Date: Thu, 14 Dec 2000 01:54:39 +0100 From: Brad Knowles <blk@skynet.be> To: "Jason C. Wells" <jcwells@nwlink.com> Cc: chat@FreeBSD.ORG, Greg Lehey <grog@lemis.com> Subject: Re: Very interesting benchmarking results... Message-ID: <v04220807b65dca4fca73@[10.0.1.2]> In-Reply-To: <Pine.SOL.3.96.1001213160828.87C-100000@utah> References: <Pine.SOL.3.96.1001213160828.87C-100000@utah>
next in thread | previous in thread | raw e-mail | index | archive | help
At 4:27 PM -0800 2000/12/13, Jason C. Wells wrote: > I thought hardware raid was supposed to be much better. These graphs show > this raid card as a fractional performer. The difference is so staggering > I had to double check that your graphs were referenced to zero to make > sure you hadn't played any graphing tricks. Theoretically, hardware RAID is more reliable than software RAID. And none of this benchmarking takes into account the CPU utilization, etc... required for vinum to do it's job. The rawio tools have methods to generate that kind of information, but I haven't taken advantage of that in my benchmarks. > Aside from the better numbers that vinum produces, I am surprised that the > raid card performance remained flat for an increased number of processes. > I am no expert, but that looks like something just ain't right with the > card. Shouldn't throughput approach the aggregate throughput of the SCSI > channel(s)? I'm reserving all other comments until such time as I get feedback from some other people and I can get a better feeling as to what these results really mean. -- These are my opinions -- not to be taken as official Skynet policy ====================================================================== Brad Knowles, <blk@skynet.be> || Belgacom Skynet SA/NV Systems Architect, Mail/News/FTP/Proxy Admin || Rue Colonel Bourg, 124 Phone/Fax: +32-2-706.13.11/12.49 || B-1140 Brussels http://www.skynet.be || Belgium "They that can give up essential liberty to obtain a little temporary safety deserve neither liberty nor safety." -Benjamin Franklin, Historical Review of Pennsylvania. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-chat" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?v04220807b65dca4fca73>