Prior to actually testing the hardware it's nearly impossible to know
what your performance level is going to be as there are way too many
On the OSS nodes the obdfilter-survey performance should be very close
to back-end maximum. On your client nodes however it depends on many
factors including LND, interconnect type, client performance level,
memory, cpu, I/O job type, etc. etc.
On 02/27/2013 03:18 PM, Michael McManus wrote:
Does anyone have a software tool or have a mathematical formula to
predict/estimate Read/Write rates on a Lustre system?
I have a specific OSS design, a selected hard disk type, a specific
MDS node design, and the size of the pipe between the compute nodes,
MDS node and the OSS nodes.
What other factors am I missing? RAID controller information?
I am using CentOS 6.3 with Lustre 2.3.
HPDD-discuss mailing list