Database Develop

[GUIDE] Android Governors Explained [Update 1/13/2013]

Update 1/13/2013:
IO Scheduler, TCP Congestion Avoidance Algorithm
Please go to Post #27
Sources and credit go to:
http://forum.xda-developers.com/showthread.php?t=1792369
http://forum.xda-developers.com/showthread.php?t=1369817
Android CPU governors explained
1: OnDemand
2: OndemandX
3: Performance
4: Powersave
5: Conservative
6: Userspace
7: Min Max
8: Interactive
9: InteractiveX
10: Smartass
11: SmartassV2
12: Scary
13: Lagfree
14: Smoothass
15: Brazilianwax
16: SavagedZen
17: Lazy
18: Lionheart
19: LionheartX
20: Intellidemand
21: Hotplug
22: Wheatley
23: Lulzactive
24: AbyssPlug
25. BadAss
1: OnDemand Governor:
This governor has a hair trigger for boosting clockspeed to the maximum speed set by the user. If the CPU load placed by the user abates, the OnDemand governor will slowly step back down through the kernel's frequency steppings until it settles at the lowest possible frequency, or the user executes another task to demand a ramp.
OnDemand has excellent interface fluidity because of its high-frequency bias, but it can also have a relatively negative effect on battery life versus other governors. OnDemand is commonly chosen by smartphone manufacturers because it is well-tested, reliable, and virtually guarantees the smoothest possible performance for the phone. This is so because users are vastly more likely to ***** about performance than they are the few hours of extra battery life another governor could have granted them.
This final fact is important to know before you read about the Interactive governor: OnDemand scales its clockspeed in a work queue context. In other words, once the task that triggered the clockspeed ramp is finished, OnDemand will attempt to move the clockspeed back to minimum. If the user executes another task that triggers OnDemand's ramp, the clockspeed will bounce from minimum to maximum. This can happen especially frequently if the user is multi-tasking. This, too, has negative implications for battery life.
2: OndemandX:
Basically an ondemand with suspend/wake profiles. This governor is supposed to be a battery friendly ondemand. When screen is off, max frequency is capped at 500 mhz. Even though ondemand is the default governor in many kernel and is considered safe/stable, the support for ondemand/ondemandX depends on CPU capability to do fast frequency switching which are very low latency frequency transitions. I have read somewhere that the performance of ondemand/ondemandx were significantly varying for different i/o schedulers. This is not true for most of the other governors. I personally feel ondemand/ondemandx goes best with SIO I/O scheduler.
3: Performance Governor:
This locks the phone's CPU at maximum frequency. While this may sound like an ugly idea, there is growing evidence to suggest that running a phone at its maximum frequency at all times will allow a faster race-to-idle. Race-to-idle is the process by which a phone completes a given task, such as syncing email, and returns the CPU to the extremely efficient low-power state. This still requires extensive testing, and a kernel that properly implements a given CPU's C-states (low power states).
4: Powersave Governor:
The opposite of the Performance governor, the Powersave governor locks the CPU frequency at the lowest frequency set by the user.
5:Conservative Governor:
This biases the phone to prefer the lowest possible clockspeed as often as possible. In other words, a larger and more persistent load must be placed on the CPU before the conservative governor will be prompted to raise the CPU clockspeed. Depending on how the developer has implemented this governor, and the minimum clockspeed chosen by the user, the conservative governor can introduce choppy performance. On the other hand, it can be good for battery life.
The Conservative Governor is also frequently described as a "slow OnDemand," if that helps to give you a more complete picture of its functionality.
6: Userspace Governor:
This governor, exceptionally rare for the world of mobile devices, allows any program executed by the user to set the CPU's operating frequency. This governor is more common amongst servers or desktop PCs where an application (like a power profile app) needs privileges to set the CPU clockspeed.
7: Min Max
well this governor makes use of only min & maximum frequency based on workload... no intermediate frequencies are used.
8: Interactive Governor:
Much like the OnDemand governor, the Interactive governor dynamically scales CPU clockspeed in response to the workload placed on the CPU by the user. This is where the similarities end. Interactive is significantly more responsive than OnDemand, because it's faster at scaling to maximum frequency.
Unlike OnDemand, which you'll recall scales clockspeed in the context of a work queue, Interactive scales the clockspeed over the course of a timer set arbitrarily by the kernel developer. In other words, if an application demands a ramp to maximum clockspeed (by placing 100% load on the CPU), a user can execute another task before the governor starts reducing CPU frequency. This can eliminate the frequency bouncing discussed in the OnDemand section. Because of this timer, Interactive is also better prepared to utilize intermediate clockspeeds that fall between the minimum and maximum CPU frequencies. This is another pro-battery life benefit of Interactive.
However, because Interactive is permitted to spend more time at maximum frequency than OnDemand (for device performance reasons), the battery-saving benefits discussed above are effectively negated. Long story short, Interactive offers better performance than OnDemand (some say the best performance of any governor) and negligibly different battery life.
Interactive also makes the assumption that a user turning the screen on will shortly be followed by the user interacting with some application on their device. Because of this, screen on triggers a ramp to maximum clockspeed, followed by the timer behavior described above.
9: InteractiveX Governor:
Created by kernel developer "Imoseyon," the InteractiveX governor is based heavily on the Interactive governor, enhanced with tuned timer parameters to better balance battery vs. performance. The InteractiveX governor's defining feature, however, is that it locks the CPU frequency to the user's lowest defined speed when the screen is off.
10: Smartass
Is based on the concept of the interactive governor.
I have always agreed that in theory the way interactive works – by taking over the idle loop – is very attractive. I have never managed to tweak it so it would behave decently in real life. Smartass is a complete rewrite of the code plus more. I think its a success. Performance is on par with the “old” minmax and I think smartass is a bit more responsive. Battery life is hard to quantify precisely but it does spend much more time at the lower frequencies.
Smartass will also cap the max frequency when sleeping to 352Mhz (or if your min frequency is higher than 352 – why?! – it will cap it to your min frequency). Lets take for example the 528/176 kernel, it will sleep at 352/176. No need for sleep profiles any more!"
11: SmartassV2:
Version 2 of the original smartass governor from Erasmux. Another favorite for many a people. The governor aim for an "ideal frequency", and ramp up more aggressively towards this freq and less aggressive after. It uses different ideal frequencies for screen on and screen off, namely awake_ideal_freq and sleep_ideal_freq. This governor scales down CPU very fast (to hit sleep_ideal_freq soon) while screen is off and scales up rapidly to awake_ideal_freq (500 mhz for GS2 by default) when screen is on. There's no upper limit for frequency while screen is off (unlike Smartass). So the entire frequency range is available for the governor to use during screen-on and screen-off state. The motto of this governor is a balance between performance and battery.
12: Scary
A new governor wrote based on conservative with some smartass features, it scales accordingly to conservatives laws. So it will start from the bottom, take a load sample, if it's above the upthreshold, ramp up only one speed at a time, and ramp down one at a time. It will automatically cap the off screen speeds to 245Mhz, and if your min freq is higher than 245mhz, it will reset the min to 120mhz while screen is off and restore it upon screen awakening, and still scale accordingly to conservatives laws. So it spends most of its time at lower frequencies. The goal of this is to get the best battery life with decent performance. It will give the same performance as conservative right now, it will get tweaked over time.
13: Lagfree:
Lagfree is similar to ondemand. Main difference is it's optimization to become more battery friendly. Frequency is gracefully decreased and increased, unlike ondemand which jumps to 100% too often. Lagfree does not skip any frequency step while scaling up or down. Remember that if there's a requirement for sudden burst of power, lagfree can not satisfy that since it has to raise cpu through each higher frequency step from current. Some users report that video playback using lagfree stutters a little.
14: Smoothass:
The same as the Smartass “governor” But MUCH more aggressive & across the board this one has a better battery life that is about a third better than stock KERNEL
15: Brazilianwax:
Similar to smartassV2. More aggressive ramping, so more performance, less battery
16: SavagedZen:
Another smartassV2 based governor. Achieves good balance between performance & battery as compared to brazilianwax.
17: Lazy:
This governor from Ezekeel is basically an ondemand with an additional parameter min_time_state to specify the minimum time CPU stays on a frequency before scaling up/down. The Idea here is to eliminate any instabilities caused by fast frequency switching by ondemand. Lazy governor polls more often than ondemand, but changes frequency only after completing min_time_state on a step overriding sampling interval. Lazy also has a screenoff_maxfreq parameter which when enabled will cause the governor to always select the maximum frequency while the screen is off.
18: Lionheart:
Lionheart is a conservative-based governor which is based on samsung's update3 source.
The tunables (such as the thresholds and sampling rate) were changed so the governor behaves more like the performance one, at the cost of battery as the scaling is very aggressive.
19: LionheartX
LionheartX is based on Lionheart but has a few changes on the tunables and features a suspend profile based on Smartass governor.
20: Intellidemand:
Intellidemand aka Intelligent Ondemand from Faux is yet another governor that's based on ondemand. Unlike what some users believe, this governor is not the replacement for OC Daemon (Having different governors for sleep and awake). The original intellidemand behaves differently according to GPU usage. When GPU is really busy (gaming, maps, benchmarking, etc) intellidemand behaves like ondemand. When GPU is 'idling' (or moderately busy), intellidemand limits max frequency to a step depending on frequencies available in your device/kernel for saving battery. This is called browsing mode. We can see some 'traces' of interactive governor here. Frequency scale-up decision is made based on idling time of CPU. Lower idling time (<20%) causes CPU to scale-up from current frequency. Frequency scale-down happens at steps=5% of max frequency. (This parameter is tunable only in conservative, among the popular governors)
To sum up, this is an intelligent ondemand that enters browsing mode to limit max frequency when GPU is idling, and (exits browsing mode) behaves like ondemand when GPU is busy; to deliver performance for gaming and such. Intellidemand does not jump to highest frequency when screen is off.
21: Hotplug Governor:
The “hotplug” governor scales CPU frequency based on load, similar to “ondemand”. It scales up to the highest frequency when “up_threshold” is crossed and scales down one frequency at a time when “down_threshold” is crossed. Unlike those governors, target frequencies are determined by directly accessing the CPUfreq frequency table, instead of taking some percentage of maximum available frequency.
The key difference in the “hotplug” governor is that it will disable auxillary CPUs when the system is very idle, and enable them again once the system becomes busy. This is achieved by averaging load over multiple sampling periods; if CPUs were online or offlined based on a single sampling period then thrashing will occur.
Sysfs entries exist for “hotplug_in_sampling_periods” and for “hotplug_out_sampling_periods” which determine how many consecutive periods get averaged to determine if auxillery CPUs should be onlined or offlined. Defaults are 5 periods and 20 periods respectively. Otherwise the standard sysfs entries you might find for “ondemand” and “conservative” governors are there.
Obviously, this governor is only available on multi-core devices.
22: Wheatley
in short words this govenor is build on “ondemand” but increases the C4 state time of the CPU and doing so trying to save juice.
23: Basically interactive governor with added smartass bits and variable (as opposed to fixed amout) frequency scaling, based on currently occuring cpu loads. Has, like smartass, a sleep profile built-in. See link for details on exact scaling.
24: Abyssplug governor is a modified hotplug governor.
25. BadAss Governor:
Badass removes all of this "fast peaking" to the max frequency. On a typical system the cpu won't go above 918Mhz and therefore stay cool and will use less power. To trigger a frequency increase, the system must run a bit @ 918Mhz with high load, then the frequency is bumped to 1188Mhz. If that is still not enough the governor gives you full throttle. (this transition should not take longer than 1-2 seconds, depending on the load your system is experiencing)
Badass will also take the gpu load into consideration. If the gpu is moderately busy it will bypass the above check and clock the cpu with 1188Mhz. If the gpu is crushed under load, badass will lift the restrictions to the cpu.

Thank you! Always helpful info to have, much appreciated

Really great Info

thanks for the tutorial.

Thank you for this. I was always confused by what the different governors meant!

So, Governors can be categorized into 3/4 on a high level:
1.a) Ondemand Based:
Works on "ramp-up on high load" principle. CPU busy-time is taken into consideration for scaling decisions. Members: Ondemand, OndemandX, Intellidemand, Lazy, Lagfree.
1.b) Conservative Based:
Members: Conservative, Lionheart, LionheartX
2) Interactive Based:
Works on "make scaling decision when CPU comes out of idle-loop" principle. Members: Interactive, InteractiveX, Lulzactive, Luzactiveq, Smartass, SmartassV2, Brazilianwax, SavagedZen.
3) Weird Category:
Members: Userspace, Powersave, Performance.
http://forum.xda-developers.com/showthread.php?t=1369817

Thanks a lot for this guide, and I mean it!

Thank You,long time searching a guide like this!!

Wow, that's a lot of thanks for a simple copy/paste. But at least you listed your source

jacklebott said:
Wow, that's a lot of thanks for a simple copy/paste. But at least you listed your source
Click to expand...
Click to collapse
Yes and you wonder why nobody cared to do it earlier, and nobody cared to Google and search themselves.
Sent from my Nexus 4 using XDA Premium HD app

Interesting article for sure. So how do we go ahead and flash these bad boys haha?

evaradar said:
Interesting article for sure. So how do we go ahead and flash these bad boys haha?
Click to expand...
Click to collapse
There governors are built into each kernel. The author of the kernel may choose to build in a different combinations of these governors.
So wait for custom kernels. Actually Faux and Franco and others released a few test builds in the Original Android Development Forum.

I've just added this guide to the Nexus 4 Complete Index
Sent from my GT-I9100 using xda premium

KidCarter93 said:
I've just added this guide to the Nexus 4 Complete Index
Sent from my GT-I9100 using xda premium
Click to expand...
Click to collapse
Thank you! :good:

richteralan said:
There governors are built into each kernel. The author of the kernel may choose to build in a different combinations of these governors.
So wait for custom kernels. Actually Faux and Franco and others released a few test builds in the Original Android Development Forum.
Click to expand...
Click to collapse
Gotcha!

You should put a disclaimer at the top saying that you didn't actually write the guide... Like that other guy did. Kinda misleading otherwise.

red12355 said:
You should put a disclaimer at the top saying that you didn't actually write the guide... Like that other guy did. Kinda misleading otherwise.
Click to expand...
Click to collapse
Why? I dont understand why people get mad or want to give hell and all he was doing is sharing great information and at the end giving credit where it's do.
He has done everything right in this post, (even naming convention) so cut the OP a darn break.
This was not misleading to me at all. He said it was a guide for kernels. I read it. Then he stated where he got his information. I think you should thank the OP for bringing this information to the forum rather than whine.
Sent from my HTC One S using xda premium

dsellers2 said:
Why? I dont understand why people get mad or want to give hell and all he was doing is sharing great information and at the end giving credit where it's do.
He has done everything right in this post, (even naming convention) so cut the OP a darn break.
This was not misleading to me at all. He said it was a guide for kernels. I read it. Then he stated where he got his information. I think you should thank the OP for bringing this information to the forum rather than whine.
Sent from my HTC One S using xda premium
Click to expand...
Click to collapse
Who's whining? Just gave a suggestion.

red12355 said:
Who's whining? Just gave a suggestion.
Click to expand...
Click to collapse
OK I'll move the source/credit link from bottom to the top and blow up the font. Or maybe add a tl;dr in front of the links.
How's that sound?

Thank you!
One question:
What do CFQ, DEADLINE, and NOOP mean?
(In regards to SetCPU App, you can choose a governor on the bottom left an then "cfq", "deadline" and "noop")
Thanks!

Gpu governors explain?

Can someone explain the first three and the last two gpu governors in Franco kernel? I don't know what they are. Also, which gpu governor is best for performance and battery? Thanks.
Sent from my Nexus 6 using XDA Free mobile app

For the governors, you can find explanations of the governors by searching on Google.
Also you're using FauxClock with Franco Kernel which does not ensure compatibility as Franco Kernel's app does not expose GPU Governors.
Also, which gpu governor is best for performance and battery? Thanks.
Click to expand...
Click to collapse
Read the governors, theres one for "powersave" and one for "performance"
Personally I'd recommend using whatever is default and just underclock the GPU and use Per-App-Modes in Franco's app to clock the GPU higher in apps/games that require it.

