To G1 the community.
Can I have your assistance in building a list of Current Roms, a Benchmark Speed Result and the settings you have your phone set at.
Benchmark Results are taking from 'Quadrant Standard' Market Link >https://market.android.com/details?id=com.aurorasoftworks.quadrant.ui.standard&feature=search_result
Here are my settings to kick things off, PLEASE NO CHAT, just pure stats & settings.
My hope is to find a ROM / Setup which is near as perfect and as fast as possible, I see a lot of post about an AWESOME Rom that is SUPER FAST but when I try it it either becomes unstable or is laggy.
The aim of this data gathering is try and achieve the best possible setup dependent on which ROM you are using.
COPY & PASTE & COMPLETE WITH YOUR PERSONAL SETUP.
ROM -
ANDROID VERSION -
KERNEL -
CPU -
MIN -
MAX -
COMPCACHE RAM -
JIT -
DITHERING -
VM HEAP SIZE -
LAUNCHER -
QUADRANT RESULT -
=-=-=-=-==-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
My Settings - based on a fresh SUPERWIPE and flash.
ROM - FROYO by LAZLO 5.2
ANDROID VERSION - 2.2.1
KERNEL - [email protected]#1
CPU - ONDEMAND -
MIN - 176
MAX - 595
COMPCACHE RAM - 18%
JIT - OFF
DITHERING - OFF
VM HEAP SIZE - 24m
LAUNCHER - LAUNCHER7
QUADRANT RESULT - 318
THANKS to all who provide details below.
My Settings - 4 weeks after flashing, no reboot for about 40 hours.
ROM - FROYO by LAZLO 5.2
ANDROID VERSION - 2.2.1
KERNEL - 2.6.34.8-cm6-
[email protected]#1
CPU - PERFORMANCE -
MIN - 176
MAX - 595
COMPCACHE RAM - ON
JIT - ON
DITHERING - ON
VM HEAP SIZE - 24m
LAUNCHER - Zeam Launcher
QUADRANT RESULT - 338
Phone G1
Radio/SPL 2825/1.33.0013d
ROM - COS-DS (self compile = repo sync 28th Apr a.m)
ANDROID VERSION - 2.3.3
KERNEL - 2.6.36.4-cos [email protected] #1
CPU - performance -
MIN - 245
MAX - 575
COMPCACHE RAM - OFF
JIT - ON
DITHERING - OFF
VM HEAP SIZE - 16m
LAUNCHER - ADW Ex (but launcher has nothing to do with it)
QUADRANT RESULT -500 , second run 442, third run 478 , 4th 512, 5th 525 = avg 491.4 ( discounting highest and lowest ) 496.666666667
Other- data data bind, ext4 no journal
Notes frequent reboots if usb is plugged in
with symlink /data/data/com.au... to /dev/ I get 569
its all down to I/O, no journal = faster r/w on sd-ext
Phone G1
Radio/SPL2825/1.33.0013d
ROM - CM7 Magpie 110324
ANDROID VERSION - 2.3.3
KERNEL - 2.6.36.4-s1-ezgb-v1
CPU - performance -
MIN - 245
MAX - 575
COMPCACHE RAM - OFF
JIT - ON
DITHERING - OFF
VM HEAP SIZE - 16m
LAUNCHER - ADW Ex (but launcher has nothing to do with it)
QUADRANT RESULT - 416
Other- data data bind, ext4 no journal
Notes steady as a rock (no issues with reboot when usb plugged)
ROM - SuperAOSP 6.0
Radio/SPL - 28.35/1.33.0013d (Noticed this added above and it made sense to include it)
ANDROID VERSION - 2.3.3
KERNEL - 2.6.35.9-SuperBler
CPU - On Demand
MIN - 128mhz
MAX - 614mhz
COMPCACHE RAM - Disabled
JIT - On
DITHERING - Off
VM HEAP SIZE - 16MB
LAUNCHER - LauncherPro (Yea, installed over stock ADW as usual)
QUADRANT RESULT - 338 (Seriously....... 500 above? -.- Seems a bit far fetched without moderate sacrifice of something valuable.
It's running as smooth as a peach though. I couldn't begin to ask for more.
you may also put a hyperlink to the rom you used. i think it is pretty usefull for those who see your results.
Chocolate Columbo said:
QUADRANT RESULT - 338 (Seriously....... 500 above? -.- Seems a bit far fetched without moderate sacrifice of something valuable.
Click to expand...
Click to collapse
Benchmarks (this one for sure) can be "cheated". That's why it says nothing what you score. My current tweaked Rom (Cya5.08) scores like sh*t on this benchmark but in practice it's faster than most GB-Roms. Especially after using the phone heavily for some time.
So while it's nice to brag about the scores but it doesn't necessarily mean the phone itself in use is any faster.
Thanks to all who replied - many people have read this thread but not left a comment I hope they found it as useful as I did.
It was more of a information gathering exercise than anything else.
Really helpful though.
Phone HTC Magic
Radio/SPL2825/1.33.0013d
ROM - ADS_Magpie_ezGingerbread 280411
ANDROID VERSION - 2.3.3
KERNEL - 2.6.36.4-s1-ezgb-v1
CPU - interactive
MIN - 176
MAX - 576
COMPCACHE RAM - 12MB (ZRAM)
JIT - ON
VM HEAP SIZE - 16m
LAUNCHER - Zeam Launcher 2.8.8
QUADRANT RESULT - 322
Other - No reboot / FC. A bit sluggish on startup, but better after a few minutes
ROM - ezGingerbread (self compiled about half an hour ago)
ANDROID VERSION - 2.3.3
KERNEL - 2.6.36.4-s1-ezgb-v1
CPU - conservative
MIN - 122
MAX - 537
COMPCACHE RAM - none
JIT - on
DITHERING - off
VM HEAP SIZE - 16m i think.... whatever is the stock setting
LAUNCHER - launcher2
QUADRANT RESULT - 315 (hm.... feels much faster.... oh well.)
Phone G1
Radio/SPL 2825/1.33.0013d
ROM - ADS_Magpie_ezGingerbread 280411
ANDROID VERSION - 2.3.3
KERNEL - 2.6.36.4-s1-ezgb-v1
CPU - performance
MIN - 245
MAX - 576
COMPCACHE RAM - OFF
JIT - ON
VM HEAP SIZE - 16m
LAUNCHER - ADW Ex
QUADRANT RESULT - 365 , 315 , 340 , 348 , 330
Other : ddb, ext4 with no Journal
Notes: I/O is around 200, half of what I get with COS.
Even after editing 05mountsd to mount as ext4 (not auto) I still get ~200
conclusion the high COS benchmarking is due to I/O tweaks
These tweaks may or may not improve real performance, but they certainly improve Quadrant Benchmark
in real use I find ADS more responsive than COS,
final conclusion
Quadrant is pants
PHONE - T-Mobile MyTouch 3G
RADIO/SPL - 2.22.28.25/1.33.0013d
ROM - CyanogenMod 6.1.0 Stable
ANDROID VERSION - 2.2.1
KERNEL - 2.6.35.13-farmatito-pershoot-ds+
CPU - ondemand
MIN - 245 MHz
MAX - 528 MHz
COMPCACHE RAM - OFF
JIT - OFF
VM HEAP SIZE - 16m
LAUNCHER - LauncherPro
QUADRANT RESULT - 316
ROM - COS-DS 4/27/11
ANDROID VERSION - Gingerbread 2.3.3
RADIO/SPL - 2708/1.33.0013d
KERNEL -2.6.36.4-cos [email protected] #1
CPU - on demand
MIN - 245
MAX - 528
COMPCACHE RAM - 18%
JIT - Enabled
DITHERING - Disabled
VM HEAP SIZE - 16m
LAUNCHER - Launcher Pro
QUADRANT RESULT - 324
Other: After a fresh superwipe.
