Return to BSD News archive
Path: euryale.cc.adfa.oz.au!newshost.anu.edu.au!harbinger.cc.monash.edu.au!news.rmit.EDU.AU!goanna.cs.rmit.EDU.AU!munnari.OZ.AU!news.ecn.uoknor.edu!paladin.american.edu!zombie.ncsc.mil!news.mathworks.com!newsfeed.internetmci.com!chi-news.cic.net!news.luc.edu!uchinews!netsrv2.spss.com!news.netins.net!news.dmacc.cc.ia.us!news.dmacc.cc.ia.us!not-for-mail
From: cfr@dmacc.cc.ia.us (Charles F. Randall)
Newsgroups: comp.unix.bsd.freebsd.misc
Subject: PCI SCSI Measured Performance (P133 w/Adaptec 2940)
Date: 8 Nov 1995 14:15:45 -0600
Organization: Des Moines Area Community College, Ankeny, Iowa (USA)
Lines: 31
Message-ID: <47r35h$r1q@Apollo.dmacc.cc.ia.us>
Reply-To: "Charles F. Randall" <crandall@dmacc.cc.ia.us>
NNTP-Posting-Host: apollo.dmacc.cc.ia.us
Using the 'bonnie' benchmark on a new P133 System (Intel Triton
chipset, 256K cache, 64 MB RAM, Adaptec 2940 PCI SCSI controller,
Seagate ST32430N [~5400 RPM, Fast SCSI-2] 2.1 GB HD) running the 11/4
snap of FreeBSD 2.1 I obtained the following numbers:
-------Sequential Output-------- ---Sequential Input-- --Random--
-Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU
flash 8 5112 97.8 23875 92.2 16031 95.4 5424 99.5 31373 100. 1176.6 35.1
flash 16 4916 99.2 7046 29.7 5699 42.6 5293 100. 23021 92.0 1250.6 40.4
flash 32 5032 98.4 5935 24.9 7090 50.7 5298 99.1 25013 99.4 1148.6 39.8
flash 64 4992 98.7 5524 23.7 1527 11.3 5064 96.4 5218 22.3 305.7 11.5
flash 128 4871 97.4 5278 23.3 1674 12.5 5031 95.8 5110 22.0 119.9 5.2
flash 256 4861 97.3 5057 21.6 1744 12.5 4988 95.2 5063 21.5 83.4 4.0
flash 512 4614 94.3 4694 20.6 1731 13.2 4726 90.3 4810 20.5 66.3 3.3
This shows ~5 MB/s block read throughput (only the file sizes >=128 MB
are worth discussing due to caching). I'm wondering if anyone has
numbers for a similar FreeBSD system configured with a Adaptec 2940W
and 5400 or 7100 RPM fast and wide disk (in particular, the Seagate
ST3243W and ST32550W).
I've seen the information from Geli Engineering
(http://www.geli.com/data/disk.perf.html), but this doesn't answer my
specific question.
-Randy
--
Charles F. Randall E-mail: crandall@dmacc.cc.ia.us
UNIX Systems Programmer Voice: (515) 965-7057 FAX: (515) 965-7305