Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752208AbbEYKBn (ORCPT ); Mon, 25 May 2015 06:01:43 -0400 Received: from mail-pd0-f176.google.com ([209.85.192.176]:36214 "EHLO mail-pd0-f176.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751203AbbEYKBj convert rfc822-to-8bit (ORCPT ); Mon, 25 May 2015 06:01:39 -0400 Subject: Re: [RFC PATCH 2/2] arm64: Implement vmalloc based thread_info allocator Mime-Version: 1.0 (Apple Message framework v1283) Content-Type: text/plain; charset=us-ascii From: Jungseok Lee In-Reply-To: <5992243.NYDGjLH37z@wuerfel> Date: Mon, 25 May 2015 19:01:33 +0900 Cc: linux-arm-kernel@lists.infradead.org, Catalin Marinas , barami97@gmail.com, Will Deacon , linux-kernel@vger.kernel.org, linux-mm@kvack.org Content-Transfer-Encoding: 8BIT Message-Id: References: <1432483340-23157-1-git-send-email-jungseoklee85@gmail.com> <5992243.NYDGjLH37z@wuerfel> To: Arnd Bergmann X-Mailer: Apple Mail (2.1283) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2434 Lines: 53 On May 25, 2015, at 2:49 AM, Arnd Bergmann wrote: > On Monday 25 May 2015 01:02:20 Jungseok Lee wrote: >> Fork-routine sometimes fails to get a physically contiguous region for >> thread_info on 4KB page system although free memory is enough. That is, >> a physically contiguous region, which is currently 16KB, is not available >> since system memory is fragmented. >> >> This patch tries to solve the problem as allocating thread_info memory >> from vmalloc space, not 1:1 mapping one. The downside is one additional >> page allocation in case of vmalloc. However, vmalloc space is large enough, >> around 240GB, under a combination of 39-bit VA and 4KB page. Thus, it is >> not a big tradeoff for fork-routine service. > > vmalloc has a rather large runtime cost. I'd argue that failing to allocate > thread_info structures means something has gone very wrong. That is why the feature is marked "N" by default. I focused on fork-routine stability rather than performance. Could you give me an idea how to evaluate performance degradation? Running some benchmarks would be helpful, but I would like to try to gather data based on meaningful methodology. > Can you describe the scenario that leads to fragmentation this bad? Android, but I could not describe an exact reproduction procedure step by step since it's behaved and reproduced randomly. As reading the following thread from mm mailing list, a similar symptom is observed on other systems. https://lkml.org/lkml/2015/4/28/59 Although I do not know the details of a system mentioned in the thread, even order-2 page allocation is not smoothly operated due to fragmentation on low memory system. I think the point is *low memory system*. 64-bit kernel is usually a feasible option when system memory is enough, but 64-bit kernel and low memory system combo is not unusual in case of ARM64. > Could the stack size be reduced to 8KB perhaps? I guess probably not. A commit, 845ad05e, says that 8KB is not enough to cover SpecWeb benchmark. The stack size is 16KB on x86_64. I am not sure whether all applications, which work fine on x86_64 machine, run very well on ARM64 with 8KB stack size. Best Regards Jungseok Lee-- 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/