Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1561446
| From | Petr Mladek <pmladek@suse.com> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | Re: [PATCH] ARM: smp: Remove CPU: shutdown notice |
| Date | 2017-01-18 11:20 +0100 |
| Message-ID | <t0Vvt-2I0-45@gated-at.bofh.it> (permalink) |
| References | <t0L34-4Oi-27@gated-at.bofh.it> <t0Lw7-4Y5-37@gated-at.bofh.it> <t0LFL-51r-11@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
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. One reason might be that the messages are pushed to a "slow" console. 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. 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. 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
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
[PATCH] ARM: smp: Remove CPU: shutdown notice Florian Fainelli <f.fainelli@gmail.com> - 2017-01-18 00:10 +0100
Re: [PATCH] ARM: smp: Remove CPU: shutdown notice Russell King - ARM Linux <linux@armlinux.org.uk> - 2017-01-18 00:40 +0100
Re: [PATCH] ARM: smp: Remove CPU: shutdown notice Florian Fainelli <f.fainelli@gmail.com> - 2017-01-18 00:50 +0100
Re: [PATCH] ARM: smp: Remove CPU: shutdown notice Petr Mladek <pmladek@suse.com> - 2017-01-18 11:20 +0100
Re: [PATCH] ARM: smp: Remove CPU: shutdown notice Florian Fainelli <f.fainelli@gmail.com> - 2017-01-18 21:00 +0100
Re: [PATCH] ARM: smp: Remove CPU: shutdown notice Sergey Senozhatsky <sergey.senozhatsky@gmail.com> - 2017-01-19 13:10 +0100
Re: [PATCH] ARM: smp: Remove CPU: shutdown notice Russell King - ARM Linux <linux@armlinux.org.uk> - 2017-01-18 23:50 +0100
Re: [PATCH] ARM: smp: Remove CPU: shutdown notice Florian Fainelli <f.fainelli@gmail.com> - 2017-01-19 00:00 +0100
[PATCH] ARM: Reduce "CPU: shutdown" message to debug level Florian Fainelli <f.fainelli@gmail.com> - 2017-01-19 00:10 +0100
Re: [PATCH] ARM: Reduce "CPU: shutdown" message to debug level Russell King - ARM Linux <linux@armlinux.org.uk> - 2017-01-19 00:30 +0100
Re: [PATCH] ARM: Reduce "CPU: shutdown" message to debug level Florian Fainelli <f.fainelli@gmail.com> - 2017-01-19 01:30 +0100
csiph-web