Fwd: x86_64 and AMD with C1E

Previous thread: [PATCH] Uninline fork.c/exit.c by Alexey Dobriyan on Monday, October 1, 2007 - 5:15 am. (3 messages)

Next thread: [PATCH] Fix timer_stats printout of events/sec by Anton Blanchard on Monday, October 1, 2007 - 6:05 am. (1 message)
From: Mikhail Kshevetskiy
Date: Monday, October 1, 2007 - 5:50 am

No, it boot and work normally. The only thing i bother, is the
additional 260 timer interrupts per seconds.
Here is short result:

c1e enabled:
  -- power consumption about 23 watts
  -- there is only C1 power state enabled
  -- there are about 260 timer interrupts per seconds
tested with  x86_64(2.6.22, 2.6.23-rc8, 2.6.23-rc8-hrt1 ),
i386(2.6.21, 2.6.22, 2.6.23-rc5-hrt1)

c1e disabled:
  -- power consumption about 27 watts
  -- there are no any power state enabled (including C1)
  -- there are no additional 260 timer interrupts per seconds
tested with 2.6.23-rc6-hrt1/x86_64.

I want to reduce the power consumption of my notebook. I see the 2 possibility:
  -- remove 260 additional timer interrupts (c1e enabled case )
  -- force enable C1, C2 and C3 states  (c1e disabled case)
Do you have any idea how it can be reached?


Mikhail Kshevetskiy
-

From: Thomas Gleixner
Date: Monday, October 1, 2007 - 7:14 am

There is work in progress on a patch, which allows to utilize the hpet
timers as per cpu timers. This should solve the problem. Be patient.

Thanks,

	tglx
-

From: Andi Kleen
Date: Monday, October 1, 2007 - 7:32 am

Given that e.g. ICH8 only has 3 HPET timers that seems doubtful
except for the special case of single-socket non hyper threaded dual core.
You'll probably do a lot of broadcasting and IPI'ing still.

Also you'll likely make user space unhappy which often requires 
at least one free HPET timer for /dev/rtc. Ok I suppose that 
could be replaced with a hrtimer.

-Andi
-

From: Thomas Gleixner
Date: Monday, October 1, 2007 - 7:59 am

Yes, we can replace rtc with a hrtimer. Also HPET can operate in non
legacy irq mode, so the legacy rtc is still available. So if the
number of hpet channels is greater/equal to the number of possible
CPUs it's perfectly fine and does not need IPI at all.

Thanks,

	tglx

-

From: Andi Kleen
Date: Monday, October 1, 2007 - 8:21 am

That is only a stop gap then. I don't see this being
generally true in the future. e.g. Intel announced SMT will be soon 
back so even a standard dual core would exceed it with
current southbridges.

Also I'm not sure but I suspect non Intel HPETs have less than
three timers. Certainly they generally miss the 64bitness.

-Andi
-

From: Thomas Gleixner
Date: Monday, October 1, 2007 - 9:44 am

Sigh. We have to deal with current hardware and the problems of exactly 
that hardware. We have the possibility to solve problems and witchcrafting 

two timers are enough and 64 bit is nice to have, but not a requirement.

	tglx

-

From: Chuck Ebbert
Date: Monday, October 1, 2007 - 10:56 am

nVidia C51/MCP51 chipset, AMD Turion X2:

hpet0: 3 32-bit timers, 25000000 Hz

-

From: Mikhail Kshevetskiy
Date: Monday, October 1, 2007 - 7:33 am

I can test it on i386/x86_64 architectures.

Mikhail Kshevetskiy
-

Previous thread: [PATCH] Uninline fork.c/exit.c by Alexey Dobriyan on Monday, October 1, 2007 - 5:15 am. (3 messages)

Next thread: [PATCH] Fix timer_stats printout of events/sec by Anton Blanchard on Monday, October 1, 2007 - 6:05 am. (1 message)