From mboxrd@z Thu Jan 1 00:00:00 1970 From: Christoph Hellwig Subject: Re: os recommendations Date: Wed, 27 Nov 2013 00:14:26 -0800 Message-ID: <20131127081426.GA12165@infradead.org> References: <20131126142243.GA7360@infradead.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from bombadil.infradead.org ([198.137.202.9]:43118 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753290Ab3K0IOb (ORCPT ); Wed, 27 Nov 2013 03:14:31 -0500 Content-Disposition: inline In-Reply-To: Sender: ceph-devel-owner@vger.kernel.org List-ID: To: Sage Weil Cc: Christoph Hellwig , Dominik Mostowiec , ceph-devel , "ceph-users@lists.ceph.com" On Tue, Nov 26, 2013 at 06:50:33AM -0800, Sage Weil wrote: > If syncfs(2) is not present, we have to use sync(2). That means you have > N daemons calling sync(2) to force a commit on a single fs, but all other > mounted fs's are also synced... which means N times the sync(2) calls. > > Fortunately syncfs(2) has been around for a while now, so this only > affects really old distros. And even when glibc does not have a syscall > wrapper for it, we try to call the syscall directly. And for btrfs you were/are using magic ioctls, right. Looks like the page reference in the last post has already been updated, thanks!