All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=751972

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=89761bba6d5ae77c1dc4be27d1490a9946f7017f2a5c78a900db1d3b22f201c0


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

chromium-rel-win10

Started bisect job https://chromeperf.appspot.com/buildbucket_job_status/8972297840828805584

=== BISECT JOB RESULTS ===
NO Perf regression found

Bisect Details
  Configuration: winx64_10_perf_bisect
  Benchmark    : system_health.memory_desktop
  Metric       : memory:chrome:all_processes:reported_by_chrome:malloc:effective_size_avg/load_games/load_games_spychase

Revision             Result                   N
chromium@489429      17434939 +- 1394739      21      good
chromium@489540      17380006 +- 1347381      21      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_x64 --output-format=chartjson --upload-results --pageset-repeat=1 --also-run-disabled-tests --story-filter=load.games.spychase 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/8972297840828805584


For feedback, file a bug with component Speed>Bisection

WontFix-ing because bisect couldn't repro.

+erikchen, perezju: this metric looks pretty noisy.

> malloc:effective_size_avg

Can we stop alerting on this metric for system_health.memory_desktop and memory.desktop? The metric shim_allocated_objects_size measures the same thing, but has 10x less noise.

+ sullivan

See c#5.

perezju, primiano, hjd: Are you okay with #5?

IIRC shim_allocated_objects_size requires heap profiling to be turned on[1] and we just turned heap profiling off for system_health.memory_desktop and memory.desktop because it was breaking a lot of the bots[2]. So I think we should at least wait till shim_allocated_objects_size is turned back on (currently blocked on the new out of process heap profiling).

[1]: https://cs.chromium.org/chromium/src/base/trace_event/malloc_dump_provider.cc?type=cs&q=shim_allocated_objects_size&sq=package:chromium&l=313
[2]: https://bugs.chromium.org/p/chromium/issues/detail?id=757847

Is there a bug open for fixing and re-enabling heap profiling on memory benchmarks?

We should block this bug on that.

Bisect unable to find culprit. This exists in stable. Ignoring.