require any support from the peer.
234 By default it's enabled with a non-zero value. 0 disables F-RTO.
236 tcp_keepalive_time - INTEGER
237 How often TCP sends out keepalive messages when keepalive is enabled.
240 tcp_keepalive_probes - INTEGER
241 How many keepalive probes TCP sends out, until it decides that the
242 connection is broken. Default value: 9.
244 tcp_keepalive_intvl - INTEGER
245 How frequently the probes are send out. Multiplied by
246 tcp_keepalive_probes it is time to kill not responding connection,
247 after probes started. Default value: 75sec i.e. connection
248 will be aborted after ~11 minutes of retries.
250 tcp_low_latency - BOOLEAN
251 If set, the TCP stack makes decisions that prefer lower
252 latency as opposed to higher throughput. By default, this
253 option is not set meaning that higher throughput is preferred.
254 An example of an application where this default should be
255 changed would be a Beowulf compute cluster.
258 tcp_max_orphans - INTEGER
259 Maximal number of TCP sockets not attached to any user file handle,
260 held by system. If this number is exceeded orphaned connections are
261 reset immediately and warning is printed. This limit exists
262 only to prevent simple DoS attacks, you _must_ not rely on this
263 or lower the limit artificially, but rather increase it
264 (probably, after increasing installed memory),
265 if network conditions require more than default value,
266 and tune network services to linger and kill such states
267 more aggressively. Let me to remind again: each orphan eats
268 up to ~64K of unswappable memory.
270 tcp_max_ssthresh - INTEGER
271 Limited Slow-Start for TCP with large congestion windows (cwnd) defined in
272 RFC3742. Limited slow-start is a mechanism to limit growth of the cwnd
273 on the region where cwnd is larger than tcp_max_ssthresh. TCP increases cwnd
274 by at most tcp_max_ssthresh segments, and by at least tcp_max_ssthresh/2
275 segments per RTT when the cwnd is above tcp_max_ssthresh.
276 If TCP connection increased cwnd to thousands (or tens of thousands) segments,
277 and thousands of packets were being dropped during slow-start, you can set
278 tcp_max_ssthresh to improve performance for new TCP connection.
281 tcp_max_syn_backlog - INTEGER
282 Maximal number of remembered connection requests, which have not
283 received an acknowledgment from connecting client.
284 The minimal value is 128 for low memory machines, and it will
285 increase in proportion to the memory of machine.
286 If server suffers from overload, try increasing this number.
288 tcp_max_tw_buckets - INTEGER
289 Maximal number of timewait sockets held by system simultaneously.
290 If this number is exceeded time-wait socket is immediately destroyed
291 and warning is printed. This limit exists only to prevent
292 simple DoS attacks, you _must_ not lower the limit artificially,
293 but rather increase it (probably, after increasing installed memory),
294 if network conditions require more than default value.
296 tcp_mem - vector of 3 INTEGERs: min, pressure, max
297 min: below this number of pages TCP is not bothered about its
300 pressure: when amount of memory allocated by TCP exceeds this number
301 of pages, TCP moderates its memory consumption and enters memory
302 pressure mode, which is exited when memory consumption falls
305 max: number of pages allowed for queueing by all TCP sockets.
307 Defaults are calculated at boot time from amount of available
310 tcp_moderate_rcvbuf - BOOLEAN
311 If set, TCP performs receive buffer auto-tuning, attempting to
312 automatically size the buffer (no greater than tcp_rmem[2]) to
313 match the size required by the path for full throughput. Enabled by
316 tcp_mtu_probing - INTEGER
317 Controls TCP Packetization-Layer Path MTU Discovery. Takes three
320 1 - Disabled by default, enabled when an ICMP black hole detected
321 2 - Always enabled, use initial MSS of tcp_base_mss.
323 tcp_no_metrics_save - BOOLEAN
324 By default, TCP saves various connection metrics in the route cache
325 when the connection closes, so that connections established in the
326 near future can use these to set initial conditions. Usually, this
327 increases overall performance, but may sometimes cause performance
328 degradation. If set, TCP will not cache metrics on closing
331 tcp_orphan_retries - INTEGER
332 This value influences the timeout of a locally closed TCP connection,
333 when RTO retransmissions remain unacknowledged.
334 See tcp_retries2 for more details.
336 The default value is 8.
337 If your machine is a loaded WEB server,
338 you should think about lowering this value, such sockets
339 may consume significant resources. Cf. tcp_max_orphans.
341 tcp_reordering - INTEGER
342 Maximal reordering of packets in a TCP stream.
345 tcp_retrans_collapse - BOOLEAN
346 Bug-to-bug compatibility with some broken printers.
347 On retransmit try to send bigger packets to work around bugs in
350 tcp_retries1 - INTEGER
351 This value influences the time, after which TCP decides, that
352 something is wrong due to unacknowledged RTO retransmissions,
353 and reports this suspicion to the network layer.
354 See tcp_retries2 for more details.
356 RFC 1122 recommends at least 3 retransmissions, which is the
359 tcp_retries2 - INTEGER
360 This value influences the timeout of an alive TCP connection,
361 when RTO retransmissions remain unacknowledged.
362 Given a value of N, a hypothetical TCP connection following
363 exponential backoff with an initial RTO of TCP_RTO_MIN would
364 retransmit N times before killing the connection at the (N+1)th RTO.
366 The default value of 15 yields a hypothetical timeout of 924.6
367 seconds and is a lower bound for the effective timeout.
368 TCP will effectively time out at the first RTO which exceeds the
369 hypothetical timeout.
371 RFC 1122 recommends at least 100 seconds for the timeout,
372 which corresponds to a value of at least 8.
374 tcp_rfc1337 - BOOLEAN
375 If set, the TCP stack behaves conforming to RFC1337. If unset,
376 we are not conforming to RFC, but prevent TCP TIME_WAIT
380 tcp_rmem - vector of 3 INTEGERs: min, default, max
381 min: Minimal size of receive buffer used by TCP sockets.
382 It is guaranteed to each TCP socket, even under moderate memory
386 default: initial size of receive buffer used by TCP sockets.
387 This value overrides net.core.rmem_default used by other protocols.
388 Default: 87380 bytes. This value results in window of 65535 with
389 default setting of tcp_adv_win_scale and tcp_app_win:0 and a bit
390 less for default tcp_app_win. See below about these variables.
