Re: [patch] TCP/IP delacks disabled with MPI

Andrea Arcangeli (andrea@suse.de)
Fri, 21 May 1999 19:56:29 +0200 (CEST)


On Fri, 21 May 1999, Josip Loncaric wrote:

>Slow start should grow cwnd 1->2->4->8->... even with smallest packets:
>
>cwnd=1 pkt->
> <- ack 1 pkt
>cwnd=2 pkt->
> pkt->
> <- ack 2 pkts
>cwnd=4 pkt->
> pkt->
> pkt->
> pkt->
> <- ack 4 pkts
>cwnd=8 ...

If you are sure the above is the right behaviour I can produce a patch
that will achieve the above.

>as well. By the way, at least one ACK must be returned for every 2*MSS
>bytes received, so the above reasoning applies to small packets only.

Are you sure that we can avoid sending an ack even if we have more than
one not acked frame in the receive queue?

Where can I found a recent TCP spec, maybe I am reading obsoleted specs.

>Some time constants in Linux TCP are way too long. Linux TCP estimates
>of RTO are kept 200ms or longer, although for us 20ms is more

Agreed completly.

>TCP socket buffer size is only 32kB. We'd prefer 2ms min. RTO in some
>cases.

The minimum resolution is 10msec due the 100HZ timer.

>Delayed ACK timeouts of 500ms are standard but about 1000 times longer
>than what we'd like. The 1 second retransmit timer which applies when

500msec in the _worst_ case: it's an high bound not a low bound. Right now
the low bound is the RTO that is lowbound to 200msec itself. If you
decrease the lowbound of the rto then also the ato will decrease.

Andrea Arcangeli

-
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/