Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
References: <20190513142410.9299-1-um@mutluit.com>
In-Reply-To: <20190513142410.9299-1-um@mutluit.com>
From:   Chen-Yu Tsai <wens@csie.org>
Date:   Fri, 5 Jul 2019 16:48:44 +0800
Message-ID: <CAGb2v67OEa+ge7qpbNa5R7DCpgwKfs4T8KHTKe4fnuQYwzJURQ@mail.gmail.com>
Subject: Re: [linux-sunxi] [PATCH v3] drivers: ata: ahci_sunxi: Increased
 SATA/AHCI DMA TX/RX FIFOs
To:     Jens Axboe <axboe@kernel.dk>, Hans de Goede <hdegoede@redhat.com>
Cc:     Maxime Ripard <maxime.ripard@bootlin.com>,
        linux-ide@vger.kernel.org,
        linux-arm-kernel <linux-arm-kernel@lists.infradead.org>,
        linux-kernel <linux-kernel@vger.kernel.org>,
        Uenal Mutlu <um@mutluit.com>,
        linux-sunxi <linux-sunxi@googlegroups.com>,
        linux-amarula <linux-amarula@amarulasolutions.com>,
        Jagan Teki <jagan@amarulasolutions.com>,
        Pablo Greco <pgreco@centosproject.org>,
        Mark Rutland <mark.rutland@arm.com>,
        Oliver Schinagl <oliver@schinagl.nl>,
        Linus Walleij <linus.walleij@linaro.org>,
        FUKAUMI Naoki <naobsd@gmail.com>,
        Andre Przywara <andre.przywara@arm.com>,
        Stefan Monnier <monnier@iro.umontreal.ca>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Mon, May 13, 2019 at 10:24 PM Uenal Mutlu <um@mutluit.com> wrote:
>
> Increasing the SATA/AHCI DMA TX/RX FIFOs (P0DMACR.TXTS and .RXTS, ie.
> TX_TRANSACTION_SIZE and RX_TRANSACTION_SIZE) from default 0x0 each
> to 0x3 each, gives a write performance boost of 120 MiB/s to 132 MiB/s
> from lame 36 MiB/s to 45 MiB/s previously.
> Read performance is above 200 MiB/s.
> [tested on SSD using dd bs=4K/8K/12K/16K/20K/24K/32K: peak-perf at 12K]
>
> Tested on the SBCs Banana Pi R1 (aka Lamobo R1) and Banana Pi M1 which
> are based on the Allwinner A20 32bit-SoC (ARMv7-a / arm-linux-gnueabihf).
> These devices are RaspberryPi-like small devices.
>
> This problem of slow SATA write-speed with these small devices lasts
> for about 7 years now (beginning with the A10 SoC). Many commentators
> throughout the years wrongly assumed the slow write speed was a
> hardware limitation. This patch finally solves the problem, which
> in fact was just a hard-to-find software problem due to lack of
> SATA/AHCI documentation by the SoC-maker Allwinner Technology.
>
> Lists of the affected sunxi and other boards and SoCs with SATA using
> the ahci_sunxi driver:
>   $ grep -i -e "^&ahci" arch/arm/boot/dts/sun*dts
>   and http://linux-sunxi.org/SATA#Devices_with_SATA_ports
>   See also http://linux-sunxi.org/Category:Devices_with_SATA_port
>
> Acked-by: Maxime Ripard <maxime.ripard@bootlin.com>
> Reviewed-by: Hans de Goede <hdegoede@redhat.com>
> Signed-off-by: Uenal Mutlu <um@mutluit.com>

Tested-by: Chen-Yu Tsai <wens@csie.org>

on a Lamabo R1 as well.

Maybe we could merge this soon so it makes the next merge window?

Thanks.