Re: suspend/resume PM criterion for application

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Wed, Sep 10, 2014 at 8:59 PM,  <Valdis.Kletnieks@xxxxxx> wrote:
> On Wed, 10 Sep 2014 20:26:48 +0300, Ran Shalit said:
>
>> What is usually the criterion for PM (power management) suspending
>> that application shall use ? Is it according to minimum threshold for
>> cpu load (as indication for no process) ?
>
> That will be highly application dependent.  Something that checks your email
> in the background may not care at all, as long as it gets network
> access every 5 minutes or so, and the entire system can power down for 4 minutes
> and 58 seconds as far as it cares.  If it's doing media streaming, it may
> insist on having at least one CPU burst per screen refresh, and the CPU can
> go to sleep for the rest of the 1/30th of  a second.
>
>> How usually it is performed, i.e.  is it some periodic process, which
>> wakes up periodically to check criterion for cpu load ? If so, isn't
>> it problematic in PM terms, becuase it mean that the system is resumed
>> periodically (as a result of the the periodic timer's interrupt), and
>> all devices are resumed ?
>
> No, it can be done on a per-device basis.
>
> 'powertop' is a possibly useful tool for playing with this stuff that will
> let you look at power management on the fly.

As far as I understand, suspend/respond PM is not per device, but for
all system,
and wakeup source will resume again the whole system.
I think you mean runtime suspend/resume in the answer.

_______________________________________________
Kernelnewbies mailing list
Kernelnewbies@xxxxxxxxxxxxxxxxx
http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies




[Index of Archives]     [Newbies FAQ]     [Linux Kernel Mentors]     [Linux Kernel Development]     [IETF Annouce]     [Git]     [Networking]     [Security]     [Bugtraq]     [Yosemite]     [MIPS Linux]     [ARM Linux]     [Linux RAID]     [Linux SCSI]     [Linux ACPI]
  Powered by Linux