Path: utzoo!attcan!utgpu!jarvis.csri.toronto.edu!mailrus!csd4.csd.uwm.edu!cs.utexas.edu!sun-barr!newstop!east!hinode!geoff
From: geoff@hinode.East.Sun.COM (Geoff Arnold @ Sun BOS - R.H. coast near the top)
Newsgroups: comp.protocols.nfs
Subject: Re: Speeding up PC-NFS
Message-ID: <803@east.East.Sun.COM>
Date: 8 Sep 89 13:21:45 GMT
References: <952@legato.LEGATO.COM>
Sender: news@east.East.Sun.COM
Reply-To: geoff@East.Sun.COM (Geoff Arnold @ Sun BOS - R.H. coast near the top)
Organization: Sun Microsystems, Billerica MA
Lines: 24

In article <952@legato.LEGATO.COM> blyon@Legato.COM (Bob Lyon) writes:
>[Lots of neat stuff about Prestoserve.]
>A PC-NFS-based beta site (I cannot disclose their name) measured a 
>600% (!) performance increase after installing Prestoserve into their
>Sun 4/110 server.  600% is a bit unbelievable.  However, we expect 
>dramatic improvements to PC-NFS networks because PC applications
>typically write small, uncached blocks (e.g. 512 bytes).
>This means that for the PC-NFS client to write 8 Kbytes, the disk must
>perform 32 writes (or 48 writes to a large files) without Prestoserve.
>With Prestoserve the same task requires only 2 (or 3) asynchronous
>writes to occur.

Just a small clarification. PC-NFS will write min(tsize,8192) byte
blocks if requested by the application. Most apps still think in
diskette terms, however, and so relatively few take advantage of this.
We do cache writes, but the buffer cache is relatively tiny (because
everyone's beating on us about size). So, if you measure things by
	COPY C:BIGFILE G:
you won't see much of a win; with dBase or Lotus in the other hand.....

Geoff Arnold,                              Internet: geoff@East.Sun.COM
PCDS Group, Sun Microsystems Inc.
---------------------------------------------------------------------------
Most bizarre title of the week: "LAN Standards - Do you Need Them?" (in BYTE)