From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tim Small Subject: Re: Deadlock in md barrier code? / RAID1 / LVM CoW snapshot + ext3 / Debian 5.0 - lenny 2.6.26 kernel Date: Mon, 06 Dec 2010 15:42:31 +0000 Message-ID: <4CFD0467.2060606@seoss.co.uk> References: <4C938103.1010304@seoss.co.uk> <20100918085925.5fee83ee@notabene> <4C97BD21.1040405@seoss.co.uk> <4C991D61.1040400@seoss.co.uk> <20100922083039.283ccdfd@notabene> <4CBC9774.6020500@seoss.co.uk> <20101019171650.20c83e7e@notabene> <4CBDC641.9090009@seoss.co.uk> <4CBDC756.7010606@seoss.co.uk> <4CBDF190.2000007@seoss.co.uk> <4CBF5267.7080304@seoss.co.uk> <20101021100429.4879a001@notabene> <4CE56AA9.2010905@seoss.co.uk> <20101122100509.76592b59@notabene.brown> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20101122100509.76592b59@notabene.brown> Sender: linux-raid-owner@vger.kernel.org To: Neil Brown Cc: "linux-raid@vger.kernel.org" List-Id: linux-raid.ids On 11/21/10 23:05, Neil Brown wrote: > Yes. Superficially, it appears that there are still 5 outstanding read > requests that are not being completed. I cannot guess how OpenVZ would > cause that, but I don't really know much about OpenVZ Hi Neil, I very much appreciate your help debugging this. I opened a bug against the relevant Debian kernel. Now that this is pretty well characterised, I think it's probably best to just workaround it (e.g. by setting speed_limit_max to 0 during the backups which were tripping over this), until such time as the kernel can be replaced with a more recent one... Cheers, Tim. -- South East Open Source Solutions Limited Registered in England and Wales with company number 06134732. Registered Office: 2 Powell Gardens, Redhill, Surrey, RH1 1TQ VAT number: 900 6633 53 http://seoss.co.uk/ +44-(0)1273-808309