1/proc/sys/net/ipv4/* Variables: 2 3ip_forward - BOOLEAN 4 0 - disabled (default) 5 not 0 - enabled 6 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 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) 17 18ip_no_pmtu_disc - INTEGER 19 Disable Path MTU Discovery. If enabled in mode 1 and a 20 fragmentation-required ICMP is received, the PMTU to this 21 destination will be set to min_pmtu (see below). You will need 22 to raise min_pmtu to the smallest interface MTU on your system 23 manually if you want to avoid locally generated fragments. 24 25 In mode 2 incoming Path MTU Discovery messages will be 26 discarded. Outgoing frames are handled the same as in mode 1, 27 implicitly setting IP_PMTUDISC_DONT on every created socket. 28 29 Mode 3 is a hardend pmtu discover mode. The kernel will only 30 accept fragmentation-needed errors if the underlying protocol 31 can verify them besides a plain socket lookup. Current 32 protocols for which pmtu events will be honored are TCP, SCTP 33 and DCCP as they verify e.g. the sequence number or the 34 association. This mode should not be enabled globally but is 35 only intended to secure e.g. name servers in namespaces where 36 TCP path mtu must still work but path MTU information of other 37 protocols should be discarded. If enabled globally this mode 38 could break other protocols. 39 40 Possible values: 0-3 41 Default: FALSE 42 43min_pmtu - INTEGER 44 default 552 - minimum discovered Path MTU 45 46ip_forward_use_pmtu - BOOLEAN 47 By default we don't trust protocol path MTUs while forwarding 48 because they could be easily forged and can lead to unwanted 49 fragmentation by the router. 50 You only need to enable this if you have user-space software 51 which tries to discover path mtus by itself and depends on the 52 kernel honoring this information. This is normally not the 53 case. 54 Default: 0 (disabled) 55 Possible values: 56 0 - disabled 57 1 - enabled 58 59fwmark_reflect - BOOLEAN 60 Controls the fwmark of kernel-generated IPv4 reply packets that are not 61 associated with a socket for example, TCP RSTs or ICMP echo replies). 62 If unset, these packets have a fwmark of zero. If set, they have the 63 fwmark of the packet they are replying to. 64 Default: 0 65 66route/max_size - INTEGER 67 Maximum number of routes allowed in the kernel. Increase 68 this when using large numbers of interfaces and/or routes. 69 From linux kernel 3.6 onwards, this is deprecated for ipv4 70 as route cache is no longer used. 71 72neigh/default/gc_thresh1 - INTEGER 73 Minimum number of entries to keep. Garbage collector will not 74 purge entries if there are fewer than this number. 75 Default: 128 76 77neigh/default/gc_thresh2 - INTEGER 78 Threshold when garbage collector becomes more aggressive about 79 purging entries. Entries older than 5 seconds will be cleared 80 when over this number. 81 Default: 512 82 83neigh/default/gc_thresh3 - INTEGER 84 Maximum number of neighbor entries allowed. Increase this 85 when using large numbers of interfaces and when communicating 86 with large numbers of directly-connected peers. 87 Default: 1024 88 89neigh/default/unres_qlen_bytes - INTEGER 90 The maximum number of bytes which may be used by packets 91 queued for each unresolved address by other network layers. 92 (added in linux 3.3) 93 Setting negative value is meaningless and will return error. 94 Default: 65536 Bytes(64KB) 95 96neigh/default/unres_qlen - INTEGER 97 The maximum number of packets which may be queued for each 98 unresolved address by other network layers. 99 (deprecated in linux 3.3) : use unres_qlen_bytes instead. 100 Prior to linux 3.3, the default value is 3 which may cause 101 unexpected packet loss. The current default value is calculated 102 according to default value of unres_qlen_bytes and true size of 103 packet. 104 Default: 31 105 106mtu_expires - INTEGER 107 Time, in seconds, that cached PMTU information is kept. 108 109min_adv_mss - INTEGER 110 The advertised MSS depends on the first hop route MTU, but will 111 never be lower than this setting. 112 113IP Fragmentation: 114 115ipfrag_high_thresh - INTEGER 116 Maximum memory used to reassemble IP fragments. When 117 ipfrag_high_thresh bytes of memory is allocated for this purpose, 118 the fragment handler will toss packets until ipfrag_low_thresh 119 is reached. This also serves as a maximum limit to namespaces 120 different from the initial one. 121 122ipfrag_low_thresh - INTEGER 123 Maximum memory used to reassemble IP fragments before the kernel 124 begins to remove incomplete fragment queues to free up resources. 125 The kernel still accepts new fragments for defragmentation. 126 127ipfrag_time - INTEGER 128 Time in seconds to keep an IP fragment in memory. 129 130ipfrag_max_dist - INTEGER 131 ipfrag_max_dist is a non-negative integer value which defines the 132 maximum "disorder" which is allowed among fragments which share a 133 common IP source address. Note that reordering of packets is 134 not unusual, but if a large number of fragments arrive from a source 135 IP address while a particular fragment queue remains incomplete, it 136 probably indicates that one or more fragments belonging to that queue 137 have been lost. When ipfrag_max_dist is positive, an additional check 138 is done on fragments before they are added to a reassembly queue - if 139 ipfrag_max_dist (or more) fragments have arrived from a particular IP 140 address between additions to any IP fragment queue using that source 141 address, it's presumed that one or more fragments in the queue are 142 lost. The existing fragment queue will be dropped, and a new one 143 started. An ipfrag_max_dist value of zero disables this check. 144 145 Using a very small value, e.g. 1 or 2, for ipfrag_max_dist can 146 result in unnecessarily dropping fragment queues when normal 147 reordering of packets occurs, which could lead to poor application 148 performance. Using a very large value, e.g. 50000, increases the 149 likelihood of incorrectly reassembling IP fragments that originate 150 from different IP datagrams, which could result in data corruption. 151 Default: 64 152 153INET peer storage: 154 155inet_peer_threshold - INTEGER 156 The approximate size of the storage. Starting from this threshold 157 entries will be thrown aggressively. This threshold also determines 158 entries' time-to-live and time intervals between garbage collection 159 passes. More entries, less time-to-live, less GC interval. 160 161inet_peer_minttl - INTEGER 162 Minimum time-to-live of entries. Should be enough to cover fragment 163 time-to-live on the reassembling side. This minimum time-to-live is 164 guaranteed if the pool size is less than inet_peer_threshold. 165 Measured in seconds. 166 167inet_peer_maxttl - INTEGER 168 Maximum time-to-live of entries. Unused entries will expire after 169 this period of time if there is no memory pressure on the pool (i.e. 170 when the number of entries in the pool is very small). 171 Measured in seconds. 172 173TCP variables: 174 175somaxconn - INTEGER 176 Limit of socket listen() backlog, known in userspace as SOMAXCONN. 177 Defaults to 128. See also tcp_max_syn_backlog for additional tuning 178 for TCP sockets. 179 180tcp_abort_on_overflow - BOOLEAN 181 If listening service is too slow to accept new connections, 182 reset them. Default state is FALSE. It means that if overflow 183 occurred due to a burst, connection will recover. Enable this 184 option _only_ if you are really sure that listening daemon 185 cannot be tuned to accept connections faster. Enabling this 186 option can harm clients of your server. 187 188tcp_adv_win_scale - INTEGER 189 Count buffering overhead as bytes/2^tcp_adv_win_scale 190 (if tcp_adv_win_scale > 0) or bytes-bytes/2^(-tcp_adv_win_scale), 191 if it is <= 0. 192 Possible values are [-31, 31], inclusive. 193 Default: 1 194 195tcp_allowed_congestion_control - STRING 196 Show/set the congestion control choices available to non-privileged 197 processes. The list is a subset of those listed in 198 tcp_available_congestion_control. 199 Default is "reno" and the default setting (tcp_congestion_control). 200 201tcp_app_win - INTEGER 202 Reserve max(window/2^tcp_app_win, mss) of window for application 203 buffer. Value 0 is special, it means that nothing is reserved. 204 Default: 31 205 206tcp_autocorking - BOOLEAN 207 Enable TCP auto corking : 208 When applications do consecutive small write()/sendmsg() system calls, 209 we try to coalesce these small writes as much as possible, to lower 210 total amount of sent packets. This is done if at least one prior 211 packet for the flow is waiting in Qdisc queues or device transmit 212 queue. Applications can still use TCP_CORK for optimal behavior 213 when they know how/when to uncork their sockets. 214 Default : 1 215 216tcp_available_congestion_control - STRING 217 Shows the available congestion control choices that are registered. 218 More congestion control algorithms may be available as modules, 219 but not loaded. 220 221tcp_base_mss - INTEGER 222 The initial value of search_low to be used by the packetization layer 223 Path MTU discovery (MTU probing). If MTU probing is enabled, 224 this is the initial MSS used by the connection. 225 226tcp_congestion_control - STRING 227 Set the congestion control algorithm to be used for new 228 connections. The algorithm "reno" is always available, but 229 additional choices may be available based on kernel configuration. 230 Default is set as part of kernel configuration. 231 For passive connections, the listener congestion control choice 232 is inherited. 233 [see setsockopt(listenfd, SOL_TCP, TCP_CONGESTION, "name" ...) ] 234 235tcp_dsack - BOOLEAN 236 Allows TCP to send "duplicate" SACKs. 