linux/Documentation/networking/ip-sysctl.txt
<<
>>
Prefs
   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
  66fib_multipath_use_neigh - BOOLEAN
  67        Use status of existing neighbor entry when determining nexthop for
  68        multipath routes. If disabled, neighbor information is not used and
  69        packets could be directed to a failed nexthop. Only valid for kernels
  70        built with CONFIG_IP_ROUTE_MULTIPATH enabled.
  71        Default: 0 (disabled)
  72        Possible values:
  73        0 - disabled
  74        1 - enabled
  75
  76route/max_size - INTEGER
  77        Maximum number of routes allowed in the kernel.  Increase
  78        this when using large numbers of interfaces and/or routes.
  79        From linux kernel 3.6 onwards, this is deprecated for ipv4
  80        as route cache is no longer used.
  81
  82neigh/default/gc_thresh1 - INTEGER
  83        Minimum number of entries to keep.  Garbage collector will not
  84        purge entries if there are fewer than this number.
  85        Default: 128
  86
  87neigh/default/gc_thresh2 - INTEGER
  88        Threshold when garbage collector becomes more aggressive about
  89        purging entries. Entries older than 5 seconds will be cleared
  90        when over this number.
  91        Default: 512
  92
  93neigh/default/gc_thresh3 - INTEGER
  94        Maximum number of neighbor entries allowed.  Increase this
  95        when using large numbers of interfaces and when communicating
  96        with large numbers of directly-connected peers.
  97        Default: 1024
  98
  99neigh/default/unres_qlen_bytes - INTEGER
 100        The maximum number of bytes which may be used by packets
 101        queued for each unresolved address by other network layers.
 102        (added in linux 3.3)
 103        Setting negative value is meaningless and will return error.
 104        Default: 65536 Bytes(64KB)
 105
 106neigh/default/unres_qlen - INTEGER
 107        The maximum number of packets which may be queued for each
 108        unresolved address by other network layers.
 109        (deprecated in linux 3.3) : use unres_qlen_bytes instead.
 110        Prior to linux 3.3, the default value is 3 which may cause
 111        unexpected packet loss. The current default value is calculated
 112        according to default value of unres_qlen_bytes and true size of
 113        packet.
 114        Default: 31
 115
 116mtu_expires - INTEGER
 117        Time, in seconds, that cached PMTU information is kept.
 118
 119min_adv_mss - INTEGER
 120        The advertised MSS depends on the first hop route MTU, but will
 121        never be lower than this setting.
 122
 123IP Fragmentation:
 124
 125ipfrag_high_thresh - INTEGER
 126        Maximum memory used to reassemble IP fragments. When
 127        ipfrag_high_thresh bytes of memory is allocated for this purpose,
 128        the fragment handler will toss packets until ipfrag_low_thresh
 129        is reached. This also serves as a maximum limit to namespaces
 130        different from the initial one.
 131
 132ipfrag_low_thresh - INTEGER
 133        Maximum memory used to reassemble IP fragments before the kernel
 134        begins to remove incomplete fragment queues to free up resources.
 135        The kernel still accepts new fragments for defragmentation.
 136
 137ipfrag_time - INTEGER
 138        Time in seconds to keep an IP fragment in memory.
 139
 140ipfrag_max_dist - INTEGER
 141        ipfrag_max_dist is a non-negative integer value which defines the
 142        maximum "disorder" which is allowed among fragments which share a
 143        common IP source address. Note that reordering of packets is
 144        not unusual, but if a large number of fragments arrive from a source
 145        IP address while a particular fragment queue remains incomplete, it
 146        probably indicates that one or more fragments belonging to that queue
 147        have been lost. When ipfrag_max_dist is positive, an additional check
 148        is done on fragments before they are added to a reassembly queue - if
 149        ipfrag_max_dist (or more) fragments have arrived from a particular IP
 150        address between additions to any IP fragment queue using that source
 151        address, it's presumed that one or more fragments in the queue are
 152        lost. The existing fragment queue will be dropped, and a new one
 153        started. An ipfrag_max_dist value of zero disables this check.
 154
 155        Using a very small value, e.g. 1 or 2, for ipfrag_max_dist can
 156        result in unnecessarily dropping fragment queues when normal
 157        reordering of packets occurs, which could lead to poor application
 158        performance. Using a very large value, e.g. 50000, increases the
 159        likelihood of incorrectly reassembling IP fragments that originate
 160        from different IP datagrams, which could result in data corruption.
 161        Default: 64
 162
 163INET peer storage:
 164
 165inet_peer_threshold - INTEGER
 166        The approximate size of the storage.  Starting from this threshold
 167        entries will be thrown aggressively.  This threshold also determines
 168        entries' time-to-live and time intervals between garbage collection
 169        passes.  More entries, less time-to-live, less GC interval.
 170
 171inet_peer_minttl - INTEGER
 172        Minimum time-to-live of entries.  Should be enough to cover fragment
 173        time-to-live on the reassembling side.  This minimum time-to-live  is
 174        guaranteed if the pool size is less than inet_peer_threshold.
 175        Measured in seconds.
 176
 177inet_peer_maxttl - INTEGER
 178        Maximum time-to-live of entries.  Unused entries will expire after
 179        this period of time if there is no memory pressure on the pool (i.e.
 180        when the number of entries in the pool is very small).
 181        Measured in seconds.
 182
 183TCP variables:
 184
 185somaxconn - INTEGER
 186        Limit of socket listen() backlog, known in userspace as SOMAXCONN.
 187        Defaults to 128.  See also tcp_max_syn_backlog for additional tuning
 188        for TCP sockets.
 189
 190tcp_abort_on_overflow - BOOLEAN
 191        If listening service is too slow to accept new connections,
 192        reset them. Default state is FALSE. It means that if overflow
 193        occurred due to a burst, connection will recover. Enable this
 194        option _only_ if you are really sure that listening daemon
 195        cannot be tuned to accept connections faster. Enabling this
 196        option can harm clients of your server.
 197
 198tcp_adv_win_scale - INTEGER
 199        Count buffering overhead as bytes/2^tcp_adv_win_scale
 200        (if tcp_adv_win_scale > 0) or bytes-bytes/2^(-tcp_adv_win_scale),
 201        if it is <= 0.
 202        Possible values are [-31, 31], inclusive.
 203        Default: 1
 204
 205tcp_allowed_congestion_control - STRING
 206        Show/set the congestion control choices available to non-privileged
 207        processes. The list is a subset of those listed in
 208        tcp_available_congestion_control.
 209        Default is "reno" and the default setting (tcp_congestion_control).
 210
 211tcp_app_win - INTEGER
 212        Reserve max(window/2^tcp_app_win, mss) of window for application
 213        buffer. Value 0 is special, it means that nothing is reserved.
 214        Default: 31
 215
 216tcp_autocorking - BOOLEAN
 217        Enable TCP auto corking :
 218        When applications do consecutive small write()/sendmsg() system calls,
 219        we try to coalesce these small writes as much as possible, to lower
 220        total amount of sent packets. This is done if at least one prior
 221        packet for the flow is waiting in Qdisc queues or device transmit
 222        queue. Applications can still use TCP_CORK for optimal behavior
 223        when they know how/when to uncork their sockets.
 224        Default : 1
 225
 226tcp_available_congestion_control - STRING
 227        Shows the available congestion control choices that are registered.
 228        More congestion control algorithms may be available as modules,
 229        but not loaded.
 230
 231tcp_base_mss - INTEGER
 232        The initial value of search_low to be used by the packetization layer
 233        Path MTU discovery (MTU probing).  If MTU probing is enabled,
 234        this is the initial MSS used by the connection.
 235
 236tcp_congestion_control - STRING
 237        Set the congestion control algorithm to be used for new
 238        connections. The algorithm "reno" is always available, but
 239        additional choices may be available based on kernel configuration.
 240        Default is set as part of kernel configuration.
 241        For passive connections, the listener congestion control choice
 242        is inherited.
 243        [see setsockopt(listenfd, SOL_TCP, TCP_CONGESTION, "name" ...) ]
 244
 245tcp_dsack - BOOLEAN
 246        Allows TCP to send "duplicate" SACKs.
 247
 248tcp_early_retrans - INTEGER
 249        Enable Early Retransmit (ER), per RFC 5827. ER lowers the threshold
 250        for triggering fast retransmit when the amount of outstanding data is
 251        small and when no previously unsent data can be transmitted (such
 252        that limited transmit could be used). Also controls the use of
 253        Tail loss probe (TLP) that converts RTOs occurring due to tail
 254        losses into fast recovery (draft-dukkipati-tcpm-tcp-loss-probe-01).
 255        Possible values:
 256                0 disables ER
 257                1 enables ER
 258                2 enables ER but delays fast recovery and fast retransmit
 259                  by a fourth of RTT. This mitigates connection falsely
 260                  recovers when network has a small degree of reordering
 261                  (less than 3 packets).
 262                3 enables delayed ER and TLP.
 263                4 enables TLP only.
 264        Default: 3
 265
 266tcp_ecn - INTEGER
 267        Control use of Explicit Congestion Notification (ECN) by TCP.
 268        ECN is used only when both ends of the TCP connection indicate
 269        support for it.  This feature is useful in avoiding losses due
 270        to congestion by allowing supporting routers to signal
 271        congestion before having to drop packets.
 272        Possible values are:
 273                0 Disable ECN.  Neither initiate nor accept ECN.
 274                1 Enable ECN when requested by incoming connections and
 275                  also request ECN on outgoing connection attempts.
 276                2 Enable ECN when requested by incoming connections
 277                  but do not request ECN on outgoing connections.
 278        Default: 2
 279
 280tcp_ecn_fallback - BOOLEAN
 281        If the kernel detects that ECN connection misbehaves, enable fall
 282        back to non-ECN. Currently, this knob implements the fallback
 283        from RFC3168, section 6.1.1.1., but we reserve that in future,
 284        additional detection mechanisms could be implemented under this
 285        knob. The value is not used, if tcp_ecn or per route (or congestion
 286        control) ECN settings are disabled.
