Date: Mon, 08 May 2006 20:10:47 -0300 From: tpeixoto@widesoft.com.br To: tpeixoto@widesoft.com.br, .@babolo.ru, Lee Johnston <lee@wildcard.net.uk>, freebsd-net@freebsd.org, Julian Elischer <julian@elischer.org>, mihai@duras.ro Subject: Re: Packet loss with traffic shaper and routing Message-ID: <445FCFF7.9070403@widesoft.com.br> In-Reply-To: <20060504015524.GV728@funkthat.com> References: <1146645702.297895.80691.nullmailer@cicuta.babolo.ru> <44595B76.9010901@widesoft.com.br> <20060504015524.GV728@funkthat.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Interesting. I'll try to take a look when I have some free time and then post some comments. Thanks. John-Mark Gurney wrote: > tpeixoto@widesoft.com.br wrote this message on Wed, May 03, 2006 at 22:40 -0300: >> Anyway, I am very curious about the result of test 2. Why do the pipes >> have influence on system performance if there is nothing passing through >> them? > > It looks like each tick all the pipes are scanned... In dummynet: > /* Sweep pipes trying to expire idle flow_queues. */ > for (i = 0; i < HASHSIZE; i++) > SLIST_FOREACH(pipe, &pipehash[i], next) > > That bit of code should probably be run less often... >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?445FCFF7.9070403>