From mboxrd@z Thu Jan  1 00:00:00 1970
From: keith.busch@intel.com (Keith Busch)
Date: Mon, 17 Jul 2017 18:56:15 -0400
Subject: [PATCH] nvme: Acknowledge completion queue on each iteration
In-Reply-To: <6d10032c-35ec-978c-6b8f-1ab9c07adf7f@codeaurora.org>
References: <1500330983-27501-1-git-send-email-okaya@codeaurora.org>
 <20170717224551.GA1496@localhost.localdomain>
 <6d10032c-35ec-978c-6b8f-1ab9c07adf7f@codeaurora.org>
Message-ID: <20170717225615.GB1496@localhost.localdomain>
To: linux-arm-kernel@lists.infradead.org
List-Id: linux-arm-kernel.lists.infradead.org

On Mon, Jul 17, 2017 at 06:46:11PM -0400, Sinan Kaya wrote:
> Hi Keith,
> 
> On 7/17/2017 6:45 PM, Keith Busch wrote:
> > On Mon, Jul 17, 2017 at 06:36:23PM -0400, Sinan Kaya wrote:
> >> Code is moving the completion queue doorbell after processing all completed
> >> events and sending callbacks to the block layer on each iteration.
> >>
> >> This is causing a performance drop when a lot of jobs are queued towards
> >> the HW. Move the completion queue doorbell on each loop instead and allow new
> >> jobs to be queued by the HW.
> > 
> > That doesn't make sense. Aggregating doorbell writes should be much more
> > efficient for high depth workloads.
> > 
> 
> Problem is that code is throttling the HW as HW cannot queue more completions until
> SW get a chance to clear it. 
> 
> As an example:
> 
> for each in N
> (
> 	blk_layer()
> )
> ring door bell
> 
> HW cannot queue new job until N x blk_layer operations are processed and queue
> element ownership is passed to the HW after the loop. HW is just sitting idle
> there if no queue entries are available.

If no completion queue entries are available, then there can't possibly
be any submission queue entries for the HW to work on either.