From: Jon Hunter <jonathanh@nvidia.com>
To: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: wander@redhat.com, Jiri Slaby <jirislaby@kernel.org>,
"Maciej W. Rozycki" <macro@orcam.me.uk>,
Johan Hovold <johan@kernel.org>, Andrew Jeffery <andrew@aj.id.au>,
"open list:SERIAL DRIVERS" <linux-serial@vger.kernel.org>,
open list <linux-kernel@vger.kernel.org>,
"linux-tegra@vger.kernel.org" <linux-tegra@vger.kernel.org>,
Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Subject: Re: [PATCH] tty: serial: Use fifo in 8250 console driver
Date: Tue, 25 Jan 2022 09:03:54 +0000 [thread overview]
Message-ID: <a58783f8-ddf3-dd18-d3f4-fb80a1cefc8d@nvidia.com> (raw)
In-Reply-To: <Ye+5xrJ2kC85E8QT@kroah.com>
On 25/01/2022 08:50, Greg Kroah-Hartman wrote:
> On Tue, Jan 25, 2022 at 08:39:24AM +0000, Jon Hunter wrote:
>>
>> On 29/10/2021 21:14, wander@redhat.com wrote:
>>> From: Wander Lairson Costa <wander@redhat.com>
>>>
>>> Note: I am using a small test app + driver located at [0] for the
>>> problem description. serco is a driver whose write function dispatches
>>> to the serial controller. sertest is a user-mode app that writes n bytes
>>> to the serial console using the serco driver.
>>>
>>> While investigating a bug in the RHEL kernel, I noticed that the serial
>>> console throughput is way below the configured speed of 115200 bps in
>>> a HP Proliant DL380 Gen9. I was expecting something above 10KB/s, but
>>> I got 2.5KB/s.
>>>
>>> $ time ./sertest -n 2500 /tmp/serco
>>>
>>> real 0m0.997s
>>> user 0m0.000s
>>> sys 0m0.997s
>>>
>>> With the help of the function tracer, I then noticed the serial
>>> controller was taking around 410us seconds to dispatch one single byte:
>>>
>>> $ trace-cmd record -p function_graph -g serial8250_console_write \
>>> ./sertest -n 1 /tmp/serco
>>>
>>> $ trace-cmd report
>>>
>>> | serial8250_console_write() {
>>> 0.384 us | _raw_spin_lock_irqsave();
>>> 1.836 us | io_serial_in();
>>> 1.667 us | io_serial_out();
>>> | uart_console_write() {
>>> | serial8250_console_putchar() {
>>> | wait_for_xmitr() {
>>> 1.870 us | io_serial_in();
>>> 2.238 us | }
>>> 1.737 us | io_serial_out();
>>> 4.318 us | }
>>> 4.675 us | }
>>> | wait_for_xmitr() {
>>> 1.635 us | io_serial_in();
>>> | __const_udelay() {
>>> 1.125 us | delay_tsc();
>>> 1.429 us | }
>>> ...
>>> ...
>>> ...
>>> 1.683 us | io_serial_in();
>>> | __const_udelay() {
>>> 1.248 us | delay_tsc();
>>> 1.486 us | }
>>> 1.671 us | io_serial_in();
>>> 411.342 us | }
>>>
>>> In another machine, I measured a throughput of 11.5KB/s, with the serial
>>> controller taking between 80-90us to send each byte. That matches the
>>> expected throughput for a configuration of 115200 bps.
>>>
>>> This patch changes the serial8250_console_write to use the 16550 fifo
>>> if available. In my benchmarks I got around 25% improvement in the slow
>>> machine, and no performance penalty in the fast machine.
>>>
>>> Signed-off-by: Wander Lairson Costa <wander@redhat.com>
>>
>>
>> On the current mainline and -next branches, I have noticed that the
>> serial output on many of our Tegra boards is corrupted and so
>> parsing the serial output is failing.
>>
>> Before this change the serial console would appear as follows ...
>>
>> [ 0.000000] Booting Linux on physical CPU 0x0000000000 [0x411fd071]
>> [ 0.000000] Linux version 5.16.0-rc6-00091-gadbfddc757ae (jonathanh@jonathanh-vm-01) (aarch64-linux-gnu-gcc (Linaro GCC 6.4-2017.08) 6.4.1 20170707, GNU ld (Linaro_Binutils-2017.08) 2.27.0.20161019) #15 SMP PREEMPT Tue Jan 25 00:15:25 PST 2022
>> [ 0.000000] Machine model: NVIDIA Jetson TX1 Developer Kit
>>
>> And now I see ...
>>
>> [ 0.000000] Booting Linux on physicalfd071]
>> [ 0.000000] Linux version 5.16.0-rc6-athanh@j-linux-g017.08) Linaro_B20161019n 25 00:[ 0.000000] Machine model: NVIDIA Jet[ 0.000000] efi: UEFI not found.
>> [ 0.000000] NUMA: No NUMA configurati[ 0.000000] NUMA: Faking a node at [m00000001[ 0.000000] NUMA: NODE_DATA [mem 0x17[ 0.000000] Zone ranges:
>>
>> Bisecting is pointing to this commit. Let me know if there are any
>> tests I can run. Otherwise we may need to disable this at least
>> for Tegra.
>
> Ick. Does this uart have any other quirks assigned to it that are
> somehow not getting assigned here?
Not that I know of, but I can have a look. I did check to see if there
are any known issues that could be related but I have not found any so far.
Jon
--
nvpublic
next prev parent reply other threads:[~2022-01-25 9:15 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-10-29 20:14 [PATCH] tty: serial: Use fifo in 8250 console driver wander
[not found] ` <CAHp75VeZBp4gKvGBDzaD=EpGRDZ1-wTvD8K9Ui6Q59kDjmkXmQ@mail.gmail.com>
2021-11-01 15:22 ` Wander Costa
2021-11-01 15:32 ` Andy Shevchenko
2021-11-10 12:10 ` Wander Costa
2021-11-12 11:58 ` David Laight
2022-01-25 8:39 ` Jon Hunter
2022-01-25 8:50 ` Greg Kroah-Hartman
2022-01-25 9:03 ` Jon Hunter [this message]
2022-01-25 9:08 ` Jiri Slaby
2022-01-25 9:36 ` Jiri Slaby
2022-01-25 10:06 ` Jon Hunter
2022-01-25 10:29 ` Wander Costa
2022-01-25 12:40 ` Jon Hunter
2022-01-25 16:53 ` Andy Shevchenko
2022-01-25 16:54 ` Andy Shevchenko
2022-01-25 18:40 ` Wander Costa
2022-01-26 8:52 ` Greg Kroah-Hartman
2022-01-26 12:09 ` Andy Shevchenko
2022-01-26 13:23 ` Wander Costa
2022-01-26 13:34 ` Andy Shevchenko
2022-01-27 18:10 ` Theodore Y. Ts'o
2022-01-25 10:18 ` Wander Costa
2022-01-25 10:38 ` Jiri Slaby
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=a58783f8-ddf3-dd18-d3f4-fb80a1cefc8d@nvidia.com \
--to=jonathanh@nvidia.com \
--cc=andrew@aj.id.au \
--cc=andriy.shevchenko@linux.intel.com \
--cc=gregkh@linuxfoundation.org \
--cc=jirislaby@kernel.org \
--cc=johan@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-serial@vger.kernel.org \
--cc=linux-tegra@vger.kernel.org \
--cc=macro@orcam.me.uk \
--cc=wander@redhat.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;
as well as URLs for NNTP newsgroup(s).