Performance and
capacity
Advances in data storage and technology make it practical
and economical to store quantities of data that would have been unthinkable a
few years ago. For example, when USAA began scanning documents and mail back in
the 1980s, it was considered to be a major technological breakthrough in storage
cost. Today, a consortium of banks has formed a check-imaging archive to store
large numbers of documents efficiently, hence further slashing storage costs and
crossing another threshold in this rapidly developing area.
This reduction in storage cost is further made possible by the
emergence of new systems such as autonomic computing. An autonomic system is an
entire system - devices, networks, file systems, data objects, and software -
that manages itself and achieves business objectives. Such a system uses
detailed knowledge of its components, current status, ultimate capacity, the
extent of its 'owned' resources, those it can borrow or lend, those that can be
shared or should be isolated to govern itself.
The storage cost of this highly efficient system is 20–80 per cent
of typical total server purchase cost, where storage personnel cost has
historically been approximately three times the purchase cost of storage. The
autonomic manager can perform tasks today done by an administrator in storage
management to achieve overall objectives. This includes reports on availability
and performance, moving data for performance, provision capacity, backups and
restoration and commissioning new hardware, thus improving availability and
response time and data integrity.
Advances in the field of shared IT resources are further
improving the performance of an organization's technological infrastructure. One
of the latest developments in this field is the emergence of grid computing,
defined by Platform Computing as 'the coordinated, transparent and secure
sharing of IT resources across geographically distributed sites'. Grid computing
will give companies the ability to share computing resources such as software
applications, data, storage and computing power both internally over the
intranet and externally over the Internet. By tapping into the enormous reserves
of under-used computer power, organizations can deliver cost-effective computer
resources on demand. It is estimated that only 5 per cent of the capacity of PCs
and 20 per cent of servers deployed by enterprises are used. By using the idea
of grid computing - which is taking under-utilized IT resources, such as PCs,
workstations and storage devices, adding a management software layer that can
pool, manage and allocate these resources
dynamically, and then enabling users to call upon these shared resources as they
need them - this usage level can be raised to 80 or 90 per cent, which will help
companies increase revenues, save costs and improve their time to develop and
market products.