H815 Kernel Setting Experiment - G4 General

Hi
I have my G4 unlocked and rooted on 10C, and thought I would try some Kernel Setting experiments using Trickster.
Stock settings use Interactive.
So I tried Userspace but seems that Userspace sets the clock speed to full nearly 90% of the time for me.
So I decided to give Ondemand and read ahead 1024 CFQ a try.
Maybe a placebo? But watching the cpu clock speeds, it doesn't seem to hang up at 1248 like it does in Interactive and drops much quicker back to 384, but equally ramps up quicker too.
I seem to get less battery drain when browsing instead of Interactive 512 CFQ (Stock setting) after a few days testing.
I know very little about kernels on Android, but thought I would share my findings if anyone is interested.

damn i hope root will come fast, i need to have conservative govenor, as it the only one that plays ppsspp tekken well.

the major isue I see is the actual hotplug that keeps all cores always on.
That is pretty strange...LG's devs must be sleeping while our cores are not

Didn't find Conservative in the options. Only Interactive, Userspace, Ondemand, Powersave, & Performance.
Haven't tried Powersave yet though?

johnny8910 said:
Didn't find Conservative in the options. Only Interactive, Userspace, Ondemand, Powersave, & Performance.
Haven't tried Powersave yet though?
Click to expand...
Click to collapse
I wouldn't play with actual governors and let them at their default value until we have a custom kernel.

Thanks, but I am still finding Ondemand seems to give me less battery drain under use such as web browsing.

Related

[Q] SetCPU governors (explained)

