From mboxrd@z Thu Jan 1 00:00:00 1970 From: Howard Chu Subject: Re: newstore direction Date: Fri, 23 Oct 2015 22:23:30 +0100 Message-ID: <562AA552.702@symas.com> References: <5626BECA.7070306@redhat.com> <5627981B.2040409@redhat.com> <562A14D3.4070509@redhat.com> <562A1E69.2050704@redhat.com> <562A4B58.1030407@symas.com> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from zill.ext.symas.net ([69.43.206.106]:56896 "EHLO zill.ext.symas.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751469AbbJWVXl (ORCPT ); Fri, 23 Oct 2015 17:23:41 -0400 In-Reply-To: Sender: ceph-devel-owner@vger.kernel.org List-ID: To: Gregory Farnum Cc: Ric Wheeler , ceph-devel Gregory Farnum wrote: > On Fri, Oct 23, 2015 at 7:59 AM, Howard Chu wrote: >> If the stream of writes is large enough, you could omit fsync because >> everything is being forced out of the cache to disk anyway. In that >> scenario, the only thing that matters is that the writes get forced out in >> the order you intended, so that an interruption or crash leaves you in a >> known (or knowable) state vs unknown. > > The RADOS storage semantics actually require that we know it's durable > on disk as well, unfortunately. But ordered writes would probably let > us batch up commit points in ways that are a lot friendlier for the > drives! Ah, that's too bad. LMDB does fine with only ordering, but never mind. -- -- Howard Chu CTO, Symas Corp. http://www.symas.com Director, Highland Sun http://highlandsun.com/hyc/ Chief Architect, OpenLDAP http://www.openldap.org/project/