- From: Willy Tarreau <w@1wt.eu>
- Date: Thu, 23 Oct 2014 19:23:02 +0200
- To: Tatsuhiro Tsujikawa <tatsuhiro.t@gmail.com>
- Cc: Mark Nottingham <mnot@mnot.net>, HTTP Working Group <ietf-http-wg@w3.org>
Hello, On Fri, Oct 24, 2014 at 01:53:09AM +0900, Tatsuhiro Tsujikawa wrote: > ???I've done quick hack to implement option 3 in nghttp2: > https://github.com/tatsuhiro-t/nghttp2/tree/hpack-opt3 Thank you very much for this! > Not much tested, but it should work for me with hpack-test-cases. > > deflatehd under src directory is handy to test compression ratio. > I don't have custom header dominated data to experiment with. Maybe Jeff can run his headers through it and compare ? That way he won't have to publish sensitive data. > ???I still think that unless it shows drastic improvements over -09 draft, > another interop is not worth it. The goal was not to show some drastic improvements but to address the regressions that make Jeff want to switch back to previous one, and at the same time try to avoid that same situation repeating for many other users in the future. I do think that what we have is fine but does not adequately cover *certain* workloads (it tends to be over-optimized for regular browsing only as we know it in 2014). Best regards, Willy
Received on Thursday, 23 October 2014 17:23:29 UTC