NFS Blocksize Optimizations

I decided to redo the NFS setup I previously had on my ol’ Itanium2 machine.

Standard disclaimer: These tests were run with purposeful cache prevention techniques so that caching would not make all subsequent tests faster, yada yada, I am not retarded.

Specs:
2x 1.5GHz Itanium2 processors
10GB ECC DDR
3x 74GB 15k RPM U320 SCSI drives in RAID5
Gigabit ethernet

I am somewhat confused as to why the NFS write performance is so appalling, while the read performance approaches the theoretical maximums of a gigabit ethernet connection.
Any advice on improving write performance over NFS would be much appreciated.
Graph of NFS throughput vs blocksize

(Graph is here if you’re reading this post without images)

1 Comment

Clean LondonNovember 20th, 2009 at 9:04 am

Thanks for posting this!

Leave a comment

Your comment

wp_footer();