Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > alt.folklore.computers > #213469
| From | Dan Espen <dan1espen@gmail.com> |
|---|---|
| Newsgroups | alt.folklore.computers |
| Subject | Re: S/360 model 20 |
| Date | 2020-08-30 15:51 -0400 |
| Organization | A noiseless patient Spider |
| Message-ID | <rih00v$455$1@dont-email.me> (permalink) |
| References | <rif9s1$s59$1@dont-email.me> <rigrfd$qq3$1@gal.iecc.com> |
John Levine <johnl@taugh.com> writes: > In article <rif9s1$s59$1@dont-email.me>, > Dan Espen <dan1espen@gmail.com> wrote: >> Main Storage consists of 4,096; 8,192; 12,288; and >> 16,384 positions of magnetic core storage. >> >>I'm guessing the 32K is accurate and was implemented in later models. > > Models 1,2,3,4 were limited to 16K, model 5 which was different > internally and somewhat faster could go to 32. I never saw a model 5. > >>It's interesting that the 2311 disk which was also sold for other S/360 >>models has fixed sector sizes on the Model 20. >> >>I always thought the variable block sizes on S/360 was a mistake. >>It put too much complexity into user space. A pity IBM didn't sectorize >>all of it's disk on all of it's models from the beginning. > > I think it was all part of the expensive memory mindset when the 360 > was designed. With CKD disks, the ISAM in-memory index only needed one > entry per track, or even one per cylinder and the channel program took > care of finding the right individual record. ... I started to write about how you could do something similar with sectors, but you're absolutely right. For the channel to search for the data in the sector it would have to understand a lot about the file to know what to match. > With the 20's disks, the > track index told it which track a record was on, but it had to read > each sector to find the right one, taking a 25ms disk revolution each > time. > > Less than a decade later VSAM KSDS used B-trees which use fixed block > sizes and put the index in the blocks themselves, on the assumption > that the computer will cache recently used blocks. I found the variable block sizes a real problem. If you pick a really large block size for the benefit of one program, all the other programs reading that file must use the same block size. Which could be a problem if a program is storage constrained. Back in the 14xx days one program might read one sector at a time, another might attempt to read the whole cylinder. It looks like IBM has tried to adapt using 4K blocks with VSAM and PDS/E. -- Dan Espen
Back to alt.folklore.computers | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
S/360 model 20 Dan Espen <dan1espen@gmail.com> - 2020-08-30 00:27 -0400
Re: S/360 model 20 John Levine <johnl@taugh.com> - 2020-08-30 18:34 +0000
Re: S/360 model 20 Dan Espen <dan1espen@gmail.com> - 2020-08-30 15:51 -0400
Re: modern computers and S/360 model 20 John Levine <johnl@taugh.com> - 2020-08-30 22:07 +0000
Re: modern computers and S/360 model 20 Dan Espen <dan1espen@gmail.com> - 2020-08-30 18:32 -0400
Re: modern computers and S/360 model 20 J. Clarke <jclarke.873638@gmail.com> - 2020-08-30 18:38 -0400
Re: modern computers and S/360 model 20 Dan Espen <dan1espen@gmail.com> - 2020-08-30 20:37 -0400
Re: modern computers and S/360 model 20 Bob Eager <news0073@eager.cx> - 2020-08-31 08:54 +0000
Re: paging, modern computers and S/360 model 20 John Levine <johnl@taugh.com> - 2020-08-31 16:36 +0000
Re: paging, modern computers and S/360 model 20 scott@slp53.sl.home (Scott Lurndal) - 2020-08-31 16:57 +0000
Re: paging, modern computers and S/360 model 20 Bob Eager <news0073@eager.cx> - 2020-08-31 17:21 +0000
Re: paging, modern computers and S/360 model 20 scott@slp53.sl.home (Scott Lurndal) - 2020-08-31 18:10 +0000
Re: paging, modern computers and S/360 model 20 Quadibloc <jsavard@ecn.ab.ca> - 2020-08-31 16:10 -0700
Re: paging, modern computers and S/360 model 20 Bob Eager <news0073@eager.cx> - 2020-09-01 14:14 +0000
Re: paging, modern computers and S/360 model 20 Bill Findlay <findlaybill@blueyonder.co.uk> - 2020-09-01 17:41 +0100
