Disk I/O Tuning is absolutely possible and in fact is the single biggest
opportunity we have in most cases.

DFSMSdfp options offer a great many choices to increase the performance with
system managed buffering, compression, stripes, and more.

Compression is a space utilization and performance enhancement with data
like SMF records, SVC dumps, and other data with easily compressed content.
I use compressed and striped on all the intermediate files dumped from the
SMF MANX datasets and it works great reduced processing time to about 1/4 of
what it was. Chuck Hopf has this and some other great tips in his MXG
presentation.  If you use MXG or don't it's still some great information on
how to handle processing lots of SMF data.  Visit
http://www.mxg.com/downloads.asp and scroll down to "MXG Simplified (2004)
Chuck Hopf" to download a copy. 

It sounds like you are still on ESCON channels. If you can spend some money
rather than buying more ESCON channels start trying to figure out how you
can migrate to FICON channels. 

The best I/O is of course no I/O so look at the opportunities to eliminate
stupid I/O with bad block sizes you can fix, repetitive PDS I/O you can
eliminate by using PDSE or LLA when you cannot change the program, etc.


        Best Regards,

                Sam Knutson, GEICO
                Performance and Availability Management
                mailto:[EMAIL PROTECTED]
                (office)  301.986.3574

"Think big, act bold, start simple, grow fast..."


-----Original Message-----
I'd say if you can go to 8 channels in width, without incurring an
unacceptable cost, go for it.  It's better redundancy, resiliency, and the
need for more data faster only increases over time so extra width is
generally a good thing.

Regards,

Gary Diehl

-----Original Message-----
From: IBM Mainframe Discussion List [mailto:[EMAIL PROTECTED] Behalf
Of Ted MacNEIL
Sent: Sunday, June 12, 2005 7:00 PM
To: [email protected]
Subject: Re: Disk I/O tuning still possible?


...
So, I ask,  is I/O tuning still possible, or even necessary? ...

<>
==================== 
This email/fax message is for the sole use of the intended recipient(s) and
may contain confidential and privileged information.  Any unauthorized
review, use, disclosure or distribution of this email/fax is prohibited.  If
you are not the intended recipient, please destroy all paper and electronic
copies of the original message. 

----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [EMAIL PROTECTED] with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Reply via email to