392 max: maximal size of receive buffer allowed for automatically
393 selected receiver buffers for TCP socket. This value does not override
394 net.core.rmem_max. Calling setsockopt() with SO_RCVBUF disables
395 automatic tuning of that socket's receive buffer size, in which
396 case this value is ignored.
397 Default: between 87380B and 6MB, depending on RAM size.
400 Enable select acknowledgments (SACKS).
402 tcp_slow_start_after_idle - BOOLEAN
403 If set, provide RFC2861 behavior and time out the congestion
404 window after an idle period. An idle period is defined at
405 the current RTO. If unset, the congestion window will not
406 be timed out after an idle period.
410 Use the Host requirements interpretation of the TCP urgent pointer field.
411 Most hosts use the older BSD interpretation, so if you turn this on
412 Linux might not communicate correctly with them.
415 tcp_synack_retries - INTEGER
416 Number of times SYNACKs for a passive TCP connection attempt will
417 be retransmitted. Should not be higher than 255. Default value
418 is 5, which corresponds to 31seconds till the last retransmission
419 with the current initial RTO of 1second. With this the final timeout
420 for a passive TCP connection will happen after 63seconds.
422 tcp_syncookies - BOOLEAN
423 Only valid when the kernel was compiled with CONFIG_SYN_COOKIES
424 Send out syncookies when the syn backlog queue of a socket
425 overflows. This is to prevent against the common 'SYN flood attack'
428 Note, that syncookies is fallback facility.
429 It MUST NOT be used to help highly loaded servers to stand
430 against legal connection rate. If you see SYN flood warnings
431 in your logs, but investigation shows that they occur
432 because of overload with legal connections, you should tune
433 another parameters until this warning disappear.
434 See: tcp_max_syn_backlog, tcp_synack_retries, tcp_abort_on_overflow.
436 syncookies seriously violate TCP protocol, do not allow
437 to use TCP extensions, can result in serious degradation
438 of some services (f.e. SMTP relaying), visible not by you,
439 but your clients and relays, contacting you. While you see
440 SYN flood warnings in logs not being really flooded, your server
441 is seriously misconfigured.
443 If you want to test which effects syncookies have to your
444 network connections you can set this knob to 2 to enable
445 unconditionally generation of syncookies.
447 tcp_fastopen - INTEGER
448 Enable TCP Fast Open feature (draft-ietf-tcpm-fastopen) to send data
449 in the opening SYN packet. To use this feature, the client application
450 must use sendmsg() or sendto() with MSG_FASTOPEN flag rather than
451 connect() to perform a TCP handshake automatically.
453 The values (bitmap) are
454 1: Enables sending data in the opening SYN on the client.
455 2: Enables TCP Fast Open on the server side, i.e., allowing data in
456 a SYN packet to be accepted and passed to the application before
457 3-way hand shake finishes.
458 4: Send data in the opening SYN regardless of cookie availability and
459 without a cookie option.
460 0x100: Accept SYN data w/o validating the cookie.
461 0x200: Accept data-in-SYN w/o any cookie option present.
462 0x400/0x800: Enable Fast Open on all listeners regardless of the
463 TCP_FASTOPEN socket option. The two different flags designate two
464 different ways of setting max_qlen without the TCP_FASTOPEN socket
469 Note that the client & server side Fast Open flags (1 and 2
470 respectively) must be also enabled before the rest of flags can take
473 See include/net/tcp.h and the code for more details.
475 tcp_syn_retries - INTEGER
476 Number of times initial SYNs for an active TCP connection attempt
477 will be retransmitted. Should not be higher than 255. Default value
478 is 6, which corresponds to 63seconds till the last retransmission
479 with the current initial RTO of 1second. With this the final timeout
480 for an active TCP connection attempt will happen after 127seconds.
482 tcp_timestamps - BOOLEAN
483 Enable timestamps as defined in RFC1323.
485 tcp_min_tso_segs - INTEGER
486 Minimal number of segments per TSO frame.
487 Since linux-3.12, TCP does an automatic sizing of TSO frames,
488 depending on flow rate, instead of filling 64Kbytes packets.
489 For specific usages, it's possible to force TCP to build big
490 TSO frames. Note that TCP stack might split too big TSO packets
491 if available window is too small.
494 tcp_tso_win_divisor - INTEGER
495 This allows control over what percentage of the congestion window
496 can be consumed by a single TSO frame.
497 The setting of this parameter is a choice between burstiness and
498 building larger TSO frames.
501 tcp_tw_recycle - BOOLEAN
502 Enable fast recycling TIME-WAIT sockets. Default value is 0.
503 It should not be changed without advice/request of technical
506 tcp_tw_reuse - BOOLEAN
507 Allow to reuse TIME-WAIT sockets for new connections when it is
508 safe from protocol viewpoint. Default value is 0.
509 It should not be changed without advice/request of technical
512 tcp_window_scaling - BOOLEAN
513 Enable window scaling as defined in RFC1323.
515 tcp_wmem - vector of 3 INTEGERs: min, default, max
516 min: Amount of memory reserved for send buffers for TCP sockets.
517 Each TCP socket has rights to use it due to fact of its birth.
520 default: initial size of send buffer used by TCP sockets. This
521 value overrides net.core.wmem_default used by other protocols.
522 It is usually lower than net.core.wmem_default.
525 max: Maximal amount of memory allowed for automatically tuned
526 send buffers for TCP sockets. This value does not override
527 net.core.wmem_max. Calling setsockopt() with SO_SNDBUF disables
528 automatic tuning of that socket's send buffer size, in which case
529 this value is ignored.
530 Default: between 64K and 4MB, depending on RAM size.
532 tcp_notsent_lowat - UNSIGNED INTEGER
533 A TCP socket can control the amount of unsent bytes in its write queue,
534 thanks to TCP_NOTSENT_LOWAT socket option. poll()/select()/epoll()
535 reports POLLOUT events if the amount of unsent bytes is below a per
536 socket value, and if the write queue is not full. sendmsg() will
537 also not add new buffers if the limit is hit.
539 This global variable controls the amount of unsent data for
540 sockets not using TCP_NOTSENT_LOWAT. For these sockets, a change
541 to the global variable has immediate effect.
543 Default: UINT_MAX (0xFFFFFFFF)
545 tcp_workaround_signed_windows - BOOLEAN
546 If set, assume no receipt of a window scaling option means the
547 remote TCP is broken and treats the window as a signed quantity.
548 If unset, assume the remote TCP is not broken even if we do
549 not receive a window scaling option from them.
552 tcp_dma_copybreak - INTEGER
553 Lower limit, in bytes, of the size of socket reads that will be
554 offloaded to a DMA copy engine, if one is present in the system
555 and CONFIG_NET_DMA is enabled.
558 tcp_thin_linear_timeouts - BOOLEAN
559 Enable dynamic triggering of linear timeouts for thin streams.
560 If set, a check is performed upon retransmission by timeout to
561 determine if the stream is thin (less than 4 packets in flight).
562 As long as the stream is found to be thin, up to 6 linear
563 timeouts may be performed before exponential backoff mode is
564 initiated. This improves retransmission latency for
565 non-aggressive thin streams, often found to be time-dependent.
566 For more information on thin streams, see
567 Documentation/networking/tcp-thin.txt
570 tcp_thin_dupack - BOOLEAN
571 Enable dynamic triggering of retransmissions after one dupACK
572 for thin streams. If set, a check is performed upon reception
573 of a dupACK to determine if the stream is thin (less than 4
574 packets in flight). As long as the stream is found to be thin,
575 data is retransmitted on the first received dupACK. This
576 improves retransmission latency for non-aggressive thin
577 streams, often found to be time-dependent.
578 For more information on thin streams, see
579 Documentation/networking/tcp-thin.txt
582 tcp_limit_output_bytes - INTEGER
583 Controls TCP Small Queue limit per tcp socket.
584 TCP bulk sender tends to increase packets in flight until it
585 gets losses notifications. With SNDBUF autotuning, this can
586 result in a large amount of packets queued in qdisc/device
587 on the local machine, hurting latency of other flows, for
588 typical pfifo_fast qdiscs.
589 tcp_limit_output_bytes limits the number of bytes on qdisc
590 or device to reduce artificial RTT/cwnd and reduce bufferbloat.
591 Note: For GSO/TSO enabled flows, we try to have at least two
592 packets in flight. Reducing tcp_limit_output_bytes might also
593 reduce the size of individual GSO packet (64KB being the max)
596 tcp_challenge_ack_limit - INTEGER
597 Limits number of Challenge ACK sent per second, as recommended
598 in RFC 5961 (Improving TCP's Robustness to Blind In-Window Attacks)
603 udp_mem - vector of 3 INTEGERs: min, pressure, max
604 Number of pages allowed for queueing by all UDP sockets.
606 min: Below this number of pages UDP is not bothered about its
607 memory appetite. When amount of memory allocated by UDP exceeds
608 this number, UDP starts to moderate memory usage.
610 pressure: This value was introduced to follow format of tcp_mem.
612 max: Number of pages allowed for queueing by all UDP sockets.
614 Default is calculated at boot time from amount of available memory.
616 udp_rmem_min - INTEGER
617 Minimal size of receive buffer used by UDP sockets in moderation.
618 Each UDP socket is able to use the size for receiving data, even if
619 total pages of UDP sockets exceed udp_mem pressure. The unit is byte.
622 udp_wmem_min - INTEGER
623 Minimal size of send buffer used by UDP sockets in moderation.
624 Each UDP socket is able to use the size for sending data, even if
625 total pages of UDP sockets exceed udp_mem pressure. The unit is byte.
630 cipso_cache_enable - BOOLEAN
631 If set, enable additions to and lookups from the CIPSO label mapping
632 cache. If unset, additions are ignored and lookups always result in a
633 miss. However, regardless of the setting the cache is still
634 invalidated when required when means you can safely toggle this on and
635 off and the cache will always be "safe".
638 cipso_cache_bucket_size - INTEGER
639 The CIPSO label cache consists of a fixed size hash table with each
640 hash bucket containing a number of cache entries. This variable limits
641 the number of entries in each hash bucket; the larger the value the
642 more CIPSO label mappings that can be cached. When the number of
643 entries in a given hash bucket reaches this limit adding new entries
644 causes the oldest entry in the bucket to be removed to make room.
647 cipso_rbm_optfmt - BOOLEAN
648 Enable the "Optimized Tag 1 Format" as defined in section 3.4.2.6 of
649 the CIPSO draft specification (see Documentation/netlabel for details).
650 This means that when set the CIPSO tag will be padded with empty
651 categories in order to make the packet data 32-bit aligned.
654 cipso_rbm_structvalid - BOOLEAN
655 If set, do a very strict check of the CIPSO option when
656 ip_options_compile() is called. If unset, relax the checks done during
657 ip_options_compile(). Either way is "safe" as errors are caught else
658 where in the CIPSO processing code but setting this to 0 (False) should
659 result in less work (i.e. it should be faster) but could cause problems
660 with other implementations that require strict checking.
665 ip_local_port_range - 2 INTEGERS
666 Defines the local port range that is used by TCP and UDP to
667 choose the local port. The first number is the first, the
668 second the last local port number. The default values are
669 32768 and 61000 respectively.
671 ip_local_reserved_ports - list of comma separated ranges
672 Specify the ports which are reserved for known third-party
673 applications. These ports will not be used by automatic port
674 assignments (e.g. when calling connect() or bind() with port
675 number 0). Explicit port allocation behavior is unchanged.
677 The format used for both input and output is a comma separated
678 list of ranges (e.g. "1,2-4,10-10" for ports 1, 2, 3, 4 and
679 10). Writing to the file will clear all previously reserved
680 ports and update the current list with the one given in the
683 Note that ip_local_port_range and ip_local_reserved_ports
684 settings are independent and both are considered by the kernel
685 when determining which ports are available for automatic port
688 You can reserve ports which are not in the current
689 ip_local_port_range, e.g.:
691 $ cat /proc/sys/net/ipv4/ip_local_port_range
693 $ cat /proc/sys/net/ipv4/ip_local_reserved_ports
696 although this is redundant. However such a setting is useful
697 if later the port range is changed to a value that will
698 include the reserved ports.
