Testing maximum adrdssu backup speed
Hello, I am going to test maximum backup speed using adrdssu to virutal tape storage, I want to memory/virtual storage as source and is it possible to create a temp dataset in VIO, then write it to the virtual tape storage via adrdssu? regards Victor -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: Testing maximum adrdssu backup speed
What version of z/OS are you running? What are the control cards you are currently using for your DFDSS dump? Lizette -Original Message- From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On Behalf Of Victor Zhang Sent: Friday, August 02, 2013 1:23 AM To: IBM-MAIN@LISTSERV.UA.EDU Subject: Testing maximum adrdssu backup speed Hello, I am going to test maximum backup speed using adrdssu to virutal tape storage, I want to memory/virtual storage as source and is it possible to create a temp dataset in VIO, then write it to the virtual tape storage via adrdssu? regards Victor -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: Testing maximum adrdssu backup speed
I'm not sure this test is valid. The maximum speed will be dictated by the channel speed to the VTL. The second factor will be the speed at which the data can be offloaded to tape (back store). The third factor is how quickly ADRDSSU can read the data off disk. By trying to read from memory you've eliminated this piece entirely. Most shops run backup jobs in parallel to maximize channel utilization. Why not backup a half-dozen volumes concurrently and measure the results? Bob Shannon Rocket Software -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: Testing maximum adrdssu backup speed
Victor, Rather than trying to look at the raw speed of the virtual tape you want to test in you environment, why not take a business case approach? Take a common and reliable (performane wise) back up using your current method, whatever that current method. Then, changing nothing other than using the virtual tape as the output media, run the same backup again. The difference in backup time - all other factors being equal, could reasonably be attributed to the change in your tape. HTH, Linda Sent from my iPhone On Aug 2, 2013, at 5:17 AM, Bob Shannon bshan...@rocketsoftware.com wrote: I'm not sure this test is valid. The maximum speed will be dictated by the channel speed to the VTL. The second factor will be the speed at which the data can be offloaded to tape (back store). The third factor is how quickly ADRDSSU can read the data off disk. By trying to read from memory you've eliminated this piece entirely. Most shops run backup jobs in parallel to maximize channel utilization. Why not backup a half-dozen volumes concurrently and measure the results? Bob Shannon Rocket Software -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
