IOPS benchmark
Hi All, We are now evluating the IOPS for some DASD (3390-3 and 3390-9). Because the DASD are shared by all LPARs in the sysplex. As per RMF IO activity, there are a few DASDs which were accessed 2000 per second at a specific time. We are afraid there may be hotpot problem occur in the near future. Is there any reference which clearly states the benchmark or thredhold for the IBM DASD (3390-3 and 3390-9)? The DASD IOPS may be 300 at a specific time in the sysplex. Is it acceptable or do we need to tune that DASD? Looking forward to hearing from you. Thanks! -- 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
Re: IOPS benchmark
In modern DASD, 3390-3, 3390-9, 3390-whatever are just logical constructs. More, hopefully most all of the I/O looks like it is directed to a volume, but actually is satisfied in cache or buffers and never really touches the physical disk. -Original Message- From: IBM Mainframe Discussion List [mailto:IBM-MAIN@bama.ua.edu] On Behalf Of Alex Wang Sent: Tuesday, August 09, 2011 5:02 AM To: IBM-MAIN@bama.ua.edu Subject: IOPS benchmark Hi All, We are now evluating the IOPS for some DASD (3390-3 and 3390-9). Because the DASD are shared by all LPARs in the sysplex. As per RMF IO activity, there are a few DASDs which were accessed 2000 per second at a specific time. We are afraid there may be hotpot problem occur in the near future. Is there any reference which clearly states the benchmark or thredhold for the IBM DASD (3390-3 and 3390-9)? The DASD IOPS may be 300 at a specific time in the sysplex. Is it acceptable or do we need to tune that DASD? Looking forward to hearing from you. Thanks! -- 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 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
Re: IOPS benchmark
Hi Alex, You should combine the DASD response time with I/O rate when you check your DASD's performance. And see how is the I/O intensity during your batch window.. On Wed, Aug 10, 2011 at 5:39 AM, Hal Merritt wrote: > In modern DASD, 3390-3, 3390-9, 3390-whatever are just logical constructs. > > More, hopefully most all of the I/O looks like it is directed to a volume, > but actually is satisfied in cache or buffers and never really touches the > physical disk. > > > > > > > > -Original Message- > From: IBM Mainframe Discussion List [mailto:IBM-MAIN@bama.ua.edu] On > Behalf Of Alex Wang > Sent: Tuesday, August 09, 2011 5:02 AM > To: IBM-MAIN@bama.ua.edu > Subject: IOPS benchmark > > Hi All, > > We are now evluating the IOPS for some DASD (3390-3 and 3390-9). Because > the DASD are shared by all LPARs in the sysplex. As per RMF IO activity, > there are a few DASDs which were accessed 2000 per second at a specific > time. We are afraid there may be hotpot problem occur in the near future. > > Is there any reference which clearly states the benchmark or thredhold for > the IBM DASD (3390-3 and 3390-9)? The DASD IOPS may be 300 at a specific > time in the sysplex. Is it acceptable or do we need to tune that DASD? > > Looking forward to hearing from you. Thanks! > > -- > 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 > 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 > -- Cobe Xu Best Regards --- z/OS Performance & Capacity Analyst z/OS System Programmer Email: cob...@gmail.com --- -- 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