[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20090701112406.GE15958@elte.hu>
Date: Wed, 1 Jul 2009 13:24:06 +0200
From: Ingo Molnar <mingo@...e.hu>
To: Jaswinder Singh Rajput <jaswinder@...nel.org>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Arjan van de Ven <arjan@...radead.org>,
Frédéric Weisbecker <fweisbec@...il.com>,
Arnaldo Carvalho de Melo <acme@...hat.com>,
Paul Mackerras <paulus@...ba.org>,
Anton Blanchard <anton@...ba.org>
Cc: Thomas Gleixner <tglx@...utronix.de>,
Peter Zijlstra <peterz@...radead.org>,
x86 maintainers <x86@...nel.org>,
LKML <linux-kernel@...r.kernel.org>,
Alan Cox <alan@...rguk.ukuu.org.uk>
Subject: Re: [PATCH 4/6 -tip] perf_counter: Add Generalized Hardware
interrupt support for AMD
* Jaswinder Singh Rajput <jaswinder@...nel.org> wrote:
>
> $ ./perf stat -e interrupts -e masked -e int-pending-mask-cycles -- ls -lR /usr/include/ > /dev/null
>
> Performance counter stats for 'ls -lR /usr/include/':
>
> 377 interrupts
> 53429936 int-mask-cycles
> 1119 int-pending-mask-cycles
>
> 0.371457539 seconds time elapsed
Agreed, this is another useful generalization - and the 'cycles
pending' metrics are not retrievable via any software means.
We could and should probably add a software counter for hardirqs as
wel. That would allow the vector/irqnr information to be passed in,
and it would allow architectures without irq metrics in the PMU to
have this counter too.
This way we could profile based on a specific interrupt source only
- say based on the networking card.
Ingo
--
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