Date: Fri, 1 Feb 2002 00:46:58 -0800 From: Luigi Rizzo <rizzo@icir.org> To: Alfred Perlstein <bright@mu.org> Cc: Terry Lambert <tlambert2@mindspring.com>, Mike Silbersack <silby@silby.com>, Storms of Perfection <gary@outloud.org>, thierry@herbelot.com, replicator@ngs.ru, hackers@FreeBSD.ORG Subject: Re: Clock Granularity (kernel option HZ) Message-ID: <20020201004658.A48810@iguana.icir.org> In-Reply-To: <20020201002835.I18604@elvis.mu.org> References: <20020131172729.X38382-100000@patrocles.silby.com> <3C59E873.4E8A82B5@mindspring.com> <20020201002339.C48439@iguana.icir.org> <20020201002835.I18604@elvis.mu.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, Feb 01, 2002 at 12:28:35AM -0800, Alfred Perlstein wrote: > > > throughput vs. overhead if you process packets to completion > > > at interrupt, and process writes to completion at write time > > > from the process. > > > > this does not match my numbers. e.g. using "fastforwarding" > > (which bypasses netisrs's) improves peak throughput > > by a factor between 1.2 and 2 on our test boxes. > > Forwarding packets is a lot less complicated than doing tcp > recieve and send. I haven't seen Terry's stuff in action, > however it makes sense that tcp would see more of an improvement > than simple IP forwarding. but exactly because of this reason, the overhead of netisr should be less and less relevant as the processing increases. Unless of course you end up in livelock, in which case performance drops to 0 without processing-to-completion, and then the performance improvement is arbitrarily high (see the table in http://info.iet.unipi.it~luigi/polling/ ). cheers luigi To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20020201004658.A48810>