[chromium-bugs] Issue 580966 in chromium: 145.9% regression in startup.warm.blank_page at 371026:371058

[c***@googlecode.com]

Status: Assigned
Owner: ***@chromium.org
Labels: Type-Bug-Regression Performance-Sheriff Pri-2 M-50

New issue 580966 by ***@chromium.org: 145.9% regression in
startup.warm.blank_page at 371026:371058
https://code.google.com/p/chromium/issues/detail?id=580966

See the link to graphs below.
--
You received this message because this project is configured to send all
issue notifications to this address.
You may adjust your notification preferences at:
https://code.google.com/hosting/settings

[c***@googlecode.com]

Comment #1 on issue 580966 by ***@chromium.org: 145.9% regression in
startup.warm.blank_page at 371026:371058
https://code.google.com/p/chromium/issues/detail?id=580966#c1

All graphs for this bug:
https://chromeperf.appspot.com/group_report?bug_id=580966

Original alerts at time of bug-filing:

https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDAh9rgqwoM


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

linux-release
--
You received this message because this project is configured to send all
issue notifications to this address.
You may adjust your notification preferences at:
https://code.google.com/hosting/settings

[c***@googlecode.com]

Updates:
Owner: ***@chromium.org
Cc: ***@chromium.org

Comment #2 on issue 580966 by ***@developer.gserviceaccount.com:
145.9% regression in startup.warm.blank_page at 371026:371058
https://code.google.com/p/chromium/issues/detail?id=580966#c2


==== Auto-CCing suspected CL author ***@chromium.org ====

Hi ***@chromium.org, the bisect results pointed to your CL below as
possibly
causing a regression. Please have a look at this info and see whether
your CL be related.

Bisect job status: Completed
Bisect job ran on: linux_perf_bisect



===== BISECT JOB RESULTS =====
Status: Positive: A suspected commit was found.

Test Command: src/tools/perf/run_benchmark -v --browser=release
--output-format=chartjson --also-run-disabled-tests startup.warm.blank_page
Test Metric: messageloop_start_time/messageloop_start_time
Relative Change: 52.45%
Score: 99.9
Retested CL with revert: Not Implemented.


===== SUSPECTED CL(s) =====
Subject : Have each SandboxedProcessLauncherDelegate maintain a zygote.
Author : kerrnel, ***@chromium.org
Commit description:

To improve component updates of PPAPI plugins, Chrome needs multiple
zygotes.
This will allow the PPAPI zygote to be recreated when a plugin is updated.
This CL allows Chrome to maintain a zygote for each process type by having
each SandboxedProcessLauncherDelegate maintain a class which can communicate
with its respective zygote. This CL will be followed up with work to allow
customization of zygotes, which will give Chrome the improve component
update
experience.

BUG=569191

Committed: https://crrev.com/3c1e16b490255119b6f70f94d1716645e897b185
Cr-Commit-Position: refs/heads/master@{#370488}

Review URL: https://codereview.chromium.org/1532423003

Cr-Commit-Position: refs/heads/master@{#371042}
Commit : afd49a83be5da2df6667a2afd14239d7783aff52
Date : Fri Jan 22 21:17:03 2016


===== TESTED REVISIONS =====
Depot Revision Mean Value Std. Dev. Num Values Good?
chromium r371025 135.883041 4.437921 18 good
chromium r371034 134.626316 3.644299 20 good
chromium r371038 135.834211 2.651794 20 good
chromium r371040 133.772853 3.065965 19 good
chromium r371041 134.207895 3.318777 20 good

chromium r371042 206.570637 3.290737 19 bad <-

chromium r371058 207.15 4.166539 20 bad



| O O | Visit http://www.chromium.org/developers/speed-infra/perf-bug-faq
| X | for more information addressing perf regression bugs. For feedback,
| / \ | file a bug with label Cr-Tests-AutoBisect. Thank you

