Re: [RT LATENCY] 249 microsecond latency caused by slub'sunfreeze_partials() code.
From: Steven Rostedt
Date: Tue Mar 26 2013 - 23:30:39 EST
On Wed, 2013-03-27 at 11:59 +0900, Joonsoo Kim wrote:
> How about using spin_try_lock() in unfreeze_partials() and
> using spin_lock_contented() in get_partial_node() to reduce latency?
> IMHO, this doesn't make code more deterministic, but can maintain
> a benefit of cpu partial page with tolerable latency.
And what do you do when you fail the try lock? Try again, or just break
out?
We can run benchmarks, but I don't like playing games in -rt. It either
is deterministic, or it isn't.
-- Steve
--
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/