This is the mail archive of the
systemtap@sourceware.org
mailing list for the systemtap project.
Re: [perfmon] Re: perfmon2 TODO list
- From: Stephane Eranian <eranian at hpl dot hp dot com>
- To: "Frank Ch. Eigler" <fche at redhat dot com>
- Cc: perfmon at napali dot hpl dot hp dot com, systemtap at sources dot redhat dot com
- Date: Thu, 13 Apr 2006 13:07:19 -0700
- Subject: Re: [perfmon] Re: perfmon2 TODO list
- Address: HP Labs, 1U-17, 1501 Page Mill road, Palo Alto, CA 94304, USA.
- E-mail: eranian@hpl.hp.com
- Organisation: HP Labs Palo Alto
- References: <20060413164112.GC22490@redhat.com>
- Reply-to: eranian at hpl dot hp dot com
Frank.
On Thu, Apr 13, 2006 at 12:41:12PM -0400, Frank Ch. Eigler wrote:
> Hi -
>
> I am a developer on the systemtap project, which Will Cohen has
> referred you to earlier in the discussion. I thought I would jump in
> just to add/refresh focus on one important perfmon requirement for
> systemtap: a kernel-side API.
>
> Because of the way systemtap works, we need kernel-side modules to be
> able to at least *read* performance counters. (Ideally, this should
> be an API that includes the 32->64-bit overflow support.) In
> addition, it would be nice if the ioctl *configuration* interface was
> also available as a kernel-side API, so that systemtap probes could
> run the ioctl() equivalents from kernel space during session
> startup/shutdown.
>
> Is this general need clear? controversial? easy?
>
I think I understand the need. I am still not clear on
the context in which the perfmon call would be made.
I just posted a response to KEvin/Will on the perfmon mailing
list asking for clarifications on systemTap. I
thanks.