OS: Tuning Completely Fair scheduler CFS - Revision history

Onnowpurbo at 04:57, 12 April 2014

2014-04-12T04:57:32Z

← Older revision		Revision as of 04:57, 12 April 2014
Line 25:		Line 25:

	Jika kita ingin agar perubahan ini permanen, kita perlu melakukan modifikasi parameter tersebut pada file /etc/sysctl.conf dan jalankan perintah sysctl -p command.		Jika kita ingin agar perubahan ini permanen, kita perlu melakukan modifikasi parameter tersebut pada file /etc/sysctl.conf dan jalankan perintah sysctl -p command.

			Untuk melihat parameter kernel yang ada dapat menggunakan perintah

			# sysctl -A \| more

			atau

			# sysctl -a \| more

Onnowpurbo at 04:35, 12 April 2014

2014-04-12T04:35:44Z

← Older revision		Revision as of 04:35, 12 April 2014
Line 4:		Line 4:
	Dalam Linux Completely Fair scheduler (CFS) terdapat parameter yang dapat kita atur untuk menyesuaikan dengan kebutuhan kita.		Dalam Linux Completely Fair scheduler (CFS) terdapat parameter yang dapat kita atur untuk menyesuaikan dengan kebutuhan kita.

	Parameter berikut dapat di akses melalui file sistem proc. Nilai default (dalam nanoseconds). Contoh ~~paramete~~ adalah sebagai berikut:		Parameter berikut dapat di akses melalui file sistem proc. Nilai default (dalam nanoseconds). Contoh parameter adalah sebagai berikut:

	* sched_min_granularity_ns (16000000): Minimum preemption granularity untuk task yang processor-bound. Task di garansi untuk run / jalan minimal waktu sched_min_granularity_ns sebelum di preempt.		* sched_min_granularity_ns (16000000): Minimum preemption granularity untuk task yang processor-bound. Task di garansi untuk run / jalan minimal waktu sched_min_granularity_ns sebelum di preempt.

Onnowpurbo: /* Pranala Menarik */

2013-04-07T06:43:23Z

Pranala Menarik

@@ Line 35: / Line 35: @@
 * [[Linux]]
 * [[Ubuntu]]
 * [[Sistem Operasi]]
 * [[Kernel]]
 * [[Compile Kernel]]
 * [[Compile Kernel: Konfigurasi Kernel]]
-* [[Kernel: Anatomi Kernel Source]]
-* [[OS: Linux Kernel]]
+===Remaster Linux===
 * [[OS: Parameter Kernel Default]]
 * [[OS: Kernel Scheduler]]
 * [[OS: Complete Teori Tuning Kernel Scheduler]]
 * [[OS: Complete Teori Tuning I/O Performance]]
-* [[OS: Tuning Kernel Scheduler]]
-* [[OS: Tuning Completely Fair Queueing CFQ I/O scheduler]]
+====Tuning Manajemen Memory====
-* [[OS: Tuning Completely Fair scheduler CFS]]
 * [[OS: Build in Monitoring Tool]]
 * [[Linux Benchmarking]]
 * [[OS: Benchmarking menggunakan UnixBench]]
 * [[OS: Benchmarking menggunakan LLCBench]]

Onnowpurbo at 01:28, 2 April 2013

2013-04-02T01:28:20Z

← Older revision		Revision as of 01:28, 2 April 2013
Line 4:		Line 4:
	Dalam Linux Completely Fair scheduler (CFS) terdapat parameter yang dapat kita atur untuk menyesuaikan dengan kebutuhan kita.		Dalam Linux Completely Fair scheduler (CFS) terdapat parameter yang dapat kita atur untuk menyesuaikan dengan kebutuhan kita.

