I did wonder about the impact on page load modality (specifically for the , but at least the ve-vp8-rt-cam cpuTime issue looks like a separate thing. I enabled replicates on the [ve-vp8-rt-cam cpuTime graph](https://treeherder.mozilla.org/perfherder/graphs?highlightAlerts=1&highlightChangelogData=0&highlightCommonAlerts=0&highlightInitialDataPoints=0&replicates=1&series=autoland,5822429,1,13&showTable=0&timerange=1209600) and it looks like the test has now become bimodal; previously it was only in the lower mode, and now we have data points in a new higher mode. I clicked a few of the dots and downloaded the `browsertime-results.tgz` artifact from the job (click the "job" link in the tooltip to get there), and it looks like the middle run of three is now taking more CPU time: [b1490b0e](https://treeherder.mozilla.org/jobs?repo=autoland&revision=b1490b0e96b49ae1ff5094500dc1400b0ac7a0d9&group_state=expanded&selectedTaskRun=K8pyUjRFRYao5TBAusluaw.0): 490, 1020, 400 [fa40ff87](https://treeherder.mozilla.org/jobs?repo=autoland&revision=fa40ff87befe2883b1009b22686d09c4a808ae4d&group_state=expanded&selectedTaskRun=Mhk7qhB-RuyxUZbbf6xtvA.0): 470, 1140, 450 So that seems like a real change from this patch.
Bug 2053041 Comment 4 Edit History
Note: The actual edited comment in the bug view page will always show the original commenter’s name and original timestamp.
I did wonder about the impact on page load modality (specifically for the "amazon largestContentfulPaint cold" and "welcome loadtime cold" tests), but at least the ve-vp8-rt-cam cpuTime issue looks like a separate thing. I enabled replicates on the [ve-vp8-rt-cam cpuTime graph](https://treeherder.mozilla.org/perfherder/graphs?highlightAlerts=1&highlightChangelogData=0&highlightCommonAlerts=0&highlightInitialDataPoints=0&replicates=1&series=autoland,5822429,1,13&showTable=0&timerange=1209600) and it looks like the test has now become bimodal; previously it was only in the lower mode, and now we have data points in a new higher mode. I clicked a few of the dots and downloaded the `browsertime-results.tgz` artifact from the job (click the "job" link in the tooltip to get there), and it looks like the middle run of three is now taking more CPU time: [b1490b0e](https://treeherder.mozilla.org/jobs?repo=autoland&revision=b1490b0e96b49ae1ff5094500dc1400b0ac7a0d9&group_state=expanded&selectedTaskRun=K8pyUjRFRYao5TBAusluaw.0): 490, 1020, 400 [fa40ff87](https://treeherder.mozilla.org/jobs?repo=autoland&revision=fa40ff87befe2883b1009b22686d09c4a808ae4d&group_state=expanded&selectedTaskRun=Mhk7qhB-RuyxUZbbf6xtvA.0): 470, 1140, 450 So that seems like a real change from this patch.
I did wonder about the impact on page load modality (specifically for the "amazon largestContentfulPaint cold" and "welcome loadtime cold" tests), but at least the ve-vp8-rt-cam cpuTime issue looks like a separate thing. I looked at the [ve-vp8-rt-cam cpuTime graph with replicates enabled](https://treeherder.mozilla.org/perfherder/graphs?highlightAlerts=1&highlightChangelogData=0&highlightCommonAlerts=0&highlightInitialDataPoints=0&replicates=1&series=autoland,5822429,1,13&showTable=0&timerange=1209600) and it looks like the replicates within the test have now become bimodal; previously it we only had data points in the lower mode, and now we have some data points in a new higher mode. I clicked a few of the dots and downloaded the `browsertime-results.tgz` artifact from the corresponding jobs (click the "job" link in the tooltip to get there), and it looks like the middle run of three is now taking more CPU time: [b1490b0e](https://treeherder.mozilla.org/jobs?repo=autoland&revision=b1490b0e96b49ae1ff5094500dc1400b0ac7a0d9&group_state=expanded&selectedTaskRun=K8pyUjRFRYao5TBAusluaw.0): 490, 1020, 400 [fa40ff87](https://treeherder.mozilla.org/jobs?repo=autoland&revision=fa40ff87befe2883b1009b22686d09c4a808ae4d&group_state=expanded&selectedTaskRun=Mhk7qhB-RuyxUZbbf6xtvA.0): 470, 1140, 450 So that seems like a real change from this patch.