- From: Willy Tarreau <w@1wt.eu>
- Date: Fri, 4 Mar 2016 23:03:47 +0100
- To: Patrick McManus <mcmanus@ducksong.com>
- Cc: Joe Touch <touch@isi.edu>, HTTP Working Group <ietf-http-wg@w3.org>
Hi Pat, On Fri, Mar 04, 2016 at 04:16:22PM -0500, Patrick McManus wrote: (...) > on the one hand, we've gone from the client having a high rate of fast > 0RTT fails (blocked from initiating by TW).. to a situation where 3 things > are going on > > 1] an unquantified "large" fraction of quick successes. (no packet loss > impact, no state machine out of sync and no blockage by a timer) > 2] a number of cases of fast 1RTT fail where a RST is received by the client > 3] a fraction that may succeed or fail, but much more slowly due to retry > behavior with its set of lovely constants and backoffs Yes that's exactly it. > If I've got that (at least vaguely) right, there seem to be situational > tradeoffs as to whether that is 'better' or not. Sounds like good > discussion material in a tuning doc :) By definition, tuning has to be performed according to a specific situation, otherwise it becomes the standard way of doing things. > Within the scope of "TCP for HTTP" would you say something different? (and > sure, I agree legacy TCP might not be the fun thing here.. but its the > topic at hand.) My goal as well is not to dictate what should be done, but to enumerate known impacts of various choices on various actors so that we can always refer to that in the future for various parts of protocol designs (eg: we've done this already when documenting the fact that we must drain a request body before closing or that there's a DoS risk for proxies passing a close received from the client). In the end it should help us design more robust and more infrastructure-friendly protocols. And that's exactly what Daniel has begun with this nice document. Thanks for your support ;-) Willy
Received on Friday, 4 March 2016 22:04:26 UTC