News

Reinventing storage virtualisation

Hu Yoshida, CTO of HDSThe initial approach to storage virtualisation, which has been around for years, was to address it in the storage-area network because the SAN sat between the storage and servers, and would cause the least disruption to these systems.

However, after nearly a decade, this approach has not taken off while server virtualisation has become widely accepted. What needs to be changed to make storage virtualisation as ubiquitous as server virtualisation?

Before the advent of server virtualisation, servers were configured for peak load but most of the time sat idling, resulting in average utilisation rates in the low teens. Many attempts were made to consolidate applications on servers to utilise idle cycles, but it was difficult to convert applications between different operating systems. The breakthrough came with the ability to virtualise the server so it could run any operating system, enabling applications to be consolidated without converting them.

The utilisation of storage systems is also low, typically in the 20% to 30% range. Storage gets stranded because application owners do not want to share storage and risk having other applications impact performance or availability. Since most open systems do not allow storage volumes to be expanded as the application generates more data, the common management practice is to simply overallocate storage capacity. While the declining cost of storage helps limit the cost of that practice, the operational cost for environmentals, change management, backup/recovery, technology refresh, and search and discovery escalates as storage capacity becomes increasingly oversubscribed and underutilised.

Storage for open systems is presented through logical unit numbers (LUN) or volumes that a storage system carves out of a RAID array group of physical disk drives and presents to the application. This process of creating LUNs and managing them is vendor unique. In order to virtualise storage from different storage systems, the difference in LUN or volume management must be masked.

Early attempts at storage virtualisation tried to address this problem by remapping heterogeneous LUNs to a common virtual LUN format for presentation to the host systems. But remapping introduced another layer of operational and management complexity, which inhibited the acceptance of the approach.

The breakthrough came with the ability to virtualise physical LUNs without the need to remap them by using a virtualisation technique based on storage control units. LUNs are configured in the external storage systems in their vendor-specific way. These LUNs are then connected to the virtualisation control unit over Fibre Channel ports as though they were connecting to a host server. Software in the control unit discovers the LUNs on the Fibre Channel port and presents them through the control unit's cache to an application server as if the LUNs were one of its own internal LUNs.

This approach does not remap the LUN, but enables LUNs from different systems to be managed with the common management tools of the storage virtualisation control unit. The LUN image is presented inside the control unit cache and inherits all the services that are available in that control unit, like copy, move and replicate. There is no need to reinvent these functions for the purposes of virtualisation. Lower-level storage can improve their native performance by connecting through the large high-performance cache of the virtualisation control unit.

This approach to storage virtualisation is simple to implement. It masks the complexity of managing heterogeneous storage systems and can aggregate the existing storage control unit services to enhance lower-level storage systems. Since virtualisation is done at the control unit level, it is not limited to SAN connections, and it provides storage virtualisation to any application server that connects through standard protocols like Fibre Channel, ESCON, FICON, network-attached storage (NAS), SAN, and direct attach.

Another feature that has been missing in early storage virtualisation approaches is partitioning. Partitioning guarantees users who share virtualised storage safe multitenancy and quality of service (QoS). In server virtualisation, time slicing is used to partition virtual servers and QoS can be managed by controlling the allocation of time slices.

In storage virtualisation, users who share a pool of storage resources must be guaranteed safe multitenancy, the guarantee that other users who share the same virtual storage resources will not be able to access their data nor impact performance. With a controller-based virtualisation approach, partitioning can be done through cache addressing and port priority processing. Partitioning can be done close to the physical storage, where it can be enforced.

The time is right for storage virtualisation, but only if storage virtualisation approaches can provide these basic capabilities:

— Use existing LUNs from heterogeneous storage systems and avoid the complexity of remapping LUNs to keep it simple

— Provide storage virtualisation for all storage users, whether they are direct attach, SAN, NAS, Fibre Channel, ESCON, FICON, etc.

— Aggregate storage services and make them available as reusable services to enhance lower-level storage systems.

— Provide users the ability to safely share resources without impacting their security, availability or performance requirements.

Storage virtualisation simplifies today's increasingly complex storage environment, allowing organisations to simplify the management of their infrastructures and consolidate storage systems from different vendors into one pool of storage. Additionally it allows organisations to mask the complexity of the underlying physical structure and greatly increase utilisation through the use of thin provisioning, the ability to provision storage capacity as it is actually used and provide it as a service to storage systems that do not have that capability. Storage virtualisation also brings about significant cost reductions and efficiencies by reducing the need for additional storage management tools, licences and administrators.

Storage virtualisation will deliver significant efficiencies, cost savings, power and cooling benefits, as well as greater agility in aligning storage infrastructure to business requirements.

Previous ArticleNext Article

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

GET TAHAWULTECH.COM IN YOUR INBOX

The free newsletter covering the top industry headlines