 287        Default: 1 (fallback enabled)
 288
 289tcp_fack - BOOLEAN
 290        Enable FACK congestion avoidance and fast retransmission.
 291        The value is not used, if tcp_sack is not enabled.
 292
 293tcp_fin_timeout - INTEGER
 294        The length of time an orphaned (no longer referenced by any
 295        application) connection will remain in the FIN_WAIT_2 state
 296        before it is aborted at the local end.  While a perfectly
 297        valid "receive only" state for an un-orphaned connection, an
 298        orphaned connection in FIN_WAIT_2 state could otherwise wait
 299        forever for the remote to close its end of the connection.
 300        Cf. tcp_max_orphans
 301        Default: 60 seconds
 302
 303tcp_frto - INTEGER
 304        Enables Forward RTO-Recovery (F-RTO) defined in RFC5682.
 305        F-RTO is an enhanced recovery algorithm for TCP retransmission
 306        timeouts.  It is particularly beneficial in networks where the
 307        RTT fluctuates (e.g., wireless). F-RTO is sender-side only
 308        modification. It does not require any support from the peer.
 309
 310        By default it's enabled with a non-zero value. 0 disables F-RTO.
 311
 312tcp_invalid_ratelimit - INTEGER
 313        Limit the maximal rate for sending duplicate acknowledgments
 314        in response to incoming TCP packets that are for an existing
 315        connection but that are invalid due to any of these reasons:
 316
 317          (a) out-of-window sequence number,
 318          (b) out-of-window acknowledgment number, or
 319          (c) PAWS (Protection Against Wrapped Sequence numbers) check failure
 320
 321        This can help mitigate simple "ack loop" DoS attacks, wherein
 322        a buggy or malicious middlebox or man-in-the-middle can
 323        rewrite TCP header fields in manner that causes each endpoint
 324        to think that the other is sending invalid TCP segments, thus
 325        causing each side to send an unterminating stream of duplicate
 326        acknowledgments for invalid segments.
 327
 328        Using 0 disables rate-limiting of dupacks in response to
 329        invalid segments; otherwise this value specifies the minimal
 330        space between sending such dupacks, in milliseconds.
 331
 332        Default: 500 (milliseconds).
 333
 334tcp_keepalive_time - INTEGER
 335        How often TCP sends out keepalive messages when keepalive is enabled.
 336        Default: 2hours.
 337
 338tcp_keepalive_probes - INTEGER
 339        How many keepalive probes TCP sends out, until it decides that the
 340        connection is broken. Default value: 9.
 341
 342tcp_keepalive_intvl - INTEGER
 343        How frequently the probes are send out. Multiplied by
 344        tcp_keepalive_probes it is time to kill not responding connection,
 345        after probes started. Default value: 75sec i.e. connection
 346        will be aborted after ~11 minutes of retries.
 347
 348tcp_l3mdev_accept - BOOLEAN
 349        Enables child sockets to inherit the L3 master device index.
 350        Enabling this option allows a "global" listen socket to work
 351        across L3 master domains (e.g., VRFs) with connected sockets
 352        derived from the listen socket to be bound to the L3 domain in
 353        which the packets originated. Only valid when the kernel was
 354        compiled with CONFIG_NET_L3_MASTER_DEV.
 355
 356tcp_low_latency - BOOLEAN
 357        If set, the TCP stack makes decisions that prefer lower
 358        latency as opposed to higher throughput.  By default, this
 359        option is not set meaning that higher throughput is preferred.
 360        An example of an application where this default should be
 361        changed would be a Beowulf compute cluster.
 362        Default: 0
 363
 364tcp_max_orphans - INTEGER
 365        Maximal number of TCP sockets not attached to any user file handle,
 366        held by system. If this number is exceeded orphaned connections are
 367        reset immediately and warning is printed. This limit exists
 368        only to prevent simple DoS attacks, you _must_ not rely on this
 369        or lower the limit artificially, but rather increase it
 370        (probably, after increasing installed memory),
 371        if network conditions require more than default value,
 372        and tune network services to linger and kill such states
 373        more aggressively. Let me to remind again: each orphan eats
 374        up to ~64K of unswappable memory.
 375
 376tcp_max_syn_backlog - INTEGER
 377        Maximal number of remembered connection requests, which have not
 378        received an acknowledgment from connecting client.
 379        The minimal value is 128 for low memory machines, and it will
 380        increase in proportion to the memory of machine.
 381        If server suffers from overload, try increasing this number.
 382
 383tcp_max_tw_buckets - INTEGER
 384        Maximal number of timewait sockets held by system simultaneously.
 385        If this number is exceeded time-wait socket is immediately destroyed
 386        and warning is printed. This limit exists only to prevent
 387        simple DoS attacks, you _must_ not lower the limit artificially,
 388        but rather increase it (probably, after increasing installed memory),
 389        if network conditions require more than default value.
 390
 391tcp_mem - vector of 3 INTEGERs: min, pressure, max
 392        min: below this number of pages TCP is not bothered about its
 393        memory appetite.
 394
 395        pressure: when amount of memory allocated by TCP exceeds this number
 396        of pages, TCP moderates its memory consumption and enters memory
 397        pressure mode, which is exited when memory consumption falls
 398        under "min".
 399
 400        max: number of pages allowed for queueing by all TCP sockets.
 401
 402        Defaults are calculated at boot time from amount of available
 403        memory.
 404
 405tcp_min_rtt_wlen - INTEGER
 406        The window length of the windowed min filter to track the minimum RTT.
 407        A shorter window lets a flow more quickly pick up new (higher)
 408        minimum RTT when it is moved to a longer path (e.g., due to traffic
 409        engineering). A longer window makes the filter more resistant to RTT
 410        inflations such as transient congestion. The unit is seconds.
 411        Default: 300
 412
 413tcp_moderate_rcvbuf - BOOLEAN
 414        If set, TCP performs receive buffer auto-tuning, attempting to
 415        automatically size the buffer (no greater than tcp_rmem[2]) to
 416        match the size required by the path for full throughput.  Enabled by
 417        default.
 418
 419tcp_mtu_probing - INTEGER
 420        Controls TCP Packetization-Layer Path MTU Discovery.  Takes three
 421        values:
 422          0 - Disabled
 423          1 - Disabled by default, enabled when an ICMP black hole detected
 424          2 - Always enabled, use initial MSS of tcp_base_mss.
 425
 426tcp_probe_interval - INTEGER
 427        Controls how often to start TCP Packetization-Layer Path MTU
 428        Discovery reprobe. The default is reprobing every 10 minutes as
 429        per RFC4821.
 430
 431tcp_probe_threshold - INTEGER
 432        Controls when TCP Packetization-Layer Path MTU Discovery probing
 433        will stop in respect to the width of search range in bytes. Default
 434        is 8 bytes.
 435
 436tcp_no_metrics_save - BOOLEAN
 437        By default, TCP saves various connection metrics in the route cache
 438        when the connection closes, so that connections established in the
 439        near future can use these to set initial conditions.  Usually, this
 440        increases overall performance, but may sometimes cause performance
 441        degradation.  If set, TCP will not cache metrics on closing
 442        connections.
 443
 444tcp_orphan_retries - INTEGER
 445        This value influences the timeout of a locally closed TCP connection,
 446        when RTO retransmissions remain unacknowledged.
 447        See tcp_retries2 for more details.
 448
 449        The default value is 8.
 450        If your machine is a loaded WEB server,
 451        you should think about lowering this value, such sockets
 452        may consume significant resources. Cf. tcp_max_orphans.
 453
 454tcp_recovery - INTEGER
 455        This value is a bitmap to enable various experimental loss recovery
 456        features.
 457
 458        RACK: 0x1 enables the RACK loss detection for fast detection of lost
 459              retransmissions and tail drops.
 460
 461        Default: 0x1
 462
 463tcp_reordering - INTEGER
 464        Initial reordering level of packets in a TCP stream.
 465        TCP stack can then dynamically adjust flow reordering level
 466        between this initial value and tcp_max_reordering
 467        Default: 3
 468
 469tcp_max_reordering - INTEGER
 470        Maximal reordering level of packets in a TCP stream.
 471        300 is a fairly conservative value, but you might increase it
 472        if paths are using per packet load balancing (like bonding rr mode)
 473        Default: 300
 474
 475tcp_retrans_collapse - BOOLEAN
 476        Bug-to-bug compatibility with some broken printers.
 477        On retransmit try to send bigger packets to work around bugs in
 478        certain TCP stacks.
 479
 480tcp_retries1 - INTEGER
 481        This value influences the time, after which TCP decides, that
 482        something is wrong due to unacknowledged RTO retransmissions,
 483        and reports this suspicion to the network layer.
 484        See tcp_retries2 for more details.
 485
 486        RFC 1122 recommends at least 3 retransmissions, which is the
 487        default.
 488
 489tcp_retries2 - INTEGER
 490        This value influences the timeout of an alive TCP connection,
 491        when RTO retransmissions remain unacknowledged.
 492        Given a value of N, a hypothetical TCP connection following
 493        exponential backoff with an initial RTO of TCP_RTO_MIN would
 494        retransmit N times before killing the connection at the (N+1)th RTO.
 495
 496        The default value of 15 yields a hypothetical timeout of 924.6
 497        seconds and is a lower bound for the effective timeout.
 498        TCP will effectively time out at the first RTO which exceeds the
 499        hypothetical timeout.
 500
 501        RFC 1122 recommends at least 100 seconds for the timeout,
 502        which corresponds to a value of at least 8.
 503
 504tcp_rfc1337 - BOOLEAN
 505        If set, the TCP stack behaves conforming to RFC1337. If unset,
 506        we are not conforming to RFC, but prevent TCP TIME_WAIT
 507        assassination.
 508        Default: 0
 509
 510tcp_rmem - vector of 3 INTEGERs: min, default, max
 511        min: Minimal size of receive buffer used by TCP sockets.
 512        It is guaranteed to each TCP socket, even under moderate memory
 513        pressure.
 514        Default: 1 page
 515
 516        default: initial size of receive buffer used by TCP sockets.
 517        This value overrides net.core.rmem_default used by other protocols.
 518        Default: 87380 bytes. This value results in window of 65535 with
 519        default setting of tcp_adv_win_scale and tcp_app_win:0 and a bit
 520        less for default tcp_app_win. See below about these variables.
