Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751964AbbEGChf (ORCPT ); Wed, 6 May 2015 22:37:35 -0400 Received: from g9t5008.houston.hp.com ([15.240.92.66]:42245 "EHLO g9t5008.houston.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751578AbbEGChe (ORCPT ); Wed, 6 May 2015 22:37:34 -0400 Message-ID: <554ACFE8.2050908@hp.com> Date: Wed, 06 May 2015 22:37:28 -0400 From: Waiman Long User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:10.0.12) Gecko/20130109 Thunderbird/10.0.12 MIME-Version: 1.0 To: Mel Gorman CC: Andrew Morton , Nathan Zimmer , Dave Hansen , Scott Norton , Daniel J Blueman , Linux-MM , LKML Subject: Re: [PATCH 0/13] Parallel struct page initialisation v4 References: <1430231830-7702-1-git-send-email-mgorman@suse.de> <554030D1.8080509@hp.com> <5543F802.9090504@hp.com> <554415B1.2050702@hp.com> <20150504143046.9404c572486caf71bdef0676@linux-foundation.org> <20150505104514.GC2462@suse.de> <20150505130255.49ff76bbf0a3b32d884ab2ce@linux-foundation.org> <20150505221329.GE2462@suse.de> <20150505152549.037679566fad8c593df176ed@linux-foundation.org> <20150506071246.GF2462@suse.de> <20150506102220.GH2462@suse.de> <554A5655.6060108@hp.com> In-Reply-To: <554A5655.6060108@hp.com> Content-Type: text/plain; charset=ISO-8859-15; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3203 Lines: 78 On 05/06/2015 01:58 PM, Waiman Long wrote: > On 05/06/2015 06:22 AM, Mel Gorman wrote: >> On Wed, May 06, 2015 at 08:12:46AM +0100, Mel Gorman wrote: >>> On Tue, May 05, 2015 at 03:25:49PM -0700, Andrew Morton wrote: >>>> On Tue, 5 May 2015 23:13:29 +0100 Mel Gorman wrote: >>>> >>>>>> Alternatively, the page allocator can go off and synchronously >>>>>> initialize some pageframes itself. Keep doing that until the >>>>>> allocation attempt succeeds. >>>>>> >>>>> That was rejected during review of earlier attempts at this >>>>> feature on >>>>> the grounds that it impacted allocator fast paths. >>>> eh? Changes are only needed on the allocation-attempt-failed path, >>>> which is slow-path. >>> We'd have to distinguish between falling back to other zones because >>> the >>> high zone is artifically exhausted and normal ALLOC_BATCH >>> exhaustion. We'd >>> also have to avoid falling back to remote nodes prematurely. While I >>> have >>> not tried an implementation, I expected they would need to be in the >>> fast >>> paths unless I used jump labels to get around it. I'm going to try >>> altering >>> when we initialise instead so that it happens earlier. >>> >> Which looks as follows. Waiman, a test on the 24TB machine would be >> appreciated again. This patch should be applied instead of "mm: meminit: >> Take into account that large system caches scale linearly with memory" >> >> ---8<--- >> mm: meminit: Finish initialisation of memory before basic setup >> >> Waiman Long reported that 24TB machines hit OOM during basic setup when >> struct page initialisation was deferred. One approach is to >> initialise memory >> on demand but it interferes with page allocator paths. This patch >> creates >> dedicated threads to initialise memory before basic setup. It then >> blocks >> on a rw_semaphore until completion as a wait_queue and counter is >> overkill. >> This may be slower to boot but it's simplier overall and also gets >> rid of a >> lot of section mangling which existed so kswapd could do the >> initialisation. >> >> Signed-off-by: Mel Gorman >> > > This patch moves the deferred meminit from kswapd to its own kernel > threads started after smp_init(). However, the hash table allocation > was done earlier than that. It seems like it will still run out of > memory in the 24TB machine that I tested on. > > I will certainly try it out, but I doubt it will solve the problem on > its own. It turns out that the two new patches did work on the 24-TB DragonHawk without the "mm: meminit: Take into account that large system caches scale linearly with memory" patch. The bootup time was 357s which was just a few seconds slower than the other bootup times that I sent you yesterday. BTW, do you want to change the following log message as kswapd will no longer be the one doing deferred meminit? kswapd 0 initialised 396098436 pages in 6024ms Cheers, Longman -- 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/