On 05/28/2013 11:26 PM, Rafael J. Wysocki wrote:
On Tuesday, May 28, 2013 03:23:37 PM Daniel Lezcano wrote:
On 05/28/2013 02:42 PM, Rafael J. Wysocki wrote:
On Tuesday, May 28, 2013 02:23:00 PM Daniel Lezcano wrote:
On 05/28/2013 01:46 PM, Rafael J. Wysocki wrote:
On Monday, May 27, 2013 11:00:58 PM Daniel Lezcano wrote:
Each governor is suitable for different kernel configurations: the menu governor suits better for a tickless system, while the ladder governor fits better for a periodic timer tick system.
The Kconfig does not allow to [un]select a governor, thus both are compiled in the kernel but the init order makes the menu governor to be the last one to be registered, so becoming the default. The only way to switch back to the ladder governor is to enable the sysfs governor switch in the kernel command line.
Because it seems nobody complained about this, the menu governor is used by default most of the time on the system, having both governors is not really necessary on a tickless system but there isn't a config option to disable one or another governor.
Create a submenu for cpuidle and add a label for each governor, so we can see the option in the menu config and enable/disable it.
The governors will be enabled depending on the CONFIG_NO_HZ option:
- If CONFIG_NO_HZ is set, then the menu governor is selected and the ladder governor is optional, defaulting to 'no'
Why not defaulting to 'yes'? That'd be backwards compatible, wouldn't it?
Yes, that wouldn't be backward compatible but who wants the ladder governor which is less efficient with a tickless system ?
I don't know and this isn't the right question to ask I think.
You need to ask who uses the ladder governor with CONFIG_NO_HZ and you need to avoid making changes that aren't backwards compatible if you don't know the answer (which I'm pretty sure is the case).
I'd prefer to default to 'yes' to start with and then to change the default to 'no' after a couple of cycles, possibly.
- If CONFIG_NO_HZ is not set, then the ladder governor is selected and the menu governor is optional, defaulting to 'no'
Are you sure this is not going to introduce regressions with CONFIG_NO_HZ unset?
Yes, a system configured with a periodic tick will use the ladder instead of the menu governor (which is less efficient on this configuration).
Well, "less efficient" meaning what exactly? Less power-efficient or less efficient performance-wise?
less power efficient.
I thought so, but that's really important, because some people *do* care about performance. In the context of changes like this one we always need to talk about both power and performance. For example, when you're saying that changing something may lead to better energy saving behavior, you should also say what the impact of that change on performance is going to be
I fully agree with you but with this very specific case, when the cpuidle is enabled in the system, it is to have the best trade-off between performance and power saving. Using the ladder governor on a tickless system is not power efficient and the performance is not significantly improved. If the governor is too agressive in power saving and impacts the performance the pm_qos will guarantee the needed performance.
Desktop will use tickless system because they want power saving, thus cpuidle and the menu governor is the best trade-off.
Server will want more responsiveness and will use a periodic timer tick system, the cpuidle and the ladder suits better.
The pm_qos will ensure a latency for both governors.
But again I agree 100% with you and keeping the old behavior makes sense until we sort this out clearly in the next cycles.
Thanks -- Daniel