Hu's Blog

Server and desktop virtualization will increase the need for enterprises to scale up storage systems as physical server demands increase. Initial installations of server virtualization were done to consolidate non-critical application servers, which were installed on lower cost modular, dual controller, storage systems. As multiple servers were virtualized and consolidated onto a single physical server, their storage was also consolidated onto a single modular storage system connected behind the physical server. The I/O workload that used to be distributed on file systems across multiple modular storage systems is now consolidated onto one virtual file system and one modular storage system.

Initially this worked since the servers and storage that were consolidated in the beginning were running at low utilization, but as more and more servers are consolidated onto the same virtual platform, modular storage systems will begin to break. Dual controller, modular storage systems were designed to support direct attached workstations, and were not designed to support large scale, virtualization servers. Virtualization servers require enterprise storage systems, which were designed from the beginning to support the scale up demands of mainframe virtualization. Enterprise storage systems are designed to integrate the power of multiple controllers through a global cache as the virtual servers demand more storage resources.

Today’s multi-core Unix and x86 servers are as powerful as mainframes were just a few years ago, and are running virtualization through multiple partitions or a hypervisor, which dramatically increases the load on storage systems. In addition, FC SANs are increasing the consolidation of more and more servers onto a storage platform with higher transmission speeds of eight Gbps. Applications are beginning to offload more workload onto the storage systems through APIs, client providers, and plugins. All this additional workload will demand that storage can scale up beyond the capabilities of a dual controller, modular storage system.

As we increase the number of virtual machines or partitions in a virtual server, we are also “putting more eggs in one basket”. This means there is a higher demand for availability from the storage system. A dual controller system is not a high availability system. When one controller is down for scheduled or unscheduled maintenance, the other controller is usually stopped in order to avoid data loss, or performance suffers as one controller tries to do the work of two. An enterprise storage system with multiple controllers and a global cache can continue to operate in the event that one or even two controllers is taken offline.

If you have already invested in modular storage for your virtual server environment and are experiencing outages and slowdowns, you don’t need to replace your investment in modular storage. You can keep your modular storage and front end it with an enterprise storage virtualization platform like VSP in order to get the scale up performance and high availability of an enterprise storage system.

For Hu’s other 2012 trends, visit this bit.ly bundle: http://bitly.com/vXGP2T