The SetCPU website explains some governors: http://www.pokedev.com/setcpu/#7
However it seems that some extra governors, not covered by the SetCPU site, have been added to some kernels; which I think should be documented so users know which one to pick.
I will add responses as to what each governor does to this post. If there are any governors not explained that you've come across, please post and we'll see if somebody can explain it.
Unexplained governors (somebody please tell me what they do)
smartass (Best explanation i've found paraphrases to: based on interactive, but better.)
----
ondemand
Available in most kernels, and the default governor in most kernels. When the CPU load reaches a certain point (see "up threshold" in Advanced Settings), ondemand will rapidly scale the CPU up to meet demand, then gradually scale the CPU down when it isn't needed. - SetCPU website
conservative
Available in some kernels. It is similar to the ondemand governor, but will scale the CPU up more gradually to better fit demand. Conservative provides a less responsive experience than ondemand, but can save battery. - SetCPU website
performance
Available in most kernels. It will keep the CPU running at the "max" set value at all times. This is a bit more efficient than simply setting "max" and "min" to the same value and using ondemand because the system will not waste resources scanning for the CPU load. This governor is recommended for stable benchmarking. - SetCPU website
powersave
Available in some kernels. It will keep the CPU running at the "min" set value at all times. - SetCPU website
userspace
A method for controlling the CPU speed that isn't currently used by SetCPU. For best results, do not use the userspace governor. - SetCPU website
Interactive
The 'interactive' governor has a different approach. Instead of sampling the cpu
at a specified rate, the governor will scale the cpu frequency up when coming
out of idle. When the cpu comes out of idle, a timer is configured to fire
within 1-2 ticks. If the cpu is 100% busy from exiting idle to when the timer
fires then we assume the cpu is underpowered and ramp to MAX speed.
If the cpu was not 100% busy, then the governor evaluates the cpu load over the
last 'min_sample_rate' (default 50000 uS) to determine the cpu speed to ramp down
to. - [Patches] For developers, interactive governor patch for leo kernel
Thanks,
RJackson
As explained by MDJ:
SMARTASS GOVERNOR - 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 245Mhz (or if your min frequency is higher than 245 - why?! - it will cap it to your min frequency). Lets take for example the 998/245 kernel, it will sleep at 245. No need for sleep profiles any more!
Click to expand...
Click to collapse
FerretAD said:
As explained by MDJ:
Click to expand...
Click to collapse
I saw that one but didn't use it because it didn't really explain what it does.
RJackson said:
smartass (Best explanation i've found paraphrases to: based on interactive, but better.)
Click to expand...
Click to collapse
Which Kernel support SmartAss? I use WildMonks with SetCPU 2.1.0 and I don't see the "smartass" governor in my list.
SalsaForte said:
Which Kernel support SmartAss? I use WildMonks with SetCPU 2.1.0 and I don't see the "smartass" governor in my list.
Click to expand...
Click to collapse
i have the "savage" kernal with smartass
LeeDroid's Kernals and ROMs support smartass as well
Leong428 said:
LeeDroid's Kernals and ROMs support smartass as well
Click to expand...
Click to collapse
Add Tiamat to the list.
add chad's incredikernel
SalsaForte said:
Which Kernel support SmartAss? I use WildMonks with SetCPU 2.1.0 and I don't see the "smartass" governor in my list.
Click to expand...
Click to collapse
On my evo shift the x99 kernel supports smartass for stockish froyo roms and cm7 roms
you have to have a kernel to add smartass to your list
RJackson said:
The SetCPU website explains some governors: http://www.pokedev.com/setcpu/#7
However it seems that some extra governors, not covered by the SetCPU site, have been added to some kernels; which I think should be documented so users know which one to pick.
I will add responses as to what each governor does to this post. If there are any governors not explained that you've come across, please post and we'll see if somebody can explain it.
Unexplained governors (somebody please tell me what they do)
smartass (Best explanation i've found paraphrases to: based on interactive, but better.)
----
ondemand
Available in most kernels, and the default governor in most kernels. When the CPU load reaches a certain point (see "up threshold" in Advanced Settings), ondemand will rapidly scale the CPU up to meet demand, then gradually scale the CPU down when it isn't needed. - SetCPU website
conservative
Available in some kernels. It is similar to the ondemand governor, but will scale the CPU up more gradually to better fit demand. Conservative provides a less responsive experience than ondemand, but can save battery. - SetCPU website
performance
Available in most kernels. It will keep the CPU running at the "max" set value at all times. This is a bit more efficient than simply setting "max" and "min" to the same value and using ondemand because the system will not waste resources scanning for the CPU load. This governor is recommended for stable benchmarking. - SetCPU website
powersave
Available in some kernels. It will keep the CPU running at the "min" set value at all times. - SetCPU website
userspace
A method for controlling the CPU speed that isn't currently used by SetCPU. For best results, do not use the userspace governor. - SetCPU website
Interactive
The 'interactive' governor has a different approach. Instead of sampling the cpu
at a specified rate, the governor will scale the cpu frequency up when coming
out of idle. When the cpu comes out of idle, a timer is configured to fire
within 1-2 ticks. If the cpu is 100% busy from exiting idle to when the timer
fires then we assume the cpu is underpowered and ramp to MAX speed.
If the cpu was not 100% busy, then the governor evaluates the cpu load over the
last 'min_sample_rate' (default 50000 uS) to determine the cpu speed to ramp down
to. - [Patches] For developers, interactive governor patch for leo kernel
Thanks,
RJackson
Click to expand...
Click to collapse
Thanks for the kind descriptions...
I've translated them to Korean for my fellow countrymen!
>,<
http://caleb1783.tistory.com/157
Thanks for this. Smartass has been a mystery to me.
When I installed SETCPU I selected auto-detect, now on my device (not a HD2, but this seemed like a good place to ask as it is directly related) now I have no way to select the governor at all (box is blank), how to I change the detection from automatic to a device type "Tegra 2" in my case, I see no option to allow me to do this?
Thanks,
ERIC
Powersave
I read on this forum that Power save SetCPU governor saves the best battery. I Hope this is true?
I am trying to get my hands on powersave
I can't find powersave in the "market" though.. What's up with that? Can anyone tell me which one it is? Maybe give the name of the developer so i can find it back easier?
thnks in advance
Im using galaxy s 2 with lite'ning rom 6.1 ninphetamine 2.0.5
ssienn said:
I read on this forum that Power save SetCPU governor saves the best battery. I Hope this is true?
I am trying to get my hands on powersave
I can't find powersave in the "market" though.. What's up with that? Can anyone tell me which one it is? Maybe give the name of the developer so i can find it back easier?
thnks in advance
Im using galaxy s 2 with lite'ning rom 6.1 ninphetamine 2.0.5
Click to expand...
Click to collapse
Yeah, that's not how it works. Governors are a part of the kernel. If you want features in your kernel that you don't have, you must flash a new kernel.
also, perhaps you should reread what 'powersave' is. It will keep your phone at the lowest cpu speed constantly. This will save battery, sure, but it will also completely destroy your phone's performance. Might as well go back to your old Moto Razr.
thx, actually, i set those gov randomly before i read this post
Ondemand vs. Smartass vs. Performance gov. - Test
The idea was, that maybe the display eats so much power,
that if it is on, the CPU setting does not make a big different.
Bottom line: it does.
Phone: HTC Sensation, Leedroid Sensational 3.1 (kernel 3.2)
Conditions: Simulating light cpu use like writing email:
Brightness 50% (no timeout), MP3 playing (Volume=1, headphone), a new document on the screen,
Wifi and 3G network off (these have fluctuation, so it is easier to compare if these are off)
Ondemand 192/1188 governor: 5 h 10 min
Performance governor: 4 h 20 min
SmartassV2 192/1188 governor: 5 h 2 min
Off course if the display is off, it is easy to choose, because there is no need for performance.
I set up Conservative 192/810, but any similar can work.
I choose Ondemand, and using "Tasker" to switch to Performance, if certain applications are active,
like Doodle Jump - which run a little smoother with the Performance, for as an example.
thanks for the info...
nice, thanks
Thanks, cleared my doubts.
completely noob question, how do u choose between governors? set cpu from the market its a paid app, and the one i downloades from the official post wont work
i have a galaxy s2 with Touch X-POWER+ 2.1 [XXKI3] rom

