diff options
author | Yujun Zhang <zhang.yujunz@zte.com.cn> | 2017-03-23 16:06:04 +0800 |
---|---|---|
committer | Yujun Zhang <zhang.yujunz@zte.com.cn> | 2017-03-23 16:27:54 +0800 |
commit | 5c4c42d794a8f3ca0708098790320d2a022ec8ec (patch) | |
tree | 5fdb51149535e5cfc4889ba0446caff27e255706 /docs/testing/developer | |
parent | f7040bb929de84ce640d67ec809f6b71cf827358 (diff) |
Sync docs from stable/danube 05ef2c4f46a9dc7a704a290eb15817c80a52c2e6
Change-Id: I519c002259143cc92417f34595a80889c93310e1
Signed-off-by: Yujun Zhang <zhang.yujunz@zte.com.cn>
Diffstat (limited to 'docs/testing/developer')
-rw-r--r-- | docs/testing/developer/design/_assets/sequence.png | bin | 0 -> 44132 bytes | |||
-rw-r--r-- | docs/testing/developer/design/_assets/standalone.png | bin | 0 -> 47515 bytes | |||
-rw-r--r-- | docs/testing/developer/design/api.rst | 2 | ||||
-rw-r--r-- | docs/testing/developer/design/arch.rst | 24 | ||||
-rw-r--r-- | docs/testing/developer/design/compute-qpi.rst | 69 | ||||
-rw-r--r-- | docs/testing/developer/design/index.rst | 7 |
6 files changed, 99 insertions, 3 deletions
diff --git a/docs/testing/developer/design/_assets/sequence.png b/docs/testing/developer/design/_assets/sequence.png Binary files differnew file mode 100644 index 00000000..b15458bf --- /dev/null +++ b/docs/testing/developer/design/_assets/sequence.png diff --git a/docs/testing/developer/design/_assets/standalone.png b/docs/testing/developer/design/_assets/standalone.png Binary files differnew file mode 100644 index 00000000..50222b5b --- /dev/null +++ b/docs/testing/developer/design/_assets/standalone.png diff --git a/docs/testing/developer/design/api.rst b/docs/testing/developer/design/api.rst new file mode 100644 index 00000000..eb2b0d67 --- /dev/null +++ b/docs/testing/developer/design/api.rst @@ -0,0 +1,2 @@ +- Which framework has been used and why +- How to extend to more api diff --git a/docs/testing/developer/design/arch.rst b/docs/testing/developer/design/arch.rst new file mode 100644 index 00000000..d95faba6 --- /dev/null +++ b/docs/testing/developer/design/arch.rst @@ -0,0 +1,24 @@ +.. This work is licensed under a Creative Commons Attribution 4.0 International License. +.. http://creativecommons.org/licenses/by/4.0 +.. (c) 2017 ZTE Corp. + + +######################## +QTIP Architecture Design +######################## + +In Danube, QTIP releases its standalone mode, which is also know as ``solo``: + +.. figure:: _assets/standalone.png + :alt: QTIP standalone mode + +The runner could be launched from CLI (command line interpreter) or API +(application programming interface) and drives the testing jobs. The generated +data including raw performance data and testing environment are fed to collector. +Performance metrics will be parsed from the raw data and used for QPI calculation. +Then the benchmark report is rendered with the benchmarking results. + +The execution can be detailed in the diagram below: + +.. figure:: _assets/sequence.png + :alt: QTIP execution sequence diff --git a/docs/testing/developer/design/compute-qpi.rst b/docs/testing/developer/design/compute-qpi.rst new file mode 100644 index 00000000..2e5aa87c --- /dev/null +++ b/docs/testing/developer/design/compute-qpi.rst @@ -0,0 +1,69 @@ +.. This work is licensed under a Creative Commons Attribution 4.0 International License. +.. http://creativecommons.org/licenses/by/4.0 +.. (c) 2016 ZTE Corp. + + +*********** +Compute QPI +*********** + +The compute QPI gives user an overall score for system compute performace. + +Summary +======= + +The compute QPI are calibrated a ZTE `E9000 <http://www.zte.com.cn/global/products/cocloud/cloud_computing/cloud_infrastructure/cloud_hw/429552>`_ server as a baseline with score of 2500 points. +Higher scores are better, with double the score indicating double the performance. +The compute QPI provides three different kinds of scores: + +* Workload Scores +* Section Scores +* Compute QPI Scores + +Baseline +======== + +ZTE E9000 server with an 2 Deca core Intel Xeon CPU processor,128560.0MB Memory. + +Workload Scores +=============== + +Each time a workload is executed QTIP calculates a score based on the computer's performance +compared to the baseline performance. + +Section Scores +============== + +QTIP uses a number of different tests, or workloads, to measure performance. +The workloads are divided into five different sections: + ++-----------------+--------------------------------------------------------------+------------------------------------------+ +| Section | Detail | Indication | ++=================+==============================================================+==========================================+ +| Integer | Integer workloads measure the integer instruction performace | All app relies on integer | +| | of host or vm by performing Dhrystone test. | performance | ++-----------------+--------------------------------------------------------------+------------------------------------------+ +| Floating point | Floating point workloads measure the floating pointperfo | Floating point performance is especially | +| | rmance by performing Whetstone test. | important in video games,digital content | +| | | creation applications. | ++-----------------+--------------------------------------------------------------+------------------------------------------+ +| Memory | Memory workloads measure memory bandwidth by performing | Software working with cipher large | +| | RamSpeed test. | amounts data relies on SSL Performace. | ++-----------------+--------------------------------------------------------------+------------------------------------------+ +| DPI | DPI workloads measure deep-packet inspection speed by | Software working with network packet | +| | performing nDPI test. | anlysis relies on DPI performance. | ++-----------------+--------------------------------------------------------------+------------------------------------------+ +| SSL | SSL Performance workloads measure cipher speeds by | Software working with cipher large | +| | using the OpenSSL tool. | amounts data relies on SSL Performace | ++-----------------+--------------------------------------------------------------+------------------------------------------+ + +A section score is the `geometric mean <https://en.wikipedia.org/wiki/Geometric_mean>`_ of all the workload scores for workloads +that are part of the section. These scores are useful for determining the performance of +the computer in a particular area. + +Compute QPI Scores +================== + +The compute QPI score is the `weighted arithmetic mean <https://en.wikipedia.org/wiki/Weighted_arithmetic_mean>`_ of the five section scores. +The compute QPI score provides a way to quickly compare performance across different +computers and different platforms without getting bogged down in details. diff --git a/docs/testing/developer/design/index.rst b/docs/testing/developer/design/index.rst index b6dd0c01..2b4bd9b0 100644 --- a/docs/testing/developer/design/index.rst +++ b/docs/testing/developer/design/index.rst @@ -10,6 +10,7 @@ QTIP Design Specifications .. toctree:: :maxdepth: 2 - dashboard.rst - compute_QPI.rst - integration_with_yardstick.rst + arch.rst + cli.rst + api.rst + compute-qpi.rst |