From: ijw11@phx.cam.ac.uk (Ian Wells) Subject: Re: Abysmal disk performance Date: 15 May 1992 13:24:47 GMT
In article <1992May14.215250.3430@news.cso.uiuc.edu> ddd42961@uxa.cso.uiuc.edu
(Daniel D Deavours) writes:
Never programmed a DMA before, but if I'm correct, the advantage may not be
so much speed in data transfer, but the ability to do disk i/o in the back-
ground. It's annoying, especially on my slow hd/controller for everything
to wait until the hard drive is done (especially when syncing.)
Yes, but everything doesn't just stop when disk access happens. The
only process that does stop running is he one using the disk. This
means that if you run disk-intensive stuff in one VC you can leave it
going and get on with your editing, etc. Basically anything that
doesn't access your hard disk much will ruin quite fast if the other
process is I/O bound.
Oh yes, 2 more questions to ask, while I think about it:
1. When you load, say, gcc twice (sepearately, as opposed to a fork()
call, is what I'm getting at), do the code and const data sections get
shared?
2. Is there a technical name for when the hard disk sits
reading/writing two separate sections of the disk some distance apart
and spends most of its time seeking? This is something annoying I've
tended to notice with Linux, but if it now does readahead on files it
may be improved in this respect.
I don't have my computer with me this term, in the hope that I'll do
some work. It's not working.
Ian Wells.