(I don't know if this has been discussed before - tried to search the archives, but either there's nothing there, or I chose bad search arguments).
Back in the days of old (when sysprogs were bold, etc.) we�d spend many happy(?) hours tinkering with the physical placement of files in order to tune the I/O response time of the DASD farm. Then along came RAID arrays. As I understand things, data on a RAID array is broken up and splattered across several separate devices. Isn't file placement therefore a moot point? Further consideration (based on one single informal technical chat with an STC engineer): in today�s RAID boxes, all your 3390 disks are emulated on a lesser number of physical SCSI disks, and you have no say in the matter of which 3390 "areas" are mixed with other 3390s � the software inside the box decides on that when you create a new 3390 volume. How can you tune response times in such a situation? Yet further: Becuase of the enormous amount of storage available in these RAID arrays, many companies hold _all_ their disk space requirements within an array. Thus, you get disk space for the mainframe, the mid-range systems and sometimes even the PCs all mixed up together on a physical disk. A possible result of this is that disk being "hit" by several disparate systems with consequent differences in performance reporting data structure, accuracy and timing synchronization. So, I ask, is I/O tuning still possible, or even necessary? John ---------------------------------------------------------------------- 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