[GUIDE] Governors for NOOBS

Interactive - Instead of sampling the cpu at a specified rate, the governor will scale the cpu frequency up when coming out of idle. When the cpu comes out of idle, a timer is configured to fire within 1-2 ticks. If the cpu is 100% busy from exiting idle to when the timer fires then we assume the cpu is underpowered and ramp to MAX speed.
Smartass- Is an improved version of interactive governor
Ondemand – Available in most kernels, and the default governor in most kernels. When the CPU load reaches a certain point (see “up threshold” in Advanced Settings), ondemand will rapidly scale the CPU up to meet demand, then gradually scale the CPU down when it isn't needed.
Conservative– Available in some kernels. It is similar to the ondemand governor, but will scale the CPU up more gradually to better fit demand. Conservative provides a less responsive experience than ondemand, but can save battery.
Performance – Available in most kernels. It will keep the CPU running at the “max” set value at all times. This is a bit more efficient than simply setting “max” and “min” to the same value and using ondemand because the system will not waste resources scanning for CPU load.
Powersave – Available in some kernels. It will keep the CPU running at the “min” set value at all times.
Userspace– A method for controlling the CPU speed that isn't currently used by SetCPU. For best results, do not use the userspace governor.
Hope those will able to help newbies to SetCPU or No Frills CPU.
Credit to LeeDroid for the infos
I believe Interactive is the most responsive kernel out there. Faster than ondemand. So it'll technically use more power when you are using the phone.
HOWEVER, isn't the best feature of Smartass the ability to cap frequencies when the screen is OFF? This essentially negates the need for using SetCPU to limit frequenceis when screen is off. Yes it's an improved version of interactive, but it should be just as responsive, but with these set limits in. I'm just not sure what the specific rules are. I used it for my Moto Milestone, but I'm unsure of what the rules are here.
window7 said:
Interactive - Instead of sampling the cpu at a specified rate, the governor will scale the cpu frequency up when coming out of idle. When the cpu comes out of idle, a timer is configured to fire within 1-2 ticks. If the cpu is 100% busy from exiting idle to when the timer fires then we assume the cpu is underpowered and ramp to MAX speed.
Smartass - Is an improved version of interactive governor
Ondemand – Available in most kernels, and the default governor in most kernels. When the CPU load reaches a certain point (see “up threshold” in Advanced Settings), ondemand will rapidly scale the CPU up to meet demand, then gradually scale the CPU down when it isn't needed.
Conservative – Available in some kernels. It is similar to the ondemand governor, but will scale the CPU up more gradually to better fit demand. Conservative provides a less responsive experience than ondemand, but can save battery.
Performance – Available in most kernels. It will keep the CPU running at the “max” set value at all times. This is a bit more efficient than simply setting “max” and “min” to the same value and using ondemand because the system will not waste resources scanning for CPU load.
Powersave – Available in some kernels. It will keep the CPU running at the “min” set value at all times.
Userspace – A method for controlling the CPU speed that isn't currently used by SetCPU. For best results, do not use the userspace governor.
Hope those will able to help newbies to SetCPU or No Frills CPU.
And do correct me if I am wrong. Thank you
Click to expand...
Click to collapse
You should credit the source you copy and pasted that from. Or even better post the link.
Sent from my Nexus S using XDA App
dmo580 said:
I believe Interactive is the most responsive kernel out there. Faster than ondemand. So it'll technically use more power when you are using the phone.
HOWEVER, isn't the best feature of Smartass the ability to cap frequencies when the screen is OFF? This essentially negates the need for using SetCPU to limit frequenceis when screen is off. Yes it's an improved version of interactive, but it should be just as responsive, but with these set limits in. I'm just not sure what the specific rules are. I used it for my Moto Milestone, but I'm unsure of what the rules are here.
Click to expand...
Click to collapse
SMARTASS is a rewrite of the INTERACTIVE governor, and it moves the CPU up/down depending on whether the phone is idle/locked/ ... etc.
But some problems that I experience with SMARTASS is that my music playback sometimes stutters(?). So I'm just sticking with INTERACTIVE.
http://setcpu.com
edit:/#7 didnt seem to work right?
matt2053 said:
You should credit the source you copy and pasted that from. Or even better post the link.
Sent from my Nexus S using XDA App
Click to expand...
Click to collapse
Thanks for telling me that. I had changed it
However, I cant post the link as I cannot find the source I find it.
I only know that LeeDroid provided me the details
window7 said:
Thanks for telling me that. I had changed it
However, I cant post the link as I cannot find the source I find it.
I only know that LeeDroid provided me the details
Click to expand...
Click to collapse
I believe it comes from SetCPU's website.
Http://www.setcpu.com
Sent from my Nexus S using XDA App
olorin86 said:
SMARTASS is a rewrite of the INTERACTIVE governor, and it moves the CPU up/down depending on whether the phone is idle/locked/ ... etc.
But some problems that I experience with SMARTASS is that my music playback sometimes stutters(?). So I'm just sticking with INTERACTIVE.
Click to expand...
Click to collapse
Is this because your screen is off? Yeah, smartass has some issues when the screen is off. Main issue is wakeup and whatever else your phone has to do. I know the Netarchy kernel with smartass just got a revision lately to deal with more wake issues.
But in terms of when your screen is on smartass should function exactly like interactive. So that's why I said smartass is essentially interactive, but with those preset rules regarding screen off that you would otherwise have to create using SetCPU.
The reason you might have worse battery might be because during screen off, your phone is struggling to do work at a slower pace (ideally you shouldn't have to do much, but maybe some people's phones have a lot of stuff running in the background), and so the more time you spent with the CPU active ends up eating more power.
This is one of the arguments about Intel Atom vs. Intel i3. Both idle at the same wattage, but the i3 uses massively more power in load. Probably 2x-3x more. However, given that the i3 is like so FAST, it gets say an encoding job done in like 1/4 the time. Your overall power (Watts * time) used is actually less with the faster CPU. This might apply with the Smartass governor. If your CPU is struggling and maxing out at its cap for a long time because its not fast enough when the screen is off, then perhaps this can be an issue. Just a thought. This is why I think the max_freq for sleep should probably be set around 500-600mhz instead of like 200mhz.
But once again I'm not sure what the governor is set at right now. If someone knows, please do tel