237 238tcp_early_retrans - INTEGER 239 Enable Early Retransmit (ER), per RFC 5827. ER lowers the threshold 240 for triggering fast retransmit when the amount of outstanding data is 241 small and when no previously unsent data can be transmitted (such 242 that limited transmit could be used). Also controls the use of 243 Tail loss probe (TLP) that converts RTOs occurring due to tail 244 losses into fast recovery (draft-dukkipati-tcpm-tcp-loss-probe-01). 245 Possible values: 246 0 disables ER 247 1 enables ER 248 2 enables ER but delays fast recovery and fast retransmit 249 by a fourth of RTT. This mitigates connection falsely 250 recovers when network has a small degree of reordering 251 (less than 3 packets). 252 3 enables delayed ER and TLP. 253 4 enables TLP only. 254 Default: 3 255 256tcp_ecn - INTEGER 257 Control use of Explicit Congestion Notification (ECN) by TCP. 258 ECN is used only when both ends of the TCP connection indicate 259 support for it. This feature is useful in avoiding losses due 260 to congestion by allowing supporting routers to signal 261 congestion before having to drop packets. 262 Possible values are: 263 0 Disable ECN. Neither initiate nor accept ECN. 264 1 Enable ECN when requested by incoming connections and 265 also request ECN on outgoing connection attempts. 266 2 Enable ECN when requested by incoming connections 267 but do not request ECN on outgoing connections. 268 Default: 2 269 270tcp_ecn_fallback - BOOLEAN 271 If the kernel detects that ECN connection misbehaves, enable fall 272 back to non-ECN. Currently, this knob implements the fallback 273 from RFC3168, section 6.1.1.1., but we reserve that in future, 274 additional detection mechanisms could be implemented under this 275 knob. The value is not used, if tcp_ecn or per route (or congestion 276 control) ECN settings are disabled. 277 Default: 1 (fallback enabled) 278 279tcp_fack - BOOLEAN 280 Enable FACK congestion avoidance and fast retransmission. 281 The value is not used, if tcp_sack is not enabled. 282 283tcp_fin_timeout - INTEGER 284 The length of time an orphaned (no longer referenced by any 285 application) connection will remain in the FIN_WAIT_2 state 286 before it is aborted at the local end. While a perfectly 287 valid "receive only" state for an un-orphaned connection, an 288 orphaned connection in FIN_WAIT_2 state could otherwise wait 289 forever for the remote to close its end of the connection. 290 Cf. tcp_max_orphans 291 Default: 60 seconds 292 293tcp_frto - INTEGER 294 Enables Forward RTO-Recovery (F-RTO) defined in RFC5682. 295 F-RTO is an enhanced recovery algorithm for TCP retransmission 296 timeouts. It is particularly beneficial in networks where the 297 RTT fluctuates (e.g., wireless). F-RTO is sender-side only 298 modification. It does not require any support from the peer. 299 300 By default it's enabled with a non-zero value. 0 disables F-RTO. 301 302tcp_invalid_ratelimit - INTEGER 303 Limit the maximal rate for sending duplicate acknowledgments 304 in response to incoming TCP packets that are for an existing 305 connection but that are invalid due to any of these reasons: 306 307 (a) out-of-window sequence number, 308 (b) out-of-window acknowledgment number, or 309 (c) PAWS (Protection Against Wrapped Sequence numbers) check failure 310 311 This can help mitigate simple "ack loop" DoS attacks, wherein 312 a buggy or malicious middlebox or man-in-the-middle can 313 rewrite TCP header fields in manner that causes each endpoint 314 to think that the other is sending invalid TCP segments, thus 315 causing each side to send an unterminating stream of duplicate 316 acknowledgments for invalid segments. 317 318 Using 0 disables rate-limiting of dupacks in response to 319 invalid segments; otherwise this value specifies the minimal 320 space between sending such dupacks, in milliseconds. 321 322 Default: 500 (milliseconds). 323 324tcp_keepalive_time - INTEGER 325 How often TCP sends out keepalive messages when keepalive is enabled. 326 Default: 2hours. 327 328tcp_keepalive_probes - INTEGER 329 How many keepalive probes TCP sends out, until it decides that the 330 connection is broken. Default value: 9. 331 332tcp_keepalive_intvl - INTEGER 333 How frequently the probes are send out. Multiplied by 334 tcp_keepalive_probes it is time to kill not responding connection, 335 after probes started. Default value: 75sec i.e. connection 336 will be aborted after ~11 minutes of retries. 337 338tcp_low_latency - BOOLEAN 339 If set, the TCP stack makes decisions that prefer lower 340 latency as opposed to higher throughput. By default, this 341 option is not set meaning that higher throughput is preferred. 342 An example of an application where this default should be 343 changed would be a Beowulf compute cluster. 344 Default: 0 345 346tcp_max_orphans - INTEGER 347 Maximal number of TCP sockets not attached to any user file handle, 348 held by system. If this number is exceeded orphaned connections are 349 reset immediately and warning is printed. This limit exists 350 only to prevent simple DoS attacks, you _must_ not rely on this 351 or lower the limit artificially, but rather increase it 352 (probably, after increasing installed memory), 353 if network conditions require more than default value, 354 and tune network services to linger and kill such states 355 more aggressively. Let me to remind again: each orphan eats 356 up to ~64K of unswappable memory. 357 358tcp_max_syn_backlog - INTEGER 359 Maximal number of remembered connection requests, which have not 360 received an acknowledgment from connecting client. 361 The minimal value is 128 for low memory machines, and it will 362 increase in proportion to the memory of machine. 363 If server suffers from overload, try increasing this number. 364 365tcp_max_tw_buckets - INTEGER 366 Maximal number of timewait sockets held by system simultaneously. 367 If this number is exceeded time-wait socket is immediately destroyed 368 and warning is printed. This limit exists only to prevent 369 simple DoS attacks, you _must_ not lower the limit artificially, 370 but rather increase it (probably, after increasing installed memory), 371 if network conditions require more than default value. 372 373tcp_mem - vector of 3 INTEGERs: min, pressure, max 374 min: below this number of pages TCP is not bothered about its 375 memory appetite. 376 377 pressure: when amount of memory allocated by TCP exceeds this number 378 of pages, TCP moderates its memory consumption and enters memory 379 pressure mode, which is exited when memory consumption falls 380 under "min". 381 382 max: number of pages allowed for queueing by all TCP sockets. 383 384 Defaults are calculated at boot time from amount of available 385 memory. 386 387tcp_min_rtt_wlen - INTEGER 388 The window length of the windowed min filter to track the minimum RTT. 389 A shorter window lets a flow more quickly pick up new (higher) 390 minimum RTT when it is moved to a longer path (e.g., due to traffic 391 engineering). A longer window makes the filter more resistant to RTT 392 inflations such as transient congestion. The unit is seconds. 393 Default: 300 394 395tcp_moderate_rcvbuf - BOOLEAN 396 If set, TCP performs receive buffer auto-tuning, attempting to 397 automatically size the buffer (no greater than tcp_rmem[2]) to 398 match the size required by the path for full throughput. Enabled by 399 default. 400 401tcp_mtu_probing - INTEGER 402 Controls TCP Packetization-Layer Path MTU Discovery. Takes three 403 values: 404 0 - Disabled 405 1 - Disabled by default, enabled when an ICMP black hole detected 406 2 - Always enabled, use initial MSS of tcp_base_mss. 407 408tcp_probe_interval - INTEGER 409 Controls how often to start TCP Packetization-Layer Path MTU 410 Discovery reprobe. The default is reprobing every 10 minutes as 411 per RFC4821. 412 413tcp_probe_threshold - INTEGER 414 Controls when TCP Packetization-Layer Path MTU Discovery probing 415 will stop in respect to the width of search range in bytes. Default 416 is 8 bytes. 417 418tcp_no_metrics_save - BOOLEAN 419 By default, TCP saves various connection metrics in the route cache 420 when the connection closes, so that connections established in the 421 near future can use these to set initial conditions. Usually, this 422 increases overall performance, but may sometimes cause performance 423 degradation. If set, TCP will not cache metrics on closing 424 connections. 425 426tcp_orphan_retries - INTEGER 427 This value influences the timeout of a locally closed TCP connection, 428 when RTO retransmissions remain unacknowledged. 429 See tcp_retries2 for more details. 430 431 The default value is 8. 432 If your machine is a loaded WEB server, 433 you should think about lowering this value, such sockets 434 may consume significant resources. Cf. tcp_max_orphans. 435 436tcp_recovery - INTEGER 437 This value is a bitmap to enable various experimental loss recovery 438 features. 439 440 RACK: 0x1 enables the RACK loss detection for fast detection of lost 441 retransmissions and tail drops. 442 443 Default: 0x1 444 445tcp_reordering - INTEGER 446 Initial reordering level of packets in a TCP stream. 447 TCP stack can then dynamically adjust flow reordering level 448 between this initial value and tcp_max_reordering 449 Default: 3 450 451tcp_max_reordering - INTEGER 452 Maximal reordering level of packets in a TCP stream. 453 300 is a fairly conservative value, but you might increase it 454 if paths are using per packet load balancing (like bonding rr mode) 455 Default: 300 456 457tcp_retrans_collapse - BOOLEAN 458 Bug-to-bug compatibility with some broken printers. 