intel_pstate driver patches by Wei Wang from 2015

intel_pstate driver patches by Wei Wang from 2015

[Marek Marczykowski-Górecki]

[-- Attachment #1.1: Type: text/plain, Size: 1227 bytes --]

Hi,

I wonder what happened to intel_pstate patch series[1] back in 2015?
I've seen there was some review feedback[2][3][4][5][6][7] on v6,
patches 4/6 and 6/6 were acked. Were the review comments ever addressed
(can't find it)?  Or maybe there is some other mechanism in place for proper
power management on recent Intel CPUs? Apparently acpi-cpufreq driver
not always does its job well[8].

[1] https://lists.xenproject.org/archives/html/xen-devel/2015-10/msg03048.html
[2] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02043.html
[3] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02410.html
[4] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02430.html
[5] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02443.html
[6] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02456.html
[7] https://lists.xenproject.org/archives/html/xen-devel/2015-10/msg03086.html
[8] https://github.com/QubesOS/qubes-issues/issues/4604#issuecomment-446816536

-- 
Best Regards,
Marek Marczykowski-Górecki
Invisible Things Lab
A: Because it messes up the order in which people normally read text.
Q: Why is top-posting such a bad thing?

[-- Attachment #1.2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

[-- Attachment #2: Type: text/plain, Size: 157 bytes --]

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel

Re: intel_pstate driver patches by Wei Wang from 2015

[Wei Wang]

On 12/14/2018 10:16 PM, Marek Marczykowski-Górecki wrote:
> Hi,
>
> I wonder what happened to intel_pstate patch series[1] back in 2015?
> I've seen there was some review feedback[2][3][4][5][6][7] on v6,
> patches 4/6 and 6/6 were acked. Were the review comments ever addressed
> (can't find it)?  Or maybe there is some other mechanism in place for proper
> power management on recent Intel CPUs? Apparently acpi-cpufreq driver
> not always does its job well[8].
>
> [1] https://lists.xenproject.org/archives/html/xen-devel/2015-10/msg03048.html
> [2] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02043.html
> [3] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02410.html
> [4] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02430.html
> [5] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02443.html
> [6] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02456.html
> [7] https://lists.xenproject.org/archives/html/xen-devel/2015-10/msg03086.html
> [8] https://github.com/QubesOS/qubes-issues/issues/4604#issuecomment-446816536
>

Hi Marek,

It was paused because there was no users in the clouds - people usually 
have P-state disabled.

Best,
Wei

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel

Re: intel_pstate driver patches by Wei Wang from 2015

[Marek Marczykowski-Górecki]

[-- Attachment #1.1: Type: text/plain, Size: 1609 bytes --]

On Mon, Dec 17, 2018 at 04:42:40PM +0800, Wei Wang wrote:
> On 12/14/2018 10:16 PM, Marek Marczykowski-Górecki wrote:
> > Hi,
> > 
> > I wonder what happened to intel_pstate patch series[1] back in 2015?
> > I've seen there was some review feedback[2][3][4][5][6][7] on v6,
> > patches 4/6 and 6/6 were acked. Were the review comments ever addressed
> > (can't find it)?  Or maybe there is some other mechanism in place for proper
> > power management on recent Intel CPUs? Apparently acpi-cpufreq driver
> > not always does its job well[8].
> > 
> > [1] https://lists.xenproject.org/archives/html/xen-devel/2015-10/msg03048.html
> > [2] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02043.html
> > [3] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02410.html
> > [4] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02430.html
> > [5] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02443.html
> > [6] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02456.html
> > [7] https://lists.xenproject.org/archives/html/xen-devel/2015-10/msg03086.html
> > [8] https://github.com/QubesOS/qubes-issues/issues/4604#issuecomment-446816536
> > 
> 
> Hi Marek,
> 
> It was paused because there was no users in the clouds - people usually have
> P-state disabled.

I see. FWIW Xen have also non-cloud use cases, like Qubes OS.

-- 
Best Regards,
Marek Marczykowski-Górecki
Invisible Things Lab
A: Because it messes up the order in which people normally read text.
Q: Why is top-posting such a bad thing?