Best CPU governor for Nexus S

which of the recent governors gives best performance?
lazy, interactive, smartassv2?
Thanks guys
I just use Ondemand. I've tried others but I always end going back to it.
I've heard interactive is good for performance. I was under the impression that lazy and smartass were more geared towards battery saving.
Sent from my Nexus S using xda premium
I use lazy or ondemand typically.
Follow the leader @corythug
for performance, ondemand with a sampling rate of 15000 and up threshold of 98.
simms22 said:
for performance, ondemand with a sampling rate of 15000 and up threshold of 98.
Click to expand...
Click to collapse
simms, I am assuming this will drain battery faster as the default sampling rate is 40000. Am I correct?
Sampling Rate – An interval (in microseconds) at which the governor will poll for updates. When this happens, the governor will decide whether to scale the CPU up or down.
Up Threshold – Defines a percentage from 1% to 100%. When the CPU load reaches this point, the governor will scale the CPU up.
i like smartassV2 1200 / 100
Naa Laa said:
simms, I am assuming this will drain battery faster as the default sampling rate is 40000. Am I correct?
Sampling Rate – An interval (in microseconds) at which the governor will poll for updates. When this happens, the governor will decide whether to scale the CPU up or down.
Up Threshold – Defines a percentage from 1% to 100%. When the CPU load reaches this point, the governor will scale the CPU up.
Click to expand...
Click to collapse
no. itll actually be a little better on battery, a little more efficient than the default. and itll give the ui a little speed boost.
Isn't interactive supposed to be a 'better OnDemand'
I'm thinking it's the opposite, that on demand was an improved interactive, but I could be wrong. I really don't notice much difference between any of them. On lazy and smartassv2 I seem to get more random problems. Really though, what's best questions are left for you to explore and find out. Some people on these threads use their phone for most their computing needs and some barely even use their phone.
Sent from my Nexus S 4G
i use smartass 1200/200 on matrix 10.0 kernal n havent had any issues..i get awesome battery life 18+ hours with light to moderate use
Sent from my Nexus S 4G using XDA Premium App
I'm voting for interactive, I've had great battery life and performance from it fwiw
Sent from my Nexus S 4G using Tapatalk
What's actually the difference? Is there any guide to read?
gellow said:
What's actually the difference? Is there any guide to read?
Click to expand...
Click to collapse
ondemand – Available in most kernels, and the default governor in most kernels. When the CPU load reaches a certain point (see “up threshold” in Advanced Settings), ondemand will rapidly scale the CPU up to meet demand, then gradually scale the CPU down when it isn't needed.
interactive – Available in newer kernels, and becoming the default scaling option in some official Android kernels. The interactive governor is functionally similar to the ondemand governor with an even greater focus on responsiveness.
conservative – Available in some kernels. It is similar to the ondemand governor, but will scale the CPU up more gradually to better fit demand. Conservative provides a less responsive experience than ondemand, but can save battery.
performance – Available in most kernels. It will keep the CPU running at the “max” set value at all times. This is a bit more efficient than simply setting “max” and “min” to the same value and using ondemand because the system will not waste resources scanning for CPU load.
powersave – Available in some kernels. It will keep the CPU running at the “min” set value at all times.
userspace – A method for controlling the CPU speed that isn't currently used by SetCPU. For best results, do not use the userspace governor.
smartass – Included in some custom kernels. The smartass governor effectively gives the phone an automatic Screen Off profile, keeping speeds at a minimum when the phone is idle.
SOURCE: http://setcpu.com/#7
I've tried different configurations but always end up going for ondemand.
There is no "best governor", just like there's no best brand of beer. My favorite, however, is smartassv2. Great performance and battery life - probably one of the better compromises.
But I don't drink beer!
Sent from my Nexus S using XDA App

[REF] CPU Governors and I/O Schedulers

Spreadsheets for CPU Governors and I/O Schedulers
GOVERNOR RESULTS
I/O SCHEDULERS
Summary of the Results
This is a summary of the six most commonly used governors, listed in order of performance.
Best Performing
#1 - Performance
--- : Use Noop or Deadline
--- : Uses a lot more battery
#2 - SmartassV2
--- : Use Noop or SIO
--- : Good choice if you use a lot of CPU intensive apps
#3 - LulzactiveV2
--- : Use Deadline or Noop
--- : Good choice if you use a lot of CPU intensive apps
--- : Uses a little more battery than SmartassV2
#4 - Lazy
--- : Use Deadline or CFQ
--- : Do not enable SOMF (Screen Off Max Frequency uses more battery)
--- : Good choice if you do not use CPU intensive apps
#5 - Ondemand
--- : Use Noop or Deadline
--- : Good choice if you do not use CPU intensive apps
--- : Saves slightly more battery than Lazy
#6 - Conservative
--- : Use CFQ or Noop
--- : Generally one of the worst governors for saving battery, see next post for why.
Check my summary in the Battery Drain thread for more info about how to save battery.
Where did the other benchmarks go?
All ICS ROM Benchmarks: this thread
Kernel Features and Benchmarks: this thread
Battery drain: this thread
Power Saving Governors: this thread
Thanks to all the developers.
Conservative Not Saving Power?
chickelnoodensoup said:
Is the summary in the first post correct with regard to conservative? Is it really "Generally one of the worst governors for saving battery"? Interesting.
Click to expand...
Click to collapse
I know it seems a little odd. It's because a lot of developers seem to have tweaked conservative to make it feel snappier, but it has resulted in more CPU time at the top frequency.
If you take a look at my new spreadsheet: http://goo.gl/ThVzX
...you can see conservative always uses more power when the screen is on (at least for the four kernels I tested).
There is just one exception where conservative saves more power than other governors, and that is when the screen is off, music is on, deep idle is on, and this only applies specifically to Air Kernel. PLEASE NOTE: Steve Garon does not include deep idle, but is working on it, neither does Eugene, but I've asked him to consider it. For these two kernels, if you are listening to music with the screen off, currently, the best power saving governor is Ondemand.
For people who don't use their phone while off, and don't use many intensive apps, Ondemand is the best power saving choice.
For people who use a lot of CPU intensive apps, SmartassV2 will be the better choice. It will scale more agressively, help prevent lags, and save energy being wasted through these delays.
If you listen to music with the screen off, and your kernel supplies deep idle, the best power saving governor is SmartassV2 (except for the case of Air Kernel, see above). This is because it keeps the CPU close to the most efficient frequency: 400MHz.
I hope that covers anything. If I've made any glaring errors in my reasoning, please let me know.
Choosing a Governor
Variety is the spice of life, so try them all! While Mathkid95 swears by Ondemand, developers Eugene373, morfic, and steve.garon all vetted this work and agreed that the highest performing CPU governor is likely to offer battery savings through the race-to-idle principal. Eugene added that finding the right I/O scheduler to combine with your governor will make a big difference too. Extra thanks to Steve for providing the kernel on which I based this test, and all his valuable input! The I/O scheduler for the test was cfq, and note: governors have settable parameters which may vary between developers.
Choosing a Scheduler
I/O schedulers perform differently depending on the governor you are using. I've investigated this using the six most popular CPU governors (vote here) vs the six available I/O schedulers in Eugene's kernel, and the four available in r_data's kernel. All governors are based on either ondemand, interactive, or conservative. Recommended reading is available here: schedulers also for governors
Schedulers tested against these popular governors:
SmartassV2 - interactive variant, and winner of the governor test.
LulzactiveV2 - interactive variant
Lazy - Ezekeel's governor, ondemand variant
Performance - included as a reference for high scores
Ondemand
Conservative
Testing Methodology
To test the kernels I want a fair environment, so any differences in the results are down to the kernel, and nothing else. To achieve this I first make sure I have a clean system:
1) Format /system and /cache and wipe dalvic
2) Install the ROM, install the kernel
3) Boot up, use nstools to select deadline for I/O scheduler
4) Then select a CPU governor and I/O scheduler depending on the test at hand
5) Titanium Backup to restore all my benchmark programs (app only). Set everything to off, no gps, no sync, no BT, airplane mode. Force GPU rendering is selected. Wifi is on for connecting to the benchmark servers. A power adaptor is in use so the battery is always full.
Then I begin testing.
For the CPU Governor Comparison study:
6) Power off and power back up. When lock screen arrives, wait one minute to settle the system, i.e. until screen auto-off. Count to three. Unlock, and begin testing, recording all scores. Start over with all the tests. Record those scores. (I now have two sets of scores for all the benchmarks to create a mean for improved accuracy). Then select next governor, power off and on, and start the cycle again.
For the I/O Scheduler Comparison study:
6) Power off and power back up. For each new scheduler I completed one test which I did not record, just to ensure that the program was properly cached in the system. I then recorded the subsequent ten results. After ten results, I would select the next scheduler, until I had finished all six, then I would also select the next governor and go back to the first scheduler. I repeated this cycle until I had collected data for performance, and the three other main governor types.
Statistics in the scheduler study are a little different to the other tests. They combine overall performance scores with overall variance scores (where lower is better). The formula is
a= Database IO score - 3 standard deviations
b= Write speed - 3 standard deviations
c= Read speed - 3 standard deviations
score=(a*b*c) to the power of 1/3
If you multiply three values together, and take the cube root (same as raising to 1/3) then you arrive at the geometric mean. This type of mean allows the comparison of two different schedulers based not just on their performance, but also how consistent in that performance they are. That score is then compensated by adjusting by half of the percentage discrepancy between the mean and median. For most scores that is an adjustment of less than 1%.