459 On retransmit try to send bigger packets to work around bugs in 460 certain TCP stacks. 461 462tcp_retries1 - INTEGER 463 This value influences the time, after which TCP decides, that 464 something is wrong due to unacknowledged RTO retransmissions, 465 and reports this suspicion to the network layer. 466 See tcp_retries2 for more details. 467 468 RFC 1122 recommends at least 3 retransmissions, which is the 469 default. 470 471tcp_retries2 - INTEGER 472 This value influences the timeout of an alive TCP connection, 473 when RTO retransmissions remain unacknowledged. 474 Given a value of N, a hypothetical TCP connection following 475 exponential backoff with an initial RTO of TCP_RTO_MIN would 476 retransmit N times before killing the connection at the (N+1)th RTO. 477 478 The default value of 15 yields a hypothetical timeout of 924.6 479 seconds and is a lower bound for the effective timeout. 480 TCP will effectively time out at the first RTO which exceeds the 481 hypothetical timeout. 482 483 RFC 1122 recommends at least 100 seconds for the timeout, 484 which corresponds to a value of at least 8. 485 486tcp_rfc1337 - BOOLEAN 487 If set, the TCP stack behaves conforming to RFC1337. If unset, 488 we are not conforming to RFC, but prevent TCP TIME_WAIT 489 assassination. 490 Default: 0 491 492tcp_rmem - vector of 3 INTEGERs: min, default, max 493 min: Minimal size of receive buffer used by TCP sockets. 494 It is guaranteed to each TCP socket, even under moderate memory 495 pressure. 496 Default: 1 page 497 498 default: initial size of receive buffer used by TCP sockets. 499 This value overrides net.core.rmem_default used by other protocols. 500 Default: 87380 bytes. This value results in window of 65535 with 501 default setting of tcp_adv_win_scale and tcp_app_win:0 and a bit 502 less for default tcp_app_win. See below about these variables. 503 504 max: maximal size of receive buffer allowed for automatically 505 selected receiver buffers for TCP socket. This value does not override 506 net.core.rmem_max. Calling setsockopt() with SO_RCVBUF disables 507 automatic tuning of that socket's receive buffer size, in which 508 case this value is ignored. 509 Default: between 87380B and 6MB, depending on RAM size. 510 511tcp_sack - BOOLEAN 512 Enable select acknowledgments (SACKS). 513 514tcp_slow_start_after_idle - BOOLEAN 515 If set, provide RFC2861 behavior and time out the congestion 516 window after an idle period. An idle period is defined at 517 the current RTO. If unset, the congestion window will not 518 be timed out after an idle period. 519 Default: 1 520 521tcp_stdurg - BOOLEAN 522 Use the Host requirements interpretation of the TCP urgent pointer field. 523 Most hosts use the older BSD interpretation, so if you turn this on 524 Linux might not communicate correctly with them. 525 Default: FALSE 526 527tcp_synack_retries - INTEGER 528 Number of times SYNACKs for a passive TCP connection attempt will 529 be retransmitted. Should not be higher than 255. Default value 530 is 5, which corresponds to 31seconds till the last retransmission 531 with the current initial RTO of 1second. With this the final timeout 532 for a passive TCP connection will happen after 63seconds. 533 534tcp_syncookies - BOOLEAN 535 Only valid when the kernel was compiled with CONFIG_SYN_COOKIES 536 Send out syncookies when the syn backlog queue of a socket 537 overflows. This is to prevent against the common 'SYN flood attack' 538 Default: 1 539 540 Note, that syncookies is fallback facility. 541 It MUST NOT be used to help highly loaded servers to stand 542 against legal connection rate. If you see SYN flood warnings 543 in your logs, but investigation shows that they occur 544 because of overload with legal connections, you should tune 545 another parameters until this warning disappear. 546 See: tcp_max_syn_backlog, tcp_synack_retries, tcp_abort_on_overflow. 547 548 syncookies seriously violate TCP protocol, do not allow 549 to use TCP extensions, can result in serious degradation 550 of some services (f.e. SMTP relaying), visible not by you, 551 but your clients and relays, contacting you. While you see 552 SYN flood warnings in logs not being really flooded, your server 553 is seriously misconfigured. 554 555 If you want to test which effects syncookies have to your 556 network connections you can set this knob to 2 to enable 557 unconditionally generation of syncookies. 558 559tcp_fastopen - INTEGER 560 Enable TCP Fast Open feature (draft-ietf-tcpm-fastopen) to send data 561 in the opening SYN packet. To use this feature, the client application 562 must use sendmsg() or sendto() with MSG_FASTOPEN flag rather than 563 connect() to perform a TCP handshake automatically. 564 565 The values (bitmap) are 566 1: Enables sending data in the opening SYN on the client w/ MSG_FASTOPEN. 567 2: Enables TCP Fast Open on the server side, i.e., allowing data in 568 a SYN packet to be accepted and passed to the application before 569 3-way hand shake finishes. 570 4: Send data in the opening SYN regardless of cookie availability and 571 without a cookie option. 572 0x100: Accept SYN data w/o validating the cookie. 573 0x200: Accept data-in-SYN w/o any cookie option present. 574 0x400/0x800: Enable Fast Open on all listeners regardless of the 575 TCP_FASTOPEN socket option. The two different flags designate two 576 different ways of setting max_qlen without the TCP_FASTOPEN socket 577 option. 578 579 Default: 1 580 581 Note that the client & server side Fast Open flags (1 and 2 582 respectively) must be also enabled before the rest of flags can take 583 effect. 584 585 See include/net/tcp.h and the code for more details. 586 587tcp_syn_retries - INTEGER 588 Number of times initial SYNs for an active TCP connection attempt 589 will be retransmitted. Should not be higher than 255. Default value 590 is 6, which corresponds to 63seconds till the last retransmission 591 with the current initial RTO of 1second. With this the final timeout 592 for an active TCP connection attempt will happen after 127seconds. 593 594tcp_timestamps - BOOLEAN 595 Enable timestamps as defined in RFC1323. 596 597tcp_min_tso_segs - INTEGER 598 Minimal number of segments per TSO frame. 599 Since linux-3.12, TCP does an automatic sizing of TSO frames, 600 depending on flow rate, instead of filling 64Kbytes packets. 601 For specific usages, it's possible to force TCP to build big 602 TSO frames. Note that TCP stack might split too big TSO packets 603 if available window is too small. 604 Default: 2 605 606tcp_pacing_ss_ratio - INTEGER 607 sk->sk_pacing_rate is set by TCP stack using a ratio applied 608 to current rate. (current_rate = cwnd * mss / srtt) 609 If TCP is in slow start, tcp_pacing_ss_ratio is applied 610 to let TCP probe for bigger speeds, assuming cwnd can be 611 doubled every other RTT. 612 Default: 200 613 614tcp_pacing_ca_ratio - INTEGER 615 sk->sk_pacing_rate is set by TCP stack using a ratio applied 616 to current rate. (current_rate = cwnd * mss / srtt) 617 If TCP is in congestion avoidance phase, tcp_pacing_ca_ratio 618 is applied to conservatively probe for bigger throughput. 619 Default: 120 620 621tcp_tso_win_divisor - INTEGER 622 This allows control over what percentage of the congestion window 623 can be consumed by a single TSO frame. 624 The setting of this parameter is a choice between burstiness and 625 building larger TSO frames. 626 Default: 3 627 628tcp_tw_recycle - BOOLEAN 629 Enable fast recycling TIME-WAIT sockets. Default value is 0. 630 It should not be changed without advice/request of technical 631 experts. 632 633tcp_tw_reuse - BOOLEAN 634 Allow to reuse TIME-WAIT sockets for new connections when it is 635 safe from protocol viewpoint. Default value is 0. 636 It should not be changed without advice/request of technical 637 experts. 638 639tcp_window_scaling - BOOLEAN 640 Enable window scaling as defined in RFC1323. 641 642tcp_wmem - vector of 3 INTEGERs: min, default, max 643 min: Amount of memory reserved for send buffers for TCP sockets. 644 Each TCP socket has rights to use it due to fact of its birth. 645 Default: 1 page 646 647 default: initial size of send buffer used by TCP sockets. This 648 value overrides net.core.wmem_default used by other protocols. 649 It is usually lower than net.core.wmem_default. 650 Default: 16K 651 652 max: Maximal amount of memory allowed for automatically tuned 653 send buffers for TCP sockets. This value does not override 654 net.core.wmem_max. Calling setsockopt() with SO_SNDBUF disables 655 automatic tuning of that socket's send buffer size, in which case 656 this value is ignored. 657 Default: between 64K and 4MB, depending on RAM size. 658 659tcp_notsent_lowat - UNSIGNED INTEGER 660 A TCP socket can control the amount of unsent bytes in its write queue, 661 thanks to TCP_NOTSENT_LOWAT socket option. poll()/select()/epoll() 662 reports POLLOUT events if the amount of unsent bytes is below a per 663 socket value, and if the write queue is not full. sendmsg() will 664 also not add new buffers if the limit is hit. 665 666 This global variable controls the amount of unsent data for 667 sockets not using TCP_NOTSENT_LOWAT. For these sockets, a change 668 to the global variable has immediate effect. 669 670 Default: UINT_MAX (0xFFFFFFFF) 671 672tcp_workaround_signed_windows - BOOLEAN 673 If set, assume no receipt of a window scaling option means the 674 remote TCP is broken and treats the window as a signed quantity. 675 If unset, assume the remote TCP is not broken even if we do 676 not receive a window scaling option from them. 677 Default: 0 678 679tcp_thin_linear_timeouts - BOOLEAN 680 Enable dynamic triggering of linear timeouts for thin streams. 