IBM Spectrum Virtualize Introduces Data Reduction Pools
IBM Spectrum Virtualize software is at the heart of IBM SAN Volume Controller, IBM Storwize family, and IBM FlashSystem V9000 and available to run on x86 servers. It brings sophisticated software-defined storage capability to these systems.
IBM Spectrum Virtualize has long been known for bringing new function, greater efficiency, improved data availability, and common capability to new and existing storage, including over 440 different storage systems from IBM and others. In this way, it simplifies operation, adds value to existing investments, and extends their useful life, all of which reduce your CAPEX and OPEX across you storage environment. For example, adding compression to existing storage can increase its effective capacity up to 5X, reducing your capital expenditures. Similarly, using IBM Spectrum Virtualize to add data-at-rest encryption capability across storage from multiple vendors makes it much easier to secure your data and reduce the OPEX associated with having different encryption technologies from your different vendors.
Over the years, IBM has added more and more data efficiency capabilities to IBM Spectrum Virtualize, such as thin provisioning and compression, while also adding automated tiering, and cloud capability. As we look forward to even more new function in the future, the time has come to build a new foundation for storage within IBM Spectrum Virtualize.
IBM Spectrum Virtualize 8.1.2 introduces new data reduction pools, which use an entirely new architecture for storing data. Data reduction pools have several immediate advantages:
â€¢ Up to 3x better throughput for compressed volumes
â€¢ Support for using compression on all volumes in a system (up to 10,000 per system)
Together, these improvements make it possible to use compression for more volumes and more workloads, which increases your cost savings in your storage estate.
Data reduction pools also support server environments that use the SCSI UNMAP command. This command is used by software to indicate storage capacity that it is no longer using. Data reduction pools release this capacity and return it to the available capacity pool.
New data reduction pools are completely transparent to applications. IBM Spectrum Virtualize systems support both traditional and data reduction pools and support nondisruptive data movement to data reduction pools by using volume mirroring.
Data reduction pools use a log-structured design, a proven technology that is designed to accommodate data whose size may change (such as with compression or other data reduction technologies) or which may be deleted (such as when a server releases space).
There are many advantages to data reduction pools, including:
â€¢ Designed to be highly scalable to support hardware with more cores and more memory
â€¢ Tightly integrated compression shares available cores with other processes for greater efficiency
â€¢ Optimization for flash storage through conversion of random write I/Os into larger sequential writes
â€¢ No limit on the number of compressed volumes enables greater use of compression (up to 5X as many volumes) and so more compression benefit and reduced storage cost
â€¢ Up to 3x better throughput for compressed data, enabling its use with a wider range of data types.
â€¢ Ability to release and reuse storage in response to server needs, reducing overall storage required
â€¢ Designed for future data reduction technologies
â€¢ Support for mirrored non-volatile metadata significantly improves failover/failback times
â€¢ Separation of metadata and user data improves cache effectiveness
“Storage efficiency has always been central to the value of SAN Volume Controller,” said Jeff Kato, Senior Analyst and Consultant, Taneja Group. “The development of data reduction pools provides a new technical foundation for IBM to deliver further efficiency capabilities and improve scalability of the system.”
IBM Spectrum Virtualize delivers innovative storage capability in IBM storage systems and also for over 440 different storage systems from IBM and others. With data reduction pools, IBM Spectrum Virtualize is building a sound foundation for innovation in the future and helps ensure today you can better control and manage your costs on IBM storage and across heterogenous storage environments from different vendors.
For complete information about the IBM Storage announcements on February 20, see our blog.