Summary of the Results
SmartassV2 won the governor benchmarks, and also performed well in the battery drain benchmarks.
The best I/O scheduler to combine with this is noop.
This is the combination I personally prefer. However, this is merely my opinion, based on my tests. Mathkid95 prefers ondemand. At the time of writing, Steve Garon and Franco prefer their own tweaked versions of conservative. (My tests indicate CFQ is the best match for conservative.)
Nice work on this!
bedalus said:
Summary of the Results
SmartassV2 won the governor benchmarks, and also performed well in the battery drain benchmarks.
The best I/O scheduler to combine with this is noop.
This is the combination I personally prefer. However, this is merely my opinion, based on my tests. Mathkid95 prefers ondemand. At the time of writing, Steve Garon and Franco prefer their own tweaked versions of conservative. (My tests indicate CFQ is the best match for conservative.)
Click to expand...
Click to collapse
Im also prefer smartassv2+noop. Really good combination
Very usefull, Thanks
Surnom said:
Very usefull, Thanks
Click to expand...
Click to collapse
No problem. If anyone is wondering why so few posts, it's because I recently separated this work away from my kernel benchmarking thread. Feel free to feedback.
bedalus said:
Summary of the Results
SmartassV2 won the governor benchmarks, and also performed well in the battery drain benchmarks.
The best I/O scheduler to combine with this is noop.
This is the combination I personally prefer. However, this is merely my opinion, based on my tests. Mathkid95 prefers ondemand. At the time of writing, Steve Garon and Franco prefer their own tweaked versions of conservative. (My tests indicate CFQ is the best match for conservative.)
Click to expand...
Click to collapse
Never kneww that SmartassV2 works best with noop! I used to have it with deadline. Now experiencing the best experience ever!
using Franco BFS Nov 1st
Thanks man! Thanks Franco!
SmartassV2/Noop +1
UPDATE: Steve had a rethink of his Conservative governor parameters, and I've updated the table to include this. Check column L.
Lower scores are natural with conservative. This time, with the new parameters, the scores are even lower. This indicates that the new conservative is throttling the frequencies more aggressively, but it should also be noted that this governor feels much more responsive than the previous incarnation.
Note - the IO score shows a great improvement, but this is due only to a boost in database IO through the recent FSYNC patch. Make sure you use stable voltages to avoid reboots and potential data loss. (No benefit to UV anyway - check the results of my battery study, see link above.)
thx mate! You do a great job!
Sent from my Nexus S using Tapatalk
Some serious work been put into this.. Anyway of listing governors in respect of there performance then a list of governors for best battery life and the recommended I/O schedulers to accompany them. I know the graph is there but it'll be easier for people like me (not so good with cpu settings) to just simply apply from a high to low list which indicates best performance or more battery life. I'm getting great battery life and decent performance using ondemand with noop but it eats battery a lot more when phone is in use compared to other combinations I've tried.
Sent from my HTC Desire S using XDA App
bedalus said:
Summary of the Results
SmartassV2 won the governor benchmarks, and also performed well in the battery drain benchmarks.
The best I/O scheduler to combine with this is noop.
Click to expand...
Click to collapse
Is it just me or does the spreadsheet say deadline is best with SmartassV2 with noop second?
dabado said:
Some serious work been put into this.. Anyway of listing governors in respect of there performance then a list of governors for best battery life and the recommended I/O schedulers to accompany them. I know the graph is there but it'll be easier for people like me (not so good with cpu settings) to just simply apply from a high to low list which indicates best performance or more battery life. I'm getting great battery life and decent performance using ondemand with noop but it eats battery a lot more when phone is in use compared to other combinations I've tried.
Sent from my HTC Desire S using XDA App
Click to expand...
Click to collapse
Good idea. I will try to do it today.
kernels ; battery ; ROM ; gov/sched
Thaks to your recommend, I use noop + SmartassV2.
I used cfq+tweaked conservative before that set, but I can't feel differece and battery life (I don't know this phrase mean but I'm saying it is very good!)
UPDATE: First post edited. Now summarises all findings. Also, makes it easier to read if you are using the XDA app
Thank you !
Bedalus, I did a little amateur test today.
I played some music with not-too-loud volume.
I keep my data ON, everything else is off.
The screen is always ON with lowest brightness because I'm looking at the CPU frequency used.
CPU min 200, max 1000.
I went to Processor settings and look at the CPU frequency used at the moment.
When I selected Conservative and let it stay for 10 seconds, the CPU freq is showing 1000 constant.
Then I selected Lazy and let it stay for another 10 seconds, the CPU freq is 400 constant.
With SmartassV2, let it stay for 10 seconds, the CPU freq is randomly jumping from 200, 400 and sometimes 1000.
Well my question is, shouldn't Conservative be constantly using the lowest frequency among the other governors?
From what I saw it is Lazy which constantly used the lowest.
What do you think?
I know this test is not reliable at all, so sorry if it's just a waste of time.
glennkaonang said:
Bedalus, I did a little amateur test today.
I played some music with not-too-loud volume.
I keep my data ON, everything else is off.
The screen is always ON with lowest brightness because I'm looking at the CPU frequency used.
CPU min 200, max 1000.
I went to Processor settings and look at the CPU frequency used at the moment.
When I selected Conservative and let it stay for 10 seconds, the CPU freq is showing 1000 constant.
Then I selected Lazy and let it stay for another 10 seconds, the CPU freq is 400 constant.
With SmartassV2, let it stay for 10 seconds, the CPU freq is randomly jumping from 200, 400 and sometimes 1000.
Well my question is, shouldn't Conservative be constantly using the lowest frequency among the other governors?
From what I saw it is Lazy which constantly used the lowest.
What do you think?
I know this test is not reliable at all, so sorry if it's just a waste of time.
Click to expand...
Click to collapse
It sounds like quite an interesting test. I'm surprised at the conservative result. Which kernel are you on?

