Re: [PATCH RFC] perf lock: Add new event "lock_acquired_waittime"for contention analysis
From: Peter Zijlstra
Date: Tue Aug 03 2010 - 04:01:09 EST
On Tue, 2010-08-03 at 16:37 +0900, Hitoshi Mitake wrote:
> But, I believe that
> - lock validation
> - lock tracing
> - in kernel light weight lock usage statistics
> should be divided into individual features, at least.
> And tracing and statistics should be available for production kernel,
> How do you think about this point?
Both the lock usage and lock validation use the lock classification
scheme and thus require the bloated lock structures, and hence I don't
think its at all reasonable to do that runtime.
lock tracing could possibly be done by patching all lock sites, but we'd
have to be somewhat careful there too not to make the whole spinlock
code even worse than it already is.
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/