Re: Odd performance results

Path	csiph.com!aioe.org!bofh.it!news.nic.it!robomod
From	Peter Zijlstra <peterz@infradead.org>
Newsgroups	linux.kernel
Subject	Re: Odd performance results
Date	Tue, 12 Jul 2016 21:00:01 +0200
Message-ID	<rUb4t-o7-7@gated-at.bofh.it> (permalink)
References	<rTexs-4cA-3@gated-at.bofh.it> <rTfjQ-4IO-5@gated-at.bofh.it> <rTods-1VQ-7@gated-at.bofh.it> <rU7kd-6jl-5@gated-at.bofh.it> <rU7tU-6CN-19@gated-at.bofh.it> <rUa8q-8da-19@gated-at.bofh.it>
MIME-Version	1.0
Content-Type	text/plain; charset=us-ascii
Content-Disposition	inline
User-Agent	Mutt/1.5.23.1 (2014-03-12)
Sender	robomod@news.nic.it
List-ID	<linux-kernel.vger.kernel.org>
X-Mailing-List	linux-kernel@vger.kernel.org
Approved	robomod@news.nic.it
Lines	31
Organization	linux.* mail to news gateway
X-Original-Cc	paulmck@linux.vnet.ibm.com, tglx@linutronix.de, mingo@elte.hu, ak@linux.intel.com, linux-kernel@vger.kernel.org
X-Original-Date	Tue, 12 Jul 2016 20:51:20 +0200
X-Original-Message-ID	<20160712185120.GX30909@twins.programming.kicks-ass.net>
X-Original-References	<20160710042639.GA4068@linux.vnet.ibm.com> <7DF218CD-22F6-4E46-A628-2138AEA3A161@infradead.org> <20160710144327.GX4650@linux.vnet.ibm.com> <20160712145551.GU30909@twins.programming.kicks-ass.net> <20160712150529.GN7094@linux.vnet.ibm.com> <27d2c710-479d-77a9-f2c6-875e9c2bc40f@zytor.com>
X-Original-Sender	linux-kernel-owner@vger.kernel.org
Xref	csiph.com linux.kernel:1441657

Show key headers only | View raw

On Tue, Jul 12, 2016 at 10:49:58AM -0700, H. Peter Anvin wrote:
> On 07/12/16 08:05, Paul E. McKenney wrote:
> The CPU in question (and /proc/cpuinfo should show this) has four cores
> with a total of eight threads.  The "siblings" and "cpu cores" fields in
> /proc/cpuinfo should show the same thing.  So I am utterly confused
> about what is unexpected here?

Typically threads are enumerated differently on Intel parts. Namely:

	cpu_id = code_id + nr_cores * smt_id

which gives, for a 4 core, 2 thread part:

	0-3: core 0-3, smt0
	4-7: core 0-3, smt1

My Core i7-2600k for example has:

$ cat /sys/devices/system/cpu/cpu*/topology/thread_siblings_list
0,4
1,5
2,6
3,7
0,4
1,5
2,6
3,7

The ordering Paul has, namely 0,1 for core0,smt{0,1} is not something
I've ever seen on an Intel part. AMD otoh does enumerate their CMT stuff
like what Paul has.

Thread

Odd performance results "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2016-07-10 06:30 +0200
  Re: Odd performance results Peter Zijlstra <peterz@infradead.org> - 2016-07-10 07:20 +0200
    Re: Odd performance results "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2016-07-10 16:50 +0200
      Re: Odd performance results Peter Zijlstra <peterz@infradead.org> - 2016-07-12 17:00 +0200
        Re: Odd performance results "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2016-07-12 17:10 +0200
          Re: Odd performance results "H. Peter Anvin" <hpa@zytor.com> - 2016-07-12 20:00 +0200
            Re: Odd performance results "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2016-07-12 20:30 +0200
            Re: Odd performance results Peter Zijlstra <peterz@infradead.org> - 2016-07-12 21:00 +0200
              Re: [CRM114spam]: Re: Odd performance results "Dr. David Alan Gilbert" <dave@treblig.org> - 2016-07-12 21:40 +0200
                Re: [CRM114spam]: Re: Odd performance results "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2016-07-12 22:10 +0200
                Re: [CRM114spam]: Re: Odd performance results Ingo Molnar <mingo@kernel.org> - 2016-07-13 09:30 +0200
              Re: Odd performance results Ingo Molnar <mingo@kernel.org> - 2016-07-13 09:20 +0200
                Re: Odd performance results Henrique de Moraes Holschuh <hmh@hmh.eng.br> - 2016-07-13 14:40 +0200
                Re: Odd performance results Peter Zijlstra <peterz@infradead.org> - 2016-07-13 14:40 +0200
                Re: Odd performance results "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2016-07-13 16:10 +0200

csiph-web