1 ================================ 1 ================================
2 Documentation for /proc/sys/net/ 2 Documentation for /proc/sys/net/
3 ================================ 3 ================================
4 4
5 Copyright 5 Copyright
6 6
7 Copyright (c) 1999 7 Copyright (c) 1999
8 8
9 - Terrehon Bowden <terrehon@pacbell.net 9 - Terrehon Bowden <terrehon@pacbell.net>
10 - Bodo Bauer <bb@ricochet.net> 10 - Bodo Bauer <bb@ricochet.net>
11 11
12 Copyright (c) 2000 12 Copyright (c) 2000
13 13
14 - Jorge Nerin <comandante@zaralinux.com 14 - Jorge Nerin <comandante@zaralinux.com>
15 15
16 Copyright (c) 2009 16 Copyright (c) 2009
17 17
18 - Shen Feng <shen@cn.fujitsu.com> 18 - Shen Feng <shen@cn.fujitsu.com>
19 19
20 For general info and legal blurb, please look 20 For general info and legal blurb, please look in index.rst.
21 21
22 ---------------------------------------------- 22 ------------------------------------------------------------------------------
23 23
24 This file contains the documentation for the s 24 This file contains the documentation for the sysctl files in
25 /proc/sys/net 25 /proc/sys/net
26 26
27 The interface to the networking parts of 27 The interface to the networking parts of the kernel is located in
28 /proc/sys/net. The following table shows all p 28 /proc/sys/net. The following table shows all possible subdirectories. You may
29 see only some of them, depending on your kerne 29 see only some of them, depending on your kernel's configuration.
30 30
31 31
32 Table : Subdirectories in /proc/sys/net 32 Table : Subdirectories in /proc/sys/net
33 33
34 ========= =================== = ========== == !! 34 ========= =================== = ========== ==================
35 Directory Content Directory Co 35 Directory Content Directory Content
36 ========= =================== = ========== == !! 36 ========= =================== = ========== ==================
37 802 E802 protocol mptcp Mu !! 37 core General parameter appletalk Appletalk protocol
38 appletalk Appletalk protocol netfilter Ne !! 38 unix Unix domain sockets netrom NET/ROM
39 ax25 AX25 netrom NE !! 39 802 E802 protocol ax25 AX25
40 bridge Bridging rose X. !! 40 ethernet Ethernet protocol rose X.25 PLP layer
41 core General parameter tipc TI <<
42 ethernet Ethernet protocol unix Un <<
43 ipv4 IP version 4 x25 X. 41 ipv4 IP version 4 x25 X.25 protocol
44 ipv6 IP version 6 !! 42 bridge Bridging decnet DEC net
45 ========= =================== = ========== == !! 43 ipv6 IP version 6 tipc TIPC
>> 44 ========= =================== = ========== ==================
46 45
47 1. /proc/sys/net/core - Network core options 46 1. /proc/sys/net/core - Network core options
48 ============================================ 47 ============================================
49 48
50 bpf_jit_enable 49 bpf_jit_enable
51 -------------- 50 --------------
52 51
53 This enables the BPF Just in Time (JIT) compil 52 This enables the BPF Just in Time (JIT) compiler. BPF is a flexible
54 and efficient infrastructure allowing to execu 53 and efficient infrastructure allowing to execute bytecode at various
55 hook points. It is used in a number of Linux k 54 hook points. It is used in a number of Linux kernel subsystems such
56 as networking (e.g. XDP, tc), tracing (e.g. kp 55 as networking (e.g. XDP, tc), tracing (e.g. kprobes, uprobes, tracepoints)
57 and security (e.g. seccomp). LLVM has a BPF ba 56 and security (e.g. seccomp). LLVM has a BPF back end that can compile
58 restricted C into a sequence of BPF instructio 57 restricted C into a sequence of BPF instructions. After program load
59 through bpf(2) and passing a verifier in the k 58 through bpf(2) and passing a verifier in the kernel, a JIT will then