[Poll] AbyssNote Kernel * Favorite Governors *

Well I am sticking to one Rom and that's Crisekelo's like in my good 'n old sgs froyo times, but I like to test various kernels, when I have time...
Anyway I never saw a Mod Kernel with so many governors as the AbyssNote kernel, which I am testing right now..
Since there are many users out there that unlike me, already own the GNote for a long time and are way more experienced than me with this particular Kernel, I decided to start this Poll-thread so users can vote on their favorite governor and prehaps elaborate a little about it..
Thanks in advance..
Since Abyss Kernel is not working for my Note (overheat), I' at FM kernel with SavagedZen governor and vr I/0 Scheduler, butter smooth and stable, goes to deep sleep as it supposed to, sharp performance and moderate battery life. I know you prefer Abyss but just wanna let you know how the other kernel is working.
When I was on Abyss I was using abyssplug governor with and without undervolting. Hope you can get Abyss work for you, if you manage to do it without overheat I would appreciate any info.
have fun!
Oops ... you reacted fast ! The poll was not even ready
At the moment I don't prefer any kernel ( Only the rom) and on a device such as the GNote, I have a hunch that we dont need a super-optimized kernel with tons of iterations and that's why I always keep CF-Root and Speedmod handy, but I like the dedication and availability of AbyssNote developer, so I am giving it another try...
Since I have not enough time to play with the GNote as I did with the sgs, I am hoping that the AbyssNote users will give this specific input ....
iceangel1980 said:
"... Abyss Kernel is not working for my Note (overheat), I' at FM kernel with SavagedZen governor and vr I/0 Scheduler, butter smooth and stable, goes ..."
Click to expand...
Click to collapse
Hi betoNL,
just give the Abyss Kernel v3.7 another try. I am really satisfied with ABYSSPLUG governor and the SIO scheduler - great balance between performance and battery life. And it is also butter smooth and stable without any overclocking indeed ;-)
To be honest: I can't understand your problem with overheating. It could have its seeds in an app with unnormal behaviour or a constant hang-up in the background. Maybe you will execute this little turnaround at the next opportunity:
1. Charge your battery to 100%
2. Use a Taskkiller and kill every open task
3. Reboot in Recovery Mode and wipe voltage & battery stats (DON'T WIPE ANYTHING ELSE, PLEASE!)
4. Reboot yours system...
Best regards
[bs]
---------- Post added at 05:53 PM ---------- Previous post was at 05:50 PM ----------
Hi,
great poll... my vote goes to the abyssplug ;-)
Would be interesting to add users choice of the I/O scheduler.
What do you think about that little improvement?
Best regards
[bs]
As I said, I recommend AbyssPlug
I don't understand how abyssplug works. So I don't use it.
I do use lulzactive because it uses mostly my lowest frequency which drains battery the least when not stressed and highest frequency when stressed and basically ignores everything in between. It's been great.
can someone explain how abyssplug works? I've been searching, it only says modified hotplug. That doesn't tell me much.
Originally Posted by mancman
here the exact explanation on RootzWiki:
Wheatley governor
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....
The known ones are really good described here one the setcpu page:
the rest is nice described here:the rest is nice described here:
lazy (http://forum.xda-developers.com/show....php?t=1276092) - is ondemand but with an added option to stay longer on a certain frequency. This is due to the fact that some CPU's dont like too quick freq changes when sampling rate for decision making is set too low. See link for more.
lulzactive (http://tegrak2x.blogspot.com/2011/11...vernor-v2.html) - is 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.
lagfree (http://forum.xda-developers.com/show....php?t=1272933) - seems to be ondemand but with a lessend tendency to ramp up to 100% but rather also use steps available in between 0-100%.
intellidemand (freely translated from http://www.android-hilfe.de/root-hac...-governor.html) - behaves like ondemand when the system is under heavy use, it behaves differently when the system is mostly ideling. That mode is colled "browsing mode" or "browser mode" or whatever. It seems to be some sort of "intelligent" demand sensing/analysing ondemand governor.
smartassV2 - this one should be known. It's the same as smartass(V1) but tweaked. Same code author. I heard one should use smartassV2 instead of smartass when available.
ondemandx - is ondemand with an added sleep profile built-in. I believe all ...X kernels are the default kernels but with an added sleep profile.
AbyssPlug Governor:
Abyssplug governor is a modified hotplug governor
>>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.
__________________
After goin thru this thread I tried the AbyssPlug governor.
And indeed its good so far.
Me likes!!!!!!!!!
Sent from my GT-N7000 using xda premium
My choice is lulzactive.
Most important things for me are smoothness, fast wake&unlock and gaming performance. I don't care about the battery life that much so it seems a perfect choice for me.
pjm77 said:
My choice is lulzactive.
