Closed
Bug 1258094
Opened 8 years ago
Closed 8 years ago
8.24 - 35.8% tp5o_scroll / tresize / tscrollx (windowsxp) regression on push d916e4520180 (Wed Mar 16 2016)
Categories
(Core :: Graphics: Layers, defect)
Core
Graphics: Layers
Tracking
()
RESOLVED
FIXED
mozilla48
Tracking | Status | |
---|---|---|
firefox48 | --- | fixed |
People
(Reporter: jmaher, Assigned: sotaro)
References
Details
(Keywords: perf, regression, Whiteboard: [talos_regression])
Attachments
(1 file)
940 bytes,
patch
|
jrmuizel
:
review+
|
Details | Diff | Splinter Review |
Talos has detected a Firefox performance regression from push d916e4520180. As author of one of the patches included in that push, we need your help to address this regression. This is a list of all known regressions and improvements related to the push: https://treeherder.mozilla.org/perf.html#/alerts?id=468 On the page above you can see an alert for each affected platform as well as a link to a graph showing the history of scores for this test. There is also a link to a treeherder page showing the Talos jobs in a pushlog format. To learn more about the regressing test(s), please see: https://wiki.mozilla.org/Buildbot/Talos/Tests#tresize https://wiki.mozilla.org/Buildbot/Talos/Tests#tscrollx https://wiki.mozilla.org/Buildbot/Talos/Tests#tp5o_scroll Reproducing and debugging the regression: If you would like to re-run this Talos test on a potential fix, use try with the following syntax: try: -b o -p win32 -u none -t chromez-e10s[Windows XP],svgr-e10s[Windows XP],g1-e10s[Windows XP] --rebuild 5 # add "mozharness: --spsProfile" to generate profile data (we suggest --rebuild 5 to be more confident in the results) To run the test locally and do a more in-depth investigation, first set up a local Talos environment: https://wiki.mozilla.lorg/Buildbot/Talos/Running#Running_locally_-_Source_Code Then run the following command from the directory where you set up Talos: talos --develop -e [path]/firefox -a tresize:tscrollx:tp5o_scroll (add --e10s to run tests in e10s mode) Making a decision: As the patch author we need your feedback to help us handle this regression. *** Please let us know your plans by Tuesday, or the offending patch(es) will be backed out! *** Our wiki page outlines the common responses and expectations: https://wiki.mozilla.org/Buildbot/Talos/RegressionBugsHandling
Reporter | ||
Comment 1•8 years ago
|
||
I did a lot of retriggers (mostly to backfill data), and I have data showing the differences from this patch vs the previous one: https://treeherder.mozilla.org/perf.html#/compare?originalProject=mozilla-inbound&originalRevision=4da14b8142a5&newProject=mozilla-inbound&newRevision=d916e4520180&framework=1 These are all winxp, and the regressions are on e10s. We are really strict on e10s vs non e10s for release criteria, so there is extra scrutiny on that. :sotaro, can you take a look at this and let us know the next steps by Tuesday?
Flags: needinfo?(sotaro.ikeda.g)
Reporter | ||
Comment 2•8 years ago
|
||
it looks like we had a big win from bug 1255320 a few days earlier and this for the most part took that win away- in fact it looked like a backout on winxp- maybe this is a net zero type of bug when looking at a few days.
Assignee | ||
Comment 3•8 years ago
|
||
Monday was public holiday in Japan. I am going to check it soon.
Reporter | ||
Comment 4•8 years ago
|
||
Thanks Sotaro!
Comment 5•8 years ago
|
||
One option with this patch is to wait until we switch to an image surface for the backbuffer. That will have more predictable and controllable performance.
Assignee | ||
Comment 6•8 years ago
|
||
Thanks for the advice. It seems better to disable the patch until we switch to an image surface.
Flags: needinfo?(sotaro.ikeda.g)
Assignee | ||
Comment 7•8 years ago
|
||
Assignee | ||
Updated•8 years ago
|
Attachment #8733188 -
Flags: review?(jmuizelaar)
Assignee | ||
Updated•8 years ago
|
Assignee: nobody → sotaro.ikeda.g
Updated•8 years ago
|
Attachment #8733188 -
Flags: review?(jmuizelaar) → review+
Comment 9•8 years ago
|
||
bugherder |
https://hg.mozilla.org/mozilla-central/rev/b68566e511b7
Status: NEW → RESOLVED
Closed: 8 years ago
Resolution: --- → FIXED
Target Milestone: --- → mozilla48
Reporter | ||
Comment 10•8 years ago
|
||
it looks like we fixed most of the winxp tp5o main_rss regression, the rest is showing up on aurora now: https://treeherder.mozilla.org/perf.html#/graphs?timerange=5184000&series=%5Bmozilla-aurora,2637dc86110a57fe7567129b4ccbe03e4cf2b686,1%5D&series=%5Bmozilla-inbound,2637dc86110a57fe7567129b4ccbe03e4cf2b686,1%5D&series=%5Bmozilla-central,2637dc86110a57fe7567129b4ccbe03e4cf2b686,1%5D&series=%5Bfx-team,2637dc86110a57fe7567129b4ccbe03e4cf2b686,1%5D
You need to log in
before you can comment on or make changes to this bug.
Description
•