Mail Archive Search: <+subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*2\.6\.10\s+TCP\s+troubles\s+\-\-\s+suggested\s+patch\s*$/>

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*2\.6\.10\s+TCP\s+troubles\s+\-\-\s+suggested\s+patch\s*$/: 80 ]

Total 80 documents matching your query.

1. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: chrisw@xxxxxxxx>; Date: Wed, 9 Feb 2005 10:59:09 -0800; Please try this patch, based on Alexey's suggestion: diff -Nru a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c -- a/net/ipv4/tcp_output.c 2005-02-09 11:01:12 -08:00 +++ b/net/ipv4/tcp_output.c 2005-0; /archives/netdev/2005-02/msg00300.html (10,040 bytes)
2. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: n@xxxxxxxxxxxx>; Date: Wed, 9 Feb 2005 12:25:09 -0800; -EBADINDENTATION :-); /archives/netdev/2005-02/msg00305.html (8,979 bytes)
3. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: xxxxx>; Date: Thu, 10 Feb 2005 21:53:20 GMT; It does not seem to solve the problem: . Linux 2.6.9 takes 15 seconds to copy 105 MB to the Mac OSX . Linux 2.6.10 with the TCP patch still takes 325 seconds.; /archives/netdev/2005-02/msg00347.html (11,099 bytes)
4. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: Pekka Savola <pekkas@xxxxxxxxxx>; Date: Thu, 10 Feb 2005 14:36:40 -0800; Hubert Tonneau wrote: It does not seem to solve the problem: . Linux 2.6.9 takes 15 seconds to copy 105 MB to the Mac OSX . Linux 2.6.10 with the TCP patch still takes 325 seconds. is there a packet; /archives/netdev/2005-02/msg00348.html (10,137 bytes)
5. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: <pablo@xxxxxxxxxxx>; Date: Thu, 10 Feb 2005 17:16:12 -0800; I know what's wrong, no trace needed, Stephen's patch misses tcp_push_one() and similar. He only added the PSH bit setting to tcp_write_xmit(). Hubert, try this patch instead. == net/ipv4/tcp_output.; /archives/netdev/2005-02/msg00358.html (12,592 bytes)
6. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: xxxx>; Date: Fri, 11 Feb 2005 21:55:49 GMT; Sorry, it still does not work, unless I made a mistake: Linux 2.6.9 takes 15 seconds to copy 105 MB to Mac OSX Linux 2.6.10 with the TCP patch below still takes 325 seconds to do the same. You can pi; /archives/netdev/2005-02/msg00395.html (13,114 bytes)
7. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: f Garzik <jgarzik@xxxxxxxxx>; Date: Fri, 11 Feb 2005 14:54:27 -0800; Hubert Tonneau wrote: Sorry, it still does not work, unless I made a mistake: Linux 2.6.9 takes 15 seconds to copy 105 MB to Mac OSX Linux 2.6.10 with the TCP patch below still takes 325 seconds to d; /archives/netdev/2005-02/msg00397.html (14,575 bytes)
8. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: f Garzik <jgarzik@xxxxxxxxx>; Date: Fri, 11 Feb 2005 15:04:20 -0800; Still not setting Push sufficiently to keep MacOSX happy. 13:40:35.027124 IP 10.107.96.230.netbios-ssn > 10.107.96.7.32801: P 924:975(51) ack 67344 win 50728 13:40:35.027186 IP 10.107.96.230.netbios-; /archives/netdev/2005-02/msg00398.html (13,567 bytes)
9. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: eau <hubert.tonneau@xxxxxxxxxxxxxx>; Date: Fri, 11 Feb 2005 15:09:11 -0800; Rick Jones wrote: 000010 10.107.96.7.32801 > 10.107.96.230.139: . 11692:13140(1448) ack 822 win 1460 <nop,nop,timestamp 534449 1709240658> NBT Packet (DF) 000004 10.107.96.7.32801 > 10.107.96.230.139; /archives/netdev/2005-02/msg00399.html (12,096 bytes)
10. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: >; Date: Fri, 11 Feb 2005 15:40:20 -0800; Er, how is this compliant with 2581 (yes, I know, it's only a SHOULD, not a MUST) - an ACK should be generated for at least every second full-sized segment received? Don't see that happening. In many; /archives/netdev/2005-02/msg00400.html (12,005 bytes)
11. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: ieu@xxxxxxxxxxxxx>; Date: Fri, 11 Feb 2005 17:07:40 -0800; I don't think it's the kernel's fault in this case. This set of data frames you quoted are all full, and are tightly interspaced. It looks exactly like a TSO frame, which we certainly set PSH on, but; /archives/netdev/2005-02/msg00407.html (10,621 bytes)
12. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: eu@xxxxxxxxxxxxx>; Date: Fri, 11 Feb 2005 17:08:17 -0800; It's compliant but stupid.; /archives/netdev/2005-02/msg00408.html (10,477 bytes)
13. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: u@xxxxxxxxxxxxx>; Date: Fri, 11 Feb 2005 17:09:58 -0800; At a maximum, "1/tcp_tso_win_divisor" of the cwnd will ever be left empty. By default, this is 1/8 of the cwnd.; /archives/netdev/2005-02/msg00409.html (10,419 bytes)
14. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: w@xxxxxxxx>; Date: Sat, 12 Feb 2005 13:11:43 +0100; If that is the problem it should be easy to test for. Just disable TSO with ethtool -K ethX tso off Hubert, does that make the problem go away? -Andi; /archives/netdev/2005-02/msg00417.html (10,713 bytes)
15. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: x>; Date: Sat, 12 Feb 2005 17:16:41 +0300; Or it was two one-segment frames. Before blaming on e1000 it would be easier to confirm that linux never worked with MacOS X, except for those kernels which had congestion avoidance mostly supppress; /archives/netdev/2005-02/msg00420.html (11,466 bytes)
16. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: i Kleen <ak@xxxxxx>; Date: Sat, 12 Feb 2005 17:31:05 +0300; In any case, receiver cannot know sender cwnd, so that "fill" or "not fill" is is not a question. What is broken in that implementation is that it does not feel slow start. ACK avoidance while slow; /archives/netdev/2005-02/msg00422.html (11,456 bytes)
17. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: xxxxxxxx>; Date: Sat, 12 Feb 2005 11:23:07 -0800; We're testing the new code that sets PSH on every TSO frame. If we disable TSO, the new code won't be exercised nor tested.; /archives/netdev/2005-02/msg00425.html (10,941 bytes)
18. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: exey Kuznetsov <kuznet@xxxxxxxxxxxxx>; Date: Sat, 12 Feb 2005 11:28:11 -0800; It is correct. Although, I am still believing that setting PSH is the avenue of investigation.; /archives/netdev/2005-02/msg00426.html (10,909 bytes)
19. Re: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: blo Neira <pablo@xxxxxxxxxxx>; Date: Sat, 12 Feb 2005 11:41:32 -0800; ... Even ignoring my TSO changes, we should be seeing at a minimum 1/2 window PSH settings which we're not as far as I can tell. (this is due to the forced_push() test in net/ipv4/tcp.c) This also po; /archives/netdev/2005-02/msg00427.html (11,354 bytes)
20. RE: 2.6.10 TCP troubles -- suggested patch (score: 1): Author: g <olh@xxxxxxx>; Date: Sat, 12 Feb 2005 11:44:45 -0800; Typically, a TSO engine sets PSH in the last packet that it builds for the TSO+PSH request. Leonid; /archives/netdev/2005-02/msg00428.html (11,564 bytes)

Current List: 1 - 20
Page: [1] [2] [3] [4]