681 If set, a check is performed upon retransmission by timeout to 682 determine if the stream is thin (less than 4 packets in flight). 683 As long as the stream is found to be thin, up to 6 linear 684 timeouts may be performed before exponential backoff mode is 685 initiated. This improves retransmission latency for 686 non-aggressive thin streams, often found to be time-dependent. 687 For more information on thin streams, see 688 Documentation/networking/tcp-thin.txt 689 Default: 0 690 691tcp_thin_dupack - BOOLEAN 692 Enable dynamic triggering of retransmissions after one dupACK 693 for thin streams. If set, a check is performed upon reception 694 of a dupACK to determine if the stream is thin (less than 4 695 packets in flight). As long as the stream is found to be thin, 696 data is retransmitted on the first received dupACK. This 697 improves retransmission latency for non-aggressive thin 698 streams, often found to be time-dependent. 699 For more information on thin streams, see 700 Documentation/networking/tcp-thin.txt 701 Default: 0 702 703tcp_limit_output_bytes - INTEGER 704 Controls TCP Small Queue limit per tcp socket. 705 TCP bulk sender tends to increase packets in flight until it 706 gets losses notifications. With SNDBUF autotuning, this can 707 result in a large amount of packets queued in qdisc/device 708 on the local machine, hurting latency of other flows, for 709 typical pfifo_fast qdiscs. 710 tcp_limit_output_bytes limits the number of bytes on qdisc 711 or device to reduce artificial RTT/cwnd and reduce bufferbloat. 712 Default: 262144 713 714tcp_challenge_ack_limit - INTEGER 715 Limits number of Challenge ACK sent per second, as recommended 716 in RFC 5961 (Improving TCP's Robustness to Blind In-Window Attacks) 717 Default: 100 718 719UDP variables: 720 721udp_mem - vector of 3 INTEGERs: min, pressure, max 722 Number of pages allowed for queueing by all UDP sockets. 723 724 min: Below this number of pages UDP is not bothered about its 725 memory appetite. When amount of memory allocated by UDP exceeds 726 this number, UDP starts to moderate memory usage. 727 728 pressure: This value was introduced to follow format of tcp_mem. 729 730 max: Number of pages allowed for queueing by all UDP sockets. 731 732 Default is calculated at boot time from amount of available memory. 733 734udp_rmem_min - INTEGER 735 Minimal size of receive buffer used by UDP sockets in moderation. 736 Each UDP socket is able to use the size for receiving data, even if 737 total pages of UDP sockets exceed udp_mem pressure. The unit is byte. 738 Default: 1 page 739 740udp_wmem_min - INTEGER 741 Minimal size of send buffer used by UDP sockets in moderation. 742 Each UDP socket is able to use the size for sending data, even if 743 total pages of UDP sockets exceed udp_mem pressure. The unit is byte. 744 Default: 1 page 745 746CIPSOv4 Variables: 747 748cipso_cache_enable - BOOLEAN 749 If set, enable additions to and lookups from the CIPSO label mapping 750 cache. If unset, additions are ignored and lookups always result in a 751 miss. However, regardless of the setting the cache is still 752 invalidated when required when means you can safely toggle this on and 753 off and the cache will always be "safe". 754 Default: 1 755 756cipso_cache_bucket_size - INTEGER 757 The CIPSO label cache consists of a fixed size hash table with each 758 hash bucket containing a number of cache entries. This variable limits 759 the number of entries in each hash bucket; the larger the value the 760 more CIPSO label mappings that can be cached. When the number of 761 entries in a given hash bucket reaches this limit adding new entries 762 causes the oldest entry in the bucket to be removed to make room. 763 Default: 10 764 765cipso_rbm_optfmt - BOOLEAN 766 Enable the "Optimized Tag 1 Format" as defined in section 3.4.2.6 of 767 the CIPSO draft specification (see Documentation/netlabel for details). 768 This means that when set the CIPSO tag will be padded with empty 769 categories in order to make the packet data 32-bit aligned. 770 Default: 0 771 772cipso_rbm_structvalid - BOOLEAN 773 If set, do a very strict check of the CIPSO option when 774 ip_options_compile() is called. If unset, relax the checks done during 775 ip_options_compile(). Either way is "safe" as errors are caught else 776 where in the CIPSO processing code but setting this to 0 (False) should 777 result in less work (i.e. it should be faster) but could cause problems 778 with other implementations that require strict checking. 779 Default: 0 780 781IP Variables: 782 783ip_local_port_range - 2 INTEGERS 784 Defines the local port range that is used by TCP and UDP to 785 choose the local port. The first number is the first, the 786 second the last local port number. 787 If possible, it is better these numbers have different parity. 788 (one even and one odd values) 789 The default values are 32768 and 60999 respectively. 790 791ip_local_reserved_ports - list of comma separated ranges 792 Specify the ports which are reserved for known third-party 793 applications. These ports will not be used by automatic port 794 assignments (e.g. when calling connect() or bind() with port 795 number 0). Explicit port allocation behavior is unchanged. 796 797 The format used for both input and output is a comma separated 798 list of ranges (e.g. "1,2-4,10-10" for ports 1, 2, 3, 4 and 799 10). Writing to the file will clear all previously reserved 800 ports and update the current list with the one given in the 801 input. 802 803 Note that ip_local_port_range and ip_local_reserved_ports 804 settings are independent and both are considered by the kernel 805 when determining which ports are available for automatic port 806 assignments. 807 808 You can reserve ports which are not in the current 809 ip_local_port_range, e.g.: 810 811 $ cat /proc/sys/net/ipv4/ip_local_port_range 812 32000 60999 813 $ cat /proc/sys/net/ipv4/ip_local_reserved_ports 814 8080,9148 815 816 although this is redundant. However such a setting is useful 817 if later the port range is changed to a value that will 818 include the reserved ports. 819 820 Default: Empty 821 822ip_nonlocal_bind - BOOLEAN 823 If set, allows processes to bind() to non-local IP addresses, 824 which can be quite useful - but may break some applications. 825 Default: 0 826 827ip_dynaddr - BOOLEAN 828 If set non-zero, enables support for dynamic addresses. 829 If set to a non-zero value larger than 1, a kernel log 830 message will be printed when dynamic address rewriting 831 occurs. 832 Default: 0 833 834ip_early_demux - BOOLEAN 835 Optimize input packet processing down to one demux for 836 certain kinds of local sockets. Currently we only do this 837 for established TCP sockets. 838 839 It may add an additional cost for pure routing workloads that 840 reduces overall throughput, in such case you should disable it. 841 Default: 1 842 843icmp_echo_ignore_all - BOOLEAN 844 If set non-zero, then the kernel will ignore all ICMP ECHO 845 requests sent to it. 846 Default: 0 847 848icmp_echo_ignore_broadcasts - BOOLEAN 849 If set non-zero, then the kernel will ignore all ICMP ECHO and 850 TIMESTAMP requests sent to it via broadcast/multicast. 851 Default: 1 852 853icmp_ratelimit - INTEGER 854 Limit the maximal rates for sending ICMP packets whose type matches 855 icmp_ratemask (see below) to specific targets. 856 0 to disable any limiting, 857 otherwise the minimal space between responses in milliseconds. 858 Note that another sysctl, icmp_msgs_per_sec limits the number 859 of ICMP packets sent on all targets. 860 Default: 1000 861 862icmp_msgs_per_sec - INTEGER 863 Limit maximal number of ICMP packets sent per second from this host. 864 Only messages whose type matches icmp_ratemask (see below) are 865 controlled by this limit. 866 Default: 1000 867 868icmp_msgs_burst - INTEGER 869 icmp_msgs_per_sec controls number of ICMP packets sent per second, 870 while icmp_msgs_burst controls the burst size of these packets. 871 Default: 50 872 873icmp_ratemask - INTEGER 874 Mask made of ICMP types for which rates are being limited. 875 Significant bits: IHGFEDCBA9876543210 876 Default mask: 0000001100000011000 (6168) 877 878 Bit definitions (see include/linux/icmp.h): 879 0 Echo Reply 880 3 Destination Unreachable * 881 4 Source Quench * 882 5 Redirect 883 8 Echo Request 884 B Time Exceeded * 885 C Parameter Problem * 886 D Timestamp Request 887 E Timestamp Reply 888 F Info Request 889 G Info Reply 890 H Address Mask Request 891 I Address Mask Reply 892 893 * These are rate limited by default (see default mask above) 894 895icmp_ignore_bogus_error_responses - BOOLEAN 896 Some routers violate RFC1122 by sending bogus responses to broadcast 897 frames. Such violations are normally logged via a kernel warning. 898 If this is set to TRUE, the kernel will not give such warnings, which 899 will avoid log file clutter. 900 Default: 1 901 902icmp_errors_use_inbound_ifaddr - BOOLEAN 903 904 If zero, icmp error messages are sent with the primary address of 905 the exiting interface. 906 907 If non-zero, the message will be sent with the primary address of 908 the interface that received the packet that caused the icmp error. 909 This is the behaviour network many administrators will expect from 910 a router. And it can make debugging complicated network layouts 911 much easier. 912 913 Note that if no primary address exists for the interface selected, 914 then the primary address of the first non-loopback interface that 915 has one will be used regardless of this setting. 