From mboxrd@z Thu Jan  1 00:00:00 1970
From: Andi Kleen <andi@firstfloor.org>
Subject: Re: [PATCH] libnuma: disable caching of node cpusmasks
Date: Tue, 16 Jun 2015 16:48:05 +0200
Message-ID: <20150616144805.GZ19417@two.firstfloor.org>
References: <1434122172-26560-1-git-send-email-pholasek@redhat.com>
 <20150612153001.GW19417@two.firstfloor.org>
 <20150616144053.GH3650@localhost.localdomain>
Mime-Version: 1.0
Return-path: <linux-numa-owner@vger.kernel.org>
Content-Disposition: inline
In-Reply-To: <20150616144053.GH3650@localhost.localdomain>
Sender: linux-numa-owner@vger.kernel.org
List-ID: <linux-numa.vger.kernel.org>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
To: Petr Holasek <pholasek@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>, linux-numa@vger.kernel.org, Filipe Brandenburger <filbranden@google.com>, Cliff Wickman <cpw@sgi.com>

> I did simple comparison for 1 million of numa_node_to_cpus() calls
> and disabled caching extended time three times (from 10 seconds to 30).

that's a big slow down. Someone could have it in their fast paths.

I think need a time out or so.

-Andi