Buildbot stdio:
http://build.chromium.org/p/tryserver.chromium.perf/builders/linux_perf_bisect/builds/5729
Job details:
https://chromeperf.appspot.com/buildbucket_job_status/9022660602224884160
--
You received this message because this project is configured to send all
issue notifications to this address.
You may adjust your notification preferences at:
https://code.google.com/hosting/settings

[c***@googlecode.com]

Updates:
Cc: ***@chromium.org

Comment #3 on issue 580966 by ***@developer.gserviceaccount.com:
145.9% regression in startup.warm.blank_page at 371026:371058
https://code.google.com/p/chromium/issues/detail?id=580966

Issue 581303 has been merged into this issue.
--
You received this message because this project is configured to send all
issue notifications to this address.
You may adjust your notification preferences at:
https://code.google.com/hosting/settings

[c***@googlecode.com]

Comment #4 on issue 580966 by ***@chromium.org: 145.9% regression in
startup.warm.blank_page at 371026:371058
https://code.google.com/p/chromium/issues/detail?id=580966#c4

The following revision refers to this bug:

https://chromium.googlesource.com/chromium/src.git/+/94807ee60fa56c118cac88b0f8f4e4e5231ef43f

commit 94807ee60fa56c118cac88b0f8f4e4e5231ef43f
Author: kerrnel <***@chromium.org>
Date: Mon Feb 01 18:57:28 2016

Use a single, generic, global zygote to temporarily resolve perf
regressions.

The CL to have multiple zygotes has caused some performance regressions,
due to the additional startup time required to launch the processes. This CL
keeps then new API in place, but uses a single global zygote, resolving the
startup overhead. Once the performance of permanent solutions has been
measured
and thought through, Chrome will return to having multiple zygote processes.

BUG=569191,580966,580974

Review URL: https://codereview.chromium.org/1643533006

Cr-Commit-Position: refs/heads/master@{#372709}

[modify]
http://crrev.com/94807ee60fa56c118cac88b0f8f4e4e5231ef43f/chrome/browser/chrome_browser_main.cc
[modify]
http://crrev.com/94807ee60fa56c118cac88b0f8f4e4e5231ef43f/components/nacl/browser/nacl_process_host.cc
[modify]
http://crrev.com/94807ee60fa56c118cac88b0f8f4e4e5231ef43f/content/browser/browser_main_loop.cc
[modify]
http://crrev.com/94807ee60fa56c118cac88b0f8f4e4e5231ef43f/content/browser/ppapi_plugin_process_host.cc
[modify]
http://crrev.com/94807ee60fa56c118cac88b0f8f4e4e5231ef43f/content/browser/renderer_host/render_process_host_impl.cc
[modify]
http://crrev.com/94807ee60fa56c118cac88b0f8f4e4e5231ef43f/content/browser/utility_process_host_impl.cc
[modify]
http://crrev.com/94807ee60fa56c118cac88b0f8f4e4e5231ef43f/content/browser/zygote_host/zygote_handle_linux.cc
[modify]
http://crrev.com/94807ee60fa56c118cac88b0f8f4e4e5231ef43f/content/public/browser/zygote_handle_linux.h
--
You received this message because this project is configured to send all
issue notifications to this address.
You may adjust your notification preferences at:
https://code.google.com/hosting/settings

[c***@googlecode.com]

Updates:
Cc: ***@chromium.org

Comment #5 on issue 580966 by ***@developer.gserviceaccount.com:
145.9% regression in startup.warm.blank_page at 371026:371058
https://code.google.com/p/chromium/issues/detail?id=580966

Issue 580982 has been merged into this issue.
--
You received this message because this project is configured to send all
issue notifications to this address.
You may adjust your notification preferences at:
https://code.google.com/hosting/settings

[c***@googlecode.com]

Updates:
Cc: ***@chromium.org

Comment #6 on issue 580966 by ***@developer.gserviceaccount.com:
145.9% regression in startup.warm.blank_page at 371026:371058
https://code.google.com/p/chromium/issues/detail?id=580966

Issue 580977 has been merged into this issue.
--
You received this message because this project is configured to send all
issue notifications to this address.
You may adjust your notification preferences at:
https://code.google.com/hosting/settings