702 ip_nonlocal_bind - BOOLEAN
703 If set, allows processes to bind() to non-local IP addresses,
704 which can be quite useful - but may break some applications.
708 If set non-zero, enables support for dynamic addresses.
709 If set to a non-zero value larger than 1, a kernel log
710 message will be printed when dynamic address rewriting
714 ip_early_demux - BOOLEAN
715 Optimize input packet processing down to one demux for
716 certain kinds of local sockets. Currently we only do this
717 for established TCP sockets.
719 It may add an additional cost for pure routing workloads that
720 reduces overall throughput, in such case you should disable it.
723 icmp_echo_ignore_all - BOOLEAN
724 If set non-zero, then the kernel will ignore all ICMP ECHO
728 icmp_echo_ignore_broadcasts - BOOLEAN
729 If set non-zero, then the kernel will ignore all ICMP ECHO and
730 TIMESTAMP requests sent to it via broadcast/multicast.
733 icmp_ratelimit - INTEGER
734 Limit the maximal rates for sending ICMP packets whose type matches
735 icmp_ratemask (see below) to specific targets.
736 0 to disable any limiting,
737 otherwise the minimal space between responses in milliseconds.
740 icmp_ratemask - INTEGER
741 Mask made of ICMP types for which rates are being limited.
742 Significant bits: IHGFEDCBA9876543210
743 Default mask: 0000001100000011000 (6168)
745 Bit definitions (see include/linux/icmp.h):
747 3 Destination Unreachable *
752 C Parameter Problem *
757 H Address Mask Request
760 * These are rate limited by default (see default mask above)
762 icmp_ignore_bogus_error_responses - BOOLEAN
763 Some routers violate RFC1122 by sending bogus responses to broadcast
764 frames. Such violations are normally logged via a kernel warning.
765 If this is set to TRUE, the kernel will not give such warnings, which
766 will avoid log file clutter.
769 icmp_errors_use_inbound_ifaddr - BOOLEAN
771 If zero, icmp error messages are sent with the primary address of
772 the exiting interface.
774 If non-zero, the message will be sent with the primary address of
775 the interface that received the packet that caused the icmp error.
776 This is the behaviour network many administrators will expect from
777 a router. And it can make debugging complicated network layouts
780 Note that if no primary address exists for the interface selected,
781 then the primary address of the first non-loopback interface that
782 has one will be used regardless of this setting.
786 igmp_max_memberships - INTEGER
787 Change the maximum number of multicast groups we can subscribe to.
790 Theoretical maximum value is bounded by having to send a membership
791 report in a single datagram (i.e. the report can't span multiple
792 datagrams, or risk confusing the switch and leaving groups you don't
795 The number of supported groups 'M' is bounded by the number of group
796 report entries you can fit into a single datagram of 65535 bytes.
798 M = 65536-sizeof (ip header)/(sizeof(Group record))
800 Group records are variable length, with a minimum of 12 bytes.
801 So net.ipv4.igmp_max_memberships should not be set higher than:
803 (65536-24) / 12 = 5459
805 The value 5459 assumes no IP header options, so in practice
806 this number may be lower.
808 conf/interface/* changes special settings per interface (where
809 "interface" is the name of your network interface)
811 conf/all/* is special, changes the settings for all interfaces
813 log_martians - BOOLEAN
814 Log packets with impossible addresses to kernel log.
815 log_martians for the interface will be enabled if at least one of
816 conf/{all,interface}/log_martians is set to TRUE,
817 it will be disabled otherwise
819 accept_redirects - BOOLEAN
820 Accept ICMP redirect messages.
821 accept_redirects for the interface will be enabled if:
822 - both conf/{all,interface}/accept_redirects are TRUE in the case
823 forwarding for the interface is enabled
825 - at least one of conf/{all,interface}/accept_redirects is TRUE in the
826 case forwarding for the interface is disabled
827 accept_redirects for the interface will be disabled otherwise
832 Enable IP forwarding on this interface.
834 mc_forwarding - BOOLEAN
835 Do multicast routing. The kernel needs to be compiled with CONFIG_MROUTE
836 and a multicast routing daemon is required.
837 conf/all/mc_forwarding must also be set to TRUE to enable multicast
838 routing for the interface
841 Integer value used to differentiate the devices by the medium they
842 are attached to. Two devices can have different id values when
843 the broadcast packets are received only on one of them.
844 The default value 0 means that the device is the only interface
845 to its medium, value of -1 means that medium is not known.
847 Currently, it is used to change the proxy_arp behavior:
848 the proxy_arp feature is enabled for packets forwarded between
849 two devices attached to different media.
853 proxy_arp for the interface will be enabled if at least one of
854 conf/{all,interface}/proxy_arp is set to TRUE,
855 it will be disabled otherwise
857 proxy_arp_pvlan - BOOLEAN
858 Private VLAN proxy arp.
859 Basically allow proxy arp replies back to the same interface
860 (from which the ARP request/solicitation was received).
862 This is done to support (ethernet) switch features, like RFC
863 3069, where the individual ports are NOT allowed to
864 communicate with each other, but they are allowed to talk to
865 the upstream router. As described in RFC 3069, it is possible
866 to allow these hosts to communicate through the upstream
867 router by proxy_arp'ing. Don't need to be used together with
870 This technology is known by different names:
871 In RFC 3069 it is called VLAN Aggregation.
872 Cisco and Allied Telesyn call it Private VLAN.
873 Hewlett-Packard call it Source-Port filtering or port-isolation.
874 Ericsson call it MAC-Forced Forwarding (RFC Draft).
876 shared_media - BOOLEAN
877 Send(router) or accept(host) RFC1620 shared media redirects.
878 Overrides ip_secure_redirects.
879 shared_media for the interface will be enabled if at least one of
880 conf/{all,interface}/shared_media is set to TRUE,
881 it will be disabled otherwise
884 secure_redirects - BOOLEAN
885 Accept ICMP redirect messages only for gateways,
886 listed in default gateway list.