60 translate these BPF proglets into native CPU i 59 translate these BPF proglets into native CPU instructions. There are
61 two flavors of JITs, the newer eBPF JIT curren 60 two flavors of JITs, the newer eBPF JIT currently supported on:
62 61
63 - x86_64 62 - x86_64
64 - x86_32 63 - x86_32
65 - arm64 64 - arm64
66 - arm32 65 - arm32
67 - ppc64 66 - ppc64
68 - ppc32 67 - ppc32
69 - sparc64 68 - sparc64
70 - mips64 69 - mips64
71 - s390x 70 - s390x
72 - riscv64 71 - riscv64
73 - riscv32 72 - riscv32
74 - loongarch64 <<
75 - arc <<
76 73
77 And the older cBPF JIT supported on the follow 74 And the older cBPF JIT supported on the following archs:
78 75
79 - mips 76 - mips
80 - sparc 77 - sparc
81 78
82 eBPF JITs are a superset of cBPF JITs, meaning 79 eBPF JITs are a superset of cBPF JITs, meaning the kernel will
83 migrate cBPF instructions into eBPF instructio 80 migrate cBPF instructions into eBPF instructions and then JIT
84 compile them transparently. Older cBPF JITs ca 81 compile them transparently. Older cBPF JITs can only translate
85 tcpdump filters, seccomp rules, etc, but not m 82 tcpdump filters, seccomp rules, etc, but not mentioned eBPF
86 programs loaded through bpf(2). 83 programs loaded through bpf(2).
87 84
88 Values: 85 Values:
89 86
90 - 0 - disable the JIT (default value) 87 - 0 - disable the JIT (default value)
91 - 1 - enable the JIT 88 - 1 - enable the JIT
92 - 2 - enable the JIT and ask the compi 89 - 2 - enable the JIT and ask the compiler to emit traces on kernel log.
93 90
94 bpf_jit_harden 91 bpf_jit_harden
95 -------------- 92 --------------
96 93
97 This enables hardening for the BPF JIT compile 94 This enables hardening for the BPF JIT compiler. Supported are eBPF
98 JIT backends. Enabling hardening trades off pe 95 JIT backends. Enabling hardening trades off performance, but can
99 mitigate JIT spraying. 96 mitigate JIT spraying.
100 97
101 Values: 98 Values:
102 99
103 - 0 - disable JIT hardening (default v 100 - 0 - disable JIT hardening (default value)
104 - 1 - enable JIT hardening for unprivi 101 - 1 - enable JIT hardening for unprivileged users only
105 - 2 - enable JIT hardening for all use 102 - 2 - enable JIT hardening for all users
106 103
107 where "privileged user" in this context means <<
108 CAP_BPF or CAP_SYS_ADMIN in the root user name <<
109 <<
110 bpf_jit_kallsyms 104 bpf_jit_kallsyms
111 ---------------- 105 ----------------
112 106
113 When BPF JIT compiler is enabled, then compile 107 When BPF JIT compiler is enabled, then compiled images are unknown
114 addresses to the kernel, meaning they neither 108 addresses to the kernel, meaning they neither show up in traces nor
115 in /proc/kallsyms. This enables export of thes 109 in /proc/kallsyms. This enables export of these addresses, which can
116 be used for debugging/tracing. If bpf_jit_hard 110 be used for debugging/tracing. If bpf_jit_harden is enabled, this
117 feature is disabled. 111 feature is disabled.
118 112
119 Values : 113 Values :
120 114
121 - 0 - disable JIT kallsyms export (def 115 - 0 - disable JIT kallsyms export (default value)
122 - 1 - enable JIT kallsyms export for p 116 - 1 - enable JIT kallsyms export for privileged users only
123 117
124 bpf_jit_limit 118 bpf_jit_limit
125 ------------- 119 -------------
126 120
127 This enforces a global limit for memory alloca 121 This enforces a global limit for memory allocations to the BPF JIT
128 compiler in order to reject unprivileged JIT r 122 compiler in order to reject unprivileged JIT requests once it has
129 been surpassed. bpf_jit_limit contains the val 123 been surpassed. bpf_jit_limit contains the value of the global limit
130 in bytes. 124 in bytes.
