tcp: add a scheduling point in established_get_first()

Browse source

Kubernetes[1] is going to stick with /proc/net/tcp for a while.

This commit reduces the scheduling latency introduced by
established_get_first(), similar to commit acffb584cd ("net: diag:
add a scheduling point in inet_diag_dump_icsk()").

In our environment, the scheduling latency affects the performance of
latency-sensitive services like Redis.

Changes in V2 :
 - call cond_resched() before checking if a bucket is empty as
   suggested by Eric Dumazet
 - removed the delay of synchronize_net() from the commit message

[1] https://github.com/google/cadvisor/blob/v0.47.2/container/libcontainer/handler.go#L130

Signed-off-by: Jian Wen <wenjian1@xiaomi.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Link: https://lore.kernel.org/r/20230711032405.3253025-1-wenjian1@xiaomi.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

...

This commit is contained in:

Jian Wen 2023-07-11 11:24:05 +08:00 • committed by Jakub Kicinski

parent e0f0a5db5f

commit 9f4a7c9302

1 changed files with 3 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

3

net/ipv4/tcp_ipv4.c

View file