Documentation/sysctl/net.txt

   1 Documentation for /proc/sys/net/*
   2         (c) 1999                Terrehon Bowden <terrehon@pacbell.net>
   3                                 Bodo Bauer <bb@ricochet.net>
   4         (c) 2000                Jorge Nerin <comandante@zaralinux.com>
   5         (c) 2009                Shen Feng <shen@cn.fujitsu.com>
   6
   7 For general info and legal blurb, please look in README.
   8
   9 ==============================================================
  10
  11 This file contains the documentation for the sysctl files in
  12 /proc/sys/net
  13
  14 The interface  to  the  networking  parts  of  the  kernel  is  located  in
  15 /proc/sys/net. The following table shows all possible subdirectories.  You may
  16 see only some of them, depending on your kernel's configuration.
  17
  18
  19 Table : Subdirectories in /proc/sys/net
  20 ..............................................................................
  21  Directory Content             Directory  Content
  22  core      General parameter   appletalk  Appletalk protocol
  23  unix      Unix domain sockets netrom     NET/ROM
  24  802       E802 protocol       ax25       AX25
  25  ethernet  Ethernet protocol   rose       X.25 PLP layer
  26  ipv4      IP version 4        x25        X.25 protocol
  27  ipx       IPX                 token-ring IBM token ring
  28  bridge    Bridging            decnet     DEC net
  29  ipv6      IP version 6        tipc       TIPC
  30 ..............................................................................
  31
  32 1. /proc/sys/net/core - Network core options
  33 -------------------------------------------------------
  34
  35 bpf_jit_enable
  36 --------------
  37
  38 This enables Berkeley Packet Filter Just in Time compiler.
  39 Currently supported on x86_64 architecture, bpf_jit provides a framework
  40 to speed packet filtering, the one used by tcpdump/libpcap for example.
  41 Values :
  42         0 - disable the JIT (default value)
  43         1 - enable the JIT
  44         2 - enable the JIT and ask the compiler to emit traces on kernel log.
  45
  46 bpf_jit_harden
  47 --------------
  48
  49 This enables hardening for the Berkeley Packet Filter Just in Time compiler.
  50 Supported are eBPF JIT backends. Enabling hardening trades off performance,
  51 but can mitigate JIT spraying.
  52 Values :
  53         0 - disable JIT hardening (default value)
  54         1 - enable JIT hardening for unprivileged users only
  55         2 - enable JIT hardening for all users
  56
  57 dev_weight
  58 --------------
  59
  60 The maximum number of packets that kernel can handle on a NAPI interrupt,
  61 it's a Per-CPU variable.
  62 Default: 64
  63
  64 default_qdisc
  65 --------------
  66
  67 The default queuing discipline to use for network devices. This allows
  68 overriding the default of pfifo_fast with an alternative. Since the default
  69 queuing discipline is created without additional parameters so is best suited
  70 to queuing disciplines that work well without configuration like stochastic
  71 fair queue (sfq), CoDel (codel) or fair queue CoDel (fq_codel). Don't use
  72 queuing disciplines like Hierarchical Token Bucket or Deficit Round Robin
  73 which require setting up classes and bandwidths. Note that physical multiqueue
  74 interfaces still use mq as root qdisc, which in turn uses this default for its
  75 leaves. Virtual devices (like e.g. lo or veth) ignore this setting and instead
  76 default to noqueue.
  77 Default: pfifo_fast
  78
  79 busy_read
  80 ----------------
  81 Low latency busy poll timeout for socket reads. (needs CONFIG_NET_RX_BUSY_POLL)
  82 Approximate time in us to busy loop waiting for packets on the device queue.
  83 This sets the default value of the SO_BUSY_POLL socket option.
  84 Can be set or overridden per socket by setting socket option SO_BUSY_POLL,
  85 which is the preferred method of enabling. If you need to enable the feature
  86 globally via sysctl, a value of 50 is recommended.
  87 Will increase power usage.
  88 Default: 0 (off)
  89
  90 busy_poll
  91 ----------------
  92 Low latency busy poll timeout for poll and select. (needs CONFIG_NET_RX_BUSY_POLL)
  93 Approximate time in us to busy loop waiting for events.
  94 Recommended value depends on the number of sockets you poll on.
  95 For several sockets 50, for several hundreds 100.
  96 For more than that you probably want to use epoll.
  97 Note that only sockets with SO_BUSY_POLL set will be busy polled,
  98 so you want to either selectively set SO_BUSY_POLL on those sockets or set
  99 sysctl.net.busy_read globally.