916 917 Default: 0 918 919igmp_max_memberships - INTEGER 920 Change the maximum number of multicast groups we can subscribe to. 921 Default: 20 922 923 Theoretical maximum value is bounded by having to send a membership 924 report in a single datagram (i.e. the report can't span multiple 925 datagrams, or risk confusing the switch and leaving groups you don't 926 intend to). 927 928 The number of supported groups 'M' is bounded by the number of group 929 report entries you can fit into a single datagram of 65535 bytes. 930 931 M = 65536-sizeof (ip header)/(sizeof(Group record)) 932 933 Group records are variable length, with a minimum of 12 bytes. 934 So net.ipv4.igmp_max_memberships should not be set higher than: 935 936 (65536-24) / 12 = 5459 937 938 The value 5459 assumes no IP header options, so in practice 939 this number may be lower. 940 941 conf/interface/* changes special settings per interface (where 942 "interface" is the name of your network interface) 943 944 conf/all/* is special, changes the settings for all interfaces 945 946igmp_qrv - INTEGER 947 Controls the IGMP query robustness variable (see RFC2236 8.1). 948 Default: 2 (as specified by RFC2236 8.1) 949 Minimum: 1 (as specified by RFC6636 4.5) 950 951log_martians - BOOLEAN 952 Log packets with impossible addresses to kernel log. 953 log_martians for the interface will be enabled if at least one of 954 conf/{all,interface}/log_martians is set to TRUE, 955 it will be disabled otherwise 956 957accept_redirects - BOOLEAN 958 Accept ICMP redirect messages. 959 accept_redirects for the interface will be enabled if: 960 - both conf/{all,interface}/accept_redirects are TRUE in the case 961 forwarding for the interface is enabled 962 or 963 - at least one of conf/{all,interface}/accept_redirects is TRUE in the 964 case forwarding for the interface is disabled 965 accept_redirects for the interface will be disabled otherwise 966 default TRUE (host) 967 FALSE (router) 968 969forwarding - BOOLEAN 970 Enable IP forwarding on this interface. 971 972mc_forwarding - BOOLEAN 973 Do multicast routing. The kernel needs to be compiled with CONFIG_MROUTE 974 and a multicast routing daemon is required. 975 conf/all/mc_forwarding must also be set to TRUE to enable multicast 976 routing for the interface 977 978medium_id - INTEGER 979 Integer value used to differentiate the devices by the medium they 980 are attached to. Two devices can have different id values when 981 the broadcast packets are received only on one of them. 982 The default value 0 means that the device is the only interface 983 to its medium, value of -1 means that medium is not known. 984 985 Currently, it is used to change the proxy_arp behavior: 986 the proxy_arp feature is enabled for packets forwarded between 987 two devices attached to different media. 988 989proxy_arp - BOOLEAN 990 Do proxy arp. 991 proxy_arp for the interface will be enabled if at least one of 992 conf/{all,interface}/proxy_arp is set to TRUE, 993 it will be disabled otherwise 994 995proxy_arp_pvlan - BOOLEAN 996 Private VLAN proxy arp. 997 Basically allow proxy arp replies back to the same interface 998 (from which the ARP request/solicitation was received). 999 1000 This is done to support (ethernet) switch features, like RFC 1001 3069, where the individual ports are NOT allowed to 1002 communicate with each other, but they are allowed to talk to 1003 the upstream router. As described in RFC 3069, it is possible 1004 to allow these hosts to communicate through the upstream 1005 router by proxy_arp'ing. Don't need to be used together with 1006 proxy_arp. 1007 1008 This technology is known by different names: 1009 In RFC 3069 it is called VLAN Aggregation. 1010 Cisco and Allied Telesyn call it Private VLAN. 1011 Hewlett-Packard call it Source-Port filtering or port-isolation. 1012 Ericsson call it MAC-Forced Forwarding (RFC Draft). 1013 1014shared_media - BOOLEAN 1015 Send(router) or accept(host) RFC1620 shared media redirects. 1016 Overrides ip_secure_redirects. 1017 shared_media for the interface will be enabled if at least one of 1018 conf/{all,interface}/shared_media is set to TRUE, 1019 it will be disabled otherwise 1020 default TRUE 1021 1022secure_redirects - BOOLEAN 1023 Accept ICMP redirect messages only for gateways, 1024 listed in default gateway list. 1025 secure_redirects for the interface will be enabled if at least one of 1026 conf/{all,interface}/secure_redirects is set to TRUE, 1027 it will be disabled otherwise 1028 default TRUE 1029 1030send_redirects - BOOLEAN 1031 Send redirects, if router. 1032 send_redirects for the interface will be enabled if at least one of 1033 conf/{all,interface}/send_redirects is set to TRUE, 1034 it will be disabled otherwise 1035 Default: TRUE 1036 1037bootp_relay - BOOLEAN 1038 Accept packets with source address 0.b.c.d destined 1039 not to this host as local ones. It is supposed, that 1040 BOOTP relay daemon will catch and forward such packets. 1041 conf/all/bootp_relay must also be set to TRUE to enable BOOTP relay 1042 for the interface 1043 default FALSE 1044 Not Implemented Yet. 1045 1046accept_source_route - BOOLEAN 1047 Accept packets with SRR option. 1048 conf/all/accept_source_route must also be set to TRUE to accept packets 1049 with SRR option on the interface 1050 default TRUE (router) 1051 FALSE (host) 1052 1053accept_local - BOOLEAN 1054 Accept packets with local source addresses. In combination with 1055 suitable routing, this can be used to direct packets between two 1056 local interfaces over the wire and have them accepted properly. 1057 default FALSE 1058 1059route_localnet - BOOLEAN 1060 Do not consider loopback addresses as martian source or destination 1061 while routing. This enables the use of 127/8 for local routing purposes. 1062 default FALSE 1063 1064rp_filter - INTEGER 1065 0 - No source validation. 1066 1 - Strict mode as defined in RFC3704 Strict Reverse Path 1067 Each incoming packet is tested against the FIB and if the interface 1068 is not the best reverse path the packet check will fail. 1069 By default failed packets are discarded. 1070 2 - Loose mode as defined in RFC3704 Loose Reverse Path 1071 Each incoming packet's source address is also tested against the FIB 1072 and if the source address is not reachable via any interface 1073 the packet check will fail. 1074 1075 Current recommended practice in RFC3704 is to enable strict mode 1076 to prevent IP spoofing from DDos attacks. If using asymmetric routing 1077 or other complicated routing, then loose mode is recommended. 1078 1079 The max value from conf/{all,interface}/rp_filter is used 1080 when doing source validation on the {interface}. 1081 1082 Default value is 0. Note that some distributions enable it 1083 in startup scripts. 1084 1085arp_filter - BOOLEAN 1086 1 - Allows you to have multiple network interfaces on the same 1087 subnet, and have the ARPs for each interface be answered 1088 based on whether or not the kernel would route a packet from 1089 the ARP'd IP out that interface (therefore you must use source 1090 based routing for this to work). In other words it allows control 1091 of which cards (usually 1) will respond to an arp request. 1092 1093 0 - (default) The kernel can respond to arp requests with addresses 1094 from other interfaces. This may seem wrong but it usually makes 1095 sense, because it increases the chance of successful communication. 1096 IP addresses are owned by the complete host on Linux, not by 1097 particular interfaces. Only for more complex setups like load- 1098 balancing, does this behaviour cause problems. 1099 1100 arp_filter for the interface will be enabled if at least one of 1101 conf/{all,interface}/arp_filter is set to TRUE, 1102 it will be disabled otherwise 1103 1104arp_announce - INTEGER 1105 Define different restriction levels for announcing the local 1106 source IP address from IP packets in ARP requests sent on 1107 interface: 1108 0 - (default) Use any local address, configured on any interface 1109 1 - Try to avoid local addresses that are not in the target's 1110 subnet for this interface. This mode is useful when target 1111 hosts reachable via this interface require the source IP 1112 address in ARP requests to be part of their logical network 1113 configured on the receiving interface. When we generate the 1114 request we will check all our subnets that include the 1115 target IP and will preserve the source address if it is from 1116 such subnet. If there is no such subnet we select source 1117 address according to the rules for level 2. 1118 2 - Always use the best local address for this target. 1119 In this mode we ignore the source address in the IP packet 1120 and try to select local address that we prefer for talks with 1121 the target host. Such local address is selected by looking 1122 for primary IP addresses on all our subnets on the outgoing 1123 interface that include the target IP address. If no suitable 1124 local address is found we select the first local address 1125 we have on the outgoing interface or on all other interfaces, 1126 with the hope we will receive reply for our request and 1127 even sometimes no matter the source IP address we announce. 1128 1129 The max value from conf/{all,interface}/arp_announce is used. 1130 1131 Increasing the restriction level gives more chance for 1132 receiving answer from the resolved target while decreasing 1133 the level announces more valid sender's information. 