Windows Server Performance Team Blog

Windows Server Operating System Performance information, tools and discussion

Configuring Windows Server 2008 Power Parameters for Increased Power Efficiency

Configuring Windows Server 2008 Power Parameters for Increased Power Efficiency

  • Comments 6
  • Likes

Matthew Robben here, I’m a Program Manager on the Windows Server Performance team and my primary responsibility is Windows Server power management. Server power efficiency is a topic of considerable importance – in today’s difficult economy, IT organizations need to contain and reduce costs. Yet the cost of energy to power and cool a 1U server is now more than the amortized cost of the server (over 3 years). 

 

Energy efficient hardware and software reduces operational costs and directly impacts an organization’s bottom line. We’re in the midst of developing Windows Server 2008 R2, and one of our goals for the product is to build a server operating system that is more power efficient than all of our previous releases. Furthermore, to help IT administrators better understand server power management and optimize their current Windows Server 2008 installations, we’re releasing a comprehensive white paper called “Power In, Dollars Out: Reducing the Flows in the Data Center” today. The white paper gives detailed explanations of many factors affecting server power efficiency, and contains a list of best practices for optimization.

 

One of the stated best practices is to properly configure Windows Server 2008’s power management features. According to the Green Grid, just turning on PPM features in the operating system can reduce power consumption by 20%. In Windows Server, this can be done simply by choosing the Balanced or Power Saver power policies (found in the Power Options applet in the Control Panel). Of course, PPM is a complicated technology, with many more toggles than a simple on/off switch. We’ve done quite a bit of work on the Windows Server processor power management (PPM) algorithms and parameters during R2 development. One of the results of this work was the development of a set of parameters that can boost power efficiency by up to 10% on standard benchmark workloads.

 

Good news - you don’t need to wait until R2 to deploy these new parameters on your servers. This blog post will describe PPM technology, explain the parameters involved, and show benchmark test results for the parameter changes on a commodity server. It will also give you a handy command-line walkthrough of the powercfg.exe commands necessary to implement these changes in your environment.

 

First, some context. Power management requires cooperation from the hardware and the operating system to work efficiently. For example, hardware might support low power states, but the operating system schedules computational work and is in the best position to decide when low power states can be leveraged. The Advanced Configuration and Power Interface (ACPI) defines an interface between the operating system and server hardware to be used for power management purposes.

ACPI Processor Performance States

The processor has traditionally consumed the most power in a server, which makes it a great candidate for power-efficiency optimizations. To add detail and flexibility for processor power management, ACPI defines a few sets of states for processors. Performance states, or P-states, are one such state that can be leveraged to increase power efficiency.

P-States

Processors can transition between multiple performance states, or P-states. P-states define incremental levels of processor performance, from P0 (most performant) to Pn (least performant). The ACPI specification does not specify a maximum number of P-states, so Pn is used to refer to the highest numbered, lowest performant P-state that a processor supports.

Each successively higher numbered P-state consumes less power than the previous P‑state. Processors can dynamically switch between these states during operation to provide only as much computational capacity as is necessary, which saves power during periods of low usage.

Figure 1 below shows a hypothetical set of six P-states that would be available to a processor. Note that the maximum P-state (P0) has the highest frequency, while successively higher numbered P-states reduce in frequency. In this case, the minimum P-state is P5, so the terms Pn and P5 would be interchangeable.

P-state explanatory chart

Figure 1. Illustration of P-state number and corresponding frequency

Tuning P-State Parameters for Increased Power Efficiency

Windows Server contains a number of configurable P-state parameters. These can be used to finely tune the power/performance balance of Windows Server PPM. The defaults for these parameters are tuned to deliver excellent power efficiency for most systems and workloads out of the box. However, these are “safe” defaults. They balance performance and power efficiency. Default settings are shown in Table 1. Note that “P-state increase” in this context refers to a transition to a lower numbered, more performant P-state, whereas “P-state decrease” refers to a transition to a higher numbered, less performant P-state. Looking back to Figure 1, an increase would mean moving upward in the chart while a decrease would mean moving downward.

Table 1. Default P-State Parameter Settings in Windows Server 2008

Name

Default

Description

Time Check

100 ms

The time interval at which the operating system considers a change of the current P-state.

Increase Time

100 ms

The minimum time period that must expire before considering a P-state increase.

Decrease Time

300 ms

The minimum time period that must expire before considering a P-state decrease.

Increase Percentage

30%

The utilization percentage1 that the CPU must exceed to increase P‑state.

