Load balancing Sung joon Choi RealTime Operating Systems Lab Seoul National University 20110915 Contents Load balancing Purpose Definition General cases Active load balancing Passive ID: 311704
Download Presentation The PPT/PDF document "Load Balance in Linux 2.6.32" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Load Balance in Linux 2.6.32 Load balancing
Sung-
joon
Choi
Real-Time Operating Systems Lab.
Seoul National University
2011-09-15Slide2
ContentsLoad balancingPurposeDefinitionGeneral casesActive load balancing
Passive
load balancingSpecial casesExecution of a new taskCPU’s shut down or intentionally being IDLELimitation
Load Balance in Linux 2.6.32Slide3
Load BalancingPurpose시스템에 코어 수보다 많은 수의 작업(task)이 있는 한, 모든 코어가
IDLE
상태
없이 수행하도록 조절Mechanism코어 간에 작업량 차이가 크지 않도록 조절DefinitionLoad balancing
SMP
구조에서 각 코어가 균등한 작업량
(load)을 가지도록 조절하는 것Load코어의 run-queue 가 갖는 모든 task 들의 weight 를 더한 값
Load Balance in Linux 2.6.32Slide4
Load BalancingDefinition (cont.)Idlest run-queueA run-queue that has the minimum load among the coresBusiest run-queueA run-queue that has the maximum value which is scale factor “load / (core’s power)”
모든
코어의 power 가 동일하다면 maximum load 를 갖는 코어의 run-queue 를 의미한다이종의 프로세서를 사용하는 시스템이라면 각 코어의
power
가 다를수도 있다
. 일반적으로 power는 capacity 또는 작업수행능력을 의미한다. Load Balance in Linux 2.6.32Slide5
ContentsLoad balancingPurposeDefinitionGeneral cases (mainly focused part)Active load balancing
Passive load balancing
Special cases
Execution of a new taskCPU’s shut down or intentionally being IDLELimitation
Load Balance in Linux 2.6.32Slide6
General
Cases
Active Load Balancing
Load Balance in Linux 2.6.32
Run-queue
Run-queue
Current task
Current task
Core 0
Core 1
Task 1
Task 2
Task 4
Task 3
Task 5
Run-queue
Run-queue
Current task
Current task
Core 0
Core 1
Task 1
Task 2
Task 4
Task 3
Run-queue
Run-queue
Current task
Current task
Core 0
Core 1
Task 1
Task 2
Task 4
Task 3
Run-queue
Run-queue
Current task
Current task
Core 0
Core 1
Task 1
Task 2
Task 3
READY
RUNNING
Going
to DEAD
Core
1 is going to IDLE
Run-queue is empty
Task migration
Task 2
(Assumption:
a
ll tasks have same weight)Slide7
Active Load BalancingImplementationWhen a task is going to end up its execution time do_exit
()
Sets task’s state to “
TASK_DEAD” schedule()In back-end procedure, if a core’s state is IDLE, it calls “idle_balance()”
idle_balance
()To pull a task on the busiest core’s run-queue, it calls “load_balance()” load_balance
()
Does a task migration
General
CasesSlide8
Active Load BalancingDrawbackActive load balancing 으로도 충분히 load balancing 을 달성할 수 있지만
코어 간 작업량 차이가 큰 상황인데도 각 태스크의 수행시간이 길어서
IDLE
상태를 갖게 되는 코어가 한동안 없다면, 단기간 내 load balancing 의 목적을 달성할 수 없다.이 상황을 피하기 위해서 주기적인 조절이 필요하다
General
CasesSlide9
General
Cases
Passive(Periodic)
load balancing
Load Balance in Linux 2.6.32
Run-queue
Run-queue
Current task
Current task
Core 0
Core 1
Task 1
Task 2
Task 5
Task 4
Task 6
Run-queue
Run-queue
Current task
Current task
Core 0
Core 1
Task 1
Task 2
Task 5
Task 3
Run-queue
Run-queue
Current task
Current task
Core 0
Core 1
Task 1
Task 2
Task 5
Task 3
Run-queue
Run-queue
Current task
Current task
Core 0
Core 1
Task 4
Task 6
Task 3
Busiest run-queue
Idlest run-queue
Task 2
Task 3
For a long time, there is no IDLE core
Task 4
Task 6
Periodic check
If there
is
big
gap of load between
cores,
it is
uncomfortable
Task 4
Task 6
Task 1
Task 2
Task 5
Task migration
READY
RUNNING
Going
to DEAD
(Assumption:
a
ll tasks have same weight)Slide10
Passive Load BalancingTriggered by scheduler_tick()Tick value is compared with a parameter “next_balance” which is the time to do load balancing
Each run-queue has “
next_balance
”If a core takes the active load balancing, the parameter is set to 1 second afterIf a core takes the passive load balancing, the parameter is set to 1 minute after1초와 1분의 차이는 IDLE 상태를
밸런싱했던
코어는 다시
IDLE 상태가 되기 쉽기 때문에 곧바로 밸런싱을 해주기 위한 것Executed by bottom-half handlerA softirq named “SCHED_SOFTIRQ” is handled by “
run_rebalance_domains
()
”
General
CasesSlide11
Passive Load BalancingImplementation – start load balance General Cases
Timer interrupt invokes “
scheduler_tick
()
”
If the
tick value is equal to or greater than parameter
“
next_balance
”,
Busiest run-queue
Idlest run-queue
READY
RUNNING
(Assumption:
a
ll tasks have same weight)
Run-queue
Run-queue
Current task
Current task
Core 0
Core 1
Task 1
Task 2
Task 5
Task 7
Task 3
Task 6
Next_balance
Next_balance
Task 4Slide12
Passive Load Balancing
Implementation – step1
General
Cases
If the
tick value is equal to or greater than parameter
“
next_balance
”,
Step1
: raises
a
softirq
“
SCHED_SOFTIRQ
” to kernel
Softirq
table
…
???
