1 .. This work is licensed under a Creative Commons Attribution 4.0 International
3 .. http://creativecommons.org/licenses/by/4.0
4 .. (c) OPNFV, Huawei Technologies Co.,Ltd and others.
6 *************************************
7 Yardstick Test Case Description TC014
8 *************************************
10 .. _unixbench: https://github.com/kdlucas/byte-unixbench/blob/master/UnixBench
12 +-----------------------------------------------------------------------------+
15 +--------------+--------------------------------------------------------------+
16 |test case id | OPNFV_YARDSTICK_TC014_PROCESSING SPEED |
18 +--------------+--------------------------------------------------------------+
19 |metric | score of single cpu running, |
20 | | score of parallel running |
22 +--------------+--------------------------------------------------------------+
23 |test purpose | The purpose of TC014 is to evaluate the IaaS compute |
24 | | performance with regards to CPU processing speed. |
25 | | It measures score of single cpu running and parallel |
28 | | The purpose is also to be able to spot the trends. |
29 | | Test results, graphs and similar shall be stored for |
30 | | comparison reasons and product evolution understanding |
31 | | between different OPNFV versions and/or configurations. |
33 +--------------+--------------------------------------------------------------+
34 |test tool | UnixBench |
36 | | Unixbench is the most used CPU benchmarking software tool. |
37 | | It can measure the performance of bash scripts, CPUs in |
38 | | multithreading and single threading. It can also measure the |
39 | | performance for parallel taks. Also, specific disk IO for |
40 | | small and large files are performed. You can use it to |
41 | | measure either linux dedicated servers and linux vps |
42 | | servers, running CentOS, Debian, Ubuntu, Fedora and other |
45 | | (UnixBench is not always part of a Linux distribution, hence |
46 | | it needs to be installed. As an example see the |
47 | | /yardstick/tools/ directory for how to generate a Linux |
48 | | image with UnixBench included.) |
50 +--------------+--------------------------------------------------------------+
51 |test | The UnixBench runs system benchmarks in a host VM on a |
52 |description | compute blade, getting information on the CPUs in the |
53 | | system. If the system has more than one CPU, the tests will |
54 | | be run twice -- once with a single copy of each test running |
55 | | at once, and once with N copies, where N is the number of |
58 | | UnixBench will processs a set of results from a single test |
59 | | by averaging the individal pass results into a single final |
62 +--------------+--------------------------------------------------------------+
63 |configuration | file: opnfv_yardstick_tc014.yaml |
65 | | run_mode: Run unixbench in quiet mode or verbose mode |
66 | | test_type: dhry2reg, whetstone and so on |
68 | | For SLA with single_score and parallel_score, both can be |
69 | | set by user, default is NA. |
71 +--------------+--------------------------------------------------------------+
72 |applicability | Test can be configured with different: |
78 | | Default values exist. |
80 | | SLA (optional) : min_score: The minimun UnixBench score that |
83 +--------------+--------------------------------------------------------------+
84 |usability | This test case is one of Yardstick's generic test. Thus it |
85 | | is runnable on most of the scenarios. |
87 +--------------+--------------------------------------------------------------+
88 |references | unixbench_ |
92 +--------------+--------------------------------------------------------------+
93 |pre-test | The test case image needs to be installed into Glance |
94 |conditions | with unixbench included in it. |
96 | | No POD specific requirements have been identified. |
98 +--------------+--------------------------------------------------------------+
99 |test sequence | description and expected result |
101 +--------------+--------------------------------------------------------------+
102 |step 1 | A host VM with UnixBench installed is booted. |
104 +--------------+--------------------------------------------------------------+
105 |step 2 | Yardstick is connected with the host VM by using ssh. |
106 | | "unixbench_benchmark" bash script is copied from Jump Host |
107 | | to the host VM via ssh tunnel. |
109 +--------------+--------------------------------------------------------------+
110 |step 3 | UnixBench is invoked. All the tests are executed using the |
111 | | "Run" script in the top-level of UnixBench directory. |
112 | | The "Run" script will run a standard "index" test, and save |
113 | | the report in the "results" directory. Then the report is |
114 | | processed by "unixbench_benchmark" and checked againsted the |
117 | | Result: Logs are stored. |
119 +--------------+--------------------------------------------------------------+
120 |step 4 | The host VM is deleted. |
122 +--------------+--------------------------------------------------------------+
123 |test verdict | Fails only if SLA is not passed, or if there is a test case |
124 | | execution problem. |
126 +--------------+--------------------------------------------------------------+