From mboxrd@z Thu Jan 1 00:00:00 1970 From: Christoph Hellwig Subject: Re: Persistent Reservation API V2 Date: Fri, 21 Aug 2015 08:59:54 +0200 Message-ID: <20150821065954.GA14559@lst.de> References: <1439360604-16192-1-git-send-email-hch@lst.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org To: Keith Busch Cc: Jens Axboe , linux-api@vger.kernel.org, dm-devel@redhat.com, linux-nvme@lists.infradead.org, linux-scsi@vger.kernel.org, linux-kernel@vger.kernel.org List-Id: linux-api@vger.kernel.org On Thu, Aug 20, 2015 at 11:56:36PM +0000, Keith Busch wrote: > NVMe can also specify > if whether or not a reservation should persist through power-loss. SCSI does as well, it's the APTPL flag. However reservations not persistent through a power loss are basically useless, so I decided to force them on in the API. From the documentation: "All implementations are expected to ensure the reservations survive a power loss" So I would prefer not to add it, or if we really have to as a negative flag to specifically opt out of the APTPL behavior. > with it. For example, NVMe can ignore existing keys when acquiring a > reservation in addition to registering a new key. This sounds like a sensible addition to me, and I wouldn't be surprised if future SPC versions will add this flag.