Hal, I don't this is a hard and fast rule to go by, especially as response time can vary for many reasons that have nothing to do with the storage. Personally I feel that throughput is equally as important. Response time can increase 200-300% as throughput increases and it will have no discernable effect on your application as long as throughput is maintained.
Because cache hits and misses for reads make for extreme differences in response time that are not reflected in any RMF number. You can be getting <1ms response time and be blissfully unaware that you have a sibling pend problem for 5% of your IO. If response time is your only metric then I'd suggest looking for ways to report response time in a far more granular manner. Use the Type 42 subtype 6 records, consider distributing disconnect time to the cache misses and remote copy writes only, or start using the internal response time and usage data that all the DASD vendors provide. When you have a 1000 disk drives and 2000 volumes doing 400K IOPS from 4 LPARS to a USP-V, Response time from RMF alone can prove to be somewhat inadequate. Ron > -----Original Message----- > From: IBM Mainframe Discussion List [mailto:ibm-m...@bama.ua.edu] On Behalf Of > Hal Merritt > Sent: Wednesday, August 25, 2010 7:32 AM > To: IBM-MAIN@bama.ua.edu > Subject: Re: [IBM-MAIN] Test DASD performance tools > > The bottom line in DASD performance is response time. RMF reports that. > > How well a given vendor performs in a given situation would be difficult to > simulate and therefore the results may not be very meaningful. > > > -----Original Message----- > From: IBM Mainframe Discussion List [mailto:ibm-m...@bama.ua.edu] On Behalf Of > Tommy Tsui > Sent: Wednesday, August 25, 2010 9:16 AM > To: IBM-MAIN@bama.ua.edu > Subject: Test DASD performance tools > > Hi all, > Our shop needs to compare the EMC & IBM DASD performance. Is there any > free tools to test the DASD performance? such as online CICS/Batch > performance? > > Many thanks > > > NOTICE: This electronic mail message and any files transmitted with it are > intended > exclusively for the individual or entity to which it is addressed. The > message, > together with any attachment, may contain confidential and/or privileged > information. > Any unauthorized review, use, printing, saving, copying, disclosure or > distribution > is strictly prohibited. If you have received this message in error, please > immediately advise the sender by reply email and delete all copies. > > ---------------------------------------------------------------------- > 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
