New issue
Advanced search Search tips
Note: Color blocks (like █ or █) mean that a user may not be available. Tooltip shows the reason.

10.4%-15.4% regression in blink_perf.dom at 516565:516656

Project Member Reported by benhenry@google.com, Nov 18 2017 
So they began to tell a different story in the description boxes.
Project Member

Comment 1 by 42576172...@developer.gserviceaccount.com, Nov 18 2017 

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=786619

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=3dedd3a067858f82e87ac793dd2764505ce3d46c14d2dd6d248e48b5747bf2a0


Bot(s) for this bug's original alert(s):

chromium-rel-mac11
linux-release
Project Member

Comment 2 by 42576172...@developer.gserviceaccount.com, Nov 18 2017 

馃搷 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/11c7e695f80000
Project Member

Comment 3 by 42576172...@developer.gserviceaccount.com, Nov 18 2017 

馃搷 Couldn't reproduce a difference.
https://pinpoint-dot-chromeperf.appspot.com/job/11c7e695f80000
Project Member

Comment 4 by 42576172...@developer.gserviceaccount.com, Jan 19 2018 

馃搷 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/14fe7e18840000
Project Member

Comment 5 by 42576172...@developer.gserviceaccount.com, Jan 19 2018 

馃搷 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/1486c118840000
Project Member

Comment 6 by 42576172...@developer.gserviceaccount.com, Jan 19 2018 

馃搷 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/16d80bd8840000

Comment 7 by sullivan@chromium.org, Jan 19 2018 

Looks like the graph that was bisected on was a different issue (not a real regression). Bisecting on some other ones.
Project Member

Comment 8 by 42576172...@developer.gserviceaccount.com, Jan 20 2018

Cc: falken@chromium.org kinuko@chromium.org leon....@intel.com ajwong@chromium.org tsepez@chromium.org brettw@chromium.org shimazu@chromium.org
Owner: ajwong@chromium.org
Status: Assigned (was: Untriaged)
馃搷 Found significant differences after each of 2 commits.
https://pinpoint-dot-chromeperf.appspot.com/job/16d80bd8840000

[ServiceWorker] Eliminate blink.mojom.ServiceWorkerRegistrationObjectInfo.handle_id
By leon.han@intel.com 路 Wed Nov 15 03:07:51 2017
chromium @ 86029dbfbf1c4927e12c8f8b09de04d706553472

Enable frame pointers in linux.
By ajwong@chromium.org 路 Wed Nov 15 06:16:22 2017
chromium @ 9f966099a3d6f91c80016226fe9d33981f291689

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions
Project Member

Comment 9 by 42576172...@developer.gserviceaccount.com, Jan 20 2018

Cc: dpranke@chromium.org thomasanderson@chromium.org caseq@chromium.org pfeldman@chromium.org
馃搷 Found significant differences after each of 3 commits.
https://pinpoint-dot-chromeperf.appspot.com/job/14fe7e18840000

Revert "[Devtools] Requests can now be intercepted on response"
By dpranke@chromium.org 路 Wed Nov 15 04:02:55 2017
chromium @ ed79b4f36846e8aac9dd90179f25f7351df8a94d

Revert "Revert "[Devtools] Requests can now be intercepted on response""
By thomasanderson@chromium.org 路 Wed Nov 15 04:37:47 2017
chromium @ ddde3f72a8dbadb6974c61fe565c562b77a1426a

Enable frame pointers in linux.
By ajwong@chromium.org 路 Wed Nov 15 06:16:22 2017
chromium @ 9f966099a3d6f91c80016226fe9d33981f291689

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions
Project Member

Comment 10 by 42576172...@developer.gserviceaccount.com, Jan 21 2018

Cc: dominickn@chromium.org kbr@chromium.org a...@chromium.org calamity@chromium.org dcheng@chromium.org klausw@chromium.org zhongyi@chromium.org patricia...@chromium.org est...@chromium.org jochen@chromium.org ckrasic@chromium.org pdr@chromium.org shend@chromium.org meade@chromium.org tapted@chromium.org benwells@chromium.org bajones@chromium.org most...@vewd.com rch@chromium.org billorr@chromium.org schenney@chromium.org
Owner: calamity@chromium.org
馃搷 Found significant differences after each of 11 commits.
https://pinpoint-dot-chromeperf.appspot.com/job/1486c118840000

