Bugzilla

I graphed the distribution of individual responsiveness values from before and the patch (using linux64 perfherder graph). There is a minor effect of being close to the 20ms cutoff, but there is a pretty clear 5ms delay. I'll take a quick look at if there is any weird JIT behaviour since `gBrowser` is a pretty exotic object and destructuring is quite complicated under the hood.

I graphed the distribution of individual responsiveness values from before and the patch (using linux64 perfherder graph). There is a minor effect of being close to the 20ms cutoff, but there is a pretty clear 5ms delay. I'll take a quick look at if there is any weird JIT behaviour since `gBrowser` is a pretty exotic object and destructuring is quite complicated under the hood.

Edit: The data is the ~1200 samples within a single run of each.