]> git.proxmox.com Git - mirror_ubuntu-artful-kernel.git/blob - Documentation/sysctl/net.txt
85ab72dcdc3c9f61198555b56020f84edfe2554b
[mirror_ubuntu-artful-kernel.git] / 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 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_poll
54 ----------------
55 Low latency busy poll timeout. (needs CONFIG_NET_LL_RX_POLL)
56 Approximate time in us to spin waiting for packets on the device queue.
57 Recommended value is 50. May increase power usage.
58 Default: 0 (off)
59
60 rmem_default
61 ------------
62
63 The default setting of the socket receive buffer in bytes.
64
65 rmem_max
66 --------
67
68 The maximum receive socket buffer size in bytes.
69
70 wmem_default
71 ------------
72
73 The default setting (in bytes) of the socket send buffer.
74
75 wmem_max
76 --------
77
78 The maximum send socket buffer size in bytes.
79
80 message_burst and message_cost
81 ------------------------------
82
83 These parameters are used to limit the warning messages written to the kernel
84 log from the networking code. They enforce a rate limit to make a
85 denial-of-service attack impossible. A higher message_cost factor, results in
86 fewer messages that will be written. Message_burst controls when messages will
87 be dropped. The default settings limit warning messages to one every five
88 seconds.
89
90 warnings
91 --------
92
93 This controls console messages from the networking stack that can occur because
94 of problems on the network like duplicate address or bad checksums. Normally,
95 this should be enabled, but if the problem persists the messages can be
96 disabled.
97
98 netdev_budget
99 -------------
100
101 Maximum number of packets taken from all interfaces in one polling cycle (NAPI
102 poll). In one polling cycle interfaces which are registered to polling are
103 probed in a round-robin manner.
104
105 netdev_max_backlog
106 ------------------
107
108 Maximum number of packets, queued on the INPUT side, when the interface
109 receives packets faster than kernel can process them.
110
111 netdev_tstamp_prequeue
112 ----------------------
113
114 If set to 0, RX packet timestamps can be sampled after RPS processing, when
115 the target CPU processes packets. It might give some delay on timestamps, but
116 permit to distribute the load on several cpus.
117
118 If set to 1 (default), timestamps are sampled as soon as possible, before
119 queueing.
120
121 optmem_max
122 ----------
123
124 Maximum ancillary buffer size allowed per socket. Ancillary data is a sequence
125 of struct cmsghdr structures with appended data.
126
127 2. /proc/sys/net/unix - Parameters for Unix domain sockets
128 -------------------------------------------------------
129
130 There is only one file in this directory.
131 unix_dgram_qlen limits the max number of datagrams queued in Unix domain
132 socket's buffer. It will not take effect unless PF_UNIX flag is specified.
133
134
135 3. /proc/sys/net/ipv4 - IPV4 settings
136 -------------------------------------------------------
137 Please see: Documentation/networking/ip-sysctl.txt and ipvs-sysctl.txt for
138 descriptions of these entries.
139
140
141 4. Appletalk
142 -------------------------------------------------------
143
144 The /proc/sys/net/appletalk directory holds the Appletalk configuration data
145 when Appletalk is loaded. The configurable parameters are:
146
147 aarp-expiry-time
148 ----------------
149
150 The amount of time we keep an ARP entry before expiring it. Used to age out
151 old hosts.
152
153 aarp-resolve-time
154 -----------------
155
156 The amount of time we will spend trying to resolve an Appletalk address.
157
158 aarp-retransmit-limit
159 ---------------------
160
161 The number of times we will retransmit a query before giving up.
162
163 aarp-tick-time
164 --------------
165
166 Controls the rate at which expires are checked.
167
168 The directory /proc/net/appletalk holds the list of active Appletalk sockets
169 on a machine.
170
171 The fields indicate the DDP type, the local address (in network:node format)
172 the remote address, the size of the transmit pending queue, the size of the
173 received queue (bytes waiting for applications to read) the state and the uid
174 owning the socket.
175
176 /proc/net/atalk_iface lists all the interfaces configured for appletalk.It
177 shows the name of the interface, its Appletalk address, the network range on
178 that address (or network number for phase 1 networks), and the status of the
179 interface.
180
181 /proc/net/atalk_route lists each known network route. It lists the target
182 (network) that the route leads to, the router (may be directly connected), the
183 route flags, and the device the route is using.
184
185
186 5. IPX
187 -------------------------------------------------------
188
189 The IPX protocol has no tunable values in proc/sys/net.
190
191 The IPX protocol does, however, provide proc/net/ipx. This lists each IPX
192 socket giving the local and remote addresses in Novell format (that is
193 network:node:port). In accordance with the strange Novell tradition,
194 everything but the port is in hex. Not_Connected is displayed for sockets that
195 are not tied to a specific remote address. The Tx and Rx queue sizes indicate
196 the number of bytes pending for transmission and reception. The state
197 indicates the state the socket is in and the uid is the owning uid of the
198 socket.
199
200 The /proc/net/ipx_interface file lists all IPX interfaces. For each interface
201 it gives the network number, the node number, and indicates if the network is
202 the primary network. It also indicates which device it is bound to (or
203 Internal for internal networks) and the Frame Type if appropriate. Linux
204 supports 802.3, 802.2, 802.2 SNAP and DIX (Blue Book) ethernet framing for
205 IPX.
206
207 The /proc/net/ipx_route table holds a list of IPX routes. For each route it
208 gives the destination network, the router node (or Directly) and the network
209 address of the router (or Connected) for internal networks.