887 secure_redirects for the interface will be enabled if at least one of
888 conf/{all,interface}/secure_redirects is set to TRUE,
889 it will be disabled otherwise
892 send_redirects - BOOLEAN
893 Send redirects, if router.
894 send_redirects for the interface will be enabled if at least one of
895 conf/{all,interface}/send_redirects is set to TRUE,
896 it will be disabled otherwise
899 bootp_relay - BOOLEAN
900 Accept packets with source address 0.b.c.d destined
901 not to this host as local ones. It is supposed, that
902 BOOTP relay daemon will catch and forward such packets.
903 conf/all/bootp_relay must also be set to TRUE to enable BOOTP relay
908 accept_source_route - BOOLEAN
909 Accept packets with SRR option.
910 conf/all/accept_source_route must also be set to TRUE to accept packets
911 with SRR option on the interface
912 default TRUE (router)
915 accept_local - BOOLEAN
916 Accept packets with local source addresses. In combination
917 with suitable routing, this can be used to direct packets
918 between two local interfaces over the wire and have them
921 rp_filter must be set to a non-zero value in order for
922 accept_local to have an effect.
926 route_localnet - BOOLEAN
927 Do not consider loopback addresses as martian source or destination
928 while routing. This enables the use of 127/8 for local routing purposes.
932 0 - No source validation.
933 1 - Strict mode as defined in RFC3704 Strict Reverse Path
934 Each incoming packet is tested against the FIB and if the interface
935 is not the best reverse path the packet check will fail.
936 By default failed packets are discarded.
937 2 - Loose mode as defined in RFC3704 Loose Reverse Path
938 Each incoming packet's source address is also tested against the FIB
939 and if the source address is not reachable via any interface
940 the packet check will fail.
942 Current recommended practice in RFC3704 is to enable strict mode
943 to prevent IP spoofing from DDos attacks. If using asymmetric routing
944 or other complicated routing, then loose mode is recommended.
946 The max value from conf/{all,interface}/rp_filter is used
947 when doing source validation on the {interface}.
949 Default value is 0. Note that some distributions enable it
953 1 - Allows you to have multiple network interfaces on the same
954 subnet, and have the ARPs for each interface be answered
955 based on whether or not the kernel would route a packet from
956 the ARP'd IP out that interface (therefore you must use source
957 based routing for this to work). In other words it allows control
958 of which cards (usually 1) will respond to an arp request.
960 0 - (default) The kernel can respond to arp requests with addresses
961 from other interfaces. This may seem wrong but it usually makes
962 sense, because it increases the chance of successful communication.
963 IP addresses are owned by the complete host on Linux, not by
964 particular interfaces. Only for more complex setups like load-
965 balancing, does this behaviour cause problems.
967 arp_filter for the interface will be enabled if at least one of
968 conf/{all,interface}/arp_filter is set to TRUE,
969 it will be disabled otherwise
971 arp_announce - INTEGER
972 Define different restriction levels for announcing the local
973 source IP address from IP packets in ARP requests sent on
975 0 - (default) Use any local address, configured on any interface
976 1 - Try to avoid local addresses that are not in the target's
977 subnet for this interface. This mode is useful when target
978 hosts reachable via this interface require the source IP
979 address in ARP requests to be part of their logical network
980 configured on the receiving interface. When we generate the
981 request we will check all our subnets that include the
982 target IP and will preserve the source address if it is from
983 such subnet. If there is no such subnet we select source
984 address according to the rules for level 2.
985 2 - Always use the best local address for this target.
986 In this mode we ignore the source address in the IP packet
987 and try to select local address that we prefer for talks with
988 the target host. Such local address is selected by looking
989 for primary IP addresses on all our subnets on the outgoing
990 interface that include the target IP address. If no suitable
991 local address is found we select the first local address
992 we have on the outgoing interface or on all other interfaces,
993 with the hope we will receive reply for our request and
994 even sometimes no matter the source IP address we announce.
996 The max value from conf/{all,interface}/arp_announce is used.
998 Increasing the restriction level gives more chance for
999 receiving answer from the resolved target while decreasing
1000 the level announces more valid sender's information.
1002 arp_ignore - INTEGER
1003 Define different modes for sending replies in response to
1004 received ARP requests that resolve local target IP addresses:
1005 0 - (default): reply for any local target IP address, configured
1007 1 - reply only if the target IP address is local address
1008 configured on the incoming interface
1009 2 - reply only if the target IP address is local address
1010 configured on the incoming interface and both with the
1011 sender's IP address are part from same subnet on this interface
1012 3 - do not reply for local addresses configured with scope host,
1013 only resolutions for global and link addresses are replied
1015 8 - do not reply for all local addresses
1017 The max value from conf/{all,interface}/arp_ignore is used
1018 when ARP request is received on the {interface}
1020 arp_notify - BOOLEAN
1021 Define mode for notification of address and device changes.
1022 0 - (default): do nothing
1023 1 - Generate gratuitous arp requests when device is brought up
1024 or hardware address changes.
1026 arp_accept - BOOLEAN
1027 Define behavior for gratuitous ARP frames who's IP is not
1028 already present in the ARP table:
1029 0 - don't create new entries in the ARP table
1030 1 - create new entries in the ARP table
1032 Both replies and requests type gratuitous arp will trigger the
1033 ARP table to be updated, if this setting is on.
1035 If the ARP table already contains the IP address of the
1036 gratuitous arp frame, the arp table will be updated regardless
1037 if this setting is on or off.
1040 app_solicit - INTEGER
1041 The maximum number of probes to send to the user space ARP daemon
1042 via netlink before dropping back to multicast probes (see
1043 mcast_solicit). Defaults to 0.
1045 disable_policy - BOOLEAN
1046 Disable IPSEC policy (SPD) for this interface
1048 disable_xfrm - BOOLEAN
1049 Disable IPSEC encryption on this interface, whatever the policy
1051 igmpv2_unsolicited_report_interval - INTEGER
1052 The interval in milliseconds in which the next unsolicited
1053 IGMPv1 or IGMPv2 report retransmit will take place.
1054 Default: 10000 (10 seconds)
1056 igmpv3_unsolicited_report_interval - INTEGER
1057 The interval in milliseconds in which the next unsolicited
1058 IGMPv3 report retransmit will take place.
1059 Default: 1000 (1 seconds)
1062 Allows you to write a number, which can be used as required.
1066 kuznet@ms2.inr.ac.ru
1072 delon.nicolas@wanadoo.fr
1077 /proc/sys/net/ipv6/* Variables:
1079 IPv6 has no global variables such as tcp_*. tcp_* settings under ipv4/ also
1080 apply to IPv6 [XXX?].
