Date: Mon, 25 May 1998 09:40:43 +0930 From: Greg Lehey <grog@lemis.com> To: dyson@FreeBSD.ORG, dwhite@resnet.uoregon.edu Cc: lfloyd@sonic.net, freebsd-questions@FreeBSD.ORG Subject: Re: Compatibility with Ultra IDE drives? Message-ID: <19980525094043.M15604@freebie.lemis.com> In-Reply-To: <199805240800.DAA00892@dyson.iquest.net>; from John S. Dyson on Sun, May 24, 1998 at 03:00:52AM -0500 References: <Pine.BSF.3.96.980523235634.9142b-100000@gdi.uoregon.edu> <199805240800.DAA00892@dyson.iquest.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sun, 24 May 1998 at 3:00:52 -0500, John S. Dyson wrote: > Doug White said: >> >> 2.2.5 doesn't, so you get standard old IDE without any UltraDMA >> improvement. -CURRENT can grok UltraDMA and can give you the (supposed) >> performance boost. >> > Given you have a very fast machine to start with (like a fast P5 or > faster), bus-master DMA does help alot. There is a very noticable > difference in responsiveness of the system under load with the > DMA. I actually wasn't convinced until I mistakenly built a system > without the DMA, and noticed that it was somehow "slow." I was recently rather astonished with the performance of modern IDE drives, and spent some time comparing the time for a 'make world' on a K6/233 with 96 MB of memory. Here are the results for an IBM DORS SCSI drive with an Adaptec 2940 host adaptor, and an IBM DHEA IDE drive with normal and Ultra DMA: Disk Elapsed User System DORS 126m22.811s 66m2.051s 16m28.411s DHEA 124m54.116s 65m3.465s 18m50.257s DHEA/Ultra 111m21.743s 66m24.344s 18m37.329s Greg -- See complete headers for address and phone numbers finger grog@lemis.com for PGP public key To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19980525094043.M15604>