Here is some info I found by searching the forum posted by another member. I take no credit for this post because I did not write it:
Thanks to deedii for posting this in another forum:
http://forum.xda-developers.com/show...65&postcount=2
Android CPU governors explained
1: OnDemand
2: OndemandX
3: Performance
4: Powersave
5: Conservative
6: Userspace
7: Min Max
8: Interactive
9: InteractiveX
10: Smartass
11: SmartassV2
12: Scary
13: Lagfree
14: Smoothass
15: Brazilianwax
16: SavagedZen
17: Lazy
18: Lionheart
19: LionheartX
20: Intellidemand
21: Hotplug
22: BadAss
23: Wheatley
24: Lulzactive
25: Pegasusq/Pegasusd
26: hotplugx
27: AbissPlug
28: MSM DCVS
29: IntelliActive
30: Adaptive
31: Nightmare
32: ZZmove
INFO I/O Scheduler go here: SCHEDULER
1: OnDemand Governor:
This governor has a hair trigger for boosting clockspeed to the maximum speed set by the user. If the CPU load placed by the user abates, the OnDemand governor will slowly step back down through the kernel's frequency steppings until it settles at the lowest possible frequency, or the user executes another task to demand a ramp.
OnDemand has excellent interface fluidity because of its high-frequency bias, but it can also have a relatively negative effect on battery life versus other governors. OnDemand is commonly chosen by smartphone manufacturers because it is well-tested, reliable, and virtually guarantees the smoothest possible performance for the phone. This is so because users are vastly more likely to ***** about performance than they are the few hours of extra battery life another governor could have granted them.
This final fact is important to know before you read about the Interactive governor: OnDemand scales its clockspeed in a work queue context. In other words, once the task that triggered the clockspeed ramp is finished, OnDemand will attempt to move the clockspeed back to minimum. If the user executes another task that triggers OnDemand's ramp, the clockspeed will bounce from minimum to maximum. This can happen especially frequently if the user is multi-tasking. This, too, has negative implications for battery life.
2: OndemandX:
Basically an ondemand with suspend/wake profiles. This governor is supposed to be a battery friendly ondemand. When screen is off, max frequency is capped at 500 mhz. Even though ondemand is the default governor in many kernel and is considered safe/stable, the support for ondemand/ondemandX depends on CPU capability to do fast frequency switching which are very low latency frequency transitions. I have read somewhere that the performance of ondemand/ondemandx were significantly varying for different i/o schedulers. This is not true for most of the other governors. I personally feel ondemand/ondemandx goes best with SIO I/O scheduler.
3: Performance Governor:
This locks the phone's CPU at maximum frequency. While this may sound like an ugly idea, there is growing evidence to suggest that running a phone at its maximum frequency at all times will allow a faster race-to-idle. Race-to-idle is the process by which a phone completes a given task, such as syncing email, and returns the CPU to the extremely efficient low-power state. This still requires extensive testing, and a kernel that properly implements a given CPU's C-states (low power states).
4: Powersave Governor:
The opposite of the Performance governor, the Powersave governor locks the CPU frequency at the lowest frequency set by the user.
5:Conservative Governor:
This biases the phone to prefer the lowest possible clockspeed as often as possible. In other words, a larger and more persistent load must be placed on the CPU before the conservative governor will be prompted to raise the CPU clockspeed. Depending on how the developer has implemented this governor, and the minimum clockspeed chosen by the user, the conservative governor can introduce choppy performance. On the other hand, it can be good for battery life.
The Conservative Governor is also frequently described as a "slow OnDemand," if that helps to give you a more complete picture of its functionality.
6: Userspace Governor:
This governor, exceptionally rare for the world of mobile devices, allows any program executed by the user to set the CPU's operating frequency. This governor is more common amongst servers or desktop PCs where an application (like a power profile app) needs privileges to set the CPU clockspeed.
7: Min Max
well this governor makes use of only min & maximum frequency based on workload... no intermediate frequencies are used.
8: Interactive Governor:
Much like the OnDemand governor, the Interactive governor dynamically scales CPU clockspeed in response to the workload placed on the CPU by the user. This is where the similarities end. Interactive is significantly more responsive than OnDemand, because it's faster at scaling to maximum frequency.
Unlike OnDemand, which you'll recall scales clockspeed in the context of a work queue, Interactive scales the clockspeed over the course of a timer set arbitrarily by the kernel developer. In other words, if an application demands a ramp to maximum clockspeed (by placing 100% load on the CPU), a user can execute another task before the governor starts reducing CPU frequency. This can eliminate the frequency bouncing discussed in the OnDemand section. Because of this timer, Interactive is also better prepared to utilize intermediate clockspeeds that fall between the minimum and maximum CPU frequencies. This is another pro-battery life benefit of Interactive.
However, because Interactive is permitted to spend more time at maximum frequency than OnDemand (for device performance reasons), the battery-saving benefits discussed above are effectively negated. Long story short, Interactive offers better performance than OnDemand (some say the best performance of any governor) and negligibly different battery life.
Interactive also makes the assumption that a user turning the screen on will shortly be followed by the user interacting with some application on their device. Because of this, screen on triggers a ramp to maximum clockspeed, followed by the timer behavior described above.
9: InteractiveX Governor:
Created by kernel developer "Imoseyon," the InteractiveX governor is based heavily on the Interactive governor, enhanced with tuned timer parameters to better balance battery vs. performance. The InteractiveX governor's defining feature, however, is that it locks the CPU frequency to the user's lowest defined speed when the screen is off.
10: Smartass
Is based on the concept of the interactive governor.
I have always agreed that in theory the way interactive works – by taking over the idle loop – is very attractive. I have never managed to tweak it so it would behave decently in real life. Smartass is a complete rewrite of the code plus more. I think its a success. Performance is on par with the “old” minmax and I think smartass is a bit more responsive. Battery life is hard to quantify precisely but it does spend much more time at the lower frequencies.
Smartass will also cap the max frequency when sleeping to 352Mhz (or if your min frequency is higher than 352 – why?! – it will cap it to your min frequency). Lets take for example the 528/176 kernel, it will sleep at 352/176. No need for sleep profiles any more!"
11: SmartassV2:
Version 2 of the original smartass governor from Erasmux. Another favorite for many a people. The governor aim for an "ideal frequency", and ramp up more aggressively towards this freq and less aggressive after. It uses different ideal frequencies for screen on and screen off, namely awake_ideal_freq and sleep_ideal_freq. This governor scales down CPU very fast (to hit sleep_ideal_freq soon) while screen is off and scales up rapidly to awake_ideal_freq (500 mhz for GS2 by default) when screen is on. There's no upper limit for frequency while screen is off (unlike Smartass). So the entire frequency range is available for the governor to use during screen-on and screen-off state. The motto of this governor is a balance between performance and battery.
12: Scary
A new governor wrote based on conservative with some smartass features, it scales accordingly to conservatives laws. So it will start from the bottom, take a load sample, if it's above the upthreshold, ramp up only one speed at a time, and ramp down one at a time. It will automatically cap the off screen speeds to 245Mhz, and if your min freq is higher than 245mhz, it will reset the min to 120mhz while screen is off and restore it upon screen awakening, and still scale accordingly to conservatives laws. So it spends most of its time at lower frequencies. The goal of this is to get the best battery life with decent performance. It will give the same performance as conservative right now, it will get tweaked over time.
13: Lagfree:
Lagfree is similar to ondemand. Main difference is it's optimization to become more battery friendly. Frequency is gracefully decreased and increased, unlike ondemand which jumps to 100% too often. Lagfree does not skip any frequency step while scaling up or down. Remember that if there's a requirement for sudden burst of power, lagfree can not satisfy that since it has to raise cpu through each higher frequency step from current. Some users report that video playback using lagfree stutters a little.
14: Smoothass:
The same as the Smartass “governor” But MUCH more aggressive & across the board this one has a better battery life that is about a third better than stock KERNEL
15: Brazilianwax:
Similar to smartassV2. More aggressive ramping, so more performance, less battery
16: SavagedZen:
Another smartassV2 based governor. Achieves good balance between performance & battery as compared to brazilianwax.
17: Lazy:
This governor from Ezekeel is basically an ondemand with an additional parameter min_time_state to specify the minimum time CPU stays on a frequency before scaling up/down. The Idea here is to eliminate any instabilities caused by fast frequency switching by ondemand. Lazy governor polls more often than ondemand, but changes frequency only after completing min_time_state on a step overriding sampling interval. Lazy also has a screenoff_maxfreq parameter which when enabled will cause the governor to always select the maximum frequency while the screen is off.
18: Lionheart:
Lionheart is a conservative-based governor which is based on samsung's update3 source.
The tunables (such as the thresholds and sampling rate) were changed so the governor behaves more like the performance one, at the cost of battery as the scaling is very aggressive.
19: LionheartX
LionheartX is based on Lionheart but has a few changes on the tunables and features a suspend profile based on Smartass governor.
20: Intellidemand:
Intellidemand aka Intelligent Ondemand from Faux is yet another governor that's based on ondemand. Unlike what some users believe, this governor is not the replacement for OC Daemon (Having different governors for sleep and awake). The original intellidemand behaves differently according to GPU usage. When GPU is really busy (gaming, maps, benchmarking, etc) intellidemand behaves like ondemand. When GPU is 'idling' (or moderately busy), intellidemand limits max frequency to a step depending on frequencies available in your device/kernel for saving battery. This is called browsing mode. We can see some 'traces' of interactive governor here. Frequency scale-up decision is made based on idling time of CPU. Lower idling time (<20%) causes CPU to scale-up from current frequency. Frequency scale-down happens at steps=5% of max frequency. (This parameter is tunable only in conservative, among the popular governors)
To sum up, this is an intelligent ondemand that enters browsing mode to limit max frequency when GPU is idling, and (exits browsing mode) behaves like ondemand when GPU is busy; to deliver performance for gaming and such. Intellidemand does not jump to highest frequency when screen is off.
21: Hotplug Governor:
The Hotplug governor performs very similarly to the OnDemand governor, with the added benefit of being more precise about how it steps down through the kernel's frequency table as the governor measures the user's CPU load. However, the Hotplug governor's defining feature is its ability to turn unused CPU cores off during periods of low CPU utilization. This is known as "hotplugging."
22: BadAss Governor:
Badass removes all of this "fast peaking" to the max frequency. On a typical system the cpu won't go above 918Mhz and therefore stay cool and will use less power. To trigger a frequency increase, the system must run a bit @ 918Mhz with high load, then the frequency is bumped to 1188Mhz. If that is still not enough the governor gives you full throttle. (this transition should not take longer than 1-2 seconds, depending on the load your system is experiencing)
Badass will also take the gpu load into consideration. If the gpu is moderately busy it will bypass the above check and clock the cpu with 1188Mhz. If the gpu is crushed under load, badass will lift the restrictions to the cpu.
23: Wheatley:
Building on the classic 'ondemand' governor is implemented Wheatley governor. The governor has two additional parameters:
target_residency - The minimum average residency in µs which is considered acceptable for a proper efficient usage of the C4 state. Default is 10000 = 10ms.
allowed_misses - The number sampling intervals in a row the average residency is allowed to be lower than target_residency before the governor reduces the frequency. This ensures that the governor is not too aggressive in scaling down the frequency and reduces it just because some background process was temporarily causing a larger number of wakeups. The default is 5.
Wheatley works as planned and does not hinder the proper C4 usage for task where the C4 can be used properly .
For internet browsing the time spend in C4 has increased by 10% points and the average residency has increased by about 1ms. I guess these differences are mostly due to the different browsing behaviour (I spend the last time more multi-tabbing). But at least we can say that Wheatley does not interfere with the proper use of the C4 state during 'light' tasks. For music playback with screen off the time spend in C4 is practically unchanged, however the average residency is reduced from around 30ms to around 18ms, but this is still more than acceptable.
So the results show that Wheatley works as intended and ensures that the C4 state is used whenever the task allows a proper efficient usage of the C4 state. For more demanding tasks which cause a large number of wakeups and prevent the efficient usage of the C4 state, the governor resorts to the next best power saving mechanism and scales down the frequency. So with the new highly-flexible Wheatley governor one can have the best of both worlds.
Obviously, this governor is only available on multi-core devices.
24: Lulzactive:
Lulzactive:
This new find from Tegrak is based on Interactive & Smartass governors and is one of the favorites.
Old Version: When workload is greater than or equal to 60%, the governor scales up CPU to next higher step. When workload is less than 60%, governor scales down CPU to next lower step. When screen is off, frequency is locked to global scaling minimum frequency.
New Version: Three more user configurable parameters: inc_cpu_load, pump_up_step, pump_down_step. Unlike older version, this one gives more control for the user. We can set the threshold at which governor decides to scale up/down. We can also set number of frequency steps to be skipped while polling up and down.
When workload greater than or equal to inc_cpu_load, governor scales CPU pump_up_step steps up. When workload is less than inc_cpu_load, governor scales CPU down pump_down_step steps down.
Example:
Consider
inc_cpu_load=70
pump_up_step=2
pump_down_step=1
If current frequency=200, Every up_sampling_time Us if cpu load >= 70%, cpu is scaled up 2 steps - to 800.
If current frequency =1200, Every down_sampling_time Us if cpu load < 70%, cpu is scaled down 1 step - to 1000.
25: Pegasusq/Pegasusd
The Pegasus-q / d is a multi-core based on the Ondemand governor and governor with integrated hot-plugging.
Ongoing processes in the queue, we know that multiple processes can run simultaneously on. These processes are active in an array, which is a field called "Run Queue" queue that is ongoing, with their priority values arranged (priority will be used by the task scheduler, which then decides which process to run next).
To ensure that each process has its fair share of resources, each running for a certain period and will eventually stop and then again placed in the queue until it is your turn again. If a program is terminated, so that others can run the program with the highest priority in the current queue is executed.
26: hotplugx
It 'a Hotplug modified and optimized for the suspension in off-screen
27: AbissPlug
It 'a Governor derived hotplug, it works the same way, but with the changes in savings for a better battery.
28: MSM DCVS
a very efficient and wide range of Dynamic Clock and
Voltage Scaling (DCVS) which addresses usage models from
active standby to mid and high level processing requirements.
A Krait CPU can smoothly scale from low power, low
leakage mode to blazingly fast performance.
Believe it's a governor that is mfg'd by qualcomm to utilize new on chip features.
MSM is the prefix for the SOC (MSM8960) and DCVS is Dynamic Clock and Voltage Scaling. Makes sense, MSM-DCVS
29: IntelliActive
Based off Google's Interactive governor with the following enhancements:
1. self-boost capability from input drivers (no need for PowerHAL assist)
2. two phase scheduling (idle/busy phases to prevent from jumping directly to max freq
3. Checks for offline cpus and short circuits some unnecessary checks to improve code execution paths
30: Adaptive
This driver adds a dynamic cpufreq policy governor
designed for latency-sensitive workloads and also for demanding
performance.
This governor attempts to reduce the latency of clock
increases so that the system is more responsive to
interactive workloads in loweset steady-state but to
to reduce power consumption in middle operation level level up
will be done in step by step to prohibit system from going to
max operation level.
31: Nightmare
A PegasusQ modified, less aggressive and more stable. A good compromise between performance and battery.
In addition to the SoD is a prevention because it usually does not hotplug.
32: ZZmove
ZZmove Governor optimized for low power consumption with the screen off, with particular attention to the limitation of consumption applications in the background with the screen off, such as listening to music. It has three settings: battery saver, balanced and performance. In addition to a performance boost, there is also the governor zzmove optimized.
Credits goes to:
http://icrontic.com/discussion/95140...m-tuner-tegrak
http://forum.xda-developers.com/show....php?t=1369817
I/O SCHEDULERS
Q. "What purposes does an i/o scheduler serve?" A.
• Minimize hard disk seek latency.
• Prioritize I/O requests from processes.
• Allocate disk bandwidth for running processes.
• Guarantee that certain requests will be served before a deadline.
So in the simplest of simplest form: Kernel controls the disk access using I/O Scheduler.
Q. "What goals every I/O scheduler tries to balance?" A.
• Fairness (let every process have its share of the access to disk)
• Performance (try to serve requests close to current disk head position first, because seeking there is fastest)
• Real-time (guarantee that a request is serviced in a given time)
Q. "Description, advantages, disadvantages of each I/O Scheduler?" A.
1) Noop
Inserts all the incoming I/O requests to a First In First Out queue and implements request merging. Best used with storage devices that does not depend on mechanical movement to access data (yes, like our flash drives). Advantage here is that flash drives does not require reordering of multiple I/O requests unlike in normal hard drives.
Advantages:
• Serves I/O requests with least number of cpu cycles. (Battery friendly?)
• Best for flash drives since there is no seeking penalty.
• Good throughput on db systems.
Disadvantages:
• Reduction in number of cpu cycles used is proportional to drop in performance.
2) Deadline
Goal is to minimize I/O latency or starvation of a request. The same is achieved by round robin policy to be fair among multiple I/O requests. Five queues are aggressively used to reorder incoming requests.
Advantages:
• Nearly a real time scheduler.
• Excels in reducing latency of any given single I/O.
• Best scheduler for database access and queries.
• Bandwidth requirement of a process - what percentage of CPU it needs, is easily calculated.
• Like noop, a good scheduler for solid state/flash drives.
Disadvantages:
• When system is overloaded, set of processes that may miss deadline is largely unpredictable.
3) CFQ
Completely Fair Queuing scheduler maintains a scalable per-process I/O queue and attempts to distribute the available I/O bandwidth equally among all I/O requests. Each per-process queue contains synchronous requests from processes. Time slice allocated for each queue depends on the priority of the 'parent' process. V2 of CFQ has some fixes which solves process' i/o starvation and some small backward seeks in the hope of improving responsiveness.
Advantages:
• Considered to deliver a balanced i/o performance.
• Easiest to tune.
• Excels on multiprocessor systems.
• Best database system performance after deadline.
Disadvantages:
• Some users report media scanning takes longest to complete using CFQ. This could be because of the property that since the bandwidth is equally distributed to all i/o operations during boot-up, media scanning is not given any special priority.
• Jitter (worst-case-delay) exhibited can sometimes be high, because of the number of tasks competing for the disk.
4) BFQ
Instead of time slices allocation by CFQ, BFQ assigns budgets. Disk is granted to an active process until it's budget (number of sectors) expires. BFQ assigns high budgets to non-read tasks. Budget assigned to a process varies over time as a function of it's behavior.
Advantages:
• Believed to be very good for usb data transfer rate.
• Believed to be the best scheduler for HD video recording and video streaming. (because of less jitter as compared to CFQ and others)
• Considered an accurate i/o scheduler.
• Achieves about 30% more throughput than CFQ on most workloads.
Disadvantages:
• Not the best scheduler for benchmarking.
• Higher budget assigned to a process can affect interactivity and increased latency.
5) SIO
Simple I/O scheduler aims to keep minimum overhead to achieve low latency to serve I/O requests. No priority quesues concepts, but only basic merging. Sio is a mix between noop & deadline. No reordering or sorting of requests.
Advantages:
• Simple, so reliable.
• Minimized starvation of requests.
Disadvantages:
• Slow random-read speeds on flash drives, compared to other schedulers.
• Sequential-read speeds on flash drives also not so good.
6) V(R)
Unlike other schedulers, synchronous and asynchronous requests are not treated separately, instead a deadline is imposed for fairness. The next request to be served is based on it's distance from last request.
Advantages:
• May be best for benchmarking because at the peak of it's 'form' VR performs best.
Disadvantages:
• Performance fluctuation results in below-average performance at times.
• Least reliable/most unstable.
Q. "Best I/O Scheduler?"
A.There is nothing called "best" i/o scheduler. Depending on your usage environment and tasks/apps been run, use different schedulers. That's the best i can suggest.
However, considering the overall performance, battery, reliability and low latency, it is believed that
SIO > Noop > Deadline > VR > BFQ > CFQ, given all schedulers are tweaked and the storage used is a flash device.
Xperia Ray->iPhone 4s->Nexus 5
Click to expand...
Click to collapse

Pilz said:
Here is some info I found by searching the forum posted by another member. I take no credit for this post because I did not write it:
Click to expand...
Click to collapse
Most of those are CPU Governors, not GPU Governors. Yeah theres "powersave" and "performance" but thats common knowledge.

zephiK said:
Most of those are CPU Governors, not GPU Governors. Yeah theres "powersave" and "performance" but thats common knowledge.
Click to expand...
Click to collapse
You're right, I read governor and immediately thought CPU

Pilz said:
You're right, I read governor and immediately thought CPU
Click to expand...
Click to collapse
its okay, we all have those days. But yeah to OP, use what is the default.
No need to change GPU Governors and not a good idea to use FauxClock for a kernel other than Faux Kernel.
Franco hid the option to change GPU Governor to simplify things for the user. I'm sure we've all been there where we used a kernel that has 10 pages of configurations from VRAM, Memory, CPU, GPU, Colors, Page Swap, etc. All of that confuses the user on what to set, and if they set it improperly they'll blame the kernel for not meeting their standards etc.
Just a simple underclock of GPU to 389-500 MHz would be better than setting a GPU Governor to "powersave." In my eyes, dont sacrifice performance for better battery but seek a compromise between performance and battery so that both sides will be happy. That way you'll maximize battery life while maintaining performance

Great answer thank you so much!
Sent from my Nexus 6

[DISCUSSION] [CPU governors] [I/O schdulers and more]

I have created this thread to discuss what cpu and gpu governors are best for battery life, why do you use such governor or scheduler and etc!
Feel free for posting your own opinion,battery results!
But dont forget to wrtie which KERNEL do you use.
Usefull information:
CPU governors:
1: OnDemand
2: OndemandX
3: Performance
4: Powersave
5: Conservative
6: Userspace
7: Min Max
8: Interactive
9: InteractiveX
10: Smartass
11: SmartassV2
12: Scary
13: Lagfree
14: Smoothass
15: Brazilianwax
16: SavagedZen
17: Lazy
18: Lionheart
19: LionheartX
20: Intellidemand
21: Hotplug
22: BadAss
23: Wheatley
24: Lulzactive
25: Pegasusq/Pegasusd
26: hotplugx
27: AbissPlug
28: MSM DCVS
29: IntelliActive
30: Adaptive
31: Nightmare
32: ZZmove
1: OnDemand Governor:
This governor has a hair trigger for boosting clockspeed to the maximum speed set by the user. If the CPU load placed by the user abates, the OnDemand governor will slowly step back down through the kernel's frequency steppings until it settles at the lowest possible frequency, or the user executes another task to demand a ramp.
OnDemand has excellent interface fluidity because of its high-frequency bias, but it can also have a relatively negative effect on battery life versus other governors. OnDemand is commonly chosen by smartphone manufacturers because it is well-tested, reliable, and virtually guarantees the smoothest possible performance for the phone. This is so because users are vastly more likely to ***** about performance than they are the few hours of extra battery life another governor could have granted them.
This final fact is important to know before you read about the Interactive governor: OnDemand scales its clockspeed in a work queue context. In other words, once the task that triggered the clockspeed ramp is finished, OnDemand will attempt to move the clockspeed back to minimum. If the user executes another task that triggers OnDemand's ramp, the clockspeed will bounce from minimum to maximum. This can happen especially frequently if the user is multi-tasking. This, too, has negative implications for battery life.
2: OndemandX:
Basically an ondemand with suspend/wake profiles. This governor is supposed to be a battery friendly ondemand. When screen is off, max frequency is capped at 500 mhz. Even though ondemand is the default governor in many kernel and is considered safe/stable, the support for ondemand/ondemandX depends on CPU capability to do fast frequency switching which are very low latency frequency transitions. I have read somewhere that the performance of ondemand/ondemandx were significantly varying for different i/o schedulers. This is not true for most of the other governors. I personally feel ondemand/ondemandx goes best with SIO I/O scheduler.
3: Performance Governor:
This locks the phone's CPU at maximum frequency. While this may sound like an ugly idea, there is growing evidence to suggest that running a phone at its maximum frequency at all times will allow a faster race-to-idle. Race-to-idle is the process by which a phone completes a given task, such as syncing email, and returns the CPU to the extremely efficient low-power state. This still requires extensive testing, and a kernel that properly implements a given CPU's C-states (low power states).
4: Powersave Governor:
The opposite of the Performance governor, the Powersave governor locks the CPU frequency at the lowest frequency set by the user.
5:Conservative Governor:
This biases the phone to prefer the lowest possible clockspeed as often as possible. In other words, a larger and more persistent load must be placed on the CPU before the conservative governor will be prompted to raise the CPU clockspeed. Depending on how the developer has implemented this governor, and the minimum clockspeed chosen by the user, the conservative governor can introduce choppy performance. On the other hand, it can be good for battery life.
The Conservative Governor is also frequently described as a "slow OnDemand," if that helps to give you a more complete picture of its functionality.
6: Userspace Governor:
This governor, exceptionally rare for the world of mobile devices, allows any program executed by the user to set the CPU's operating frequency. This governor is more common amongst servers or desktop PCs where an application (like a power profile app) needs privileges to set the CPU clockspeed.
7: Min Max
well this governor makes use of only min & maximum frequency based on workload... no intermediate frequencies are used.
8: Interactive Governor:
Much like the OnDemand governor, the Interactive governor dynamically scales CPU clockspeed in response to the workload placed on the CPU by the user. This is where the similarities end. Interactive is significantly more responsive than OnDemand, because it's faster at scaling to maximum frequency.
Unlike OnDemand, which you'll recall scales clockspeed in the context of a work queue, Interactive scales the clockspeed over the course of a timer set arbitrarily by the kernel developer. In other words, if an application demands a ramp to maximum clockspeed (by placing 100% load on the CPU), a user can execute another task before the governor starts reducing CPU frequency. This can eliminate the frequency bouncing discussed in the OnDemand section. Because of this timer, Interactive is also better prepared to utilize intermediate clockspeeds that fall between the minimum and maximum CPU frequencies. This is another pro-battery life benefit of Interactive.
However, because Interactive is permitted to spend more time at maximum frequency than OnDemand (for device performance reasons), the battery-saving benefits discussed above are effectively negated. Long story short, Interactive offers better performance than OnDemand (some say the best performance of any governor) and negligibly different battery life.
Interactive also makes the assumption that a user turning the screen on will shortly be followed by the user interacting with some application on their device. Because of this, screen on triggers a ramp to maximum clockspeed, followed by the timer behavior described above.
9: InteractiveX Governor:
Created by kernel developer "Imoseyon," the InteractiveX governor is based heavily on the Interactive governor, enhanced with tuned timer parameters to better balance battery vs. performance. The InteractiveX governor's defining feature, however, is that it locks the CPU frequency to the user's lowest defined speed when the screen is off.
10: Smartass
Is based on the concept of the interactive governor.
I have always agreed that in theory the way interactive works – by taking over the idle loop – is very attractive. I have never managed to tweak it so it would behave decently in real life. Smartass is a complete rewrite of the code plus more. I think its a success. Performance is on par with the “old” minmax and I think smartass is a bit more responsive. Battery life is hard to quantify precisely but it does spend much more time at the lower frequencies.
Smartass will also cap the max frequency when sleeping to 352Mhz (or if your min frequency is higher than 352 – why?! – it will cap it to your min frequency). Lets take for example the 528/176 kernel, it will sleep at 352/176. No need for sleep profiles any more!"
11: SmartassV2:
Version 2 of the original smartass governor from Erasmux. Another favorite for many a people. The governor aim for an "ideal frequency", and ramp up more aggressively towards this freq and less aggressive after. It uses different ideal frequencies for screen on and screen off, namely awake_ideal_freq and sleep_ideal_freq. This governor scales down CPU very fast (to hit sleep_ideal_freq soon) while screen is off and scales up rapidly to awake_ideal_freq (500 mhz for GS2 by default) when screen is on. There's no upper limit for frequency while screen is off (unlike Smartass). So the entire frequency range is available for the governor to use during screen-on and screen-off state. The motto of this governor is a balance between performance and battery.
12: Scary
A new governor wrote based on conservative with some smartass features, it scales accordingly to conservatives laws. So it will start from the bottom, take a load sample, if it's above the upthreshold, ramp up only one speed at a time, and ramp down one at a time. It will automatically cap the off screen speeds to 245Mhz, and if your min freq is higher than 245mhz, it will reset the min to 120mhz while screen is off and restore it upon screen awakening, and still scale accordingly to conservatives laws. So it spends most of its time at lower frequencies. The goal of this is to get the best battery life with decent performance. It will give the same performance as conservative right now, it will get tweaked over time.
13: Lagfree:
Lagfree is similar to ondemand. Main difference is it's optimization to become more battery friendly. Frequency is gracefully decreased and increased, unlike ondemand which jumps to 100% too often. Lagfree does not skip any frequency step while scaling up or down. Remember that if there's a requirement for sudden burst of power, lagfree can not satisfy that since it has to raise cpu through each higher frequency step from current. Some users report that video playback using lagfree stutters a little.
14: Smoothass:
The same as the Smartass “governor” But MUCH more aggressive & across the board this one has a better battery life that is about a third better than stock KERNEL
15: Brazilianwax:
Similar to smartassV2. More aggressive ramping, so more performance, less battery
16: SavagedZen:
Another smartassV2 based governor. Achieves good balance between performance & battery as compared to brazilianwax.
17: Lazy:
This governor from Ezekeel is basically an ondemand with an additional parameter min_time_state to specify the minimum time CPU stays on a frequency before scaling up/down. The Idea here is to eliminate any instabilities caused by fast frequency switching by ondemand. Lazy governor polls more often than ondemand, but changes frequency only after completing min_time_state on a step overriding sampling interval. Lazy also has a screenoff_maxfreq parameter which when enabled will cause the governor to always select the maximum frequency while the screen is off.
18: Lionheart:
Lionheart is a conservative-based governor which is based on samsung's update3 source.
The tunables (such as the thresholds and sampling rate) were changed so the governor behaves more like the performance one, at the cost of battery as the scaling is very aggressive.
19: LionheartX
LionheartX is based on Lionheart but has a few changes on the tunables and features a suspend profile based on Smartass governor.
20: Intellidemand:
Intellidemand aka Intelligent Ondemand from Faux is yet another governor that's based on ondemand. Unlike what some users believe, this governor is not the replacement for OC Daemon (Having different governors for sleep and awake). The original intellidemand behaves differently according to GPU usage. When GPU is really busy (gaming, maps, benchmarking, etc) intellidemand behaves like ondemand. When GPU is 'idling' (or moderately busy), intellidemand limits max frequency to a step depending on frequencies available in your device/kernel for saving battery. This is called browsing mode. We can see some 'traces' of interactive governor here. Frequency scale-up decision is made based on idling time of CPU. Lower idling time (= 70%, cpu is scaled up 2 steps - to 800.
If current frequency =1200, Every down_sampling_time Us if cpu load < 70%, cpu is scaled down 1 step - to 1000.
25: Pegasusq/Pegasusd
The Pegasus-q / d is a multi-core based on the Ondemand governor and governor with integrated hot-plugging.
Ongoing processes in the queue, we know that multiple processes can run simultaneously on. These processes are active in an array, which is a field called "Run Queue" queue that is ongoing, with their priority values ​​arranged (priority will be used by the task scheduler, which then decides which process to run next).
To ensure that each process has its fair share of resources, each running for a certain period and will eventually stop and then again placed in the queue until it is your turn again. If a program is terminated, so that others can run the program with the highest priority in the current queue is executed.
26: hotplugx
It 'a Hotplug modified and optimized for the suspension in off-screen
27: AbissPlug
It 'a Governor derived hotplug, it works the same way, but with the changes in savings for a better battery.
28: MSM DCVS
a very efficient and wide range of Dynamic Clock and
Voltage Scaling (DCVS) which addresses usage models from
active standby to mid and high level processing requirements.
A Krait CPU can smoothly scale from low power, low
leakage mode to blazingly fast performance.
Believe it's a governor that is mfg'd by qualcomm to utilize new on chip features.
MSM is the prefix for the SOC (MSM8960) and DCVS is Dynamic Clock and Voltage Scaling. Makes sense, MSM-DCVS
29: IntelliActive
Based off Google's Interactive governor with the following enhancements:
1. self-boost capability from input drivers (no need for PowerHAL assist)
2. two phase scheduling (idle/busy phases to prevent from jumping directly to max freq
3. Checks for offline cpus and short circuits some unnecessary checks to improve code execution paths
30: Adaptive
This driver adds a dynamic cpufreq policy governor
designed for latency-sensitive workloads and also for demanding
performance.
This governor attempts to reduce the latency of clock
increases so that the system is more responsive to
interactive workloads in loweset steady-state but to
to reduce power consumption in middle operation level level up
will be done in step by step to prohibit system from going to
max operation level.
31: Nightmare
A PegasusQ modified, less aggressive and more stable. A good compromise between performance and battery.
In addition to the SoD is a prevention because it usually does not hotplug.
32: ZZmove
ZZmove Governor optimized for low power consumption with the screen off, with particular attention to the limitation of consumption applications in the background with the screen off, such as listening to music. It has three settings: battery saver, balanced and performance. In addition to a performance boost, there is also the governor zzmove optimized.
I/O schedulers:
1) Noop
Inserts all the incoming I/O requests to a First In First Out queue and implements request merging. Best used with storage devices that does not depend on mechanical movement to access data (yes, like our flash drives). Advantage here is that flash drives does not require reordering of multiple I/O requests unlike in normal hard drives.
Advantages:
Serves I/O requests with least number of cpu cycles. (Battery friendly?)
Best for flash drives since there is no seeking penalty.
Good throughput on db systems.
Disadvantages:
Reduction in number of cpu cycles used is proportional to drop in performance.
2) Deadline
Goal is to minimize I/O latency or starvation of a request. The same is achieved by round robin policy to be fair among multiple I/O requests. Five queues are aggressively used to reorder incoming requests.
Advantages:
Nearly a real time scheduler.
Excels in reducing latency of any given single I/O.
Best scheduler for database access and queries.
Bandwidth requirement of a process - what percentage of CPU it needs, is easily calculated.
Like noop, a good scheduler for solid state/flash drives.
Disadvantages:
When system is overloaded, set of processes that may miss deadline is largely unpredictable.
3) CFQ
Completely Fair Queuing scheduler maintains a scalable per-process I/O queue and attempts to distribute the available I/O bandwidth equally among all I/O requests. Each per-process queue contains synchronous requests from processes. Time slice allocated for each queue depends on the priority of the 'parent' process. V2 of CFQ has some fixes which solves process' i/o starvation and some small backward seeks in the hope of improving responsiveness.
Advantages:
Considered to deliver a balanced i/o performance.
Easiest to tune.
Excels on multiprocessor systems.
Best database system performance after deadline.
Disadvantages:
Some users report media scanning takes longest to complete using CFQ. This could be because of the property that since the bandwidth is equally distributed to all i/o operations during boot-up, media scanning is not given any special priority.
Jitter (worst-case-delay) exhibited can sometimes be high, because of the number of tasks competing for the disk.
4) BFQ
Instead of time slices allocation by CFQ, BFQ assigns budgets. Disk is granted to an active process until it's budget (number of sectors) expires. BFQ assigns high budgets to non-read tasks. Budget assigned to a process varies over time as a function of it's behavior.
Advantages:
Believed to be very good for usb data transfer rate.
Believed to be the best scheduler for HD video recording and video streaming. (because of less jitter as compared to CFQ and others)
Considered an accurate i/o scheduler.
Achieves about 30% more throughput than CFQ on most workloads.
Disadvantages:
Not the best scheduler for benchmarking.
Higher budget assigned to a process can affect interactivity and increased latency.
5) SIO
Simple I/O scheduler aims to keep minimum overhead to achieve low latency to serve I/O requests. No priority quesues concepts, but only basic merging. Sio is a mix between noop & deadline. No reordering or sorting of requests.
Advantages:
Simple, so reliable.
Minimized starvation of requests.
Disadvantages:
Slow random-read speeds on flash drives, compared to other schedulers.
Sequential-read speeds on flash drives also not so good.
6) V(R)
Unlike other schedulers, synchronous and asynchronous requests are not treated separately, instead a deadline is imposed for fairness. The next request to be served is based on it's distance from last request.
Advantages:
May be best for benchmarking because at the peak of it's 'form' VR performs best.
Disadvantages:
Performance fluctuation results in below-average performance at times.
Least reliable/most unstable.
7) Anticipatory
Based on two facts
i) Disk seeks are really slow.
ii) Write operations can happen whenever, but there is always some process waiting for read operation.
So anticipatory prioritize read operations over write. It anticipates synchronous read operations.
Advantages:
Read requests from processes are never starved.
As good as noop for read-performance on flash drives.
Disadvantages:
'Guess works' might not be always reliable.
Reduced write-performance on high performance disks.
Credits go to Google and XDA forum for provided information!