1082 bindv6only - BOOLEAN
1083 Default value for IPV6_V6ONLY socket option,
1084 which restricts use of the IPv6 socket to IPv6 communication
1086 TRUE: disable IPv4-mapped address feature
1087 FALSE: enable IPv4-mapped address feature
1089 Default: FALSE (as specified in RFC3493)
1093 ip6frag_high_thresh - INTEGER
1094 Maximum memory used to reassemble IPv6 fragments. When
1095 ip6frag_high_thresh bytes of memory is allocated for this purpose,
1096 the fragment handler will toss packets until ip6frag_low_thresh
1099 ip6frag_low_thresh - INTEGER
1100 See ip6frag_high_thresh
1102 ip6frag_time - INTEGER
1103 Time in seconds to keep an IPv6 fragment in memory.
1105 ip6frag_secret_interval - INTEGER
1106 Regeneration interval (in seconds) of the hash secret (or lifetime
1107 for the hash secret) for IPv6 fragments.
1111 Change the interface-specific default settings.
1115 Change all the interface-specific settings.
1117 [XXX: Other special features than forwarding?]
1119 conf/all/forwarding - BOOLEAN
1120 Enable global IPv6 forwarding between all interfaces.
1122 IPv4 and IPv6 work differently here; e.g. netfilter must be used
1123 to control which interfaces may forward packets and which not.
1125 This also sets all interfaces' Host/Router setting
1126 'forwarding' to the specified value. See below for details.
1128 This referred to as global forwarding.
1134 Change special settings per interface.
1136 The functional behaviour for certain settings is different
1137 depending on whether local forwarding is enabled or not.
1140 Accept Router Advertisements; autoconfigure using them.
1142 It also determines whether or not to transmit Router
1143 Solicitations. If and only if the functional setting is to
1144 accept Router Advertisements, Router Solicitations will be
1147 Possible values are:
1148 0 Do not accept Router Advertisements.
1149 1 Accept Router Advertisements if forwarding is disabled.
1150 2 Overrule forwarding behaviour. Accept Router Advertisements
1151 even if forwarding is enabled.
1153 Functional default: enabled if local forwarding is disabled.
1154 disabled if local forwarding is enabled.
1156 accept_ra_defrtr - BOOLEAN
1157 Learn default router in Router Advertisement.
1159 Functional default: enabled if accept_ra is enabled.
1160 disabled if accept_ra is disabled.
1162 accept_ra_pinfo - BOOLEAN
1163 Learn Prefix Information in Router Advertisement.
1165 Functional default: enabled if accept_ra is enabled.
1166 disabled if accept_ra is disabled.
1168 accept_ra_rt_info_max_plen - INTEGER
1169 Maximum prefix length of Route Information in RA.
1171 Route Information w/ prefix larger than or equal to this
1172 variable shall be ignored.
1174 Functional default: 0 if accept_ra_rtr_pref is enabled.
1175 -1 if accept_ra_rtr_pref is disabled.
1177 accept_ra_rtr_pref - BOOLEAN
1178 Accept Router Preference in RA.
1180 Functional default: enabled if accept_ra is enabled.
1181 disabled if accept_ra is disabled.
1183 accept_redirects - BOOLEAN
1186 Functional default: enabled if local forwarding is disabled.
1187 disabled if local forwarding is enabled.
1189 accept_source_route - INTEGER
1190 Accept source routing (routing extension header).
1192 >= 0: Accept only routing header type 2.
1193 < 0: Do not accept routing header.
1198 Autoconfigure addresses using Prefix Information in Router
1201 Functional default: enabled if accept_ra_pinfo is enabled.
1202 disabled if accept_ra_pinfo is disabled.
1204 dad_transmits - INTEGER
1205 The amount of Duplicate Address Detection probes to send.
1208 forwarding - INTEGER
1209 Configure interface-specific Host/Router behaviour.
1211 Note: It is recommended to have the same setting on all
1212 interfaces; mixed router/host scenarios are rather uncommon.
1214 Possible values are:
1215 0 Forwarding disabled
1216 1 Forwarding enabled
1220 By default, Host behaviour is assumed. This means:
1222 1. IsRouter flag is not set in Neighbour Advertisements.
1223 2. If accept_ra is TRUE (default), transmit Router
1225 3. If accept_ra is TRUE (default), accept Router
1226 Advertisements (and do autoconfiguration).
1227 4. If accept_redirects is TRUE (default), accept Redirects.
1231 If local forwarding is enabled, Router behaviour is assumed.
1232 This means exactly the reverse from the above:
1234 1. IsRouter flag is set in Neighbour Advertisements.
1235 2. Router Solicitations are not sent unless accept_ra is 2.
1236 3. Router Advertisements are ignored unless accept_ra is 2.
1237 4. Redirects are ignored.
1239 Default: 0 (disabled) if global forwarding is disabled (default),
1240 otherwise 1 (enabled).
1243 Default Hop Limit to set.
1247 Default Maximum Transfer Unit
1248 Default: 1280 (IPv6 required minimum)
1250 router_probe_interval - INTEGER
1251 Minimum interval (in seconds) between Router Probing described
1256 router_solicitation_delay - INTEGER
1257 Number of seconds to wait after interface is brought up
1258 before sending Router Solicitations.
1261 router_solicitation_interval - INTEGER
1262 Number of seconds to wait between Router Solicitations.
1265 router_solicitations - INTEGER
1266 Number of Router Solicitations to send until assuming no
1267 routers are present.
1270 use_tempaddr - INTEGER
1271 Preference for Privacy Extensions (RFC3041).
1272 <= 0 : disable Privacy Extensions
1273 == 1 : enable Privacy Extensions, but prefer public
1274 addresses over temporary addresses.
1275 > 1 : enable Privacy Extensions and prefer temporary
1276 addresses over public addresses.
1277 Default: 0 (for most devices)
1278 -1 (for point-to-point devices and loopback devices)
1280 temp_valid_lft - INTEGER
1281 valid lifetime (in seconds) for temporary addresses.