131 125
132 dev_weight 126 dev_weight
133 ---------- 127 ----------
134 128
135 The maximum number of packets that kernel can 129 The maximum number of packets that kernel can handle on a NAPI interrupt,
136 it's a Per-CPU variable. For drivers that supp 130 it's a Per-CPU variable. For drivers that support LRO or GRO_HW, a hardware
137 aggregated packet is counted as one packet in 131 aggregated packet is counted as one packet in this context.
138 132
139 Default: 64 133 Default: 64
140 134
141 dev_weight_rx_bias 135 dev_weight_rx_bias
142 ------------------ 136 ------------------
143 137
144 RPS (e.g. RFS, aRFS) processing is competing w 138 RPS (e.g. RFS, aRFS) processing is competing with the registered NAPI poll function
145 of the driver for the per softirq cycle netdev 139 of the driver for the per softirq cycle netdev_budget. This parameter influences
146 the proportion of the configured netdev_budget 140 the proportion of the configured netdev_budget that is spent on RPS based packet
147 processing during RX softirq cycles. It is fur 141 processing during RX softirq cycles. It is further meant for making current
148 dev_weight adaptable for asymmetric CPU needs 142 dev_weight adaptable for asymmetric CPU needs on RX/TX side of the network stack.
149 (see dev_weight_tx_bias) It is effective on a 143 (see dev_weight_tx_bias) It is effective on a per CPU basis. Determination is based
150 on dev_weight and is calculated multiplicative 144 on dev_weight and is calculated multiplicative (dev_weight * dev_weight_rx_bias).
151 145
152 Default: 1 146 Default: 1
153 147
154 dev_weight_tx_bias 148 dev_weight_tx_bias
155 ------------------ 149 ------------------
156 150
157 Scales the maximum number of packets that can 151 Scales the maximum number of packets that can be processed during a TX softirq cycle.
158 Effective on a per CPU basis. Allows scaling o 152 Effective on a per CPU basis. Allows scaling of current dev_weight for asymmetric
159 net stack processing needs. Be careful to avoi 153 net stack processing needs. Be careful to avoid making TX softirq processing a CPU hog.
160 154
161 Calculation is based on dev_weight (dev_weight 155 Calculation is based on dev_weight (dev_weight * dev_weight_tx_bias).
162 156
163 Default: 1 157 Default: 1
164 158
165 default_qdisc 159 default_qdisc
166 ------------- 160 -------------
167 161
168 The default queuing discipline to use for netw 162 The default queuing discipline to use for network devices. This allows
169 overriding the default of pfifo_fast with an a 163 overriding the default of pfifo_fast with an alternative. Since the default
170 queuing discipline is created without addition 164 queuing discipline is created without additional parameters so is best suited
171 to queuing disciplines that work well without 165 to queuing disciplines that work well without configuration like stochastic
172 fair queue (sfq), CoDel (codel) or fair queue 166 fair queue (sfq), CoDel (codel) or fair queue CoDel (fq_codel). Don't use
173 queuing disciplines like Hierarchical Token Bu 167 queuing disciplines like Hierarchical Token Bucket or Deficit Round Robin
174 which require setting up classes and bandwidth 168 which require setting up classes and bandwidths. Note that physical multiqueue
175 interfaces still use mq as root qdisc, which i 169 interfaces still use mq as root qdisc, which in turn uses this default for its
176 leaves. Virtual devices (like e.g. lo or veth) 170 leaves. Virtual devices (like e.g. lo or veth) ignore this setting and instead
177 default to noqueue. 171 default to noqueue.
178 172
179 Default: pfifo_fast 173 Default: pfifo_fast
180 174
181 busy_read 175 busy_read
182 --------- 176 ---------
183 177
184 Low latency busy poll timeout for socket reads 178 Low latency busy poll timeout for socket reads. (needs CONFIG_NET_RX_BUSY_POLL)
185 Approximate time in us to busy loop waiting fo 179 Approximate time in us to busy loop waiting for packets on the device queue.
186 This sets the default value of the SO_BUSY_POL 180 This sets the default value of the SO_BUSY_POLL socket option.
187 Can be set or overridden per socket by setting 181 Can be set or overridden per socket by setting socket option SO_BUSY_POLL,
188 which is the preferred method of enabling. If 182 which is the preferred method of enabling. If you need to enable the feature
189 globally via sysctl, a value of 50 is recommen 183 globally via sysctl, a value of 50 is recommended.
190 184
191 Will increase power usage. 185 Will increase power usage.
192 186
193 Default: 0 (off) 187 Default: 0 (off)
194 188
195 busy_poll 189 busy_poll
196 ---------------- 190 ----------------
197 Low latency busy poll timeout for poll and sel 191 Low latency busy poll timeout for poll and select. (needs CONFIG_NET_RX_BUSY_POLL)
198 Approximate time in us to busy loop waiting fo 192 Approximate time in us to busy loop waiting for events.
199 Recommended value depends on the number of soc 193 Recommended value depends on the number of sockets you poll on.
200 For several sockets 50, for several hundreds 1 194 For several sockets 50, for several hundreds 100.
201 For more than that you probably want to use ep 195 For more than that you probably want to use epoll.
202 Note that only sockets with SO_BUSY_POLL set w 196 Note that only sockets with SO_BUSY_POLL set will be busy polled,
203 so you want to either selectively set SO_BUSY_ 197 so you want to either selectively set SO_BUSY_POLL on those sockets or set
204 sysctl.net.busy_read globally. 198 sysctl.net.busy_read globally.
205 199
206 Will increase power usage. 200 Will increase power usage.
207 201
208 Default: 0 (off) 202 Default: 0 (off)
209 203
210 mem_pcpu_rsv <<
211 ------------ <<
212 <<
213 Per-cpu reserved forward alloc cache size in p <<
214 <<
215 rmem_default 204 rmem_default
216 ------------ 205 ------------
217 206
218 The default setting of the socket receive buff 207 The default setting of the socket receive buffer in bytes.
219 208
220 rmem_max 209 rmem_max
221 -------- 210 --------
222 211
223 The maximum receive socket buffer size in byte 212 The maximum receive socket buffer size in bytes.
224 213
225 rps_default_mask <<
226 ---------------- <<
227 <<
228 The default RPS CPU mask used on newly created <<
229 mask means RPS disabled by default. <<
230 <<
231 tstamp_allow_data 214 tstamp_allow_data
232 ----------------- 215 -----------------
233 Allow processes to receive tx timestamps loope 216 Allow processes to receive tx timestamps looped together with the original
234 packet contents. If disabled, transmit timesta 217 packet contents. If disabled, transmit timestamp requests from unprivileged
235 processes are dropped unless socket option SOF 218 processes are dropped unless socket option SOF_TIMESTAMPING_OPT_TSONLY is set.
236 219
237 Default: 1 (on) 220 Default: 1 (on)
238 221
239 222
240 wmem_default 223 wmem_default
241 ------------ 224 ------------
242 225
243 The default setting (in bytes) of the socket s 226 The default setting (in bytes) of the socket send buffer.
244 227
245 wmem_max 228 wmem_max
246 -------- 229 --------
247 230
248 The maximum send socket buffer size in bytes. 231 The maximum send socket buffer size in bytes.
249 232
250 message_burst and message_cost 233 message_burst and message_cost
251 ------------------------------ 234 ------------------------------
252 235
253 These parameters are used to limit the warnin 236 These parameters are used to limit the warning messages written to the kernel
254 log from the networking code. They enforc 237 log from the networking code. They enforce a rate limit to make a
255 denial-of-service attack impossible. A higher 238 denial-of-service attack impossible. A higher message_cost factor, results in
256 fewer messages that will be written. Message_b 239 fewer messages that will be written. Message_burst controls when messages will
257 be dropped. The default settings limit wa 240 be dropped. The default settings limit warning messages to one every five
258 seconds. 241 seconds.
259 242
260 warnings 243 warnings
261 -------- 244 --------
262 245
263 This sysctl is now unused. 246 This sysctl is now unused.
264 247
265 This was used to control console messages from 248 This was used to control console messages from the networking stack that
266 occur because of problems on the network like 249 occur because of problems on the network like duplicate address or bad
267 checksums. 250 checksums.
