New issue
Advanced search Search tips

Issue 599739 link

Starred by 0 users

Issue metadata

Status: Duplicate
Merged: issue 599490
Owner:
Closed: Apr 2016
EstimatedDays: ----
NextAction: ----
OS: ----
Pri: 2
Type: Bug-Regression



Sign in to add a comment

regression in service_worker.service_worker_micro_benchmark at 384059:384105

Project Member Reported by horo@chromium.org, Apr 1 2016

Issue description

Performance dashboard identified a 5.0% regression in service_worker.service_worker_micro_benchmark/concurrent_10_response_50_percentile on chromium-rel-mac10 at revision range 384080:384100. Graph: https://chromeperf.appspot.com/report?masters=ChromiumPerf&bots=chromium-rel-mac10&tests=service_worker.service_worker_micro_benchmark%2Fconcurrent_10_response_50_percentile&checked=concurrent_10_response_50_percentile%2Cconcurrent_10_response_50_percentile_ref%2Cref&rev=384100

Performance dashboard identified a 3.9% regression in service_worker.service_worker_micro_benchmark/concurrent_1_response_50_percentile on chromium-rel-win8-dual at revision range 384059:384105. Graph: https://chromeperf.appspot.com/report?masters=ChromiumPerf&bots=chromium-rel-win8-dual&tests=service_worker.service_worker_micro_benchmark%2Fconcurrent_1_response_50_percentile&checked=concurrent_1_response_50_percentile%2Cconcurrent_1_response_50_percentile_ref%2Cref&rev=384105

Performance dashboard identified a 3.4% regression in service_worker.service_worker_micro_benchmark/concurrent_10_response_50_percentile on chromium-rel-mac11 at revision range 384059:384100. Graph: https://chromeperf.appspot.com/report?masters=ChromiumPerf&bots=chromium-rel-mac11&tests=service_worker.service_worker_micro_benchmark%2Fconcurrent_10_response_50_percentile&checked=concurrent_10_response_50_percentile%2Cconcurrent_10_response_50_percentile_ref%2Cref&rev=384100

Performance dashboard identified a 4.7% regression in service_worker.service_worker_micro_benchmark/concurrent_1_response_50_percentile on chromium-rel-mac-retina at revision range 384080:384100. Graph: https://chromeperf.appspot.com/report?masters=ChromiumPerf&bots=chromium-rel-mac-retina&tests=service_worker.service_worker_micro_benchmark%2Fconcurrent_1_response_50_percentile&checked=concurrent_1_response_50_percentile%2Cconcurrent_1_response_50_percentile_ref%2Cref&rev=384100

 

Comment 1 by horo@chromium.org, Apr 1 2016

All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=599739

Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?keys=agxzfmNocm9tZXBlcmZyFAsSB0Fub21hbHkYgICgiNv3ogkM


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

chromium-rel-win8-dual
Mergedinto: 599490
Status: Duplicate (was: Assigned)

===== BISECT JOB RESULTS =====
Status: completed


===== SUSPECTED CL(s) =====
Subject : [BlobAsync] Asynchronous Blob Construction Final Patch
Author  : dmurph
Commit description:
  This is the final patch that hooks up the blob storage system to the new
async protocol. In this patch we:
 * Hook up the new classes and modules we created in the previous patches.
 * Remove the old way of creating blobs.
 * Create a few classes like blob_message_filter and blob_dispatcher_host
   for handing IPC messages.

The result of this change makes renderer-initiated blob construction
asynchronous instead of synchronous. So constructing new blobs should be
faster, but the time from construction to read should be the same, as
the reading still has to wait for the blob to be transferred to the
browser.

Because we let the renderer continue before we've sent all of the data,
we use ChildProcess::AddRefProcess() system to keep the renderer alive
while we transfer data.

Patches:
1: https://codereview.chromium.org/1287303002 (committed!)
2: https://codereview.chromium.org/1288373002 (committed!)
3: https://codereview.chromium.org/1292523002 (committed!)
4: https://codereview.chromium.org/1098853003 (committed!)
Hookup: https://codereview.chromium.org/1234813004

BUG= 375297 

Review URL: https://codereview.chromium.org/1234813004

Cr-Commit-Position: refs/heads/master@{#384093}
Commit  : 1fb98480c61c563587cbb01de87cfad180fec942
Date    : Wed Mar 30 21:15:51 2016


===== TESTED REVISIONS =====
Revision                Mean Value  Std. Dev.   Num Values  Good?
chromium@384079         0.856       0.009618    5           good
chromium@384090         0.854       0.008216    5           good
chromium@384092         0.858       0.009747    5           good
chromium@384093         0.894       0.008944    5           bad         <-
chromium@384095         0.895       0.012748    5           bad
chromium@384100         0.89        0.006124    5           bad

Bisect job ran on: mac_retina_perf_bisect
Bug ID: 599739

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --also-run-disabled-tests service_worker.service_worker_micro_benchmark
Test Metric: concurrent_1_response_50_percentile/concurrent_1_response_50_percentile
Relative Change: 3.97%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_retina_perf_bisect/builds/1238
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9016623902032559712


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=599739

| 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 component Tests>AutoBisect.  Thank you!

===== BISECT JOB RESULTS =====
Status: completed


===== SUSPECTED CL(s) =====
Subject : [BlobAsync] Asynchronous Blob Construction Final Patch
Author  : dmurph
Commit description:
  This is the final patch that hooks up the blob storage system to the new
async protocol. In this patch we:
 * Hook up the new classes and modules we created in the previous patches.
 * Remove the old way of creating blobs.
 * Create a few classes like blob_message_filter and blob_dispatcher_host
   for handing IPC messages.

The result of this change makes renderer-initiated blob construction
asynchronous instead of synchronous. So constructing new blobs should be
faster, but the time from construction to read should be the same, as
the reading still has to wait for the blob to be transferred to the
browser.

Because we let the renderer continue before we've sent all of the data,
we use ChildProcess::AddRefProcess() system to keep the renderer alive
while we transfer data.

Patches:
1: https://codereview.chromium.org/1287303002 (committed!)
2: https://codereview.chromium.org/1288373002 (committed!)
3: https://codereview.chromium.org/1292523002 (committed!)
4: https://codereview.chromium.org/1098853003 (committed!)
Hookup: https://codereview.chromium.org/1234813004

BUG= 375297 

Review URL: https://codereview.chromium.org/1234813004

Cr-Commit-Position: refs/heads/master@{#384093}
Commit  : 1fb98480c61c563587cbb01de87cfad180fec942
Date    : Wed Mar 30 21:15:51 2016


===== TESTED REVISIONS =====
Revision                Mean Value  Std. Dev.   Num Values  Good?
chromium@384058         4.16        0.131244    5           good
chromium@384079         4.088       0.293803    5           good
chromium@384090         4.2575      0.029962    12          good
chromium@384092         4.291667    0.052063    12          good
chromium@384093         4.36        0.036056    12          bad         <-
chromium@384095         4.379       0.035777    5           bad
chromium@384100         4.409       0.016733    5           bad

Bisect job ran on: mac_10_11_perf_bisect
Bug ID: 599739

Test Command: src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --also-run-disabled-tests service_worker.service_worker_micro_benchmark
Test Metric: concurrent_10_response_50_percentile/concurrent_10_response_50_percentile
Relative Change: 5.99%
Score: 99.9

Buildbot stdio: http://build.chromium.org/p/tryserver.chromium.perf/builders/mac_10_11_perf_bisect/builds/561
Job details: https://chromeperf.appspot.com/buildbucket_job_status/9016623906834322464


Not what you expected? We'll investigate and get back to you!
  https://chromeperf.appspot.com/bad_bisect?try_job_id=599739

| 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 component Tests>AutoBisect.  Thank you!

Sign in to add a comment