EMC blew NetApp and others away with a CIFS benchmark in January. Now NetApp has returned that favour with interest, blowing EMC away in an NFS benchmark.
The two benchmarks are the CFS and NFS versions of the SPECsfs2008 file access benchmarks. What gives them special piquancy is that this is the first public performance match between two different approaches to flash memory use in storage arrays with the latest controller technology.
EMC has led with idea of using solid state drives (SSD) as a high-performance tier of storage in its VMAX and other arrays. NetApp favours the use of flash as a storage controller cache, its Flash Cache technology. Which is best? Here are are the numbers.
In January EMC's Celerra NS-G8 NAS gateway product front-ended a VMAX with 96 SSDs and scored 118,463 IOPS with an average latency of 1.92 msecs. NetApp's FAS3140 with a Flash Cache could only do 55,398 IOPS with 1.25 msec latency.
Celerra NS-G8 technology achieved 110,621 IOPS and 2.32 msecs latency in the NFS version of the benchmark. A VG8 Celerra with one less data mover engine and a Fibre Channel disk drive VMAX achieved a higher 135,521 IOPS in August this year.
Now NetApp has released benchmark numbers for its new FAS3270 and FAS6240 arrays, the latter with Flash Cache. The 3270 is rated at 101,183 IOPS, much better than the 3140 but failing to beat the Celerra NS-G8 SPECsfs2008 NFS numbers. The 6240 though, achieved 190,675 IOPS, 41 per cent faster than the Celerra VG8, and the second highest SPECsfs2008 NFS score to date.
HP leads the field with a 333,574 IOPS score achieved by a four-node BL860c cluster, using Itanium CPUs, not X86 ones.
What NetApp has done here is to show that, in file-access speed, its Flash Cache-using FAS arrays are superior to the SSD-using VMAX in the configurations tested and with current controller CPU resources. There seems to be no inherent limitation in using a storage controller flash cache instead of an SSD storage array tier. ®