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: <ec9c378c-fedd-5a90-bb12-085395e0d22e@acm.org>
Date:   Wed, 31 May 2023 05:48:27 -0700
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:102.0) Gecko/20100101
 Thunderbird/102.10.0
Subject: Re: [PATCH v2 1/3] scsi: ufs: core: Introduce mcq ops to config cqid
Content-Language: en-US
To:     Stanley Chu <chu.stanley@gmail.com>
Cc:     Po-Wen Kao <powen.kao@mediatek.com>, linux-scsi@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-arm-kernel@lists.infradead.org,
        linux-mediatek@lists.infradead.org,
        Alim Akhtar <alim.akhtar@samsung.com>,
        Avri Altman <avri.altman@wdc.com>,
        "James E.J. Bottomley" <jejb@linux.ibm.com>,
        "Martin K. Petersen" <martin.petersen@oracle.com>,
        Matthias Brugger <matthias.bgg@gmail.com>,
        AngeloGioacchino Del Regno 
        <angelogioacchino.delregno@collabora.com>,
        wsd_upstream@mediatek.com, peter.wang@mediatek.com,
        stanley.chu@mediatek.com, alice.chao@mediatek.com,
        naomi.chu@mediatek.com, chun-hung.wu@mediatek.com,
        cc.chou@mediatek.com, eddie.huang@mediatek.com
References: <20230530023227.16653-1-powen.kao@mediatek.com>
 <20230530023227.16653-2-powen.kao@mediatek.com>
 <1c182151-6e8c-5068-b38c-f8e842e6e13b@acm.org>
 <CAGaU9a9TsoaUtoMX8cNmAhfBnCddRtWYEG8ACdRNJfri+sdasg@mail.gmail.com>
From:   Bart Van Assche <bvanassche@acm.org>
In-Reply-To: <CAGaU9a9TsoaUtoMX8cNmAhfBnCddRtWYEG8ACdRNJfri+sdasg@mail.gmail.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 5/30/23 18:54, Stanley Chu wrote:
> In addition, some benchmark data shows that the performance can be
> improved by using fewer CQs to aggregate the interrupt handling of
> completion requests.

What has been measured? IOPS only or both IOPS and latency?

How big is the difference? A few percent or more?

For which number of SQs and which number of CQs has performance data 
been measured?

Would the following work instead of introducing a new vop?
- Introduce a new capability flag, e.g. UFSHCD_CAP_SINGLE_CQ.
- Set that flag from inside ufs_mtk_init().
- Modify the UFS core driver such that the number of completion queues
   depends on the UFSHCD_CAP_SINGLE_CQ flag.

> Therefore, we would like to introduce a vop to allow the host to
> configure it accordingly.

We do not accept new vops upstream without a user. Where is the 
implementation of the new .config_cqid() callback?

Thanks,

Bart.