Concept Guide

Benchmarks and test tools
28 Dell EMC Ready Solutions for HPC BeeGFS High Performance Storage | ID 460
IOzone Argument
Description
-t
Number of threads
-e
Includes flush in the timing calculations
-r
Records size
-s
File size
-t
Number of threads
-+m
Location of clients to run IOzone when in clustered mode
-w
Does not unlink (delete) temporary file
-I
Use O_DIRECT, bypass client cache
-O
Give results in ops/sec
A.2 IOR
The command used to run the test is given below:
mpirun -machinefile $hostlist --map-by node -np $threads -mca btl openib,self
~/bin/ior -w -r -i 3 -d 3 -e -O beegfsNumTargets=33,beegfsChunkSize=$record_size
-o $working_dir/ior.out -s 1 -g -t $record_size -b $file_size
The following table describes the IOR command-line arguments.
Appendix A — IOR command line arguments
BeeGFS Tuning Parameter
Description
beegfsNumTargets
Number of storage targets to use for striping
beegfsChunkSize
Striping chunk size in bytes (Accepts k=kilo, m=mega, g=giga etc)
mpirun Argument
Description
-machinefile
Tells mpirun where the hostfile is located
-map-by node
Launch processes one per node, cycling by node in a round robin
fashion. This spreads processes evenly among nodes and assigns
MPI_COMM_WORLD ranks in a round-robin, “by-node” manner.
-np
Number of processes
IOR Argument
Description
-w
Write benchmark
-r
Read benchmark
-i
Number of repetitions
-d
Delay between repetitions in seconds
-e
perform fsync upon POSIX write close (make sure reads are only
started after all writes are done)