lkml.org 
[lkml]   [2017]   [Jan]   [18]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
SubjectRe: [PATCH] ARM: smp: Remove CPU: shutdown notice
From
Date
On 01/18/2017 01:55 AM, Petr Mladek wrote:
> On Tue 2017-01-17 15:39:45, Florian Fainelli wrote:
>> On 01/17/2017 03:23 PM, Russell King - ARM Linux wrote:
>>> On Tue, Jan 17, 2017 at 03:07:12PM -0800, Florian Fainelli wrote:
>>>> This message is not particularly informative, and is not paired with an
>>>> identical message when a CPU is brought online. Finally, it slows the
>>>> CPU hotplug path down, thus allowing less CPU hotplug operations per
>>>> second. Just remove it.
>>>
>>> CPU hotplug isn't a fast operation anyway - it's also fairly disruptive
>>> in that it uses stop_machine() to halt activity everywhere while taking
>>> the CPU offline.
>>
>> We have a test that consists in shutting down all CPUs as frequently as
>> we can and do this for about 2 million iterations which takes roughly
>> 24h, and this printk slows thing down by a reasonable amount. Here are
>> some numbers on 500 hotplug operations:
>>
>> w/ printk:
>> real 0m9.997s
>> user 0m0.725s
>> sys 0m3.030s
>> #
>>
>> w/o printk:
>> real 0m8.547s
>> user 0m0.436s
>> sys 0m1.838s
>
> I am curious that a single printk() might make such a big difference.

It does, because of how printk() is implemented (there is nothing wrong
with it, just slow by nature and how the UART gets written to as well).

>
> One reason might be that the messages are pushed to a "slow" console.

115200 UART, yes that's slow, but not unusual.

>
> Another reason might be that there are many other messages printed
> on the system and there is a contention on logbuf_lock or other
> console related locks.

The other messages being printed are those from the hotplug script that
I run which just checkpoints its running every 50 instances, so it does
not occur that often, the console really is not busy, which really
extracts the overhead of printing "CPU: shutdown".

>
> There might be also the opposite problem. The messages are also read
> by userspace tools that store them into /var/log/messages or systemd
> logs. If these are the only messages printed to the log and if there
> is no other activity on the system. Then the waken loggers might make
> a difference, especially if all CPUs are getting disabled and only
> one is available at some point.

There is none of that, no systemd, no syslog, just minimal userspace
running.

>
> Well, I am not sure what other operations are needed to do the
> CPU hotplug operation.
>
> I cannot judge how the message is useful and if the speed up
> is worth removing it.
>
> Best Regards,
> Petr
>


--
Florian

\
 
 \ /
  Last update: 2017-01-18 20:57    [W:0.084 / U:0.584 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site