From owner-freebsd-arch@FreeBSD.ORG Wed Nov 30 21:43:14 2011 Return-Path: Delivered-To: freebsd-arch@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id A662F1065670 for ; Wed, 30 Nov 2011 21:43:14 +0000 (UTC) (envelope-from andreast-list@fgznet.ch) Received: from smtp.fgznet.ch (mail.fgznet.ch [81.92.96.47]) by mx1.freebsd.org (Postfix) with ESMTP id 4AB938FC08 for ; Wed, 30 Nov 2011 21:43:13 +0000 (UTC) Received: from deuterium.andreas.nets (dhclient-91-190-14-19.flashcable.ch [91.190.14.19]) by smtp.fgznet.ch (8.13.8/8.13.8/Submit_SMTPAUTH) with ESMTP id pAULg1Cg009303; Wed, 30 Nov 2011 22:42:03 +0100 (CET) (envelope-from andreast-list@fgznet.ch) Message-ID: <4ED6A36D.1050107@fgznet.ch> Date: Wed, 30 Nov 2011 22:43:09 +0100 From: Andreas Tobler User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.5; rv:8.0) Gecko/20111105 Thunderbird/8.0 MIME-Version: 1.0 To: Kostik Belousov References: <4ED5BE19.70805@fgznet.ch> <20111130162236.GA50300@deviant.kiev.zoral.com.ua> <4ED65F70.7050700@fgznet.ch> <20111130170936.GB50300@deviant.kiev.zoral.com.ua> <4ED66B75.3060409@fgznet.ch> <20111130200103.GE50300@deviant.kiev.zoral.com.ua> <4ED698EB.8090904@fgznet.ch> <20111130212439.GF50300@deviant.kiev.zoral.com.ua> In-Reply-To: <20111130212439.GF50300@deviant.kiev.zoral.com.ua> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Scanned-By: MIMEDefang 2.64 on 81.92.96.47 Cc: FreeBSD Arch Subject: Re: powerpc64 malloc limit? X-BeenThere: freebsd-arch@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussion related to FreeBSD architecture List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 30 Nov 2011 21:43:14 -0000 On 30.11.11 22:24, Kostik Belousov wrote: > On Wed, Nov 30, 2011 at 09:58:19PM +0100, Andreas Tobler wrote: >> On 30.11.11 21:01, Kostik Belousov wrote: >>> On Wed, Nov 30, 2011 at 06:44:21PM +0100, Andreas Tobler wrote: >>>> On 30.11.11 18:09, Kostik Belousov wrote: >>>>> On Wed, Nov 30, 2011 at 05:53:04PM +0100, Andreas Tobler wrote: >>>>>> On 30.11.11 17:22, Kostik Belousov wrote: >>>>>>> On Wed, Nov 30, 2011 at 06:24:41AM +0100, Andreas Tobler wrote: >>>>>>>> All, >>>>>>>> >>>>>>>> while working on gcc I found a very strange situation which renders my >>>>>>>> powerpc64 machine unusable. >>>>>>>> The test case below tries to allocate that much memory as 'wanted'. >>>>>>>> The >>>>>>>> same test case on amd64 returns w/o trying to allocate mem because the >>>>>>>> size is far to big. >>>>>>>> >>>>>>>> I couldn't find the reason so far, that's why I'm here. >>>>>>>> >>>>>>>> As Nathan pointed out the VM_MAXUSER_SIZE is the biggest on powerpc64: >>>>>>>> #define VM_MAXUSER_ADDRESS (0x7ffffffffffff000UL) >>>>>>>> >>>>>>>> So, I'd expect a system to return an allocation error when a user >>>>>>>> tries >>>>>>>> to allocate too much memory and not really trying it and going to be >>>>>>>> unusable. Iow, I'd exepect the situation on powerpc64 as I see on >>>>>>>> amd64. >>>>>>>> >>>>>>>> Can anybody explain me the situation, why do I not have a working >>>>>>>> limit >>>>>>>> on powerpc64? >>>>>>>> >>>>>>>> The machine itself has 7GB RAM and 12GB swap. The amd64 where I >>>>>>>> compared >>>>>>>> has around 4GB/4GB RAM/swap. >>>>>>>> >>>>>>>> TIA, >>>>>>>> Andreas >>>>>>>> >>>>>>>> include >>>>>>>> #include >>>>>>>> >>>>>>>> int main() >>>>>>>> { >>>>>>>> void *p; >>>>>>>> >>>>>>>> p = (void*) malloc (1152921504606846968ULL); >>>>>>>> if (p != NULL) >>>>>>>> printf("p = %p\n", p); >>>>>>>> >>>>>>>> printf("p = %p\n", p); >>>>>>>> return (0); >>>>>>>> } >>>>>>> >>>>>>> First, you should provide details of what consistutes 'the unusable >>>>>>> machine situation' on powerpc. >>>>>> >>>>>> I can not login anymore, everything is stuck except the core control >>>>>> mechanisms for example the fan controller. >>>>>> >>>>>> Top reports 'ugly' figures, below from a earlier try: >>>>>> >>>>>> last pid: 6790; load averages: 0.78, 0.84, 0.86 up 0+00:34:52 >>>>>> 22:42:29 47 processes: 1 running, 46 sleeping >>>>>> CPU: 0.0% user, 0.0% nice, 15.4% system, 11.8% interrupt, 72.8% idle >>>>>> Mem: 5912M Active, 570M Inact, 280M Wired, 26M Cache, 104M Buf, 352K >>>>>> Free >>>>>> Swap: 12G Total, 9904M Used, 2383M Free, 80% Inuse, 178M Out >>>>>> >>>>>> PID USERNAME THR PRI NICE SIZE RES STATE C TIME WCPU >>>>>> COMMAND >>>>>> 6768 andreast 1 52 01073741824G 6479M pfault 1 0:58 >>>>>> 18.90% 31370. >>>>>> >>>>>> And after my mem and swap are full I see swap_pager_getswapspace(16) >>>>>> failed. >>>>>> >>>>>> In this state I can only power-cycle the machine. >>>>>> >>>>>>> That said, on amd64 the user map is between 0 and 0x7fffffffffff, which >>>>>>> obviously less then the requested allocation size 0x100000000000000. >>>>>>> If you look at the kdump output on amd64, you will see that malloc() >>>>>>> tries to mmap() the area, fails and retries with obreak(). Default >>>>>>> virtual memory limit is unlimited, so my best quess is that on amd64 >>>>>>> vm_map_findspace() returns immediately. >>>>>>> >>>>>>> On powerpc64, I see no reason why vm_map_entry cannot be allocated, but >>>>>>> please note that vm object and pages shall be only allocated on demand. >>>>>>> So I am curious how does your machine breaks and where. >>>>>> >>>>>> I would expect that the 'system' does not allow me to allocate that much >>>>>> of ram. >>>>> >>>>> Does the issue with machine going into limbo reproducable with the code >>>>> you posted ? >>>> >>>> If I understand you correctly, yes. I can launch the test case and the >>>> machine is immediately unusable. Means I can not kill the process nor >>>> can I log in. Also, top does not show anything useful. >>> Again, let me restate my question: the single mmap() of the huge size is >>> enough for powerpc64 machine to break apart ? >> >> I can't answer. I don't know yet. >> >>> What happen if you insert sleep(1000000); call before return ? Do not kill >>> the process, I want to know is machine dead while the process sleeps. >> >> Ok, during the 'sleep' the machine is usable. top is reporting figures, >> I can log in and edit files. The process runs now for aboutt 30'. >> >> When I kill the process, I do not get back to the shell nor can I log >> in. Also top stops reporting. >> But as you said, I didn't kill in this run. > Then, as Alan Cox pointed out, caused by the approach taken in powerpc64 > pmap to handle pmap_remove(). It is definitely arch-specific. Ok. I think you mean moea64_remove which is pmap_remove, right? Where did Alan pointed this out? Thank you for the analysis. Andreas