From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jamie Lokier Subject: Re: [patch 9/9] mm: do_sync_mapping_range integrity fix Date: Fri, 31 Oct 2008 20:03:04 +0000 Message-ID: <20081031200304.GE16128@shareable.org> References: <20081028144715.683011000@suse.de> <20081028145734.706927000@nick.local0.net> <20081030161344.0ed5ca52.akpm@linux-foundation.org> <20081031091616.GF19268@wotan.suse.de> <20081031030432.426e3c51.akpm@linux-foundation.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Nick Piggin , linux-fsdevel@vger.kernel.org, david@fromorbit.com, chris.mason@oracle.com To: Andrew Morton Return-path: Received: from mail2.shareable.org ([80.68.89.115]:53630 "EHLO mail2.shareable.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751284AbYJaUDI (ORCPT ); Fri, 31 Oct 2008 16:03:08 -0400 Content-Disposition: inline In-Reply-To: <20081031030432.426e3c51.akpm@linux-foundation.org> Sender: linux-fsdevel-owner@vger.kernel.org List-ID: Andrew Morton wrote: > That's a bit grubby, because userspace could do > > sync_file_range(SYNC_FILE_RANGE_WAIT_BEFORE); > sync_file_range(SYNC_FILE_RANGE_WRITE); > > expecting it to have the same behaviour as > > sync_file_range(SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE); Yes it could. The documentation for sync_file_range is unclear enough already. If the distinction is useful, a different SYNC_FILE_RANGE_ flag may be appropriate to indicate write-for-performance vs write-for-integrity, rather than such a peculiar subtlety. -- Jamie