In a message dated 4/13/2007 2:35:18 P.M. Central Daylight Time, [EMAIL PROTECTED] writes: >>I have heard that a CE has to replace at least 1 disk per month on some of these boxes. (DMX3000 - EMC, DS8000 - IBM, etc....) >That appears to be awfully frequent. Lynn Wheeler posted this comment: "here is some MTBF numbers of some disks _http://www.digit-life.com/articles2/storage/maxtor15k2.html_ (http://www.digit-life.com/articles2/storage/maxtor15k2.html) in the million-plus hrs. " The average "month" has 730.5 hours [1]. Assume the MTTF for one disk is 1,000,000 hours. Assume the DASD controller (aka storage processor) has 1,369 disks in its array (I picked this weird number to make the math easier). Then in one month the entire array logs 1,000,000 disk-hours (730.5 multiplied by 1,369). In an average month, this array will have one disk failure. And 1,369 disks is a small array (at least for EMC, with which I am most familiar). Or if your DASD farm has 250 controllers each of which has 4,096 disks in its array, then you have over 1,000,000 disks in your farmplex, and you will be having one disk failure every hour somewhere on the farm. Do the math. One failure per month in the entire farm is to be expected, but one per month within a single box is indeed awfully frequent. Bill Fairchild Plainfield, IL [1] The average year has 365.25 days. There are 12 months in one year. Thus an average month has 30.4375 days. Each day has 24 hours. Thus an average month has 730.5 hours. "The correct use of language must begin at the very top of government.... The ruler must correct his own behavior for the people to follow his leadership." [Confucius]
************************************** See what's free at http://www.aol.com. ---------------------------------------------------------------------- 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
