Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!usc!ucsd!pacbell.com!decwrl!shelby!portia.stanford.edu!dhinds From: dhinds@portia.Stanford.EDU (David Hinds) Newsgroups: comp.arch Subject: Re: Data Storage density questions Message-ID: <1990Jul31.233407.11825@portia.Stanford.EDU> Date: 31 Jul 90 23:34:07 GMT References: <2684@network.ucsd.edu> <1990Jul31.200043.5189@nlm.nih.gov> Organization: AIR, Stanford University Lines: 24 In article <1990Jul31.200043.5189@nlm.nih.gov> states@tech.NLM.NIH.GOV (David States) writes: >While on the subject, why do disks spin so slowly? At 3600 RPM, you >have an intrinsic delay of up to 16 msec waiting for the platter to >come around, no matter how fast the heads move. You could increase the >speed of a 5 1/4" disk by an order of magnitude without worrying about >g forces. Aerodynamic heating becomes a problem at higher velocities, >but you don't hit the speed of sound until ~120,000 RPM. As far as the disk head is concerned, wouldn't increasing RPM's be the same as increasing recording density? So, for a given speed of drive electronics, you can either push density or RPM's. Either gives you a higher transfer rate. Pushing density gives you a higher capacity, while pushing RPM's gives you a higher random access speed. Sector slewing can practically eliminate the rotational delay for sequential access. So, if you are designing for sequential access speed, it is best to maximize density and leave RPM's alone, until you reach the limiting density of the recording medium. Some drives do spin at different speeds. I think I saw somewhere that IBM is putting 5400 RPM drives in its RS6000 machines. And my PC has an 80MB drive that is essentially a 40MB drive spinning at 2700 RPM and using RLL encoding to achieve the higher density. -David Hinds dhinds@popserver.stanford.edu