From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Date: Fri, 16 Jun 2017 11:02:49 -0700 From: Christoph Hellwig To: Jens Axboe Cc: Christoph Hellwig , "Darrick J. Wong" , linux-fsdevel@vger.kernel.org, linux-block@vger.kernel.org, adilger@dilger.ca, martin.petersen@oracle.com Subject: Re: [PATCH 04/11] fs: add support for allowing applications to pass in write life time hints Message-ID: <20170616180249.GC27996@infradead.org> References: <1497498312-17704-1-git-send-email-axboe@kernel.dk> <1497498312-17704-5-git-send-email-axboe@kernel.dk> <20170615041503.GB4521@birch.djwong.org> <20170615081914.GD10599@infradead.org> <7f8e2e3c-fa15-6864-7afd-b82e5afb87b5@kernel.dk> <20170616073339.GC8682@infradead.org> <0ac0bb7e-ce8d-cb63-985c-ab2d1f3402f1@kernel.dk> <20170616155206.GB27209@infradead.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: List-ID: On Fri, Jun 16, 2017 at 09:59:38AM -0600, Jens Axboe wrote: > >> Did you see v5? It adds enum write_hint and passes it all the way down, > >> until we transform them into rq/bio flags. > > > > Yes. But with all the way down I mean all the way down to the driver :) > > Only missing part is the request flags. And why make that any different > than the flags we already have now? It'd be trivial to pack the value > into the request flags as well, but I'm struggling to see the point of > that, honestly. > > Please expand on why you think changing the request flags to also > carry that value would be useful, as opposed to just mapping it when > we setup the request. If you have a valid concern I don't mind making > the change, but I just don't see one right now. Mostly so that we can pass the value down in one form through the whole stack. > How so? It's pretty straight forward. The only downside I see is that > we'll have a delay between seeing the first valid write hint and to > the time when nvme has it enabled. But that's so short, and in the > grander scheme of things, doesn't matter one bit. I'll take your word for that. To be honest I hope future standards won't make the mistake to come up with something as ugly as streams and just take something like our hints on a per-I/O basis..