home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!munnari.oz.au!spool.mu.edu!news.cs.indiana.edu!umn.edu!lynx!zia.aoc.nrao.edu!rmilner
- From: rmilner@zia.aoc.nrao.edu (Ruth Milner)
- Newsgroups: comp.protocols.nfs
- Subject: Re: NFS I/O Ops/seconds
- Message-ID: <1992Jul22.185748.852@zia.aoc.nrao.edu>
- Date: 22 Jul 92 18:57:48 GMT
- Article-I.D.: zia.1992Jul22.185748.852
- References: <1992Jul22.061146.15641@u.washington.edu> <64081@hydra.gatech.EDU>
- Reply-To: rmilner@zia.aoc.nrao.edu (Ruth Milner)
- Distribution: usa
- Organization: National Radio Astronomy Observatory, Socorro NM
- Lines: 34
-
- In article <64081@hydra.gatech.EDU> gt1111a@prism.gatech.EDU (Vincent Fox) writes:
- >In <1992Jul22.061146.15641@u.washington.edu> kint@rio.engr.washington.edu (Rick Kint) writes:
- >> We're buying a Sun to serve as an NFS server in one of our departments.
- >>The Sun rep commented that a typical Ethernet allows 300 NFS ops per second,
- >>so if you're on a single wire any server bandwidth beyond that is wasted.
- >
- >Hmmm. I'm a bit skeptical. All NFS operations are not created equal.
- >A write obviously takes a lot longer to complete than a getattr. I've seen
- >claims up to 1,000 or better. Auspex claims this I feel certain.
-
- Not on a single Ethernet, they don't. You need 4 Ethernets to get these kinds
- of figures.
-
- >>typical mix of operations; since a getattr is presumably quicker than a write
-
- By a factor of about 15.
-
- >>how useful are these numbers anyway?
- >
- >Not much. Sun reps usually know less than you do.
-
- Yes, but the Sun reps don't run the benchmarks (thank god). In this case the
- 300 ops/sec/Ethernet maximum is about right for the default mix nhfsstone uses
- (which is actually a pretty typical mix).
-
- Quite honestly, I think 60 Suns on a single unsubnetted, unbridged Ethernet
- is really pushing it. You won't get 300 NFS ops/sec out of a server that can't
- get that much of the bandwidth, even if "all" it is providing is user files.
- One of our users recently generated 4 *gigabytes* of NFS traffic between the
- server and his workstation in a 36-hour period, and that was sure not the OS
- or the application executables!
- --
- Ruth Milner NRAO/VLA Socorro NM
- Computing Division Head rmilner@zia.aoc.nrao.edu
-