268 251
269 These messages are now emitted at KERN_DEBUG a 252 These messages are now emitted at KERN_DEBUG and can generally be enabled
270 and controlled by the dynamic_debug facility. 253 and controlled by the dynamic_debug facility.
271 254
272 netdev_budget 255 netdev_budget
273 ------------- 256 -------------
274 257
275 Maximum number of packets taken from all inter 258 Maximum number of packets taken from all interfaces in one polling cycle (NAPI
276 poll). In one polling cycle interfaces which a 259 poll). In one polling cycle interfaces which are registered to polling are
277 probed in a round-robin manner. Also, a pollin 260 probed in a round-robin manner. Also, a polling cycle may not exceed
278 netdev_budget_usecs microseconds, even if netd 261 netdev_budget_usecs microseconds, even if netdev_budget has not been
279 exhausted. 262 exhausted.
280 263
281 netdev_budget_usecs 264 netdev_budget_usecs
282 --------------------- 265 ---------------------
283 266
284 Maximum number of microseconds in one NAPI pol 267 Maximum number of microseconds in one NAPI polling cycle. Polling
285 will exit when either netdev_budget_usecs have 268 will exit when either netdev_budget_usecs have elapsed during the
286 poll cycle or the number of packets processed 269 poll cycle or the number of packets processed reaches netdev_budget.
287 270
288 netdev_max_backlog 271 netdev_max_backlog
289 ------------------ 272 ------------------
290 273
291 Maximum number of packets, queued on the INPUT 274 Maximum number of packets, queued on the INPUT side, when the interface
292 receives packets faster than kernel can proces 275 receives packets faster than kernel can process them.
293 276
294 netdev_rss_key 277 netdev_rss_key
295 -------------- 278 --------------
296 279
297 RSS (Receive Side Scaling) enabled drivers use 280 RSS (Receive Side Scaling) enabled drivers use a 40 bytes host key that is
298 randomly generated. 281 randomly generated.
299 Some user space might need to gather its conte 282 Some user space might need to gather its content even if drivers do not
300 provide ethtool -x support yet. 283 provide ethtool -x support yet.
301 284
302 :: 285 ::
303 286
304 myhost:~# cat /proc/sys/net/core/netdev_rss_ 287 myhost:~# cat /proc/sys/net/core/netdev_rss_key
305 84:50:f4:00:a8:15:d1:a7:e9:7f:1d:60:35:c7:47 288 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)
306 289
307 File contains nul bytes if no driver ever call 290 File contains nul bytes if no driver ever called netdev_rss_key_fill() function.
308 291
309 Note: 292 Note:
310 /proc/sys/net/core/netdev_rss_key contains 5 293 /proc/sys/net/core/netdev_rss_key contains 52 bytes of key,
311 but most drivers only use 40 bytes of it. 294 but most drivers only use 40 bytes of it.
312 295
313 :: 296 ::
314 297
315 myhost:~# ethtool -x eth0 298 myhost:~# ethtool -x eth0
316 RX flow hash indirection table for eth0 with 299 RX flow hash indirection table for eth0 with 8 RX ring(s):
317 0: 0 1 2 3 4 5 300 0: 0 1 2 3 4 5 6 7
318 RSS hash key: 301 RSS hash key:
319 84:50:f4:00:a8:15:d1:a7:e9:7f:1d:60:35:c7:47 302 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
320 303
321 netdev_tstamp_prequeue 304 netdev_tstamp_prequeue
322 ---------------------- 305 ----------------------
323 306
324 If set to 0, RX packet timestamps can be sampl 307 If set to 0, RX packet timestamps can be sampled after RPS processing, when
325 the target CPU processes packets. It might giv 308 the target CPU processes packets. It might give some delay on timestamps, but
326 permit to distribute the load on several cpus. 309 permit to distribute the load on several cpus.
327 310
328 If set to 1 (default), timestamps are sampled 311 If set to 1 (default), timestamps are sampled as soon as possible, before
329 queueing. 312 queueing.
