Received-SPF: pass (google.com: domain of linux-kernel+bounces-186554-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Date: Wed, 22 May 2024 11:32:02 -0600
From: Keith Busch <kbusch@kernel.org>
To: John Meneghini <jmeneghi@redhat.com>
Cc: hch@lst.de, sagi@grimberg.me, emilne@redhat.com,
	linux-nvme@lists.infradead.org, linux-kernel@vger.kernel.org,
	jrani@purestorage.com, randyj@purestorage.com, hare@kernel.org
Subject: Re: [PATCH v5] nvme: multipath: Implemented new iopolicy
 "queue-depth"
Message-ID: <Zk4sEpypKqeU67dg@kbusch-mbp.dhcp.thefacebook.com>
References: <20240522165406.702362-1-jmeneghi@redhat.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20240522165406.702362-1-jmeneghi@redhat.com>

On Wed, May 22, 2024 at 12:54:06PM -0400, John Meneghini wrote:
> From: "Ewan D. Milne" <emilne@redhat.com>
> 
> The round-robin path selector is inefficient in cases where there is a
> difference in latency between paths.  In the presence of one or more
> high latency paths the round-robin selector continues to use the high
> latency path equally. This results in a bias towards the highest latency
> path and can cause a significant decrease in overall performance as IOs
> pile on the highest latency path. This problem is acute with NVMe-oF
> controllers.
> 
> The queue-depth policy instead sends I/O requests down the path with the
> least amount of requests in its request queue. Paths with lower latency
> will clear requests more quickly and have less requests in their queues
> compared to higher latency paths. The goal of this path selector is to
> make more use of lower latency paths which will bring down overall IO
> latency and increase throughput and performance.

I'm okay with this as-is, though I don't think you need either
atomic_set() calls.

Christoph, Sagi, 6.10 merge window is still open and this has been
iterating long before that. Any objection?