 521
 522        max: maximal size of receive buffer allowed for automatically
 523        selected receiver buffers for TCP socket. This value does not override
 524        net.core.rmem_max.  Calling setsockopt() with SO_RCVBUF disables
 525        automatic tuning of that socket's receive buffer size, in which
 526        case this value is ignored.
 527        Default: between 87380B and 6MB, depending on RAM size.
 528
 529tcp_sack - BOOLEAN
 530        Enable select acknowledgments (SACKS).
 531
 532tcp_slow_start_after_idle - BOOLEAN
 533        If set, provide RFC2861 behavior and time out the congestion
 534        window after an idle period.  An idle period is defined at
 535        the current RTO.  If unset, the congestion window will not
 536        be timed out after an idle period.
 537        Default: 1
 538
 539tcp_stdurg - BOOLEAN
 540        Use the Host requirements interpretation of the TCP urgent pointer field.
 541        Most hosts use the older BSD interpretation, so if you turn this on
 542        Linux might not communicate correctly with them.
 543        Default: FALSE
 544
 545tcp_synack_retries - INTEGER
 546        Number of times SYNACKs for a passive TCP connection attempt will
 547        be retransmitted. Should not be higher than 255. Default value
 548        is 5, which corresponds to 31seconds till the last retransmission
 549        with the current initial RTO of 1second. With this the final timeout
 550        for a passive TCP connection will happen after 63seconds.
 551
 552tcp_syncookies - BOOLEAN
 553        Only valid when the kernel was compiled with CONFIG_SYN_COOKIES
 554        Send out syncookies when the syn backlog queue of a socket
 555        overflows. This is to prevent against the common 'SYN flood attack'
 556        Default: 1
 557
 558        Note, that syncookies is fallback facility.
 559        It MUST NOT be used to help highly loaded servers to stand
 560        against legal connection rate. If you see SYN flood warnings
 561        in your logs, but investigation shows that they occur
 562        because of overload with legal connections, you should tune
 563        another parameters until this warning disappear.
 564        See: tcp_max_syn_backlog, tcp_synack_retries, tcp_abort_on_overflow.
 565
 566        syncookies seriously violate TCP protocol, do not allow
 567        to use TCP extensions, can result in serious degradation
 568        of some services (f.e. SMTP relaying), visible not by you,
 569        but your clients and relays, contacting you. While you see
 570        SYN flood warnings in logs not being really flooded, your server
 571        is seriously misconfigured.
 572
 573        If you want to test which effects syncookies have to your
 574        network connections you can set this knob to 2 to enable
 575        unconditionally generation of syncookies.
 576
 577tcp_fastopen - INTEGER
 578        Enable TCP Fast Open (RFC7413) to send and accept data in the opening
 579        SYN packet.
 580
 581        The client support is enabled by flag 0x1 (on by default). The client
 582        then must use sendmsg() or sendto() with the MSG_FASTOPEN flag,
 583        rather than connect() to send data in SYN.
 584
 585        The server support is enabled by flag 0x2 (off by default). Then
 586        either enable for all listeners with another flag (0x400) or
 587        enable individual listeners via TCP_FASTOPEN socket option with
 588        the option value being the length of the syn-data backlog.
 589
 590        The values (bitmap) are
 591          0x1: (client) enables sending data in the opening SYN on the client.
 592          0x2: (server) enables the server support, i.e., allowing data in
 593                        a SYN packet to be accepted and passed to the
 594                        application before 3-way handshake finishes.
 595          0x4: (client) send data in the opening SYN regardless of cookie
 596                        availability and without a cookie option.
 597        0x200: (server) accept data-in-SYN w/o any cookie option present.
 598        0x400: (server) enable all listeners to support Fast Open by
 599                        default without explicit TCP_FASTOPEN socket option.
 600
 601        Default: 0x1
 602
 603        Note that that additional client or server features are only
 604        effective if the basic support (0x1 and 0x2) are enabled respectively.
 605
 606tcp_syn_retries - INTEGER
 607        Number of times initial SYNs for an active TCP connection attempt
 608        will be retransmitted. Should not be higher than 127. Default value
 609        is 6, which corresponds to 63seconds till the last retransmission
 610        with the current initial RTO of 1second. With this the final timeout
 611        for an active TCP connection attempt will happen after 127seconds.
 612
 613tcp_timestamps - BOOLEAN
 614        Enable timestamps as defined in RFC1323.
 615
 616tcp_min_tso_segs - INTEGER
 617        Minimal number of segments per TSO frame.
 618        Since linux-3.12, TCP does an automatic sizing of TSO frames,
 619        depending on flow rate, instead of filling 64Kbytes packets.
 620        For specific usages, it's possible to force TCP to build big
 621        TSO frames. Note that TCP stack might split too big TSO packets
 622        if available window is too small.
 623        Default: 2
 624
 625tcp_pacing_ss_ratio - INTEGER
 626        sk->sk_pacing_rate is set by TCP stack using a ratio applied
 627        to current rate. (current_rate = cwnd * mss / srtt)
 628        If TCP is in slow start, tcp_pacing_ss_ratio is applied
 629        to let TCP probe for bigger speeds, assuming cwnd can be
 630        doubled every other RTT.
 631        Default: 200
 632
 633tcp_pacing_ca_ratio - INTEGER
 634        sk->sk_pacing_rate is set by TCP stack using a ratio applied
 635        to current rate. (current_rate = cwnd * mss / srtt)
 636        If TCP is in congestion avoidance phase, tcp_pacing_ca_ratio
 637        is applied to conservatively probe for bigger throughput.
 638        Default: 120
 639
 640tcp_tso_win_divisor - INTEGER
 641        This allows control over what percentage of the congestion window
 642        can be consumed by a single TSO frame.
 643        The setting of this parameter is a choice between burstiness and
 644        building larger TSO frames.
 645        Default: 3
 646
 647tcp_tw_recycle - BOOLEAN
 648        Enable fast recycling TIME-WAIT sockets. Default value is 0.
 649        It should not be changed without advice/request of technical
 650        experts.
 651
 652tcp_tw_reuse - BOOLEAN
 653        Allow to reuse TIME-WAIT sockets for new connections when it is
 654        safe from protocol viewpoint. Default value is 0.
 655        It should not be changed without advice/request of technical
 656        experts.
 657
 658tcp_window_scaling - BOOLEAN
 659        Enable window scaling as defined in RFC1323.
 660
 661tcp_wmem - vector of 3 INTEGERs: min, default, max
 662        min: Amount of memory reserved for send buffers for TCP sockets.
 663        Each TCP socket has rights to use it due to fact of its birth.
 664        Default: 1 page
 665
 666        default: initial size of send buffer used by TCP sockets.  This
 667        value overrides net.core.wmem_default used by other protocols.
 668        It is usually lower than net.core.wmem_default.
 669        Default: 16K
 670
 671        max: Maximal amount of memory allowed for automatically tuned
 672        send buffers for TCP sockets. This value does not override
 673        net.core.wmem_max.  Calling setsockopt() with SO_SNDBUF disables
 674        automatic tuning of that socket's send buffer size, in which case
 675        this value is ignored.
 676        Default: between 64K and 4MB, depending on RAM size.
 677
 678tcp_notsent_lowat - UNSIGNED INTEGER
 679        A TCP socket can control the amount of unsent bytes in its write queue,
 680        thanks to TCP_NOTSENT_LOWAT socket option. poll()/select()/epoll()
 681        reports POLLOUT events if the amount of unsent bytes is below a per
 682        socket value, and if the write queue is not full. sendmsg() will
 683        also not add new buffers if the limit is hit.
 684
 685        This global variable controls the amount of unsent data for
 686        sockets not using TCP_NOTSENT_LOWAT. For these sockets, a change
 687        to the global variable has immediate effect.
 688
 689        Default: UINT_MAX (0xFFFFFFFF)
 690
 691tcp_workaround_signed_windows - BOOLEAN
 692        If set, assume no receipt of a window scaling option means the
 693        remote TCP is broken and treats the window as a signed quantity.
 694        If unset, assume the remote TCP is not broken even if we do
 695        not receive a window scaling option from them.
 696        Default: 0
 697
 698tcp_thin_linear_timeouts - BOOLEAN
 699        Enable dynamic triggering of linear timeouts for thin streams.
 700        If set, a check is performed upon retransmission by timeout to
 701        determine if the stream is thin (less than 4 packets in flight).
 702        As long as the stream is found to be thin, up to 6 linear
 703        timeouts may be performed before exponential backoff mode is
 704        initiated. This improves retransmission latency for
 705        non-aggressive thin streams, often found to be time-dependent.
 706        For more information on thin streams, see
 707        Documentation/networking/tcp-thin.txt
 708        Default: 0
 709
 710tcp_thin_dupack - BOOLEAN
 711        Enable dynamic triggering of retransmissions after one dupACK
 712        for thin streams. If set, a check is performed upon reception
 713        of a dupACK to determine if the stream is thin (less than 4
 714        packets in flight). As long as the stream is found to be thin,
 715        data is retransmitted on the first received dupACK. This
 716        improves retransmission latency for non-aggressive thin
 717        streams, often found to be time-dependent.
 718        For more information on thin streams, see
 719        Documentation/networking/tcp-thin.txt
 720        Default: 0
 721
 722tcp_limit_output_bytes - INTEGER
 723        Controls TCP Small Queue limit per tcp socket.
 724        TCP bulk sender tends to increase packets in flight until it
 725        gets losses notifications. With SNDBUF autotuning, this can
 726        result in a large amount of packets queued in qdisc/device
 727        on the local machine, hurting latency of other flows, for
 728        typical pfifo_fast qdiscs.
 729        tcp_limit_output_bytes limits the number of bytes on qdisc
 730        or device to reduce artificial RTT/cwnd and reduce bufferbloat.
 731        Default: 262144
 732
 733tcp_challenge_ack_limit - INTEGER
 734        Limits number of Challenge ACK sent per second, as recommended
 735        in RFC 5961 (Improving TCP's Robustness to Blind In-Window Attacks)
 736        Default: 100
 737
 738UDP variables:
 739
 740udp_mem - vector of 3 INTEGERs: min, pressure, max
 741        Number of pages allowed for queueing by all UDP sockets.
 742
 743        min: Below this number of pages UDP is not bothered about its
 744        memory appetite. When amount of memory allocated by UDP exceeds
 745        this number, UDP starts to moderate memory usage.
 746
 747        pressure: This value was introduced to follow format of tcp_mem.
 748
 749        max: Number of pages allowed for queueing by all UDP sockets.
 750
 751        Default is calculated at boot time from amount of available memory.
 752
 753udp_rmem_min - INTEGER
 754        Minimal size of receive buffer used by UDP sockets in moderation.
 755        Each UDP socket is able to use the size for receiving data, even if
 756        total pages of UDP sockets exceed udp_mem pressure. The unit is byte.
 757        Default: 1 page
 758
 759udp_wmem_min - INTEGER
 760        Minimal size of send buffer used by UDP sockets in moderation.
 761        Each UDP socket is able to use the size for sending data, even if
 762        total pages of UDP sockets exceed udp_mem pressure. The unit is byte.
 763        Default: 1 page
 764
 765CIPSOv4 Variables:
 766
 767cipso_cache_enable - BOOLEAN
 768        If set, enable additions to and lookups from the CIPSO label mapping
 769        cache.  If unset, additions are ignored and lookups always result in a
 770        miss.  However, regardless of the setting the cache is still
 771        invalidated when required when means you can safely toggle this on and
 772        off and the cache will always be "safe".
 773        Default: 1
 774
 775cipso_cache_bucket_size - INTEGER
 776        The CIPSO label cache consists of a fixed size hash table with each
 777        hash bucket containing a number of cache entries.  This variable limits
 778        the number of entries in each hash bucket; the larger the value the
 779        more CIPSO label mappings that can be cached.  When the number of
 780        entries in a given hash bucket reaches this limit adding new entries
 781        causes the oldest entry in the bucket to be removed to make room.
 782        Default: 10
 783
 784cipso_rbm_optfmt - BOOLEAN
 785        Enable the "Optimized Tag 1 Format" as defined in section 3.4.2.6 of
 786        the CIPSO draft specification (see Documentation/netlabel for details).
 787        This means that when set the CIPSO tag will be padded with empty
 788        categories in order to make the packet data 32-bit aligned.
 789        Default: 0
 790
 791cipso_rbm_structvalid - BOOLEAN
 792        If set, do a very strict check of the CIPSO option when
 793        ip_options_compile() is called.  If unset, relax the checks done during
 794        ip_options_compile().  Either way is "safe" as errors are caught else
 795        where in the CIPSO processing code but setting this to 0 (False) should
 796        result in less work (i.e. it should be faster) but could cause problems
 797        with other implementations that require strict checking.
 798        Default: 0
 799
 800IP Variables:
 801
 802ip_local_port_range - 2 INTEGERS
 803        Defines the local port range that is used by TCP and UDP to
 804        choose the local port. The first number is the first, the
 805        second the last local port number.
 806        If possible, it is better these numbers have different parity.
 807        (one even and one odd values)
 808        The default values are 32768 and 60999 respectively.
 809
 810ip_local_reserved_ports - list of comma separated ranges
 811        Specify the ports which are reserved for known third-party
 812        applications. These ports will not be used by automatic port
 813        assignments (e.g. when calling connect() or bind() with port
 814        number 0). Explicit port allocation behavior is unchanged.
 815
 816        The format used for both input and output is a comma separated
 817        list of ranges (e.g. "1,2-4,10-10" for ports 1, 2, 3, 4 and
 818        10). Writing to the file will clear all previously reserved
 819        ports and update the current list with the one given in the
 820        input.
 821
 822        Note that ip_local_port_range and ip_local_reserved_ports
 823        settings are independent and both are considered by the kernel
 824        when determining which ports are available for automatic port
 825        assignments.
 826
 827        You can reserve ports which are not in the current
 828        ip_local_port_range, e.g.:
 829
 830        $ cat /proc/sys/net/ipv4/ip_local_port_range
 831        32000   60999
 832        $ cat /proc/sys/net/ipv4/ip_local_reserved_ports
 833        8080,9148
 834
 835        although this is redundant. However such a setting is useful
 836        if later the port range is changed to a value that will
 837        include the reserved ports.
 838
 839        Default: Empty
 840
 841ip_nonlocal_bind - BOOLEAN
 842        If set, allows processes to bind() to non-local IP addresses,
 843        which can be quite useful - but may break some applications.
 844        Default: 0
 845
 846ip_dynaddr - BOOLEAN
 847        If set non-zero, enables support for dynamic addresses.
 848        If set to a non-zero value larger than 1, a kernel log
 849        message will be printed when dynamic address rewriting
 850        occurs.
 851        Default: 0
 852
 853ip_early_demux - BOOLEAN
 854        Optimize input packet processing down to one demux for
 855        certain kinds of local sockets.  Currently we only do this
 856        for established TCP sockets.
 857
 858        It may add an additional cost for pure routing workloads that
 859        reduces overall throughput, in such case you should disable it.
 860        Default: 1
 861
 862icmp_echo_ignore_all - BOOLEAN
 863        If set non-zero, then the kernel will ignore all ICMP ECHO
 864        requests sent to it.
 865        Default: 0
 866
 867icmp_echo_ignore_broadcasts - BOOLEAN
 868        If set non-zero, then the kernel will ignore all ICMP ECHO and
 869        TIMESTAMP requests sent to it via broadcast/multicast.
 870        Default: 1
 871
 872icmp_ratelimit - INTEGER
 873        Limit the maximal rates for sending ICMP packets whose type matches
 874        icmp_ratemask (see below) to specific targets.
 875        0 to disable any limiting,
 876        otherwise the minimal space between responses in milliseconds.
 877        Note that another sysctl, icmp_msgs_per_sec limits the number
 878        of ICMP packets sent on all targets.
 879        Default: 1000
 880
 881icmp_msgs_per_sec - INTEGER
 882        Limit maximal number of ICMP packets sent per second from this host.
 883        Only messages whose type matches icmp_ratemask (see below) are
 884        controlled by this limit.
 885        Default: 1000
 886
 887icmp_msgs_burst - INTEGER
 888        icmp_msgs_per_sec controls number of ICMP packets sent per second,
 889        while icmp_msgs_burst controls the burst size of these packets.
 890        Default: 50
 891
 892icmp_ratemask - INTEGER
 893        Mask made of ICMP types for which rates are being limited.
 894        Significant bits: IHGFEDCBA9876543210
 895        Default mask:     0000001100000011000 (6168)
 896
 897        Bit definitions (see include/linux/icmp.h):
 898                0 Echo Reply
 899                3 Destination Unreachable *
 900                4 Source Quench *
 901                5 Redirect
 902                8 Echo Request
 903                B Time Exceeded *
 904                C Parameter Problem *
 905                D Timestamp Request
 906                E Timestamp Reply
 907                F Info Request
 908                G Info Reply
 909                H Address Mask Request
 910                I Address Mask Reply
 911
 912        * These are rate limited by default (see default mask above)
 913
 914icmp_ignore_bogus_error_responses - BOOLEAN
 915        Some routers violate RFC1122 by sending bogus responses to broadcast
 916        frames.  Such violations are normally logged via a kernel warning.
 917        If this is set to TRUE, the kernel will not give such warnings, which
 918        will avoid log file clutter.
 919        Default: 1
 920
 921icmp_errors_use_inbound_ifaddr - BOOLEAN
 922
 923        If zero, icmp error messages are sent with the primary address of
 924        the exiting interface.
 925
 926        If non-zero, the message will be sent with the primary address of
 927        the interface that received the packet that caused the icmp error.
 928        This is the behaviour network many administrators will expect from
 929        a router. And it can make debugging complicated network layouts
 930        much easier.
 931
 932        Note that if no primary address exists for the interface selected,
 933        then the primary address of the first non-loopback interface that
 934        has one will be used regardless of this setting.
 935
 936        Default: 0
 937
 938igmp_max_memberships - INTEGER
 939        Change the maximum number of multicast groups we can subscribe to.
 940        Default: 20
 941
 942        Theoretical maximum value is bounded by having to send a membership
 943        report in a single datagram (i.e. the report can't span multiple
 944        datagrams, or risk confusing the switch and leaving groups you don't
 945        intend to).
 946
 947        The number of supported groups 'M' is bounded by the number of group
 948        report entries you can fit into a single datagram of 65535 bytes.
 949
 950        M = 65536-sizeof (ip header)/(sizeof(Group record))
 951
 952        Group records are variable length, with a minimum of 12 bytes.
 953        So net.ipv4.igmp_max_memberships should not be set higher than:
 954
 955        (65536-24) / 12 = 5459
 956
 957        The value 5459 assumes no IP header options, so in practice
 958        this number may be lower.
 959
 960igmp_max_msf - INTEGER
 961        Maximum number of addresses allowed in the source filter list for a
 962        multicast group.
 963        Default: 10
 964
 965igmp_qrv - INTEGER
 966        Controls the IGMP query robustness variable (see RFC2236 8.1).
 967        Default: 2 (as specified by RFC2236 8.1)
 968        Minimum: 1 (as specified by RFC6636 4.5)
 969
 970conf/interface/*  changes special settings per interface (where
 971"interface" is the name of your network interface)
 972
 973conf/all/*        is special, changes the settings for all interfaces
 974
 975log_martians - BOOLEAN
 976        Log packets with impossible addresses to kernel log.
 977        log_martians for the interface will be enabled if at least one of
 978        conf/{all,interface}/log_martians is set to TRUE,
 979        it will be disabled otherwise
 980
 981accept_redirects - BOOLEAN
 982        Accept ICMP redirect messages.
 983        accept_redirects for the interface will be enabled if:
 984        - both conf/{all,interface}/accept_redirects are TRUE in the case
 985          forwarding for the interface is enabled
 986        or
 987        - at least one of conf/{all,interface}/accept_redirects is TRUE in the
 988          case forwarding for the interface is disabled
 989        accept_redirects for the interface will be disabled otherwise
 990        default TRUE (host)
 991                FALSE (router)
 992
 993forwarding - BOOLEAN
 994        Enable IP forwarding on this interface.
 995
 996mc_forwarding - BOOLEAN
 997        Do multicast routing. The kernel needs to be compiled with CONFIG_MROUTE
 998        and a multicast routing daemon is required.
 999        conf/all/mc_forwarding must also be set to TRUE to enable multicast
1000        routing for the interface
1001
1002medium_id - INTEGER
1003        Integer value used to differentiate the devices by the medium they
1004        are attached to. Two devices can have different id values when
1005        the broadcast packets are received only on one of them.
1006        The default value 0 means that the device is the only interface
1007        to its medium, value of -1 means that medium is not known.
1008
1009        Currently, it is used to change the proxy_arp behavior:
1010        the proxy_arp feature is enabled for packets forwarded between
1011        two devices attached to different media.
1012
1013proxy_arp - BOOLEAN
1014        Do proxy arp.
1015        proxy_arp for the interface will be enabled if at least one of
1016        conf/{all,interface}/proxy_arp is set to TRUE,
1017        it will be disabled otherwise
1018
1019proxy_arp_pvlan - BOOLEAN
1020        Private VLAN proxy arp.
1021        Basically allow proxy arp replies back to the same interface
1022        (from which the ARP request/solicitation was received).
1023
1024        This is done to support (ethernet) switch features, like RFC
1025        3069, where the individual ports are NOT allowed to
1026        communicate with each other, but they are allowed to talk to
1027        the upstream router.  As described in RFC 3069, it is possible
1028        to allow these hosts to communicate through the upstream
1029        router by proxy_arp'ing. Don't need to be used together with
1030        proxy_arp.
1031
1032        This technology is known by different names:
1033          In RFC 3069 it is called VLAN Aggregation.
1034          Cisco and Allied Telesyn call it Private VLAN.
1035          Hewlett-Packard call it Source-Port filtering or port-isolation.
1036          Ericsson call it MAC-Forced Forwarding (RFC Draft).
1037
1038shared_media - BOOLEAN
1039        Send(router) or accept(host) RFC1620 shared media redirects.
1040        Overrides secure_redirects.
1041        shared_media for the interface will be enabled if at least one of
1042        conf/{all,interface}/shared_media is set to TRUE,
1043        it will be disabled otherwise
1044        default TRUE
1045
1046secure_redirects - BOOLEAN
1047        Accept ICMP redirect messages only to gateways listed in the
1048        interface's current gateway list. Even if disabled, RFC1122 redirect
1049        rules still apply.
1050        Overridden by shared_media.
1051        secure_redirects for the interface will be enabled if at least one of
1052        conf/{all,interface}/secure_redirects is set to TRUE,
1053        it will be disabled otherwise
1054        default TRUE
1055
1056send_redirects - BOOLEAN
1057        Send redirects, if router.
1058        send_redirects for the interface will be enabled if at least one of
1059        conf/{all,interface}/send_redirects is set to TRUE,
1060        it will be disabled otherwise
1061        Default: TRUE
1062
1063bootp_relay - BOOLEAN
1064        Accept packets with source address 0.b.c.d destined
1065        not to this host as local ones. It is supposed, that
1066        BOOTP relay daemon will catch and forward such packets.
1067        conf/all/bootp_relay must also be set to TRUE to enable BOOTP relay
1068        for the interface
1069        default FALSE
1070        Not Implemented Yet.
1071
1072accept_source_route - BOOLEAN
1073        Accept packets with SRR option.
1074        conf/all/accept_source_route must also be set to TRUE to accept packets
1075        with SRR option on the interface
1076        default TRUE (router)
1077                FALSE (host)
1078
1079accept_local - BOOLEAN
1080        Accept packets with local source addresses. In combination with
1081        suitable routing, this can be used to direct packets between two
1082        local interfaces over the wire and have them accepted properly.
1083        default FALSE
1084
1085route_localnet - BOOLEAN
1086        Do not consider loopback addresses as martian source or destination
1087        while routing. This enables the use of 127/8 for local routing purposes.
1088        default FALSE
1089
1090rp_filter - INTEGER
1091        0 - No source validation.
1092        1 - Strict mode as defined in RFC3704 Strict Reverse Path
1093            Each incoming packet is tested against the FIB and if the interface
1094            is not the best reverse path the packet check will fail.
1095            By default failed packets are discarded.
1096        2 - Loose mode as defined in RFC3704 Loose Reverse Path
1097            Each incoming packet's source address is also tested against the FIB
1098            and if the source address is not reachable via any interface
1099            the packet check will fail.
1100
1101        Current recommended practice in RFC3704 is to enable strict mode
1102        to prevent IP spoofing from DDos attacks. If using asymmetric routing
1103        or other complicated routing, then loose mode is recommended.
1104
1105        The max value from conf/{all,interface}/rp_filter is used
1106        when doing source validation on the {interface}.
1107
1108        Default value is 0. Note that some distributions enable it
1109        in startup scripts.
1110
1111arp_filter - BOOLEAN
1112        1 - Allows you to have multiple network interfaces on the same
1113        subnet, and have the ARPs for each interface be answered
1114        based on whether or not the kernel would route a packet from
1115        the ARP'd IP out that interface (therefore you must use source
1116        based routing for this to work). In other words it allows control
1117        of which cards (usually 1) will respond to an arp request.
1118
1119        0 - (default) The kernel can respond to arp requests with addresses
1120        from other interfaces. This may seem wrong but it usually makes
1121        sense, because it increases the chance of successful communication.
1122        IP addresses are owned by the complete host on Linux, not by
1123        particular interfaces. Only for more complex setups like load-
1124        balancing, does this behaviour cause problems.
1125
1126        arp_filter for the interface will be enabled if at least one of
1127        conf/{all,interface}/arp_filter is set to TRUE,
1128        it will be disabled otherwise
1129
1130arp_announce - INTEGER
1131        Define different restriction levels for announcing the local
1132        source IP address from IP packets in ARP requests sent on
1133        interface:
1134        0 - (default) Use any local address, configured on any interface
1135        1 - Try to avoid local addresses that are not in the target's
1136        subnet for this interface. This mode is useful when target
1137        hosts reachable via this interface require the source IP
1138        address in ARP requests to be part of their logical network
1139        configured on the receiving interface. When we generate the
1140        request we will check all our subnets that include the
1141        target IP and will preserve the source address if it is from
1142        such subnet. If there is no such subnet we select source
1143        address according to the rules for level 2.
1144        2 - Always use the best local address for this target.
1145        In this mode we ignore the source address in the IP packet
1146        and try to select local address that we prefer for talks with
1147        the target host. Such local address is selected by looking
1148        for primary IP addresses on all our subnets on the outgoing
1149        interface that include the target IP address. If no suitable
1150        local address is found we select the first local address
1151        we have on the outgoing interface or on all other interfaces,
1152        with the hope we will receive reply for our request and
1153        even sometimes no matter the source IP address we announce.
1154
1155        The max value from conf/{all,interface}/arp_announce is used.
1156
1157        Increasing the restriction level gives more chance for
1158        receiving answer from the resolved target while decreasing
1159        the level announces more valid sender's information.
1160
1161arp_ignore - INTEGER
1162        Define different modes for sending replies in response to
1163        received ARP requests that resolve local target IP addresses:
1164        0 - (default): reply for any local target IP address, configured
1165        on any interface
1166        1 - reply only if the target IP address is local address
1167        configured on the incoming interface
1168        2 - reply only if the target IP address is local address
1169        configured on the incoming interface and both with the
1170        sender's IP address are part from same subnet on this interface
1171        3 - do not reply for local addresses configured with scope host,
1172        only resolutions for global and link addresses are replied
1173        4-7 - reserved
1174        8 - do not reply for all local addresses
1175
1176        The max value from conf/{all,interface}/arp_ignore is used
1177        when ARP request is received on the {interface}
1178
1179arp_notify - BOOLEAN
1180        Define mode for notification of address and device changes.
1181        0 - (default): do nothing
1182        1 - Generate gratuitous arp requests when device is brought up
1183            or hardware address changes.
1184
1185arp_accept - BOOLEAN
1186        Define behavior for gratuitous ARP frames who's IP is not
1187        already present in the ARP table:
1188        0 - don't create new entries in the ARP table
1189        1 - create new entries in the ARP table
1190
1191        Both replies and requests type gratuitous arp will trigger the
1192        ARP table to be updated, if this setting is on.
1193
1194        If the ARP table already contains the IP address of the
1195        gratuitous arp frame, the arp table will be updated regardless
1196        if this setting is on or off.
1197
1198mcast_solicit - INTEGER
1199        The maximum number of multicast probes in INCOMPLETE state,
1200        when the associated hardware address is unknown.  Defaults
1201        to 3.
1202
1203ucast_solicit - INTEGER
1204        The maximum number of unicast probes in PROBE state, when
1205        the hardware address is being reconfirmed.  Defaults to 3.
1206
1207app_solicit - INTEGER
1208        The maximum number of probes to send to the user space ARP daemon
1209        via netlink before dropping back to multicast probes (see
1210        mcast_resolicit).  Defaults to 0.
1211
1212mcast_resolicit - INTEGER
1213        The maximum number of multicast probes after unicast and
1214        app probes in PROBE state.  Defaults to 0.
1215
1216disable_policy - BOOLEAN
1217        Disable IPSEC policy (SPD) for this interface
1218
1219disable_xfrm - BOOLEAN
1220        Disable IPSEC encryption on this interface, whatever the policy
1221
1222igmpv2_unsolicited_report_interval - INTEGER
1223        The interval in milliseconds in which the next unsolicited
1224        IGMPv1 or IGMPv2 report retransmit will take place.
1225        Default: 10000 (10 seconds)
1226
1227igmpv3_unsolicited_report_interval - INTEGER
1228        The interval in milliseconds in which the next unsolicited
1229        IGMPv3 report retransmit will take place.
1230        Default: 1000 (1 seconds)
1231
1232promote_secondaries - BOOLEAN
1233        When a primary IP address is removed from this interface
1234        promote a corresponding secondary IP address instead of
1235        removing all the corresponding secondary IP addresses.
