From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752959AbdEENQx (ORCPT ); Fri, 5 May 2017 09:16:53 -0400 Received: from mail-wm0-f49.google.com ([74.125.82.49]:36529 "EHLO mail-wm0-f49.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751352AbdEENQw (ORCPT ); Fri, 5 May 2017 09:16:52 -0400 Date: Fri, 5 May 2017 16:16:49 +0300 From: "Kirill A. Shutemov" To: Dave Hansen Cc: linux-kernel@vger.kernel.org, akpm@linux-foundation.org, linux-mm@kvack.org, kirill.shutemov@linux.intel.com Subject: Re: [PATCH] mm, sparsemem: break out of loops early Message-ID: <20170505131649.t5ffmg7xspndtrc4@node.shutemov.name> References: <20170504174434.C45A4735@viggo.jf.intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20170504174434.C45A4735@viggo.jf.intel.com> User-Agent: NeoMutt/20170428 (1.8.2) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, May 04, 2017 at 10:44:34AM -0700, Dave Hansen wrote: > > From: Dave Hansen > > There are a number of times that we loop over NR_MEM_SECTIONS, > looking for section_present() on each section. But, when we have > very large physical address spaces (large MAX_PHYSMEM_BITS), > NR_MEM_SECTIONS becomes very large, making the loops quite long. > > With MAX_PHYSMEM_BITS=46 and a section size of 128MB, the current > loops are 512k iterations, which we barely notice on modern > hardware. But, raising MAX_PHYSMEM_BITS higher (like we will see > on systems that support 5-level paging) makes this 64x longer and > we start to notice, especially on slower systems like simulators. > A 10-second delay for 512k iterations is annoying. But, a 640- > second delay is crippling. > > This does not help if we have extremely sparse physical address > spaces, but those are quite rare. We expect that most of the > "slow" systems where this matters will also be quite small and > non-sparse. > > To fix this, we track the highest section we've ever encountered. > This lets us know when we will *never* see another > section_present(), and lets us break out of the loops earlier. > > Doing the whole for_each_present_section_nr() macro is probably > overkill, but it will ensure that any future loop iterations that > we grow are more likely to be correct. > > Signed-off-by: Dave Hansen > Cc: Kirill A. Shutemov Tested-by: Kirill A. Shutemov It shaved almost 40 seconds from boot time in qemu with 5-level paging enabled for me :) -- Kirill A. Shutemov