Date: Sun, 17 Feb 2002 18:27:59 -0800 From: Alfred Perlstein <bright@mu.org> To: Anthony Atkielski <anthony@freebie.atkielski.com> Cc: FreeBSD Questions <freebsd-questions@freebsd.org> Subject: Re: in-kernel HTTP Server for FreeBSD? Message-ID: <20020218022759.GM12136@elvis.mu.org> In-Reply-To: <018c01c1b816$6482f5a0$0a00000a@atkielski.com> References: <20020217143343.41758.qmail@web21104.mail.yahoo.com> <20020217173609.A25030@energyhq.homeip.net> <3C703154.91ED7FB4@mindspring.com> <20020217224724.GL12136@elvis.mu.org> <018c01c1b816$6482f5a0$0a00000a@atkielski.com>
next in thread | previous in thread | raw e-mail | index | archive | help
* Anthony Atkielski <anthony@freebie.atkielski.com> [020217 16:51] wrote: > Alfred writes: > > > The real problem is that most of the generic > > web servers available (as well as most commercial > > ones) just suck for handling IO and events. > > A well thought out design can give you quite > > a perf boost without needing to stick the > > _entire_ thing into the kernel. > > In a production environment, the cheapest and safest way to improve > performance is to buy more hardware. That's untrue, short sighed and off topic. But since you brought it up... :) More hardware means more sysadmin time, means higher chances of failure, means your software must be more robust in dealing with failures. An example is a large server farm that I know of that even with true ECC ram gets several non-recoverable memory errors per-day. Expenses go up the larger your cluster is, both in power, cost for space and cost for replacement parts, and how many parts you must have on hand for replacement. Your cluster will also never scale linearly such that at a certain point adding more nodes/cpus/loadbalancers "just works". No amount of hardware thrown at a problem can equal a well thought out design. Case in point Ebay when they maxed out their e10ks a couple of years back. Eventually they _needed_ to rethink their design in order to make the site usable again. Most of the "clusters" I've seen have ben a resul of poor core engineering. <queue theme from popular 80's show> If you have a cluster, if no one can get it to scale and if you can find him, maybe you can hire.... -- -Alfred Perlstein [alfred@freebsd.org] 'Instead of asking why a piece of software is using "1970s technology," start asking why software is ignoring 30 years of accumulated wisdom.' Tax deductible donations for FreeBSD: http://www.freebsdfoundation.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20020218022759.GM12136>