Path: utzoo!utgpu!news-server.csri.toronto.edu!clyde.concordia.ca!uunet!decwrl!elroy.jpl.nasa.gov!ames!dftsrv!mimsy!chris From: chris@mimsy.umd.edu (Chris Torek) Newsgroups: comp.arch Subject: drive rpm (was Data Storage density questions) Message-ID: <25901@mimsy.umd.edu> Date: 5 Aug 90 22:41:47 GMT References: <2684@network.ucsd.edu> <25891@bellcore.bellcore.com> Organization: U of Maryland, Dept. of Computer Science, Coll. Pk., MD 20742 Lines: 22 In article <25891@bellcore.bellcore.com> mo@messy.bellcore.com (Michael O'Dell) writes: >the newest CDC drives (Imprimis come Seagate) spin at 5400 rpm and >position noticably faster. good for almost a 50% throughput >increase on random traffic.... Yes, a faster spin helps quite a bit, considering that the track to track seek times are running on the order of 1 ms while the half-way-around-the-disk rotational times are running on the order of 10 ms, at 3600 rpm. (`On the order of' here means `rounded and extremely approximate'.) (The so-called `average seek time' of a disk is relatively unimportant to modern file systems in many cases, since actual average seeks are not 1/3 of the length of the disk. [This is the usual metric for `average seek time'.] Track-to-track seek time and rotational delays are far more important for single-file access under 4BSD Unix, for instance.) -- In-Real-Life: Chris Torek, Univ of MD Comp Sci Dept (+1 301 454 7163) Domain: chris@cs.umd.edu Path: uunet!mimsy!chris (New campus phone system, active sometime soon: +1 301 405 2750)