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 ++
> 


Reply via email to