> So ATA66 is about as fast as your hardware will exploit with two > drives on the cable. ATA100 reduces bus contention for "both rives > ready simultaneously" Okay..okay.. This is VERY Off-track.. but maybe you guys can shed some light.. I just bought a CD-writer (52x24x52 attached as master on 2nd IDE channel - UDMA mode 2) and I've got 2 HD attached to the primary IDE channel. Both drives are UDMA5 on ATA100 (on a ATA133 capable M/B) Burning disc using Nero can't get me higher than 24x! The reason it's giving me is..transfer rate from source data is too slow. (I'm burning from a 120GB 8MB cache Master Drive. Slave is a 20GB 2MB Cache) So.. what's up.. Running a disk transfer rate test saw my 120GB transferring at ~40MB/s. So..what's up. Does the above holds true??? Cheers, Mun Heng, Ow H/M Engineering Western Digital M'sia DID : 03-7870 5168 -----Original Message----- From: Jesse Keating [mailto:hosting@xxxxxxxxxxxxxxx] Sent: Friday, September 26, 2003 12:24 AM To: shrike-list@xxxxxxxxxx Subject: Re: SATA problems On Thursday 25 September 2003 09:05, Brian T. Brunner wrote: > SATA vs ATA150 vs ATA133 vs ATA100 vs ATA66.... phooey! > > The real limiter is the data transfer rate at the disk head. > > Generally Speaking (IIRC), 7200 RPM drives move data to and from the > platters at around ATA33 speed. > > So ATA66 is about as fast as your hardware will exploit with two > drives on the cable. ATA100 reduces bus contention for "both rives > ready simultaneously" about as low as it will go; ergo ATA5000 is not > faster than ATA100 in measurable effect. > > Buy more RAM... that'll speed you up more than going ATA5000 instead > of ATA100. Sounds good on paper, but when you get better performance out of an ATA133 drive than an ATA100 drive, same chassis, came controller, same drive MANUFACTURER, same RPM, same cache, just a different ATA speed, then it goes to show you, whats on paper doesn't always match whats in the field. Being able to pull data from the on-disk cache and get it through the ATA bus faster _does_ make a difference in real world performance. -- Jesse Keating RHCE MCSE http://geek.j2solutions.net Mondo DevTeam (http://www.microwerks.net/~hugo/) Was I helpful? Let others know: http://svcs.affero.net/rm.php?r=jkeating -- Shrike-list mailing list Shrike-list@xxxxxxxxxx https://www.redhat.com/mailman/listinfo/shrike-list -- Shrike-list mailing list Shrike-list@xxxxxxxxxx https://www.redhat.com/mailman/listinfo/shrike-list