1134 1135arp_ignore - INTEGER 1136 Define different modes for sending replies in response to 1137 received ARP requests that resolve local target IP addresses: 1138 0 - (default): reply for any local target IP address, configured 1139 on any interface 1140 1 - reply only if the target IP address is local address 1141 configured on the incoming interface 1142 2 - reply only if the target IP address is local address 1143 configured on the incoming interface and both with the 1144 sender's IP address are part from same subnet on this interface 1145 3 - do not reply for local addresses configured with scope host, 1146 only resolutions for global and link addresses are replied 1147 4-7 - reserved 1148 8 - do not reply for all local addresses 1149 1150 The max value from conf/{all,interface}/arp_ignore is used 1151 when ARP request is received on the {interface} 1152 1153arp_notify - BOOLEAN 1154 Define mode for notification of address and device changes. 1155 0 - (default): do nothing 1156 1 - Generate gratuitous arp requests when device is brought up 1157 or hardware address changes. 1158 1159arp_accept - BOOLEAN 1160 Define behavior for gratuitous ARP frames who's IP is not 1161 already present in the ARP table: 1162 0 - don't create new entries in the ARP table 1163 1 - create new entries in the ARP table 1164 1165 Both replies and requests type gratuitous arp will trigger the 1166 ARP table to be updated, if this setting is on. 1167 1168 If the ARP table already contains the IP address of the 1169 gratuitous arp frame, the arp table will be updated regardless 1170 if this setting is on or off. 1171 1172mcast_solicit - INTEGER 1173 The maximum number of multicast probes in INCOMPLETE state, 1174 when the associated hardware address is unknown. Defaults 1175 to 3. 1176 1177ucast_solicit - INTEGER 1178 The maximum number of unicast probes in PROBE state, when 1179 the hardware address is being reconfirmed. Defaults to 3. 1180 1181app_solicit - INTEGER 1182 The maximum number of probes to send to the user space ARP daemon 1183 via netlink before dropping back to multicast probes (see 1184 mcast_resolicit). Defaults to 0. 1185 1186mcast_resolicit - INTEGER 1187 The maximum number of multicast probes after unicast and 1188 app probes in PROBE state. Defaults to 0. 1189 1190disable_policy - BOOLEAN 1191 Disable IPSEC policy (SPD) for this interface 1192 1193disable_xfrm - BOOLEAN 1194 Disable IPSEC encryption on this interface, whatever the policy 1195 1196igmpv2_unsolicited_report_interval - INTEGER 1197 The interval in milliseconds in which the next unsolicited 1198 IGMPv1 or IGMPv2 report retransmit will take place. 1199 Default: 10000 (10 seconds) 1200 1201igmpv3_unsolicited_report_interval - INTEGER 1202 The interval in milliseconds in which the next unsolicited 1203 IGMPv3 report retransmit will take place. 1204 Default: 1000 (1 seconds) 1205 1206promote_secondaries - BOOLEAN 1207 When a primary IP address is removed from this interface 1208 promote a corresponding secondary IP address instead of 1209 removing all the corresponding secondary IP addresses. 1210 1211 1212tag - INTEGER 1213 Allows you to write a number, which can be used as required. 1214 Default value is 0. 1215 1216xfrm4_gc_thresh - INTEGER 1217 The threshold at which we will start garbage collecting for IPv4 1218 destination cache entries. At twice this value the system will 1219 refuse new allocations. The value must be set below the flowcache 1220 limit (4096 * number of online cpus) to take effect. 1221 1222igmp_link_local_mcast_reports - BOOLEAN 1223 Enable IGMP reports for link local multicast groups in the 1224 224.0.0.X range. 1225 Default TRUE 1226 1227Alexey Kuznetsov. 1228kuznet@ms2.inr.ac.ru 1229 1230Updated by: 1231Andi Kleen 1232ak@muc.de 1233Nicolas Delon 1234delon.nicolas@wanadoo.fr 1235 1236 1237 1238 1239/proc/sys/net/ipv6/* Variables: 1240 1241IPv6 has no global variables such as tcp_*. tcp_* settings under ipv4/ also 1242apply to IPv6 [XXX?]. 1243 1244bindv6only - BOOLEAN 1245 Default value for IPV6_V6ONLY socket option, 1246 which restricts use of the IPv6 socket to IPv6 communication 1247 only. 1248 TRUE: disable IPv4-mapped address feature 1249 FALSE: enable IPv4-mapped address feature 1250 1251 Default: FALSE (as specified in RFC3493) 1252 1253flowlabel_consistency - BOOLEAN 1254 Protect the consistency (and unicity) of flow label. 1255 You have to disable it to use IPV6_FL_F_REFLECT flag on the 1256 flow label manager. 1257 TRUE: enabled 1258 FALSE: disabled 1259 Default: TRUE 1260 1261auto_flowlabels - INTEGER 1262 Automatically generate flow labels based on a flow hash of the 1263 packet. This allows intermediate devices, such as routers, to 1264 identify packet flows for mechanisms like Equal Cost Multipath 1265 Routing (see RFC 6438). 1266 0: automatic flow labels are completely disabled 1267 1: automatic flow labels are enabled by default, they can be 1268 disabled on a per socket basis using the IPV6_AUTOFLOWLABEL 1269 socket option 1270 2: automatic flow labels are allowed, they may be enabled on a 1271 per socket basis using the IPV6_AUTOFLOWLABEL socket option 1272 3: automatic flow labels are enabled and enforced, they cannot 1273 be disabled by the socket option 1274 Default: 1 1275 1276flowlabel_state_ranges - BOOLEAN 1277 Split the flow label number space into two ranges. 0-0x7FFFF is 1278 reserved for the IPv6 flow manager facility, 0x80000-0xFFFFF 1279 is reserved for stateless flow labels as described in RFC6437. 1280 TRUE: enabled 1281 FALSE: disabled 1282 Default: true 1283 1284anycast_src_echo_reply - BOOLEAN 1285 Controls the use of anycast addresses as source addresses for ICMPv6 1286 echo reply 1287 TRUE: enabled 1288 FALSE: disabled 1289 Default: FALSE 1290 1291idgen_delay - INTEGER 1292 Controls the delay in seconds after which time to retry 1293 privacy stable address generation if a DAD conflict is 1294 detected. 1295 Default: 1 (as specified in RFC7217) 1296 1297idgen_retries - INTEGER 1298 Controls the number of retries to generate a stable privacy 1299 address if a DAD conflict is detected. 1300 Default: 3 (as specified in RFC7217) 1301 1302mld_qrv - INTEGER 1303 Controls the MLD query robustness variable (see RFC3810 9.1). 1304 Default: 2 (as specified by RFC3810 9.1) 1305 Minimum: 1 (as specified by RFC6636 4.5) 1306 1307IPv6 Fragmentation: 1308 1309ip6frag_high_thresh - INTEGER 1310 Maximum memory used to reassemble IPv6 fragments. When 1311 ip6frag_high_thresh bytes of memory is allocated for this purpose, 1312 the fragment handler will toss packets until ip6frag_low_thresh 1313 is reached. 1314 1315ip6frag_low_thresh - INTEGER 1316 See ip6frag_high_thresh 1317 1318ip6frag_time - INTEGER 1319 Time in seconds to keep an IPv6 fragment in memory. 1320 1321conf/default/*: 1322 Change the interface-specific default settings. 1323 1324 1325conf/all/*: 1326 Change all the interface-specific settings. 1327 1328 [XXX: Other special features than forwarding?] 1329 1330conf/all/forwarding - BOOLEAN 1331 Enable global IPv6 forwarding between all interfaces. 1332 1333 IPv4 and IPv6 work differently here; e.g. netfilter must be used 1334 to control which interfaces may forward packets and which not. 1335 1336 This also sets all interfaces' Host/Router setting 1337 'forwarding' to the specified value. See below for details. 1338 1339 This referred to as global forwarding. 1340 1341proxy_ndp - BOOLEAN 1342 Do proxy ndp. 1343 1344fwmark_reflect - BOOLEAN 1345 Controls the fwmark of kernel-generated IPv6 reply packets that are not 1346 associated with a socket for example, TCP RSTs or ICMPv6 echo replies). 1347 If unset, these packets have a fwmark of zero. If set, they have the 1348 fwmark of the packet they are replying to. 1349 Default: 0 1350 1351conf/interface/*: 1352 Change special settings per interface. 1353 1354 The functional behaviour for certain settings is different 1355 depending on whether local forwarding is enabled or not. 1356 1357accept_ra - INTEGER 1358 Accept Router Advertisements; autoconfigure using them. 1359 1360 It also determines whether or not to transmit Router 1361 Solicitations. If and only if the functional setting is to 1362 accept Router Advertisements, Router Solicitations will be 1363 transmitted. 1364 1365 Possible values are: 1366 0 Do not accept Router Advertisements. 1367 1 Accept Router Advertisements if forwarding is disabled. 1368 2 Overrule forwarding behaviour. Accept Router Advertisements 1369 even if forwarding is enabled. 1370 1371 Functional default: enabled if local forwarding is disabled. 1372 disabled if local forwarding is enabled. 1373 1374accept_ra_defrtr - BOOLEAN 1375 Learn default router in Router Advertisement. 1376 1377 Functional default: enabled if accept_ra is enabled. 1378 disabled if accept_ra is disabled. 1379 1380accept_ra_from_local - BOOLEAN 1381 Accept RA with source-address that is found on local machine 1382 if the RA is otherwise proper and able to be accepted. 1383 Default is to NOT accept these as it may be an un-intended 1384 network loop. 1385 1386 Functional default: 1387 enabled if accept_ra_from_local is enabled 1388 on a specific interface. 1389 disabled if accept_ra_from_local is disabled 1390 on a specific interface. 1391 1392accept_ra_min_hop_limit - INTEGER 1393 Minimum hop limit Information in Router Advertisement. 1394 1395 Hop limit Information in Router Advertisement less than this 1396 variable shall be ignored. 1397 1398 Default: 1 1399 1400accept_ra_pinfo - BOOLEAN 1401 Learn Prefix Information in Router Advertisement. 1402 1403 Functional default: enabled if accept_ra is enabled. 1404 disabled if accept_ra is disabled. 1405 1406accept_ra_rt_info_max_plen - INTEGER 1407 Maximum prefix length of Route Information in RA. 1408 1409 Route Information w/ prefix larger than or equal to this 1410 variable shall be ignored. 1411 1412 Functional default: 0 if accept_ra_rtr_pref is enabled. 1413 -1 if accept_ra_rtr_pref is disabled. 1414 1415accept_ra_rtr_pref - BOOLEAN 1416 Accept Router Preference in RA. 1417 1418 Functional default: enabled if accept_ra is enabled. 1419 disabled if accept_ra is disabled. 1420 1421accept_ra_mtu - BOOLEAN 1422 Apply the MTU value specified in RA option 5 (RFC4861). If 1423 disabled, the MTU specified in the RA will be ignored. 1424 1425 Functional default: enabled if accept_ra is enabled. 1426 disabled if accept_ra is disabled. 1427 1428accept_redirects - BOOLEAN 1429 Accept Redirects. 1430 1431 Functional default: enabled if local forwarding is disabled. 1432 disabled if local forwarding is enabled. 1433 1434accept_source_route - INTEGER 1435 Accept source routing (routing extension header). 1436 1437 >= 0: Accept only routing header type 2. 1438 < 0: Do not accept routing header. 1439 1440 Default: 0 1441 1442autoconf - BOOLEAN 1443 Autoconfigure addresses using Prefix Information in Router 1444 Advertisements. 1445 1446 Functional default: enabled if accept_ra_pinfo is enabled. 1447 disabled if accept_ra_pinfo is disabled. 1448 1449dad_transmits - INTEGER 1450 The amount of Duplicate Address Detection probes to send. 1451 Default: 1 1452 1453forwarding - INTEGER 1454 Configure interface-specific Host/Router behaviour. 1455 1456 Note: It is recommended to have the same setting on all 1457 interfaces; mixed router/host scenarios are rather uncommon. 1458 1459 Possible values are: 1460 0 Forwarding disabled 1461 1 Forwarding enabled 1462 1463 FALSE (0): 1464 1465 By default, Host behaviour is assumed. This means: 1466 1467 1. IsRouter flag is not set in Neighbour Advertisements. 1468 2. If accept_ra is TRUE (default), transmit Router 1469 Solicitations. 1470 3. If accept_ra is TRUE (default), accept Router 1471 Advertisements (and do autoconfiguration). 1472 4. If accept_redirects is TRUE (default), accept Redirects. 1473 1474 TRUE (1): 1475 1476 If local forwarding is enabled, Router behaviour is assumed. 1477 This means exactly the reverse from the above: 1478 1479 1. IsRouter flag is set in Neighbour Advertisements. 1480 2. Router Solicitations are not sent unless accept_ra is 2. 1481 3. Router Advertisements are ignored unless accept_ra is 2. 1482 4. Redirects are ignored. 1483 1484 Default: 0 (disabled) if global forwarding is disabled (default), 1485 otherwise 1 (enabled). 1486 1487hop_limit - INTEGER 1488 Default Hop Limit to set. 1489 Default: 64 1490 1491mtu - INTEGER 1492 Default Maximum Transfer Unit 1493 Default: 1280 (IPv6 required minimum) 1494 1495ip_nonlocal_bind - BOOLEAN 1496 If set, allows processes to bind() to non-local IPv6 addresses, 1497 which can be quite useful - but may break some applications. 1498 Default: 0 1499 1500router_probe_interval - INTEGER 1501 Minimum interval (in seconds) between Router Probing described 1502 in RFC4191. 1503 1504 Default: 60 1505 1506router_solicitation_delay - INTEGER 1507 Number of seconds to wait after interface is brought up 1508 before sending Router Solicitations. 1509 Default: 1 1510 1511router_solicitation_interval - INTEGER 1512 Number of seconds to wait between Router Solicitations. 1513 Default: 4 1514 1515router_solicitations - INTEGER 1516 Number of Router Solicitations to send until assuming no 1517 routers are present. 1518 Default: 3 1519 1520use_oif_addrs_only - BOOLEAN 1521 When enabled, the candidate source addresses for destinations 1522 routed via this interface are restricted to the set of addresses 1523 configured on this interface (vis. RFC 6724, section 4). 1524 1525 Default: false 1526 1527use_tempaddr - INTEGER 1528 Preference for Privacy Extensions (RFC3041). 1529 <= 0 : disable Privacy Extensions 1530 == 1 : enable Privacy Extensions, but prefer public 1531 addresses over temporary addresses. 1532 > 1 : enable Privacy Extensions and prefer temporary 1533 addresses over public addresses. 1534 Default: 0 (for most devices) 1535 -1 (for point-to-point devices and loopback devices) 1536 1537temp_valid_lft - INTEGER 1538 valid lifetime (in seconds) for temporary addresses. 1539 Default: 604800 (7 days) 1540 1541temp_prefered_lft - INTEGER 1542 Preferred lifetime (in seconds) for temporary addresses. 1543 Default: 86400 (1 day) 1544 1545max_desync_factor - INTEGER 1546 Maximum value for DESYNC_FACTOR, which is a random value 1547 that ensures that clients don't synchronize with each 1548 other and generate new addresses at exactly the same time. 1549 value is in seconds. 1550 Default: 600 1551 1552regen_max_retry - INTEGER 1553 Number of attempts before give up attempting to generate 1554 valid temporary addresses. 1555 Default: 5 1556 1557max_addresses - INTEGER 1558 Maximum number of autoconfigured addresses per interface. Setting 1559 to zero disables the limitation. It is not recommended to set this 1560 value too large (or to zero) because it would be an easy way to 1561 crash the kernel by allowing too many addresses to be created. 1562 Default: 16 1563 1564disable_ipv6 - BOOLEAN 1565 Disable IPv6 operation. If accept_dad is set to 2, this value 1566 will be dynamically set to TRUE if DAD fails for the link-local 1567 address. 1568 Default: FALSE (enable IPv6 operation) 1569 1570 When this value is changed from 1 to 0 (IPv6 is being enabled), 1571 it will dynamically create a link-local address on the given 1572 interface and start Duplicate Address Detection, if necessary. 1573 1574 When this value is changed from 0 to 1 (IPv6 is being disabled), 1575 it will dynamically delete all address on the given interface. 1576 1577accept_dad - INTEGER 1578 Whether to accept DAD (Duplicate Address Detection). 1579 0: Disable DAD 1580 1: Enable DAD (default) 1581 2: Enable DAD, and disable IPv6 operation if MAC-based duplicate 1582 link-local address has been found. 1583 1584force_tllao - BOOLEAN 1585 Enable sending the target link-layer address option even when 1586 responding to a unicast neighbor solicitation. 1587 Default: FALSE 1588 1589 Quoting from RFC 2461, section 4.4, Target link-layer address: 1590 1591 "The option MUST be included for multicast solicitations in order to 1592 avoid infinite Neighbor Solicitation "recursion" when the peer node 1593 does not have a cache entry to return a Neighbor Advertisements 1594 message. When responding to unicast solicitations, the option can be 1595 omitted since the sender of the solicitation has the correct link- 1596 layer address; otherwise it would not have be able to send the unicast 1597 solicitation in the first place. However, including the link-layer 1598 address in this case adds little overhead and eliminates a potential 1599 race condition where the sender deletes the cached link-layer address 1600 prior to receiving a response to a previous solicitation." 1601 1602ndisc_notify - BOOLEAN 1603 Define mode for notification of address and device changes. 1604 0 - (default): do nothing 1605 1 - Generate unsolicited neighbour advertisements when device is brought 1606 up or hardware address changes. 1607 1608mldv1_unsolicited_report_interval - INTEGER 1609 The interval in milliseconds in which the next unsolicited 1610 MLDv1 report retransmit will take place. 1611 Default: 10000 (10 seconds) 1612 1613mldv2_unsolicited_report_interval - INTEGER 1614 The interval in milliseconds in which the next unsolicited 1615 MLDv2 report retransmit will take place. 1616 Default: 1000 (1 second) 1617 1618force_mld_version - INTEGER 1619 0 - (default) No enforcement of a MLD version, MLDv1 fallback allowed 1620 1 - Enforce to use MLD version 1 1621 2 - Enforce to use MLD version 2 1622 1623suppress_frag_ndisc - INTEGER 1624 Control RFC 6980 (Security Implications of IPv6 Fragmentation 1625 with IPv6 Neighbor Discovery) behavior: 1626 1 - (default) discard fragmented neighbor discovery packets 1627 0 - allow fragmented neighbor discovery packets 1628 1629optimistic_dad - BOOLEAN 1630 Whether to perform Optimistic Duplicate Address Detection (RFC 4429). 1631 0: disabled (default) 1632 1: enabled 1633 1634use_optimistic - BOOLEAN 1635 If enabled, do not classify optimistic addresses as deprecated during 1636 source address selection. Preferred addresses will still be chosen 1637 before optimistic addresses, subject to other ranking in the source 1638 address selection algorithm. 1639 0: disabled (default) 1640 1: enabled 1641 1642stable_secret - IPv6 address 1643 This IPv6 address will be used as a secret to generate IPv6 1644 addresses for link-local addresses and autoconfigured 1645 ones. All addresses generated after setting this secret will 1646 be stable privacy ones by default. This can be changed via the 1647 addrgenmode ip-link. conf/default/stable_secret is used as the 1648 secret for the namespace, the interface specific ones can 1649 overwrite that. Writes to conf/all/stable_secret are refused. 1650 1651 It is recommended to generate this secret during installation 1652 of a system and keep it stable after that. 1653 1654 By default the stable secret is unset. 1655 1656icmp/*: 1657ratelimit - INTEGER 1658 Limit the maximal rates for sending ICMPv6 packets. 1659 0 to disable any limiting, 1660 otherwise the minimal space between responses in milliseconds. 1661 Default: 1000 1662 1663xfrm6_gc_thresh - INTEGER 1664 The threshold at which we will start garbage collecting for IPv6 1665 destination cache entries. At twice this value the system will 1666 refuse new allocations. The value must be set below the flowcache 1667 limit (4096 * number of online cpus) to take effect. 