If you found new cpu and gpu governors or i/o schedulers with explanation just pm me(provide the link to post/site/thread)

reserved

Good thread
i am on hellscore kernel ver.b8.0
my setting
min cpu 652 max 1497 Hellsactive cpu governor , max cpu online at on time =3
UV=-35000uv
i/o=1024 KB AND fiops (when i set noop it's change )
i can't reach SOT More than 3h
what should i change

7sen said:
Good thread
i am on hellscore kernel ver.b8.0
my setting
min cpu 652 max 1497 Hellsactive cpu governor , max cpu online at on time =3
UV=-35000uv
i/o=1024 KB AND fiops (when i set noop it's change )
i can't reach SOT More than 3h
what should i change
Click to expand...
Click to collapse
Have you tried hellscore kernel app?(it supports n5)
Sent from my Nexus 5 using XDA Free mobile app

I'm using Hellscore 8.5-L with hellsactive governor. It's nice and smooth, with a medium battery life (can be improved with a few tweaks). Best I/O scheduler is FIOPS IMO.
otavio

What are the adventages of fiops compared to deadline ? I saw some comparisons showing that fiops has few higher scores in read / write tests, but what about battery management ? :/

I use UBER-L kernel with optipop rom and settings below :
- CPU max core = 2
- CPU freq min = 652 MHz
- CPU freq max = 1728 MHz
- CPU Governor = uberdemand
- Multicore power saving = aggressive
- CPU undervolt = -30 mV
- I/O scheduler = FIOPS
- I/O read-ahead = 2048 KB
- GPU governor = ondemand
- GPU max freq = 320 MHz
- GPU down threshold = 50
- GPU up treshold = 75
I can use my phone for 2 days with internet navigation, sms, calls and game each days.
GPS and wifi are disabled when i don't need it.

airbat said:
I use UBER-L kernel with optipop rom and settings below :
- CPU max core = 2
- CPU freq min = 652 MHz
- CPU freq max = 1728 MHz
- CPU Governor = uberdemand
- Multicore power saving = aggressive
- CPU undervolt = -30 mV
- I/O scheduler = FIOPS
- I/O read-ahead = 2048 KB
- GPU governor = ondemand
- GPU max freq = 320 MHz
- GPU down threshold = 50
- GPU up treshold = 75
I can use my phone for 2 days with internet navigation, sms, calls and game each days.
GPS and wifi are disabled when i don't need it.
Click to expand...
Click to collapse
How much time of SoT?
Sent from my Nexus 5 using XDA Free mobile app

Synapse tell me this :
Total = 100 %
sleep = 78,3 %
awake = 21,7 %
Most significant CPU states are :
300 MHz = 30%
652 MHz = 20 %
960 MHz = 5 %
1190 MHz = 5 %
1728 MHz = 38,8 %
I can't monitor GPU states actually son i can't tell which states are the most used.

Ah memories, i remember these from my XMP days, was a bit of a shock when i came on to N5 to find only 3-4 governors but then again i learned how to modify the existing governs for my liking. Most kernels ship with their own custom governors like elementalX. As for scheduling i switch between BFQ and noop.

I use ElementalX kernel.
Recommended governor.
However, by using BFQ as i/o scheduler and a larger read ahead value, this is the only way I've been able to avoid the audio/video playback buffer jitter that seems to be a lollipop introduced issue.
It isn't a perfect fix but seems to help a lot with smooth audio/video playback. Any latency that I can report is not so much a disadvantage. I can type fast and accurately still, and the frustration with not being able to listen to music without constant interruption was worse than any lag in responsiveness i have introduced. Gaming would probably suffer, but I don't game at all.

kgs1992 said:
Hey,
To the best of my understanding, they are I/O schedulers based on certain algorithms.
It's easy to explain if you know how queues are implemented.
noop is just a First In First Out standard queue of I/O operations.
cfq (Completely Fair Scheduling) is similar to the Round Robin algorithm and basically allots a fixed execution time for each I/O operation (they are implemented as a circular queue)
deadline is like a priority queue with an aging concept. Basically it adds a dealine for each I/O operation & implements a priority queue
Furthermore, there are 2 queues, one for read & one for write operations.
I'm sorry if this doesn't make sense, you just asked a technical question & I don't know how to explain better than this!
EDIT: Okay, I didn't see the link, most of the info I gave is present there.
EDIT: Here's an analogy, if people were queuing up to buy ice cream:
noop would implement the first come first serve rule.
cfq would let each person to buy one ice cream at a time & go back to the end of the queue if he wants another.
deadline would keep a separate queue for certain people (like older people & people who have been waiting for too long; somewhat setting a priority) & would serve the separate queue first.
Tried my best.
Click to expand...
Click to collapse
Here is an interesting explanation about schedulers. Credit to him.

FIOPS is hands on the best scheduler for the N5.
http://www.phoronix.com/scan.php?page=news_item&px=MTAzOTU
This new I/O scheduler is designed around the following assumptions about Flash-based storage devices: no I/O seek time, read and write I/O cost is usually different from rotating media, time to make a request depends upon the request size, and high through-put and higher IOPS with low-latency. With these flash characteristics in mind, he wrote FIOPS.
Click to expand...
Click to collapse
Pair FIOPS with f2fs, and you've got a winner.

JayR_L said:
FIOPS is hands on the best scheduler for the N5.
http://www.phoronix.com/scan.php?page=news_item&px=MTAzOTU
Pair FIOPS with f2fs, and you've got a winner.
Click to expand...
Click to collapse
agreed, have that setup right now
this thing flies

By the way, OP, I don't want to troll your thread, but just stating "XDA" in your sources. This doesn't credit the author.
So I'll do it for you.
http://forum.xda-developers.com/showthread.php?t=2222345
And he in turn just copied and pasted from various parts of the net, as he says in post number 8.
So please people, do some of your own research before believing everything you see on the net.

JayR_L said:
By the way, OP, I don't want to troll your thread, but just stating "XDA" in your sources. This doesn't credit the author.
So I'll do it for you.
http://forum.xda-developers.com/showthread.php?t=2222345
And he in turn just copied and pasted from various parts of the net, as he says in post number 8.
So please people, do some of your own research before believing everything you see on the net.
Click to expand...
Click to collapse
Oops
My fault
Sorry
Sent from my Nexus 5 using XDA Free mobile app

Dr.Pepper said:
If you found new cpu and gpu governors or i/o schedulers with explanation just pm me(provide the link to post/site/thread)
Click to expand...
Click to collapse
Oh yeah, I've found a lot of them here... :good:

Good thread. Wish pple would concentrate on the real life use of the phone and forget about benchmark. Noop, on demand, and Westwood. are the best trio when used together. Used them for years, with tests of others, but this works for me. Using Marchmellow and EX Kernel

[KERNEL][TW/LP][13.10.15][SM-T800][SM-T805] IronKernel V2.5 STweaks

Hey guys, I'm back with a new KERNEL for both Variants of the Tab S 10.5 (T800 and T805)!
Some guys probably know me from the IronRom . I decided myselfe to create a custom kernel for our really great Tab s 10.5, I'm getting better and better at this stuff, I don't thought that
It is basically the normal kernel with some modifications for better performance and hopefully also batterylife. It is for the stock kitkat (4.4.2) touchwiz and not for cyanogenmod or something else.
I excuse all devs here visiting my github page, it is such a mess (with the commits)! I know it, but I'm doing this the first time, so hopefully you will forgive me.
The kernel is pretty stable, I just call it a beta version, because I can't test the T800 version, so if with thisone also all works great -> stable
IF YOU FOLLOW MY STEPS BELOW, YOU WILL MAY LOSE YOUR WARRANTY, KNOX WILL DISPLAY 0x1! I'M NOT RESPONSIBLE FOR ANY DAMAGED DEVICE!
You can try to use the kernel adiutor app, or just the preinstalled sTweaks, but not both at the same time! This will cause problems.
Notice, V2.0 and onwards is only for TW lollipop and not for kitkat anymore!!
Features of my Kernel::​- Built with latest 5.2 Toolchain compiled by myself!!
- Latest Kernel version 3.4.109, includes all updates from linux mainstream, patched it form 3.4.39 up to 3.4.109 (was a lot of work)
- Choose between different CPU governors: Interactive (default), Powersave, Performance, Userspace, Conservative, Intellidemand, Intelliactive, Ondemand, Adaptive, Abyssplug, AbyssplugV2, Badass, DanceDance, ZZmove, Nightmare, Wheatley, Lionheart, Darkness, PegasusQ and Intellimm
- Built with latest ramdisk sources from samsung
- Kernelsource from T805XXU1BOG2
- Underclock to 200MHz and Overclock to 2.0GHz
- GPU works from 100MHz to 733MHz (default)
- I/O schedulers: ROW (Default), cfq, No-op, Deadline, Test, BFQ, FIOPS, SIO, VR, ZEN, FIFO and SIOplus
- Readahead can be set
- UKSM (Ultar Kernel Samepage Merging)
- Gentlefairsleeper and ARCH power
- Android Logger
- data and cache f2fs support!
- Init.d Support
- Busybox support
- Full STweaks support
- Charging Control
- Cpufreq voltcontrol
- ZRam and Swap
- Allow ADB-Insecure
- Low Memory Kill
- TCP (Network) control: Cubic (default), Reno, Bic, Westwood, Highspeed, Hybla, HTCP, Vegas, Veno, Scalable, LP, Yeah and Illinois
- SeLinux is set to permissive
- Compiled as small as it could be (just around 6MB)
Download:​In the second post
Googy Max STweaks​
Bugs/Problems:​-sTweaks can't enable the right GPU over and underclock freqency
-Some other stweaks stuff, you will see
-Didn't tried the voltage table​
Instructions:​
If you want to install the Kernel, follow this:
1. Install a custom recovery for your tablet, like this one here: TWRP Recovery
2. Follow the instructions on the page above, until you get a working recovery
3. Download the Kernel from below and copy it to your external SD Card
4. Reboot to your recovery by pressing volume up, home button and power button at the same time.
5. Install zip, and select the kernel
6. Wipe cache and dalvik cache (recommand)
7. Reboot
Support:​If you like my work, please hit a thanks down on my posts. A thanks is enough!:highfive: If you really really really really really like my work, you can donate something to me, but it is not necessary. I created a paypal account, just in case, someone would give me a small donation. :good:
As I said, you don't have to give me something, but this keeps me motivated to built better roms and keep updating everything. It's your choice, and I'm very thankfull for every donation! No matter how big it is! Thank you so much for supporting me, cheers and have a nice day :fingers-crossed:​
Donators for the Kernel:​- @Hookmt Thank you very much for your support giving to me! I really love that and it also wasn't the first time you donate something to me! Thank you so much, I really really really appreciat that mate. Transaction number: 42P214019W495221S
Credits/Thanks:​- Samsung for sources
- @Christopher83 for the compiler
- @UpInTheAir for the work he already did in his own kernel (could use some of his commits on github (opensource) and see what he did when I didn't know what I did wrong). He also inspired me to work on my own stuff and kernel, thank you very much!
- @googy_anas, without him, I would not have a working kernel here, he did so much for me and also for his own kernel! He
let me use everything he already did, I got so much stuff from his page and included it in my kernel. I'm so thankfull for all the support he gave to me! I know a thank you isn't enough, but I wanted to write it here.
- @googy_anas (again this great man!) and @kryten2k35 thank you so much for let me using your stweaks app! Great work you have done on thatone!
- @faux123 for all the great stuff he did for the kernels
- @Yank555
If you want to take my work and need it somewhere, or do other things with it, please ask me first for the permission. Otherwise you are not allowed to take it! Thank you !
XDA:DevDB Information
Stock Based Kernel for Tab S 10.5, Kernel for the Samsung Galaxy Tab S
Contributors
Tkkg1994, @googy_anas
Source Code: https://github.com/Tkkg1994/IronKernel
Kernel Special Features:
Version Information
Status: Stable
Current Stable Version: V2.5
Stable Release Date: 2015-10-13
Current Beta Version: 1.0
Beta Release Date: 2015-02-19
Created 2015-02-20
Last Updated 2015-10-12

Changelog:
Kitkat
IronKernel Beta V1.0 on 20.02.2015:
Initial release!
Ironkernel V1.1 26.02.2015:
-Temporarly removed Intelli-Plug
-Added voltcontroll for CPU
-Added Stweaks support and Stweaks app (all credits and stuff goes to @googy_anas and @Kryten2k35
-Hell lot of improvements
-Init.d support and busybox support
-GPU overclock to 733MHz
-CPU overclock to 2.1GHz (sorry, I couldn't get it stable )
-for more what I had done, visit here: Commits IronKernel
-Added fast charge support
IronKernel V1.2 01.03.2015:
- Built with latest toolchain (2015.02) by christopher83
- Use frandom from now
- Enable dynamic page writeback with earlysuspend
- Better battery charging control (kernel and stweaks)
- Auto install the right sTweaks version
- Reduce overestimating rq->avg_idle
- Optimize find_busiest_queue()
- Some CPUfreq optimizations
- Dynamic sync control with earlysuspend support
- Lowmemorykiller: implement task's adj rbtree
- Check free memory when tasks switch to background
- Dynamic FSync
- SOO Much more but I don't remember all
- After flashing the kernel, it will be successfull, but then show an error (becaus of mounting partition) don't worry, just reboot. Just ignore it
Changelog V1.3.5 08.03.15:
- Prerelease of V1.3 was on the ironrom
- Script auto-removes all knox containors/apps
- cpufreq: Retain only online cpus in managed_policy->cpus
- cpufreq: make the "scaling_cur_freq" sysfs entry pollable
- cpufreq: Make the "scaling_governor" sysfs node pollable
- cpufreq: Save and restore min and max frequencies
- fix some missing stuff with default governor
- cpufreq: Notify governors when cpus are hot-[un]plugged
- Updated nightmare and zzmoove governors
- net: ipv6: Add a sysctl to make optimistic addresses useful candidates
- fs/proc/task_mmu.c: add user-space support for resetting mm
- net: ipv6: allow choosing optimistic addresses with use_optimistic
- sched/idle: Avoid spurious wakeup IPIs
- cpufreq: Return directly in __cpufreq_get if policy is NULL
- new relation between governors
- ARM: 8226/1: cacheflush: get rid of restarting block
Changelog V1.4 23.03.15:
- It is simply to much to write everything here.. what I did
- Wolfson Control for the sound on our Tab S
- Added voltage control (doesen't work 100%)
- sched: Add an rq migration call-back to sched_class
- sched: Account for blocked load waking back up …
- sched: Normalize tg load contributions against runnable time
- sched: Refactor update_shares_cpu() -> update_blocked_avgs()
- sched/fair: Set se->vruntime directly in place_entity()
- sched: provide per cpu-cgroup option to notify on migrations
- sched: Make sure to not re-read variables after validation
- sched: Add WAKEUP_PREEMPTION feature flag, on by default
And this goes on for like 2 or 3 pages lol So the changelog is tooooooo long.
Lollipop
Changelog V2.0 10.04.15:
- Full lollipop compatible! (not with kitkat anymore!)
- Support CIFS
- Overclock to 2.0 GHz (other will be back soon)
- Include all features of all previous releases! Such as stweask, overclocked gpu etc.
- Based on latest samsung opensource T800XXU1BOCC
Was a lot of work to port all to Lollipop
If you got problems with sTweaks showing "loaded", but nothing happen, go to a root explorer, navigate to system/xbin, copy Busybox and past it in /sbin direction!
Changelog V2.1 16.05.15:
- Fix stweaks problems
- Voltage is still NOT working
- add tripndroid scheduler
- add row scheduler
- add and enable UKSM (ultra kernel samepage merging)
- update ramdisk to latest versions
- f2fs
- update linux to 3.4.107
- more stuff I may forgot
Changelog V2.2 08.07.15:
- Update to latest linux mainstream (3.4.108)
- Updated ramdisk source to OE3
- New source patches from official kernel opensource center (samsung)
- this does only work on the newer bases, as BOE3, the old ones will get a bootloop!
Changelog V2.2.5 16.07.15:
- Fixed "slow" charging (Thanks to AndreiLux and UpInTheAir!)
- Incrased sound so it will be a louder by default
- Some other small ramdisk fixes
Changelog V2.3 08.09.15:
- Kernel Rebased on latest OG2 kernel source
- Fix some heating issues that where reported
- Ramdisk update to OG2
- Fully support f2fs in /data and /cache
- Build with latest 4.9.4 toolchain
Changelog V2.4 05.10.15:
- Update to 5.2 toolchain compiled by myself!
- updated to 3.4.109 linux
- ftrace: Make all inline tags also include notrace
- compiler-gcc4.h: correct verion check for __compiletime_error
- compiler.h: add __visible
- compiler{,-gcc4}.h, bug.h: Remove duplicate macros
- some more optimisations concerning compiler
- msm: cpufreq: Only apply driver limits for scaling_min/max_freq writes
- drivers: cpufreq: Send a uevent when governor changes
- cpufreq: Save user policy min/max instead of policy min/max during hotplug
- cpufreq: Fix broken uevents for cpufreq governor and cpu devices
- cpufreq: Always allow update of user policy
- drivers: cpufreq: Upstream optimizations
- cpufreq: Export user_policy min/max
- cpufreq: Add policy notifiers
- cpufreq: Simplify cpufreq_add_dev()
- some more cpufreq things that I made
- cpufreq_stats: do not remove sysfs files if frequency table is not present
- sched/numa: Rewrite the CONFIG_NUMA sched domain support
- sched/numa: Fix the new NUMA topology bits
- sched/numa: Don't scale the imbalance
- sched/debug: Fix printing large integers on 32-bit platforms
- sched: Remove stale power aware scheduling remnants and dysfunctional knobs
- f2fs: update to latest version
- tima debug log disabled
- uksm: disabled by default
Changelog V2.5 13.10.15:
- enabled tima debug again
- fixed some Random reboots people had
- added pegasusq cpugovernor
- arm/crypto: Add optimized AES and SHA1 routines
- added cifs, nfs, exportfs, cdrom, all ramdisk support (joystick too)
- ARM: 7626/1: arm/crypto: Make asm SHA-1 and AES code Thumb-2 compatible
- ARM: 7723/1: crypto: sha1-armv4-large.S: fix SP handling
- ARM: 8119/1: crypto: sha1: add ARM NEON implementation
- ARM: 8120/1: crypto: sha512: add ARM NEON implementation
- a lot of other crypto optimisations (like 10 patches)
- cpufreq: Move get_cpu_idle_time() to cpufreq.c
- workqueue: set delayed_work->timer function on initialization
- workqueue: don't use WQ_HIGHPRI for unbound workqueues
- workqueue: factor out worker_pool from global_cwq
- workqueue: use @pool instead of @gcwq or @Cpu where applicable
- workqueue: separate out worker_pool flags
- workqueue: introduce NR_WORKER_POOLS and for_each_worker_pool()
- workqueue: reimplement WQ_HIGHPRI using a separate worker_pool
- hashtable: introduce a small and naive hashtable
- workqueue: use new hashtable implementation
- workqueue: drop @bind from create_worker()
- much more workqueue updates, to see them all, please visit here: Github Kernel Updates