330 313
331 netdev_unregister_timeout_secs 314 netdev_unregister_timeout_secs
332 ------------------------------ 315 ------------------------------
333 316
334 Unregister network device timeout in seconds. 317 Unregister network device timeout in seconds.
335 This option controls the timeout (in seconds) 318 This option controls the timeout (in seconds) used to issue a warning while
336 waiting for a network device refcount to drop 319 waiting for a network device refcount to drop to 0 during device
337 unregistration. A lower value may be useful du 320 unregistration. A lower value may be useful during bisection to detect
338 a leaked reference faster. A larger value may 321 a leaked reference faster. A larger value may be useful to prevent false
339 warnings on slow/loaded systems. 322 warnings on slow/loaded systems.
340 Default value is 10, minimum 1, maximum 3600. 323 Default value is 10, minimum 1, maximum 3600.
341 324
342 skb_defer_max 325 skb_defer_max
343 ------------- 326 -------------
344 327
345 Max size (in skbs) of the per-cpu list of skbs 328 Max size (in skbs) of the per-cpu list of skbs being freed
346 by the cpu which allocated them. Used by TCP s 329 by the cpu which allocated them. Used by TCP stack so far.
347 330
348 Default: 64 331 Default: 64
349 332
350 optmem_max 333 optmem_max
351 ---------- 334 ----------
352 335
353 Maximum ancillary buffer size allowed per sock 336 Maximum ancillary buffer size allowed per socket. Ancillary data is a sequence
354 of struct cmsghdr structures with appended dat !! 337 of struct cmsghdr structures with appended data.
355 optmem_max as a limit for its internal structu <<
356 <<
357 Default : 128 KB <<
358 338
359 fb_tunnels_only_for_init_net 339 fb_tunnels_only_for_init_net
360 ---------------------------- 340 ----------------------------
361 341
362 Controls if fallback tunnels (like tunl0, gre0 342 Controls if fallback tunnels (like tunl0, gre0, gretap0, erspan0,
363 sit0, ip6tnl0, ip6gre0) are automatically crea 343 sit0, ip6tnl0, ip6gre0) are automatically created. There are 3 possibilities
364 (a) value = 0; respective fallback tunnels are 344 (a) value = 0; respective fallback tunnels are created when module is
365 loaded in every net namespaces (backward compa 345 loaded in every net namespaces (backward compatible behavior).
366 (b) value = 1; [kcmd value: initns] respective 346 (b) value = 1; [kcmd value: initns] respective fallback tunnels are
367 created only in init net namespace and every o 347 created only in init net namespace and every other net namespace will
368 not have them. 348 not have them.
369 (c) value = 2; [kcmd value: none] fallback tun 349 (c) value = 2; [kcmd value: none] fallback tunnels are not created
370 when a module is loaded in any of the net name 350 when a module is loaded in any of the net namespace. Setting value to
371 "2" is pointless after boot if these modules a 351 "2" is pointless after boot if these modules are built-in, so there is
372 a kernel command-line option that can change t 352 a kernel command-line option that can change this default. Please refer to
373 Documentation/admin-guide/kernel-parameters.tx 353 Documentation/admin-guide/kernel-parameters.txt for additional details.
374 354
375 Not creating fallback tunnels gives control to 355 Not creating fallback tunnels gives control to userspace to create
376 whatever is needed only and avoid creating dev 356 whatever is needed only and avoid creating devices which are redundant.
377 357
378 Default : 0 (for compatibility reasons) 358 Default : 0 (for compatibility reasons)
379 359
380 devconf_inherit_init_net 360 devconf_inherit_init_net
381 ------------------------ 361 ------------------------
382 362
383 Controls if a new network namespace should inh 363 Controls if a new network namespace should inherit all current
384 settings under /proc/sys/net/{ipv4,ipv6}/conf/ 364 settings under /proc/sys/net/{ipv4,ipv6}/conf/{all,default}/. By
385 default, we keep the current behavior: for IPv 365 default, we keep the current behavior: for IPv4 we inherit all current
386 settings from init_net and for IPv6 we reset a 366 settings from init_net and for IPv6 we reset all settings to default.