1236
1237drop_unicast_in_l2_multicast - BOOLEAN
1238        Drop any unicast IP packets that are received in link-layer
1239        multicast (or broadcast) frames.
1240        This behavior (for multicast) is actually a SHOULD in RFC
1241        1122, but is disabled by default for compatibility reasons.
1242        Default: off (0)
1243
1244drop_gratuitous_arp - BOOLEAN
1245        Drop all gratuitous ARP frames, for example if there's a known
1246        good ARP proxy on the network and such frames need not be used
1247        (or in the case of 802.11, must not be used to prevent attacks.)
1248        Default: off (0)
1249
1250
1251tag - INTEGER
1252        Allows you to write a number, which can be used as required.
1253        Default value is 0.
1254
1255xfrm4_gc_thresh - INTEGER
1256        The threshold at which we will start garbage collecting for IPv4
1257        destination cache entries.  At twice this value the system will
1258        refuse new allocations. The value must be set below the flowcache
1259        limit (4096 * number of online cpus) to take effect.
1260
1261igmp_link_local_mcast_reports - BOOLEAN
1262        Enable IGMP reports for link local multicast groups in the
1263        224.0.0.X range.
1264        Default TRUE
1265
1266Alexey Kuznetsov.
1267kuznet@ms2.inr.ac.ru
1268
1269Updated by:
1270Andi Kleen
1271ak@muc.de
1272Nicolas Delon
1273delon.nicolas@wanadoo.fr
1274
1275
1276
1277
1278/proc/sys/net/ipv6/* Variables:
1279
1280IPv6 has no global variables such as tcp_*.  tcp_* settings under ipv4/ also
1281apply to IPv6 [XXX?].
1282
1283bindv6only - BOOLEAN
1284        Default value for IPV6_V6ONLY socket option,
1285        which restricts use of the IPv6 socket to IPv6 communication
1286        only.
1287                TRUE: disable IPv4-mapped address feature
1288                FALSE: enable IPv4-mapped address feature
1289
1290        Default: FALSE (as specified in RFC3493)
1291
1292flowlabel_consistency - BOOLEAN
1293        Protect the consistency (and unicity) of flow label.
1294        You have to disable it to use IPV6_FL_F_REFLECT flag on the
1295        flow label manager.
1296        TRUE: enabled
1297        FALSE: disabled
1298        Default: TRUE
1299
1300auto_flowlabels - INTEGER
1301        Automatically generate flow labels based on a flow hash of the
1302        packet. This allows intermediate devices, such as routers, to
1303        identify packet flows for mechanisms like Equal Cost Multipath
1304        Routing (see RFC 6438).
1305        0: automatic flow labels are completely disabled
1306        1: automatic flow labels are enabled by default, they can be
1307           disabled on a per socket basis using the IPV6_AUTOFLOWLABEL
1308           socket option
1309        2: automatic flow labels are allowed, they may be enabled on a
1310           per socket basis using the IPV6_AUTOFLOWLABEL socket option
1311        3: automatic flow labels are enabled and enforced, they cannot
1312           be disabled by the socket option
1313        Default: 1
1314
1315flowlabel_state_ranges - BOOLEAN
1316        Split the flow label number space into two ranges. 0-0x7FFFF is
1317        reserved for the IPv6 flow manager facility, 0x80000-0xFFFFF
1318        is reserved for stateless flow labels as described in RFC6437.
1319        TRUE: enabled
1320        FALSE: disabled
1321        Default: true
1322
1323anycast_src_echo_reply - BOOLEAN
1324        Controls the use of anycast addresses as source addresses for ICMPv6
1325        echo reply
1326        TRUE:  enabled
1327        FALSE: disabled
1328        Default: FALSE
1329
1330idgen_delay - INTEGER
1331        Controls the delay in seconds after which time to retry
1332        privacy stable address generation if a DAD conflict is
1333        detected.
1334        Default: 1 (as specified in RFC7217)
1335
1336idgen_retries - INTEGER
1337        Controls the number of retries to generate a stable privacy
1338        address if a DAD conflict is detected.
1339        Default: 3 (as specified in RFC7217)
1340
1341mld_qrv - INTEGER
1342        Controls the MLD query robustness variable (see RFC3810 9.1).
1343        Default: 2 (as specified by RFC3810 9.1)
1344        Minimum: 1 (as specified by RFC6636 4.5)
1345
1346IPv6 Fragmentation:
1347
1348ip6frag_high_thresh - INTEGER
1349        Maximum memory used to reassemble IPv6 fragments. When
1350        ip6frag_high_thresh bytes of memory is allocated for this purpose,
1351        the fragment handler will toss packets until ip6frag_low_thresh
1352        is reached.
1353
1354ip6frag_low_thresh - INTEGER
1355        See ip6frag_high_thresh
1356
1357ip6frag_time - INTEGER
1358        Time in seconds to keep an IPv6 fragment in memory.
1359
1360conf/default/*:
1361        Change the interface-specific default settings.
1362
1363
1364conf/all/*:
1365        Change all the interface-specific settings.
1366
1367        [XXX:  Other special features than forwarding?]
1368
1369conf/all/forwarding - BOOLEAN
1370        Enable global IPv6 forwarding between all interfaces.
1371
1372        IPv4 and IPv6 work differently here; e.g. netfilter must be used
1373        to control which interfaces may forward packets and which not.
1374
1375        This also sets all interfaces' Host/Router setting
1376        'forwarding' to the specified value.  See below for details.
1377
1378        This referred to as global forwarding.
1379
1380proxy_ndp - BOOLEAN
1381        Do proxy ndp.
1382
1383fwmark_reflect - BOOLEAN
1384        Controls the fwmark of kernel-generated IPv6 reply packets that are not
1385        associated with a socket for example, TCP RSTs or ICMPv6 echo replies).
1386        If unset, these packets have a fwmark of zero. If set, they have the
1387        fwmark of the packet they are replying to.
1388        Default: 0
1389
1390conf/interface/*:
1391        Change special settings per interface.
1392
1393        The functional behaviour for certain settings is different
1394        depending on whether local forwarding is enabled or not.
1395
1396accept_ra - INTEGER
1397        Accept Router Advertisements; autoconfigure using them.
1398
1399        It also determines whether or not to transmit Router
1400        Solicitations. If and only if the functional setting is to
1401        accept Router Advertisements, Router Solicitations will be
1402        transmitted.
1403
1404        Possible values are:
1405                0 Do not accept Router Advertisements.
1406                1 Accept Router Advertisements if forwarding is disabled.
1407                2 Overrule forwarding behaviour. Accept Router Advertisements
1408                  even if forwarding is enabled.
1409
1410        Functional default: enabled if local forwarding is disabled.
1411                            disabled if local forwarding is enabled.
1412
1413accept_ra_defrtr - BOOLEAN
1414        Learn default router in Router Advertisement.
1415
1416        Functional default: enabled if accept_ra is enabled.
1417                            disabled if accept_ra is disabled.
1418
1419accept_ra_from_local - BOOLEAN
1420        Accept RA with source-address that is found on local machine
1421        if the RA is otherwise proper and able to be accepted.
1422        Default is to NOT accept these as it may be an un-intended
1423        network loop.
1424
1425        Functional default:
1426           enabled if accept_ra_from_local is enabled
1427               on a specific interface.
1428           disabled if accept_ra_from_local is disabled
1429               on a specific interface.
1430
1431accept_ra_min_hop_limit - INTEGER
1432        Minimum hop limit Information in Router Advertisement.
1433
1434        Hop limit Information in Router Advertisement less than this
1435        variable shall be ignored.
1436
1437        Default: 1
1438
1439accept_ra_pinfo - BOOLEAN
1440        Learn Prefix Information in Router Advertisement.
1441
1442        Functional default: enabled if accept_ra is enabled.
1443                            disabled if accept_ra is disabled.
1444
1445accept_ra_rt_info_max_plen - INTEGER
1446        Maximum prefix length of Route Information in RA.
1447
1448        Route Information w/ prefix larger than or equal to this
1449        variable shall be ignored.
1450
1451        Functional default: 0 if accept_ra_rtr_pref is enabled.
1452                            -1 if accept_ra_rtr_pref is disabled.
1453
1454accept_ra_rtr_pref - BOOLEAN
1455        Accept Router Preference in RA.
1456
1457        Functional default: enabled if accept_ra is enabled.
1458                            disabled if accept_ra is disabled.
1459
1460accept_ra_mtu - BOOLEAN
1461        Apply the MTU value specified in RA option 5 (RFC4861). If
1462        disabled, the MTU specified in the RA will be ignored.
1463
1464        Functional default: enabled if accept_ra is enabled.
1465                            disabled if accept_ra is disabled.
1466
1467accept_redirects - BOOLEAN
1468        Accept Redirects.
1469
1470        Functional default: enabled if local forwarding is disabled.
1471                            disabled if local forwarding is enabled.
1472
1473accept_source_route - INTEGER
1474        Accept source routing (routing extension header).
1475
1476        >= 0: Accept only routing header type 2.
1477        < 0: Do not accept routing header.
1478
1479        Default: 0
1480
1481autoconf - BOOLEAN
1482        Autoconfigure addresses using Prefix Information in Router
1483        Advertisements.
1484
1485        Functional default: enabled if accept_ra_pinfo is enabled.
1486                            disabled if accept_ra_pinfo is disabled.
1487
1488dad_transmits - INTEGER
1489        The amount of Duplicate Address Detection probes to send.
1490        Default: 1
1491
1492forwarding - INTEGER
1493        Configure interface-specific Host/Router behaviour.
1494
1495        Note: It is recommended to have the same setting on all
1496        interfaces; mixed router/host scenarios are rather uncommon.
1497
1498        Possible values are:
1499                0 Forwarding disabled
1500                1 Forwarding enabled
1501
1502        FALSE (0):
1503
1504        By default, Host behaviour is assumed.  This means:
1505
1506        1. IsRouter flag is not set in Neighbour Advertisements.