Governors and I/O Scheduler:
Original Thread: Governor Explained, all credits go to @stempox
1: OnDemand
2: OndemandX
3: Performance
4: Powersave
5: Conservative
6: Userspace
7: Min Max
8: Interactive
9: InteractiveX
10: Smartass
11: SmartassV2
12: Scary
13: Lagfree
14: Smoothass
15: Brazilianwax
16: SavagedZen
17: Lazy
18: Lionheart
19: LionheartX
20: Intellidemand
21: Hotplug
22: BadAss
23: Wheatley
24: Lulzactive
25: Pegasusq/Pegasusd
26: hotplugx
27: AbissPlug
28: MSM DCVS
29: IntelliActive
30: Adaptive
31: Nightmare
32: ZZmove
1: OnDemand Governor:
This governor has a hair trigger for boosting clockspeed to the maximum speed set by the user. If the CPU load placed by the user abates, the OnDemand governor will slowly step back down through the kernel's frequency steppings until it settles at the lowest possible frequency, or the user executes another task to demand a ramp.
OnDemand has excellent interface fluidity because of its high-frequency bias, but it can also have a relatively negative effect on battery life versus other governors. OnDemand is commonly chosen by smartphone manufacturers because it is well-tested, reliable, and virtually guarantees the smoothest possible performance for the phone. This is so because users are vastly more likely to ***** about performance than they are the few hours of extra battery life another governor could have granted them.
This final fact is important to know before you read about the Interactive governor: OnDemand scales its clockspeed in a work queue context. In other words, once the task that triggered the clockspeed ramp is finished, OnDemand will attempt to move the clockspeed back to minimum. If the user executes another task that triggers OnDemand's ramp, the clockspeed will bounce from minimum to maximum. This can happen especially frequently if the user is multi-tasking. This, too, has negative implications for battery life.
2: OndemandX:
Basically an ondemand with suspend/wake profiles. This governor is supposed to be a battery friendly ondemand. When screen is off, max frequency is capped at 500 mhz. Even though ondemand is the default governor in many kernel and is considered safe/stable, the support for ondemand/ondemandX depends on CPU capability to do fast frequency switching which are very low latency frequency transitions. I have read somewhere that the performance of ondemand/ondemandx were significantly varying for different i/o schedulers. This is not true for most of the other governors. I personally feel ondemand/ondemandx goes best with SIO I/O scheduler.
3: Performance Governor:
This locks the phone's CPU at maximum frequency. While this may sound like an ugly idea, there is growing evidence to suggest that running a phone at its maximum frequency at all times will allow a faster race-to-idle. Race-to-idle is the process by which a phone completes a given task, such as syncing email, and returns the CPU to the extremely efficient low-power state. This still requires extensive testing, and a kernel that properly implements a given CPU's C-states (low power states).
4: Powersave Governor:
The opposite of the Performance governor, the Powersave governor locks the CPU frequency at the lowest frequency set by the user.
5:Conservative Governor:
This biases the phone to prefer the lowest possible clockspeed as often as possible. In other words, a larger and more persistent load must be placed on the CPU before the conservative governor will be prompted to raise the CPU clockspeed. Depending on how the developer has implemented this governor, and the minimum clockspeed chosen by the user, the conservative governor can introduce choppy performance. On the other hand, it can be good for battery life.
The Conservative Governor is also frequently described as a "slow OnDemand," if that helps to give you a more complete picture of its functionality.
6: Userspace Governor:
This governor, exceptionally rare for the world of mobile devices, allows any program executed by the user to set the CPU's operating frequency. This governor is more common amongst servers or desktop PCs where an application (like a power profile app) needs privileges to set the CPU clockspeed.
7: Min Max
well this governor makes use of only min & maximum frequency based on workload... no intermediate frequencies are used.
8: Interactive Governor:
Much like the OnDemand governor, the Interactive governor dynamically scales CPU clockspeed in response to the workload placed on the CPU by the user. This is where the similarities end. Interactive is significantly more responsive than OnDemand, because it's faster at scaling to maximum frequency.
Unlike OnDemand, which you'll recall scales clockspeed in the context of a work queue, Interactive scales the clockspeed over the course of a timer set arbitrarily by the kernel developer. In other words, if an application demands a ramp to maximum clockspeed (by placing 100% load on the CPU), a user can execute another task before the governor starts reducing CPU frequency. This can eliminate the frequency bouncing discussed in the OnDemand section. Because of this timer, Interactive is also better prepared to utilize intermediate clockspeeds that fall between the minimum and maximum CPU frequencies. This is another pro-battery life benefit of Interactive.
However, because Interactive is permitted to spend more time at maximum frequency than OnDemand (for device performance reasons), the battery-saving benefits discussed above are effectively negated. Long story short, Interactive offers better performance than OnDemand (some say the best performance of any governor) and negligibly different battery life.
Interactive also makes the assumption that a user turning the screen on will shortly be followed by the user interacting with some application on their device. Because of this, screen on triggers a ramp to maximum clockspeed, followed by the timer behavior described above.
9: InteractiveX Governor:
Created by kernel developer "Imoseyon," the InteractiveX governor is based heavily on the Interactive governor, enhanced with tuned timer parameters to better balance battery vs. performance. The InteractiveX governor's defining feature, however, is that it locks the CPU frequency to the user's lowest defined speed when the screen is off.
10: Smartass
Is based on the concept of the interactive governor.
I have always agreed that in theory the way interactive works – by taking over the idle loop – is very attractive. I have never managed to tweak it so it would behave decently in real life. Smartass is a complete rewrite of the code plus more. I think its a success. Performance is on par with the “old” minmax and I think smartass is a bit more responsive. Battery life is hard to quantify precisely but it does spend much more time at the lower frequencies.
Smartass will also cap the max frequency when sleeping to 352Mhz (or if your min frequency is higher than 352 – why?! – it will cap it to your min frequency). Lets take for example the 528/176 kernel, it will sleep at 352/176. No need for sleep profiles any more!"
11: SmartassV2:
Version 2 of the original smartass governor from Erasmux. Another favorite for many a people. The governor aim for an "ideal frequency", and ramp up more aggressively towards this freq and less aggressive after. It uses different ideal frequencies for screen on and screen off, namely awake_ideal_freq and sleep_ideal_freq. This governor scales down CPU very fast (to hit sleep_ideal_freq soon) while screen is off and scales up rapidly to awake_ideal_freq (500 mhz for GS2 by default) when screen is on. There's no upper limit for frequency while screen is off (unlike Smartass). So the entire frequency range is available for the governor to use during screen-on and screen-off state. The motto of this governor is a balance between performance and battery.
12: Scary
A new governor wrote based on conservative with some smartass features, it scales accordingly to conservatives laws. So it will start from the bottom, take a load sample, if it's above the upthreshold, ramp up only one speed at a time, and ramp down one at a time. It will automatically cap the off screen speeds to 245Mhz, and if your min freq is higher than 245mhz, it will reset the min to 120mhz while screen is off and restore it upon screen awakening, and still scale accordingly to conservatives laws. So it spends most of its time at lower frequencies. The goal of this is to get the best battery life with decent performance. It will give the same performance as conservative right now, it will get tweaked over time.
13: Lagfree:
Lagfree is similar to ondemand. Main difference is it's optimization to become more battery friendly. Frequency is gracefully decreased and increased, unlike ondemand which jumps to 100% too often. Lagfree does not skip any frequency step while scaling up or down. Remember that if there's a requirement for sudden burst of power, lagfree can not satisfy that since it has to raise cpu through each higher frequency step from current. Some users report that video playback using lagfree stutters a little.
14: Smoothass:
The same as the Smartass “governor” But MUCH more aggressive & across the board this one has a better battery life that is about a third better than stock KERNEL
15: Brazilianwax:
Similar to smartassV2. More aggressive ramping, so more performance, less battery
16: SavagedZen:
Another smartassV2 based governor. Achieves good balance between performance & battery as compared to brazilianwax.
17: Lazy:
This governor from Ezekeel is basically an ondemand with an additional parameter min_time_state to specify the minimum time CPU stays on a frequency before scaling up/down. The Idea here is to eliminate any instabilities caused by fast frequency switching by ondemand. Lazy governor polls more often than ondemand, but changes frequency only after completing min_time_state on a step overriding sampling interval. Lazy also has a screenoff_maxfreq parameter which when enabled will cause the governor to always select the maximum frequency while the screen is off.
18: Lionheart:
Lionheart is a conservative-based governor which is based on samsung's update3 source.
The tunables (such as the thresholds and sampling rate) were changed so the governor behaves more like the performance one, at the cost of battery as the scaling is very aggressive.
19: LionheartX
LionheartX is based on Lionheart but has a few changes on the tunables and features a suspend profile based on Smartass governor.
20: Intellidemand:
Intellidemand aka Intelligent Ondemand from Faux is yet another governor that's based on ondemand. Unlike what some users believe, this governor is not the replacement for OC Daemon (Having different governors for sleep and awake). The original intellidemand behaves differently according to GPU usage. When GPU is really busy (gaming, maps, benchmarking, etc) intellidemand behaves like ondemand. When GPU is 'idling' (or moderately busy), intellidemand limits max frequency to a step depending on frequencies available in your device/kernel for saving battery. This is called browsing mode. We can see some 'traces' of interactive governor here. Frequency scale-up decision is made based on idling time of CPU. Lower idling time (<20%) causes CPU to scale-up from current frequency. Frequency scale-down happens at steps=5% of max frequency. (This parameter is tunable only in conservative, among the popular governors)
To sum up, this is an intelligent ondemand that enters browsing mode to limit max frequency when GPU is idling, and (exits browsing mode) behaves like ondemand when GPU is busy; to deliver performance for gaming and such. Intellidemand does not jump to highest frequency when screen is off.
21: Hotplug Governor:
The Hotplug governor performs very similarly to the OnDemand governor, with the added benefit of being more precise about how it steps down through the kernel's frequency table as the governor measures the user's CPU load. However, the Hotplug governor's defining feature is its ability to turn unused CPU cores off during periods of low CPU utilization. This is known as "hotplugging."
22: BadAss Governor:
Badass removes all of this "fast peaking" to the max frequency. On a typical system the cpu won't go above 918Mhz and therefore stay cool and will use less power. To trigger a frequency increase, the system must run a bit @ 918Mhz with high load, then the frequency is bumped to 1188Mhz. If that is still not enough the governor gives you full throttle. (this transition should not take longer than 1-2 seconds, depending on the load your system is experiencing)
Badass will also take the gpu load into consideration. If the gpu is moderately busy it will bypass the above check and clock the cpu with 1188Mhz. If the gpu is crushed under load, badass will lift the restrictions to the cpu.
23: Wheatley:
Building on the classic 'ondemand' governor is implemented Wheatley governor. The governor has two additional parameters:
target_residency - The minimum average residency in µs which is considered acceptable for a proper efficient usage of the C4 state. Default is 10000 = 10ms.
allowed_misses - The number sampling intervals in a row the average residency is allowed to be lower than target_residency before the governor reduces the frequency. This ensures that the governor is not too aggressive in scaling down the frequency and reduces it just because some background process was temporarily causing a larger number of wakeups. The default is 5.
Wheatley works as planned and does not hinder the proper C4 usage for task where the C4 can be used properly .
For internet browsing the time spend in C4 has increased by 10% points and the average residency has increased by about 1ms. I guess these differences are mostly due to the different browsing behaviour (I spend the last time more multi-tabbing). But at least we can say that Wheatley does not interfere with the proper use of the C4 state during 'light' tasks. For music playback with screen off the time spend in C4 is practically unchanged, however the average residency is reduced from around 30ms to around 18ms, but this is still more than acceptable.
So the results show that Wheatley works as intended and ensures that the C4 state is used whenever the task allows a proper efficient usage of the C4 state. For more demanding tasks which cause a large number of wakeups and prevent the efficient usage of the C4 state, the governor resorts to the next best power saving mechanism and scales down the frequency. So with the new highly-flexible Wheatley governor one can have the best of both worlds.
Obviously, this governor is only available on multi-core devices.
24: Lulzactive:
Lulzactive:
This new find from Tegrak is based on Interactive & Smartass governors and is one of the favorites.
Old Version: When workload is greater than or equal to 60%, the governor scales up CPU to next higher step. When workload is less than 60%, governor scales down CPU to next lower step. When screen is off, frequency is locked to global scaling minimum frequency.
New Version: Three more user configurable parameters: inc_cpu_load, pump_up_step, pump_down_step. Unlike older version, this one gives more control for the user. We can set the threshold at which governor decides to scale up/down. We can also set number of frequency steps to be skipped while polling up and down.
When workload greater than or equal to inc_cpu_load, governor scales CPU pump_up_step steps up. When workload is less than inc_cpu_load, governor scales CPU down pump_down_step steps down.
Example:
Consider
inc_cpu_load=70
pump_up_step=2
pump_down_step=1
If current frequency=200, Every up_sampling_time Us if cpu load >= 70%, cpu is scaled up 2 steps - to 800.
If current frequency =1200, Every down_sampling_time Us if cpu load < 70%, cpu is scaled down 1 step - to 1000.
25: Pegasusq/Pegasusd
The Pegasus-q / d is a multi-core based on the Ondemand governor and governor with integrated hot-plugging.
Ongoing processes in the queue, we know that multiple processes can run simultaneously on. These processes are active in an array, which is a field called "Run Queue" queue that is ongoing, with their priority values ​​arranged (priority will be used by the task scheduler, which then decides which process to run next).
To ensure that each process has its fair share of resources, each running for a certain period and will eventually stop and then again placed in the queue until it is your turn again. If a program is terminated, so that others can run the program with the highest priority in the current queue is executed.
26: hotplugx
It 'a Hotplug modified and optimized for the suspension in off-screen
27: AbissPlug
It 'a Governor derived hotplug, it works the same way, but with the changes in savings for a better battery.
28: MSM DCVS
a very efficient and wide range of Dynamic Clock and
Voltage Scaling (DCVS) which addresses usage models from
active standby to mid and high level processing requirements.
A Krait CPU can smoothly scale from low power, low
leakage mode to blazingly fast performance.
Believe it's a governor that is mfg'd by qualcomm to utilize new on chip features.
MSM is the prefix for the SOC (MSM8960) and DCVS is Dynamic Clock and Voltage Scaling. Makes sense, MSM-DCVS
29: IntelliActive
Based off Google's Interactive governor with the following enhancements:
1. self-boost capability from input drivers (no need for PowerHAL assist)
2. two phase scheduling (idle/busy phases to prevent from jumping directly to max freq
3. Checks for offline cpus and short circuits some unnecessary checks to improve code execution paths
30: Adaptive
This driver adds a dynamic cpufreq policy governor
designed for latency-sensitive workloads and also for demanding
performance.
This governor attempts to reduce the latency of clock
increases so that the system is more responsive to
interactive workloads in loweset steady-state but to
to reduce power consumption in middle operation level level up
will be done in step by step to prohibit system from going to
max operation level.
31: Nightmare
A PegasusQ modified, less aggressive and more stable. A good compromise between performance and battery.
In addition to the SoD is a prevention because it usually does not hotplug.
32: ZZmove
ZZmove Governor optimized for low power consumption with the screen off, with particular attention to the limitation of consumption applications in the background with the screen off, such as listening to music. It has three settings: battery saver, balanced and performance. In addition to a performance boost, there is also the governor zzmove optimized.
I/O Scheduler: Thread:I/O Scheduler explained
The Scheduler is an algorithm that, given a set of requests for access to a resource, establishing a temporal order for the execution of such requests, favoring those that meet certain criteria in order to optimize access to that resource.
The difference between the various scheduler is the focus on certain criteria rather than on others.
The choice of a given scheduler does not produce visible changes so as to the choice of the governor, but still provides some improvements.
As usual schedulers are personally tested to find one that best suits your needs.
Deadline
It aims to provide a deadline, a deadline for all requests in order to avoid undesirable phenomena such as the "starvation" or the eternal waiting for some requests that occurs when one or more background processes are left indefinitely in the queue the ready, because there is always at least one of the highest priority ready process.
V (r)
The next request is performed according to the distance from the last request. In the network running good opinions about this scheduler.
No-op
Push all requests in a single queue simply by their arrival order, grouping together those contiguous.
SIO
E 'the scheduler simpler, does not make any type of sort, is intended only for the purpose of obtaining a low-latency, ie to reduce the amount of time that elapses between the instant at which the request is generated and that in which the request is satisfied.
CFQ
Order requests of different processes in queues for each queue type and assigns a specific interval of time whose duration depends on the priorities assigned to processes. Can be considered the Ondemand the scheduler, the scheduler is in fact more balanced, doing its job in an honest manner.
BFQ
It 's based on CFQ but, instead of the intervals of time, assigns a part of the bandwidth of the disc to each process running in a proportional manner.
Anticipatory
Order requests based on criteria predictive, that puts the demands paused for a short period of time in anticipation that more of this to come to aggregate them.
ADAPTIVE ANTICIPATORY SCHEDULER
For the anticipatory scheduler, we scale up the anticipation timeout (antic expire) using the latency scaling factor over time. When the virtual disk latencies are low a small scaling of the timeout is sucient to prevent deceptive idleness, whereas when the latencies are high a larger scaling of the timeout value may be required to achieve the same. Note that such dynamic setting of the timeout value ensures that we attain a good trade-o between throughput (lost due to idling) and deceptive idleness mitigation. Setting a high value for the scaling factor (increasing idling time) only happens when the disk service latencies themselves are higher. This may not necessarily cause a signicant loss in throughput, because submitting a request from another process instead of idling is not going to improve throughput if the virtual disk itself does not get any faster than it is at the current period. A higher anticipation timeout might also be capable of absorbing process scheduling eects inside the VM. The results for the adaptive anticipatory scheduler are shown in Figure 2. The read time with our modied implementation (third bar in the dierent scheduler combinations) shows that it is possible to mitigate the eects of deceptive idleness by adapting the timeout. An interesting related observation is that the level to which the improve- ment is possible varies for dierent Domain-0 schedulers; noop - 39%, anticipatory - 67% and cfq - 36%. This again points to the fact that the I/O scheduler used in Domain-0 is important for the VM's ability in enforcing I/O scheduling guarantees. Dierent Domain-0 I/O schedulers likely have a dierent service latency footprint inside the VMs, contributing to dierent levels of improvement.
ROW
Row stands for READ Over WRITE which is the main requests dispatch policy of this algorithm. The ROW IO scheduler was developed with the mobile devices needs in mind. In mobile devices we favor user experience upon everything else, thus we want to give READ IO requests as much priority as possible. In mobile devices we won't have as much parallel threads as on desktops. Usually it's a single thread or at most 2 simultaneous working threads for read & write. Favoring READ requests over WRITEs decreases the READ latency greatly.
The main idea of the ROW scheduling policy is: If there are READ requests in pipe - dispatch them but don't starve the WRITE requests too much. Bellow you'll find a small comparison of ROW to existing schedulers. The test that was run for these measurements is parallel read and write.
FIOS
Flash-based solid-state drives (SSDs) have the potential to eliminate the I/O bottlenecks in data-intensive applications However the large performance discrepancy between Flash reads and writes introduces challenges for fair resource usage. Further, existing fair queuing and quanta-based I/O schedulers poorly manage the I/O anticipation for Flash I/O fairness and efficiency. Some also suppress the I/O parallelism which causes substantial performance degradation on Flash. This paper develops FIOS, a new Flash I/O scheduler that attains fairness and high efficiency at the same time. FIOS employs a fair I/O time-slice management with mechanisms for read preference, parallelism, and fairness-oriented I/O anticipation. Evaluation demonstrates that FIOS achieves substantially better fairness and efficiency compared to the Linux CFQ scheduler, the SFQ(D) fair queuing scheduler, and the Argon quanta-based scheduler on several Flash-based storage devices (including a CompactFlash card in a low-power wimpy node). In particular, FIOS reduces the worst-case slowdown bya factor of 2.3 or more when the read-only SPECweb workload runs together with the write-intensive TPC

