> On Thu, 8 Aug 1996, Douglas Bates wrote: > > the combination of the IDE controller in the Triton chipset with an > > EIDE drive is as fast as fast, wide SCSI. > > SCSI's advantage is that it can handle multiple outstanding requests at > the same time, while EIDE has to wait for one to complete before it can > start a second one.
SCSI can handle multiple request to _different_ devices on the same SCSI bus, but I don't think you can have multiple requests to the same device. EIDE, on the other hand, can only have one device active at a given time. Considering that you can only have two devices, this isn't too bad, but if one of them is something slow like a tape drive or a CDROM, it will really slow down a hard disk. > with a a few meg of cache > on the drive. (This allows the drive to start being clever and resort > the queue'd I/O's for fastest return. E.g. If the head is on cylinder > 7, and it gets a read request for cylinder 2000, and cylinder 500, it > will do the 500 on the way to the one for 2000.) This is known as elevator seeking and should be done at the OS level. The order that data is written out is very important for data reliability, and for this reason, I don't think any hard disk change the order of the writes. The really big problem that IDE had that EIDE fixed was that IDE couldn't do DMA, so the OS had to move each byte from the disk drive. On the other hand, SCSI's command overhead can be significant, often adding up to 10ms to the simplest command. I would expect that if you only have one disk per EIDE controller, you will significantly outperform a single SCSI bus with two disks on it. -wayne
