TCO
Reinvented
Copyright IBM Corporation 2009
14
Less human intervention and error
The XIV system further prevents system downtime by avoiding human error that leads to
equipment or system failure. Its self-management of volumes avoids the traditional need
for manual configuration planning
– a task that not only consumes much time, but often
increases the risk of data unavailability or data loss (DUDL) due to human errors made
when the plans are carried out. Its automatic self-healing, which returns the system to full
data redundancy upon hardware failure, avoids the need to rush to repair a failed
component, avoiding the kind of human error that can take place when parts are replaced
under pressure and at odd hours of the day and night. Furthermore, the XIV system calls
for maintenance tasks to be performed only when the system is fully redundant, thus
ensuring against data loss caused by human error during maintenance activities, such as
removal of a working disk rather than the faulty disk.
High availability and non-disruptive changes
In most enterprise storage systems, planned downtime for data migration and
maintenance is costly
– and a major inconvenience for the IT team and end users.
Minimizing downtime involves much planning. Multiple teams are involved to represent
the interests of end users, management, vendors, and service personnel.
Negotiating downtime for maintenance is another inevitable source of friction, as
maintenance must compete with other, higher priority demands. In traditional systems,
rolling out a business application may also require system downtime, with similar costs
and conflicts.
The IBM XIV Storage System is designed and implemented to grow, shrink, or change
without the need to reconfigure or shut down the system at any time. The administrative
headaches enumerated above have been eliminated through XIV's single-tier, constantly
balanced architecture.
The XIV architecture allows hardware components to be added to or removed from a new
or existing, operational XIV system without downtime. The XIV system provides an easy
and seamless non-disruptive procedure for component changes with little management
effort and no disruption. Upon any physical capacity change, the system automatically
redistributes volume data, maintaining full system equilibrium.
The XIV system’s built-in, redundant UPS units provide ongoing protection against data
loss while increasing reliability by avoiding the wear and tear to electronic and
electromechanical parts caused by inevitable data surges. By sparing its hardware parts
undue exposure to fluctuating power, the XIV system essentially lengthens the lifespan of
these parts, saving costs by bringing their shelf life closer to their theoretical lifespan.
Hot, online, intra- and inter-family code upgrades
The XIV system allows hot code upgrades and patches within and outside a code family.
This eliminates the need to schedule plant downtime, while ensuring ongoing access to
