Date: Tue, 14 Apr 1998 16:52:46 -0700 (PDT) From: Simon Shapiro <shimon@simon-shapiro.org> To: bh@epigram.com Cc: freebsd-scsi@FreeBSD.ORG Subject: RE: RAID performance/benchmarking Message-ID: <XFMail.980414165246.shimon@simon-shapiro.org> In-Reply-To: <3533BBE4.DF09519@epigram.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On 14-Apr-98 Brandon Huey wrote: > Dell PowerEdge 4200/300, 96MB RAM, 3 9GB Seagate Barracuda SCA drives > DPT PM3334UW w/64MB cache > > FreeBSD 2.2.6 > DPT kernel options: DPTOPT > DPT_MEASURE_PERFORMANCE > DPT_FREELIST_IS_STACK > > i created an array group with the dos util 'dptmgr' from default > settings. > > using IOZONE and Bonnie, i create a 128MB file for read/write > benchmarking. > > i am aware of the performance implications of RAID-5, but I am getting > about 2MByte/sec max write transfer rate compared with 19MByte/sec on > reads. > > For a pci ultrawide controller, are these figures suspect? What kind of > write performance hit should one expect w/RAID-5 ? Depends on array size, type of controller, amount of cache, type of access. RAID arrays are not a good benefit for sequential access. RAID-5 are evel less of a match. I perfrom ALL my tests on random seeks, 2GB data sets or better. 128MB dataset will have in the vicinity of 50% cache hit rate on a full controller. Expect something between 21 and 6 MB/Sec for RAID-5 WRITE perfromace. configuration dependant. ---------- Sincerely Yours, Simon Shapiro Shimon@Simon-Shapiro.ORG Voice: 503.799.2313 To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-scsi" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?XFMail.980414165246.shimon>