1282 Default: 604800 (7 days)
1284 temp_prefered_lft - INTEGER
1285 Preferred lifetime (in seconds) for temporary addresses.
1286 Default: 86400 (1 day)
1288 max_desync_factor - INTEGER
1289 Maximum value for DESYNC_FACTOR, which is a random value
1290 that ensures that clients don't synchronize with each
1291 other and generate new addresses at exactly the same time.
1292 value is in seconds.
1295 regen_max_retry - INTEGER
1296 Number of attempts before give up attempting to generate
1297 valid temporary addresses.
1300 max_addresses - INTEGER
1301 Maximum number of autoconfigured addresses per interface. Setting
1302 to zero disables the limitation. It is not recommended to set this
1303 value too large (or to zero) because it would be an easy way to
1304 crash the kernel by allowing too many addresses to be created.
1307 disable_ipv6 - BOOLEAN
1308 Disable IPv6 operation. If accept_dad is set to 2, this value
1309 will be dynamically set to TRUE if DAD fails for the link-local
1311 Default: FALSE (enable IPv6 operation)
1313 When this value is changed from 1 to 0 (IPv6 is being enabled),
1314 it will dynamically create a link-local address on the given
1315 interface and start Duplicate Address Detection, if necessary.
1317 When this value is changed from 0 to 1 (IPv6 is being disabled),
1318 it will dynamically delete all address on the given interface.
1320 accept_dad - INTEGER
1321 Whether to accept DAD (Duplicate Address Detection).
1323 1: Enable DAD (default)
1324 2: Enable DAD, and disable IPv6 operation if MAC-based duplicate
1325 link-local address has been found.
1327 force_tllao - BOOLEAN
1328 Enable sending the target link-layer address option even when
1329 responding to a unicast neighbor solicitation.
1332 Quoting from RFC 2461, section 4.4, Target link-layer address:
1334 "The option MUST be included for multicast solicitations in order to
1335 avoid infinite Neighbor Solicitation "recursion" when the peer node
1336 does not have a cache entry to return a Neighbor Advertisements
1337 message. When responding to unicast solicitations, the option can be
1338 omitted since the sender of the solicitation has the correct link-
1339 layer address; otherwise it would not have be able to send the unicast
1340 solicitation in the first place. However, including the link-layer
1341 address in this case adds little overhead and eliminates a potential
1342 race condition where the sender deletes the cached link-layer address
1343 prior to receiving a response to a previous solicitation."
1345 ndisc_notify - BOOLEAN
1346 Define mode for notification of address and device changes.
1347 0 - (default): do nothing
1348 1 - Generate unsolicited neighbour advertisements when device is brought
1349 up or hardware address changes.
1351 mldv1_unsolicited_report_interval - INTEGER
1352 The interval in milliseconds in which the next unsolicited
1353 MLDv1 report retransmit will take place.
1354 Default: 10000 (10 seconds)
1356 mldv2_unsolicited_report_interval - INTEGER
1357 The interval in milliseconds in which the next unsolicited
1358 MLDv2 report retransmit will take place.
1359 Default: 1000 (1 second)
1361 force_mld_version - INTEGER
1362 0 - (default) No enforcement of a MLD version, MLDv1 fallback allowed
1363 1 - Enforce to use MLD version 1
1364 2 - Enforce to use MLD version 2
1366 suppress_frag_ndisc - INTEGER
1367 Control RFC 6980 (Security Implications of IPv6 Fragmentation
1368 with IPv6 Neighbor Discovery) behavior:
1369 1 - (default) discard fragmented neighbor discovery packets
1370 0 - allow fragmented neighbor discovery packets
1374 Limit the maximal rates for sending ICMPv6 packets.
1375 0 to disable any limiting,
1376 otherwise the minimal space between responses in milliseconds.
1381 Pekka Savola <pekkas@netcore.fi>
1382 YOSHIFUJI Hideaki / USAGI Project <yoshfuji@linux-ipv6.org>
1385 /proc/sys/net/bridge/* Variables:
1387 bridge-nf-call-arptables - BOOLEAN
1388 1 : pass bridged ARP traffic to arptables' FORWARD chain.
1392 bridge-nf-call-iptables - BOOLEAN
1393 1 : pass bridged IPv4 traffic to iptables' chains.
1397 bridge-nf-call-ip6tables - BOOLEAN
1398 1 : pass bridged IPv6 traffic to ip6tables' chains.
1402 bridge-nf-filter-vlan-tagged - BOOLEAN
1403 1 : pass bridged vlan-tagged ARP/IP/IPv6 traffic to {arp,ip,ip6}tables.
1407 bridge-nf-filter-pppoe-tagged - BOOLEAN
1408 1 : pass bridged pppoe-tagged IP/IPv6 traffic to {ip,ip6}tables.
1412 bridge-nf-pass-vlan-input-dev - BOOLEAN
1413 1: if bridge-nf-filter-vlan-tagged is enabled, try to find a vlan
1414 interface on the bridge and set the netfilter input device to the vlan.
1415 This allows use of e.g. "iptables -i br0.1" and makes the REDIRECT
1416 target work with vlan-on-top-of-bridge interfaces. When no matching
1417 vlan interface is found, or this switch is off, the input device is
1418 set to the bridge interface.
1419 0: disable bridge netfilter vlan interface lookup.
1422 proc/sys/net/sctp/* Variables:
1424 addip_enable - BOOLEAN
1425 Enable or disable extension of Dynamic Address Reconfiguration
1426 (ADD-IP) functionality specified in RFC5061. This extension provides
1427 the ability to dynamically add and remove new addresses for the SCTP
1430 1: Enable extension.
1432 0: Disable extension.
1436 addip_noauth_enable - BOOLEAN
1437 Dynamic Address Reconfiguration (ADD-IP) requires the use of
1438 authentication to protect the operations of adding or removing new
1439 addresses. This requirement is mandated so that unauthorized hosts
1440 would not be able to hijack associations. However, older
1441 implementations may not have implemented this requirement while
1442 allowing the ADD-IP extension. For reasons of interoperability,
1443 we provide this variable to control the enforcement of the
1444 authentication requirement.
1446 1: Allow ADD-IP extension to be used without authentication. This
1447 should only be set in a closed environment for interoperability
1448 with older implementations.
