From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753332Ab1CFCuT (ORCPT ); Sat, 5 Mar 2011 21:50:19 -0500 Received: from smtp-out.google.com ([74.125.121.67]:28781 "EHLO smtp-out.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752308Ab1CFCuR (ORCPT ); Sat, 5 Mar 2011 21:50:17 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=google.com; s=beta; h=date:from:x-x-sender:to:cc:subject:in-reply-to:message-id :references:user-agent:mime-version:content-type; b=CNNfWtnY7hBRWK1mQOYMnpWpjp8PLvubxaG2mR2mOscxqh0Ezum7boPsr+LmXGIhpB 7ERGTuO1lEFhTBtfp5FA== Date: Sat, 5 Mar 2011 18:50:11 -0800 (PST) From: David Rientjes X-X-Sender: rientjes@chino.kir.corp.google.com To: Justin Mattock cc: Linux Kernel Mailing List Subject: Re: [] ? __alloc_pages_nodemask+0x622/0x696 In-Reply-To: Message-ID: References: User-Agent: Alpine 2.00 (DEB 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-System-Of-Record: true Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Sat, 5 Mar 2011, Justin Mattock wrote: > [ 339.787008] SLUB: Unable to allocate memory on node -1 (gfp=0x20) > [ 339.787008] cache: kmalloc-8192, object size: 8192, buffer size: > 8264, default order: 3, min order: 2 > [ 339.787008] kmalloc-8192 debugging increased min order, use > slub_debug=O to disable. > [ 339.787008] node 0: slabs: 181, objs: 543, free: 0 > [ 339.790575] skbuff alloc of size 3904 failed > [ 339.823775] swapper: page allocation failure. order:2, mode:0x4020 > [ 339.823781] Pid: 0, comm: swapper Not tainted 2.6.38-rc7-00143-gd1b152c #7 > [ 339.823783] Call Trace: > [ 339.823786] [] ? __alloc_pages_nodemask+0x622/0x696 > [ 339.823811] [] ? ath_rxbuf_alloc+0x29/0x9a [ath] > [ 339.823815] [] ? new_slab+0x7b/0x1c6 > [ 339.823819] [] ? ath_rxbuf_alloc+0x29/0x9a [ath] > [ 339.823823] [] ? T.925+0x163/0x29c > [ 339.823827] [] ? mempool_destroy+0xf/0x17 > [ 339.823832] [] ? ath_rxbuf_alloc+0x29/0x9a [ath] > [ 339.823836] [] ? __kmalloc_track_caller+0xfe/0x190 > Order-2 atomic allocations are always going to be difficult since we can't do synchronous compaction or reclaim, but I'd try the suggestion shown above: boot with slub_debug=O or disable slub debugging so that kmalloc-8192 is actually order-1 like it should be.