All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=763095

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=b682e273377a6835a127120b313416323f93a0572d468731f77f58e2e0b6ae4b


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

chromium-rel-mac12

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8969081669455376864

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

Hi ericrk@chromium.org, the bisect results pointed to your CL, please take a look at the
results.


=== BISECT JOB RESULTS ===
Perf regression found with culprit

Suspected Commit
  Author : Eric Karl
  Commit : 6a0f206ccbe0b1e81f53a79f37474a4ba3c760e8
  Date   : Tue Sep 05 20:05:40 2017
  Subject: Use GPU Discardable in Image Decode Cache

Bisect Details
  Configuration: mac_10_12_perf_bisect
  Benchmark    : system_health.memory_desktop
  Metric       : memory:chrome:all_processes:reported_by_chrome:malloc:effective_size_avg/browse_news/browse_news_nytimes
  Change       : 29.83% | 60574269.3333 -> 78645077.5

Revision             Result                    N
chromium@499602      60574269 +- 2103980       6      good
chromium@499675      60216616 +- 2052784       6      good
chromium@499712      58425879 +- 12111138      6      good
chromium@499721      60227989 +- 2465834       6      good
chromium@499723      60835407 +- 1949348       6      good
chromium@499724      76781946 +- 2622184       6      bad       <--
chromium@499726      77421524 +- 3788598       6      bad
chromium@499730      78560494 +- 6718728       6      bad
chromium@499748      78645078 +- 4501906       6      bad

Please refer to the following doc on diagnosing memory regressions:
  https://chromium.googlesource.com/chromium/src/+/master/docs/memory-infra/memory_benchmarks.md

To Run This Test
  src/tools/perf/run_benchmark -v --browser=release --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=browse.news.nytimes system_health.memory_desktop

More information on addressing performance regressions:
  http://g.co/ChromePerformanceRegressions

Debug information about this bisect:
  https://chromeperf.appspot.com/buildbucket_job_status/8969081669455376864


For feedback, file a bug with component Speed>Bisection

 Issue 763090  has been merged into this issue.

 Issue 762964  has been merged into this issue.

Issue 763063 has been merged into this issue.

 Issue 763484  has been merged into this issue.

ericrk: any update on this bug? Looks like a pretty big memory regression on many test cases.

The change which triggered this has been reverted, but some graphs haven't recovered. Splitting those out and re-bisecting.

Looks like the majority of things recovered except for ~6 graphs which I've split out. Closing this bug.