1507        2. If accept_ra is TRUE (default), transmit Router
1508           Solicitations.
1509        3. If accept_ra is TRUE (default), accept Router
1510           Advertisements (and do autoconfiguration).
1511        4. If accept_redirects is TRUE (default), accept Redirects.
1512
1513        TRUE (1):
1514
1515        If local forwarding is enabled, Router behaviour is assumed.
1516        This means exactly the reverse from the above:
1517
1518        1. IsRouter flag is set in Neighbour Advertisements.
1519        2. Router Solicitations are not sent unless accept_ra is 2.
1520        3. Router Advertisements are ignored unless accept_ra is 2.
1521        4. Redirects are ignored.
1522
1523        Default: 0 (disabled) if global forwarding is disabled (default),
1524                 otherwise 1 (enabled).
1525
1526hop_limit - INTEGER
1527        Default Hop Limit to set.
1528        Default: 64
1529
1530mtu - INTEGER
1531        Default Maximum Transfer Unit
1532        Default: 1280 (IPv6 required minimum)
1533
1534ip_nonlocal_bind - BOOLEAN
1535        If set, allows processes to bind() to non-local IPv6 addresses,
1536        which can be quite useful - but may break some applications.
1537        Default: 0
1538
1539router_probe_interval - INTEGER
1540        Minimum interval (in seconds) between Router Probing described
1541        in RFC4191.
1542
1543        Default: 60
1544
1545router_solicitation_delay - INTEGER
1546        Number of seconds to wait after interface is brought up
1547        before sending Router Solicitations.
1548        Default: 1
1549
1550router_solicitation_interval - INTEGER
1551        Number of seconds to wait between Router Solicitations.
1552        Default: 4
1553
1554router_solicitations - INTEGER
1555        Number of Router Solicitations to send until assuming no
1556        routers are present.
1557        Default: 3
1558
1559use_oif_addrs_only - BOOLEAN
1560        When enabled, the candidate source addresses for destinations
1561        routed via this interface are restricted to the set of addresses
1562        configured on this interface (vis. RFC 6724, section 4).
1563
1564        Default: false
1565
1566use_tempaddr - INTEGER
1567        Preference for Privacy Extensions (RFC3041).
1568          <= 0 : disable Privacy Extensions
1569          == 1 : enable Privacy Extensions, but prefer public
1570                 addresses over temporary addresses.
1571          >  1 : enable Privacy Extensions and prefer temporary
1572                 addresses over public addresses.
1573        Default:  0 (for most devices)
1574                 -1 (for point-to-point devices and loopback devices)
1575
1576temp_valid_lft - INTEGER
1577        valid lifetime (in seconds) for temporary addresses.
1578        Default: 604800 (7 days)
1579
1580temp_prefered_lft - INTEGER
1581        Preferred lifetime (in seconds) for temporary addresses.
1582        Default: 86400 (1 day)
1583
1584keep_addr_on_down - INTEGER
1585        Keep all IPv6 addresses on an interface down event. If set static
1586        global addresses with no expiration time are not flushed.
1587          >0 : enabled
1588           0 : system default
1589          <0 : disabled
1590
1591        Default: 0 (addresses are removed)
1592
1593max_desync_factor - INTEGER
1594        Maximum value for DESYNC_FACTOR, which is a random value
1595        that ensures that clients don't synchronize with each
1596        other and generate new addresses at exactly the same time.
1597        value is in seconds.
1598        Default: 600
1599
1600regen_max_retry - INTEGER
1601        Number of attempts before give up attempting to generate
1602        valid temporary addresses.
1603        Default: 5
1604
1605max_addresses - INTEGER
1606        Maximum number of autoconfigured addresses per interface.  Setting
1607        to zero disables the limitation.  It is not recommended to set this
1608        value too large (or to zero) because it would be an easy way to
1609        crash the kernel by allowing too many addresses to be created.
1610        Default: 16
1611
1612disable_ipv6 - BOOLEAN
1613        Disable IPv6 operation.  If accept_dad is set to 2, this value
1614        will be dynamically set to TRUE if DAD fails for the link-local
1615        address.
1616        Default: FALSE (enable IPv6 operation)
1617
1618        When this value is changed from 1 to 0 (IPv6 is being enabled),
1619        it will dynamically create a link-local address on the given
1620        interface and start Duplicate Address Detection, if necessary.
1621
1622        When this value is changed from 0 to 1 (IPv6 is being disabled),
1623        it will dynamically delete all address on the given interface.
1624
1625accept_dad - INTEGER
1626        Whether to accept DAD (Duplicate Address Detection).
1627        0: Disable DAD
1628        1: Enable DAD (default)
1629        2: Enable DAD, and disable IPv6 operation if MAC-based duplicate
1630           link-local address has been found.
1631
1632force_tllao - BOOLEAN
1633        Enable sending the target link-layer address option even when
1634        responding to a unicast neighbor solicitation.
1635        Default: FALSE
1636
1637        Quoting from RFC 2461, section 4.4, Target link-layer address:
1638
1639        "The option MUST be included for multicast solicitations in order to
1640        avoid infinite Neighbor Solicitation "recursion" when the peer node
1641        does not have a cache entry to return a Neighbor Advertisements
1642        message.  When responding to unicast solicitations, the option can be
1643        omitted since the sender of the solicitation has the correct link-
1644        layer address; otherwise it would not have be able to send the unicast
1645        solicitation in the first place. However, including the link-layer
1646        address in this case adds little overhead and eliminates a potential
1647        race condition where the sender deletes the cached link-layer address
1648        prior to receiving a response to a previous solicitation."
1649
1650ndisc_notify - BOOLEAN
1651        Define mode for notification of address and device changes.
1652        0 - (default): do nothing
1653        1 - Generate unsolicited neighbour advertisements when device is brought
1654            up or hardware address changes.
1655
1656mldv1_unsolicited_report_interval - INTEGER
1657        The interval in milliseconds in which the next unsolicited
1658        MLDv1 report retransmit will take place.
1659        Default: 10000 (10 seconds)
1660
1661mldv2_unsolicited_report_interval - INTEGER
1662        The interval in milliseconds in which the next unsolicited
1663        MLDv2 report retransmit will take place.
1664        Default: 1000 (1 second)
1665
1666force_mld_version - INTEGER
1667        0 - (default) No enforcement of a MLD version, MLDv1 fallback allowed
1668        1 - Enforce to use MLD version 1
1669        2 - Enforce to use MLD version 2
1670
1671suppress_frag_ndisc - INTEGER
1672        Control RFC 6980 (Security Implications of IPv6 Fragmentation
1673        with IPv6 Neighbor Discovery) behavior:
1674        1 - (default) discard fragmented neighbor discovery packets
1675        0 - allow fragmented neighbor discovery packets
1676
1677optimistic_dad - BOOLEAN
1678        Whether to perform Optimistic Duplicate Address Detection (RFC 4429).
1679                0: disabled (default)
1680                1: enabled
1681
1682use_optimistic - BOOLEAN
1683        If enabled, do not classify optimistic addresses as deprecated during
1684        source address selection.  Preferred addresses will still be chosen
1685        before optimistic addresses, subject to other ranking in the source
1686        address selection algorithm.
1687                0: disabled (default)
1688                1: enabled
1689
1690stable_secret - IPv6 address
1691        This IPv6 address will be used as a secret to generate IPv6
1692        addresses for link-local addresses and autoconfigured
1693        ones. All addresses generated after setting this secret will
1694        be stable privacy ones by default. This can be changed via the
1695        addrgenmode ip-link. conf/default/stable_secret is used as the
1696        secret for the namespace, the interface specific ones can
1697        overwrite that. Writes to conf/all/stable_secret are refused.
1698
1699        It is recommended to generate this secret during installation
1700        of a system and keep it stable after that.
1701
1702        By default the stable secret is unset.
1703
1704drop_unicast_in_l2_multicast - BOOLEAN
1705        Drop any unicast IPv6 packets that are received in link-layer
1706        multicast (or broadcast) frames.
1707
1708        By default this is turned off.
1709
1710drop_unsolicited_na - BOOLEAN
1711        Drop all unsolicited neighbor advertisements, for example if there's
1712        a known good NA proxy on the network and such frames need not be used
1713        (or in the case of 802.11, must not be used to prevent attacks.)
1714
1715        By default this is turned off.
1716
1717icmp/*:
1718ratelimit - INTEGER
1719        Limit the maximal rates for sending ICMPv6 packets.
1720        0 to disable any limiting,
1721        otherwise the minimal space between responses in milliseconds.
1722        Default: 1000
1723
1724xfrm6_gc_thresh - INTEGER
1725        The threshold at which we will start garbage collecting for IPv6
1726        destination cache entries.  At twice this value the system will
1727        refuse new allocations. The value must be set below the flowcache
1728        limit (4096 * number of online cpus) to take effect.
1729
1730
1731IPv6 Update by:
1732Pekka Savola <pekkas@netcore.fi>
1733YOSHIFUJI Hideaki / USAGI Project <yoshfuji@linux-ipv6.org>
1734
1735
1736/proc/sys/net/bridge/* Variables:
1737
1738bridge-nf-call-arptables - BOOLEAN
1739        1 : pass bridged ARP traffic to arptables' FORWARD chain.
1740        0 : disable this.
1741        Default: 1
1742
1743bridge-nf-call-iptables - BOOLEAN
1744        1 : pass bridged IPv4 traffic to iptables' chains.
1745        0 : disable this.
1746        Default: 1
1747
1748bridge-nf-call-ip6tables - BOOLEAN
1749        1 : pass bridged IPv6 traffic to ip6tables' chains.
1750        0 : disable this.
1751        Default: 1
1752
1753bridge-nf-filter-vlan-tagged - BOOLEAN
1754        1 : pass bridged vlan-tagged ARP/IP/IPv6 traffic to {arp,ip,ip6}tables.
1755        0 : disable this.
1756        Default: 0
1757
1758bridge-nf-filter-pppoe-tagged - BOOLEAN
1759        1 : pass bridged pppoe-tagged IP/IPv6 traffic to {ip,ip6}tables.
1760        0 : disable this.
1761        Default: 0
1762
1763bridge-nf-pass-vlan-input-dev - BOOLEAN
1764        1: if bridge-nf-filter-vlan-tagged is enabled, try to find a vlan
1765        interface on the bridge and set the netfilter input device to the vlan.