387 367
388 If set to 1, both IPv4 and IPv6 settings are f 368 If set to 1, both IPv4 and IPv6 settings are forced to inherit from
389 current ones in init_net. If set to 2, both IP 369 current ones in init_net. If set to 2, both IPv4 and IPv6 settings are
390 forced to reset to their default values. If se 370 forced to reset to their default values. If set to 3, both IPv4 and IPv6
391 settings are forced to inherit from current on 371 settings are forced to inherit from current ones in the netns where this
392 new netns has been created. 372 new netns has been created.
393 373
394 Default : 0 (for compatibility reasons) 374 Default : 0 (for compatibility reasons)
395 375
396 txrehash 376 txrehash
397 -------- 377 --------
398 378
399 Controls default hash rethink behaviour on soc !! 379 Controls default hash rethink behaviour on listening socket when SO_TXREHASH
400 to SOCK_TXREHASH_DEFAULT (i. e. not overridden !! 380 option is set to SOCK_TXREHASH_DEFAULT (i. e. not overridden by setsockopt).
401 381
402 If set to 1 (default), hash rethink is perform 382 If set to 1 (default), hash rethink is performed on listening socket.
403 If set to 0, hash rethink is not performed. 383 If set to 0, hash rethink is not performed.
404 384
405 gro_normal_batch 385 gro_normal_batch
406 ---------------- 386 ----------------
407 387
408 Maximum number of the segments to batch up on 388 Maximum number of the segments to batch up on output of GRO. When a packet
409 exits GRO, either as a coalesced superframe or 389 exits GRO, either as a coalesced superframe or as an original packet which
410 GRO has decided not to coalesce, it is placed 390 GRO has decided not to coalesce, it is placed on a per-NAPI list. This
411 list is then passed to the stack when the numb 391 list is then passed to the stack when the number of segments reaches the
412 gro_normal_batch limit. 392 gro_normal_batch limit.
413 393
414 high_order_alloc_disable 394 high_order_alloc_disable
415 ------------------------ 395 ------------------------
416 396
417 By default the allocator for page frags tries 397 By default the allocator for page frags tries to use high order pages (order-3
418 on x86). While the default behavior gives good 398 on x86). While the default behavior gives good results in most cases, some users
419 might have hit a contention in page allocation 399 might have hit a contention in page allocations/freeing. This was especially
420 true on older kernels (< 5.14) when high-order 400 true on older kernels (< 5.14) when high-order pages were not stored on per-cpu
421 lists. This allows to opt-in for order-0 alloc 401 lists. This allows to opt-in for order-0 allocation instead but is now mostly of
422 historical importance. 402 historical importance.
423 403
424 Default: 0 404 Default: 0
425 405
426 2. /proc/sys/net/unix - Parameters for Unix do 406 2. /proc/sys/net/unix - Parameters for Unix domain sockets
427 ---------------------------------------------- 407 ----------------------------------------------------------
428 408
429 There is only one file in this directory. 409 There is only one file in this directory.
430 unix_dgram_qlen limits the max number of datag 410 unix_dgram_qlen limits the max number of datagrams queued in Unix domain
431 socket's buffer. It will not take effect unles 411 socket's buffer. It will not take effect unless PF_UNIX flag is specified.
432 412
433 413
434 3. /proc/sys/net/ipv4 - IPV4 settings 414 3. /proc/sys/net/ipv4 - IPV4 settings
435 ------------------------------------- 415 -------------------------------------
436 Please see: Documentation/networking/ip-sysctl 416 Please see: Documentation/networking/ip-sysctl.rst and
437 Documentation/admin-guide/sysctl/net.rst for d 417 Documentation/admin-guide/sysctl/net.rst for descriptions of these entries.
438 418
439 419
440 4. Appletalk 420 4. Appletalk
441 ------------ 421 ------------
442 422
443 The /proc/sys/net/appletalk directory holds 423 The /proc/sys/net/appletalk directory holds the Appletalk configuration data
444 when Appletalk is loaded. The configurable par 424 when Appletalk is loaded. The configurable parameters are:
445 425
446 aarp-expiry-time 426 aarp-expiry-time
447 ---------------- 427 ----------------
448 428
449 The amount of time we keep an ARP entry bef 429 The amount of time we keep an ARP entry before expiring it. Used to age out
450 old hosts. 430 old hosts.