1450 0: Enforce the authentication requirement
1454 auth_enable - BOOLEAN
1455 Enable or disable Authenticated Chunks extension. This extension
1456 provides the ability to send and receive authenticated chunks and is
1457 required for secure operation of Dynamic Address Reconfiguration
1460 1: Enable this extension.
1461 0: Disable this extension.
1465 prsctp_enable - BOOLEAN
1466 Enable or disable the Partial Reliability extension (RFC3758) which
1467 is used to notify peers that a given DATA should no longer be expected.
1475 The limit of the number of new packets that can be initially sent. It
1476 controls how bursty the generated traffic can be.
1480 association_max_retrans - INTEGER
1481 Set the maximum number for retransmissions that an association can
1482 attempt deciding that the remote end is unreachable. If this value
1483 is exceeded, the association is terminated.
1487 max_init_retransmits - INTEGER
1488 The maximum number of retransmissions of INIT and COOKIE-ECHO chunks
1489 that an association will attempt before declaring the destination
1490 unreachable and terminating.
1494 path_max_retrans - INTEGER
1495 The maximum number of retransmissions that will be attempted on a given
1496 path. Once this threshold is exceeded, the path is considered
1497 unreachable, and new traffic will use a different path when the
1498 association is multihomed.
1502 pf_retrans - INTEGER
1503 The number of retransmissions that will be attempted on a given path
1504 before traffic is redirected to an alternate transport (should one
1505 exist). Note this is distinct from path_max_retrans, as a path that
1506 passes the pf_retrans threshold can still be used. Its only
1507 deprioritized when a transmission path is selected by the stack. This
1508 setting is primarily used to enable fast failover mechanisms without
1509 having to reduce path_max_retrans to a very low value. See:
1510 http://www.ietf.org/id/draft-nishida-tsvwg-sctp-failover-05.txt
1511 for details. Note also that a value of pf_retrans > path_max_retrans
1512 disables this feature
1516 rto_initial - INTEGER
1517 The initial round trip timeout value in milliseconds that will be used
1518 in calculating round trip times. This is the initial time interval
1519 for retransmissions.
1524 The maximum value (in milliseconds) of the round trip timeout. This
1525 is the largest time interval that can elapse between retransmissions.
1530 The minimum value (in milliseconds) of the round trip timeout. This
1531 is the smallest time interval the can elapse between retransmissions.
1535 hb_interval - INTEGER
1536 The interval (in milliseconds) between HEARTBEAT chunks. These chunks
1537 are sent at the specified interval on idle paths to probe the state of
1538 a given path between 2 associations.
1542 sack_timeout - INTEGER
1543 The amount of time (in milliseconds) that the implementation will wait
1548 valid_cookie_life - INTEGER
1549 The default lifetime of the SCTP cookie (in milliseconds). The cookie
1550 is used during association establishment.
1554 cookie_preserve_enable - BOOLEAN
1555 Enable or disable the ability to extend the lifetime of the SCTP cookie
1556 that is used during the establishment phase of SCTP association
1558 1: Enable cookie lifetime extension.
1563 cookie_hmac_alg - STRING
1564 Select the hmac algorithm used when generating the cookie value sent by
1565 a listening sctp socket to a connecting client in the INIT-ACK chunk.
1570 Ability to assign md5 or sha1 as the selected alg is predicated on the
1571 configuration of those algorithms at build time (CONFIG_CRYPTO_MD5 and
1572 CONFIG_CRYPTO_SHA1).
1574 Default: Dependent on configuration. MD5 if available, else SHA1 if
1575 available, else none.
1577 rcvbuf_policy - INTEGER
1578 Determines if the receive buffer is attributed to the socket or to
1579 association. SCTP supports the capability to create multiple
1580 associations on a single socket. When using this capability, it is
1581 possible that a single stalled association that's buffering a lot
1582 of data may block other associations from delivering their data by
1583 consuming all of the receive buffer space. To work around this,
1584 the rcvbuf_policy could be set to attribute the receiver buffer space
1585 to each association instead of the socket. This prevents the described
1588 1: rcvbuf space is per association
1589 0: rcvbuf space is per socket
1593 sndbuf_policy - INTEGER
1594 Similar to rcvbuf_policy above, this applies to send buffer space.
1596 1: Send buffer is tracked per association
1597 0: Send buffer is tracked per socket.
1601 sctp_mem - vector of 3 INTEGERs: min, pressure, max
1602 Number of pages allowed for queueing by all SCTP sockets.
1604 min: Below this number of pages SCTP is not bothered about its
1605 memory appetite. When amount of memory allocated by SCTP exceeds
1606 this number, SCTP starts to moderate memory usage.
1608 pressure: This value was introduced to follow format of tcp_mem.
1610 max: Number of pages allowed for queueing by all SCTP sockets.
1612 Default is calculated at boot time from amount of available memory.
1614 sctp_rmem - vector of 3 INTEGERs: min, default, max
1615 Only the first value ("min") is used, "default" and "max" are
1618 min: Minimal size of receive buffer used by SCTP socket.
1619 It is guaranteed to each SCTP socket (but not association) even
1620 under moderate memory pressure.
1624 sctp_wmem - vector of 3 INTEGERs: min, default, max
1625 Currently this tunable has no effect.
1627 addr_scope_policy - INTEGER
1628 Control IPv4 address scoping - draft-stewart-tsvwg-sctp-ipv4-00
1630 0 - Disable IPv4 address scoping
1631 1 - Enable IPv4 address scoping
1632 2 - Follow draft but allow IPv4 private addresses
1633 3 - Follow draft but allow IPv4 link local addresses
1638 /proc/sys/net/core/*
1639 Please see: Documentation/sysctl/net.txt for descriptions of these entries.
1642 /proc/sys/net/unix/*
1643 max_dgram_qlen - INTEGER
1644 The maximum length of dgram socket receive queue
1651 /proc/sys/net/irda/*
1652 fast_poll_increase FIXME
1653 warn_noreply_time FIXME
1654 discovery_slots FIXME
1657 discovery_timeout FIXME
1658 lap_keepalive_time FIXME
1659 max_noreply_time FIXME
1660 max_tx_data_size FIXME
1662 min_tx_turn_time FIXME