[-- Attachment #1.2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

[-- Attachment #2: Type: text/plain, Size: 157 bytes --]

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel

Re: intel_pstate driver patches by Wei Wang from 2015

[Andrew Cooper]

On 17/12/2018 11:09, Marek Marczykowski-Górecki wrote:
> On Mon, Dec 17, 2018 at 04:42:40PM +0800, Wei Wang wrote:
>> On 12/14/2018 10:16 PM, Marek Marczykowski-Górecki wrote:
>>> Hi,
>>>
>>> I wonder what happened to intel_pstate patch series[1] back in 2015?
>>> I've seen there was some review feedback[2][3][4][5][6][7] on v6,
>>> patches 4/6 and 6/6 were acked. Were the review comments ever addressed
>>> (can't find it)?  Or maybe there is some other mechanism in place for proper
>>> power management on recent Intel CPUs? Apparently acpi-cpufreq driver
>>> not always does its job well[8].
>>>
>>> [1] https://lists.xenproject.org/archives/html/xen-devel/2015-10/msg03048.html
>>> [2] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02043.html
>>> [3] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02410.html
>>> [4] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02430.html
>>> [5] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02443.html
>>> [6] https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg02456.html
>>> [7] https://lists.xenproject.org/archives/html/xen-devel/2015-10/msg03086.html
>>> [8] https://github.com/QubesOS/qubes-issues/issues/4604#issuecomment-446816536
>>>
>> Hi Marek,
>>
>> It was paused because there was no users in the clouds - people usually have
>> P-state disabled.
> I see. FWIW Xen have also non-cloud use cases, like Qubes OS.

Where has the claim about "no users in clouds use pstates" come from? 
I've got several customers who are public clouds you'd definitely
recognise who tend to notice when pstates/turbo gets broken.

~Andrew

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel

Re: intel_pstate driver patches by Wei Wang from 2015

[Wang, Wei W]

On Monday, December 17, 2018 9:19 PM, Andrew Cooper wrote:
> On 17/12/2018 11:09, Marek Marczykowski-Górecki wrote:
> > On Mon, Dec 17, 2018 at 04:42:40PM +0800, Wei Wang wrote:
> >> On 12/14/2018 10:16 PM, Marek Marczykowski-Górecki wrote:
> >>> Hi,
> >>>
> >>> I wonder what happened to intel_pstate patch series[1] back in 2015?
> >>> I've seen there was some review feedback[2][3][4][5][6][7] on v6,
> >>> patches 4/6 and 6/6 were acked. Were the review comments ever
> >>> addressed (can't find it)?  Or maybe there is some other mechanism
> >>> in place for proper power management on recent Intel CPUs?
> >>> Apparently acpi-cpufreq driver not always does its job well[8].
> >>>
> >>> [1]
> >>> https://lists.xenproject.org/archives/html/xen-devel/2015-10/msg0304
> >>> 8.html [2]
> >>> https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg0204
> >>> 3.html [3]
> >>> https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg0241
> >>> 0.html [4]
> >>> https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg0243
> >>> 0.html [5]
> >>> https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg0244
> >>> 3.html [6]
> >>> https://lists.xenproject.org/archives/html/xen-devel/2015-11/msg0245
> >>> 6.html [7]
> >>> https://lists.xenproject.org/archives/html/xen-devel/2015-10/msg0308
> >>> 6.html [8]
> >>> https://github.com/QubesOS/qubes-issues/issues/4604#issuecomment-
> 446
> >>> 816536
> >>>
> >> Hi Marek,
> >>
> >> It was paused because there was no users in the clouds - people
> >> usually have P-state disabled.
> > I see. FWIW Xen have also non-cloud use cases, like Qubes OS.
> 
> Where has the claim about "no users in clouds use pstates" come from? I've
> got several customers who are public clouds you'd definitely recognise who
> tend to notice when pstates/turbo gets broken.

OK. We didn’t get any official requests from people to enable it,
and all the customers that we've been in touch with seems to have no interest in it so far.

Best,
Wei
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel