Re: [dev] [quark] Performance issues

From: Anselm Garbe <>
Date: Mon, 23 Sep 2019 13:07:47 -0700

On Mon, 23 Sep 2019 at 12:50, Richard Ulmer
<> wrote:
> I checked the performance of revision
> 22b5b3cfa6b28f8e0c6c35c04ad9b4cb609b5643 like this:
> echo 'foo bar' > index.html
> doas quark > /dev/null &
> ab -n 10000 -c 20 'http://localhost:8083/'
> And I got 942 requests/second, so I'd say there is no significant
> difference to the current version of quark.

Thanks for doing that and letting me know. So the reason you see this
performance penalty in contrast to the other web servers you mention
is, that quark is a fork() based web server (and current HEAD is still
fork() based). That's the whole reason ;)

The decision for making it fork() based was on purpose, to keep its
implementation as simple as possible. However, I do see potential to
revise quark's current implementation and to consider dropping various
features, but up to Laslo. ;)

Best regards,
Received on Mon Sep 23 2019 - 22:07:47 CEST

This archive was generated by hypermail 2.3.0 : Tue Sep 24 2019 - 05:36:08 CEST