The Top Ten Storage Trends for 2011

osc.edu

As shipped storage capacities continue to grow at a compounded annual growth rate of nearly 50%, enterprises are now under great pressure than ever before to transform their data centres from an infrastructure-oriented operation to an agile service-oriented operation that delivers exactly the right service levels for each business unit.

Hu Yoshida

Faced with such considerable challenge, many data centre managers may wonder how they can build such a dynamic and service-driven data centre.

Hubert Yoshida, renowned though-leader and Chief Technology Officer of Hitachi Data Systems, shares his forecasts and insights on key trends within the storage industry.

These predictions affirm the importance of new technologies that are already paving the way for the creation of next-generation data centres.

Yoshida is also Chairman of the Scientific Advisory Board for the Data Storage Institute of the Government of Singapore.

1. Acceptance of storage virtualization and dynamic provisioning will accelerate as they become the foundation for cloud operations and for dynamic, high availability data centres.

Yoshida forecasts that the benefits of storage virtualization will become even greater in the year ahead. Yoshida believes that storage virtualization together with Dynamic Provisioning will become the solid foundation for cloud infrastructure and dynamic data centres. According to Yoshida, their acceptance will increase swiftly in 2011. This is because storage virtualization provides the ability to non-disruptively migrate from one array to another and eliminate the costly down time required to refresh storage systems.

This is complemented by the fact that dynamic provisioning enables storage to be provisioned in a matter of minutes, simplifying performance tuning with automatic wide striping, and enabling on-demand capacity for a truly agile storage infrastructure.

2. Closer integration of server and storage virtualization will be required to increase the adoption of data centre virtualization.

Yoshida predicts that integration between servers and storage virtualization will become closer, and the convergence of servers, storage and network infrastructure will significantly increase in 2011. Hypervisors like VMware are providing APIs to off load formatting of storage, movement of data, and cluster consistency locking to storage systems so that server virtualization can achieve greater scalability. While this requires upgrades to storage systems microcode, external storage can participate if they are virtualized behind a Virtual Storage Platform.

3. Virtual tiering will be adopted for data life cycle management.

Next-generation data centres must not only be virtualized, they must also be intelligent and agile in their ability to manage and provision data. Yoshida believes Virtual Tiering or Dynamic Tiering can address this and will soon be popular in the market. Virtual Tiering has the ability to assign a volume to a pool of storage containing multiple tiers of cost and performance, and has the intelligence to move parts of that volume to different tiers based on access counts and activity. This automates and optimizes data access performance and storage capacity throughout the entire data life cycle.

4. Serial Attached SCSI (SAS) will be adopted for increased availability and performance in enterprise storage systems.

Thanks to its increased availability and performance in enterprise storage, Yoshida predicts that the acceptance of SAS will become more widespread. Indeed, SAS has a faster speed than FC Arbitrated Loop with point-to-point access, is dual-ported, and is compatible with large capacity SATA which is single-ported.

5. SSD will be accepted as the solution for higher performance and lower costs in a virtual tiered configuration.

Yoshida also predicts the adoption of SSD will provide higher performance and lower costs in a virtual tiered configuration. This is because 80% or more of a volume is usually inactive. Only a small amount of SSDs need to be in Tier 1 to serve the active parts of a volume, meaning the majority of the volume can reside on lower-cost SAS or SATA drives.

This multi-tiered approach to storage using a combination of SSD, SAS or SATA drives can provide 4 to 5 times the IOPs at a lower cost than a single tier of high performance FC or SAS disks

6. Small Form Factor Drives (SFF) will become prevalent for their power and cooling efficiencies.

One of the main obstacles for data centre transformation is how to balance costs and efficiency. IT organizations are primarily concerned with how an IT purchase will help reduce operating costs, improve business processes, and mitigate risk. Yoshida predicts Small Form Factor Drives (SFF) will become prevalent for their power and cooling efficiencies. SFFs can dramatically reduce power and cooling costs, while also enabling an additional saving of floor space. SFF 2.5 inch disk require about half the power of traditional 3.5 inch disks.

7. Cloud will be accepted as a valid infrastructure model.

According to Yoshida, One of the key objectives in data centre transformation is to provide the right IT service level to each application or business unit, particularly in terms of availability, performance and recovery. Yoshida added that Cloud is increasingly considered to be a valid infrastructure for facilitating the management tools and orchestration layers that enable end-to-end transparency, thus ensuring service level objectives and chargeback.

8. Convergence in data centres will begin to take off.

As Cloud computing is accepted as a valid infrastructure model, convergence in data centres will begin to take off, with convergence of server, storage and network infrastructure making it simpler and faster to deploy applications.

9. Applications will require increased application transparency in a storage virtualization or cloud infrastructure.

As Cloud is seen as valid infrastructure for facilitating end-to-end transparency, Yoshida predicts this increased application transparency in storage virtualization or cloud infrastructure will become more and more important not only in 2011.

10. Remote managed services will be provided to offload lower-level monitoring, alerting, reporting, and management tasks that are currently limiting many IT operations from embracing new technologies.

Yoshida also pinpoints the need to give the data centre operations people time to be trained and do the planning to implement these new technologies. One way to do this is to offload some of their day to day tasks to a Service Operations Centre. Through the use of remote management tools a SOC can leverage its skills across multiple installations to provide monitoring, reporting, and provisioning so that the operations staff can concentrate on driving a higher and quicker return on technology investments.

-futuregov.com