Path: utzoo!utgpu!news-server.csri.toronto.edu!clyde.concordia.ca!uunet!rayssd!sud509!heiser@tdw201.ed.ray.com From: heiser@tdw201.ed.ray.com Newsgroups: comp.periphs.scsi Subject: Re: Read-ahead and power failure Message-ID: <2396@sud509.ed.ray.com> Date: 12 Sep 90 19:22:53 GMT References: <1990Aug31.211751.10553@simasd.uucp> <2344@sud509.ed.ray.com> <201@xstor.UUCP> Sender: heiser@sud509.ed.ray.com (Bill Heiser - Unix Sys Admin @ Raytheon Company, Sudbury MA) Distribution: na Organization: Raytheon Company, Sudbury MA Lines: 35 In article <201@xstor.UUCP> iverson@xstor.UUCP (Tim Iverson) writes: > >This is not true. Read-ahead caching is purely write-through, so there are >no problems with cache concurrency. The power fail problems all result from >unix's block device buffering scheme, which is write-back. Depending on >how your system is used, turning read-ahead on can cause a performance >*decrease* in rare cases due to the increased overhead involved in >performing the read-ahead (e.g. when your system never wants the data the >data that has been cached). The thing to do is try it and see. Interesting -- thanks for the info. >BTW, I'd axe the consultant - paying for misinformation is a bad idea when >you can get it for free from the net :-). Agreed. I wasn't actually paying him for anything anyway -- he offered to *give* me some fixes and utilites he had for Esix -- and then "mentioned" that he had tape drives for sale (from what I've found on the net, his price was almost double the going price), and also told me about the cache "problem." After all this, I've opted not to implement his fixes (his fixed boot disk wouldn't boot anyway!), and just stick to the net for my info. Thanks for the feedback. bill -- Work: heiser@tdw201.ed.ray.com {decuac,necntc,uunet}!rayssd!tdw201!heiser Home(1): bill%unixland.uucp@world.std.com -or- uunet!world!unixland!bill Public Access Unix Coming Soon! Home(2): Bill.Heiser@f240.n322.z1.fidonet.org (BBS: 1-508-655-3848) Other: heiser@world.std.com (Pub. Access Unix)