All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=871406

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=bf71c37651f47d22683a006675ef9a40a1dbdf66a17365e617541c9101e74068


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

mac-10_12_laptop_low_end-perf

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/128a3a5fa40000

📍 Found significant differences after each of 2 commits.
https://pinpoint-dot-chromeperf.appspot.com/job/128a3a5fa40000

[content] Disable V8 untrusted code mitigations when site isolation is enabled. by rmcilroy@chromium.org
https://chromium.googlesource.com/chromium/src/+/3ba9207178ac7303393cb74dba77509755dbc4e4
17.42 → 20.11 (+2.689)

MacViews: Push VSync parameters from RHWVMac to BridgedNativeView by ccameron@chromium.org
https://chromium.googlesource.com/chromium/src/+/9eed7b76473c66cbdc5a9436c1a1a6aec851cc95
20.14 → 21.15 (+1.006)

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

The "Disable V8 untrusted code mitigations" should be purely a performance improvement on JavaScript execution, in fact if I look at the perf improvements around this point [1] I see that this benchmark improved on most bots around this CL).

It's not clear to me whether there is significant JS running in this test (nothing V8 related appears in the traces), so I'm not sure why my change would be causing this apparent regression. Maybe ccameron@ has a better idea.

[1] https://chromeperf.appspot.com/group_report?rev=579643

Respecting VSync will change performance

 Issue 871946  has been merged into this issue.

 Issue 871947  has been merged into this issue.

 Issue 872128  has been merged into this issue.