There’s no doubt that from a storage perspective cloud computing introduces a lot of additional complexity into the data center environment. To help IT organizations better understand the nuances of cloud storage, Load DynamiX, a provider of a storage I/O testing platform, has added the ability to run tests against NFSv4.1, CEPH, Amazon S3, and OpenStack Swift cloud storage along with support for Fiber Channel over Ethernet (FCoE).
Len Rosenthal, vice president of marketing for Load Dynamix, says more often than not most IT organizations wind up over provisioning storage because they don’t have a lot of visibility into actual I/O performance inside their data center environments.
“Storage today on average makes up 40 percent of the IT budget,” says Rosenthal. “We enable organizations to cut costs by simulating storage I/O performance against production data.”
The Load DynamiX platform consists of a dedicated appliance to run the test and the modules needed to create them. Priced starting at $100,000, Rosenthal says the Load DynamiX platform is designed to take a lot of the trial and error now associated with deploying storage systems, with an eye towards reducing the amount of physical space needed for storage systems inside the data center.
In terms of OpenStack Support, Load DynamiX currently supports both the Swift and Cinder storage protocols. Later this year, Load DynamiX will add support for the Manila file-based protocol once it is finalized by the OpenStack community.
Originally developed to enable storage vendors to test their offerings, Rosenthal says Load DynamiX is now being embraced by IT organizations that need to address I/O storage bottlenecks across block, file, and object-based storage systems.
To simplify that process in complex data center environment, Load DynamiX in this release is also making available a Composite Workload Editor facility that can be used to create multi-threaded I/O patterns across multi-tiered storage infrastructure and access protocols.
While vendors generally rate their storage systems in terms of maximum throughput, the number of IOPs a storage system can support tends to vary widely by application environment. Making things more challenging is that in the era of software-defined storage, many IT organizations have started to embrace white box storage systems that can be configured with any number of solid-state and magnetic storage systems.
Optimizing and then validating each storage system configuration across any number of types of application workloads represents a major investment in both time and money that most IT organizations would probably prefer to be able to apply somewhere else.