Compcache

vee (Talk | contribs)
(New page: Compcache or Ramzswap, hitherto referred as ramz is a method for using a chunk of 'normal' ram and using it as a compressed virtual memory(VM) swap space. That is, we use ram as virtual r...)
Newer edit →

Revision as of 10:10, 28 May 2012

Compcache or Ramzswap, hitherto referred as ramz is a method for using a chunk of 'normal' ram and using it as a compressed virtual memory(VM) swap space. That is, we use ram as virtual ram by compressing the contents on the fly. This is in order to squeeze as much from the ram space as possible.


N8x0

To be added by a wild N8x0 user...


N900

Lack of ram is seen as one on the main performance bottlenecks an N900 user has to contend with. In it's stock set up the N900 is prone to having massive swap space coronerys. This can leads to poor performance, diminished user sexual function and in the worst cases, a reboot due to watchdog timers becoming ignored. This is generally alleviated in 1 of 3 ways.


1. Install 'swappolube'


Swappolube is a set of VM tweaks initially dreamed up by the user Hawaii. For MOST users the installation of swappolube from the repositories and applying the default settings will suffice to alleviate the problem.


2. Swap on micro SD card(uSD)


It has been found that an easy way to alleviate eMMC contention is to move the swap space to the uSD card[1].


3. Swap fragmentation


It has been found that as the swap space fills up the OS is unable to allocate continuous space on the swap space. This leads to poor performance. The package ereswap was created to try and alleviate this.


4. Compcache


The articles namesake. The use of compcache has been a contentious issue. Most users have found it to cause extremely poor system performance as soon as the ramz space gets filled, which is pretty quick. It has been suggested that by some users that the 'extreme' settings of swappolube that most users run are utterly wrong for ramz. Swappolube sets the VM to swap little bits rarely. This does not work for ramz. The opposite approach for ramz must be taken, the device must swap a lot, all the time. AS the swapping is to ram, there will be little penalty in speed. Although it has been suggested that there will perhaps be a slight penalty in processor use (de/compression of ramz) and thus battery life.


Caveats!


While ramz does work on kernel power version 49 (KP49) it is highly recommended that you use KP50!

Ramz requires a disksize that is specified in KB in powers of 2. Acceptable sizes are:

Ramzsize English mofo
2048 2MB
4096 4MB
8192 8MB
16384 16MB
32768 32MB
65536 64MB
131072 128MB

You MUST have swap enabled on a physical disk before enabling ramz or your n900 WILL insta-crash potentially taking your file system with it!


How to enable compcache


To enable compcache you must enter the following command, the following will create a ramz disk of 64MB:

insmod /lib/modules/current/ramzswap.ko disksize_kb=65536

Once enabled you must tell the system to use the ramz disk:

swapon /dev/ramzswap0

For any of this to be any benefit the ramz disk needs to have a higher priority than the 'physical' swap space. Make sure ALL applications are closed and disable then re-enable your physical swap. On a stock setup (swap on eMMC) you can do this:

swapoff /dev/mmcblk0p3 && sleep 1 && swapon /dev/mmcblk0p3

For other setups i.e. when you have swap on uSD you must substitute 'mmcblk0p3' with the location of your swap space. (If you swap partition is the second partition on the uSD then it will be 'mmcblk1p2').

You can now check you have the appropriate partitions with:

cat /proc/swaps
Filename				Type		Size	Used	Priority
/dev/mmcblk0p3                          partition	786424	64476	-2
/dev/ramzswap0                          partition	65528	61572	-1

You can see ramzswap is 64MB AND with a higher priority than mmcblk0p3.

Now you must change you VM settings to effectivly use the new ramz setup. The following settings have been found to work with 32MB, 64MB and 128MB ramz sizes. They are a work in progress and will be updated as they are tuned to the authors workload (heavy user, treating n900 as a pocket laptop as oppose to merely a phone).

echo 3 > /proc/sys/vm/dirty_ratio
echo 3 > /proc/sys/vm/dirty_background_ratio
echo 100 > /proc/sys/vm/dirty_writeback_centisecs 
echo 100 > /proc/sys/vm/dirty_expire_centisecs 
echo 32 > /proc/sys/vm/min_free_kbytes 
echo 95 > /proc/sys/vm/swappiness 
echo 200 > /proc/sys/vm/vfs_cache_pressure 
echo 0 > /proc/sys/vm/page-cluster
echo 4 > /sys/block/mmcblk0/queue/nr_requests
echo 4 > /sys/block/mmcblk1/queue/nr_requests


How to do this all at once

Paste the below code into a root xterm.

insmod /lib/modules/current/ramzswap.ko disksize_kb=65536 && sleep 1
swapon /dev/ramzswap0 && sleep 1
swapoff /dev/mmcblk0p3 && sleep 1 && swapon /dev/mmcblk0p3 && sleep 1
echo 3 > /proc/sys/vm/dirty_ratio
echo 3 > /proc/sys/vm/dirty_background_ratio
echo 100 > /proc/sys/vm/dirty_writeback_centisecs 
echo 100 > /proc/sys/vm/dirty_expire_centisecs 
echo 32 > /proc/sys/vm/min_free_kbytes 
echo 95 > /proc/sys/vm/swappiness 
echo 200 > /proc/sys/vm/vfs_cache_pressure 
echo 0 > /proc/sys/vm/page-cluster
echo 4 > /sys/block/mmcblk0/queue/nr_requests
echo 4 > /sys/block/mmcblk1/queue/nr_requests


Making all this happen automatically


There is a package called swapset[2], it claims to setup swaps and the ramz module automatically. The author of this article has not used it and thus cannot vouch for it's effectiveness. Using swapset AND putting the above settings into swappolube would probably cause all of the above to work automatically.

N9/50

To be added by an ardent masochist.