Re: paging, modern computers and S/360 model 20 Bob Eager <news0073@eager.cx> - 2020-09-02 08:34 +0000
Re: modern computers and S/360 model 20 usenet@only.tnx (Questor) - 2020-09-02 07:04 +0000
Re: S/360 model 20 Charlie Gibbs <cgibbs@kltpzyxm.invalid> - 2020-09-01 04:40 +0000
Re: S/360 model 20 Quadibloc <jsavard@ecn.ab.ca> - 2020-08-31 22:10 -0700
Re: S/360 model 20 Charlie Gibbs <cgibbs@kltpzyxm.invalid> - 2020-09-01 19:09 +0000
Re: S/360 model 20 Dan Espen <dan1espen@gmail.com> - 2020-09-01 15:41 -0400
Re: S/360 model 20 Jon Elson <elson@pico-systems.com> - 2020-09-03 10:44 -0500
Re: S/360 model 20 Dan Espen <dan1espen@gmail.com> - 2020-09-03 11:51 -0400
Re: S/360 model 20 Niklas Karlsson <anksil@yahoo.se> - 2020-09-03 16:41 +0000
Re: S/360 model 20 J. Clarke <jclarke.873638@gmail.com> - 2020-09-03 12:46 -0400
Re: S/360 model 20 drb@ihatespam.msu.edu (Dennis Boone) - 2020-09-03 13:32 -0500
Re: S/360 model 20 Dan Espen <dan1espen@gmail.com> - 2020-09-03 14:44 -0400
Re: staying up, S/360 model 20 John Levine <johnl@taugh.com> - 2020-09-03 22:28 +0000
Re: S/360 model 20 hancock4@bbs.cpcn.com - 2020-09-03 11:09 -0700
Re: S/360 model 20 Peter Flass <peter_flass@yahoo.com> - 2020-09-03 11:48 -0700
Re: S/360 model 20 Charlie Gibbs <cgibbs@kltpzyxm.invalid> - 2020-09-03 19:49 +0000
Re: S/360 model 20 Dave Garland <dave.garland@wizinfo.com> - 2020-09-04 10:06 -0500
Re: S/360 model 20 Charlie Gibbs <cgibbs@kltpzyxm.invalid> - 2020-09-04 16:13 +0000
Re: S/360 model 20 J. Clarke <jclarke.873638@gmail.com> - 2020-09-03 17:30 -0400
Re: S/360 model 20 John Levine <johnl@taugh.com> - 2020-09-03 22:55 +0000
Re: S/360 model 20 Robin Vowels <robin.vowels@gmail.com> - 2020-09-03 19:44 -0700
Re: S/360 model 20 Quadibloc <jsavard@ecn.ab.ca> - 2020-09-04 23:27 -0700
Re: S/360 model 20 hancock4@bbs.cpcn.com - 2020-09-01 11:03 -0700
Re: S/360 model 20 Jon Elson <elson@pico-systems.com> - 2020-09-03 10:42 -0500
Re: S/360 model 20 hancock4@bbs.cpcn.com - 2020-09-03 11:12 -0700
Re: S/360 model 20 Peter Flass <peter_flass@yahoo.com> - 2020-09-03 11:48 -0700
Re: S/360 model 20 Charlie Gibbs <cgibbs@kltpzyxm.invalid> - 2020-09-03 19:49 +0000
Re: S/360 model 20 hancock4@bbs.cpcn.com - 2020-09-10 11:37 -0700
Re: S/360 model 20 Charlie Gibbs <cgibbs@kltpzyxm.invalid> - 2020-09-10 23:34 +0000
Re: S/360 model 20 Peter Flass <peter_flass@yahoo.com> - 2020-09-10 18:06 -0700
Re: S/360 model 20 Charlie Gibbs <cgibbs@kltpzyxm.invalid> - 2020-09-11 20:41 +0000
Re: S/360 model 20 Peter Flass <peter_flass@yahoo.com> - 2020-09-11 16:21 -0700
Re: S/360 model 20 Terry Kennedy <terry-groups@glaver.org> - 2020-09-11 17:26 -0700
Re: S/360 model 20 Bob Eager <news0073@eager.cx> - 2020-09-12 09:30 +0000
Re: S/360 model 20 Quadibloc <jsavard@ecn.ab.ca> - 2020-09-10 20:39 -0700
Re: S/360 model 20 Quadibloc <jsavard@ecn.ab.ca> - 2020-09-10 20:46 -0700
Re: S/360 model 20 J. Clarke <jclarke.873638@gmail.com> - 2020-09-03 17:41 -0400
Re: S/360 model 20 hancock4@bbs.cpcn.com - 2020-09-01 11:00 -0700
Re: S/360 model 20 Quadibloc <jsavard@ecn.ab.ca> - 2020-09-01 17:05 -0700
Re: S/360 model 20 J. Clarke <jclarke.873638@gmail.com> - 2020-09-01 20:25 -0400
Re: S/360 model 20 Quadibloc <jsavard@ecn.ab.ca> - 2020-09-10 20:44 -0700
Re: S/360 model 20 J. Clarke <jclarke.873638@gmail.com> - 2020-09-11 00:30 -0400
Re: S/360 model 20 Peter Flass <peter_flass@yahoo.com> - 2020-09-11 06:48 -0700
Re: S/360 model 20 drb@ihatespam.msu.edu (Dennis Boone) - 2020-09-11 11:02 -0500
Re: S/360 model 20 Peter Flass <peter_flass@yahoo.com> - 2020-09-11 11:18 -0700
Re: S/360 model 20 "Kerr-Mudd,John" <notsaying@127.0.0.1> - 2020-10-03 10:29 +0000
Re: S/360 model 20 Peter Flass <peter_flass@yahoo.com> - 2020-10-03 07:38 -0700
Re: S/360 model 20 scott@slp53.sl.home (Scott Lurndal) - 2020-10-03 16:17 +0000
Re: S/360 model 20 drb@ihatespam.msu.edu (Dennis Boone) - 2020-10-04 11:24 -0500
Re: S/360 model 20 Charlie Gibbs <cgibbs@kltpzyxm.invalid> - 2020-09-02 00:50 +0000
Re: S/360 model 20 Jon Elson <elson@pico-systems.com> - 2020-09-03 10:51 -0500
csiph-web