I don't understand the uniqueness argument! >One example that refutes the "DASD is Generic" argument is a multi-Petabyte >customer that recently made their MIM Control file Cache Resident, which >almost doubled the IO rate even though it was already 100% cache hit.
Our MIM control dataset, and later GRS, was/is in the CF. We gave up on disk years ago. >This had an immediate positive impact on the throughput of the Sysplexes that >used MIM. This is a feature that EMC and HDS offer, but IBM doesn't, which makes the "no major technological difference" argument seem a bit odd to me. If the dataset in the CF, what does this feature mean? >SSD drives are another example. It could be somewhat futile to install these puppies if the read miss performance of your storage can't crack 50K IOPS, or they fire hose the back-end paths shared with regular disk drives. I haven't had the privilidge of working with SSD since the old STK 4301's. >It would be stretching things to say that all vendor technology is equal in this regard. If you say so. >Even features like PAV are not equal. The feature is not as important as response. >Have we forgotten when one vendor only supported eight Aliases. >Or what about customers that find sixteen FlashCopy V2 sessions on a volume stopped some copies being converted to host based IO, or FlashCopy interoperability means they can change from HDS to IBM, and back again without changing a single piece of JCL. The important point is response. NOT specific details. >Or how about the small shop that wants to share midrange storage with UNIX and z/OS, but wants it connected to FICON so they can keep on using FDRINSTANT to make volume and dataset copies. >Are you trying to say that Mainframe Virtualization is an generic feature offered by all vendors? Since I never discussed it, I can't answer a 'have you stopped beating your wife' question. >It seems to me that you are lucky to work in a site that has no unique or >esoteric requirements. What I said was, with all features equal, price is the driving factor. If one vendor doesn't have the feature I need, that one is not in the mix. What I never said, was that exluding required features was on the table. >That is certainly rare for medium and large DASD farms today. I'm certain that we envy you the simplicity of a site where "There is NO one feature, other than cost, that will make me pick one over the other." If I need the feature, I will, of course, require it. But, I have never seen a feature that drives one vendor over another. Maybe (most likely) I was unclear, but what I meant was, I have never been in a situation where a specific feature was so needed that it was a deal breaker. But, then (as typing this) I do recall the AMDAHL 6100 fiasco. I've worked for very conservative organisations that, by the time a feature has been required, the big three have had it available. And, for example, we haven't needed mainframe virtualisation, yet. The bottom line: If the features are 'equal', regardless of implementation details, cost is the over-riding feature. - I'm a SuperHero with neither powers, nor motivation! Kimota! ---------------------------------------------------------------------- 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
