From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752906AbYLCOvM (ORCPT ); Wed, 3 Dec 2008 09:51:12 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751098AbYLCOu5 (ORCPT ); Wed, 3 Dec 2008 09:50:57 -0500 Received: from one.firstfloor.org ([213.235.205.2]:47249 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750895AbYLCOu4 (ORCPT ); Wed, 3 Dec 2008 09:50:56 -0500 To: "wassim dagash" Cc: linux-kernel@vger.kernel.org Subject: Re: KSWAPD Algorithm From: Andi Kleen References: Date: Wed, 03 Dec 2008 15:51:11 +0100 In-Reply-To: (wassim dagash's message of "Wed, 3 Dec 2008 09:02:49 +0200") Message-ID: <87prk9xqg0.fsf@basil.nowhere.org> User-Agent: Gnus/5.1008 (Gnus v5.10.8) Emacs/21.3 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org "wassim dagash" writes: > Hi All, > Description: > I countered a weird problem with kswapd: > it runs in some infinite loop trying to swap until order 10 of zone > highmem is OK, While zone higmem (as I understand) has nothing to do > with contiguous physical memory (cause there is no 1-1 mapping) which > means kswapd will continue to try to balance order 10 of zone highmem > forever (or until someone release a very large chunk of highmem). > Can anyone please explain me the algorithm of kswapd and why it tries > to balance order 10 of zone higmem ? hugetlbfs requires large continuous mappings even in highmem to map 2MB pages or similar to user space. However order 10 seems pretty high, normally that's only order 8 on a i386 system. -Andi -- ak@linux.intel.com