For example, even though a database
application is assigned to the highest
tier, some data generated by this application may become less critical and not
used as much as before. Without sub-volume tiering, this older data would be
confined to the highest tier, taking up
space that could perhaps be better used
by other mission-critical applications.
By spreading a data volume over two
or more tiers, even older data originally
created by mission-critical applications
can be transferred to lower tiers to keep
space open for newer data coming into
the system.
Even with the many automated mechanisms included in automated storage tiering technology, a degree of user input can
be very useful to help enterprises maximize the benefits of automated storage
tiering. User input can be important in
several areas, including the timing of data
migration and the way in which volumes
are stored across multiple tiers with sub-volume tiering.
Many solutions conduct data migration according to schedules set by the
system itself. However, data migration requires computing resources, and
conducting data migration during business hours when applications are running at full speed may not be the best
option due to the potential performance
impact.
Ensuring that data migration occurs
during off-peak hours so that any impact
on applications can be avoided is critical,
and scheduling options with which users
can decide themselves when data migration is conducted are therefore very important.
The aforementioned sub-volume tiering can also benefit from user input. If a
user has the ability to specify the ratios
in which a volume is stored on different
tiers, sub-volume tiering can be fine-tuned
based on specific application characteristics. For example, if a user finds that a
large part of a data volume serves mission-critical operations, being able to allocate a
corresponding ratio of the data volume to
higher tiers can optimize resource utilization.
SSDs in Automated Storage Tiering
SSDs offer superior performance levels
compared to traditional HDDs and are particularly suited to IOPS-intensive (input/
output operations per second) applications. In the past, SSD prices were high to
the extent that very few enterprises were
able to afford them. However, SSD prices
have come down significantly. SSDs have
also received a boost from the HDD shortages, resulting from the 2011 flooding in
Thailand, making SSDs a viable option for
enterprises.
In traditional storage arrays without
automated storage tiering, SSDs tended to
be quickly filled with older data and were
not fully optimized for serving new data
generated by mission-critical applications.
Offloading data from SSDs to other storage media tended to be a time-consuming
process.
With automated storage tiering, which
incorporates automatic data migration,
older data is automatically offloaded from
SSD to other storage media so that valuable SSD capacity can be best used for
what SSDs do best. With sub-volume tiering, older data within a data volume can
be automatically moved to lower tiers
and thereby not occupy valuable space
on SSDs. By integrating only a minimal
number of SSDs in an automated storage
tiering architecture, enterprises can easily
meet the demand of their high-performance applications in a cost-effective way.
Benefits of Automated Storage
Tiering and SSDs
Enterprises run a wide array of applications to operate their businesses. The
service-level requirements of these applications can differ significantly, creating
the need for adaptive IT solutions that can
precisely meet these requirements without wasting resources and spending significant amounts of time on configuring
solutions.
For the storage part of IT operations,
automated storage tiering technology can
meet the aforementioned needs by creating different tiers that provide different
service levels and by integrating automatic
data migration processes that distribute
data among available storage resources in
the most efficient manner.
Furthermore, data storage performance
can be greatly enhanced by integrating
SSDs, which deliver performance levels
far beyond what SAS or nearline drives
are able to offer. Adopting SSDs in a
tiered architecture enables users to cost-efficiently meet the stringent demands of
mission-critical applications, as automatic
data migration ensures that SSD capacity
can be fully allocated to the high-performance applications for which SSDs are
designed.
As mentioned above, data is automatically migrated based on data usage
patterns. This ensures the most efficient
data distribution a storage pool and offers
excellent resource utilization.
Automated storage tiering can greatly
optimize storage performance while
reducing costs and increasing available
capacity. The long-term impact of these
improvements can be very significant and
greatly enhance ROI. In addition, if storage space can be more efficiently used
with the help of storage tiering, storage
systems acquired by enterprises will have
a longer lifespan. More efficient storage
utilization also reduces storage footprint
and lowers power consumption. Power
consumption is further reduced by the use
of SSDs in storage tiering architectures,
as these drives consume only limited
amounts of power when compared to other
drive types.
Storage tiering simplifies and reduces
management operations of storage systems. For traditional storage systems,
IT administrators have to manually configure data migration operations and
assign applications to specific storage
media. With storage tiering, many of
these operations are done automatically,
simplifying management, reducing time
administrators have to spend on storage
management, and lowering management
costs.
v
Galvin Chang is the associate director of
global marketing for Infortrend Tech. Inc.
Chang has more than 15 years of work
experience in enterprise I T solution consulting and marketing, and received his master
of science degree in computer science, as well as an MBA,
from National Taiwan University. He is interested in sharing
his experience in data center planning and enterprise IT
solutions.
