Path: utzoo!utgpu!news-server.csri.toronto.edu!rutgers!usc!sdd.hp.com!zaphod.mps.ohio-state.edu!rpi!crdgw1!crdos1!davidsen From: davidsen@crdos1.crd.ge.COM (Wm E Davidsen Jr) Newsgroups: comp.arch Subject: Re: CD-ROM documents (was Paperless Office) Message-ID: <2995@crdos1.crd.ge.COM> Date: 5 Dec 90 13:57:18 GMT References: <11191@pt.cs.cmu.edu> <00940487.15804140@KING.ENG.UMD.EDU> <28083@mimsy.umd.edu> <1990Nov29.162726.11411@mozart.amd.com> <11212@charm.UUCP> <2974@crdos1.crd.ge.COM> <1990Dec3.220850.18352@watdragon.waterloo.edu> Reply-To: davidsen@crdos1.crd.ge.com (bill davidsen) Organization: GE Corp R&D Center, Schenectady NY Lines: 25 In article aglew@crhc.uiuc.edu (Andy Glew) writes: | Why are CD-ROM seeks so slow? Is it related to the spiral tracking? That seems to be it. Also, the drives were designed to deliver continuous data, and seek was not a time critical issue for the musical usage. Finally, I believe these drives use constant bpi, so the rotational speed in radians per sec changes as the head moves. | Other optical disks (WORM and RW) have seeks on the order of 70ms. | Proximal seeks are faster. Do CD-ROMs have proximal seeks? I'm going to let someone else handle that, I believe the answer is yes, but don't speak with certainty. The question is really one of what the buyers want... would a 4x improvement help anything? I think not, it would still be a very slow drive for random access. Perhaps it's better to keep the drive cheap and use caching to get the effective speed up. If you know the start of sections you can have a "branch target cache" for CD-ROM, too. That still won't help with truely random access to any byte on the media, or with very small records. -- bill davidsen (davidsen@crdos1.crd.GE.COM -or- uunet!crdgw1!crdos1!davidsen) VMS is a text-only adventure game. If you win you can use unix. Brought to you by Super Global Mega Corp .com