Supporting Hardware - Expert Consolidation in Oracle Database 12c - page 97

32 - 64 us: 10 0
64 - 128 us: 364355 0
128 - 256 us: 90531 0
256 - 512 us: 4281 0
512 - 1024 us: 2444 0
1024 - 2048 us: 244 0
2048 - 4096 us: 38 0
4096 - 8192 us: 8 0
8192 - 16384 us: 0 0
16384 - 32768 us: 0 0
32768 - 65536 us: 0 0
65536 - 131072 us: 0 0
131072 - 262144 us: 0 0
262144 - 524288 us: 0 0
524288 - 1048576 us: 0 0
1048576 - 2097152 us: 0 0
2097152 - 4194304 us: 0 0
4194304 - 8388608 us: 0 0
8388608 - 16777216 us: 0 0
16777216 - 33554432 us: 0 0
33554432 - 67108864 us: 0 0
67108864 - 134217728 us: 0 0
134217728 - 268435456 us: 0 0a

This output has been produced from a testbed environment; the numbers are not to be used for comparison with
a real storage backend.
Large I/Os are random by default but can be defined as sequential if desired. To add write testing to the benchmark,
you need to tell ORION to do so. The -write flag indicates how many percent of I/Os should be writes, and according to
the documentation the default is 0.

■ Caution write testing wiLL deStroY existing data. double or triple check that the Luns you test against do not

contain data!

At the end of the benchmark, you are presented with a lot of information. All the result files are prefixed with the
test name you chose with an added time stamp:

[oracle@server1 temp]# ls -l
total 104
-rw-r--r--. 1 oracle oracle 19261 Jul 22 10:13 test1_20130722_0953_hist.txt
-rw-r--r--. 1 oracle oracle 742 Jul 22 10:13 test1_20130722_0953_iops.csv
-rw-r--r--. 1 oracle oracle 761 Jul 22 10:13 test1_20130722_0953_lat.csv
-rw-r--r--. 1 oracle oracle 570 Jul 22 10:13 test1_20130722_0953_mbps.csv
-rw-r--r--. 1 oracle oracle 1859 Jul 22 10:13 test1_20130722_0953_summary.txt
-rw-r--r--. 1 oracle oracle 18394 Jul 22 10:13 test1_20130722_0953_trace.txt
-rw-r--r--. 1 oracle oracle 20 Jul 22 09:46 test1.lun
[oracle@server1 temp]#