Home > Workload Solutions > High Performance Computing > White Papers > HPC High-Performance Storage Solution for BeeGFS > IOzone reference and options
The IOzone tests were N-to-N. Meaning, N client threads would read or write N independent files. The commands used to run the IOzone benchmarks are given below:
Sequential Writes: iozone -i 0 -c -e -w -r 1m -s $SIZE -t $THREAD -+n -+m /path/to/threadlist
Sequential Reads: iozone -i 1 -c -e -r 1m -s $SIZE -t $THREAD -+n -+m / path/to/threadlist |
By using -c and -e in the test, IOzone provides a more realistic view of what a typical application is doing.
iozone -i 2 -c -O -I -r 4k -s $SIZE -t $THREAD -+n -+m /path/to/threadlist
The O_Direct command line parameter enables bypassing the cache on the compute node on which the IOzone thread is running. The following table describes 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 |
-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 |