Re: [RFC] observe and act upon workload parallelism: PERF_TYPE_PARALLELISM (Was: [RFC][PATCH] sched_wait_block: wait for blocked threads)

[Stijn Devriendt]

> This would be a perfect and suitable use of poll() concepts i think -
> and well-optimized one as well. It could even be plugged into epoll().
>
>        Ingo

Sorry for not replying earlier, but I was knocked out on the couch
(and still am). I'll have a more thorough look later on when my head
stops spinning 'round and 'round.

I must say that even without applying this perf_event to userspace
scheduling, it's probably a nice event to have anyway in order
to measure concurrency in existing applications. That it would
be suitable to actually control parallellism is probably just a nice
extra. But let's look at things again when the clouds have left
the brain ;)

Stijn
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/