Re: [RFC][PATCH] Scalable Scheduling

Hubertus Franke (frankeh@us.ibm.com)
Fri, 10 Aug 2001 20:04:13 -0400


Chris, I looked into the availability of this stuff. The people
here at Watson will put some of their low level stuff together and
hopefully we get some insights in a few weeks.
I keep you posted

Hubertus Franke
Enterprise Linux Group (Mgr), Linux Technology Center (Member Scalability)
, OS-PIC (Chair)
email: frankeh@us.ibm.com
(w) 914-945-2003 (fax) 914-945-4425 TL: 862-2003

Chris Wedgwood <cw@f00f.org> on 08/10/2001 07:58:27 PM

To: "David S. Miller" <davem@redhat.com>
cc: lm@bitmover.com, torvalds@transmeta.com, Hubertus
Franke/Watson/IBM@IBMUS, mkravetz@beaverton.ibm.com,
linux-kernel@vger.kernel.org, wscott@bitmover.com
Subject: Re: [RFC][PATCH] Scalable Scheduling

On Wed, Aug 08, 2001 at 11:53:28AM -0700, David S. Miller wrote:

1) tell me D-cache misses in user and/or kernel mode
2) tell me D-cache misses that hit the E-cache
in user and/or kernel mode
3) tell me I-cache misses, but only those which actually
ended up stalling the pipeline
4) tell me E-cache misses, where the chip was not able
to get granted to memory bus immediately
5) Same as #4, but how many total bus cycles were spent
waiting for bus grant for the E-cache miss

ia32 for PPro and above can do all of that too pretty much (perhaps
not exactly the same metric, but hopefully equally useful). The only
thing is, you can read them all at once, only a small number of them,
and they are for all kernel/userland states, so you would need to
save/read them on context switches.

--cw

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/