 100 Will increase power usage.
 101 Default: 0 (off)
 102
 103 rmem_default
 104 ------------
 105
 106 The default setting of the socket receive buffer in bytes.
 107
 108 rmem_max
 109 --------
 110
 111 The maximum receive socket buffer size in bytes.
 112
 113 tstamp_allow_data
 114 -----------------
 115 Allow processes to receive tx timestamps looped together with the original
 116 packet contents. If disabled, transmit timestamp requests from unprivileged
 117 processes are dropped unless socket option SOF_TIMESTAMPING_OPT_TSONLY is set.
 118 Default: 1 (on)
 119
 120
 121 wmem_default
 122 ------------
 123
 124 The default setting (in bytes) of the socket send buffer.
 125
 126 wmem_max
 127 --------
 128
 129 The maximum send socket buffer size in bytes.
 130
 131 message_burst and message_cost
 132 ------------------------------
 133
 134 These parameters  are used to limit the warning messages written to the kernel
 135 log from  the  networking  code.  They  enforce  a  rate  limit  to  make  a
 136 denial-of-service attack  impossible. A higher message_cost factor, results in
 137 fewer messages that will be written. Message_burst controls when messages will
 138 be dropped.  The  default  settings  limit  warning messages to one every five
 139 seconds.
 140
 141 warnings
 142 --------
 143
 144 This sysctl is now unused.
 145
 146 This was used to control console messages from the networking stack that
 147 occur because of problems on the network like duplicate address or bad
 148 checksums.
 149
 150 These messages are now emitted at KERN_DEBUG and can generally be enabled
 151 and controlled by the dynamic_debug facility.
 152
 153 netdev_budget
 154 -------------
 155
 156 Maximum number of packets taken from all interfaces in one polling cycle (NAPI
 157 poll). In one polling cycle interfaces which are registered to polling are
 158 probed in a round-robin manner.
 159
 160 netdev_max_backlog
 161 ------------------
 162
 163 Maximum number  of  packets,  queued  on  the  INPUT  side, when the interface
 164 receives packets faster than kernel can process them.
 165
 166 netdev_rss_key
 167 --------------
 168
 169 RSS (Receive Side Scaling) enabled drivers use a 40 bytes host key that is
 170 randomly generated.
 171 Some user space might need to gather its content even if drivers do not
 172 provide ethtool -x support yet.
 173
 174 myhost:~# cat /proc/sys/net/core/netdev_rss_key
 175 84:50:f4:00:a8:15:d1:a7:e9:7f:1d:60:35:c7:47:25:42:97:74:ca:56:bb:b6:a1:d8: ... (52 bytes total)
 176
 177 File contains nul bytes if no driver ever called netdev_rss_key_fill() function.
 178 Note:
 179 /proc/sys/net/core/netdev_rss_key contains 52 bytes of key,
 180 but most drivers only use 40 bytes of it.
 181
 182 myhost:~# ethtool -x eth0
 183 RX flow hash indirection table for eth0 with 8 RX ring(s):
 184     0:    0     1     2     3     4     5     6     7
 185 RSS hash key:
 186 84:50:f4:00:a8:15:d1:a7:e9:7f:1d:60:35:c7:47:25:42:97:74:ca:56:bb:b6:a1:d8:43:e3:c9:0c:fd:17:55:c2:3a:4d:69:ed:f1:42:89
 187
 188 netdev_tstamp_prequeue
 189 ----------------------
 190
 191 If set to 0, RX packet timestamps can be sampled after RPS processing, when
 192 the target CPU processes packets. It might give some delay on timestamps, but
 193 permit to distribute the load on several cpus.
 194
 195 If set to 1 (default), timestamps are sampled as soon as possible, before
 196 queueing.
 197
 198 optmem_max
 199 ----------
 200
 201 Maximum ancillary buffer size allowed per socket. Ancillary data is a sequence
 202 of struct cmsghdr structures with appended data.
 203
 204 2. /proc/sys/net/unix - Parameters for Unix domain sockets
 205 -------------------------------------------------------
 206
 207 There is only one file in this directory.
 208 unix_dgram_qlen limits the max number of datagrams queued in Unix domain
 209 socket's buffer. It will not take effect unless PF_UNIX flag is specified.
 210
 211
 212 3. /proc/sys/net/ipv4 - IPV4 settings
 213 -------------------------------------------------------
 214 Please see: Documentation/networking/ip-sysctl.txt and ipvs-sysctl.txt for
 215 descriptions of these entries.
 216
 217
 218 4. Appletalk
 219 -------------------------------------------------------
 220
 221 The /proc/sys/net/appletalk  directory  holds the Appletalk configuration data
 222 when Appletalk is loaded. The configurable parameters are:
 223
 224 aarp-expiry-time
 225 ----------------
 226
 227 The amount  of  time  we keep an ARP entry before expiring it. Used to age out
 228 old hosts.
 229
 230 aarp-resolve-time
 231 -----------------
 232
 233 The amount of time we will spend trying to resolve an Appletalk address.
 234
 235 aarp-retransmit-limit
 236 ---------------------
 237
 238 The number of times we will retransmit a query before giving up.
 239
 240 aarp-tick-time
 241 --------------
 242
 243 Controls the rate at which expires are checked.
 244
 245 The directory  /proc/net/appletalk  holds the list of active Appletalk sockets
 246 on a machine.
 247
 248 The fields  indicate  the DDP type, the local address (in network:node format)
 249 the remote  address,  the  size of the transmit pending queue, the size of the
 250 received queue  (bytes waiting for applications to read) the state and the uid
 251 owning the socket.
 252
 253 /proc/net/atalk_iface lists  all  the  interfaces  configured for appletalk.It
 254 shows the  name  of the interface, its Appletalk address, the network range on
 255 that address  (or  network number for phase 1 networks), and the status of the
 256 interface.
 257
 258 /proc/net/atalk_route lists  each  known  network  route.  It lists the target
 259 (network) that the route leads to, the router (may be directly connected), the
 260 route flags, and the device the route is using.
 261
 262
 263 5. IPX
 264 -------------------------------------------------------
 265
 266 The IPX protocol has no tunable values in proc/sys/net.
 267
 268 The IPX  protocol  does,  however,  provide  proc/net/ipx. This lists each IPX
 269 socket giving  the  local  and  remote  addresses  in  Novell  format (that is
 270 network:node:port). In  accordance  with  the  strange  Novell  tradition,
 271 everything but the port is in hex. Not_Connected is displayed for sockets that
 272 are not  tied to a specific remote address. The Tx and Rx queue sizes indicate
 273 the number  of  bytes  pending  for  transmission  and  reception.  The  state
 274 indicates the  state  the  socket  is  in and the uid is the owning uid of the
 275 socket.
 276
 277 The /proc/net/ipx_interface  file lists all IPX interfaces. For each interface
 278 it gives  the network number, the node number, and indicates if the network is
 279 the primary  network.  It  also  indicates  which  device  it  is bound to (or
 280 Internal for  internal  networks)  and  the  Frame  Type if appropriate. Linux
 281 supports 802.3,  802.2,  802.2  SNAP  and DIX (Blue Book) ethernet framing for
 282 IPX.
 283
 284 The /proc/net/ipx_route  table  holds  a list of IPX routes. For each route it
 285 gives the  destination  network, the router node (or Directly) and the network
 286 address of the router (or Connected) for internal networks.
 287
 288 6. TIPC
 289 -------------------------------------------------------
 290
 291 tipc_rmem
 292 ----------
 293
 294 The TIPC protocol now has a tunable for the receive memory, similar to the
 295 tcp_rmem - i.e. a vector of 3 INTEGERs: (min, default, max)
 296
 297     # cat /proc/sys/net/tipc/tipc_rmem
 298     4252725 34021800        68043600
 299     #
 300
 301 The max value is set to CONN_OVERLOAD_LIMIT, and the default and min values
 302 are scaled (shifted) versions of that same value.  Note that the min value
 303 is not at this point in time used in any meaningful way, but the triplet is
 304 preserved in order to be consistent with things like tcp_rmem.
 305
 306 named_timeout
 307 --------------
 308
 309 TIPC name table updates are distributed asynchronously in a cluster, without
 310 any form of transaction handling. This means that different race scenarios are
 311 possible. One such is that a name withdrawal sent out by one node and received
 312 by another node may arrive after a second, overlapping name publication already
 313 has been accepted from a third node, although the conflicting updates
 314 originally may have been issued in the correct sequential order.
 315 If named_timeout is nonzero, failed topology updates will be placed on a defer
 316 queue until another event arrives that clears the error, or until the timeout
 317 expires. Value is in milliseconds.