Commit a6d4f258 authored by Eric Dumazet's avatar Eric Dumazet Committed by Jakub Kicinski
Browse files

net: set net.core.rmem_max and net.core.wmem_max to 4 MB 



SO_RCVBUF and SO_SNDBUF have limited range today, unless
distros or system admins change rmem_max and wmem_max.

Even iproute2 uses 1 MB SO_RCVBUF which is capped by
the kernel.

Decouple [rw]mem_max and [rw]mem_default and increase
[rw]mem_max to 4 MB.

Before:

$ sysctl net.core.rmem_default net.core.rmem_max net.core.wmem_default net.core.wmem_max
net.core.rmem_default = 212992
net.core.rmem_max = 212992
net.core.wmem_default = 212992
net.core.wmem_max = 212992

After:

$ sysctl net.core.rmem_default net.core.rmem_max net.core.wmem_default net.core.wmem_max
net.core.rmem_default = 212992
net.core.rmem_max = 4194304
net.core.wmem_default = 212992
net.core.wmem_max = 4194304

Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Reviewed-by: default avatarNeal Cardwell <ncardwell@google.com>
Link: https://patch.msgid.link/20250819174030.1986278-1-edumazet@google.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 2a2e6e53

Documentation/admin-guide/sysctl/net.rst

+4 −0
Original line number Diff line number Diff line
@@ -222,6 +222,8 @@ rmem_max 


The maximum receive socket buffer size in bytes.



Default: 4194304



rps_default_mask

----------------
@@ -247,6 +249,8 @@ wmem_max 


The maximum send socket buffer size in bytes.



Default: 4194304



message_burst and message_cost

------------------------------

Documentation/networking/ip-sysctl.rst

+3 −3
Original line number Diff line number Diff line
@@ -209,7 +209,7 @@ neigh/default/unres_qlen_bytes - INTEGER 


	Setting negative value is meaningless and will return error.



	Default: SK_WMEM_MAX, (same as net.core.wmem_default).

	Default: SK_WMEM_DEFAULT, (same as net.core.wmem_default).



		Exact value depends on architecture and kernel options,

		but should be enough to allow queuing 256 packets
@@ -805,8 +805,8 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max 
	This value results in initial window of 65535.



	max: maximal size of receive buffer allowed for automatically

	selected receiver buffers for TCP socket. This value does not override

	net.core.rmem_max.  Calling setsockopt() with SO_RCVBUF disables

	selected receiver buffers for TCP socket.

	Calling setsockopt() with SO_RCVBUF disables

	automatic tuning of that socket's receive buffer size, in which

	case this value is ignored.

	Default: between 131072 and 32MB, depending on RAM size.

include/net/sock.h

+2 −2
Original line number Diff line number Diff line
@@ -2970,8 +2970,8 @@ void sk_get_meminfo(const struct sock *sk, u32 *meminfo); 
 */

#define _SK_MEM_PACKETS		256

#define _SK_MEM_OVERHEAD	SKB_TRUESIZE(256)

#define SK_WMEM_MAX		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)

#define SK_RMEM_MAX		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)

#define SK_WMEM_DEFAULT		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)

#define SK_RMEM_DEFAULT		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)



extern __u32 sysctl_wmem_max;

extern __u32 sysctl_rmem_max;

net/core/sock.c

+4 −4
Original line number Diff line number Diff line
@@ -281,12 +281,12 @@ static struct lock_class_key af_elock_keys[AF_MAX]; 
static struct lock_class_key af_kern_callback_keys[AF_MAX];



/* Run time adjustable parameters. */

__u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX;

__u32 sysctl_wmem_max __read_mostly = 4 << 20;

EXPORT_SYMBOL(sysctl_wmem_max);

__u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX;

__u32 sysctl_rmem_max __read_mostly = 4 << 20;

EXPORT_SYMBOL(sysctl_rmem_max);

__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;

__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;

__u32 sysctl_wmem_default __read_mostly = SK_WMEM_DEFAULT;

__u32 sysctl_rmem_default __read_mostly = SK_RMEM_DEFAULT;



DEFINE_STATIC_KEY_FALSE(memalloc_socks_key);

EXPORT_SYMBOL_GPL(memalloc_socks_key);

net/ipv4/arp.c

+1 −1
Original line number Diff line number Diff line
@@ -170,7 +170,7 @@ struct neigh_table arp_tbl = { 
			[NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ,

			[NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ,

			[NEIGH_VAR_GC_STALETIME] = 60 * HZ,

			[NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX,

			[NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_DEFAULT,

			[NEIGH_VAR_PROXY_QLEN] = 64,

			[NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ,

			[NEIGH_VAR_PROXY_DELAY]	= (8 * HZ) / 10,