On Thu, 25 Feb 1999, David Miller wrote:
> Date: Thu, 25 Feb 1999 16:24:40 -0800
> From: pw@dancer.ca.sandia.gov (Pete Wyckoff)
>
> 2.2dump.txt:
>
>I'm going to analyze this trace from the perspective of ACK'ing (at
>the receiver) and congestion avoidance (at the sender):
>
> 13.957811 client.1582 > server.3000: S 28534252:28534252(0) win 8192 <mss 1460> (DF) [tos 0x10]
> 13.957907 server.3000 > client.1582: S 1635428655:1635428655(0) ack 28534253 win 32120 <mss 1460> (DF)
> 13.958224 client.1582 > server.3000: . ack 1 win 8760 (DF) [tos 0x10]
>
>Normal startup, looks fine.
>
> 13.959084 client.1582 > server.3000: P 1:36(35) ack 1 win 8760 (DF) [tos 0x10]
>
>First data packet, congestion window should be exactly 1 on the NT box.
>
> 13.959154 server.3000 > client.1582: . ack 36 win 32120 (DF)
>
>Ack immediately first data packet, so the sender can begin to leave
>slow start (and thus increase his congestion window), his congestion
>window should be at 2 when he receives this ack (and thus be allowed
>to send two frames).
The congestion window of NT is still 1 because it sent out only 35 bytes
of data. It will become 2 when NT will have sent out 1460 byte of data.
Do you think my guess could be right? Is NT allowed to increase the
congestion window counting the number of full-sized packets that are been
acked, instead of counting the number of in-order ack that it gets (as
Linux does).
I don't own NT and check if my guess is right is not easy for me...
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/