* Re: [Powertop] 700+mW for nic:virbr0?
@ 2017-08-30 23:47 Chris Murphy
0 siblings, 0 replies; 3+ messages in thread
From: Chris Murphy @ 2017-08-30 23:47 UTC (permalink / raw)
To: powertop
[-- Attachment #1: Type: text/plain, Size: 666 bytes --]
On Wed, Aug 30, 2017 at 3:48 PM, Arjan van de Ven <arjan(a)linux.intel.com> wrote:
> On 8/30/2017 2:36 PM, Chris Murphy wrote:
>>
>> The #2 power consumer on my laptop according to powertop is
>> nic:virbr0 which seems unlikely. That's more than Firefox, and a bit
>> less than the display backlight. And it's nearly 300x more power than
>> used by the wifi driver.
>>
>
> so powertop seems to correlate virbr activity with power consumption...
> so while it may not be the virtual bridge itself to cause power consumption,
> the usage of it very likely is
>
It varies a lot, even while connected to the same AP. 190mW up to 2W.
--
Chris Murphy
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [Powertop] 700+mW for nic:virbr0?
@ 2017-08-30 21:48 Arjan van de Ven
0 siblings, 0 replies; 3+ messages in thread
From: Arjan van de Ven @ 2017-08-30 21:48 UTC (permalink / raw)
To: powertop
[-- Attachment #1: Type: text/plain, Size: 469 bytes --]
On 8/30/2017 2:36 PM, Chris Murphy wrote:
> The #2 power consumer on my laptop according to powertop is
> nic:virbr0 which seems unlikely. That's more than Firefox, and a bit
> less than the display backlight. And it's nearly 300x more power than
> used by the wifi driver.
>
so powertop seems to correlate virbr activity with power consumption...
so while it may not be the virtual bridge itself to cause power consumption, the usage of it very likely is
^ permalink raw reply [flat|nested] 3+ messages in thread
* [Powertop] 700+mW for nic:virbr0?
@ 2017-08-30 21:36 Chris Murphy
0 siblings, 0 replies; 3+ messages in thread
From: Chris Murphy @ 2017-08-30 21:36 UTC (permalink / raw)
To: powertop
[-- Attachment #1: Type: text/plain, Size: 639 bytes --]
The #2 power consumer on my laptop according to powertop is
nic:virbr0 which seems unlikely. That's more than Firefox, and a bit
less than the display backlight. And it's nearly 300x more power than
used by the wifi driver.
https://pastebin.com/GuxA4Dsg
862 mW 0.0 pkts/s Device nic:virbr0
If it's wrong, it's a powertop bug. If it's real, then it's a bug
somewhere maybe in libvirt or maybe the kernel? There has been no VM
running during this boot, so nic:virbr0 shouldn't even be in use.
Is this the actual wifi radio, but somehow virb0 is just getting dinged?
--
Chris Murphy
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2017-08-30 23:47 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2017-08-30 23:47 [Powertop] 700+mW for nic:virbr0? Chris Murphy
-- strict thread matches above, loose matches on Subject: below --
2017-08-30 21:48 Arjan van de Ven
2017-08-30 21:36 Chris Murphy
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.