	Parameter berikut dapat di akses melalui file sistem proc. Nilai default (dalam nanoseconds Contoh paramete adalah sebagai berikut:		Parameter berikut dapat di akses melalui file sistem proc. Nilai default (dalam nanoseconds). Contoh paramete adalah sebagai berikut:

	* sched_min_granularity_ns (16000000): Minimum preemption granularity ~~for~~ processor-bound ~~tasks~~. ~~Tasks are guaranteed to~~ run ~~for this minimum time before they are preempted~~.		* sched_min_granularity_ns (16000000): Minimum preemption granularity untuk task yang processor-bound. Task di garansi untuk run / jalan minimal waktu sched_min_granularity_ns sebelum di preempt.
	* sched_latency_ns (80000000): ~~Period over which~~ CFQ ~~tries to fairly~~ schedule ~~the tasks on the~~ runqueue. ~~All of the tasks on the~~ runqueue ~~are guaranteed to be scheduled once within this period~~.		* sched_latency_ns (80000000): Perioda dimana CFQ akan mencoba untuk melakukan schedule secara fair untuk task yang ada di runqueue. Semua task di runqueue akan di garansi jalan minimal satu kali dalam perioda tersebut.
	* sched_wakeup_granularity_ns (20000000): ~~Ability of tasks being woken to~~ preempt ~~the current~~ task. ~~The smaller the value~~, ~~the easier it is for the~~ task ~~to force the preemption~~.		* sched_wakeup_granularity_ns (20000000): Kemampuan untuk task yang bangun untuk mem-preempt task yang sedang berjalan. Semakin kecil nilainya, semakin mudah untuk sebuah task memaksa preempt task yang sedang berjalan.

	Untuk memverifikasi nilai dari masing-masing parameter, gunakan perintah berikut:		Untuk memverifikasi nilai dari masing-masing parameter, gunakan perintah berikut:
Line 18:		Line 18:
	# echo 20000 > /proc/sys/kernel/sched_latency_ns		# echo 20000 > /proc/sys/kernel/sched_latency_ns

	~~In the~~ test ~~environment~~, ~~best results were achieved with the following values for these three parameters~~:		Dalam salah satu lingkungan test, hasil terbaik nampaknya akan di peroleh untuk nilai parameter berikut:

	kernel.sched_min_granularity_ns = 100000		kernel.sched_min_granularity_ns = 100000
Line 24:		Line 24:
	kernel.sched_latency_ns = 1000000		kernel.sched_latency_ns = 1000000

	~~If you want to make these changes permanent~~, ~~you can modify these parameters in the~~ /etc/sysctl.conf ~~file and run the~~ sysctl -p command.		Jika kita ingin agar perubahan ini permanen, kita perlu melakukan modifikasi parameter tersebut pada file /etc/sysctl.conf dan jalankan perintah sysctl -p command.

Onnowpurbo at 04:16, 1 April 2013

2013-04-01T04:16:56Z

← Older revision		Revision as of 04:16, 1 April 2013
Line 4:		Line 4:
	Dalam Linux Completely Fair scheduler (CFS) terdapat parameter yang dapat kita atur untuk menyesuaikan dengan kebutuhan kita.		Dalam Linux Completely Fair scheduler (CFS) terdapat parameter yang dapat kita atur untuk menyesuaikan dengan kebutuhan kita.

	~~The following parameters can be accessed through the~~ proc ~~file system~~. ~~The~~ default ~~values~~ (in nanoseconds~~) of these parameters from SLES 11 SP1 are shown in parentheses.~~		Parameter berikut dapat di akses melalui file sistem proc. Nilai default (dalam nanoseconds Contoh paramete adalah sebagai berikut:

	sched_min_granularity_ns (16000000): Minimum preemption granularity for processor-bound tasks. Tasks are guaranteed to run for this minimum time before they are preempted.		* sched_min_granularity_ns (16000000): Minimum preemption granularity for processor-bound tasks. Tasks are guaranteed to run for this minimum time before they are preempted.
	sched_latency_ns (80000000): Period over which CFQ tries to fairly schedule the tasks on the runqueue. All of the tasks on the runqueue are guaranteed to be scheduled once within this period.		* sched_latency_ns (80000000): Period over which CFQ tries to fairly schedule the tasks on the runqueue. All of the tasks on the runqueue are guaranteed to be scheduled once within this period.
	sched_wakeup_granularity_ns (20000000): Ability of tasks being woken to preempt the current task. The smaller the value, the easier it is for the task to force the preemption.		* sched_wakeup_granularity_ns (20000000): Ability of tasks being woken to preempt the current task. The smaller the value, the easier it is for the task to force the preemption.