ROM - COS-DS-04262011-Full
ANDROID VERSION - 2.3.3
KERNEL - 2.6.36.4-s1-cos
CPU - CONSERVATIVE
MIN - 128
MAX - 614
COMPCACHE RAM - DISABLED
JIT - ENABLED
DITHERING - DISABLED
VM HEAP SIZE - 12m
LAUNCHER - ADW (Stock)
QUADRANT RESULT - 354
ROM - COS-DS-07182011
ANDROID VERSION - 2.3.4
KERNEL - 2.6.36.4-s3-cos [email protected] #1
CPU - CONSERVATIVE
MIN - 245
MAX - 576
COMPCACHE RAM - DISABLED
JIT - ENABLED
DITHERING - DISABLED
VM HEAP SIZE - 16m
LAUNCHER - LauncherPro
QUADRANT RESULT - 470~520
SD-EXT enabled, data/data bind, no journal (that's what made it go to upper 400s)
T-Mobile MyTouch3G 1.2
ROM - SuperBler-MVZ-MD-4
ANDROID VERSION - 2.2.1
KERNEL - 2.6.34.8-cm6-biffmod ezterry
CPU - on demand
MIN - 245
MAX - 528
COMPCACHE RAM - no
JIT - no
DITHERING - no
VM HEAP SIZE - 16mb
LAUNCHER - Launcherpro
QUADRANT RESULT - 316
{
"lightbox_close": "Close",
"lightbox_next": "Next",
"lightbox_previous": "Previous",
"lightbox_error": "The requested content cannot be loaded. Please try again later.",
"lightbox_start_slideshow": "Start slideshow",
"lightbox_stop_slideshow": "Stop slideshow",
"lightbox_full_screen": "Full screen",
"lightbox_thumbnails": "Thumbnails",
"lightbox_download": "Download",
"lightbox_share": "Share",
"lightbox_zoom": "Zoom",
"lightbox_new_window": "New window",
"lightbox_toggle_sidebar": "Toggle sidebar"
}
Fluid UI | Lagless gaming | Battery friendly | Multitasking
Project Fluid is latest project im working on.
It consists from build.prop tweaks and init.d tweaks.
This is also a discussion thread you can always suggest me something.
If this project helped you in any way feel free to rate this thread 5* and thank me its free. Also comment how is your phone feeling with Project Fluid
NAVIGATION | Build.prop | Script | Other
CREDITS:
zeppelinrox
pikachu01
iONEx
LENAROX
smokin1337
imbawind
slaid480
smokin1337
[email protected]
darky
lpy
totiadrenalin
lambgx02
doomlord
Hero
if you think you should be here send me PM
Navigation | BUILD.PROP | Script | Other
REQUIREMENTS:
rooted phone
android 2.3+
INSTALLATION:
A)
Open "Root Explorer" and click the R/W
Go to /system/build.prop
Backup yout current build.prop
Long-press on Build.Prop and you’ll see a pop up
Text Editor
Type in those few line of words below into the last line of the text then save
reboot and enjoy
B)
Open "Root Explorer" and click R/W
Go to /system and copy build.prop to your sd card
Copy build.prop to your pc
Move build.prop again to /system and change permission
TWEAKS:
Qualcomm specific tweaks. Might cause reboot on other.
Code:
com.qc.hardware=1
debug.qc.hardware=true
debug.qctwa.preservebuf=1
debug.qctwa.statusbar=1
Unlock fps limit
Code:
debug.egl.swapinterval=0
Render UI with GPU and GPU tweaks
Code:
debug.composition.type=gpu
debug.egl.hw=1
debug.sf.hw=1
ro.sf.compbypass.enable=0
#enable harware egl profile
debug.egl.profiler=1
#Enable tile rendering
debug.enabletr=true
persist.sys.composition.type=gpu
#16BIT transparency , Smother Scrolling
persist.sys.use_16bpp_alpha=1
#3d performance
persist.android.strictmode=0
ro.min_pointer_dur=1
ro.secure=0
Fluid UI
Code:
persist.service.lgospd.enable=0
persist.service.pcsync.enable=0
Device supports EHRPD
Code:
ro.config.ehrpd=true
System prop for tethering denied
Code:
ro.tether.denied=false
Possible screen glitch fix
Code:
debug.gr.numframebuffers=3
Disable boot animation for faster boot
Code:
debug.sf.nobootanimation=1
Disable debugging notify icon on statusbar
Code:
persist.adb.notify=0
Enable Hardware 3D
Code:
hw3d.force=1
Phone will not wake up from hitting the volume rocker
Code:
ro.config.hwfeature_wakeupkey=0
Unlock phone by menu key
Code:
ro.config.hw_menu_unlockscreen=false
Save power while phone is in sleep mode
Code:
ro.ril.disable.power.collapse=1
Ringtone rings without delay
Code:
ro.telephony.call_ring.delay=0
The wifi scan interval in seconds so you can use a lower or higher value.