[c***@googlecode.com]

Updates:
Cc: ***@chromium.org

Comment #7 on issue 580966 by ***@chromium.org: 145.9% regression in
startup.warm.blank_page at 371026:371058
https://code.google.com/p/chromium/issues/detail?id=580966

These perf issues should now be resolved by commit
94807ee60fa56c118cac88b0f8f4e4e5231ef43f. alexclarke can you confirm if
that's the case?
--
You received this message because this project is configured to send all
issue notifications to this address.
You may adjust your notification preferences at:
https://code.google.com/hosting/settings

[c***@googlecode.com]

Updates:
Status: Fixed
Owner: ***@chromium.org

Comment #8 on issue 580966 by ***@chromium.org: 145.9% regression in
startup.warm.blank_page at 371026:371058
https://code.google.com/p/chromium/issues/detail?id=580966

Please send this back if the benchmark is still not back to acceptable
levels.
--
You received this message because this project is configured to send all
issue notifications to this address.
You may adjust your notification preferences at:
https://code.google.com/hosting/settings

[c***@googlecode.com]

Updates:
Cc: nacl-***@chromium.org

Comment #9 on issue 580966 by ***@chromium.org: 145.9% regression in
startup.warm.blank_page at 371026:371058
https://code.google.com/p/chromium/issues/detail?id=580966

Issue 580974 has been merged into this issue.
--
You received this message because this project is configured to send all
issue notifications to this address.
You may adjust your notification preferences at:
https://code.google.com/hosting/settings

[c***@googlecode.com]

Updates:
Status: Verified

Comment #10 on issue 580966 by ***@chromium.org: 145.9% regression
in startup.warm.blank_page at 371026:371058
https://code.google.com/p/chromium/issues/detail?id=580966

The messageloop start time has recovered. The other regression hasn't and
I unlinked it from this bug.
--
You received this message because this project is configured to send all
issue notifications to this address.
You may adjust your notification preferences at:
https://code.google.com/hosting/settings

[c***@googlecode.com]

Comment #15 on issue 580966 by ***@chromium.org: 145.9% regression in
startup.warm.blank_page at 371026:371058
https://code.google.com/p/chromium/issues/detail?id=580966

Thanks. I am also surprised if my change regressed, specifically, Korean
page load times but will dig into the issue is root caused and resolved.
--
You received this message because this project is configured to send all
issue notifications to this address.
You may adjust your notification preferences at:
https://code.google.com/hosting/settings

[c***@googlecode.com]

Comment #16 on issue 580966 by ***@chromium.org: 145.9% regression in
startup.warm.blank_page at 371026:371058
https://code.google.com/p/chromium/issues/detail?id=580966

Just looking to this bug after some chat with kerrnel
Yeah I think this bug mistakenly mixed two different regressions that just
happened at the same time.

My feeling is that kerrnel's CL did indeed cause a regression on the
linux-release bots but they are fixed after the revert and as visible here:
https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDAh9rgqwoM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDA-5edswkM,agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgIDAh9rgqwkM


The 74 regressions on Android instead are still on. There is one catch
though: we don't use the chrome sandbox at all on Android, so that is
likely to be something else there.
(which, I believe, is the reason why Alex dis-owned kerrnel@ here)
--
You received this message because this project is configured to send all
issue notifications to this address.
You may adjust your notification preferences at:
https://code.google.com/hosting/settings

[c***@googlecode.com]

Updates:
Cc: ***@chromium.org

Comment #17 on issue 580966 by ***@chromium.org: 145.9% regression
in startup.warm.blank_page at 371026:371058
https://code.google.com/p/chromium/issues/detail?id=580966

I don't think any further action is needed here by ***@.

Unfortunately the android bisects seem to be failing, e.g.
https://chromeperf.appspot.com/buildbucket_job_status/9021006848302061200

+sullivan@ Can you please help me notify the right people about these
bisect failures :)
--
You received this message because this project is configured to send all
issue notifications to this address.
You may adjust your notification preferences at:
https://code.google.com/hosting/settings