451 431
452 aarp-resolve-time 432 aarp-resolve-time
453 ----------------- 433 -----------------
454 434
455 The amount of time we will spend trying to res 435 The amount of time we will spend trying to resolve an Appletalk address.
456 436
457 aarp-retransmit-limit 437 aarp-retransmit-limit
458 --------------------- 438 ---------------------
459 439
460 The number of times we will retransmit a query 440 The number of times we will retransmit a query before giving up.
461 441
462 aarp-tick-time 442 aarp-tick-time
463 -------------- 443 --------------
464 444
465 Controls the rate at which expires are checked 445 Controls the rate at which expires are checked.
466 446
467 The directory /proc/net/appletalk holds the 447 The directory /proc/net/appletalk holds the list of active Appletalk sockets
468 on a machine. 448 on a machine.
469 449
470 The fields indicate the DDP type, the local 450 The fields indicate the DDP type, the local address (in network:node format)
471 the remote address, the size of the transmi 451 the remote address, the size of the transmit pending queue, the size of the
472 received queue (bytes waiting for application 452 received queue (bytes waiting for applications to read) the state and the uid
473 owning the socket. 453 owning the socket.
474 454
475 /proc/net/atalk_iface lists all the interfa 455 /proc/net/atalk_iface lists all the interfaces configured for appletalk.It
476 shows the name of the interface, its Appleta 456 shows the name of the interface, its Appletalk address, the network range on
477 that address (or network number for phase 1 457 that address (or network number for phase 1 networks), and the status of the
478 interface. 458 interface.
479 459
480 /proc/net/atalk_route lists each known netw 460 /proc/net/atalk_route lists each known network route. It lists the target
481 (network) that the route leads to, the router 461 (network) that the route leads to, the router (may be directly connected), the
482 route flags, and the device the route is using 462 route flags, and the device the route is using.
483 463
484 5. TIPC 464 5. TIPC
485 ------- 465 -------
486 466
487 tipc_rmem 467 tipc_rmem
488 --------- 468 ---------
489 469
490 The TIPC protocol now has a tunable for the re 470 The TIPC protocol now has a tunable for the receive memory, similar to the
491 tcp_rmem - i.e. a vector of 3 INTEGERs: (min, 471 tcp_rmem - i.e. a vector of 3 INTEGERs: (min, default, max)
492 472
493 :: 473 ::
494 474
495 # cat /proc/sys/net/tipc/tipc_rmem 475 # cat /proc/sys/net/tipc/tipc_rmem
496 4252725 34021800 68043600 476 4252725 34021800 68043600
497 # 477 #
498 478
499 The max value is set to CONN_OVERLOAD_LIMIT, a 479 The max value is set to CONN_OVERLOAD_LIMIT, and the default and min values
500 are scaled (shifted) versions of that same val 480 are scaled (shifted) versions of that same value. Note that the min value
501 is not at this point in time used in any meani 481 is not at this point in time used in any meaningful way, but the triplet is
502 preserved in order to be consistent with thing 482 preserved in order to be consistent with things like tcp_rmem.
503 483
504 named_timeout 484 named_timeout
505 ------------- 485 -------------
506 486
507 TIPC name table updates are distributed asynch 487 TIPC name table updates are distributed asynchronously in a cluster, without
508 any form of transaction handling. This means t 488 any form of transaction handling. This means that different race scenarios are
509 possible. One such is that a name withdrawal s 489 possible. One such is that a name withdrawal sent out by one node and received
510 by another node may arrive after a second, ove 490 by another node may arrive after a second, overlapping name publication already
511 has been accepted from a third node, although 491 has been accepted from a third node, although the conflicting updates
512 originally may have been issued in the correct 492 originally may have been issued in the correct sequential order.
513 If named_timeout is nonzero, failed topology u 493 If named_timeout is nonzero, failed topology updates will be placed on a defer
514 queue until another event arrives that clears 494 queue until another event arrives that clears the error, or until the timeout
515 expires. Value is in milliseconds. 495 expires. Value is in milliseconds.
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.