From mboxrd@z Thu Jan 1 00:00:00 1970 From: Josh Durgin Subject: Re: About Fio backend with ObjectStore API Date: Tue, 30 Jun 2015 16:21:19 -0700 Message-ID: <5593246F.2030201@redhat.com> References: <99767EA2E27DD44DB4E9F9B9ACA458C03B319D0D@SSIEXCH-MB3.ssi.samsung.com> <99767EA2E27DD44DB4E9F9B9ACA458C03B319DF2@SSIEXCH-MB3.ssi.samsung.com> <55931A5E.5000408@redhat.com> <55931EEE.9070604@kernel.dk> <559323CC.1000003@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from mx1.redhat.com ([209.132.183.28]:52705 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751772AbbF3XVT (ORCPT ); Tue, 30 Jun 2015 19:21:19 -0400 In-Reply-To: <559323CC.1000003@redhat.com> Sender: ceph-devel-owner@vger.kernel.org List-ID: To: Jens Axboe , Mark Nelson , "James (Fei) Liu-SSI" , Casey Bodley Cc: Haomai Wang , "ceph-devel@vger.kernel.org" , daniel.gollub@gmail.com On 06/30/2015 04:18 PM, Josh Durgin wrote: > Note that ceph's ObjectStore api is internal, and not stable. Maybe not > the best thing to include in packages, though keeping it as an option > at build time might make sense. The api itself isn't that prone to > change, but internal symbols (hooray c++...) certainly are, so any > update of ceph would likely need a recompile of the backend. And now I see the ObjectStore is included statically, so it is doable. It just won't be updated for new ceph without recompiling the backend, which seems fine to me. > > Josh > > On 06/30/2015 03:57 PM, Jens Axboe wrote: >> I'd be more than happy to include it. Daniel has contributed to fio >> before. >> >> Daniel (CC'ed), was it your intent to get this upstream? How do we make >> this happen?