	~~To verify the value of each~~ parameter, ~~use the following command~~:		Untuk memverifikasi nilai dari masing-masing parameter, gunakan perintah berikut:

	# cat /proc/sys/kernel/sched_latency_ns		# cat /proc/sys/kernel/sched_latency_ns

	~~To modify the value of each~~ parameter, ~~use the following command:~~		Untuk memodifikasi nilai dari masing-masing parameter, gunakan perintah berikut (misalnya)

	# echo 20000 > /proc/sys/kernel/sched_latency_ns		# echo 20000 > /proc/sys/kernel/sched_latency_ns

Onnowpurbo at 04:12, 31 March 2013

2013-03-31T04:12:55Z

← Older revision		Revision as of 04:12, 31 March 2013
Line 2:		Line 2:


	~~The~~ Linux Completely Fair scheduler (CFS) ~~includes parameters that you can adjust to fit your specific needs~~.		Dalam Linux Completely Fair scheduler (CFS) terdapat parameter yang dapat kita atur untuk menyesuaikan dengan kebutuhan kita.

	The following parameters can be accessed through the proc file system. The default values (in nanoseconds) of these parameters from SLES 11 SP1 are shown in parentheses.		The following parameters can be accessed through the proc file system. The default values (in nanoseconds) of these parameters from SLES 11 SP1 are shown in parentheses.
Line 12:		Line 12:
	To verify the value of each parameter, use the following command:		To verify the value of each parameter, use the following command:

	# cat /proc/sys/kernel/sched_latency_ns		# cat /proc/sys/kernel/sched_latency_ns

	To modify the value of each parameter, use the following command:		To modify the value of each parameter, use the following command:

	# echo 20000 > /proc/sys/kernel/sched_latency_ns		# echo 20000 > /proc/sys/kernel/sched_latency_ns

	In the test environment, best results were achieved with the following values for these three parameters:		In the test environment, best results were achieved with the following values for these three parameters:

	kernel.sched_min_granularity_ns = 100000		kernel.sched_min_granularity_ns = 100000
	kernel.sched_wakeup_granularity_ns = 25000		kernel.sched_wakeup_granularity_ns = 25000
	kernel.sched_latency_ns = 1000000		kernel.sched_latency_ns = 1000000

	If you want to make these changes permanent, you can modify these parameters in the /etc/sysctl.conf file and run the sysctl -p command.		If you want to make these changes permanent, you can modify these parameters in the /etc/sysctl.conf file and run the sysctl -p command.

