![]() |
|
|
IBM Improves Its Capacity on Demand for iSeries Servers by Timothy Prickett Morgan While the dot-com bubble has wreaked all sorts of havoc with the economy in general and in the IT industry in particular, one good idea emerged from the chaos and is being embraced by server and storage suppliers--capacity on demand enabled by sophisticated Web-based controls, implemented by hardware vendors. As part of the iSeries Model 890 announcements, IBM has significantly improved its Capacity Upgrade on Demand offering for the iSeries. IBM's changes make CUoD a standard, free feature that is available on more iSeries machines.
With capacity on demand, an IT vendor ships extra processors or storage in a server; these resources can be activated with special keys, provided over the Internet by the vendor, when increasing workloads demand it. Customers do not have to take their machines offline, install extra processors or disks, and then reboot their servers. They just turn the key, the vendor kicks out an invoice, and they pay for the capacity they have added. This is much easier than buying a server and doing an upgrade, but capacity on demand does have one pesky shortcoming: Once you activate capacity, you own it and you must pay for it. You cannot turn processing or storage capacity on, use it for a while, and then go back to where you were. Once IBM and other vendors have sorted out grid-based Web services and transaction processing, this may be possible. IBM is also playing around with some other options, which I will explain in next week's issue. In addition to capacity on demand, IBM offers selected customers capacity standby, which means that additional servers and storage are kept on site, in case these machines are needed. A vendor cannot really do capacity on demand with uniprocessor, for instance, since there are no extra CPUs to activate when demand spikes. So, instead, most big server vendors offers customers the option of paying a slight premium to keep spare servers and storage on site, which can be plugged into their racks right away, not 14 days after an order is placed. This option is really only necessary for service providers and large enterprises with similarly expansive server infrastructure and big processing and storage needs. Since OS/400 V4R5, IBM has offered some capacity on demand features in the iSeries Model 840 server. To take advantage of CUoD, however, customers had to pay a 15 percent premium for processing capacity, compared with buying a server and doing traditional incremental upgrades. IBM does not like to build servers and keep spare processing capacity around unsold, but it is better than the other option, which is customers resisting processor and storage upgrades because the processor is so onerous. IBM has been offering S/390 and zSeries mainframes with the full processor complements in the box--in fact, it has little choice but to do so because of the way these machines are designed--and it had had great success with this model. My guess is that IBM has figured out that it takes a few financial lumps on the front end of a deal by putting the extra processors and storage in a zSeries or iSeries server, but the ease of upgrading tempts customers to buy more capacity in the long run than they might otherwise--particularly since they don't have to go through the arduous financial approval cycle if they negotiate for capacity increases as part of an original server purchase. Moreover, since the iSeries did not offer capacity on demand across the Model 8XX machines though most midrange and enterprise server vendors did, those machines did not, at least in this regard, look as attractive as the Unix and mainframe alternatives. Capacity on demand is becoming a tick mark on a deal, like RAID 5 storage or support for open standards has long since been. In April, IBM started offering its CUoD packaging and pricing on all Model 830, Model 840, and Model 890 servers with four or more processors. There is no premium for these CUoD features. All of the machines in this group of iSeries models are CUoD-enabled, but IBM is offering customers the choice of ordering machines with CUoD preconfigured from the get-go, to speed up the capacity on demand process and to track the popularity of this option. With the CUoD offering on the iSeries, customers buy a base machine and pay $41,000 per processor to activate those processors on Model 830 and Model 840 machines or $61,000 per processor on Model 890 machines. Customers have to pay to add interactive capacity on top of this, as usual. (To see a list of the possible iSeries configurations under the CUoD pricing and the cost of each configuration, click here.) Here's how the CUoD iSeries are configured, in terms of initial processors and standby processors:
Customers can activate some or all of the spare capacity in these machines for 14 days on a trial basis. No IPL is required in order to do this. The CUoD clock keeps track of the time when the CUoD capacity is activated and automatically decommissions it after the 14 days are up. Once a customer buys additional CUoD capacity in the iSeries server, the trial settings are reset and the machine is then available for another 14-day trial period in the future. The trial activation turns on all of the extra processors in the box, by the way, not just one or a few, and it is really intended for capacity planning purposes, to help customers figure out how many CPUs to activate. Once you decide to activate excess capacity, IBM posts a CUoD key, unique to your server, on a special Web site and also mails it to you so you can turn that capacity on. Customers with Model 720, 730, and 740 AS/400 machines, as well as those with Model 820 and Model 830 machines, with fewer than four processors, can upgrade to these new CUoD iSeries configurations. Next week, I'll tell you about other capacity on demand projects that IBM has cooking for the iSeries.
|
Editor Contact the Editors |
Last Updated: 5/19/02 Copyright © 1996-2008 Guild Companies, Inc. All Rights Reserved. |