Decrease Percentage

50%

The utilization percentage that the CPU must be below to decrease P-state

Domain

Accounting

Policy

0 (On)

Determines how the kernel power manager accumulates idle time. Settings:

 0 (On): idle time is accumulated only when all processors in an idle state domain2 are idle.

1 (Off): idle time is accumulated and P-states are calculated for each processor without regard to any other processor in the domain.

Increase Policy

IDEAL (0)

Determines how P-state transition decisions are made. Settings:

 IDEAL (0): calculates the target P-state based only on processor utilization and then finds a nearby available P-state on the system.

SINGLE (1): calculates an ideal P-state but only increases or decreases by one P-state per time check interval.

ROCKET (2):  transitions to the highest P-state available on increase or lowest P-state available on decrease

Decrease Policy

SINGLE (1)

1The utilization percentage referenced here is not the same as the CPU usage counter in the Task Manager tool. Without going into more details, this setting is best optimized through empirical experimentation.

2A “state domain” is a dependency between different processor cores or packages on a server.  Often, processor designs require that if one core is at a particular performance or idle state, the other cores or packages in the domain must also be at the same state. The hardware notifies the operating system of this dependency by establishing a domain through the ACPI interface.

During Windows Server 2008 R2 development, our team determined a set of parameters that can boost energy efficiency with a very minor performance cost. Notice in Table 1 that the decrease time default is larger than the increase time default. This setting favors P-state increases over decreases. The default increase and decrease percentage settings of 30 and 50 percent, the default domain accounting policy, and the increase and decrease policy defaults favor P‑state increases as well.

 

To tune the machine for more aggressive power savings, we suggest reducing the decrease time to 100 ms to match the increase time, changing the increase and decrease policies to favor P-state decrease, and switching the domain accounting policy to 0 (off). We left the increase and decrease percentages as their defaults to ensure that the system PPM parameters were not completely biased toward power savings and to reduce negative performance consequences. Table 2 summarizes these changes.

Important:  Modifying any of these parameters changes the behavior of performance state handling from the out-of-box experience. Before you deploy to production servers, validate the effects of any changes in a test environment.

Table 2. Default and New PPM Parameter Values

Setting

Default value

“Aggressive” value

Time Check

100 ms

100 ms

Increase Time

100 ms

100 ms

Decrease Time

300 ms

100 ms

Increase Percentage

30 %

30 %

Decrease Percentage

50 %

50 %

Domain Accounting Policy

0 (On)

1 (Off)

Increase Policy

0 (Ideal)

1 (Single)

Decrease Policy

1 (Single)

0 (Ideal)

 

These parameters can only be set using the powercfg.exe command-line tool, which is installed by default to the Windows\System32 folder on Windows Server 2008. The commands to change the P-state settings by using powercfg.exe are given at the end of this post.

Energy Efficiency Analysis of P-State Settings

To test the efficiency of these new power settings (henceforth called “Aggressive” settings), we performed a set of benchmark runs on a four-socket quad-core server. Table 3 gives the system configuration.

Table 3. Four-Socket Quad-Core Server Configuration

System configuration

Processors

  4  quad-core 2.9-GHz

Memory

32 4-GB DDR2 667-MHz DIMMs

Disk

  4  72-GB, 15,000 SCSI

Network adapter

  2  1-GBps 

 

We ran the SPECPower benchmark with both the default settings and the Aggressive power saving settings. Figure 2 and Figure 3 show the power usage and power efficiency across different workload levels. The Aggressive settings exhibit significant power efficiency over the default settings at a majority of the load levels. The maximum power saving is achieved at 60‑percent workload level on this configuration with approximately 10‑percent improvement in power efficiency when it is compared to the default setting. There is a negligible reduction in overall throughput at utilization levels above 97%.

Power savings of Default vs. Aggressive parameters

Figure 2.  System power across varying SPECPower load levels

Efficiency of default vs. aggressive settings

Figure 3.  System power efficiency across varying SPECPower load levels

These settings were tested on commodity servers with the SPECPower workload. Your particular hardware and workload might deliver different results. Please test any parameter changes before deploying in your production environment.

 

Changing P-State Parameters with Powercfg.exe

If you decide you want to deploy the new P-state parameter settings in your environment, you’ll first need to verify that your Windows Server 2008 installation is configured to use the Balanced power policy. Verify this by going to Power Options in the Control Panel.

 

Done? Next, you need to start a command prompt with administrator privileges. Get the binary dataset that represents the current Balanced AC power settings for P‑states with the following command line (corrected from earlier versions of this post, thanks to Asmus for the heads up!):

>powercfg /getpossiblevalue sub_processor procperf 2

You should see the following:

Type: BINARY

Value: 640864000000A0860100E09304001E00000032000000

 

This value represents an encoded dataset of power policy parameters. The parameter values for this dataset can be shown with the decode command:

>powercfg /ppmperf /decode 640864000000A0860100E09304001E00000032000000

Verify that your power parameter values match the defaults shown below and in Table 1. If your parameter settings do not match these values, your Windows Server parameters may have already been reconfigured for optimal power efficiency in your environment.

Busy Adjust Threshold: 100

Time Check: 100

Increase Time: 100000

Decrease Time: 300000

Increase Percent: 30

Decrease Percent: 50

Domain Accounting Policy: 0

Increase Policy: 0

Decrease Policy: 1

Next, you need to change the parameter values to match the “Aggressive” settings described in this post. To do so, use the following command:

>powercfg /ppmperf /encode base 640864000000A0860100E09304001E00000032000000 /decreasetime 100000 /domainaccountingpolicy 1 /increasepolicy 1 /decreasepolicy 0

After executing this command, powercfg will print out a binary dataset representing the new values, like the one shown below.

640364000000A0860100A08601001E00000032000000

 

You need to apply the new dataset by using the setpossiblevalue command:

>powercfg /setpossiblevalue /sub_processor /procperf 2 binary 640364000000A0860100A08601001E00000032000000

 

Finally, use the setactive command to enable the new parameter set. No reboot is necessary for these parameters to take effect.

>powercfg /setactive scheme_balanced

 

If you want to restore the default setttings, use the setpossiblevalue command with the default dataset value (shown below), and follow it with a setactive command:

>powercfg /setpossiblevalue /sub_processor /procperf 2 binary 640864000000A0860100E09304001E00000032000000

>powercfg /setactive scheme_balanced 

 

That’s it! You’ve taken your first step to increasing energy efficiency in your datacenter. As our white paper explains, there’s even more you can do. It’s a highly recommended read for cost-sensitive administrators.

 

Thanks for reading!

 

Matthew Robben

Program Manager

Windows Server Performance Team

 

Comments
  • PingBack from http://www.ditii.com/2008/12/04/windows-server-2008-configuring-power-parameters-for-increased-power-efficiency/

  • The Windows Server performance team has posted a great blog on best practices for tuning Windows Server

  • The default parameter set increase percent-30% and decrease percent-50%. What will happen if the CPU usage is 40%? If there will be any competition?

  • Good question, new learner - the underlying algorithm and how these percentages are interpreted is a bit confusing. CPU usage does not map directly to the increase and decrease percentages.  I want to avoid getting into detailed specifics (see footnote under table 1) as our algorithm for determining P-state changes is proprietary. But a bit more detail is appropriate. :)

    When Windows boots, the OS and hardware communicate P-state availability through ACPI. The OS builds a table of performance states as a percentage of maximum processor frequency.

    The algorithm uses the current utilization, current p-state, and next highest and lowest P-states (if any) to determine if a state switch should occur. Because we are determining the increase and decrease thresholds using the P-states above and below the current state, the algorithm can be designed so that there is no competition between the increase and decrease thresholds.

    So in the scenario you're referring to, a CPU utilization of 40% means nothing by itself. The algorithm would need to evaluate its current P-state and surrounding P-states to determine if a change is necessary using the increase and decrease percentages specified by the user.

    Note that 40% utilization != 40% of maximum frequency. This raises another issue, that % utilization is actually dependent on processor state. 40% utilization at P0 means something very different from 40% utilization at Pn (P0 has more cycles per unit time than Pn, so Pn has higher % utilization for the same workload). We are targeting this topic for a future blog post. Stay tuned and thanks for reading!

  • Thanks for the excellent article!

    If I understand the powercfg syntax correctly, I believe there's an error above under "Changing P-State Parameters with Powercfg.exe"

    In the first few sample commands, you're working on the index value "1" -- which I believe stands for a "Power Saver" policy, running on DC/battery.  For example:

    powercfg /getpossiblevalue sub_processor procperf 1

    However, when you apply the changes later, you switch to Index value 2, which is the Balanced policy (AC power) that I believe you were actually intending to change:

    >powercfg /setpossiblevalue /sub_processor /procperf 2 binary (and so on)

    The above commands do work, but users will have no record of what the value was in their "Balanced" power setting before making the changes, since that value is not output beforehand in your example.

    Or did I misunderstand something?

  • Indeed, you're right! Thanks for the sharp eyes, Asmus. I corrected this inline in the article.

    ~Matt Robben

Your comment has been posted.   Close
Thank you, your comment requires moderation so it may take a while to appear.   Close
Leave a Comment