From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jason Dillaman Subject: Re: Re: Re:Re: Re:Re:Re:Re: How does rbd-mirror preserve the order of WRITE operations that finished on the primary cluster Date: Tue, 6 Jun 2017 07:20:02 -0400 Message-ID: References: <70c5c552.66e6.15c766dce68.Coremail.xxhdx1985126@163.com> <75e21ee8.f334.15c78f23929.Coremail.xxhdx1985126@163.com> <428d3e79.3d2.15c7a56a64f.Coremail.xxhdx1985126@163.com> <448ceff0.46ce.15c7b5c0b16.Coremail.xxhdx1985126@163.com> <344a1254.5a75.15c7b942fa4.Coremail.xxhdx1985126@163.com> <762fe21a.9068.15c7c58f41b.Coremail.xxhdx1985126@163.com> <349ebded.9bdc.15c7c722502.Coremail.xxhdx1985126@163.com> Reply-To: dillaman@redhat.com Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Return-path: Received: from mail-yb0-f177.google.com ([209.85.213.177]:33469 "EHLO mail-yb0-f177.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751577AbdFFLUD (ORCPT ); Tue, 6 Jun 2017 07:20:03 -0400 Received: by mail-yb0-f177.google.com with SMTP id 202so40620748ybd.0 for ; Tue, 06 Jun 2017 04:20:03 -0700 (PDT) In-Reply-To: <349ebded.9bdc.15c7c722502.Coremail.xxhdx1985126@163.com> Sender: ceph-devel-owner@vger.kernel.org List-ID: To: xxhdx1985126 Cc: Haomai Wang , Sage Weil , "ceph-devel@vger.kernel.org" On Tue, Jun 6, 2017 at 4:07 AM, xxhdx1985126 wrote: > So, if that case happens, rbd-mirror will go on replicate subsequent writes, is this right? Yes -- until it reaches a flush event and is stalled on the uncommitted IO from the down OSD (or until it reaches the hard-stop of 100 in-flight, uncommitted IOs). -- Jason