From mboxrd@z Thu Jan 1 00:00:00 1970 From: Rutger ter Borg Subject: Rados consistency model Date: Tue, 18 Dec 2012 09:51:03 +0100 Message-ID: Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from plane.gmane.org ([80.91.229.3]:54834 "EHLO plane.gmane.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753947Ab2LRIvP (ORCPT ); Tue, 18 Dec 2012 03:51:15 -0500 Received: from list by plane.gmane.org with local (Exim 4.69) (envelope-from ) id 1Tksta-0002Pd-FA for ceph-devel@vger.kernel.org; Tue, 18 Dec 2012 09:51:26 +0100 Received: from gl-95017.prolocation.net ([62.204.95.17]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Tue, 18 Dec 2012 09:51:26 +0100 Received: from rutger by gl-95017.prolocation.net with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Tue, 18 Dec 2012 09:51:26 +0100 Sender: ceph-devel-owner@vger.kernel.org List-ID: To: ceph-devel@vger.kernel.org Dear list, I have a question regarding concurrency guarantees of Rados. Suppose I have two nodes, say A and B, both running a process, and both using the same rados storage pool, maybe connected through different OSDs. Suppose node A updates an object in the storage pool, and after completion immediately notifies B (through its own messaging layer) that that specific object has been updated. Then, can I assume that, if B re-reads that object, it will always get the updated one? If not, what would be the recommended way of notifying B? IOW, what kind of consistency model should I assume? Thanks, Rutger