TestEngineering/Performance/FAQ: Difference between revisions

Jump to navigation Jump to search
no edit summary
No edit summary
Line 1: Line 1:
= Perfherder =
== What is Perfherder? ==
== What is Perfherder? ==
[https://treeherder.mozilla.org/perf.html#/graphs Perfherder] is a tool that takes data points from log files and graphs them over time.  Primarily this is used for performance data from [[TestEngineering/Performance/Talos|Talos]], but also from [[AWSY/Tests|AWSY]], build_metrics, [[EngineeringProductivity/Autophone|Autophone]] and platform_microbenchmarks. All these are test harnesses and you can find more about them [[TestEngineering/Performance/Sheriffing/Alerts|here]].  
[https://treeherder.mozilla.org/perf.html#/graphs Perfherder] is a tool that takes data points from log files and graphs them over time.  Primarily this is used for performance data from [[TestEngineering/Performance/Talos|Talos]], but also from [[AWSY/Tests|AWSY]], build_metrics, [[EngineeringProductivity/Autophone|Autophone]] and platform_microbenchmarks. All these are test harnesses and you can find more about them [[TestEngineering/Performance/Sheriffing/Alerts|here]].  
Line 56: Line 54:


[[File:Ph_Muting.jpg]]
[[File:Ph_Muting.jpg]]
= Tree =


== What makes branches different from one another? ==
== What makes branches different from one another? ==
Line 133: Line 129:
* OSX does not do PGO builds, so we do not have -Non-PGO branches for those platforms. (i.e. we only have Mozilla-Inbound)
* OSX does not do PGO builds, so we do not have -Non-PGO branches for those platforms. (i.e. we only have Mozilla-Inbound)
* PGO alerts will probably have different regression percentages, but the overall list of platforms/tests for a given revision will be almost identical
* PGO alerts will probably have different regression percentages, but the overall list of platforms/tests for a given revision will be almost identical
= Alerts =


== What alerts are displayed in Alert Manager? ==
== What alerts are displayed in Alert Manager? ==
Line 176: Line 170:
NOTE: for the reverse tests we take that into account, so the bar graph will know to look in the correct direction.
NOTE: for the reverse tests we take that into account, so the bar graph will know to look in the correct direction.


= Noise =
== What is noise? ==
== What is noise? ==
Generally a test reports values that are in a range instead of a consistent value.  The larger the range of 'normal' results, the more noise we have.
Generally a test reports values that are in a range instead of a consistent value.  The larger the range of 'normal' results, the more noise we have.
Line 242: Line 235:
== What is random noise? ==
== What is random noise? ==
Random noise are the data-points that don't fit in the graph trend of the test. They happen because of various uncontrollable factors (and this is assumed) or because the test is unstable.
Random noise are the data-points that don't fit in the graph trend of the test. They happen because of various uncontrollable factors (and this is assumed) or because the test is unstable.
= Bugzilla =


== How do I identify the current firefox release meta-bug? ==
== How do I identify the current firefox release meta-bug? ==
342

edits

Navigation menu