From owner-freebsd-hackers Thu May 15 11:12:52 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.5/8.8.5) id LAA04841 for hackers-outgoing; Thu, 15 May 1997 11:12:52 -0700 (PDT) Received: from caipfs.rutgers.edu (caipfs.rutgers.edu [128.6.155.100]) by hub.freebsd.org (8.8.5/8.8.5) with ESMTP id LAA04833 for ; Thu, 15 May 1997 11:12:47 -0700 (PDT) Received: from jenolan.caipgeneral (jenolan.rutgers.edu [128.6.111.5]) by caipfs.rutgers.edu (8.8.5/8.8.5) with SMTP id OAA20617; Thu, 15 May 1997 14:12:00 -0400 (EDT) Received: by jenolan.caipgeneral (SMI-8.6/SMI-SVR4) id OAA01276; Thu, 15 May 1997 14:10:28 -0400 Date: Thu, 15 May 1997 14:10:28 -0400 Message-Id: <199705151810.OAA01276@jenolan.caipgeneral> From: "David S. Miller" To: terry@lambert.org CC: ejc@bazzle.com, james@westongold.com, freebsd-hackers@FreeBSD.ORG In-reply-to: <199705151709.KAA15089@phaeton.artisoft.com> (message from Terry Lambert on Thu, 15 May 1997 10:09:21 -0700 (MST)) Subject: Re: mmap() Sender: owner-hackers@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk From: Terry Lambert Date: Thu, 15 May 1997 10:09:21 -0700 (MST) This is not to say the situation is hopeless; you *could* crank up the sequential I/O performance of mmap(), at a cost of a save and compare in the general page fault case. Or you could add intelligent page prefetching/prefaulting, see the JACM article on prefetching about 3 or 4 issues ago for an extremely clever strategy to pull this off in an online fashion. Although be careful, their scheme is patented, but you could implement something similar just using something other than LNZ compression code selection (ie. use another compression scheme's code selection). There is proof even in the computer learning field that this is an extremely effective limited history prefetching strategy. ---------------------------------------------//// Yow! 11.26 MB/s remote host TCP bandwidth & //// 199 usec remote TCP latency over 100Mb/s //// ethernet. Beat that! //// -----------------------------------------////__________ o David S. Miller, davem@caip.rutgers.edu /_____________/ / // /_/ ><