]> err.no Git - linux-2.6/commit
[TCP]: congestion control API pass RTT in microseconds
authorStephen Hemminger <shemminger@linux-foundation.org>
Thu, 26 Jul 2007 06:49:34 +0000 (23:49 -0700)
committerDavid S. Miller <davem@sunset.davemloft.net>
Tue, 31 Jul 2007 09:27:57 +0000 (02:27 -0700)
commit30cfd0baf0a0c4329fff1ef4b622919297969ec8
tree945a72f636ced1b443d894495704237e4cb7816d
parent6a302358d87fedaf7bda12b8e909265ebf1ce674
[TCP]: congestion control API pass RTT in microseconds

This patch changes the API for the callback that is done after an ACK is
received. It solves a couple of issues:

  * Some congestion controls want higher resolution value of RTT
    (controlled by TCP_CONG_RTT_SAMPLE flag). These don't really want a ktime, but
    all compute a RTT in microseconds.

  * Other congestion control could use RTT at jiffies resolution.

To keep API consistent the units should be the same for both cases, just the
resolution should change.

Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
12 files changed:
include/net/tcp.h
net/ipv4/tcp_bic.c
net/ipv4/tcp_cubic.c
net/ipv4/tcp_htcp.c
net/ipv4/tcp_illinois.c
net/ipv4/tcp_input.c
net/ipv4/tcp_lp.c
net/ipv4/tcp_vegas.c
net/ipv4/tcp_vegas.h
net/ipv4/tcp_veno.c
net/ipv4/tcp_westwood.c
net/ipv4/tcp_yeah.c