On Sat, 3 Nov 2001 01:19, Jason Lim wrote: > Hum... if the Highpoint chipsets are merely IDE controllers... whats the > advantage to using them over the regular plain vanilla generic IDE > controller cards? > > Don't they offload ANY work from the processor at ALL? They have to have > SOME sort of benefit... otherwise, why market them as RAID controllers?
For RAID-0 the only work is to do a translation: drive = blocknum % 2; drive_blocknum = blocknum / 2; For RAID-1 the only work is to decide which drive has a shorter queue for reading and to write the same data to both drives for writing, and of course the rebuild on reboot. It's not so much work. The benefit of hardware RAID (including BIOS software RAID) for RAID-0 and RAID-1 is to enable booting from the RAID without any hassles. RAID-5 is another issue though. But then you have to consider that Linux software RAID kills the performance of most hardware RAID controllers. Run an Athlon 800 with two IDE drives in RAID-1 and expect 2-4 times the performance for bulk IO that an entry level Mylex RAID controller with Ultra2 SCSI 10K rpm drives. I expect that a top-end Mylex controller will perform well (but who can afford one of them?). -- http://www.coker.com.au/bonnie++/ Bonnie++ hard drive benchmark http://www.coker.com.au/postal/ Postal SMTP/POP benchmark http://www.coker.com.au/projects.html Projects I am working on http://www.coker.com.au/~russell/ My home page
