Comment Re:A Traditional Holy War: ATA vs SCSI (Score 1) 180
First of all, as stated by some others, Windows has already had ATA 100 support. A friend of mine ordered and received an ABIT KA7 board a week ago that had 4 IDE channels on it including 2 ATA 100. Obviously there were windows drivers included with the board.
IBM's latest IDE release, the 75GXP, maxes out at 37MB/s sustained on the outer tracks of the drive which makes it the first IDE drive to surpass the theoretical limit of ATA33. It can be argued that Maxtor's Diamond Max 40+ at just over 30MB/s sustained was the first drive to exceed the real world limit of ATA33. For a comparison basis, the current SCSI speed champs, the Quantum Atlas 10k II and Seagate X15 weigh in at 40 and 41MB/s respectively which is not a significant speed increase.
Now I'm not implying that the IBM drive is anywhere near the performance of the 2 SCSI drives. 10k RPM and 15k RPM drives have significantly lower access time which will give them a distinct speed advantage, but the interface does not limit access time, it limits throughput.
SCSI 160 is bogus at this point, ignoring the fact you will need 4 of either of the above mentioned 2 drives to max the throughput. The problem is that it requires a 64bit PCI slot which no mainstream consumer level board carries. 32bit PCI which we all have has a theoretical limit of 133MB/s for the whole bus.
The release of USB2 will eliminate almost all of SCSI's external peripherals, except for highend hard drives.
Most current gen IDE drives do support command queuing. Whether or not it actually works is anyone's guess, as there is no way to actually test it as far as I know.
Your CDROM comment is about 2 years too late as well. The reason ATA CDROM drives used to kill system performance was due to a lack of DMA, not because IDE could only access one device per bus at a time. The advent of DMA has elminated this bottleneck.
IBM's latest IDE release, the 75GXP, maxes out at 37MB/s sustained on the outer tracks of the drive which makes it the first IDE drive to surpass the theoretical limit of ATA33. It can be argued that Maxtor's Diamond Max 40+ at just over 30MB/s sustained was the first drive to exceed the real world limit of ATA33. For a comparison basis, the current SCSI speed champs, the Quantum Atlas 10k II and Seagate X15 weigh in at 40 and 41MB/s respectively which is not a significant speed increase.
Now I'm not implying that the IBM drive is anywhere near the performance of the 2 SCSI drives. 10k RPM and 15k RPM drives have significantly lower access time which will give them a distinct speed advantage, but the interface does not limit access time, it limits throughput.
SCSI 160 is bogus at this point, ignoring the fact you will need 4 of either of the above mentioned 2 drives to max the throughput. The problem is that it requires a 64bit PCI slot which no mainstream consumer level board carries. 32bit PCI which we all have has a theoretical limit of 133MB/s for the whole bus.
The release of USB2 will eliminate almost all of SCSI's external peripherals, except for highend hard drives.
Most current gen IDE drives do support command queuing. Whether or not it actually works is anyone's guess, as there is no way to actually test it as far as I know.
Your CDROM comment is about 2 years too late as well. The reason ATA CDROM drives used to kill system performance was due to a lack of DMA, not because IDE could only access one device per bus at a time. The advent of DMA has elminated this bottleneck.
