From owner-freebsd-hackers Mon Apr 19 14:22: 2 1999 Delivered-To: freebsd-hackers@freebsd.org Received: from apollo.backplane.com (apollo.backplane.com [209.157.86.2]) by hub.freebsd.org (Postfix) with ESMTP id C38DD14F59 for ; Mon, 19 Apr 1999 14:21:59 -0700 (PDT) (envelope-from dillon@apollo.backplane.com) Received: (from dillon@localhost) by apollo.backplane.com (8.9.3/8.9.1) id OAA90535; Mon, 19 Apr 1999 14:19:29 -0700 (PDT) (envelope-from dillon) Date: Mon, 19 Apr 1999 14:19:29 -0700 (PDT) From: Matthew Dillon Message-Id: <199904192119.OAA90535@apollo.backplane.com> To: Jonathan Lemon Cc: Arjan.deVet@adv.iae.nl, hackers@FreeBSD.ORG Subject: Re: Directories not VMIO cached at all! References: <199904192058.PAA16517@free.pcs> Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG :Which is why Peregrine prefers to use raw disk partitions (along with :a userland variant of LFS) to store the pages, since the filesystem :currently imposes too much overhead for good performance. : :It's interesting, LFS seems to be a great web-cache filesystem, you :don't really need to preserve every file, you just throw some away. :No fsck; if the system crashes, you can just start all over again; :after all, it _is_ a cache, right? (In Peregrine, this behavior is :tunable; some environments don't want to lose the entire cache). :-- :Jonathan Going through the buffered block device for a partition would be quite efficient. FreeBSD can parallelize block I/O very nicely - there are no locks to get in the way. Using a file isn't terrible, though. You just have to use more then one. I used this trick in Diablo ( my usenet news transit system ). Each file caches multiple articles. It doesn't take a very large ratio to achieve optimal performance. By limiting the number of files, you virtually guarentee namei cache hits. -Matt Matthew Dillon To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message