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.


Reply via email to