Date: Thu, 30 Nov 2000 19:14:14 +0100
From: Andi Kleen <ak@suse.de>
> The problem is that if data happens to be written via method (2),
> then the PUSH flag is never set on any packets generated. This is
> a bug, surely?
I just tried it on 2.2.17 and 2.4.0test11 and it sets PUSH for
writev() for both cases just fine. Maybe you could supply a test
program and tcpdump logs for what you think is wrong ?
One thing which could affect the behavior is if the Zeus
folks are futzing around with the TCP_CORK socket option.
Ben, are you guys playing with it?
Finally, are you doing these writes from a userspace program
or directly inside of a kernel module?
Later,
David S. Miller
davem@redhat.com
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Thu Nov 30 2000 - 21:00:25 EST