Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:5 as permitted sender) client-ip=2620:137:e000::3:5;
MIME-Version: 1.0
References: <20230829020451.9828-1-wenchao.chen@unisoc.com> <20230829020451.9828-3-wenchao.chen@unisoc.com>
In-Reply-To: <20230829020451.9828-3-wenchao.chen@unisoc.com>
From:   Ulf Hansson <ulf.hansson@linaro.org>
Date:   Thu, 14 Sep 2023 14:57:04 +0200
Message-ID: <CAPDyKFo67SOWS3eYgEDKGOtmZJY5UtPw7+V0BEdkF_Y8yY2i5A@mail.gmail.com>
Subject: Re: [PATCH V3 2/2] mmc: hsq: dynamic adjustment of hsq->depth
To:     Wenchao Chen <wenchao.chen@unisoc.com>
Cc:     linux-mmc@vger.kernel.org, linux-kernel@vger.kernel.org,
        wenchao.chen666@gmail.com, zhenxiong.lai@unisoc.com,
        yuelin.tang@unisoc.com
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Tue, 29 Aug 2023 at 04:05, Wenchao Chen <wenchao.chen@unisoc.com> wrote:
>
> Increasing hsq_depth improves random write performance.
>
> Signed-off-by: Wenchao Chen <wenchao.chen@unisoc.com>
> ---
>  drivers/mmc/host/mmc_hsq.c | 27 +++++++++++++++++++++++++++
>  drivers/mmc/host/mmc_hsq.h |  5 +++++
>  2 files changed, 32 insertions(+)
>
> diff --git a/drivers/mmc/host/mmc_hsq.c b/drivers/mmc/host/mmc_hsq.c
> index 8556cacb21a1..0984c39108ba 100644
> --- a/drivers/mmc/host/mmc_hsq.c
> +++ b/drivers/mmc/host/mmc_hsq.c
> @@ -21,6 +21,31 @@ static void mmc_hsq_retry_handler(struct work_struct *work)
>         mmc->ops->request(mmc, hsq->mrq);
>  }
>
> +static void mmc_hsq_modify_threshold(struct mmc_hsq *hsq)
> +{
> +       struct mmc_host *mmc = hsq->mmc;
> +       struct mmc_request *mrq;
> +       struct hsq_slot *slot;
> +       int need_change = 0;

Rather than using a variable to keep track of this, why not just do
the below here?

mmc->hsq_depth = HSQ_NORMAL_DEPTH;

> +       int tag;
> +
> +       for (tag = 0; tag < HSQ_NUM_SLOTS; tag++) {
> +               slot = &hsq->slot[tag];
> +               mrq = slot->mrq;
> +               if (mrq && mrq->data &&
> +                       (mrq->data->blksz * mrq->data->blocks == 4096) &&
> +                       (mrq->data->flags & MMC_DATA_WRITE))
> +                       need_change++;

And following above, then we can do the below here:
mmc->hsq_depth = HSQ_PERFORMANCE_DEPTH;
break;

That should simplify and make this more efficient too, right?

> +               else
> +                       break;
> +       }
> +
> +       if (need_change > 1)
> +               mmc->hsq_depth = HSQ_PERFORMANCE_DEPTH;
> +       else
> +               mmc->hsq_depth = HSQ_NORMAL_DEPTH;
> +}
> +

[...]

Kind regards
Uffe