Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!samsung!usc!snorkelwacker.mit.edu!apple!amdcad!brahms!phil From: phil@brahms.amd.com (Phil Ngai) Newsgroups: comp.arch Subject: Re: Sun bogosities, including MMU thrashing Message-ID: <1991Jan24.185653.21429@amd.com> Date: 24 Jan 91 18:56:53 GMT References: <5390@auspex.auspex.com> <1991Jan21.225211.17757@gpu.utcs.utoronto.ca> Sender: usenet@amd.com (NNTP Posting) Organization: Advanced Micro Devices, Inc; Sunnyvale, CA Lines: 15 In article <1991Jan21.225211.17757@gpu.utcs.utoronto.ca> dennis@gpu.utcs.utoronto.ca (Dennis Ferguson) writes: |While I'm unwilling to dig through the references to determine whether |Thompson and Ritchie actually said this, if they did I do think they may If I recall correctly, the argument was that sequential look ahead on reads has all the advantages provided by bigger block size without the fragmentation problems. This probably assumed reads were much more frequent than writes, which may have some dependency on the use of program swapping since a program which is in swap space only needs to be read in, not written out. -- When someone drinks and drives and hurts someone, the abuser is blamed. When someone drinks and handles a gun and hurts someone, the media calls for a gun ban.