Onnowpurbo: /* Pranala Menarik */

2013-03-21T13:18:00Z

Pranala Menarik

← Older revision		Revision as of 13:18, 21 March 2013
Line 40:		Line 40:
	* [[Ubuntu]]		* [[Ubuntu]]
	* [[Sistem Operasi]]		* [[Sistem Operasi]]
			* [[Kernel]]
			* [[Compile Kernel]]
			* [[Compile Kernel: Konfigurasi Kernel]]
			* [[Kernel: Anatomi Kernel Source]]
	* [[OS: Linux Kernel]]		* [[OS: Linux Kernel]]
			* [[OS: Parameter Kernel Default]]
	* [[OS: Kernel Scheduler]]		* [[OS: Kernel Scheduler]]
			* [[OS: Complete Teori Tuning Kernel Scheduler]]
			* [[OS: Complete Teori Tuning I/O Performance]]
	* [[OS: Tuning Kernel Scheduler]]		* [[OS: Tuning Kernel Scheduler]]
	* [[OS: Tuning Completely Fair Queueing CFQ I/O scheduler]]		* [[OS: Tuning Completely Fair Queueing CFQ I/O scheduler]]
	* [[OS: Tuning Completely Fair scheduler CFS]]		* [[OS: Tuning Completely Fair scheduler CFS]]
	* [[OS: Build in Monitoring Tool]]		* [[OS: Build in Monitoring Tool]]
			* [[Linux Benchmarking]]
			* [[OS: Benchmarking menggunakan UnixBench]]
			* [[OS: Benchmarking menggunakan LLCBench]]
			* [[OS: Mengerti System Call]]
			* [[OS: Membuat Kernel Modul]]

Onnowpurbo: /* Pranala Menarik */

2013-03-08T12:57:34Z

Pranala Menarik

← Older revision		Revision as of 12:57, 8 March 2013
Line 36:		Line 36:

	==Pranala Menarik==		==Pranala Menarik==

			* [[Linux]]
			* [[Ubuntu]]
			* [[Sistem Operasi]]
			* [[OS: Linux Kernel]]
			* [[OS: Kernel Scheduler]]
			* [[OS: Tuning Kernel Scheduler]]
			* [[OS: Tuning Completely Fair Queueing CFQ I/O scheduler]]
			* [[OS: Tuning Completely Fair scheduler CFS]]
			* [[OS: Build in Monitoring Tool]]

Onnowpurbo: New page: Sumber: http://publib.boulder.ibm.com/infocenter/lnxinfo/v3r0m0/index.jsp?topic=%2Fliaai%2Fsaptuning%2Fsaptuningadjust.htm The Linux Completely Fair scheduler (CFS) includes parameters t...

2013-03-08T12:54:45Z

New page: Sumber: http://publib.boulder.ibm.com/infocenter/lnxinfo/v3r0m0/index.jsp?topic=%2Fliaai%2Fsaptuning%2Fsaptuningadjust.htm The Linux Completely Fair scheduler (CFS) includes parameters t...

New page

Sumber: http://publib.boulder.ibm.com/infocenter/lnxinfo/v3r0m0/index.jsp?topic=%2Fliaai%2Fsaptuning%2Fsaptuningadjust.htm

The Linux Completely Fair scheduler (CFS) includes parameters that you can adjust to fit your specific needs.

The following parameters can be accessed through the proc file system. The default values (in nanoseconds) of these parameters from SLES 11 SP1 are shown in parentheses.

sched_min_granularity_ns (16000000): Minimum preemption granularity for processor-bound tasks. Tasks are guaranteed to run for this minimum time before they are preempted.
sched_latency_ns (80000000): Period over which CFQ tries to fairly schedule the tasks on the runqueue. All of the tasks on the runqueue are guaranteed to be scheduled once within this period.
sched_wakeup_granularity_ns (20000000): Ability of tasks being woken to preempt the current task. The smaller the value, the easier it is for the task to force the preemption.

To verify the value of each parameter, use the following command:

# cat /proc/sys/kernel/sched_latency_ns

To modify the value of each parameter, use the following command:

# echo 20000 > /proc/sys/kernel/sched_latency_ns

In the test environment, best results were achieved with the following values for these three parameters:

kernel.sched_min_granularity_ns = 100000
kernel.sched_wakeup_granularity_ns = 25000
kernel.sched_latency_ns = 1000000

If you want to make these changes permanent, you can modify these parameters in the /etc/sysctl.conf file and run the sysctl -p command.

==Referensi==

* http://publib.boulder.ibm.com/infocenter/lnxinfo/v3r0m0/index.jsp?topic=%2Fliaai%2Fsaptuning%2Fsaptuningadjust.htm

==Pranala Menarik==