Messages in this thread | | | Date | Thu, 25 Feb 1999 13:18:25 -0800 | From | (Pete Wyckoff) | Subject | Re: very poor TCP performance with 2.2.2 |
| |
mjr@ranney.com writes:
> running the client under 2.0.36 and the server on 2.2. It doesn't > look like dropped packets in this case, but things are much much > slower.
It's all in the tcpdump again:
35.946640 lisa.15108 > pornucopia.http: S 3647705548:3647705548(0) win 512 <mss 1460> 35.946691 pornucopia.http > lisa.15108: S 629466495:629466495(0) ack 3647705549 win 32120 <mss 1460> (DF) 35.946845 lisa.15108 > pornucopia.http: . ack 1 win 32120 (DF) 35.947892 lisa.15108 > pornucopia.http: P 1:73(72) ack 1 win 32120 (DF) 35.948524 pornucopia.http > lisa.15108: . 1:1461(1460) ack 73 win 32120 (DF) 36.270955 lisa.15108 > pornucopia.http: . ack 1461 win 32120 (DF) 36.271000 pornucopia.http > lisa.15108: FP 1461:2210(749) ack 73 win 32120 (DF) 36.271262 lisa.15108 > pornucopia.http: . ack 2211 win 31370 (DF) 36.271680 lisa.15108 > pornucopia.http: F 73:73(0) ack 2211 win 32120 36.271716 pornucopia.http > lisa.15108: . ack 74 win 32120 (DF)
The client, lisa, gets the first segment from the server, then sits on it for 300 ms hoping there'll be another. I'm not too familiar with the old 2.0 network code, but this looks like tcp_delack_estimator() is just setting ato to 333 ms, and not doing the "quickack" stuff of 2.2.
Would you mind summarizing any unexplained behavior? I'm trying to see if there's really a problem in the v2.2.2 TCP code, or if you've just uncovered some odd interactions among various stacks.
-- Pete --------------------------------------------- Pete Wyckoff | wyckoff@ca.sandia.gov Sandia National Labs | 925 294 3503 (voice) MS 9011, P.O. Box 969 | 925 294 1225 (fax) Livermore, CA 94551 |
- 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/
| |