Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753484Ab0GZFEJ (ORCPT ); Mon, 26 Jul 2010 01:04:09 -0400 Received: from mga01.intel.com ([192.55.52.88]:52729 "EHLO mga01.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753290Ab0GZFEF (ORCPT ); Mon, 26 Jul 2010 01:04:05 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.55,260,1278313200"; d="scan'208";a="589627674" Subject: Re: [PATCH] Don't apply for write lock on tasklist_lock if parent doesn't ptrace other processes From: "Zhang, Yanmin" To: Oleg Nesterov Cc: Roland McGrath , Andrew Morton , LKML , andi.kleen@intel.com, stable@kernel.org In-Reply-To: <20100723173453.GA29831@redhat.com> References: <1279176663.2096.1264.camel@ymzhang.sh.intel.com> <20100721144944.5351c741.akpm@linux-foundation.org> <20100721222529.EFBAA400B6@magilla.sf.frob.com> <20100722090524.GA6647@redhat.com> <1279874705.2096.1274.camel@ymzhang.sh.intel.com> <20100723173453.GA29831@redhat.com> Content-Type: text/plain; charset="ISO-8859-1" Date: Mon, 26 Jul 2010 13:05:31 +0800 Message-Id: <1280120732.2085.3.camel@ymzhang.sh.intel.com> Mime-Version: 1.0 X-Mailer: Evolution 2.28.0 (2.28.0-2.fc12) Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1359 Lines: 34 On Fri, 2010-07-23 at 19:34 +0200, Oleg Nesterov wrote: > On 07/23, Zhang, Yanmin wrote: > > > > On Thu, 2010-07-22 at 11:05 +0200, Oleg Nesterov wrote: > > > I am not surpized perf blaims tasklist, but I am really surpized this patch > > > adds 10% improvement... > > I changed aim7 workfile to focus on fork/exec and other a couple of sub-cases. > > And this behavior is clear on 8-socket machines. > > Thanks... > > > After applying my patch (although it's incorrect as there is a race with TRACEME), > > perf shows write_lock_irq in forget_original_parent consumes less than 40% cpu time on > > 8-socket machine. > > Any chance you can test the patch I sent? It should have the same effect, > otherwise there is something interesting. 1) with my patch, we got about 13% improvement; 2) With your patch, we got about 11% improvement; Performance is very sensitive to spinlock contention on large machines. > > > Is it possible to optimize it to use finer locks instead of the global tasklist_lock? > > Heh. We must optimize it. But it is not clear when ;) Thanks. It's better to remove the big lock. -- 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/