: this is about headroom. How much headroom do you still have once you're done loading your abstractions?
-
-
Replying to @slightlylate @asolove
: ...and do your tools lead you naturally to load things things well or badly?
2 replies 0 retweets 1 like -
Replying to @slightlylate @asolove
good loading is good, but we also need to shift where compute happens out of the main thread. a
@nolanlawson fav.2 replies 0 retweets 0 likes -
Replying to @rektide
: maybe? That can help, so long as you aren't core-constrained...which on mobile you almost always are /cc
@asolove@nolanlawson1 reply 0 retweets 0 likes -
mobile was was a big impetus *for* workers in Nolan's EmpireJS talk: many wimpy cores.
1 reply 0 retweets 0 likes -
Replying to @rektide
: you do not get to spin up all the cores all the time. Not even the little ones. Thermals kills you. /cc
@asolove@nolanlawson1 reply 0 retweets 0 likes -
: you can see this sort of thing in chrome:tracing or chrome:inspect?tracing
1 reply 0 retweets 0 likes -
: light-colored sections of work are unscheduled sections. Happens a LOT.
1 reply 0 retweets 0 likes -
: we have many more threads than cores already.
1 reply 0 retweets 0 likes -
Replying to @slightlylate
Do you have an example trace showing this? Surprising to me since most dead time I see is due to single/main thread jank.
2 replies 0 retweets 0 likes
: for JS-driven apps, main-thread tends to be most active/scheduled. But other threads starve. Lots of this on network thread.
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
& Web Standards TL; Blink API OWNER
Named PWAs w/
DMs open. Tweets my own; press@google.com for official comms.