1766        This allows use of e.g. "iptables -i br0.1" and makes the REDIRECT
1767        target work with vlan-on-top-of-bridge interfaces.  When no matching
1768        vlan interface is found, or this switch is off, the input device is
1769        set to the bridge interface.
1770        0: disable bridge netfilter vlan interface lookup.
1771        Default: 0
1772
1773proc/sys/net/sctp/* Variables:
1774
1775addip_enable - BOOLEAN
1776        Enable or disable extension of  Dynamic Address Reconfiguration
1777        (ADD-IP) functionality specified in RFC5061.  This extension provides
1778        the ability to dynamically add and remove new addresses for the SCTP
1779        associations.
1780
1781        1: Enable extension.
1782
1783        0: Disable extension.
1784
1785        Default: 0
1786
1787pf_enable - INTEGER
1788        Enable or disable pf (pf is short for potentially failed) state. A value
1789        of pf_retrans > path_max_retrans also disables pf state. That is, one of
1790        both pf_enable and pf_retrans > path_max_retrans can disable pf state.
1791        Since pf_retrans and path_max_retrans can be changed by userspace
1792        application, sometimes user expects to disable pf state by the value of
1793        pf_retrans > path_max_retrans, but occasionally the value of pf_retrans
1794        or path_max_retrans is changed by the user application, this pf state is
1795        enabled. As such, it is necessary to add this to dynamically enable
1796        and disable pf state. See:
1797        https://datatracker.ietf.org/doc/draft-ietf-tsvwg-sctp-failover for
1798        details.
1799
1800        1: Enable pf.
1801
1802        0: Disable pf.
1803
1804        Default: 1
1805
1806addip_noauth_enable - BOOLEAN
1807        Dynamic Address Reconfiguration (ADD-IP) requires the use of
1808        authentication to protect the operations of adding or removing new
1809        addresses.  This requirement is mandated so that unauthorized hosts
1810        would not be able to hijack associations.  However, older
1811        implementations may not have implemented this requirement while
1812        allowing the ADD-IP extension.  For reasons of interoperability,
1813        we provide this variable to control the enforcement of the
1814        authentication requirement.
1815
1816        1: Allow ADD-IP extension to be used without authentication.  This
1817           should only be set in a closed environment for interoperability
1818           with older implementations.
1819
1820        0: Enforce the authentication requirement
1821
1822        Default: 0
1823
1824auth_enable - BOOLEAN
1825        Enable or disable Authenticated Chunks extension.  This extension
1826        provides the ability to send and receive authenticated chunks and is
1827        required for secure operation of Dynamic Address Reconfiguration
1828        (ADD-IP) extension.
1829
1830        1: Enable this extension.
1831        0: Disable this extension.
1832
1833        Default: 0
1834
1835prsctp_enable - BOOLEAN
1836        Enable or disable the Partial Reliability extension (RFC3758) which
1837        is used to notify peers that a given DATA should no longer be expected.
1838
1839        1: Enable extension
1840        0: Disable
1841
1842        Default: 1
1843
1844max_burst - INTEGER
1845        The limit of the number of new packets that can be initially sent.  It
1846        controls how bursty the generated traffic can be.
1847
1848        Default: 4
1849
1850association_max_retrans - INTEGER
1851        Set the maximum number for retransmissions that an association can
1852        attempt deciding that the remote end is unreachable.  If this value
1853        is exceeded, the association is terminated.
1854
1855        Default: 10
1856
1857max_init_retransmits - INTEGER
1858        The maximum number of retransmissions of INIT and COOKIE-ECHO chunks
1859        that an association will attempt before declaring the destination
1860        unreachable and terminating.
1861
1862        Default: 8
1863
1864path_max_retrans - INTEGER
1865        The maximum number of retransmissions that will be attempted on a given
1866        path.  Once this threshold is exceeded, the path is considered
1867        unreachable, and new traffic will use a different path when the
1868        association is multihomed.
1869
1870        Default: 5
1871
1872pf_retrans - INTEGER
1873        The number of retransmissions that will be attempted on a given path
1874        before traffic is redirected to an alternate transport (should one
1875        exist).  Note this is distinct from path_max_retrans, as a path that
1876        passes the pf_retrans threshold can still be used.  Its only
1877        deprioritized when a transmission path is selected by the stack.  This
1878        setting is primarily used to enable fast failover mechanisms without
1879        having to reduce path_max_retrans to a very low value.  See:
1880        http://www.ietf.org/id/draft-nishida-tsvwg-sctp-failover-05.txt
1881        for details.  Note also that a value of pf_retrans > path_max_retrans
1882        disables this feature. Since both pf_retrans and path_max_retrans can
1883        be changed by userspace application, a variable pf_enable is used to
1884        disable pf state.
1885
1886        Default: 0
1887
1888rto_initial - INTEGER
1889        The initial round trip timeout value in milliseconds that will be used
1890        in calculating round trip times.  This is the initial time interval
1891        for retransmissions.
1892
1893        Default: 3000
1894
1895rto_max - INTEGER
1896        The maximum value (in milliseconds) of the round trip timeout.  This
1897        is the largest time interval that can elapse between retransmissions.
1898
1899        Default: 60000
1900
1901rto_min - INTEGER
1902        The minimum value (in milliseconds) of the round trip timeout.  This
1903        is the smallest time interval the can elapse between retransmissions.
1904
1905        Default: 1000
1906
1907hb_interval - INTEGER
1908        The interval (in milliseconds) between HEARTBEAT chunks.  These chunks
1909        are sent at the specified interval on idle paths to probe the state of
1910        a given path between 2 associations.
1911
1912        Default: 30000
1913
1914sack_timeout - INTEGER
1915        The amount of time (in milliseconds) that the implementation will wait
1916        to send a SACK.
1917
1918        Default: 200
1919
1920valid_cookie_life - INTEGER
1921        The default lifetime of the SCTP cookie (in milliseconds).  The cookie
1922        is used during association establishment.
1923
1924        Default: 60000
1925
1926cookie_preserve_enable - BOOLEAN
1927        Enable or disable the ability to extend the lifetime of the SCTP cookie
1928        that is used during the establishment phase of SCTP association
1929
1930        1: Enable cookie lifetime extension.
1931        0: Disable
1932
1933        Default: 1
1934
1935cookie_hmac_alg - STRING
1936        Select the hmac algorithm used when generating the cookie value sent by
1937        a listening sctp socket to a connecting client in the INIT-ACK chunk.
1938        Valid values are:
1939        * md5
1940        * sha1
1941        * none
1942        Ability to assign md5 or sha1 as the selected alg is predicated on the
1943        configuration of those algorithms at build time (CONFIG_CRYPTO_MD5 and
1944        CONFIG_CRYPTO_SHA1).
1945
1946        Default: Dependent on configuration.  MD5 if available, else SHA1 if
1947        available, else none.
1948
1949rcvbuf_policy - INTEGER
1950        Determines if the receive buffer is attributed to the socket or to
1951        association.   SCTP supports the capability to create multiple
1952        associations on a single socket.  When using this capability, it is
1953        possible that a single stalled association that's buffering a lot
1954        of data may block other associations from delivering their data by
1955        consuming all of the receive buffer space.  To work around this,
1956        the rcvbuf_policy could be set to attribute the receiver buffer space
1957        to each association instead of the socket.  This prevents the described
1958        blocking.
1959
1960        1: rcvbuf space is per association
1961        0: rcvbuf space is per socket
1962
1963        Default: 0
1964
1965sndbuf_policy - INTEGER
1966        Similar to rcvbuf_policy above, this applies to send buffer space.
1967
1968        1: Send buffer is tracked per association
1969        0: Send buffer is tracked per socket.
1970
1971        Default: 0
1972
1973sctp_mem - vector of 3 INTEGERs: min, pressure, max
1974        Number of pages allowed for queueing by all SCTP sockets.
1975
1976        min: Below this number of pages SCTP is not bothered about its
1977        memory appetite. When amount of memory allocated by SCTP exceeds
1978        this number, SCTP starts to moderate memory usage.
1979
1980        pressure: This value was introduced to follow format of tcp_mem.
1981
1982        max: Number of pages allowed for queueing by all SCTP sockets.
1983
1984        Default is calculated at boot time from amount of available memory.
1985
1986sctp_rmem - vector of 3 INTEGERs: min, default, max
1987        Only the first value ("min") is used, "default" and "max" are
1988        ignored.
1989
1990        min: Minimal size of receive buffer used by SCTP socket.
1991        It is guaranteed to each SCTP socket (but not association) even
1992        under moderate memory pressure.
1993
1994        Default: 1 page
1995
1996sctp_wmem  - vector of 3 INTEGERs: min, default, max
1997        Currently this tunable has no effect.
1998
1999addr_scope_policy - INTEGER
2000        Control IPv4 address scoping - draft-stewart-tsvwg-sctp-ipv4-00
2001
2002        0   - Disable IPv4 address scoping
2003        1   - Enable IPv4 address scoping
2004        2   - Follow draft but allow IPv4 private addresses
2005        3   - Follow draft but allow IPv4 link local addresses
2006
2007        Default: 1
2008
2009
2010/proc/sys/net/core/*
2011        Please see: Documentation/sysctl/net.txt for descriptions of these entries.
2012
2013
2014/proc/sys/net/unix/*
2015max_dgram_qlen - INTEGER
2016        The maximum length of dgram socket receive queue
2017
2018        Default: 10
2019
2020
2021UNDOCUMENTED:
2022
2023/proc/sys/net/irda/*
2024        fast_poll_increase FIXME
2025        warn_noreply_time FIXME
2026        discovery_slots FIXME
2027        slot_timeout FIXME
2028        max_baud_rate FIXME
2029        discovery_timeout FIXME
2030        lap_keepalive_time FIXME
2031        max_noreply_time FIXME
2032        max_tx_data_size FIXME
2033        max_tx_window FIXME
2034        min_tx_turn_time FIXME
2035
lxr.linux.no kindly hosted by Redpill Linpro AS, provider of Linux consulting and operations services since 1995.