Linux Renesas SOC kernel development
 help / color / mirror / Atom feed
From: Richard Weinberger <richard@nod.at>
To: Christian Loehle <CLoehle@hyperstone.com>
Cc: Biju Das <biju.das.jz@bp.renesas.com>,
	linux-mmc <linux-mmc@vger.kernel.org>,
	linux-renesas-soc <linux-renesas-soc@vger.kernel.org>,
	wsa+renesas <wsa+renesas@sang-engineering.com>,
	ulf hansson <ulf.hansson@linaro.org>
Subject: Re: Poor write performance to boot area using rcar-gen3-sdhi
Date: Tue, 9 May 2023 13:28:20 +0200 (CEST)	[thread overview]
Message-ID: <615854031.8233438.1683631700226.JavaMail.zimbra@nod.at> (raw)
In-Reply-To: <398e244a4d3746f1bd7b4c32d1ea70e3@hyperstone.com>

----- Ursprüngliche Mail -----
> Von: "Christian Loehle" <CLoehle@hyperstone.com>
> There are probably some more differences if you really want to go down that
> rabbit hole,
> like different bus modes for uboot and linux.
> Anyway I don't really know how I could help you out here, if you could provide a
> trace showing the busy times,
> that would be a smoking gun for the eMMC vendor.

So I went down the rabbit hole.
After analyzing the operation traces from Linux and u-boot in more detail I had
another chat with the vendor. It turned out their boot area *is* different,
it operates on a much larger internal block size.

While u-boot does basically all IO with one op code, Linux's writeback
via page cache writes 4k wise which leads to catastrophic performance.
Using O_DIRECT mitigates the issue, though.

Thanks everyone for your valuable input!
//richard

  reply	other threads:[~2023-05-09 11:28 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-04-17 20:08 Poor write performance to boot area using rcar-gen3-sdhi Richard Weinberger
2023-04-18  6:09 ` Biju Das
2023-04-18  6:16   ` Richard Weinberger
2023-04-18  7:48     ` Christian Loehle
2023-04-18  8:11       ` Richard Weinberger
2023-04-18  8:36         ` Christian Loehle
2023-04-18 11:58           ` Richard Weinberger
2023-04-20 15:18             ` Richard Weinberger
2023-04-21 16:23               ` Christian Loehle
2023-05-09 11:28                 ` Richard Weinberger [this message]
2023-05-11  9:46                   ` Christian Loehle
2023-05-11 10:35                     ` Richard Weinberger
2023-04-18  8:12       ` Biju Das

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=615854031.8233438.1683631700226.JavaMail.zimbra@nod.at \
    --to=richard@nod.at \
    --cc=CLoehle@hyperstone.com \
    --cc=biju.das.jz@bp.renesas.com \
    --cc=linux-mmc@vger.kernel.org \
    --cc=linux-renesas-soc@vger.kernel.org \
    --cc=ulf.hansson@linaro.org \
    --cc=wsa+renesas@sang-engineering.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox