blob: 98335b7a533795607ccedcfb5d3975a45acba0fe [file] [log] [blame]
Shen Feng760df932009-04-02 16:57:20 -07001Documentation 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
7For general info and legal blurb, please look in README.
8
9==============================================================
10
11This 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
14The interface to the networking parts of the kernel is located in
15/proc/sys/net. The following table shows all possible subdirectories.You may
16see only some of them, depending on your kernel's configuration.
17
18
19Table : 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
321. /proc/sys/net/core - Network core options
33-------------------------------------------------------
34
Eric Dumazet0a148422011-04-20 09:27:32 +000035bpf_jit_enable
36--------------
37
38This enables Berkeley Packet Filter Just in Time compiler.
39Currently supported on x86_64 architecture, bpf_jit provides a framework
40to speed packet filtering, the one used by tcpdump/libpcap for example.
41Values :
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
Shan Weic60f6aa2012-04-26 16:52:52 +000046dev_weight
47--------------
48
49The maximum number of packets that kernel can handle on a NAPI interrupt,
50it's a Per-CPU variable.
51Default: 64
52
Shen Feng760df932009-04-02 16:57:20 -070053rmem_default
54------------
55
56The default setting of the socket receive buffer in bytes.
57
58rmem_max
59--------
60
61The maximum receive socket buffer size in bytes.
62
63wmem_default
64------------
65
66The default setting (in bytes) of the socket send buffer.
67
68wmem_max
69--------
70
71The maximum send socket buffer size in bytes.
72
73message_burst and message_cost
74------------------------------
75
76These parameters are used to limit the warning messages written to the kernel
77log from the networking code. They enforce a rate limit to make a
78denial-of-service attack impossible. A higher message_cost factor, results in
79fewer messages that will be written. Message_burst controls when messages will
80be dropped. The default settings limit warning messages to one every five
81seconds.
82
83warnings
84--------
85
86This controls console messages from the networking stack that can occur because
87of problems on the network like duplicate address or bad checksums. Normally,
88this should be enabled, but if the problem persists the messages can be
89disabled.
90
91netdev_budget
92-------------
93
94Maximum number of packets taken from all interfaces in one polling cycle (NAPI
95poll). In one polling cycle interfaces which are registered to polling are
96probed in a round-robin manner. The limit of packets in one such probe can be
97set per-device via sysfs class/net/<device>/weight .
98
99netdev_max_backlog
100------------------
101
102Maximum number of packets, queued on the INPUT side, when the interface
103receives packets faster than kernel can process them.
104
Eric Dumazet3b098e22010-05-15 23:57:10 -0700105netdev_tstamp_prequeue
106----------------------
107
108If set to 0, RX packet timestamps can be sampled after RPS processing, when
109the target CPU processes packets. It might give some delay on timestamps, but
110permit to distribute the load on several cpus.
111
112If set to 1 (default), timestamps are sampled as soon as possible, before
113queueing.
114
Shen Feng760df932009-04-02 16:57:20 -0700115optmem_max
116----------
117
118Maximum ancillary buffer size allowed per socket. Ancillary data is a sequence
119of struct cmsghdr structures with appended data.
120
1212. /proc/sys/net/unix - Parameters for Unix domain sockets
122-------------------------------------------------------
123
Li Xiaodong45dad7b2009-04-02 16:57:21 -0700124There is only one file in this directory.
125unix_dgram_qlen limits the max number of datagrams queued in Unix domain
Li Zefanca8b9952009-04-13 14:39:36 -0700126socket's buffer. It will not take effect unless PF_UNIX flag is specified.
Shen Feng760df932009-04-02 16:57:20 -0700127
128
1293. /proc/sys/net/ipv4 - IPV4 settings
130-------------------------------------------------------
131Please see: Documentation/networking/ip-sysctl.txt and ipvs-sysctl.txt for
132descriptions of these entries.
133
134
1354. Appletalk
136-------------------------------------------------------
137
138The /proc/sys/net/appletalk directory holds the Appletalk configuration data
139when Appletalk is loaded. The configurable parameters are:
140
141aarp-expiry-time
142----------------
143
144The amount of time we keep an ARP entry before expiring it. Used to age out
145old hosts.
146
147aarp-resolve-time
148-----------------
149
150The amount of time we will spend trying to resolve an Appletalk address.
151
152aarp-retransmit-limit
153---------------------
154
155The number of times we will retransmit a query before giving up.
156
157aarp-tick-time
158--------------
159
160Controls the rate at which expires are checked.
161
162The directory /proc/net/appletalk holds the list of active Appletalk sockets
163on a machine.
164
165The fields indicate the DDP type, the local address (in network:node format)
166the remote address, the size of the transmit pending queue, the size of the
167received queue (bytes waiting for applications to read) the state and the uid
168owning the socket.
169
170/proc/net/atalk_iface lists all the interfaces configured for appletalk.It
171shows the name of the interface, its Appletalk address, the network range on
172that address (or network number for phase 1 networks), and the status of the
173interface.
174
175/proc/net/atalk_route lists each known network route. It lists the target
176(network) that the route leads to, the router (may be directly connected), the
177route flags, and the device the route is using.
178
179
1805. IPX
181-------------------------------------------------------
182
183The IPX protocol has no tunable values in proc/sys/net.
184
185The IPX protocol does, however, provide proc/net/ipx. This lists each IPX
186socket giving the local and remote addresses in Novell format (that is
187network:node:port). In accordance with the strange Novell tradition,
188everything but the port is in hex. Not_Connected is displayed for sockets that
189are not tied to a specific remote address. The Tx and Rx queue sizes indicate
190the number of bytes pending for transmission and reception. The state
191indicates the state the socket is in and the uid is the owning uid of the
192socket.
193
194The /proc/net/ipx_interface file lists all IPX interfaces. For each interface
195it gives the network number, the node number, and indicates if the network is
196the primary network. It also indicates which device it is bound to (or
197Internal for internal networks) and the Frame Type if appropriate. Linux
198supports 802.3, 802.2, 802.2 SNAP and DIX (Blue Book) ethernet framing for
199IPX.
200
201The /proc/net/ipx_route table holds a list of IPX routes. For each route it
202gives the destination network, the router node (or Directly) and the network
203address of the router (or Connected) for internal networks.