From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from relay.sgi.com (relay2.corp.sgi.com [137.38.102.29]) by oss.sgi.com (Postfix) with ESMTP id 9AF787F51 for ; Sat, 7 Mar 2015 13:14:57 -0600 (CST) Received: from cuda.sgi.com (cuda3.sgi.com [192.48.176.15]) by relay2.corp.sgi.com (Postfix) with ESMTP id 86DE0304043 for ; Sat, 7 Mar 2015 11:14:54 -0800 (PST) Received: from mx-rz-3.rrze.uni-erlangen.de (mx-rz-3.rrze.uni-erlangen.de [131.188.11.22]) by cuda.sgi.com with ESMTP id j8r9aVVr3WU9VzSs (version=TLSv1 cipher=AES256-SHA bits=256 verify=NO) for ; Sat, 07 Mar 2015 11:14:53 -0800 (PST) Received: from boeck1.rrze.uni-erlangen.de (boeck1.rrze.uni-erlangen.de [131.188.11.31]) by mx-rz-3.rrze.uni-erlangen.de (Postfix) with ESMTP id 3kzwVg0xC4zFLM9 for ; Sat, 7 Mar 2015 20:14:51 +0100 (CET) Received: from mx-rz-3.rrze.uni-erlangen.de ([131.188.11.22]) by boeck1.rrze.uni-erlangen.de (boeck1.rrze.uni-erlangen.de [131.188.11.31]) (amavisd-new, port 10026) with LMTP id BaAf2D4ipaqS for ; Sat, 7 Mar 2015 20:14:50 +0100 (CET) Received: from mx-rz-smart.rrze.uni-erlangen.de (mx-rz-smart.rrze.uni-erlangen.de [IPv6:2001:638:a000:1025::1e]) by mx-rz-3.rrze.uni-erlangen.de (Postfix) with ESMTP id 3kzwVf2zSlzFLcS for ; Sat, 7 Mar 2015 20:14:50 +0100 (CET) Received: from [131.188.78.30] (legolas.rrze.uni-erlangen.de [131.188.78.30]) by mailhub.rrze.uni-erlangen.de (Postfix) with ESMTP id 3kzwVf1xbhzFLM9 for ; Sat, 7 Mar 2015 20:14:50 +0100 (CET) Message-ID: <54FB4E29.7080705@fau.de> Date: Sat, 07 Mar 2015 20:14:49 +0100 From: Michael Meier MIME-Version: 1.0 Subject: Re: XFS hangs with XFS: possible memory allocation deadlock in kmem_alloc References: <54FAAE16.6090505@fau.de> <20150307140721.GA9098@bfoster.bfoster> In-Reply-To: <20150307140721.GA9098@bfoster.bfoster> List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: xfs-bounces@oss.sgi.com Sender: xfs-bounces@oss.sgi.com To: xfs@oss.sgi.com On 03/07/2015 03:07 PM, Brian Foster wrote: > Thanks for the data. Some notes from the backtraces in the first > instance: Thank you for the quick reply. I'm not sure if the first instance is the most representative: It was very short - only one message was logged and then everything was fine again. The later one starting at 00:48 in the logs however was long enough to make our nagios complain. > Considering this is a large memory box (64g), I wonder if some vm tuning > might help mitigate this behavior..? For example, increase > /proc/sys/vm/min_free_kbytes in hopes of allowing more memory for these > allocations when under pressure, or tune down the > dirty_ratio/dirty_background_ratio thresholds to more aggressively get > data onto disk..? That idea had occoured to me too, but at least vm.min_free_kbytes=4000000 vm.vfs_cache_pressure=200 did not prevent the problem from occouring. Regards, -- Michael Meier, Zentrale Systeme Friedrich-Alexander-Universitaet Erlangen-Nuernberg Regionales Rechenzentrum Erlangen Martensstrasse 1, 91058 Erlangen, Germany Tel.: +49 9131 85-28973, Fax: +49 9131 302941 michael.meier@fau.de www.rrze.fau.de _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs