Path: utzoo!utgpu!jarvis.csri.toronto.edu!clyde.concordia.ca!mcgill-vision!bloom-beacon!bu.edu!bu-cs!snorkelwacker!tut.cis.ohio-state.edu!zaphod.mps.ohio-state.edu!math.lsa.umich.edu!emv
From: pvo3366@sapphire.OCE.ORST.EDU (Paul O'Neill)
Newsgroups: comp.archives
Subject: [comp.sys.next] WrenV caching (Re: Wren V 94181-702 installation)
Message-ID: <10806@stag.math.lsa.umich.edu>
Date: 6 Feb 90 23:54:38 GMT
Sender: news@math.lsa.umich.edu
Reply-To: pvo3366@sapphire.OCE.ORST.EDU (Paul O'Neill)
Followup-To: comp.sys.next
Lines: 34
Approved: emv@math.lsa.umich.edu (Edward Vielmetti)

Archive-name: next-wrenv-cache/05-Feb-90
Original-posting-by: pvo3366@sapphire.OCE.ORST.EDU (Paul O'Neill)
Original-subject: WrenV caching (Re: Wren V 94181-702 installation)
Archive-site: sutro.sfsu.edu [130.212.15.230]
Reposted-by: emv@math.lsa.umich.edu (Edward Vielmetti)

In article <15477@orstcs.CS.ORST.EDU> pvo3366@sapphire.OCE.ORST.EDU (I) wrote:

>.........................I'm guessing that the operating system is
>not telling the Wren V to use its 32k cache buffer.  Anyone know how
>to do this?
>

Well, gosh, it turns out *I* know how to do this. :-)

Take the Product Specification, mix gently but thoroughly with
	/NextDeveloper/Examples/SCSI/sg_example.c
and the result is
	cachecon.c

I just ftp'ed it to the cs.orst.edu archives as WrenV_cache.tar.Z.

Speed of sequential reads measured by the 'disk' program has gone
from 250 KB/s to 350 KB/s.

It looks like it may work on Wren IV's, also.

Now all we have to do is figure out this rotational latency stuff.  Help!!


Paul O'Neill                 pvo@oce.orst.edu
Coastal Imaging Lab
OSU--Oceanography
Corvallis, OR  97331         503-737-3251