home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.protocols.nfs
- Path: sparky!uunet!charon.amdahl.com!pacbell.com!mips!decwrl!sgi!rhyolite!vjs
- From: vjs@rhyolite.wpd.sgi.com (Vernon Schryver)
- Subject: Re: Free NFS Response Time Measurement Software
- Message-ID: <opjofug@rhyolite.wpd.sgi.com>
- Organization: Silicon Graphics, Inc. Mountain View, CA
- References: <1992Aug10.045921.13353@aim.com> <nxfyh!-@rpi.edu> <4-gyl#c@rpi.edu>
- Date: Wed, 19 Aug 1992 23:22:06 GMT
- Lines: 45
-
- In article <4-gyl#c@rpi.edu>, fitzgb@mml0.meche.rpi.edu (Brian Fitzgerald) writes:
- > Vernon Schryver writes:
- > >In article <nxfyh!-@rpi.edu>, fitzgb@mml0.meche.rpi.edu (Brian Fitzgerald) writes:
- > >> > FREE NFS SERVER RESPONSE TIME UTILITY
- > >> > *************************************
- > >>
- > >> ... cool program. For anyone interested, here's an example output of
- > >> the free demo they sent me. Good teaser for the sharpshooter.
- > >> ...
- > ...
- > >I'd be very surprised if the AIM test is very valuable. I could be
- > >wrong, of course, especially since I have never seen the AIM NFS test.
- > >
- > >I don't make this attack lightly, but the history of commerical
- > >benchmarks is not pretty. If you think the system vendors are scum,
- > ...
- >
- > Don't know much about NFS, or NFS performance monitoring and tuning
- > myself, but at least look over the brochure before dismissing it out of
- > hand.
-
- What kind of brochure contains enough technical information to evaluate
- something as complicated as a benchmark? Brochures are generally 2 or
- 4 pages loing and are no more than come-on's to get you to look at the
- product. It's not as if half a dozen numbers or a list of 6 features
- is enough to let you decide if a benchmark or a network file system is
- wonderful or junk.
-
-
- > More to the point, that NFS performance tuning is such a lucrative
- > business is a telling commentary on the reliability of NFS.
-
- If that were rephrased that, I might agree.
-
- "Reliability" is entirely separate from "speed". Or does the AIM
- benchmark measure reliability in addition to or instead of "speed"?
-
- In my opinion, the biggest single defect of the SPEC LADDIS effort is
- that measurements of "speed" have not been sufficently separated from
- considerations of "reliability". Both issues are of vital importance,
- but require very different techniques to quantify and are quantified in
- entirely different units.
-
-
- Vernon Schryver, vjs@sgi.com
-