Messages in this thread | | | Date | Wed, 18 Nov 1998 00:37:03 -0800 | From | "David S. Miller" <> | Subject | Re: [patch] delayed acks decrease performances in congestioned networks |
| |
From: Andi Kleen <ak@muc.de> Date: 17 Nov 1998 16:23:52 +0100
In article <E0zfUWw-0007KA-00@danube.inka.de>, olaf@bigred.inka.de (Olaf Titz) writes: >> For extremely shitty networks (I mean here, every other packet always >> dropped etc.), delayed acks are worse than non-delayed ones. But as >> you mention it contributes to congestion and degrades performance for >> people with at least half-way decent connectivity.
> This clearly marks it as a sysctl candidate.
It is already settable:
setsockopt(sk, SOL_TCP, TCP_NODELAY, ((int *){1}), sizeof int);
Last time I checked that controls the Nagle algorithm, it doesn't control delayed ACKs at all.
Later, David S. Miller davem@dm.cobaltmicro.com
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |