[erlang-questions] How to understand busyness of driver job queue?

Michael Truog mjtruog@REDACTED
Tue Mar 12 21:58:46 CET 2013


You may have thought that the async threads use a shared job queue, but they don't... each thread has its own queue.  So, that means it is easy to plug up the async thread pool, if you have long running operations.  By increasing the pool size to a much larger value, you are no longer blocking on a randomly overworked async thread.

On 03/12/2013 01:10 PM, Max Lapshin wrote:
> So, I need to run dtrace on live system?
>
> I've found that if I increase +A from 16 to 160, system starts working excelently.
>
>
> _______________________________________________
> erlang-questions mailing list
> erlang-questions@REDACTED
> http://erlang.org/mailman/listinfo/erlang-questions

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://erlang.org/pipermail/erlang-questions/attachments/20130312/3dd5ba9b/attachment.htm>


More information about the erlang-questions mailing list