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 dev_weight
  47 --------------
  48
  49 The maximum number of packets that kernel can handle on a NAPI interrupt,
  50 it's a Per-CPU variable.
  51 Default: 64
  52
  53 low_latency_read
  54 ----------------
  55 Low latency busy poll timeout for socket reads. (needs CONFIG_NET_LL_RX_POLL)
  56 Approximate time in us to busy loop waiting for packets on the device queue.
  57 This sets the default value of the SO_LL socket option.
  58 Can be set or overridden per socket by setting socket option SO_LL, which is
  59 the preferred method of enabling.
  60 If you need to enable the feature globally via sysctl, a value of 50 is recommended.
  61 Will increase power usage.
  62 Default: 0 (off)
  63
  64 low_latency_poll
  65 ----------------
  66 Low latency busy poll timeout for poll and select. (needs CONFIG_NET_LL_RX_POLL)
  67 Approximate time in us to busy loop waiting for events.
  68 Recommended value depends on the number of sockets you poll on.
  69 For several sockets 50, for several hundreds 100.
  70 For more than that you probably want to use epoll.
  71 Note that only sockets with SO_LL set will be busy polled, so you want to either
  72 selectively set SO_LL on those sockets or set sysctl.net.low_latency_read globally.
  73 Will increase power usage.
  74 Default: 0 (off)
  75
  76 rmem_default
  77 ------------
  78
  79 The default setting of the socket receive buffer in bytes.
  80
  81 rmem_max
  82 --------
  83
  84 The maximum receive socket buffer size in bytes.
  85
  86 wmem_default
  87 ------------
  88
  89 The default setting (in bytes) of the socket send buffer.
  90
  91 wmem_max
  92 --------
  93
  94 The maximum send socket buffer size in bytes.
  95
  96 message_burst and message_cost
  97 ------------------------------
  98
  99 These parameters  are used to limit the warning messages written to the kernel
 100 log from  the  networking  code.  They  enforce  a  rate  limit  to  make  a
 101 denial-of-service attack  impossible. A higher message_cost factor, results in
 102 fewer messages that will be written. Message_burst controls when messages will
 103 be dropped.  The  default  settings  limit  warning messages to one every five
 104 seconds.
 105
 106 warnings
 107 --------
 108
 109 This controls console messages from the networking stack that can occur because
 110 of problems on the network like duplicate address or bad checksums. Normally,
 111 this should be enabled, but if the problem persists the messages can be
 112 disabled.
 113
 114 netdev_budget
 115 -------------
 116
 117 Maximum number of packets taken from all interfaces in one polling cycle (NAPI
 118 poll). In one polling cycle interfaces which are registered to polling are
 119 probed in a round-robin manner.
 120
 121 netdev_max_backlog
 122 ------------------
 123
 124 Maximum number  of  packets,  queued  on  the  INPUT  side, when the interface
 125 receives packets faster than kernel can process them.
 126
 127 netdev_tstamp_prequeue
 128 ----------------------
 129
 130 If set to 0, RX packet timestamps can be sampled after RPS processing, when
 131 the target CPU processes packets. It might give some delay on timestamps, but
 132 permit to distribute the load on several cpus.
 133
 134 If set to 1 (default), timestamps are sampled as soon as possible, before
 135 queueing.
 136
 137 optmem_max
 138 ----------
 139
 140 Maximum ancillary buffer size allowed per socket. Ancillary data is a sequence
 141 of struct cmsghdr structures with appended data.
 142
 143 2. /proc/sys/net/unix - Parameters for Unix domain sockets
 144 -------------------------------------------------------
 145
 146 There is only one file in this directory.
 147 unix_dgram_qlen limits the max number of datagrams queued in Unix domain
 148 socket's buffer. It will not take effect unless PF_UNIX flag is specified.
 149
 150
 151 3. /proc/sys/net/ipv4 - IPV4 settings
 152 -------------------------------------------------------
 153 Please see: Documentation/networking/ip-sysctl.txt and ipvs-sysctl.txt for
 154 descriptions of these entries.
 155
 156
 157 4. Appletalk
 158 -------------------------------------------------------
 159
 160 The /proc/sys/net/appletalk  directory  holds the Appletalk configuration data
 161 when Appletalk is loaded. The configurable parameters are:
 162
 163 aarp-expiry-time
 164 ----------------
 165
 166 The amount  of  time  we keep an ARP entry before expiring it. Used to age out
 167 old hosts.
 168
 169 aarp-resolve-time
 170 -----------------
 171
 172 The amount of time we will spend trying to resolve an Appletalk address.
 173
 174 aarp-retransmit-limit
 175 ---------------------
 176
 177 The number of times we will retransmit a query before giving up.
 178
 179 aarp-tick-time
 180 --------------
 181
 182 Controls the rate at which expires are checked.
 183
 184 The directory  /proc/net/appletalk  holds the list of active Appletalk sockets
 185 on a machine.
 186
 187 The fields  indicate  the DDP type, the local address (in network:node format)
 188 the remote  address,  the  size of the transmit pending queue, the size of the
 189 received queue  (bytes waiting for applications to read) the state and the uid
 190 owning the socket.
 191
 192 /proc/net/atalk_iface lists  all  the  interfaces  configured for appletalk.It
 193 shows the  name  of the interface, its Appletalk address, the network range on
 194 that address  (or  network number for phase 1 networks), and the status of the
 195 interface.
 196
 197 /proc/net/atalk_route lists  each  known  network  route.  It lists the target
 198 (network) that the route leads to, the router (may be directly connected), the
 199 route flags, and the device the route is using.
 200
 201
 202 5. IPX
 203 -------------------------------------------------------
 204
 205 The IPX protocol has no tunable values in proc/sys/net.
 206
 207 The IPX  protocol  does,  however,  provide  proc/net/ipx. This lists each IPX
 208 socket giving  the  local  and  remote  addresses  in  Novell  format (that is
 209 network:node:port). In  accordance  with  the  strange  Novell  tradition,
 210 everything but the port is in hex. Not_Connected is displayed for sockets that
 211 are not  tied to a specific remote address. The Tx and Rx queue sizes indicate
 212 the number  of  bytes  pending  for  transmission  and  reception.  The  state
 213 indicates the  state  the  socket  is  in and the uid is the owning uid of the
 214 socket.
 215
 216 The /proc/net/ipx_interface  file lists all IPX interfaces. For each interface
 217 it gives  the network number, the node number, and indicates if the network is
 218 the primary  network.  It  also  indicates  which  device  it  is bound to (or
 219 Internal for  internal  networks)  and  the  Frame  Type if appropriate. Linux
 220 supports 802.3,  802.2,  802.2  SNAP  and DIX (Blue Book) ethernet framing for
 221 IPX.
 222
 223 The /proc/net/ipx_route  table  holds  a list of IPX routes. For each route it
 224 gives the  destination  network, the router node (or Directly) and the network
 225 address of the router (or Connected) for internal networks.
 226
 227 6. TIPC
 228 -------------------------------------------------------
 229
 230 The TIPC protocol now has a tunable for the receive memory, similar to the
 231 tcp_rmem - i.e. a vector of 3 INTEGERs: (min, default, max)
 232
 233     # cat /proc/sys/net/tipc/tipc_rmem
 234     4252725 34021800        68043600
 235     #
 236
 237 The max value is set to CONN_OVERLOAD_LIMIT, and the default and min values
 238 are scaled (shifted) versions of that same value.  Note that the min value
 239 is not at this point in time used in any meaningful way, but the triplet is
 240 preserved in order to be consistent with things like tcp_rmem.