Code:
wifi.supplicant_scan_interval=180
Better scrolling responsiveness
Code:
windowsmgr.max_events_per_sec=90
ro.max.fling_velocity=12000
ro.min.fling_velocity=8000
Better touchscreen responsiveness
Code:
touch.pressure.scale=0.001
Support for ipv4 and ipv6.
Code:
persist.telephony.support.ipv4=1
persist.telephony.support.ipv6=1
Faster boot
Code:
persist.sys.shutdown.mode=hibernate
ro.config.hw_quickpoweron=true
Better battery life
Code:
ro.config.hw_fast_dormancy=1
ro.config.hw_power_saving=true
Enable 16 BIT
Code:
debug.fb.rgb565=1
VM tweak
Code:
ro.vold.umsdirtyratio=20
Disable Zygote loader
Code:
ro.wmt.blcr.enable=0
Better in call voice quality
Code:
ro.ril.enable.amr.wideband=1
Signal Tweaks
Code:
persist.cust.tel.eons=1
ro.ril.gprsclass=10
ro.ril.hsdpa.category=8
ro.ril.hsupa.category=6
ro.ril.hsxpa=1
Wireless Speed Tweaks
Code:
net.ipv4.ip_no_pmtu_disc=0
net.ipv4.route.flush=1
net.ipv4.tcp_ecn=0
net.ipv4.tcp_fack=1
net.ipv4.tcp_mem=187000 187000 187000
net.ipv4.tcp_moderate_rcvbuf=1
net.ipv4.tcp_no_metrics_save=1
net.ipv4.tcp_rfc1337=1
net.ipv4.tcp_rmem=4096 39000 187000
net.ipv4.tcp_sack=1
net.ipv4.tcp_timestamps=1
net.ipv4.tcp_window_scaling=1
net.ipv4.tcp_wmem=4096 39000 187000
net.tcp.buffersize.default=4096,87380,256960,4096, 16384,256960
net.tcp.buffersize.edge=4096,87380,256960,4096,163 84,256960
net.tcp.buffersize.gprs=4096,87380,256960,4096,163 84,256960
net.tcp.buffersize.umts=4096,87380,256960,4096,163 84,256960
net.tcp.buffersize.wifi=4096,87380,256960,4096,163 84,256960
Website Bypass
Code:
net.dns1=8.8.8.8
net.dns2=8.8.4.4
net.rmnet0.dns1=8.8.8.8
net.rmnet0.dns2=8.8.4.4
Graphics Enhancement
Code:
#Raise photo and video recording quality
ro.media.enc.hprof.vid.bps=8000000
ro.media.enc.hprof.vid.fps=75
#Raise JPG quality to 100%
ro.media.enc.jpeg.quality=100
ro.media.dec.aud.wma.enabled=1
ro.media.dec.vid.wmv.enabled=1
ro.media.cam.preview.fps=0
ro.media.codec_priority_for_thumb=so
DalvikVM
Code:
dalvik.gc.type=precise
dalvik.vm.dexopt-data-only=1
#Enables register map for tracking objects to garbage collect. Might give a little more RAM at the cost of a few CPU cycles.
dalvik.vm.dexopt-flags=m=v,o=y
dalvik.vm.jniopts=forcecopy
dalvik.vm.lockprof.threshold=500
dalvik.vm.stack-trace-file=/data/anr/traces.txt
dalvik.vm.verify-bytecode=false
Unknown functions
Code:
debug.kill_allocating_task=0
debug.overlayui.enable=0
dev.pm.dyn_samplingrate=1
ENFORCE_PROCESS_LIMIT=false
persist.sampling_profiler=0
ro.debuggable=1
ro.config.disable.hw_accel=false
ro.fb.mode=1
Not working
Code:
#debug.performance.tuning=1
#video.accelerate.hw=1
#persist.sys.ui.hw=1
#dalvik.vm.checkjni=false
#dalvik.vm.execution-mode=int:jit
#dalvik.vm.heapgrowthlimit=48m
#dalvik.vm.heapsize=64m
#Raise photo and video recording quality
#ro.media.dec.jpeg.memcap=20000000
#Enable surface dithering
#persist.sys.use_dithering=0
#Allow purging of assets
#persist.sys.purgeable_assets=0
#Force launcher into memory
#ro.HOME_APP_ADJ=1
# Disables data sent and logging.Only for HTC
#profiler.force_disable_err_rpt=1
#profiler.force_disable_ulog=1
#ro.config.nocheckin=1
#sleep mode for battery savings. 0 power collapse suspend, 1 power collapse (best), 2 apps go to sleep, 3 show clock and wait, 4 wait for interrupt
#pm.sleep_mode=1
#Fix some application issues/Disable kernel error logging
#ro.kernel.android.checkjni=0
#ro.kernel.checkjni=0
Navigation | Build.prop | SCRIPT | Other
REQUIREMENTS:
rooted phone
android 2.3+
kernel/rom with init.d support
5mb free in system
busybox
FEATURES:
VM tweaks | better battery life and performance
SD card tweaks | faster sd card read and write and mount speed
Full GPU rendering | Removes the android cpu rendering so the system can only use the gpu for rendering
Darky zipaling | Will zipalign all apk files to increase performance and reduce memory consumption
Battery tweaks | Tweaks that improve power consumpion
Kernel tweaks | better battery life and performance
Internet speed tweaks | Improves general browsing speed
disable logger | Disables the Android logger
Hacked host | ad-free browsing and applications
Reduced /dbdata, /data, /sdcard usage of *.db files and faster database access
IO scheduler tweaks
Cache cleared at every boot
It backups your old init.d scripts
Various tweaks
Manny other (scroll down)
INSTALLATION:
copy it on your sd card
go to recovery mod
flash it
reboot
enjoy
DOWNLOADS:
v1 (not flashable zip)
v1.1
v1.2
v1.3
v2
v3
v3.1
v3.2
CHANGELOG:
Code:
[LIST][*][SIZE="5"]v1:[/SIZE][SIZE="4"][LIST]
[*]initial release
[/LIST][/SIZE]
[*][SIZE="5"]v1.1[/SIZE]
[SIZE="4"][LIST]
[*]flashable .zip
[*]entropy seeder generator fixed
[*]removed touchscreen tweak (only samsung phone)
[*]now script will backup you old init.d script in /sdcard/Fluid_engine
[/LIST][/SIZE]
[*][SIZE="5"]v1.2[/SIZE]
[SIZE="4"][LIST]
[*]fixes
[/LIST][/SIZE]
[*][SIZE="5"]v1.3[/SIZE]
[SIZE="4"][LIST]
[*]fixes
[/LIST][/SIZE]
[*][SIZE="5"]v2[/SIZE]
[SIZE="4"][LIST]
[*]updated mpengine
[*]live entropy seeder
[*]removed some double lines
[*]changed some values
[/LIST][/SIZE]
[*][SIZE="5"]v3[/SIZE]
[SIZE="4"][LIST]
[*]fixes
[*]removed default scheduler
[*]hacked host for no ads
[*]various changes
[*]removed rpengine only cause it gets many updates and this way it will be easier for people to update it
[*]fully compatible with RPEngine, supercharger, seeder, crossbreder
[/LIST][/SIZE]
[*][SIZE="5"]v3.1[/SIZE]
[SIZE="4"][LIST]
[*]bug fixes [some values didnt apply]
[*]new values
[/LIST][/SIZE]
[*][SIZE="5"]v3.2[/SIZE]
[SIZE="4"][LIST]
[*]bug fixes
[*]new values
[*]removed renice apps
[*]now you are going to have more free ram
[*]since of more free ram your battery life will be better
[/LIST][/SIZE]
[/LIST]
Navigation | Build.prop | Script | OTHER
OPTIONAL:
Governor tweaks from thunderbolt script
remove .txt extension
move this to system/etc/init.d
set permission
Disable journalism
remove .txt extension
move this to system/etc/init.d
set permission
tweak for general apps to open instantly (ram usage might be higher)
remove .txt extension
move this to system/etc/init.d
set permission
removes lag from keyboard, phone, superuser and other most used apps
sqlite for gb/ics
remove .txt extension
move this to system/xbin
set permission
sqlite for jb
you move this to system/xbin
vsync activator
flash this zip
VSync synchronizes things. It tells the GPU to wait for the screen to finish its line by line drawing before loading the next frame.
The VSync pulse is now used to start all the processing for the next frame.
Fluid Libs
flash this zip
xperia 2011 devices only
collection of newest xperia libs
xperia T jelly bean libs, xperia S modified adreno libs, new egl libs, xperia V/T sound libs
INSTALLATION:
Copy it on your sd card
move to right place
set permission
reboot
EXPLANATIONS:
vm/block_dump
This enables block I/O debugging when set to a nonzero value. If you want to find out which process caused the disk to spin up (see /proc/sys/vm/laptop_mode), you can gather information by setting the flag.
When this flag is set, Linux reports all disk read and write operations that take place, and all block dirtyings done to files. This makes it possible to debug why a disk needs to spin up, and to increase battery life even more. The output of block_dump is written to the kernel output, and it can be retrieved using "dmesg". When you use block_dump and your kernel logging level also includes kernel debugging messages, you probably want to turn off klogd, otherwise the output of block_dump will be logged, causing disk activity that is not normally there.
vm/dirty_background_bytes
Contains the amount of dirty memory at which the pdflush background writeback daemon will start writeback.
If dirty_background_bytes is written, dirty_background_ratio becomes a function of its value (dirty_background_bytes / the amount of dirtyable system memory).
vm/dirty_background_ratio
Contains, as a percentage of total system memory, the number of pages at which the pdflush background writeback daemon will start writing out dirty data.
vm/dirty_bytes
Contains the amount of dirty memory at which a process generating disk writes will itself start writeback.
If dirty_bytes is written, dirty_ratio becomes a function of its value (dirty_bytes / the amount of dirtyable system memory).
Note: the minimum value allowed for dirty_bytes is two pages (in bytes); any value lower than this limit will be ignored and the old configuration will be retained.
vm/dirty_expire_centisecs and vm/dirty_writeback_centisecs
expire:
How old "dirty" data should be before the kernel considers it old enough to be written to disk. It is expressed in 100ths of a second.
writeback:
This is the interval of when the writeback daemons periodically wake up and write "old" data out to disk. It is expressed in 100ths of a second.
vm/dirty_ratio
Contains, as a percentage of total system memory, the number of pages at which a process which is generating disk writes will itself start writing out dirty data.
vm/drop_caches
Writing to this will cause the kernel to drop clean caches, dentries and inodes from memory, causing that memory to become free.
To free pagecache:
echo 1 > /proc/sys/vm/drop_caches
To free dentries and inodes:
echo 2 > /proc/sys/vm/drop_caches
To free pagecache, dentries and inodes:
echo 3 > /proc/sys/vm/drop_caches
As this is a non-destructive operation, and dirty objects are not freeable, the user should run "sync" first in order to make sure all cached objects are freed.
vm/laptop_mode
laptop_mode is a knob that controls "laptop mode". When the knob is set, any physical disk I/O (that might have caused the hard disk to spin up, see /proc/sys/vm/block_dump) causes Linux to flush all dirty blocks. The result of this is that after a disk has spun down, it will not be spun up anymore to write dirty blocks, because those blocks had already been written immediately after the most recent read operation. The value of the laptop_mode knob determines the time between the occurrence of disk I/O and when the flush is triggered. A sensible value for the knob is 5 seconds. Setting the knob to 0 disables laptop mode.
vm/lowmem_reserve_ratio
Ratio of total pages to free pages for each memory zone.
vm/max_map_count
This file contains the maximum number of memory map areas a process may have. Memory map areas are used as a side-effect of calling malloc, directly by mmap and mprotect, and also when loading shared libraries.
While most applications need less than a thousand maps, certain programs, particularly malloc debuggers, may consume lots of them, e.g., up to one or two maps per allocation.
The default value is 65536.
vm_min_free kbytes
This is used to force the Linux VM to keep a minimum number of kilobytes free. The VM uses this number to compute a pages_min value for each lowmem zone in the system. Each lowmem zone gets a number of reserved free pages based proportionally on its size.
vm/mmap_min_addr
This file indicates the amount of address space which a user process will be restricted from mmaping. Since kernel null dereference bugs could accidentally operate based on the information in the first couple of pages of memory userspace processes should not be allowed to write to them.
By default this value is set to 0 and no protections will be enforced by the security module. Setting this value to something like 64k will allow the vast majority of applications to work correctly and provide defense in depth against future potential kernel bugs.
vm/nr_pdflush_threads
The count of currently-running pdflush threads. This is a read-only value.
vm/oom_dump_tasks
Enables a system-wide task dump (excluding kernel threads) to be produced when the kernel performs an OOM-killing and includes such information as pid, uid, tgid, vm size, rss, cpu, oom_adj score, and name. This is helpful to determine why the OOM killer was invoked and to identify the rogue task that caused it.
