The Standard Performance Evaluation Corp. (SPEC) has released the SPEC SFS® 2014 benchmark, a complete rewrite of the performance evaluation software used to measure the maximum sustainable throughput that a storage solution can deliver.
SPEC SFS committee members contributing to the new benchmark include EMC, Hitachi, Huawei, IBM, Microsoft, NetApp, Oracle and Seagate. Iozone.org provided the source code for the benchmark.
A fundamental shift
"The SPEC SFS 2014 benchmark represents a fundamental shift from measuring performance at the component level to measuring an end-to-end storage solution for specific applications," says Don Capps, SPEC SFS committee chair. "It provides holistic storage performance measurement within an extensible framework to accommodate future technological evolution."
Vendors will use the SPEC SFS 2014 benchmark to measure and improve server performance, for capacity planning, and to publish results for competitive positioning in the storage solutions market. IT managers will use the benchmark to validate server performance, plan capacity, and conduct internal performance studies.
Major new developments
The SPEC SFS 2014 benchmark incorporates five major developments:
· The migration from a component-level benchmark to a complete solution benchmark that measures performance of the entire storage configuration as it interacts with application-based workloads.
· An upgrade from one general-purpose workload to four different workloads representing specific application areas. Workloads now measure the number of simultaneous builds that can be done, the number of video streams that can be captured, the number of simultaneous databases that can be sustained, and the number of virtual desktops that can be maintained.
· Protocol independence, enabling the benchmark to run over any version of NFS or SMB/CIFS and on any clustered, object-oriented, local or other POSIX-compatible file system.
· A new methodology that permits vendors to demonstrate their unique storage accelerators.
· A new facility that allows users to create their own customized workloads for measuring storage system performance.
The new benchmark completely replaces the SPEC SFS 2008 benchmark and no legitimate comparisons can be made of results from the two different versions.