From mboxrd@z Thu Jan  1 00:00:00 1970
From: David Miller <davem@davemloft.net>
Subject: Re: SLUB performance regression vs SLAB
Date: Fri, 05 Oct 2007 14:31:24 -0700 (PDT)
Message-ID: <20071005.143124.74549703.davem@davemloft.net>
References: <20071004.135537.39158051.davem@davemloft.net>
	<470554D9.2050505@redhat.com>
	<1191616320.5838.26.camel@lappy>
Mime-Version: 1.0
Content-Type: Text/Plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Cc: cebbert@redhat.com, willy@linux.intel.com, clameter@sgi.com,
	nickpiggin@yahoo.com.au, hch@lst.de, mel@skynet.ie,
	linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
	dgc@sgi.com, jens.axboe@oracle.com, suresh.b.siddha@intel.com
To: a.p.zijlstra@chello.nl
Return-path: <linux-fsdevel-owner@vger.kernel.org>
Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:46310
	"EHLO sunset.davemloft.net" rhost-flags-OK-FAIL-OK-OK)
	by vger.kernel.org with ESMTP id S1752095AbXJEVbZ (ORCPT
	<rfc822;linux-fsdevel@vger.kernel.org>);
	Fri, 5 Oct 2007 17:31:25 -0400
In-Reply-To: <1191616320.5838.26.camel@lappy>
Sender: linux-fsdevel-owner@vger.kernel.org
List-Id: linux-fsdevel.vger.kernel.org

From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Fri, 05 Oct 2007 22:32:00 +0200

> Focus on the slab allocator usage, instrument it, record a trace,
> generate a statistical model that matches, and write a small
> programm/kernel module that has the same allocation pattern. Then verify
> this statistical workload still shows the same performance difference.
> 
> Easy: no
> Doable: yes

The other important bit is likely to generate a lot of DMA traffic
such that the L2 cache bandwidth is getting used on the bus
side by the PCI controller doing invalidations of both dirty
and clean L2 cache lines as devices DMA to/from them.

This will also be exercising the memory controller, further contending
with the cpu when SLAB touches cold data structures.