From mboxrd@z Thu Jan 1 00:00:00 1970 From: Greg Stark Subject: Re: [PATCH] scsi/sata write barrier support Date: 01 Mar 2005 10:55:27 -0500 Message-ID: <87r7izz7gw.fsf@stark.xeocode.com> References: <20050127120244.GO2751@suse.de> <87acpxurwf.fsf@stark.xeocode.com> <20050222071340.GC2835@suse.de> <874qg4v81q.fsf@stark.xeocode.com> <20050301084741.GD12295@suse.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Received: from stark.xeocode.com ([216.58.44.227]:49545 "EHLO stark.xeocode.com") by vger.kernel.org with ESMTP id S261956AbVCAPzk (ORCPT ); Tue, 1 Mar 2005 10:55:40 -0500 In-Reply-To: <20050301084741.GD12295@suse.de> Sender: linux-scsi-owner@vger.kernel.org List-Id: linux-scsi@vger.kernel.org To: Jens Axboe Cc: Greg Stark , Linux Kernel , Bartlomiej Zolnierkiewicz , Jeff Garzik , linux-scsi@vger.kernel.org Jens Axboe writes: > > What about a non-journaled fs, or at least a meta-data-only-journaled fs? > > Journaled FS's don't mix well with transaction based databases since they're > > basically doing their own journaling anyways. > > Only works on ext3 and reiserfs currently. Does it work in resierfs with data=writeback or ext3 with tune2fs's journal_data_writeback? What I'm wondering is whether it only kicks in when the journal gets synchronized or whether it kicks in whenever you call fsync even if no journaling is involved. Writeback mode isn't really necessary, Postgres makes every effort to use fdatasync or equivalent so no metadata changes are really necessary. So the question is also, do the filesystems initiate a cache flush even if no metadata changes are being synchronized? -- greg