If this is set to zero, this information is suppressed. On very large systems with thousands of tasks it may not be feasible to dump the memory state information for each one. Such systems should not be forced to incur a performance penalty in OOM conditions when the information may not be desired.
If this is set to non-zero, this information is shown whenever the OOM killer actually kills a memory-hogging task.
The default value is 0.
vm/oom_kill_allocating_task
This enables or disables killing the OOM-triggering task in out-of-memory situations.
If this is set to zero, the OOM killer will scan through the entire tasklist and select a task based on heuristics to kill. This normally selects a rogue memory-hogging task that frees up a large amount of memory when killed.
If this is set to non-zero, the OOM killer simply kills the task that triggered the out-of-memory condition. This avoids the expensive tasklist scan.
If panic_on_oom is selected, it takes precedence over whatever value is used in oom_kill_allocating_task.
The default value is 0.
vm overcommit memory
This controls overcommit of system memory, possibly allowing processes to allocate (but not use) more memory than is actually available.
0 - Heuristic overcommit handling. Obvious overcommits of address space are refused. Used for a typical system. It ensures a seriously wild allocation fails while allowing overcommit to reduce swap usage. root is allowed to allocate slighly more memory in this mode. This is the default.
1 - Always overcommit. Appropriate for some scientific applications.
2 - Don't overcommit. The total address space commit for the system is not permitted to exceed swap plus a configurable percentage (default is 50) of physical RAM. Depending on the percentage you use, in most situations this means a process will not be killed while attempting to use already-allocated memory but will receive errors on memory allocation as appropriate.
vm overcommit ratio
Percentage of physical memory size to include in overcommit calculations.
Memory allocation limit = swapspace + physmem * (overcommit_ratio / 100)
swapspace = total size of all swap areas
physmem = size of physical memory in system
vm/page-cluster
This controls the number of pages which are written to swap in a single attempt. The swap I/O size.
It is a logarithmic value - setting it to zero means "1 page", setting it to 1 means "2 pages", setting it to 2 means "4 pages", etc.
The default value is three (eight pages at a time). There may be some small benefits in tuning this to a different value if your workload is swap-intensive.
vm/panic_on_oom
This enables or disables panic on out-of-memory feature. If this is set to 1, the kernel panics when out-of-memory happens. If this is set to 0, the kernel will kill some rogue process, by calling oom_kill().
Usually, oom_killer can kill rogue processes and system will survive. If you want to panic the system rather than killing rogue processes, set this to 1.
The default value is 0.
Panic is a system error that is detected by the kernel.
vm/percpu_pagelist_fraction
This is the fraction of pages at most (high mark pcp->high) in each zone that are allocated for each per cpu page list. The min value for this is 8. It means that we don't allow more than 1/8th of pages in each zone to be allocated in any single per_cpu_pagelist. This entry only changes the value of hot per cpu pagelists. User can specify a number like 100 to allocate 1/100th of each zone to each per cpu page list.
The batch value of each per cpu pagelist is also updated as a result. It is set to pcp->high / 4. The upper limit of batch is (PAGE_SHIFT * 8).
The initial value is zero. Kernel does not use this value at boot time to set the high water marks for each per cpu page list.
vm/scan_unevictable_pages
When written to, this tunable will initiate a scan of individual or all zones' unevictable lists and move any pages that have become evictable onto the respective zone's inactive list, where shrink_inactive_list() will deal with them. If evictable pages are found in unevictable lru, kernel will print filenames and file offsets of those pages.
vm/swappiness
swappiness is a parameter which sets the kernel's balance between reclaiming pages from the page cache and swapping process memory. The default value is 60.
If you want kernel to swap out more process memory and thus cache more file contents increase the value. Otherwise, if you would like kernel to swap less decrease it.
more information
vm vfs cache presure
Now here is where it gets interesting! File system cache (dentry/inode) is really more important than the block cache above in dirty ratio and dirty background ratio, so we really want the kernel to use up much more of the RAM for file system cache, this will increas the performance of the system without sacrificing performance at the application level. The default value is 100, as a percentage, and what you want to do is lower the value to tell the kernel to favor the file system cache and not drop them aggressively.