Enable frame pointers in linux.
By ajwong@chromium.org 路 Wed Nov 15 06:16:22 2017
chromium @ 9f966099a3d6f91c80016226fe9d33981f291689

Specify REAL_IO_THREAD in the TestBrowserThreadBundle for ImportantSitesUsageCounterTest.
By dominickn@chromium.org 路 Wed Nov 15 06:17:27 2017
chromium @ afac65b656d03ff4a85c4aca3f3537d906d5490a

Revert "Use sibling HasInlineTransform to enable more squashing"
By schenney@chromium.org 路 Wed Nov 15 06:17:32 2017
chromium @ 90bb5240fe42935776901f33bc7c515e8c24da1c

Blink changes to support WebVR on Desktop
By billorr@chromium.org 路 Wed Nov 15 06:18:36 2017
chromium @ f1a97e71878f0c30f87aa17a2c4dde7ed1be9140

relnote: fix a DCHECK in an unused method: SendConnectivityProbingPacket
By zhongyi@chromium.org 路 Wed Nov 15 06:19:46 2017
chromium @ 42573c993f1932b02861b45ef9a67ec11bee7d0c

Treat invalid tokens in referrer policy headers as errors
By jochen@chromium.org 路 Wed Nov 15 06:20:53 2017
chromium @ 87e8c1785c682ed6fd83e0c9cf97cc4f359385db

[jumbo] avoid ToBrowserAccessibilityAuraLinux redefinition
By mostynb@vewd.com 路 Wed Nov 15 07:05:13 2017
chromium @ b1622826665b8e03c6732bb8ecdb16ed736cc358

Desktop Page Info/Harmony: Show close button for internal pages.
By patricialor@chromium.org 路 Wed Nov 15 07:22:00 2017
chromium @ acf2f0799f6f732dd70f45ddd252d773be7afd11

[css-typed-om] Implement multiplication of numeric types.
By shend@chromium.org 路 Wed Nov 15 07:26:45 2017
chromium @ 0254d21dc41d8ec25b49356ec1e55f7e8ccf3c66

Views: Labels with gfx::NO_ELIDE now set their minimum size to the text size.
By patricialor@chromium.org 路 Wed Nov 15 07:35:09 2017
chromium @ c2c3b4582b337db011eb1bdac4c2c159197a32a5

Remove elide_middle argument from IconLabelBubbleView.
By calamity@chromium.org 路 Wed Nov 15 07:54:59 2017
chromium @ 53ad802897c1cff23f42d7a533fcb6ba8d812fdc

Understanding performance regressions:
  http://g.co/ChromePerformanceRegressions

Comment 11 by dominickn@chromium.org, Jan 21 2018

Cc: -dominickn@chromium.org
My change is test only, so taking myself off CC.

Comment 12 by falken@chromium.org, Jan 22 2018 

Regarding c#8, it seems unlikely that the service worker refactoring change would affect the test blink_perf.dom which I don't expect to be making service worker API calls.

It looks like the "Enable frame pointers in linux." is the only CL in all three of the bisect results.

Comment 13 by zhongyi@chromium.org, Jan 22 2018 

My change is in an unused method, so taking myself from the cc list.

Comment 14 by ajwong@chromium.org, Jan 22 2018

Cc: erikc...@chromium.org
Status: WontFix (was: Assigned)
Highly likely this was the Enable FP change at 9f966099a3d6f91c80016226fe9d33981f291689.  There were similar alerts when we landed.

This should have only affected linux_rel though and not Mac.  It brings us in-line with the perf of ChromeOS and other platforms so we deemed it okay.  Closing won't fix.

Comment 15 by zhongyi@chromium.org, Jan 22 2018

Cc: -zhongyi@chromium.org
►

Sign in to add a comment