Mail Archive Search: <+subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*\[PATCH\]\s+Too\s+aggressive\s+cwnd\s+backoff\s*$/>

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*\[PATCH\]\s+Too\s+aggressive\s+cwnd\s+backoff\s*$/: 24 ]

Total 24 documents matching your query.

1. [PATCH] Too aggressive cwnd backoff (score: 1): Author: Baruch Even <baruch@xxxxxxxxx>; Date: Thu, 7 Apr 2005 19:41:46 +0300; The cwnd backoff is down in two places and drops the cwnd to one quarter instead of to one half. On congestion events we reset tp->ssthresh to the result of tcp_recalc_ssthresh. This cuts the cwnd by; /archives/netdev/2005-04/msg00338.html (9,197 bytes)
2. Re: [PATCH] Too aggressive cwnd backoff (score: 1): Author: Stephen Hemminger <shemminger@xxxxxxxx>; Date: Thu, 7 Apr 2005 10:16:53 -0700; I think this is a real problem, and was observed by Werner with umlsim. Don't know when it got introduced because it appears to pre-date the '04 work in adding Westwood, BIC, Vegas. Perhaps Alexey ca; /archives/netdev/2005-04/msg00339.html (10,313 bytes)
3. Re: [PATCH] Too aggressive cwnd backoff (score: 1): Author: Baruch Even <baruch@xxxxxxxxx>; Date: Thu, 07 Apr 2005 19:14:45 +0100; Stephen Hemminger wrote: On Thu, 7 Apr 2005 19:41:46 +0300 Baruch Even <baruch@xxxxxxxxx> wrote: The provided patch will set limit to tp->ssthresh. This was the original behaviour in some older versi; /archives/netdev/2005-04/msg00340.html (10,195 bytes)
4. Re: [PATCH] Too aggressive cwnd backoff (score: 1): Author: "David S. Miller" <davem@xxxxxxxxxxxxx>; Date: Thu, 7 Apr 2005 11:31:21 -0700; Not true, that division by 2 is in the 2.4.23 sources, I just checked. It is there as far back as BK logs go in both the 2.4.x and 2.6.x trees. Perhaps the WEB100 guys patched that test, I bet that's; /archives/netdev/2005-04/msg00341.html (9,209 bytes)
5. Re: [PATCH] Too aggressive cwnd backoff (score: 1): Author: "David S. Miller" <davem@xxxxxxxxxxxxx>; Date: Thu, 7 Apr 2005 11:33:51 -0700; As stated in another email, it is still unknown where this "changed" or if it even "changed" at all in the vanilla sources. Could you track this down? I still strongly believe this is some WEB100 cha; /archives/netdev/2005-04/msg00342.html (9,266 bytes)
6. Re: [PATCH] Too aggressive cwnd backoff (score: 1): Author: John Heffner <jheffner@xxxxxxx>; Date: Thu, 7 Apr 2005 14:37:08 -0400 (EDT); This test looks correct to me. (We never touched it.) It is the bounding parameter specified in rate halving. If you actually get down that far, then rate halving is getting confused, though. -John; /archives/netdev/2005-04/msg00343.html (9,876 bytes)
7. Re: [PATCH] Too aggressive cwnd backoff (score: 1): Author: Baruch Even <baruch@xxxxxxxxx>; Date: Thu, 07 Apr 2005 20:18:09 +0100; David S. Miller wrote: On Thu, 7 Apr 2005 19:41:46 +0300 Baruch Even <baruch@xxxxxxxxx> wrote: However, in tcp_cwnd_down we will not stop reducing the cwnd until we get to limit which is set to tp->s; /archives/netdev/2005-04/msg00346.html (10,270 bytes)
8. Re: [PATCH] Too aggressive cwnd backoff (score: 1): Author: Werner Almesberger <werner@xxxxxxxxxxxxxxx>; Date: Thu, 7 Apr 2005 17:26:41 -0300; If this is still the old cwnd quartering bug, then it's very very old. Cheng Jin and I spotted it at the end of 2002 in 2.4.18, but didn't look at earlier versions. (Later, I used this problem to dem; /archives/netdev/2005-04/msg00349.html (10,506 bytes)
9. Re: [PATCH] Too aggressive cwnd backoff (score: 1): Author: "David S. Miller" <davem@xxxxxxxxxxxxx>; Date: Thu, 7 Apr 2005 13:37:54 -0700; That makes sense. And as John Heffner has pointed out, this change is correct and is part of rate-halving.; /archives/netdev/2005-04/msg00351.html (9,406 bytes)
10. Re: [PATCH] Too aggressive cwnd backoff (score: 1): Author: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>; Date: Fri, 08 Apr 2005 07:42:18 +1000; Looking at the vger tree this was introduced back in 2000: Cheers, -- Visit Openswan at http://www.openswan.org/ Email: Herbert Xu ~{PmV>HI~} <herbert@xxxxxxxxxxxxxxxxxxx> Home Page: http://gondor.ap; /archives/netdev/2005-04/msg00358.html (9,568 bytes)
11. Re: [PATCH] Too aggressive cwnd backoff (score: 1): Author: "David S. Miller" <davem@xxxxxxxxxxxxx>; Date: Thu, 7 Apr 2005 14:45:07 -0700; Heh, wish I was better at changelog messages back in the CVS days :-); /archives/netdev/2005-04/msg00359.html (9,075 bytes)
12. Re: [PATCH] Too aggressive cwnd backoff (score: 1): Author: Baruch Even <baruch@xxxxxxxxx>; Date: Fri, 08 Apr 2005 22:33:58 +0100; John Heffner wrote: This test looks correct to me. (We never touched it.) It is the bounding parameter specified in rate halving. If you actually get down that far, then rate halving is getting confu; /archives/netdev/2005-04/msg00407.html (10,333 bytes)
13. [PATCH] Too aggressive cwnd backoff (score: 1): Author: Baruch Even <baruch@xxxxxxxxx>; Date: Thu, 7 Apr 2005 19:41:46 +0300; The cwnd backoff is down in two places and drops the cwnd to one quarter instead of to one half. On congestion events we reset tp->ssthresh to the result of tcp_recalc_ssthresh. This cuts the cwnd by; /archives/netdev/2005-04/msg01474.html (9,197 bytes)
14. Re: [PATCH] Too aggressive cwnd backoff (score: 1): Author: Stephen Hemminger <shemminger@xxxxxxxx>; Date: Thu, 7 Apr 2005 10:16:53 -0700; I think this is a real problem, and was observed by Werner with umlsim. Don't know when it got introduced because it appears to pre-date the '04 work in adding Westwood, BIC, Vegas. Perhaps Alexey ca; /archives/netdev/2005-04/msg01475.html (10,371 bytes)
15. Re: [PATCH] Too aggressive cwnd backoff (score: 1): Author: Baruch Even <baruch@xxxxxxxxx>; Date: Thu, 07 Apr 2005 19:14:45 +0100; Stephen Hemminger wrote: On Thu, 7 Apr 2005 19:41:46 +0300 Baruch Even <baruch@xxxxxxxxx> wrote: The provided patch will set limit to tp->ssthresh. This was the original behaviour in some older versi; /archives/netdev/2005-04/msg01476.html (10,406 bytes)
16. Re: [PATCH] Too aggressive cwnd backoff (score: 1): Author: "David S. Miller" <davem@xxxxxxxxxxxxx>; Date: Thu, 7 Apr 2005 11:31:21 -0700; Not true, that division by 2 is in the 2.4.23 sources, I just checked. It is there as far back as BK logs go in both the 2.4.x and 2.6.x trees. Perhaps the WEB100 guys patched that test, I bet that's; /archives/netdev/2005-04/msg01477.html (9,317 bytes)
17. Re: [PATCH] Too aggressive cwnd backoff (score: 1): Author: "David S. Miller" <davem@xxxxxxxxxxxxx>; Date: Thu, 7 Apr 2005 11:33:51 -0700; As stated in another email, it is still unknown where this "changed" or if it even "changed" at all in the vanilla sources. Could you track this down? I still strongly believe this is some WEB100 cha; /archives/netdev/2005-04/msg01478.html (9,324 bytes)
18. Re: [PATCH] Too aggressive cwnd backoff (score: 1): Author: John Heffner <jheffner@xxxxxxx>; Date: Thu, 7 Apr 2005 14:37:08 -0400 (EDT); This test looks correct to me. (We never touched it.) It is the bounding parameter specified in rate halving. If you actually get down that far, then rate halving is getting confused, though. -John; /archives/netdev/2005-04/msg01479.html (10,034 bytes)
19. Re: [PATCH] Too aggressive cwnd backoff (score: 1): Author: Baruch Even <baruch@xxxxxxxxx>; Date: Thu, 07 Apr 2005 20:18:09 +0100; However, in tcp_cwnd_down we will not stop reducing the cwnd until we get to limit which is set to tp->ssthresh/2. The provided patch will set limit to tp->ssthresh. This was the original behaviour; /archives/netdev/2005-04/msg01482.html (10,339 bytes)
20. Re: [PATCH] Too aggressive cwnd backoff (score: 1): Author: Werner Almesberger <werner@xxxxxxxxxxxxxxx>; Date: Thu, 7 Apr 2005 17:26:41 -0300; If this is still the old cwnd quartering bug, then it's very very old. Cheng Jin and I spotted it at the end of 2002 in 2.4.18, but didn't look at earlier versions. (Later, I used this problem to dem; /archives/netdev/2005-04/msg01485.html (10,703 bytes)

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