Mail Archive Search: <+subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*TCP\s+receiver\'s\s+window\s+calculation\s+problem\s*$/>

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*TCP\s+receiver\'s\s+window\s+calculation\s+problem\s*$/: 12 ]

Total 12 documents matching your query.

1. TCP receiver's window calculation problem (score: 1): Author: xxxx>; Date: Wed, 23 Jun 2004 22:49:54 -0700 (PDT); We have been running some iperf experiments over long-latency high-capacity networks for protocol testing. We noticed a strange receiver's window limitation of 3,147,776 bytes even when the iperf se; /archives/netdev/2004-06/msg00707.html (10,028 bytes)
2. Re: TCP receiver's window calculation problem (score: 1): Author: xxxx>; Date: Thu, 24 Jun 2004 13:43:27 -0400 (EDT); I've run in to this problem, too. This code prevents advertising more rcvbuf space than you are likely to need. This is good for something like an X11 connection, but obviously very bad for the bulk; /archives/netdev/2004-06/msg00721.html (11,655 bytes)
3. Re: TCP receiver's window calculation problem (score: 1): Author: xx>; Date: Thu, 24 Jun 2004 12:18:19 -0700 (PDT); Thanks for confirming this problem. I would think this is already taken care of at the sender by application limited cwnd so cwnd wouldn't increase beyond what is being actually used. I think having; /archives/netdev/2004-06/msg00722.html (9,059 bytes)
4. Re: TCP receiver's window calculation problem (score: 1): Author: Vincent Perrier <vincent-perrier@xxxxxxxxxxxxxxxx>; Date: Thu, 24 Jun 2004 15:26:27 -0400 (EDT); The core of the problem is that you are describing a truesize of each skb at about 16k, but each of those only contains < 1500 bytes of payload. You are wasting 90% of your socket memory. Announcing; /archives/netdev/2004-06/msg00724.html (8,887 bytes)
5. Re: TCP receiver's window calculation problem (score: 1): Author: xxxxxx>; Date: Thu, 24 Jun 2004 23:37:35 -0700 (PDT); The receiver is set to use a 9000 MTU, but the sender uses a 1500-byte MTU, which is not really a pathological case. It would have made more sense for the receiver to allocate skbs of the right size; /archives/netdev/2004-06/msg00739.html (9,290 bytes)
6. Re: TCP receiver's window calculation problem (score: 1): Author: herbert@xxxxxxxxxxxxxxxxxxx>; Date: Fri, 25 Jun 2004 09:43:32 -0400 (EDT); Some drivers are apparently optimized for this case. I have not confirmed this. I haven't looked too hard in to this. Any device driver people want to chime in? -John; /archives/netdev/2004-06/msg00745.html (8,750 bytes)
7. TCP receiver's window calculation problem (score: 1): Author: Cheng Jin <chengjin@xxxxxxxxxxxxxx>; Date: Wed, 23 Jun 2004 22:49:54 -0700 (PDT); Hi, We have been running some iperf experiments over long-latency high-capacity networks for protocol testing. We noticed a strange receiver's window limitation of 3,147,776 bytes even when the iperf; /archives/netdev/2004-06/msg01591.html (10,052 bytes)
8. Re: TCP receiver's window calculation problem (score: 1): Author: John Heffner <jheffner@xxxxxxx>; Date: Thu, 24 Jun 2004 13:43:27 -0400 (EDT); I've run in to this problem, too. This code prevents advertising more rcvbuf space than you are likely to need. This is good for something like an X11 connection, but obviously very bad for the bulk; /archives/netdev/2004-06/msg01605.html (11,703 bytes)
9. Re: TCP receiver's window calculation problem (score: 1): Author: Cheng Jin <chengjin@xxxxxxxxxxxxxx>; Date: Thu, 24 Jun 2004 12:18:19 -0700 (PDT); Hi, John, Thanks for confirming this problem. I would think this is already taken care of at the sender by application limited cwnd so cwnd wouldn't increase beyond what is being actually used. I thi; /archives/netdev/2004-06/msg01606.html (9,107 bytes)
10. Re: TCP receiver's window calculation problem (score: 1): Author: John Heffner <jheffner@xxxxxxx>; Date: Thu, 24 Jun 2004 15:26:27 -0400 (EDT); The core of the problem is that you are describing a truesize of each skb at about 16k, but each of those only contains < 1500 bytes of payload. You are wasting 90% of your socket memory. Announcing; /archives/netdev/2004-06/msg01608.html (8,934 bytes)
11. Re: TCP receiver's window calculation problem (score: 1): Author: Cheng Jin <chengjin@xxxxxxxxxxxxxx>; Date: Thu, 24 Jun 2004 23:37:35 -0700 (PDT); John, The receiver is set to use a 9000 MTU, but the sender uses a 1500-byte MTU, which is not really a pathological case. It would have made more sense for the receiver to allocate skbs of the right; /archives/netdev/2004-06/msg01623.html (9,338 bytes)
12. Re: TCP receiver's window calculation problem (score: 1): Author: John Heffner <jheffner@xxxxxxx>; Date: Fri, 25 Jun 2004 09:43:32 -0400 (EDT); Some drivers are apparently optimized for this case. I have not confirmed this. I haven't looked too hard in to this. Any device driver people want to chime in? -John; /archives/netdev/2004-06/msg01629.html (8,797 bytes)

Current List: 1 - 12
Page: [1]