Amdahl had an internal tool that did this.
With the introduction of caching control units in the mid '80's, Amdahl
developed a marketing tool acronym'd (application of the Fairchild verbing
rule) CSIM -- Cache Simulator. The intended use of CSIM was to size caches
in 6880 and 6100 control units and later NVS in 6100's based on GTF CCW
trace data. If I recall correctly, a CSIM utility took a snapshot of the
subject volume(s) VTOC during tracing and this is what CSIM used to convert
seek addresses to dataset names. CSIM allowed the user to "rerun" the CCW
trace data through it with different cache configurations and CSIM
approximated the results.
The marketing people usually delivered a CSIM install tape to a site and
worked with a customer person to do the monitoring and simulation.
One of the CSIM reports accurately resembled an RMF Direct Access Device
Activity Report -- with the exception that rather than producing one line
per DASD volume, this report contained one line *per dataset*. This allowed
the user to "drill down" from the RMF DASD Activity report to the dataset
level.
As an SE and later a consultant, I most often used CSIM to identify *hot
datasets* where RMF was not able go deeper than the volume level.
For those who were not there at the time -- in the 80's, when cache and
fast-write were first introduced, caches were tiny compared to current
technology, and NVS sizes were even smaller -- much smaller. Memory for
cache and NVS was quite expensive. Caching and fast-write were, for a short
time, specified on a dataset by dataset basis.
Many internal marketing tools have corners cut in development (well I guess
some companies even cut corners on their products!) and have very rough user
interfaces, but not CSIM, which had all the attributes, look and feel of a
flagship product. It was not a product, but was a tool for internal people
to use -- although it was probably left with some customers.
I suppose this tool could have been used to model the performance of
different cache algorithms but I doubt it was ever used in that mode.
I distinctly remember the name of the CSIM developer and I am hesitant to
post his name here because I never met him in person (only exchanged a few
emails) and don't know his current status. As far as I can tell he has
never posted here -- sorry Bill. The CSIM developer was once active in CMG
and may still be.
Larry Chenevert
----- Original Message -----
From: "Bill Fairchild" <bi...@mainstar.com>
Newsgroups: bit.listserv.ibm-main
To: <IBM-MAIN@bama.ua.edu>
Sent: Monday, May 03, 2010 12:27 PM
Subject: Re: How to analyze a volume's access by dataset
I never worked with GTFPARS, and only now vaguely remember it, thanks to
your mentioning it.
After CA bought UCCEL in 1987 and redundanted me [1], I lost all contact
with FastDASD's goings-on. So I don't know about its functional
replacement by Astex which occurred with CA's subsequent acquisition of
Legent.
"It used to have a pretty good LRU cache modeler built in." Assuming that
"it" means FastDASD, then I don't remember the upper limit on the
supported cache size. Supporting that function was one of my all-time
favorite projects. And thanks for the honorable mention.
Bill Fairchild
[Most nouns and adjectives can easily be verbed, as in "The operator
onlined the volume".]
Software Developer
Rocket Software
275 Grove Street * Newton, MA 02466-2272 * USA
Tel: +1.617.614.4503 * Mobile: +1.508.341.1715
Email: bi...@mainstar.com
Web: www.rocketsoftware.com
-----Original Message-----
From: IBM Mainframe Discussion List [mailto:ibm-m...@bama.ua.edu] On
Behalf Of Ron Hawkins
Sent: Monday, May 03, 2010 11:21 AM
To: IBM-MAIN@bama.ua.edu
Subject: Re: How to analyze a volume's access by dataset
Bill,
Cast your mind back to GTFPARS. This IBM FDP would build seek histograms
using IEHLIST VTOC Listings as input to map the extents of the datasets on
the volume.
CA-ASTEX does some very good IO level analysis. As with FASTDASD, CA-ASTEX
intercepts every IO. I think that this replaced FASTDASD after CA bought
Legent.
It used to have a pretty good LRU cache modeler built in. I wonder if it
still works and supports 512GB or more of cache?
Ron
----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
