Axp-List Archive
Re: Lockups during heavy disk I/O?

Subject: Re: Lockups during heavy disk I/O?
From: W Bauske (wsb@paralleldata.com)
Date: Thu Jul 13 22:50:51 2000


Paul Allen wrote:
>
> Alvin Starr wrote:
> >
> > Linux has a bit of a Feature;) in that when there is a lot of disk buffers
> > that need to be written out to disk, Linux will write them all out at once
> > and take some time to do it. While this is happning things will generaly
> > grind to a halt.
>
> Hmmm... that's what appears to be happening. I've just never noticed
> it on any other platform. I've seen Linux on SPARC and Intel, for
> example, and haven't noticed this sort of thing. I routinely do large
> disk-to-disk copies on my home system, for example, and never have
> the mouse freeze on me. Is this specific to the Alpha port? Or,
> is it related to having way too much RAM?
>

I don't see this at all and I move massive amounts of data
on my systems(Think multi GB files). It may get a bit sluggish
but it still responds which is what I expect. Note however,
I keep Linux on it's own disk, not where I store data. I give
Linux a token drive of a few GB and then put very large UATA66
drives on Promise cards. Just assembled an XP1000 with 4 60GB
Maxtor drives. As to your problem, I'd bet you're using the same
disk for OS and data. Add a separate data disk and I'll bet
it works fine. Heck, you can buy a 60GB Maxtor for $240 and
a promise card for $30 and have massive data storage for $270...

SCSI isn't even close for $$/MB. You could buy 3 60GB Maxtors
for the price of a 50GB SCSI drive.

You will need the E-IDE DMA patches to make it hum. Contact me
if you decide to try it and I can tell you what to watch out
for.

Wes

-- 
To unsubscribe: send e-mail to axp-list-request@redhat.com with
'unsubscribe' as the subject.  Do not send it to axp-list@redhat.com



This archive was generated by hypermail version 2a22 on Tue Aug 1 04:53:12 2000 PDT
Send any problems or questions about this archive to webmaster@alphalinux.org.