1================================ 2Documentation for /proc/sys/net/ 3================================ 4 5Copyright 6 7Copyright (c) 1999 8 9 - Terrehon Bowden <terrehon@pacbell.net> 10 - Bodo Bauer <bb@ricochet.net> 11 12Copyright (c) 2000 13 14 - Jorge Nerin <comandante@zaralinux.com> 15 16Copyright (c) 2009 17 18 - Shen Feng <shen@cn.fujitsu.com> 19 20For general info and legal blurb, please look in index.rst. 21 22------------------------------------------------------------------------------ 23 24This file contains the documentation for the sysctl files in 25/proc/sys/net 26 27The interface to the networking parts of the kernel is located in 28/proc/sys/net. The following table shows all possible subdirectories. You may 29see only some of them, depending on your kernel's configuration. 30 31 32Table : Subdirectories in /proc/sys/net 33 34 ========= =================== = ========== =================== 35 Directory Content Directory Content 36 ========= =================== = ========== =================== 37 802 E802 protocol mptcp Multipath TCP 38 appletalk Appletalk protocol netfilter Network Filter 39 ax25 AX25 netrom NET/ROM 40 bridge Bridging rose X.25 PLP layer 41 core General parameter tipc TIPC 42 ethernet Ethernet protocol unix Unix domain sockets 43 ipv4 IP version 4 x25 X.25 protocol 44 ipv6 IP version 6 45 ========= =================== = ========== =================== 46 471. /proc/sys/net/core - Network core options 48============================================ 49 50bpf_jit_enable 51-------------- 52 53This enables the BPF Just in Time (JIT) compiler. BPF is a flexible 54and efficient infrastructure allowing to execute bytecode at various 55hook points. It is used in a number of Linux kernel subsystems such 56as networking (e.g. XDP, tc), tracing (e.g. kprobes, uprobes, tracepoints) 57and security (e.g. seccomp). LLVM has a BPF back end that can compile 58restricted C into a sequence of BPF instructions. After program load 59through bpf(2) and passing a verifier in the kernel, a JIT will then 60translate these BPF proglets into native CPU instructions. There are 61two flavors of JITs, the newer eBPF JIT currently supported on: 62 63 - x86_64 64 - x86_32 65 - arm64 66 - arm32 67 - ppc64 68 - ppc32 69 - sparc64 70 - mips64 71 - s390x 72 - riscv64 73 - riscv32 74 - loongarch64 75 - arc 76 77And the older cBPF JIT supported on the following archs: 78 79 - mips 80 - sparc 81 82eBPF JITs are a superset of cBPF JITs, meaning the kernel will 83migrate cBPF instructions into eBPF instructions and then JIT 84compile them transparently. Older cBPF JITs can only translate 85tcpdump filters, seccomp rules, etc, but not mentioned eBPF 86programs loaded through bpf(2). 87 88Values: 89 90 - 0 - disable the JIT (default value) 91 - 1 - enable the JIT 92 - 2 - enable the JIT and ask the compiler to emit traces on kernel log. 93 94bpf_jit_harden 95-------------- 96 97This enables hardening for the BPF JIT compiler. Supported are eBPF 98JIT backends. Enabling hardening trades off performance, but can 99mitigate JIT spraying. 100 101Values: 102 103 - 0 - disable JIT hardening (default value) 104 - 1 - enable JIT hardening for unprivileged users only 105 - 2 - enable JIT hardening for all users 106 107where "privileged user" in this context means a process having 108CAP_BPF or CAP_SYS_ADMIN in the root user name space. 109 110bpf_jit_kallsyms 111---------------- 112 113When BPF JIT compiler is enabled, then compiled images are unknown 114addresses to the kernel, meaning they neither show up in traces nor 115in /proc/kallsyms. This enables export of these addresses, which can 116be used for debugging/tracing. If bpf_jit_harden is enabled, this 117feature is disabled. 118 119Values : 120 121 - 0 - disable JIT kallsyms export (default value) 122 - 1 - enable JIT kallsyms export for privileged users only 123 124bpf_jit_limit 125------------- 126 127This enforces a global limit for memory allocations to the BPF JIT 128compiler in order to reject unprivileged JIT requests once it has 129been surpassed. bpf_jit_limit contains the value of the global limit 130in bytes. 131 132dev_weight 133---------- 134 135The maximum number of packets that kernel can handle on a NAPI interrupt, 136it's a Per-CPU variable. For drivers that support LRO or GRO_HW, a hardware 137aggregated packet is counted as one packet in this context. 138 139Default: 64 140 141dev_weight_rx_bias 142------------------ 143 144RPS (e.g. RFS, aRFS) processing is competing with the registered NAPI poll function 145of the driver for the per softirq cycle netdev_budget. This parameter influences 146the proportion of the configured netdev_budget that is spent on RPS based packet 147processing during RX softirq cycles. It is further meant for making current 148dev_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 per CPU basis. Determination is based 150on dev_weight and is calculated multiplicative (dev_weight * dev_weight_rx_bias). 151 152Default: 1 153 154dev_weight_tx_bias 155------------------ 156 157Scales the maximum number of packets that can be processed during a TX softirq cycle. 158Effective on a per CPU basis. Allows scaling of current dev_weight for asymmetric 159net stack processing needs. Be careful to avoid making TX softirq processing a CPU hog. 160 161Calculation is based on dev_weight (dev_weight * dev_weight_tx_bias). 162 163Default: 1 164 165default_qdisc 166------------- 167 168The default queuing discipline to use for network devices. This allows 169overriding the default of pfifo_fast with an alternative. Since the default 170queuing discipline is created without additional parameters so is best suited 171to queuing disciplines that work well without configuration like stochastic 172fair queue (sfq), CoDel (codel) or fair queue CoDel (fq_codel). Don't use 173queuing disciplines like Hierarchical Token Bucket or Deficit Round Robin 174which require setting up classes and bandwidths. Note that physical multiqueue 175interfaces still use mq as root qdisc, which in turn uses this default for its 176leaves. Virtual devices (like e.g. lo or veth) ignore this setting and instead 177default to noqueue. 178 179Default: pfifo_fast 180 181busy_read 182--------- 183 184Low latency busy poll timeout for socket reads. (needs CONFIG_NET_RX_BUSY_POLL) 185Approximate time in us to busy loop waiting for packets on the device queue. 186This sets the default value of the SO_BUSY_POLL socket option. 187Can be set or overridden per socket by setting socket option SO_BUSY_POLL, 188which is the preferred method of enabling. If you need to enable the feature 189globally via sysctl, a value of 50 is recommended. 190 191Will increase power usage. 192 193Default: 0 (off) 194 195busy_poll 196---------------- 197Low latency busy poll timeout for poll and select. (needs CONFIG_NET_RX_BUSY_POLL) 198Approximate time in us to busy loop waiting for events. 199Recommended value depends on the number of sockets you poll on. 200For several sockets 50, for several hundreds 100. 201For more than that you probably want to use epoll. 202Note that only sockets with SO_BUSY_POLL set will be busy polled, 203so you want to either selectively set SO_BUSY_POLL on those sockets or set 204sysctl.net.busy_read globally. 205 206Will increase power usage. 207 208Default: 0 (off) 209 210mem_pcpu_rsv 211------------ 212 213Per-cpu reserved forward alloc cache size in page units. Default 1MB per CPU. 214 215rmem_default 216------------ 217 218The default setting of the socket receive buffer in bytes. 219 220rmem_max 221-------- 222 223The maximum receive socket buffer size in bytes. 224 225Default: 4194304 226 227rps_default_mask 228---------------- 229 230The default RPS CPU mask used on newly created network devices. An empty 231mask means RPS disabled by default. 232 233tstamp_allow_data 234----------------- 235Allow processes to receive tx timestamps looped together with the original 236packet contents. If disabled, transmit timestamp requests from unprivileged 237processes are dropped unless socket option SOF_TIMESTAMPING_OPT_TSONLY is set. 238 239Default: 1 (on) 240 241 242wmem_default 243------------ 244 245The default setting (in bytes) of the socket send buffer. 246 247wmem_max 248-------- 249 250The maximum send socket buffer size in bytes. 251 252Default: 4194304 253 254message_burst and message_cost 255------------------------------ 256 257These parameters are used to limit the warning messages written to the kernel 258log from the networking code. They enforce a rate limit to make a 259denial-of-service attack impossible. A higher message_cost factor, results in 260fewer messages that will be written. Message_burst controls when messages will 261be dropped. The default settings limit warning messages to one every five 262seconds. 263 264warnings 265-------- 266 267This sysctl is now unused. 268 269This was used to control console messages from the networking stack that 270occur because of problems on the network like duplicate address or bad 271checksums. 272 273These messages are now emitted at KERN_DEBUG and can generally be enabled 274and controlled by the dynamic_debug facility. 275 276netdev_budget 277------------- 278 279Maximum number of packets taken from all interfaces in one polling cycle (NAPI 280poll). In one polling cycle interfaces which are registered to polling are 281probed in a round-robin manner. Also, a polling cycle may not exceed 282netdev_budget_usecs microseconds, even if netdev_budget has not been 283exhausted. 284 285netdev_budget_usecs 286--------------------- 287 288Maximum number of microseconds in one NAPI polling cycle. Polling 289will exit when either netdev_budget_usecs have elapsed during the 290poll cycle or the number of packets processed reaches netdev_budget. 291 292netdev_max_backlog 293------------------ 294 295Maximum number of packets, queued on the INPUT side, when the interface 296receives packets faster than kernel can process them. 297 298netdev_rss_key 299-------------- 300 301RSS (Receive Side Scaling) enabled drivers use a 40 bytes host key that is 302randomly generated. 303Some user space might need to gather its content even if drivers do not 304provide ethtool -x support yet. 305 306:: 307 308 myhost:~# cat /proc/sys/net/core/netdev_rss_key 309 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) 310 311File contains nul bytes if no driver ever called netdev_rss_key_fill() function. 312 313Note: 314 /proc/sys/net/core/netdev_rss_key contains 52 bytes of key, 315 but most drivers only use 40 bytes of it. 316 317:: 318 319 myhost:~# ethtool -x eth0 320 RX flow hash indirection table for eth0 with 8 RX ring(s): 321 0: 0 1 2 3 4 5 6 7 322 RSS hash key: 323 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:f1:42:89 324 325netdev_tstamp_prequeue 326---------------------- 327 328If set to 0, RX packet timestamps can be sampled after RPS processing, when 329the target CPU processes packets. It might give some delay on timestamps, but 330permit to distribute the load on several cpus. 331 332If set to 1 (default), timestamps are sampled as soon as possible, before 333queueing. 334 335netdev_unregister_timeout_secs 336------------------------------ 337 338Unregister network device timeout in seconds. 339This option controls the timeout (in seconds) used to issue a warning while 340waiting for a network device refcount to drop to 0 during device 341unregistration. A lower value may be useful during bisection to detect 342a leaked reference faster. A larger value may be useful to prevent false 343warnings on slow/loaded systems. 344Default value is 10, minimum 1, maximum 3600. 345 346skb_defer_max 347------------- 348 349Max size (in skbs) of the per-cpu list of skbs being freed 350by the cpu which allocated them. Used by TCP stack so far. 351 352Default: 64 353 354optmem_max 355---------- 356 357Maximum ancillary buffer size allowed per socket. Ancillary data is a sequence 358of struct cmsghdr structures with appended data. TCP tx zerocopy also uses 359optmem_max as a limit for its internal structures. 360 361Default : 128 KB 362 363fb_tunnels_only_for_init_net 364---------------------------- 365 366Controls if fallback tunnels (like tunl0, gre0, gretap0, erspan0, 367sit0, ip6tnl0, ip6gre0) are automatically created. There are 3 possibilities 368(a) value = 0; respective fallback tunnels are created when module is 369loaded in every net namespaces (backward compatible behavior). 370(b) value = 1; [kcmd value: initns] respective fallback tunnels are 371created only in init net namespace and every other net namespace will 372not have them. 373(c) value = 2; [kcmd value: none] fallback tunnels are not created 374when a module is loaded in any of the net namespace. Setting value to 375"2" is pointless after boot if these modules are built-in, so there is 376a kernel command-line option that can change this default. Please refer to 377Documentation/admin-guide/kernel-parameters.txt for additional details. 378 379Not creating fallback tunnels gives control to userspace to create 380whatever is needed only and avoid creating devices which are redundant. 381 382Default : 0 (for compatibility reasons) 383 384devconf_inherit_init_net 385------------------------ 386 387Controls if a new network namespace should inherit all current 388settings under /proc/sys/net/{ipv4,ipv6}/conf/{all,default}/. By 389default, we keep the current behavior: for IPv4 we inherit all current 390settings from init_net and for IPv6 we reset all settings to default. 391 392If set to 1, both IPv4 and IPv6 settings are forced to inherit from 393current ones in init_net. If set to 2, both IPv4 and IPv6 settings are 394forced to reset to their default values. If set to 3, both IPv4 and IPv6 395settings are forced to inherit from current ones in the netns where this 396new netns has been created. 