Thread (8 messages) 8 messages, 3 authors, 2017-04-03

Re: [PATCH net-next] sock: avoid dirtying sk_stamp, if possible

From: David Miller <davem@davemloft.net>
Date: 2017-03-31 03:29:28

From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 30 Mar 2017 14:03:06 +0200
sock_recv_ts_and_drops() unconditionally set sk->sk_stamp for
every packet, even if the SOCK_TIMESTAMP flag is not set in the
related socket.
If selinux is enabled, this cause a cache miss for every packet
since sk->sk_stamp and sk->sk_security share the same cacheline.
With this change sk_stamp is set only if the SOCK_TIMESTAMP
flag is set, and is cleared for the first packet, so that the user
perceived behavior is unchanged.

This gives up to 5% speed-up under udp-flood with small packets.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Applied, thanks.
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help