home *** CD-ROM | disk | FTP | other *** search
- Xref: sparky comp.protocols.nfs:1948 comp.sys.sun.hardware:3533
- Path: sparky!uunet!iWarp.intel.com|inews!cadev5!mfineman
- From: mfineman@cadev5.intel.com ( Mark S. Fineman )
- Newsgroups: comp.protocols.nfs,comp.sys.sun.hardware
- Subject: Re: NFS I/O Ops/seconds
- Message-ID: <12470@inews.intel.com>
- Date: 24 Jul 92 22:25:44 GMT
- References: <1992Jul22.061146.15641@u.washington.edu> <l6r4uvINNf0p@exodus.Eng.Sun.COM>
- Sender: news@inews.intel.com
- Reply-To: mfineman@cadev5.UUCP ( Mark S. Fineman )
- Organization: Intel Corporation, Santa Clara, CA
- Lines: 25
-
- In article <l6r4uvINNf0p@exodus.Eng.Sun.COM> beepy@tabitha.Eng.Sun.COM (Brian Pawlowski) writes:
- >...
- >The number "300 NFS ops/s per ether" is a rule-of-thumb
- >(that's not quite the right word) maximum NFS ops/s as
- >generated by nhfsstone (Legato) or PRE-LADDIS (SPEC)
- >benchmark. I'll assume an equivalence of "NFS ops/s"
- >and "NFS I/O ops/s". [Is there a difference?]
-
- From what I've heard from various people at various vendors of
- file servers the PRE-LADDIS OP/S are about 2 times the
- nhfsstone OP/S for equivalent mixes.
-
- 150 or so would be fair for nhfsstone,
- 300 or so would be fair for PRE-LADDIS.
-
- 340 using PRE-LADDIS and the equivalent mix to the default
- mix in nhfsstone would be pretty good. I don't think
- you could get 340 using nhfssone and that mix.
-
- I haven't looked at the PRE-LADDIS stuff in detail so I
- can't say why the 2x difference.
- >
- (408) 765-4277; MS SC3-36, 2220 Mission College Blvd.,
- P.O. Box 58119, Santa Clara, CA 95052-8119
- mfineman@scdt.intel.com
-