Note: I spammed some retriggers for the talos test-tasks that had reports here, for the start/end of the range, so that we'd have 5+ samples before and after, rather than 1 before and 1 after. This adds some credibility to the regression & gives Perfherder's a bit more info for its analysis. As a side effect of this, we got some additional tscrollx and tsvgx runs (because those are part of the same task as `tart` so they rode along with the retriggers), and it seems PerfHerder thinks we had improvements for those talos suites as well.
Bug 1596416 Comment 3 Edit History
Note: The actual edited comment in the bug view page will always show the original commenter’s name and original timestamp.
Note: I spammed some retriggers for the talos test-tasks that had reports here, for the start/end of the range, so that we'd have 5+ samples before and after, rather than 1 before and 1 after. This adds some credibility to the regression & gives Perfherder's a bit more info for its analysis. As a side effect of this, we got some additional tscrollx and tsvgx runs (because those are part of the same task as `tart` so they rode along with the retriggers), and it seems that now PerfHerder thinks we had improvements for those talos suites as well (based on the new data at least).