1668 1669 1670IPv6 Update by: 1671Pekka Savola <pekkas@netcore.fi> 1672YOSHIFUJI Hideaki / USAGI Project <yoshfuji@linux-ipv6.org> 1673 1674 1675/proc/sys/net/bridge/* Variables: 1676 1677bridge-nf-call-arptables - BOOLEAN 1678 1 : pass bridged ARP traffic to arptables' FORWARD chain. 1679 0 : disable this. 1680 Default: 1 1681 1682bridge-nf-call-iptables - BOOLEAN 1683 1 : pass bridged IPv4 traffic to iptables' chains. 1684 0 : disable this. 1685 Default: 1 1686 1687bridge-nf-call-ip6tables - BOOLEAN 1688 1 : pass bridged IPv6 traffic to ip6tables' chains. 1689 0 : disable this. 1690 Default: 1 1691 1692bridge-nf-filter-vlan-tagged - BOOLEAN 1693 1 : pass bridged vlan-tagged ARP/IP/IPv6 traffic to {arp,ip,ip6}tables. 1694 0 : disable this. 1695 Default: 0 1696 1697bridge-nf-filter-pppoe-tagged - BOOLEAN 1698 1 : pass bridged pppoe-tagged IP/IPv6 traffic to {ip,ip6}tables. 1699 0 : disable this. 1700 Default: 0 1701 1702bridge-nf-pass-vlan-input-dev - BOOLEAN 1703 1: if bridge-nf-filter-vlan-tagged is enabled, try to find a vlan 1704 interface on the bridge and set the netfilter input device to the vlan. 1705 This allows use of e.g. "iptables -i br0.1" and makes the REDIRECT 1706 target work with vlan-on-top-of-bridge interfaces. When no matching 1707 vlan interface is found, or this switch is off, the input device is 1708 set to the bridge interface. 1709 0: disable bridge netfilter vlan interface lookup. 1710 Default: 0 1711 1712proc/sys/net/sctp/* Variables: 1713 1714addip_enable - BOOLEAN 1715 Enable or disable extension of Dynamic Address Reconfiguration 1716 (ADD-IP) functionality specified in RFC5061. This extension provides 1717 the ability to dynamically add and remove new addresses for the SCTP 1718 associations. 1719 1720 1: Enable extension. 1721 1722 0: Disable extension. 1723 1724 Default: 0 1725 1726addip_noauth_enable - BOOLEAN 1727 Dynamic Address Reconfiguration (ADD-IP) requires the use of 1728 authentication to protect the operations of adding or removing new 1729 addresses. This requirement is mandated so that unauthorized hosts 1730 would not be able to hijack associations. However, older 1731 implementations may not have implemented this requirement while 1732 allowing the ADD-IP extension. For reasons of interoperability, 1733 we provide this variable to control the enforcement of the 1734 authentication requirement. 1735 1736 1: Allow ADD-IP extension to be used without authentication. This 1737 should only be set in a closed environment for interoperability 1738 with older implementations. 1739 1740 0: Enforce the authentication requirement 1741 1742 Default: 0 1743 1744auth_enable - BOOLEAN 1745 Enable or disable Authenticated Chunks extension. This extension 1746 provides the ability to send and receive authenticated chunks and is 1747 required for secure operation of Dynamic Address Reconfiguration 1748 (ADD-IP) extension. 1749 1750 1: Enable this extension. 1751 0: Disable this extension. 1752 1753 Default: 0 1754 1755prsctp_enable - BOOLEAN 1756 Enable or disable the Partial Reliability extension (RFC3758) which 1757 is used to notify peers that a given DATA should no longer be expected. 1758 1759 1: Enable extension 1760 0: Disable 1761 1762 Default: 1 1763 1764max_burst - INTEGER 1765 The limit of the number of new packets that can be initially sent. It 1766 controls how bursty the generated traffic can be. 1767 1768 Default: 4 1769 1770association_max_retrans - INTEGER 1771 Set the maximum number for retransmissions that an association can 1772 attempt deciding that the remote end is unreachable. If this value 1773 is exceeded, the association is terminated. 1774 1775 Default: 10 1776 1777max_init_retransmits - INTEGER 1778 The maximum number of retransmissions of INIT and COOKIE-ECHO chunks 1779 that an association will attempt before declaring the destination 1780 unreachable and terminating. 1781 1782 Default: 8 1783 1784path_max_retrans - INTEGER 1785 The maximum number of retransmissions that will be attempted on a given 1786 path. Once this threshold is exceeded, the path is considered 1787 unreachable, and new traffic will use a different path when the 1788 association is multihomed. 1789 1790 Default: 5 1791 1792pf_retrans - INTEGER 1793 The number of retransmissions that will be attempted on a given path 1794 before traffic is redirected to an alternate transport (should one 1795 exist). Note this is distinct from path_max_retrans, as a path that 1796 passes the pf_retrans threshold can still be used. Its only 1797 deprioritized when a transmission path is selected by the stack. This 1798 setting is primarily used to enable fast failover mechanisms without 1799 having to reduce path_max_retrans to a very low value. See: 1800 http://www.ietf.org/id/draft-nishida-tsvwg-sctp-failover-05.txt 1801 for details. Note also that a value of pf_retrans > path_max_retrans 1802 disables this feature 1803 1804 Default: 0 1805 1806rto_initial - INTEGER 1807 The initial round trip timeout value in milliseconds that will be used 1808 in calculating round trip times. This is the initial time interval 1809 for retransmissions. 1810 1811 Default: 3000 1812 1813rto_max - INTEGER 1814 The maximum value (in milliseconds) of the round trip timeout. This 1815 is the largest time interval that can elapse between retransmissions. 1816 1817 Default: 60000 1818 1819rto_min - INTEGER 1820 The minimum value (in milliseconds) of the round trip timeout. This 1821 is the smallest time interval the can elapse between retransmissions. 1822 1823 Default: 1000 1824 1825hb_interval - INTEGER 1826 The interval (in milliseconds) between HEARTBEAT chunks. These chunks 1827 are sent at the specified interval on idle paths to probe the state of 1828 a given path between 2 associations. 1829 1830 Default: 30000 1831 1832sack_timeout - INTEGER 1833 The amount of time (in milliseconds) that the implementation will wait 1834 to send a SACK. 1835 1836 Default: 200 1837 1838valid_cookie_life - INTEGER 1839 The default lifetime of the SCTP cookie (in milliseconds). The cookie 1840 is used during association establishment. 1841 1842 Default: 60000 1843 1844cookie_preserve_enable - BOOLEAN 1845 Enable or disable the ability to extend the lifetime of the SCTP cookie 1846 that is used during the establishment phase of SCTP association 1847 1848 1: Enable cookie lifetime extension. 1849 0: Disable 1850 1851 Default: 1 1852 1853cookie_hmac_alg - STRING 1854 Select the hmac algorithm used when generating the cookie value sent by 1855 a listening sctp socket to a connecting client in the INIT-ACK chunk. 1856 Valid values are: 1857 * md5 1858 * sha1 1859 * none 1860 Ability to assign md5 or sha1 as the selected alg is predicated on the 1861 configuration of those algorithms at build time (CONFIG_CRYPTO_MD5 and 1862 CONFIG_CRYPTO_SHA1). 1863 1864 Default: Dependent on configuration. MD5 if available, else SHA1 if 1865 available, else none. 1866 1867rcvbuf_policy - INTEGER 1868 Determines if the receive buffer is attributed to the socket or to 1869 association. SCTP supports the capability to create multiple 1870 associations on a single socket. When using this capability, it is 1871 possible that a single stalled association that's buffering a lot 1872 of data may block other associations from delivering their data by 1873 consuming all of the receive buffer space. To work around this, 1874 the rcvbuf_policy could be set to attribute the receiver buffer space 1875 to each association instead of the socket. This prevents the described 1876 blocking. 1877 1878 1: rcvbuf space is per association 1879 0: rcvbuf space is per socket 1880 1881 Default: 0 1882 1883sndbuf_policy - INTEGER 1884 Similar to rcvbuf_policy above, this applies to send buffer space. 1885 1886 1: Send buffer is tracked per association 1887 0: Send buffer is tracked per socket. 1888 1889 Default: 0 1890 1891sctp_mem - vector of 3 INTEGERs: min, pressure, max 1892 Number of pages allowed for queueing by all SCTP sockets. 1893 1894 min: Below this number of pages SCTP is not bothered about its 1895 memory appetite. When amount of memory allocated by SCTP exceeds 1896 this number, SCTP starts to moderate memory usage. 1897 1898 pressure: This value was introduced to follow format of tcp_mem. 1899 1900 max: Number of pages allowed for queueing by all SCTP sockets. 1901 1902 Default is calculated at boot time from amount of available memory. 1903 1904sctp_rmem - vector of 3 INTEGERs: min, default, max 1905 Only the first value ("min") is used, "default" and "max" are 1906 ignored. 1907 1908 min: Minimal size of receive buffer used by SCTP socket. 1909 It is guaranteed to each SCTP socket (but not association) even 1910 under moderate memory pressure. 1911 1912 Default: 1 page 1913 1914sctp_wmem - vector of 3 INTEGERs: min, default, max 1915 Currently this tunable has no effect. 1916 1917addr_scope_policy - INTEGER 1918 Control IPv4 address scoping - draft-stewart-tsvwg-sctp-ipv4-00 1919 1920 0 - Disable IPv4 address scoping 1921 1 - Enable IPv4 address scoping 1922 2 - Follow draft but allow IPv4 private addresses 1923 3 - Follow draft but allow IPv4 link local addresses 1924 1925 Default: 1 1926 1927 1928/proc/sys/net/core/* 1929 Please see: Documentation/sysctl/net.txt for descriptions of these entries. 1930 1931 1932/proc/sys/net/unix/* 1933max_dgram_qlen - INTEGER 1934 The maximum length of dgram socket receive queue 1935 1936 Default: 10 1937 1938 1939UNDOCUMENTED: 1940 1941/proc/sys/net/irda/* 1942 fast_poll_increase FIXME 1943 warn_noreply_time FIXME 1944 discovery_slots FIXME 1945 slot_timeout FIXME 1946 max_baud_rate FIXME 1947 discovery_timeout FIXME 1948 lap_keepalive_time FIXME 1949 max_noreply_time FIXME 1950 max_tx_data_size FIXME 1951 max_tx_window FIXME 1952 min_tx_turn_time FIXME 1953