Sweet! In terms of battery life, did it improve for you? You made one of the best TW roms and now this great job!

DUHAsianSKILLZ said:
Sweet! In terms of battery life, did it improve for you? You made one of the best TW roms and now this great job!
Click to expand...
Click to collapse
Thank you! I think we have less devs here in Tab S section, so I have to do something here
I couldn't test the batterylife till now, I was testing whole 2 weeks to get the kernel working (got holidays) So I will report you back!
Intelli-Plug speeks for better batterylife, it shuts down 3 cores if they are not needed (screen off = only 1 core working with 200Mhz or something)

Tkkg1994 said:
Thank you! I think we have less devs here in Tab S section, so I have to do something here
I couldn't test the batterylife till now, I was testing whole 2 weeks to get the kernel working (got holidays) So I will report you back!
Intelli-Plug speeks for better batterylife, it shuts down 3 cores if they are not needed (screen off = only 1 core working with 200Mhz or something)
Click to expand...
Click to collapse
Thanks! Ill downgrade tommrow or so back to kitkat and try xnote rom. I can try your kernel when I do that.

DUHAsianSKILLZ said:
Thanks! Ill downgrade tommrow or so back to kitkat and try xnote rom. I can try your kernel when I do that.
Click to expand...
Click to collapse
Always a pleasure to have you as a user!
Not the ironrom

Wrong thread

Mokum020 said:
Thank you for your great work (again)!
Your kernel is running perfect here on T805 with X-Note.
would love to be able to try 2.1/2.2Ghz, 2.1Ghz is no problem for my Tab S with SkyHigh.
View attachment 3174370View attachment 3174371
Click to expand...
Click to collapse
I always make kind of a "stresstest" for the CPU freq. I set min freq to 2.1GHz and max freq to 2.1GHz. Than see what happen. I couldn't get it stable enough for daily use, but if I can, I will enable 2.1GHz for sure

Confirmed working on the T800 with xnote rom.

DUHAsianSKILLZ said:
Confirmed working on the T800 with xnote rom.
Click to expand...
Click to collapse
Thank you for testing
I added a description of governors and I/O schedulers above

To install this with Ironrom, should I do anything with Synapse first to either return settings to default or uninstall? Or should I reflash IronRom, leaving out Synapse in Aroma and then flash the new kernel? I plan on trying Kernel Auditor.
Also, will you be adding this kernel to the aroma options soon (or are you waiting for more testing to come in)?

Hookmt said:
To install this with Ironrom, should I do anything with Synapse first to either return settings to default or uninstall? Or should I reflash IronRom, leaving out Synapse in Aroma and then flash the new kernel? I plan on trying Kernel Auditor.
Also, will you be adding this kernel to the aroma options soon (or are you waiting for more testing to come in)?
Click to expand...
Click to collapse
The kernel doesn' support synapse. You can just uninstall it if you like to and than install your kernel auditor.
Yes it will come to aroma soon, I'm waiting for samsung to release a new base for T800
And yes, testing is always welcome

Can you include some tips for let's say performance settings, battery settings, both battery and performance settings etc. I'm still testing a few things too, but can't figure out the best battery settings in faux.

DUHAsianSKILLZ said:
Can you include some tips for let's say performance settings, battery settings, both battery and performance settings etc. I'm still testing a few things too, but can't figure out the best battery settings in faux.
Click to expand...
Click to collapse
Intelli-plug, KSM enabled, Governor... I would say intellimm is good for battery but a bit slow. Interactive with intelliplug is nice

With Stweaks Support does the Kernel support BLN (blinking Soft Keys)? God, this would be awesome!!
If not, could you create a Custom Kernel with this Feature?

haselchen said:
With Stweaks Support does the Kernel support BLN (blinking Soft Keys)? God, this would be awesome!!
If not, could you create a Custom Kernel with this Feature?
Click to expand...
Click to collapse
If you would have read correctly, you will see that I'm currently adding sTweaks support. And it don't supports it now, but seems like a good idea!

Please realize this idea

Tkkg1994, this is what I call a very promising start.
Detailed walkthrough, FAQ style, and a very interesting feature rich kernel... I'm on CM12 right now, but already eager to try this in the coming days with IronRom, of course.
A Big Thanks from the other side of the world... Porto, Portugal.

Tkkg1994 said:
Intelli-plug, KSM enabled, Governor... I would say intellimm is good for battery but a bit slow. Interactive with intelliplug is nice
Click to expand...
Click to collapse
IntellIplug is nice but sometimes you cant turn the tablet on when it's enabled. I even set the screen off frequency to something above 200mhz. I had to force reboot a couple times. Did you managed to get it work? I even tryed all the profiles including balanced etc and also changing the governer. For now I'll keep it off but battery seems good so far!

[KERNEL][TW/LP][13.10.15][SM-T700][SM-T705] IronKernel V2.5 STweaks

Hey guys, I'm back with a new KERNEL for both Variants of the Tab S 8.4 (T700 and T705)!
Some guys probably know me from the IronRom . I decided myselfe to create a custom kernel for our really great Tab s 8.4, I'm getting better and better at this stuff, I don't thought that
It is basically the normal kernel with some modifications for better performance and hopefully also batterylife. It is for the stock kitkat (4.4.2) touchwiz and not for cyanogenmod or something else.
I excuse all devs here visiting my github page, it is such a mess (with the commits)! I know it, but I'm doing this the first time, so hopefully you will forgive me.
The kernel is pretty stable, I just call it a beta version, because I can't test the T700 and T705 version, so if with thisone also all works great -> stable
IF YOU FOLLOW MY STEPS BELOW, YOU WILL MAY LOSE YOUR WARRANTY, KNOX WILL DISPLAY 0x1! I'M NOT RESPONSIBLE FOR ANY DAMAGED DEVICE!
You can try to use the kernel adiutor app, or just the preinstalled sTweaks, but not both at the same time! This will cause problems.
Features of my Kernel::​- Built with latest Linaro Toolchain 4.9.3 made by christopher83
- Latest Kernel version 3.4.109, includes all important linux patches, patched it form 3.4.39 up to 3.4.109 (was a lot of work)
- Choose between different CPU governors: Interactive (default), Powersave, Performance, Userspace, Conservative, Intellidemand, Intelliactive, Ondemand, Adaptive, Abyssplug, AbyssplugV2, Badass, DanceDance, ZZmove, Nightmare, Wheatley, Lionheart, Darkness, PegasusQ and Intellimm
- Built with latest ramdisk sources from samsung
- Kernelsource from T805XXU1BOG2
- Underclock to 200MHz and Overclock to 2.0GHz
- GPU works from 100MHz to 733MHz (default)
- I/O schedulers: ROW (Default), CFQ, No-op, Deadline, Test, BFQ, FIOPS, SIO, VR, ZEN, FIFO and SIOplus
- Readahead can be set
- KSM (Kernel Samepage Merging)
- Gentlefairsleeper and ARCH power
- Android Logger
- Init.d Support
- data and cache f2fs support!
- Busybox support
- Full STweaks support
- Charging Control
- Cpufreq voltcontrol
- ZRam and Swap
- Allow ADB-Insecure
- Low Memory Kill
- TCP (Network) control: Cubic (default), Reno, Bic, Westwood, Highspeed, Hybla, HTCP, Vegas, Veno, Scalable, LP, Yeah and Illinois
- SeLinux is set to permissive
- Compiled as small as it could be (just around 6MB)
Download:​In the second post
Googy-Max STweaks​
Bugs/Problems:​-sTweaks can't enable the right GPU over and underclock freqency
-Some other stweaks stuff, you will see
-Didn't tried the voltage table​
Instructions:​
If you want to install the Kernel, follow this:
1. Install a custom recovery for your tablet, like this one here: TWRP Recovery
2. Follow the instructions on the page above, until you get a working recovery
3. Download the Kernel from below and copy it to your external SD Card
4. Reboot to your recovery by pressing volume up, home button and power button at the same time.
5. Install zip, and select the kernel
6. Wipe cache and dalvik cache (recommand)
7. Reboot
Support:​If you like my work, please hit a thanks down on my posts. A thanks is enough!:highfive: If you really really really really really like my work, you can donate something to me, but it is not necessary. I created a paypal account, just in case, someone would give me a small donation. :good:
As I said, you don't have to give me something, but this keeps me motivated to built better roms and keep updating everything. It's your choice, and I'm very thankfull for every donation! No matter how big it is! Thank you so much for supporting me, cheers and have a nice day :fingers-crossed:​
Donators for the Kernel:​
Credits/Thanks:​- Samsung for sources
- @Christopher83 for the compiler
- @UpInTheAir for the work he already did in his own kernel (could use some of his commits on github (opensource) and see what he did when I didn't know what I did wrong). He also inspired me to work on my own stuff and kernel, thank you very much!
- @googy_anas, without him, I would not have a working kernel here, he did so much for me and also for his own kernel! He
let me use everything he already did, I got so much stuff from his page and included it in my kernel. I'm so thankfull for all the support he gave to me! I know a thank you isn't enough, but I wanted to write it here.
- @googy_anas (again ) and @kryten2k35 for the great stweaks app and that I can use your modification in the app (I don't edited it) Thank you so much!
- @faux123 for all the great stuff he did for the kernels
- @Yank555
- @AndreiLux
- @Halaszk87
If you want to take my work and need it somewhere, or do other things with it, please ask me first for the permission. Otherwise you are not allowed to take it! Thank you !
XDA:DevDB Information
Stock Based Kernel for Tab S 8.4, Kernel for the Samsung Galaxy Tab S
Contributors
Tkkg1994, @googy_anas
Source Code: https://github.com/Tkkg1994/IronKernel
Kernel Special Features:
Version Information
Status: Stable
Current Stable Version: V2.5
Stable Release Date: 2015-10-13
Current Beta Version: 1.0
Beta Release Date: 2015-02-20
Created 2015-02-20
Last Updated 2015-10-12

Changelog:
Kitkat
Ironkernel Beta V1.0 20.02.2015:
- Initial Release!
Ironkernel V1.1 26.02.2015:
-Temporarly removed Intelli-Plug
-Added voltcontroll for CPU
-Added Stweaks support and Stweaks app (all credits and stuff goes to @googy_anas and @Kryten2k35
-Hell lot of improvements
-Init.d support and busybox support
-GPU overclock to 733MHz
-CPU overclock to 2.1GHz (sorry, I couldn't get it stable )
-Fast charge control
-for more what I had done, visit here: Commits IronKernel
IronKernel V1.2 01.03.2015:
- Built with latest toolchain (2015.02) by christopher83
- Use frandom from now
- Enable dynamic page writeback with earlysuspend
- Better battery charging control (kernel and stweaks)
- Auto install the right sTweaks version
- Reduce overestimating rq->avg_idle
- Optimize find_busiest_queue()
- Some CPUfreq optimizations
- Dynamic sync control with earlysuspend support
- Lowmemorykiller: implement task's adj rbtree
- Check free memory when tasks switch to background
- Dynamic FSync
- SOO Much more but I don't remember all
- After flashing the kernel, it will be successfull, but then show an error (becaus of mounting partition) don't worry, just reboot. Just ignore it
Changelog V1.3.5 08.03.15:
- Prerelease of V1.3 was on the ironrom
- Script auto-removes all knox containors/apps
- cpufreq: Retain only online cpus in managed_policy->cpus
- cpufreq: make the "scaling_cur_freq" sysfs entry pollable
- cpufreq: Make the "scaling_governor" sysfs node pollable
- cpufreq: Save and restore min and max frequencies
- fix some missing stuff with default governor
- cpufreq: Notify governors when cpus are hot-[un]plugged
- Updated nightmare and zzmoove governors
- net: ipv6: Add a sysctl to make optimistic addresses useful candidates
- fs/proc/task_mmu.c: add user-space support for resetting mm
- net: ipv6: allow choosing optimistic addresses with use_optimistic
- sched/idle: Avoid spurious wakeup IPIs
- cpufreq: Return directly in __cpufreq_get if policy is NULL
- new relation between governors
- ARM: 8226/1: cacheflush: get rid of restarting block
Changelog V1.4 23.03.15:
- It is simply to much to write everything here.. what I did
- Wolfson Control for the sound on our Tab S
- Added voltage control (doesen't work 100%)
- sched: Add an rq migration call-back to sched_class
- sched: Account for blocked load waking back up …
- sched: Normalize tg load contributions against runnable time
- sched: Refactor update_shares_cpu() -> update_blocked_avgs()
- sched/fair: Set se->vruntime directly in place_entity()
- sched: provide per cpu-cgroup option to notify on migrations
- sched: Make sure to not re-read variables after validation
- sched: Add WAKEUP_PREEMPTION feature flag, on by default
And this goes on for like 2 or 3 pages lol So the changelog is tooooooo long.
Lollipop
Changelog V2.0 08.07.15:
- @Richcar confirmed that it works (trust him )
- updated to linux 3.4.108 mainstream
- f2fs update
- add tripndroid scheduler
- add row scheduler
- add and enable UKSM (ultra kernel samepage merging)
- update ramdisk to latest versions
- more things I may forgot
- ONLY for touchwiz lollipop! You MUST have a EO3 base or higher (your rom)
Changelog V2.0.5 16.07.15:
- Fixed "slow" charging (Thanks to AndreiLux and UpInTheAir!)
- Incrased sound so it will be a louder by default
- Some other small ramdisk fixes
- Update to OF1 and OF2 ramdisk
- You have to be on latest samsung based roms (as OEx or OFx) otherwise not booting!
Changelog V2.5 13.10.15:
- Merged latest OG2 source, adapted by OE9 source from T705, fully rebased kernel!
- Update to 5.2 toolchain compiled by myself!
- this kernel is now up-to-date with T800/T805 kernel!
- updated to 3.4.109 linux
- ftrace: Make all inline tags also include notrace
- compiler-gcc4.h: correct verion check for __compiletime_error
- compiler.h: add __visible
- compiler{,-gcc4}.h, bug.h: Remove duplicate macros
- some more optimisations concerning compiler
- msm: cpufreq: Only apply driver limits for scaling_min/max_freq writes
- drivers: cpufreq: Send a uevent when governor changes
- cpufreq: Save user policy min/max instead of policy min/max during hotplug
- cpufreq: Fix broken uevents for cpufreq governor and cpu devices
- cpufreq: Always allow update of user policy
- drivers: cpufreq: Upstream optimizations
- cpufreq: Export user_policy min/max
- cpufreq: Add policy notifiers
- cpufreq: Simplify cpufreq_add_dev()
- some more cpufreq things that I made
- cpufreq_stats: do not remove sysfs files if frequency table is not present
- sched/numa: Rewrite the CONFIG_NUMA sched domain support
- sched/numa: Fix the new NUMA topology bits
- sched/numa: Don't scale the imbalance
- sched/debug: Fix printing large integers on 32-bit platforms
- sched: Remove stale power aware scheduling remnants and dysfunctional knobs
- f2fs: update to latest version
- uksm: disabled by default
- fixed some Random reboots people had
- added pegasusq cpugovernor
- arm/crypto: Add optimized AES and SHA1 routines
- added cifs, nfs, exportfs, cdrom, all ramdisk support (joystick too)
- ARM: 7626/1: arm/crypto: Make asm SHA-1 and AES code Thumb-2 compatible
- ARM: 7723/1: crypto: sha1-armv4-large.S: fix SP handling
- ARM: 8119/1: crypto: sha1: add ARM NEON implementation
- ARM: 8120/1: crypto: sha512: add ARM NEON implementation
- a lot of other crypto optimisations (like 10 patches)
- cpufreq: Move get_cpu_idle_time() to cpufreq.c
- workqueue: set delayed_work->timer function on initialization
- workqueue: don't use WQ_HIGHPRI for unbound workqueues
- workqueue: factor out worker_pool from global_cwq
- workqueue: use @pool instead of @gcwq or @Cpu where applicable
- workqueue: separate out worker_pool flags
- workqueue: introduce NR_WORKER_POOLS and for_each_worker_pool()
- workqueue: reimplement WQ_HIGHPRI using a separate worker_pool
- hashtable: introduce a small and naive hashtable
- workqueue: use new hashtable implementation
- workqueue: drop @bind from create_worker()
- much more workqueue updates, to see them all, please visit here: Github Kernel Updates

Governors and I/O Scheduler:
Original Thread: Governor Explained, all credits go to @stempox
1: OnDemand
2: OndemandX
3: Performance
4: Powersave
5: Conservative
6: Userspace
7: Min Max
8: Interactive
9: InteractiveX
10: Smartass
11: SmartassV2
12: Scary
13: Lagfree
14: Smoothass
15: Brazilianwax
16: SavagedZen
17: Lazy
18: Lionheart
19: LionheartX
20: Intellidemand
21: Hotplug
22: BadAss
23: Wheatley
24: Lulzactive
25: Pegasusq/Pegasusd
26: hotplugx
27: AbissPlug
28: MSM DCVS
29: IntelliActive
30: Adaptive
31: Nightmare
32: ZZmove
1: OnDemand Governor:
This governor has a hair trigger for boosting clockspeed to the maximum speed set by the user. If the CPU load placed by the user abates, the OnDemand governor will slowly step back down through the kernel's frequency steppings until it settles at the lowest possible frequency, or the user executes another task to demand a ramp.
OnDemand has excellent interface fluidity because of its high-frequency bias, but it can also have a relatively negative effect on battery life versus other governors. OnDemand is commonly chosen by smartphone manufacturers because it is well-tested, reliable, and virtually guarantees the smoothest possible performance for the phone. This is so because users are vastly more likely to ***** about performance than they are the few hours of extra battery life another governor could have granted them.
This final fact is important to know before you read about the Interactive governor: OnDemand scales its clockspeed in a work queue context. In other words, once the task that triggered the clockspeed ramp is finished, OnDemand will attempt to move the clockspeed back to minimum. If the user executes another task that triggers OnDemand's ramp, the clockspeed will bounce from minimum to maximum. This can happen especially frequently if the user is multi-tasking. This, too, has negative implications for battery life.
2: OndemandX:
Basically an ondemand with suspend/wake profiles. This governor is supposed to be a battery friendly ondemand. When screen is off, max frequency is capped at 500 mhz. Even though ondemand is the default governor in many kernel and is considered safe/stable, the support for ondemand/ondemandX depends on CPU capability to do fast frequency switching which are very low latency frequency transitions. I have read somewhere that the performance of ondemand/ondemandx were significantly varying for different i/o schedulers. This is not true for most of the other governors. I personally feel ondemand/ondemandx goes best with SIO I/O scheduler.
3: Performance Governor:
This locks the phone's CPU at maximum frequency. While this may sound like an ugly idea, there is growing evidence to suggest that running a phone at its maximum frequency at all times will allow a faster race-to-idle. Race-to-idle is the process by which a phone completes a given task, such as syncing email, and returns the CPU to the extremely efficient low-power state. This still requires extensive testing, and a kernel that properly implements a given CPU's C-states (low power states).
4: Powersave Governor:
The opposite of the Performance governor, the Powersave governor locks the CPU frequency at the lowest frequency set by the user.
5:Conservative Governor:
This biases the phone to prefer the lowest possible clockspeed as often as possible. In other words, a larger and more persistent load must be placed on the CPU before the conservative governor will be prompted to raise the CPU clockspeed. Depending on how the developer has implemented this governor, and the minimum clockspeed chosen by the user, the conservative governor can introduce choppy performance. On the other hand, it can be good for battery life.
The Conservative Governor is also frequently described as a "slow OnDemand," if that helps to give you a more complete picture of its functionality.
6: Userspace Governor:
This governor, exceptionally rare for the world of mobile devices, allows any program executed by the user to set the CPU's operating frequency. This governor is more common amongst servers or desktop PCs where an application (like a power profile app) needs privileges to set the CPU clockspeed.
7: Min Max
well this governor makes use of only min & maximum frequency based on workload... no intermediate frequencies are used.
8: Interactive Governor:
Much like the OnDemand governor, the Interactive governor dynamically scales CPU clockspeed in response to the workload placed on the CPU by the user. This is where the similarities end. Interactive is significantly more responsive than OnDemand, because it's faster at scaling to maximum frequency.
Unlike OnDemand, which you'll recall scales clockspeed in the context of a work queue, Interactive scales the clockspeed over the course of a timer set arbitrarily by the kernel developer. In other words, if an application demands a ramp to maximum clockspeed (by placing 100% load on the CPU), a user can execute another task before the governor starts reducing CPU frequency. This can eliminate the frequency bouncing discussed in the OnDemand section. Because of this timer, Interactive is also better prepared to utilize intermediate clockspeeds that fall between the minimum and maximum CPU frequencies. This is another pro-battery life benefit of Interactive.
However, because Interactive is permitted to spend more time at maximum frequency than OnDemand (for device performance reasons), the battery-saving benefits discussed above are effectively negated. Long story short, Interactive offers better performance than OnDemand (some say the best performance of any governor) and negligibly different battery life.
Interactive also makes the assumption that a user turning the screen on will shortly be followed by the user interacting with some application on their device. Because of this, screen on triggers a ramp to maximum clockspeed, followed by the timer behavior described above.
9: InteractiveX Governor:
Created by kernel developer "Imoseyon," the InteractiveX governor is based heavily on the Interactive governor, enhanced with tuned timer parameters to better balance battery vs. performance. The InteractiveX governor's defining feature, however, is that it locks the CPU frequency to the user's lowest defined speed when the screen is off.
10: Smartass
Is based on the concept of the interactive governor.
I have always agreed that in theory the way interactive works – by taking over the idle loop – is very attractive. I have never managed to tweak it so it would behave decently in real life. Smartass is a complete rewrite of the code plus more. I think its a success. Performance is on par with the “old” minmax and I think smartass is a bit more responsive. Battery life is hard to quantify precisely but it does spend much more time at the lower frequencies.
Smartass will also cap the max frequency when sleeping to 352Mhz (or if your min frequency is higher than 352 – why?! – it will cap it to your min frequency). Lets take for example the 528/176 kernel, it will sleep at 352/176. No need for sleep profiles any more!"
11: SmartassV2:
Version 2 of the original smartass governor from Erasmux. Another favorite for many a people. The governor aim for an "ideal frequency", and ramp up more aggressively towards this freq and less aggressive after. It uses different ideal frequencies for screen on and screen off, namely awake_ideal_freq and sleep_ideal_freq. This governor scales down CPU very fast (to hit sleep_ideal_freq soon) while screen is off and scales up rapidly to awake_ideal_freq (500 mhz for GS2 by default) when screen is on. There's no upper limit for frequency while screen is off (unlike Smartass). So the entire frequency range is available for the governor to use during screen-on and screen-off state. The motto of this governor is a balance between performance and battery.
12: Scary
A new governor wrote based on conservative with some smartass features, it scales accordingly to conservatives laws. So it will start from the bottom, take a load sample, if it's above the upthreshold, ramp up only one speed at a time, and ramp down one at a time. It will automatically cap the off screen speeds to 245Mhz, and if your min freq is higher than 245mhz, it will reset the min to 120mhz while screen is off and restore it upon screen awakening, and still scale accordingly to conservatives laws. So it spends most of its time at lower frequencies. The goal of this is to get the best battery life with decent performance. It will give the same performance as conservative right now, it will get tweaked over time.
13: Lagfree:
Lagfree is similar to ondemand. Main difference is it's optimization to become more battery friendly. Frequency is gracefully decreased and increased, unlike ondemand which jumps to 100% too often. Lagfree does not skip any frequency step while scaling up or down. Remember that if there's a requirement for sudden burst of power, lagfree can not satisfy that since it has to raise cpu through each higher frequency step from current. Some users report that video playback using lagfree stutters a little.
14: Smoothass:
The same as the Smartass “governor” But MUCH more aggressive & across the board this one has a better battery life that is about a third better than stock KERNEL
15: Brazilianwax:
Similar to smartassV2. More aggressive ramping, so more performance, less battery
16: SavagedZen:
Another smartassV2 based governor. Achieves good balance between performance & battery as compared to brazilianwax.
17: Lazy:
This governor from Ezekeel is basically an ondemand with an additional parameter min_time_state to specify the minimum time CPU stays on a frequency before scaling up/down. The Idea here is to eliminate any instabilities caused by fast frequency switching by ondemand. Lazy governor polls more often than ondemand, but changes frequency only after completing min_time_state on a step overriding sampling interval. Lazy also has a screenoff_maxfreq parameter which when enabled will cause the governor to always select the maximum frequency while the screen is off.
18: Lionheart:
Lionheart is a conservative-based governor which is based on samsung's update3 source.
The tunables (such as the thresholds and sampling rate) were changed so the governor behaves more like the performance one, at the cost of battery as the scaling is very aggressive.
19: LionheartX
LionheartX is based on Lionheart but has a few changes on the tunables and features a suspend profile based on Smartass governor.
20: Intellidemand:
Intellidemand aka Intelligent Ondemand from Faux is yet another governor that's based on ondemand. Unlike what some users believe, this governor is not the replacement for OC Daemon (Having different governors for sleep and awake). The original intellidemand behaves differently according to GPU usage. When GPU is really busy (gaming, maps, benchmarking, etc) intellidemand behaves like ondemand. When GPU is 'idling' (or moderately busy), intellidemand limits max frequency to a step depending on frequencies available in your device/kernel for saving battery. This is called browsing mode. We can see some 'traces' of interactive governor here. Frequency scale-up decision is made based on idling time of CPU. Lower idling time (<20%) causes CPU to scale-up from current frequency. Frequency scale-down happens at steps=5% of max frequency. (This parameter is tunable only in conservative, among the popular governors)
To sum up, this is an intelligent ondemand that enters browsing mode to limit max frequency when GPU is idling, and (exits browsing mode) behaves like ondemand when GPU is busy; to deliver performance for gaming and such. Intellidemand does not jump to highest frequency when screen is off.
21: Hotplug Governor:
The Hotplug governor performs very similarly to the OnDemand governor, with the added benefit of being more precise about how it steps down through the kernel's frequency table as the governor measures the user's CPU load. However, the Hotplug governor's defining feature is its ability to turn unused CPU cores off during periods of low CPU utilization. This is known as "hotplugging."
22: BadAss Governor:
Badass removes all of this "fast peaking" to the max frequency. On a typical system the cpu won't go above 918Mhz and therefore stay cool and will use less power. To trigger a frequency increase, the system must run a bit @ 918Mhz with high load, then the frequency is bumped to 1188Mhz. If that is still not enough the governor gives you full throttle. (this transition should not take longer than 1-2 seconds, depending on the load your system is experiencing)
Badass will also take the gpu load into consideration. If the gpu is moderately busy it will bypass the above check and clock the cpu with 1188Mhz. If the gpu is crushed under load, badass will lift the restrictions to the cpu.
23: Wheatley:
Building on the classic 'ondemand' governor is implemented Wheatley governor. The governor has two additional parameters:
target_residency - The minimum average residency in µs which is considered acceptable for a proper efficient usage of the C4 state. Default is 10000 = 10ms.
allowed_misses - The number sampling intervals in a row the average residency is allowed to be lower than target_residency before the governor reduces the frequency. This ensures that the governor is not too aggressive in scaling down the frequency and reduces it just because some background process was temporarily causing a larger number of wakeups. The default is 5.
Wheatley works as planned and does not hinder the proper C4 usage for task where the C4 can be used properly .
For internet browsing the time spend in C4 has increased by 10% points and the average residency has increased by about 1ms. I guess these differences are mostly due to the different browsing behaviour (I spend the last time more multi-tabbing). But at least we can say that Wheatley does not interfere with the proper use of the C4 state during 'light' tasks. For music playback with screen off the time spend in C4 is practically unchanged, however the average residency is reduced from around 30ms to around 18ms, but this is still more than acceptable.
So the results show that Wheatley works as intended and ensures that the C4 state is used whenever the task allows a proper efficient usage of the C4 state. For more demanding tasks which cause a large number of wakeups and prevent the efficient usage of the C4 state, the governor resorts to the next best power saving mechanism and scales down the frequency. So with the new highly-flexible Wheatley governor one can have the best of both worlds.
Obviously, this governor is only available on multi-core devices.
24: Lulzactive:
Lulzactive:
This new find from Tegrak is based on Interactive & Smartass governors and is one of the favorites.
Old Version: When workload is greater than or equal to 60%, the governor scales up CPU to next higher step. When workload is less than 60%, governor scales down CPU to next lower step. When screen is off, frequency is locked to global scaling minimum frequency.
New Version: Three more user configurable parameters: inc_cpu_load, pump_up_step, pump_down_step. Unlike older version, this one gives more control for the user. We can set the threshold at which governor decides to scale up/down. We can also set number of frequency steps to be skipped while polling up and down.
When workload greater than or equal to inc_cpu_load, governor scales CPU pump_up_step steps up. When workload is less than inc_cpu_load, governor scales CPU down pump_down_step steps down.
Example:
Consider
inc_cpu_load=70
pump_up_step=2
pump_down_step=1
If current frequency=200, Every up_sampling_time Us if cpu load >= 70%, cpu is scaled up 2 steps - to 800.
If current frequency =1200, Every down_sampling_time Us if cpu load < 70%, cpu is scaled down 1 step - to 1000.
25: Pegasusq/Pegasusd
The Pegasus-q / d is a multi-core based on the Ondemand governor and governor with integrated hot-plugging.
Ongoing processes in the queue, we know that multiple processes can run simultaneously on. These processes are active in an array, which is a field called "Run Queue" queue that is ongoing, with their priority values ​​arranged (priority will be used by the task scheduler, which then decides which process to run next).
To ensure that each process has its fair share of resources, each running for a certain period and will eventually stop and then again placed in the queue until it is your turn again. If a program is terminated, so that others can run the program with the highest priority in the current queue is executed.
26: hotplugx
It 'a Hotplug modified and optimized for the suspension in off-screen
27: AbissPlug
It 'a Governor derived hotplug, it works the same way, but with the changes in savings for a better battery.
28: MSM DCVS
a very efficient and wide range of Dynamic Clock and
Voltage Scaling (DCVS) which addresses usage models from
active standby to mid and high level processing requirements.
A Krait CPU can smoothly scale from low power, low
leakage mode to blazingly fast performance.
Believe it's a governor that is mfg'd by qualcomm to utilize new on chip features.
MSM is the prefix for the SOC (MSM8960) and DCVS is Dynamic Clock and Voltage Scaling. Makes sense, MSM-DCVS
29: IntelliActive
Based off Google's Interactive governor with the following enhancements:
1. self-boost capability from input drivers (no need for PowerHAL assist)
2. two phase scheduling (idle/busy phases to prevent from jumping directly to max freq
3. Checks for offline cpus and short circuits some unnecessary checks to improve code execution paths
30: Adaptive
This driver adds a dynamic cpufreq policy governor
designed for latency-sensitive workloads and also for demanding
performance.
This governor attempts to reduce the latency of clock
increases so that the system is more responsive to
interactive workloads in loweset steady-state but to
to reduce power consumption in middle operation level level up
will be done in step by step to prohibit system from going to
max operation level.
31: Nightmare
A PegasusQ modified, less aggressive and more stable. A good compromise between performance and battery.
In addition to the SoD is a prevention because it usually does not hotplug.
32: ZZmove
ZZmove Governor optimized for low power consumption with the screen off, with particular attention to the limitation of consumption applications in the background with the screen off, such as listening to music. It has three settings: battery saver, balanced and performance. In addition to a performance boost, there is also the governor zzmove optimized.
I/O Scheduler: Thread:I/O Scheduler explained
The Scheduler is an algorithm that, given a set of requests for access to a resource, establishing a temporal order for the execution of such requests, favoring those that meet certain criteria in order to optimize access to that resource.
The difference between the various scheduler is the focus on certain criteria rather than on others.
The choice of a given scheduler does not produce visible changes so as to the choice of the governor, but still provides some improvements.
As usual schedulers are personally tested to find one that best suits your needs.
Deadline
It aims to provide a deadline, a deadline for all requests in order to avoid undesirable phenomena such as the "starvation" or the eternal waiting for some requests that occurs when one or more background processes are left indefinitely in the queue the ready, because there is always at least one of the highest priority ready process.
V (r)
The next request is performed according to the distance from the last request. In the network running good opinions about this scheduler.
No-op
Push all requests in a single queue simply by their arrival order, grouping together those contiguous.
SIO
E 'the scheduler simpler, does not make any type of sort, is intended only for the purpose of obtaining a low-latency, ie to reduce the amount of time that elapses between the instant at which the request is generated and that in which the request is satisfied.
CFQ
Order requests of different processes in queues for each queue type and assigns a specific interval of time whose duration depends on the priorities assigned to processes. Can be considered the Ondemand the scheduler, the scheduler is in fact more balanced, doing its job in an honest manner.
BFQ
It 's based on CFQ but, instead of the intervals of time, assigns a part of the bandwidth of the disc to each process running in a proportional manner.
Anticipatory
Order requests based on criteria predictive, that puts the demands paused for a short period of time in anticipation that more of this to come to aggregate them.
ADAPTIVE ANTICIPATORY SCHEDULER
For the anticipatory scheduler, we scale up the anticipation timeout (antic expire) using the latency scaling factor over time. When the virtual disk latencies are low a small scaling of the timeout is sucient to prevent deceptive idleness, whereas when the latencies are high a larger scaling of the timeout value may be required to achieve the same. Note that such dynamic setting of the timeout value ensures that we attain a good trade-o between throughput (lost due to idling) and deceptive idleness mitigation. Setting a high value for the scaling factor (increasing idling time) only happens when the disk service latencies themselves are higher. This may not necessarily cause a signicant loss in throughput, because submitting a request from another process instead of idling is not going to improve throughput if the virtual disk itself does not get any faster than it is at the current period. A higher anticipation timeout might also be capable of absorbing process scheduling eects inside the VM. The results for the adaptive anticipatory scheduler are shown in Figure 2. The read time with our modied implementation (third bar in the dierent scheduler combinations) shows that it is possible to mitigate the eects of deceptive idleness by adapting the timeout. An interesting related observation is that the level to which the improve- ment is possible varies for dierent Domain-0 schedulers; noop - 39%, anticipatory - 67% and cfq - 36%. This again points to the fact that the I/O scheduler used in Domain-0 is important for the VM's ability in enforcing I/O scheduling guarantees. Dierent Domain-0 I/O schedulers likely have a dierent service latency footprint inside the VMs, contributing to dierent levels of improvement.
ROW
Row stands for READ Over WRITE which is the main requests dispatch policy of this algorithm. The ROW IO scheduler was developed with the mobile devices needs in mind. In mobile devices we favor user experience upon everything else, thus we want to give READ IO requests as much priority as possible. In mobile devices we won't have as much parallel threads as on desktops. Usually it's a single thread or at most 2 simultaneous working threads for read & write. Favoring READ requests over WRITEs decreases the READ latency greatly.
The main idea of the ROW scheduling policy is: If there are READ requests in pipe - dispatch them but don't starve the WRITE requests too much. Bellow you'll find a small comparison of ROW to existing schedulers. The test that was run for these measurements is parallel read and write.
FIOS
Flash-based solid-state drives (SSDs) have the potential to eliminate the I/O bottlenecks in data-intensive applications However the large performance discrepancy between Flash reads and writes introduces challenges for fair resource usage. Further, existing fair queuing and quanta-based I/O schedulers poorly manage the I/O anticipation for Flash I/O fairness and efficiency. Some also suppress the I/O parallelism which causes substantial performance degradation on Flash. This paper develops FIOS, a new Flash I/O scheduler that attains fairness and high efficiency at the same time. FIOS employs a fair I/O time-slice management with mechanisms for read preference, parallelism, and fairness-oriented I/O anticipation. Evaluation demonstrates that FIOS achieves substantially better fairness and efficiency compared to the Linux CFQ scheduler, the SFQ(D) fair queuing scheduler, and the Argon quanta-based scheduler on several Flash-based storage devices (including a CompactFlash card in a low-power wimpy node). In particular, FIOS reduces the worst-case slowdown bya factor of 2.3 or more when the read-only SPECweb workload runs together with the write-intensive TPC

