All graphs for this bug:
  https://chromeperf.appspot.com/group_report?bug_id=916853

(For debugging:) Original alerts at time of bug-filing:
  https://chromeperf.appspot.com/group_report?sid=d81077f7f42e655be9b6c5e989e10c2855c58e4d3699b553e13e4fa4bbf9162a


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

Win 7 Nvidia GPU Perf
Win 7 Perf

blink_perf.parser - Benchmark documentation link:
  https://bit.ly/blink-perf-benchmarks

📍 Pinpoint job started.
https://pinpoint-dot-chromeperf.appspot.com/job/11bc1ee6140000

I think this is because r616192 accidentally disabled context snapshots. After r617061, the graphs recovered a bit, but maybe not completely.

Assigning to peria@ to check if there are further actions needed.

📍 Found a significant difference after 1 commit.
https://pinpoint-dot-chromeperf.appspot.com/job/11bc1ee6140000

Field Trial: Drop runtime flag for V8ContextSnapshot by peria@chromium.org
https://chromium.googlesource.com/chromium/src/+/523efae2ae9590d0bc4c0229277020db49fb5438
iframe-append-remove: 1186 → 1066 (-120)

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

Benchmark documentation link:
  https://bit.ly/blink-perf-benchmarks

Why are you merging this one in my bug for incremental steps? The V8 revision for it is not even part of the regression range.

Oops. I copied a wrong issue ID for them. I'm sorry, I'll update them soon.