Dell PowerVault MD1200 - Manual (Page 35)

Improving NFS Performance on HPC Clusters with Dell Fluid Cache for DAS
35
Appendix B: Benchmarks and tests
The
iozone
benchmark was used to measure sequential read and write throughput (MiB/sec) as well as
random read and write I/O operations per second (IOPS).
The
mdtest
benchmark was used to test metadata operation performance.
B.1. IOzone
You can download the
IOzone
from http://www.iozone.org/ . Version 3.4.08 was used for these tests
and installed the compute nodes.
The
IOzone
tests were run from 1-64 nodes in clustered mode. All tests were N-to-N, that is N clients
would read or write N independent files.
Between tests, the following procedure was followed to minimize cache effects:
• Unmount NFS share on clients.
• Stop the NFS service and unmount the XFS file system on the server.
• Mount XFS file system on the server and start the NFS service.
• Mount NFS Share on clients.
In addition for the cold cache tests described in Section 3.4, the disk managed by Dell Fluid Cache for
DAS was disabled and the SSDs that are part of the cache pool were disabled after a write operation.
DFC was re-configured prior to the read tests thus ensuring that all reads were from a cold-cache.
The following table describes the IOzone command line arguments.
IOzone Argument Description
-i 0 Write test
-i 1 Read test
-i 2 Random Access test
-+n No retest
-c Includes close in the timing calculations
-t Number of threads
-e Includes flush in the timing calculations
-r Records size
-s File size