https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=236513
--- Comment #11 from stockhau...@collogia.de ---
Memo for myself: This can only occur if acpi_bus_alloc_gas() fails in
bus_alloc_resource_any():
acpi_bus_alloc_gas()
{
...
error = ENOMEM;
...
*res = bus_alloc_resource_any(de
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=236513
--- Comment #10 from stockhau...@collogia.de ---
Findings so far:
acpi_cpu_cx_cst() runs fine for CPU core 0. With core 1 something is going
wrong:
1. acpi_cpu_cx_cst() finds C2 state (WHAT WE EXPECT!)
2. in the function the valid states l
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=236513
stockhau...@collogia.de changed:
What|Removed |Added
Version|11.2-STABLE |12.0-RELEASE
--
You are
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=236513
--- Comment #9 from stockhau...@collogia.de ---
Bug https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=189267 shows other
occurences of CPUs where c states for the first core is C1+C2 while all other
cores are C1 only.
--
You are receiving
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=236513
--- Comment #8 from stockhau...@collogia.de ---
Created attachment 203050
--> https://bugs.freebsd.org/bugzilla/attachment.cgi?id=203050&action=edit
Fedora powertop
--
You are receiving this mail because:
You are the assignee for the bug
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=236513
--- Comment #7 from stockhau...@collogia.de ---
Just fired up a Fedora 29 on the HP T730.
Running a cpu intensive task and looking at the powertop output I would say
that C2 states are core independent.
Conclusion: Linux kernel detects C
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=236513
--- Comment #6 from stockhau...@collogia.de ---
Created attachment 203049
--> https://bugs.freebsd.org/bugzilla/attachment.cgi?id=203049&action=edit
Screenshot dmesg
--
You are receiving this mail because:
You are the assignee for the bu
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=236513
--- Comment #5 from stockhau...@collogia.de ---
Finally I got time to retest everything with 12.0-RELEASE.
Situation is the same. Only the first CPU can go to C2 state. All other cores
only show up with cx_lowest = C1.
Only difference this
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=236513
--- Comment #4 from stockhau...@collogia.de ---
Speculative question in advance. If this situation does not change in 12.0:
Might it be that the system only supports C2 state for the whole CPU package?
And if yes: Shouldn't this be reflect
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=236513
--- Comment #3 from stockhau...@collogia.de ---
Thanks for the quick response. I'll give 12.0 a try and give feedback asap.
--
You are receiving this mail because:
You are the assignee for the bug.
_
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=236513
--- Comment #2 from Conrad Meyer ---
(In reply to Conrad Meyer from comment #1)
> I don't know if r326956 has been MFCed to 11.x
FWIW, that change is not present in 11.x, but is in 12.0. Please try running
12.0, if possible.
--
You are
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=236513
--- Comment #1 from Conrad Meyer ---
This is a Jaguar-class (Family 16h) AMD CPU.
This information is probed automatically out of the ACPI information presented
by your BIOS. That code hasn't changed appreciably in 4 years. It seems your
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=236513
Bug ID: 236513
Summary: Different power states (C1/C2/...) per CPU core
Product: Base System
Version: 11.2-STABLE
Hardware: amd64
OS: Any
Status: New
13 matches
Mail list logo
