From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andrey Korolyov Subject: XFS preallocation with lot of small objects Date: Wed, 11 Dec 2013 11:24:23 +0400 Message-ID: <52A81327.1000402@xdel.ru> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Return-path: Received: from mail-bk0-f43.google.com ([209.85.214.43]:45932 "EHLO mail-bk0-f43.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750759Ab3LKHZj (ORCPT ); Wed, 11 Dec 2013 02:25:39 -0500 Received: by mail-bk0-f43.google.com with SMTP id mz12so148222bkb.16 for ; Tue, 10 Dec 2013 23:25:38 -0800 (PST) Received: from [192.168.1.34] (95-31-29-125.broadband.corbina.ru. [95.31.29.125]) by mx.google.com with ESMTPSA id no2sm13779559bkb.15.2013.12.10.23.25.36 for (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Tue, 10 Dec 2013 23:25:37 -0800 (PST) Sender: ceph-devel-owner@vger.kernel.org List-ID: To: ceph-devel@vger.kernel.org Hello, Due to lot of reports of ENOSPC for xfs-based stores may be it worth to introduce an option to, say, ceph-deploy which will pass allocsize= param to the mount effectively disabling Dynamic Preallocation? Of course not every case really worth it because of related performance impact. If there is any method to calculate 'real' allocation on such volumes, it can be put to the docs as a measurement suggestion too.