EDIT: Does anyone know why there's that spike for most of the benchmarks starting February 8th/10th? Seems like it affected both Chrome/Chromium and Firefox, although in some cases FF seems to have been hit the most. A Kernel update maybe? Some syscall changed?
Could be a readjustment in the metrics. They fix test and measurement errors from time to time and it often looks like a spike. They attach notes to the data points sometimes. Maybe clicking one of them during that time will shed some light.
I think it is so that on all graphs “lower” down is better. But agree it’s kind of unusual layout. Looking at the graphs for Linux i wonder what happened in feb 11:th this year - where all values for Firefox got a lot worse.
Sometimes the hardware or software configurations of the machines running the tests changes, or a bug in the test harness itself is fixed, which can skew all of the results at once.
mozilla.social
Hot