Can't wait to try this out on my t700

You might want to amend your OP. If you study the source code a little more and try understand things. You'll find there are no (actual) A7 100 MHz. A7 cores freq are doubled 100-650 (become 200-1300) MHz. A15 cores 800-1900+. Samsung have done it this way for IKS to work easily.
Some CPU control apps will just read the table but not able to differentiate between the A7 and A15 cores, and just display what's read from the frequency table.
You've made a good start, but 99% over those governors aren't suitable and/or optimized for Exynos. A "shotgun" approach isn't always the best way, but hey, this is your toy.

UpInTheAir said:
You might want to amend your OP. If you study the source code a little more and try understand things. You'll find there are no (actual) A7 100 MHz. A7 cores freq are doubled 100-650 (become 200-1300) MHz. A15 cores 800-1900+. Samsung have done it this way for IKS to work easily.
Some CPU control apps will just read the table but not able to differentiate between the A7 and A15 cores, and just display what's read from the frequency table.
You've made a good start, but 99% over those governors aren't suitable and/or optimized for Exynos. A "shotgun" approach isn't always the best way, but hey, this is your toy.
Click to expand...
Click to collapse
Now I understand that a little bit more. Because I added first a 100MHz support and added all stuff to get it work and than, it displayed me 50MHz and I thought, what the heck is going wrong here?
So I removed it again. Thank you for helping out here.
Suitable are they, but optimized not at the moment. You know, otherwise I wont have work left
And that's also why I call it a beta version at the moment.

Tkkg1994 said:
Now I understand that a little bit more. Because I added first a 100MHz support and added all stuff to get it work and than, it displayed me 50MHz and I thought, what the heck is going wrong here?
So I removed it again. Thank you for helping out here.
Suitable are they, but optimized not at the moment. You know, otherwise I wont have work left
And that's also why I call it a beta version at the moment.
Click to expand...
Click to collapse
No, a lot are not suitable, as they are written for krait SoC (4 main cores), just like intelli-plug etc. I found they were more of a hassle and eroded kernel stability, hence I never committed the changes for release. You might find otherwise, so no harm to try. Can be fun, and also a headache too
Snapdragon 810 will be using big.LITTLE architecture same as Exynos, so hopefully faux will port some of his work over. Although it will be HMP, maybe we can adapt to our IKS kernel.

UpInTheAir said:
No, a lot are not suitable, as they are written for krait SoC (4 main cores), just like intelli-plug etc. I found they were more of a hassle and eroded kernel stability, hence I never committed the changes for release. You might find otherwise, so no harm to try. Can be fun, and also a headache too
Snapdragon 810 will be using big.LITTLE architecture same as Exynos, so hopefully faux will port some of his work over. Although it will be HMP, maybe we can adapt to our IKS kernel.
Click to expand...
Click to collapse
Nobody says that we can't port it to 8 cores you know, it is a lot of work for sure, but not impossible.
I barely had problems with the governors, more with intelliplug.
But I think it is good that we don't have the same opinion.
Otherwise we would have 2 similar kernels here.

Tkkg1994 said:
Nobody says that we can't port it to 8 cores you know, it is a lot of work for sure, but not impossible.
I barely had problems with the governors, more with intelliplug.
But I think it is good that we don't have the same opinion.
Otherwise we would have 2 similar kernels here.
Click to expand...
Click to collapse
I don't think you understand me yet. We use IKS and 4 cores at once big.LITTLE . NOT HMP (all cores running). If you study the governors and what exactly the frequency/cores are actually doing in real time, you will find out and learn from it ... Just because something compiles and are able to switch between variables, does not make it compatible.
I never said or implied that anything was impossible, but you need to re-write (not adapt) a lot of code. In effect, create a "new" governor. This is fact, not my opinion
Best of luck with your project, keep at it !

UpInTheAir said:
I don't think you understand me yet. We use IKS and 4 cores at once big.LITTLE . NOT HMP (all cores running). If you study the governors and what exactly the frequency/cores are actually doing in real time, you will find out and learn from it ... Just because something compiles and are able to switch between variables, does not make it compatible.
I never said or implied that anything was impossible, but you need to re-write (not adapt) a lot of code. In effect, create a "new" governor. This is fact, not my opinion
Best of luck with your project, keep at it !
Click to expand...
Click to collapse
I read the wiki article
I think our Exynos5 5420 use HMP and can use all cores together if it uses it?
I was talking about the intelli-plug stuff not the governors. I hope samsung will release a S6 with exynos (only) and than we will get more support.
If you want to talk with me (and yes I like to) than PM?

Tkkg1994 said:
I read the wiki article
I think our Exynos5 5420 use HMP and can use all cores together if it uses it?
I was talking about the intelli-plug stuff not the governors. I hope samsung will release a S6 with exynos (only) and than we will get more support.
If you want to talk with me (and yes I like to) than PM?
Click to expand...
Click to collapse
Keep reading and learning Particularly what IKS is and does. Please don't take this the wrong way, this is relevant and you really need to learn how the basics of our 5420 kernel actually work.
There have been test HMP for Exynos 5420, BUT, no Android powered Exynos 5420 is ever capable of HMP. AndreiLux has explained why in various posts.
HMP kernels (such as I'm using with my Note Edge Skyhigh kernel) is completely different, but some things might be adapted with little work.
I just don't have the time to answer or clarify every single question (I don't pretend to always know), even by PM. It's just a matter of reading, learning, and trial by many errors.

UpInTheAir said:
Keep reading and learning Particularly what IKS is and does. Please don't take this the wrong way, this is relevant and you really need to learn how the basics of our 5420 kernel actually work.
There have been test HMP for Exynos 5420, BUT, no Android powered Exynos 5420 is ever capable of HMP. AndreiLux has explained why in various posts.
HMP kernels (such as I'm using with my Note Edge Skyhigh kernel) is completely different, but some things might be adapted with little work.
I just don't have the time to answer or clarify every single question (I don't pretend to always know), even by PM. It's just a matter of reading, learning, and trial by many errors.
Click to expand...
Click to collapse
I'm doing this the first time, so hopefully you and the others will understand that. I hope you can excuse me I have to learn many things I know that.
See you soon!

Changelog V1.1:
-Temporarly removed Intelli-Plug
-Added voltcontroll for CPU
-Added Stweaks support and Stweaks app (all credits and stuff goes to @googy_anas and @Kryten2k35
-Hell lot of improvements
-GPU overclock to 733MHz
-CPU overclock to 2.1GHz (sorry, I couldn't get it stable )
-for more what I had done, visit here: Commits IronKernel

Tkkg1994 said:
-Temporarly removed Intelli-Plug
-Added voltcontroll for CPU
-Added Stweaks support and Stweaks app (all credits and stuff goes to @googy_anas and @Kryten2k35
-Hell lot of improvements
-GPU overclock to 733MHz
-CPU overclock to 2.1GHz (sorry, I couldn't get it stable )
-for more what I had done, visit here: Commits IronKernel
Click to expand...
Click to collapse
Kernel update is awesome I love the GPU OC seems stable also went to 2GHZ CPU OC no issues I would go to 2.1GHZ but I think it may get unstable
TAPATALKED WITH MY XPE R IA Z
My Z3 app Ports to all devices

danny19901 said:
Kernel update is awesome I love the GPU OC seems stable also went to 2GHZ CPU OC no issues I would go to 2.1GHZ but I think it may get unstable
TAPATALKED WITH MY XPE R IA Z
My Z3 app Ports to all devices
Click to expand...
Click to collapse
Better let it at 2.0 GHz. Best for stability! Great you enjoy it

danny19901 said:
Kernel update is awesome I love the GPU OC seems stable also went to 2GHZ CPU OC no issues I would go to 2.1GHZ but I think it may get unstable
TAPATALKED WITH MY XPE R IA Z
My Z3 app Ports to all devices
Click to expand...
Click to collapse
N/A

fishdrop said:
N/A
Click to expand...
Click to collapse
Just putting N/A doesn't help much if you need help or something

New changelog:
IronKernel V1.2 01.03.2015:
- Built with latest toolchain (2015.02) by christopher83
- Use frandom from now
- Enable dynamic page writeback with earlysuspend
- Better battery charging control (kernel and stweaks)
- Auto install the right sTweaks version
- Reduce overestimating rq->avg_idle
- Optimize find_busiest_queue()
- Some CPUfreq optimizations
- Dynamic sync control with earlysuspend support
- Lowmemorykiller: implement task's adj rbtree
- Check free memory when tasks switch to background
- Dynamic FSync
- SOO Much more but I don't remember all
- After flashing the kernel, it will be successfull, but then show an error (becaus of mounting partition) don't worry, just reboot. Just ignore it

THANKYOU !!! Why is it that most other developers can't use common sense and say right up front that their work will kill Knox.

hillg001 said:
THANKYOU !!! Why is it that most other developers can't use common sense and say right up front that their work will kill Knox.
Click to expand...
Click to collapse
This won't actually trip Knox counter...
By installing a custom recovery (pre-requisite to install kernel.zip) will already trip the counter, and not within the scope of most Developers concern. Wouldn't the user already have tripped the counter prior to flashing the kernel? Think about it. .. Having the warning in OP doesn't hurt though