Documentation/sysctl/net.txt

   1 Documentation for /proc/sys/net/*       kernel version 2.4.0-test11-pre4
   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 and is valid for Linux kernel version 2.4.0-test11-pre4.
  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
  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 rmem_default
  47 ------------
  48
  49 The default setting of the socket receive buffer in bytes.
  50
  51 rmem_max
  52 --------
  53
  54 The maximum receive socket buffer size in bytes.
  55
  56 wmem_default
  57 ------------
  58
  59 The default setting (in bytes) of the socket send buffer.
  60
  61 wmem_max
  62 --------
  63
  64 The maximum send socket buffer size in bytes.
  65
  66 message_burst and message_cost
  67 ------------------------------
  68
  69 These parameters  are used to limit the warning messages written to the kernel
  70 log from  the  networking  code.  They  enforce  a  rate  limit  to  make  a
  71 denial-of-service attack  impossible. A higher message_cost factor, results in
  72 fewer messages that will be written. Message_burst controls when messages will
  73 be dropped.  The  default  settings  limit  warning messages to one every five
  74 seconds.
  75
  76 warnings
  77 --------
  78
  79 This controls console messages from the networking stack that can occur because
  80 of problems on the network like duplicate address or bad checksums. Normally,
  81 this should be enabled, but if the problem persists the messages can be
  82 disabled.
  83
  84 netdev_budget
  85 -------------
  86
  87 Maximum number of packets taken from all interfaces in one polling cycle (NAPI
  88 poll). In one polling cycle interfaces which are registered to polling are
  89 probed in a round-robin manner. The limit of packets in one such probe can be
  90 set per-device via sysfs class/net/<device>/weight .
  91
  92 netdev_max_backlog
  93 ------------------
  94
  95 Maximum number  of  packets,  queued  on  the  INPUT  side, when the interface
  96 receives packets faster than kernel can process them.
  97
  98 netdev_tstamp_prequeue
  99 ----------------------
 100
 101 If set to 0, RX packet timestamps can be sampled after RPS processing, when
 102 the target CPU processes packets. It might give some delay on timestamps, but
 103 permit to distribute the load on several cpus.
 104
 105 If set to 1 (default), timestamps are sampled as soon as possible, before
 106 queueing.
 107
 108 optmem_max
 109 ----------
 110
 111 Maximum ancillary buffer size allowed per socket. Ancillary data is a sequence
 112 of struct cmsghdr structures with appended data.
 113
 114 2. /proc/sys/net/unix - Parameters for Unix domain sockets
 115 -------------------------------------------------------
 116
 117 There is only one file in this directory.
 118 unix_dgram_qlen limits the max number of datagrams queued in Unix domain
 119 socket's buffer. It will not take effect unless PF_UNIX flag is specified.
 120
 121
 122 3. /proc/sys/net/ipv4 - IPV4 settings
 123 -------------------------------------------------------
 124 Please see: Documentation/networking/ip-sysctl.txt and ipvs-sysctl.txt for
 125 descriptions of these entries.
 126
 127
 128 4. Appletalk
 129 -------------------------------------------------------
 130
 131 The /proc/sys/net/appletalk  directory  holds the Appletalk configuration data
 132 when Appletalk is loaded. The configurable parameters are:
 133
 134 aarp-expiry-time
 135 ----------------
 136
 137 The amount  of  time  we keep an ARP entry before expiring it. Used to age out
 138 old hosts.
 139
 140 aarp-resolve-time
 141 -----------------
 142
 143 The amount of time we will spend trying to resolve an Appletalk address.
 144
 145 aarp-retransmit-limit
 146 ---------------------
 147
 148 The number of times we will retransmit a query before giving up.
 149
 150 aarp-tick-time
 151 --------------
 152
 153 Controls the rate at which expires are checked.
 154
 155 The directory  /proc/net/appletalk  holds the list of active Appletalk sockets
 156 on a machine.
 157
 158 The fields  indicate  the DDP type, the local address (in network:node format)
 159 the remote  address,  the  size of the transmit pending queue, the size of the
 160 received queue  (bytes waiting for applications to read) the state and the uid
 161 owning the socket.
 162
 163 /proc/net/atalk_iface lists  all  the  interfaces  configured for appletalk.It
 164 shows the  name  of the interface, its Appletalk address, the network range on
 165 that address  (or  network number for phase 1 networks), and the status of the
 166 interface.
 167
 168 /proc/net/atalk_route lists  each  known  network  route.  It lists the target
 169 (network) that the route leads to, the router (may be directly connected), the
 170 route flags, and the device the route is using.
 171
 172
 173 5. IPX
 174 -------------------------------------------------------
 175
 176 The IPX protocol has no tunable values in proc/sys/net.
 177
 178 The IPX  protocol  does,  however,  provide  proc/net/ipx. This lists each IPX
 179 socket giving  the  local  and  remote  addresses  in  Novell  format (that is
 180 network:node:port). In  accordance  with  the  strange  Novell  tradition,
 181 everything but the port is in hex. Not_Connected is displayed for sockets that
 182 are not  tied to a specific remote address. The Tx and Rx queue sizes indicate
 183 the number  of  bytes  pending  for  transmission  and  reception.  The  state
 184 indicates the  state  the  socket  is  in and the uid is the owning uid of the
 185 socket.
 186
 187 The /proc/net/ipx_interface  file lists all IPX interfaces. For each interface
 188 it gives  the network number, the node number, and indicates if the network is
 189 the primary  network.  It  also  indicates  which  device  it  is bound to (or
 190 Internal for  internal  networks)  and  the  Frame  Type if appropriate. Linux
 191 supports 802.3,  802.2,  802.2  SNAP  and DIX (Blue Book) ethernet framing for
 192 IPX.
 193
 194 The /proc/net/ipx_route  table  holds  a list of IPX routes. For each route it
 195 gives the  destination  network, the router node (or Directly) and the network
 196 address of the router (or Connected) for internal networks.