Disk IO Performance Guidelines
BMC publishes Performance data in order to provide the BMC Atrium Discovery user information that is meant to help determine if a particular system used to host BMC Atrium Discovery is powerful enough to discover the estate at the desired frequency.
The performance of a BMC Atrium Discovery appliance (whether Physical or Virtual) is dependent on a number of characteristics (such as number of CPUs and CPU speed), but the performance profile of the I/O subsystem is particularly important and is harder to quantify. The metrics published on this page are all gathered on systems that are based on the recommended HP servers that run a disk controller with a battery-backed write cache and are the basis for any BMC Atrium Discovery data provided.
A BMC Atrium Discovery appliance where the I/O subsystem does not match or exceed the performance shown below will not achieve the same levels of discovery, reporting and consolidation performance.
IoZone
To provide guidance on the necessary I/O performance, performance profiles have been produced based on the powerful disk I/O performance measurement tool called IoZone. IoZone is pre-installed on the BMC Atrium Discovery appliance.
This tool can be configured to run various customized I/O tests, and the following benchmark data is produced using IoZone test that mimics the disk access profile of the BMC Atrium Discovery product as closely as possible.
To achieve this, the following command is run on a number of files:
/opt/iozone/bin/iozone -a -i 0 -i 2 -g 32G -q 32k -y 32k -f <filename>
where <filename> is a file on the disk being profiled. The tideway services should be stopped during the test. For more information about the options used, see the IoZone Documentation (PDF).
NOTE: You should stop the ADDM services prior to any iozone tests so that they are not being impaired by parallel disk activity.
This results in the execution of four tests:
- Consecutive Write
- Consecutive Read
- Random Write
- Random Read
The two random tests are the ones that reflect the BMC Atrium Discovery IO access profile; the other two tests are not used but cannot be disabled. Each test is performed against a range of files with sizes ranging from 64Kb to 32Gb.
The results of running this test against a HP DL 385 G5 are shown in the following graph. Click on it to see the full version:
The data behind the graph is available in raw form here:
File Size KB |
Random Read Kb/sec |
Random Write Kb/sec |
---|---|---|
64 |
2560003 |
901408 |
128 |
4266666 |
1777775 |
256 |
4196720 |
1753423 |
512 |
3820896 |
1673203 |
1024 |
2348624 |
1189314 |
2048 |
2096212 |
1050256 |
4096 |
2166049 |
1055670 |
8192 |
2207491 |
1027338 |
16384 |
2181915 |
1023744 |
32768 |
2165047 |
949411 |
65536 |
2174602 |
1007874 |
131072 |
2170820 |
962759 |
262144 |
1557488 |
795433 |
524288 |
2117103 |
946086 |
1048576 |
2165387 |
977598 |
2097152 |
1532333 |
796689 |
4194304 |
1876090 |
837364 |
8388608 |
1895734 |
81144 |
16777216 |
17200 |
21388 |
33554432 |
6382 |
18270 |
Comments
Log in or register to comment.