Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <7f553d34-9ada-426c-4847-c7cd1aba64a8@grimberg.me>
Date:   Mon, 17 Apr 2023 16:45:37 +0300
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:102.0) Gecko/20100101
 Thunderbird/102.9.0
Subject: Re: [PATCH] nvme/tcp: Add support to set the tcp worker cpu affinity
Content-Language: en-US
To:     Li Feng <fengli@smartx.com>, Keith Busch <kbusch@kernel.org>,
        Jens Axboe <axboe@fb.com>, Christoph Hellwig <hch@lst.de>,
        "open list:NVM EXPRESS DRIVER" <linux-nvme@lists.infradead.org>,
        open list <linux-kernel@vger.kernel.org>
Cc:     lifeng1519@gmail.com
References: <20230413062339.2454616-1-fengli@smartx.com>
 <20230413063317.2455680-1-fengli@smartx.com>
From:   Sagi Grimberg <sagi@grimberg.me>
In-Reply-To: <20230413063317.2455680-1-fengli@smartx.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Precedence: bulk

Hey Li,

> The default worker affinity policy is using all online cpus, e.g. from 0
> to N-1. However, some cpus are busy for other jobs, then the nvme-tcp will
> have a bad performance.
> 
> This patch adds a module parameter to set the cpu affinity for the nvme-tcp
> socket worker threads.  The parameter is a comma separated list of CPU
> numbers.  The list is parsed and the resulting cpumask is used to set the
> affinity of the socket worker threads.  If the list is empty or the
> parsing fails, the default affinity is used.

I can see how this may benefit a specific set of workloads, but I have a
few issues with this.

- This is exposing a user interface for something that is really
internal to the driver.

- This is something that can be misleading and could be tricky to get
right, my concern is that this would only benefit a very niche case.

- If the setting should exist, it should not be global.

- I prefer not to introduce new modparams.

- I'd prefer to find a way to support your use-case without introducing
a config knob for it.

- It is not backed by performance improvements, but more importantly
does not cover any potential regressions in key metrics (bw/iops/lat)
or lack there of.