This message is from the T13 list server.
Also FWIW, Read Ahead can encounter a bad sector - it should be dealt with in a logical way without failing sectors around it. I only mention this because I've seen system software implementations that don't work correctly with read-ahead type processing. -- David F. TeraByte Unlimited http://www.terabyteunlimited.com > -----Original Message----- > From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On > Behalf Of Sheffield, Robert L > Sent: Wednesday, June 29, 2005 9:46 AM > To: Hale Landis; [email protected] > Subject: RE: [t13] Read Look Ahead > > This message is from the T13 list server. > > > Hale, > > Read cache and read look ahead are decidedly different concepts. > > Read cache tries to assess the probability that a previously > read set of data will be read again in the near future, and > therefore attempts to retain in "cache" data that seems to > have a high probability of being accessed again based on a > locality of reference. > > Read look ahead is used when data access is sequential, and > attepts to pre-buffer data that, because of the sequential > nature of the data access, is likely to be requested in the > near future (actually, likely in the very next request). The > difference is that the read look ahead data hasn't > necessarily been read recently, and, in fact, may never have > been previously read since it was last written (could be > days, weeks, months, or even years since it was last accessed). > > Both functions consume buffer space in the drive, but the > similarity ends there. > > Bob > > -----Original Message----- > From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On > Behalf Of Hale Landis > Sent: Wednesday, June 29, 2005 9:32 AM > To: [email protected] > Subject: Re: [t13] Read Look Ahead > > This message is from the T13 list server. > > > Curtis Stevens wrote: > > This message is from the T13 list server. > > Hale > > I have to disagree with you. I do not have any > recollection of read > > ahead controlling read cache. To the best of my knowledge, this > disables > > look ahead in WD drives but has no effect on read cache. Quite > frankly I > > was shocked to hear that someone was actually interpreting the > function as a > > cache disable. No ATA rev has even hinted that this was a cache > disable... > > So both you and Mark are saying there is no documented way to > disable read caching in an ATA drive? It is only possible to > disable the "read look ahead" part of some more complex "read > caching" algorithm? > > Hale > > -- > > ++ Hale Landis ++ www.ata-atapi.com ++ >