Most important things for me are smoothness, fast wake&unlock and gaming performance. I don't care about the battery life that much so it seems a perfect choice for me.
Click to expand...
Click to collapse
I like lulzactive, too!
What, no smartassv2 love here ? I found it at least as good as lulzactive for my usage.
My priorities - Fast response after sleep, smoothness, battery.
My governor choices on top were : SmartAssV2 (Currently using), AbyssPlus (Used it, liked it, later will compare to SmartAssV2) and Lulzactive (which is pretty good as well).
betoNL said:
Originally Posted by mancman
here the exact explanation on RootzWiki:
Wheatley governor
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....
The known ones are really good described here one the setcpu page:
the rest is nice described here:the rest is nice described here:
lazy (http://forum.xda-developers.com/show....php?t=1276092) - is ondemand but with an added option to stay longer on a certain frequency. This is due to the fact that some CPU's dont like too quick freq changes when sampling rate for decision making is set too low. See link for more.
lulzactive (http://tegrak2x.blogspot.com/2011/11...vernor-v2.html) - is 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.
lagfree (http://forum.xda-developers.com/show....php?t=1272933) - seems to be ondemand but with a lessend tendency to ramp up to 100% but rather also use steps available in between 0-100%.
intellidemand (freely translated from http://www.android-hilfe.de/root-hac...-governor.html) - behaves like ondemand when the system is under heavy use, it behaves differently when the system is mostly ideling. That mode is colled "browsing mode" or "browser mode" or whatever. It seems to be some sort of "intelligent" demand sensing/analysing ondemand governor.
smartassV2 - this one should be known. It's the same as smartass(V1) but tweaked. Same code author. I heard one should use smartassV2 instead of smartass when available.
ondemandx - is ondemand with an added sleep profile built-in. I believe all ...X kernels are the default kernels but with an added sleep profile.
AbyssPlug Governor:
Abyssplug governor is a modified hotplug governor
>>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.
__________________
Click to expand...
Click to collapse
Again, it's just a modified hotplug. What's modified about it?
betoNL said:
Oops ... you reacted fast ! The poll was not even ready
Click to expand...
Click to collapse
guess I was in chatty mood
BrainSex said:
\
To be honest: I can't understand your problem with overheating. It could have its seeds in an app with unnormal behaviour or a constant hang-up in the background. Maybe you will execute this little turnaround at the next opportunity:
1. Charge your battery to 100%
2. Use a Taskkiller and kill every open task
3. Reboot in Recovery Mode and wipe voltage & battery stats (DON'T WIPE ANYTHING ELSE, PLEASE!)
4. Reboot yours system...
Click to expand...
Click to collapse
Believe me I don't get it either and I'm pretty upset I can't use that kernel which is so valued by other android users. I was trying your advice and any other I could find in Abyss Kernel thread, nothing works for me. What is really funny I don't have any problems on other kernels. Well maybe I'm just unlucky this way. I'm thinking about getting my Note to Samsung for screen display exchange, so maybe they can do something about overheating too, maybe it's hardware related.
Thank you for your interest and advice
anyone using the app 2nd core and turning on dynamic hotplug?
It rly helps the battery
Might be useless to use along side abyssplug tho since it does the same thing
I use lulzactive, don't care about a little more battery drain
I use too 500mhz minimum speed @ 800mv, with it is pretty strange because 100 and 200 are not stable at that voltage and need 825, so having more speed I use less battery.
You don't use less battery because it's not only determined by voltage. Frequency us also a factor in power consumption, so 100MHz at 825 uses less battery for sure.
Sent from my superior GT-N7000 using Tapatalk
Zamboney said:
You don't use less battery because it's not only determined by voltage. Frequency us also a factor in power consumption, so 100MHz at 825 uses less battery for sure.
Sent from my superior GT-N7000 using Tapatalk
Click to expand...
Click to collapse
There's a post here somewhere here in the gnote forum that shows a study where they explain how 50 and 100MHz do consume more battery cause the CPU gets more stressed and takes longer to perform the task that would take less time and effort to accomplish at a higher frequency (or something like that)
Actually a higher frequency @ same voltage as a lower frequency would consume LESS battery because it will complete the task faster.
Sent from my GT-N7000 using Tapatalk
With my setup only ondemand really worked well, my second core scaling is always set to 2 cores enabled and I have a landscape setting for ADWex and any other governor will give me like 10-15fps when opening the app drawer.
Abyssplug fits my needs: I don't need so much power (no playstation-like games) but I use phone h24, from music to calls, from surfing to calendar/alarm...quite all stuff by BT headset and voice command. Battery drains slower than expected, my Note stays alive 'till night

Categories

Resources