home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!cs.utexas.edu!sdd.hp.com!zaphod.mps.ohio-state.edu!rpi!psinntp!psinntp!vaxsar.vassar.edu!biwine
- From: biwine@vaxsar.vassar.edu
- Newsgroups: comp.os.vms
- Subject: Measuring performance
- Message-ID: <1992Jul23.140159.429@vaxsar.vassar.edu>
- Date: 23 Jul 92 14:01:59 +1000
- Organization: Vassar College
- Lines: 25
-
- I am interested in comparing the real-world performance of various
- VMS, Ultrix and non-DEC systems. I have seen published ratings for
- CPU and I/O, but these do not tell the entire story. For
- example, a MV3100 is rated at 2.7 VUPS, but would not support as many
- users as a VAX 6220, because the bus and I/O capacities are very
- different. IBM RS/6000 machines have fantastic Specmarks, Mips and
- Mflops, but I have read reports that they not do nearly as well in
- multi-user support as these numbers would suggest.
-
- What I would like to see is some sort of a meaningful rating system.
- For example, that a machine configured with this much memory, this
- many disks on this many I/O channels can support this number of
- database users, or this number of All-in-one users, or some mix of
- both.
-
- Is this sort of information available? Are TPC-A ratings a good way
- of comparing real-world performance? Are there independent companies
- that do this sort of rating?
-
- Your comments are welcome.
-
- Bill Wine
- System Manager
- Vassar College
- biwine@vassar.edu
-