> -----Original Message-----
>From: linux kernel account [SMTP:linker@nightshade.z.ml.org]
>Sent: Monday, January 05, 1998 8:51 PM
>To: pmonta@imedia.com
>Cc: jhohertz@golden.net; h.milz@seneca.muc.de;
linux-kernel@vger.rutgers.edu
>Subject: Re: lack of raw disk devices>
>.
>On Mon, 5 Jan 1998, Peter Monta wrote:>
>
>> A raw device doesn't go through the buffer cache. For
example, if you
>> issue two reads for the same block, a raw device will
physically go
>> out to disk each time, whereas a buffered device will satisfy
the
>> second request from the cache.
>>
>> I've read all of the discussion I can find about this, in
linux-kernel
>> archives and elsewhere, and while I don't want to beat a dead
horse, I
>> disagree with those who say raw devices are useless or
intrinsically
>> bad. Granted, the vast majority of the time a buffered
device is the
>> right thing. But I have one application in mind that cries
out for a
>> raw device---it involves moving digital video as fast as
possible from
>> disk to DRAM (and subsequently out to a PCI bus master). The
system
>> will never again need to refer to this data, so a buffered
device both
>> incurs a copying expense (from buffer cache to DRAM buffer)
and
>> trashes the buffer cache to no purpose.
>
>They are not bad, however, the implimentation would be
sufficently
>difficult and cumbersom, to mostly out weigh the benifits.. In
the future,
>it would be nice if you could adjust the buffercache
characteristics on a
>device by device basis and potentiall on each group of block
reads
>(wouldn't it be neat if ext2fs could be told by the app 'this
is a mpg
>movie dont cache it' while it's accessed, while the rest of the
device
>would be cached normally)..
>
>>
>> Cheers,
>> Peter Monta pmonta@imedia.com
>> Imedia Corp.