397 398Default : 0 (for compatibility reasons) 399 400txrehash 401-------- 402 403Controls default hash rethink behaviour on socket when SO_TXREHASH option is set 404to SOCK_TXREHASH_DEFAULT (i. e. not overridden by setsockopt). 405 406If set to 1 (default), hash rethink is performed on listening socket. 407If set to 0, hash rethink is not performed. 408 409gro_normal_batch 410---------------- 411 412Maximum number of the segments to batch up on output of GRO. When a packet 413exits GRO, either as a coalesced superframe or as an original packet which 414GRO has decided not to coalesce, it is placed on a per-NAPI list. This 415list is then passed to the stack when the number of segments reaches the 416gro_normal_batch limit. 417 418high_order_alloc_disable 419------------------------ 420 421By default the allocator for page frags tries to use high order pages (order-3 422on x86). While the default behavior gives good results in most cases, some users 423might have hit a contention in page allocations/freeing. This was especially 424true on older kernels (< 5.14) when high-order pages were not stored on per-cpu 425lists. This allows to opt-in for order-0 allocation instead but is now mostly of 426historical importance. 427 428Default: 0 429 4302. /proc/sys/net/unix - Parameters for Unix domain sockets 431---------------------------------------------------------- 432 433There is only one file in this directory. 434unix_dgram_qlen limits the max number of datagrams queued in Unix domain 435socket's buffer. It will not take effect unless PF_UNIX flag is specified. 436 437 4383. /proc/sys/net/ipv4 - IPV4 settings 439------------------------------------- 440Please see: Documentation/networking/ip-sysctl.rst and 441Documentation/admin-guide/sysctl/net.rst for descriptions of these entries. 442 443 4444. Appletalk 445------------ 446 447The /proc/sys/net/appletalk directory holds the Appletalk configuration data 448when Appletalk is loaded. The configurable parameters are: 449 450aarp-expiry-time 451---------------- 452 453The amount of time we keep an ARP entry before expiring it. Used to age out 454old hosts. 455 456aarp-resolve-time 457----------------- 458 459The amount of time we will spend trying to resolve an Appletalk address. 460 461aarp-retransmit-limit 462--------------------- 463 464The number of times we will retransmit a query before giving up. 465 466aarp-tick-time 467-------------- 468 469Controls the rate at which expires are checked. 470 471The directory /proc/net/appletalk holds the list of active Appletalk sockets 472on a machine. 473 474The fields indicate the DDP type, the local address (in network:node format) 475the remote address, the size of the transmit pending queue, the size of the 476received queue (bytes waiting for applications to read) the state and the uid 477owning the socket. 478 479/proc/net/atalk_iface lists all the interfaces configured for appletalk.It 480shows the name of the interface, its Appletalk address, the network range on 481that address (or network number for phase 1 networks), and the status of the 482interface. 483 484/proc/net/atalk_route lists each known network route. It lists the target 485(network) that the route leads to, the router (may be directly connected), the 486route flags, and the device the route is using. 487 4885. TIPC 489------- 490 491tipc_rmem 492--------- 493 494The TIPC protocol now has a tunable for the receive memory, similar to the 495tcp_rmem - i.e. a vector of 3 INTEGERs: (min, default, max) 496 497:: 498 499 # cat /proc/sys/net/tipc/tipc_rmem 500 4252725 34021800 68043600 501 # 502 503The max value is set to CONN_OVERLOAD_LIMIT, and the default and min values 504are scaled (shifted) versions of that same value. Note that the min value 505is not at this point in time used in any meaningful way, but the triplet is 506preserved in order to be consistent with things like tcp_rmem. 507 508named_timeout 509------------- 510 511TIPC name table updates are distributed asynchronously in a cluster, without 512any form of transaction handling. This means that different race scenarios are 513possible. One such is that a name withdrawal sent out by one node and received 514by another node may arrive after a second, overlapping name publication already 515has been accepted from a third node, although the conflicting updates 516originally may have been issued in the correct sequential order. 517If named_timeout is nonzero, failed topology updates will be placed on a defer 518queue until another event arrives that clears the error, or until the timeout 519expires. Value is in milliseconds. 520