On Tue, Jul 30, 2013 at 2:33 PM, <[email protected]> wrote: > [...] Our assumption is that with a high sampling rate we can afford > allocating one > CPU core to the profile event processor and the sampling rate would be > limited > by the performance of that thread. So we intentionally want to have the > core be > busy exclusively with the profile events processing.
Have you measured how much the rapid delivery of signals affects JavaScript performance, especially on low-end platforms like ARM? Context switching is not that cheap, but I don't really have a gut feeling how much it actually costs. I would really like to see some numbers before we increase the rate by a factor of 10. -- -- v8-dev mailing list [email protected] http://groups.google.com/group/v8-dev --- You received this message because you are subscribed to the Google Groups "v8-dev" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. For more options, visit https://groups.google.com/groups/opt_out.
