tcp: increase tcp_rmem[2] to 32 MB

Last change to tcp_rmem[2] happened in 2012, in commit b49960a05e
("tcp: change tcp_adv_win_scale and tcp_rmem[2]")

TCP performance on WAN is mostly limited by tcp_rmem[2] for receivers.

After this series improvements, it is time to increase the default.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250513193919.1089692-12-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Eric Dumazet
2025-05-13 19:39:19 +00:00
committed by Jakub Kicinski
parent c4221a8cc3
commit 572be9bf9d
2 changed files with 2 additions and 2 deletions

View File

@@ -735,7 +735,7 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max
net.core.rmem_max. Calling setsockopt() with SO_RCVBUF disables net.core.rmem_max. Calling setsockopt() with SO_RCVBUF disables
automatic tuning of that socket's receive buffer size, in which automatic tuning of that socket's receive buffer size, in which
case this value is ignored. case this value is ignored.
Default: between 131072 and 6MB, depending on RAM size. Default: between 131072 and 32MB, depending on RAM size.
tcp_sack - BOOLEAN tcp_sack - BOOLEAN
Enable select acknowledgments (SACKS). Enable select acknowledgments (SACKS).

View File

@@ -5231,7 +5231,7 @@ void __init tcp_init(void)
/* Set per-socket limits to no more than 1/128 the pressure threshold */ /* Set per-socket limits to no more than 1/128 the pressure threshold */
limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7); limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7);
max_wshare = min(4UL*1024*1024, limit); max_wshare = min(4UL*1024*1024, limit);
max_rshare = min(6UL*1024*1024, limit); max_rshare = min(32UL*1024*1024, limit);
init_net.ipv4.sysctl_tcp_wmem[0] = PAGE_SIZE; init_net.ipv4.sysctl_tcp_wmem[0] = PAGE_SIZE;
init_net.ipv4.sysctl_tcp_wmem[1] = 16*1024; init_net.ipv4.sysctl_tcp_wmem[1] = 16*1024;