LINKS TO IMPORTANT THREADS:
Thunderbolt
incompatible
Adrenaline engine
incompatible
Adrenaline boost
use it only if you are on gingerbread
Ultimate jar power tools
compatible and suggested
Supercharger
incompatible
BANNERS:
great!
I think you almost categorized all existing build.prop tweaks on the net... the list just goes on and on joking!
If you should need any help....
keep it up!
iONEx said:
great!
I think you almost categorized all existing build.prop tweaks on the net... the list just goes on and on joking!
If you should need any help....
keep it up!
Click to expand...
Click to collapse
I did like 30 reboots to test those tweaks
i commented out tweaks which dont work on ics
every group is in alphabetical order
no double lines
i plan to explain lines and which values can we use
but first need to finish script
Does this work on jelly bean 4.1.2? Is smoother performance noticeable after this tweaks?
Echelonex said:
Does this work on jelly bean 4.1.2? Is smoother performance noticeable after this tweaks?
Click to expand...
Click to collapse
+1 ... want to know this too
Echelonex said:
Does this work on jelly bean 4.1.2? Is smoother performance noticeable after this tweaks?
Click to expand...
Click to collapse
yes they work on jb
but not all of them
but it wont dmg your phone if u have ones that dont work
OK, I opened up those two guides and with triumphant smile I started to check which one of BUSTED ones appear in your tweak and you've already commented them! no fun for me
Can I use this tweaks on cm10?
Sent from my Xperia Mini using xda premium
working on jb
najodleglejszy said:
OK, I opened up those two guides and with triumphant smile I started to check which one of BUSTED ones appear in your tweak and you've already commented them! no fun for me
Click to expand...
Click to collapse
this really took time to organize it, remove every double line, to comment not working ones
and i did reboot for every new line (something like 30 reboots)
this one was ment for ics
later i will add gb and jb
but first i will finish script
Fluid Engine
mv_style said:
this really took time to organize it, remove every double line, to comment not working ones
and i did reboot for every new line (something like 30 reboots)
this one was ment for ics
later i will add gb and jb
but first i will finish script
Fluid Engine
Click to expand...
Click to collapse
well, big plus for not copying placebo tweaks it really shows that you care, so I can't wait to see the full mod released!
I mean, of course I can, take your time to polish it
hey buddy,
you might wanna check this line: ro.telephony.call_ring.delay=0
I've found out, atleast on GB that it causes this bug with ringtones not repeating.
If you get a call, the ringtone rings one time only and stops.
Don't know about ICS, but just to be sure test it
iONEx said:
hey buddy,
you might wanna check this line: ro.telephony.call_ring.delay=0
I've found out, atleast on GB that it causes this bug with ringtones not repeating.
If you get a call, the ringtone rings one time only and stops.
Don't know about ICS, but just to be sure test it
Click to expand...
Click to collapse
ok thanks for info
i will check that tommorow
working on something else now
_________
Actually that line was ment for that
i will update op with info
i was working on Fluid Engine for long time today
i might finish it tommorow
Do any of these overlaps with Pimp My Rom prop tweaks? Thanks for these btw :highfive:
Final stage just few more things do:
i need to see if there are any double lines and such
what it offers you?
-- all things from unlimited boost but with no double lines, better values and new tweaks
-- i included some things from lazerdroid which werent included
-- full gpu rendering (fluid ui, smoother gaming)
it will have few optional tweaks which u can flash later:
-- disable journalism
-- governor tweaks (for users with custom kernel)
-- tweak for most used apps to open faster
in updates i will search for better values, and new lines
i think i wont need to do rework it again cause it organized very well
_________________
testing stage
Comparision:
*all test are on hyouka
1.With project fluid build.prop tweaks+gpu rendering+adreno.config tweaks
gaming is preety smooth (in 2min of gaming no lags only one minor almost which was almost unnoticable)
but it took long time for game 2 load
ui is preety smooth and fluid 2.
game tested was subway surfers
2. with fluid engine and previous tweaks
phone boots faster, gaming is even smoother
game has loaded for 2sec (showed image)
3.test will be soon with all optional tweaks
it will be released today (i hope)
i still have some things to finish but first i want to relax cause i was working on it from 19:00 until 2:00
and today for 3 hours