[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Re: no merit from using DMA-66?


----- Original Message -----
From: Vachirasuk <vachi@pop07.odn.ne.jp>
To: <Stephan.Hachinger@gmx.de>
Cc: <debian-user@lists.debian.org>
Sent: Monday, March 20, 2000 7:34 PM
Subject: Re: no merit from using DMA-66?

> I have tried asking around on japanese debian-user list and there is a
> person said he got 25MB/sec DTR on IBM harddisk from the test with
> hdparm. Moreover from hdparm manpage about -t option:
>               This  displays  the  speed  of  reading through the
>               buffer cache to the disk without any prior  caching
>               of  data.  This measurement is an indication of how
>               fast the drive can sustain  sequential  data  reads
> so I guess the DTR is measured with the cache on. This should give
> some better DTR over DMA-33 harddisk, if I got it right?

Don't know, but if it's really a test with caching, it will probably really
give back higher data rates. Up to now, I always tested my hds with Dr.
Hardware for DOS ;-) or with some Windoze software, which also could switch
on or switch off the cache due to user request. But the results with caching
are not significant anyway in my opinion, because it is important, at what
speed the drive can read permanently (at least for my applications, I think,
other people might have other opinions...).

Kind Regards,

Stephan Hachinger

Reply to: