[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <18827.41762.860654.259240@cargo.ozlabs.ibm.com>
Date: Fri, 6 Feb 2009 13:40:34 +1100
From: Paul Mackerras <paulus@...ba.org>
To: Ingo Molnar <mingo@...e.hu>
Cc: "Zhang, Yanmin" <yanmin_zhang@...ux.intel.com>,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH] perf_counter: Prevent oopses from per-cpu software
counters
Ingo Molnar writes:
> You are right that "pagefaults" and "context switches" do get generated by
> tasks - but there is a per cpu and system wide notion of 'number of
> pagefaults', and people might be interested in monitoring that.
Sure. What I was trying to say was that the existing code for the
page fault, context switch and task migration software counters uses
"current", so as it is, they can't be used as per-cpu counters.
> The existence and widespread use of "vmstat", and its display of system-wide
> count of "context switches" (and administrator's reliance on judging a
> workload based on those counts) is i think ample proof that it makes sense
> to have those counters on a per CPU basis too.
>
> So how about fixing these sw counts to properly work as percpu counters too?
> Or am i misssing something subtle that makes that impossible?
I'll do that, but I think it can be a second patch on top of the one I
posted. My existing patch doesn't disable anything that previously
worked, it just stops you doing things that would cause an oops. So I
think it is strictly an improvement on the current situation.
Paul.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists