Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751559Ab0FYFJ6 (ORCPT ); Fri, 25 Jun 2010 01:09:58 -0400 Received: from mail-iw0-f174.google.com ([209.85.214.174]:50750 "EHLO mail-iw0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751077Ab0FYFJ5 convert rfc822-to-8bit (ORCPT ); Fri, 25 Jun 2010 01:09:57 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=MZw4ibd6woE4LATlIWuhkRJaMYjyAta8dZ36V52HtSOgQZlKlMiu3iMvv5R6S0C+OX aXgNfd6TgMaJ6o5YtYCPJBxTaSy3VDQOP0H3bnYFoICQECrwYmm16kKrtHio/UdGuE5c eMHCfySONFfBQlpqQzhWmZK6rPtnLZYFLHEsQ= MIME-Version: 1.0 In-Reply-To: <20100625133542.8047.A69D9226@jp.fujitsu.com> References: <20100625133542.8047.A69D9226@jp.fujitsu.com> Date: Fri, 25 Jun 2010 15:09:56 +1000 Message-ID: Subject: Re: 2.6.35-rc1 system oom, many processes killed but memory not free From: Andrew Hendry To: KOSAKI Motohiro Cc: linux-kernel Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2593 Lines: 78 Yes I made a mistake setting up ramdisk too big, but not sure why it allowed me to set it up like that. I think after ramdisk used all the memory, even after unmounting then other processes still cannot use it. oom killer gets very aggressive but cannot fix problem. I have updated to rc3 and will test again on weekend. I will turn on mem leak checker, is there anything else i should configure? On Fri, Jun 25, 2010 at 3:00 PM, KOSAKI Motohiro wrote: >> I left a 2.6.35-rc1 system, ubuntu 10.4/64 building randconfigs in a >> ramdisk overnight. >> /dev/ram0 ? ? ? ? ? ? ?9842848 ? 5141780 ? 4201068 ?56% /media/ramdisk > > your total memory size is 8GB, but ramdisk size is 9.8GB. it's odd settings. > >> >> After about 3 hours oom killer started killing nearly all the >> processes, but the memory is still not released. Could ramdisk cause >> this? How can I find out what is still using all the memory? > > Could. > but I'm unclear your case was happen by only ramdisk. > Can you remove such ramdisk at once? > >> >> cat /proc/meminfo >> MemTotal: ? ? ? ?8187304 kB >> MemFree: ? ? ? ? ?231976 kB >> Buffers: ? ? ? ? ? ? 424 kB >> Cached: ? ? ? ? ? ?19728 kB >> SwapCached: ? ? ? ?51144 kB >> Active: ? ? ? ? ? ?14056 kB >> Inactive: ? ? ? ? ?72592 kB >> Active(anon): ? ? ?12900 kB >> Inactive(anon): ? ?53940 kB >> Active(file): ? ? ? 1156 kB >> Inactive(file): ? ?18652 kB >> Unevictable: ? ? ? ? ? 0 kB >> Mlocked: ? ? ? ? ? ? ? 0 kB >> SwapTotal: ? ? ? 1986556 kB >> SwapFree: ? ? ? ?1504676 kB >> Dirty: ? ? ? ? ? ? ? ? 0 kB >> Writeback: ? ? ? ? 19720 kB >> AnonPages: ? ? ? ? 32884 kB >> Mapped: ? ? ? ? ? ? 4760 kB >> Shmem: ? ? ? ? ? ? ? ? 4 kB >> Slab: ? ? ? ? ? ? ?51652 kB >> SReclaimable: ? ? ?28816 kB >> SUnreclaim: ? ? ? ?22836 kB >> KernelStack: ? ? ? ?2880 kB >> PageTables: ? ? ? ?18484 kB >> NFS_Unstable: ? ? ? ? ?0 kB >> Bounce: ? ? ? ? ? ? ? ?0 kB >> WritebackTmp: ? ? ? ? ?0 kB >> CommitLimit: ? ? 6080208 kB >> Committed_AS: ? ?1133944 kB >> VmallocTotal: ? 34359738367 kB >> VmallocUsed: ? ? ?350936 kB >> VmallocChunk: ? 34359369212 kB >> HardwareCorrupted: ? ? 0 kB >> HugePages_Total: ? ? ? 0 >> HugePages_Free: ? ? ? ?0 >> HugePages_Rsvd: ? ? ? ?0 >> HugePages_Surp: ? ? ? ?0 >> Hugepagesize: ? ? ? 2048 kB >> DirectMap4k: ? ? ? ?7616 kB >> DirectMap2M: ? ? 8372224 kB > > > > -- 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/