SCHED_SOFTIRQ
Busiest run-queue
Idlest run-queue
READY
RUNNING
(Assumption:
a
ll tasks have same weight)
Run-queue
Run-queue
Current task
Current task
Core 0
Core 1
Task 1
Task 2
Task 5
Task 7
Task 3
Task 6
Next_balance
Next_balance
Task 4Slide13
Passive Load Balancing
Implementation – step2
General
Cases
Run-queue
Run-queue
Current task
Current task
Core 0
Core 1
Task 1
Task 2
ksoftirqd
Task 5
Task 7
Busiest run-queue
Idlest run-queue
Task 3
READY
RUNNING
(Assumption:
a
ll tasks have same weight)
If the
tick value is equal to or greater than parameter
“
next_balance
”,
Step1: raises a
softirq
“
SCHED_SOFTIRQ
” to kernel
Step2: finds the idlest run-queue to invoke a kernel thread “
ksoftirqd
”
Softirq
table
…
???
SCHED_SOFTIRQ
Task 6
Next_balance
Next_balance
Task 4Slide14
Passive Load Balancing
Implementation – step3
General
Cases
Run-queue
Run-queue
Current task
Current task
Core 0
Core 1
Task 1
Task 2
ksoftirqd
Task 5
Task 7
Busiest run-queue
Idlest run-queue
Task 3
READY
RUNNING
(Assumption:
a
ll tasks have same weight)
If the
tick value is equal to or greater than parameter
“
next_balance
”,
Step1: raises a
softirq
“
SCHED_SOFTIRQ
” to kernel
Step2: finds the idlest run-queue to invoke a kernel thread “
ksoftirqd
”
Softirq
table
…
???
SCHED_SOFTIRQ
Task 6
Next_balance
Next_balance
Task 4
Step3: the thread executes a function “
do_ksoftirqd
()
” that
picks a
softirq
and calls its handler function
run_rebalance_domains
()
Handler function (bottom-half handler)Slide15
Passive Load Balancing
Implementation – step4
General
Cases
Run-queue
Run-queue
Current task
Current task
Core 0
Core 1
Task 1
Task 2
ksoftirqd
Task 5
Task 7
Busiest run-queue
Idlest run-queue
Task 3
READY
RUNNING
(Assumption:
a
ll tasks have same weight)
If the
tick value is equal to or greater than parameter
“
next_balance
”,
Step1: raises a
softirq
“
SCHED_SOFTIRQ
” to kernel
Step2: finds the idlest run-queue to invoke a kernel thread “
ksoftirqd
”
Softirq
table
…
???
SCHED_SOFTIRQ
Task 6
Next_balance
Next_balance
Task 4
Step3: the thread executes a function “
do_ksoftirqd
()
” that
picks a
softirq
and calls its handler function
Step4:
the handler function finds the busiest run-queue to pull a task
run_rebalance_domains
()
Handler function (bottom-half handler)Slide16
Passive Load Balancing
Implementation – step5
General
Cases
Run-queue
Run-queue
Current task
Current task
Core 0
Core 1
Task 1
Task 2
ksoftirqd
Task 5
Task 7
Busiest run-queue
Idlest run-queue
Task 3
READY
RUNNING
(Assumption:
a
ll tasks have same weight)
If the
tick value is equal to or greater than parameter
“
next_balance
”,
Step1: raises a
softirq
“
SCHED_SOFTIRQ
” to kernel
Step2: finds the idlest run-queue to invoke a kernel thread “
ksoftirqd
”
Softirq
table
…
???
SCHED_SOFTIRQ
Task 6
Next_balance
Next_balance
Task 4
Step3: the thread executes a function “
do_ksoftirqd
()
” that
picks a
softirq
and calls its handler function
Step4:
the handler function finds the busiest run-queue to pull a task
Step5:
task migration
run_rebalance_domains
()
Handler function (bottom-half handler)
Task 4Slide17
Passive Load Balancing
Implementation
General
Cases
Run-queue
Run-queue
Current task
Current task
Core 0
Core 1
Task 1
Task 2
Task 5
Task 6
Task 3
Task 4
Next_balance
Next_balance
Task 7
Run-queue
Run-queue
Current task
Current task
Core 0
Core 1
Task 1
Task 2
Task 5
Task 7
Task 3
Task 6
Next_balance
Next_balance
Task 4Slide18
Passive Load BalancingDrawbackThis algorithm has large overheadThe algorithm should check the maximum and minimum load out of all cores
And, if a current core is
not
the idlest one, The kernel thread “ksoftirqd” should be enqueued to the idlest run-queue of other core and waken upAlso, a current task of the target core that has the idlest run-queue is preempted by “ksoftirqd”
Tradeoff: balancing time interval
throughput latencyGeneral CasesSlide19
ContentsLoad balancingPurposeDefinitionGeneral casesActive load balancingPassive load balancing
Special cases
Execution of a new task
CPU’s shut down or intentionally being IDLELimitation
Load Balance in Linux 2.6.32Slide20
Special CasesExecution of a new taskWhen a new task is created in one core, kernel checks the core’s load whether it is reasonable to handle a new taskIf the load is unacceptable, current task of the core is migrated to the idlest core’s run-queue and rescheduledAnd a new task is executed in the core (not the idlest core)
CPU’s shut down or intentionally being IDLE
When one core should be shut down or intentionally be IDLE
, such as in POWER_SAVING_LOAD_BALANCEAll tasks in its run-queue are migrated to other coresActually, this case is just a task migrationLoad Balance in Linux 2.6.32Slide21
ContentsLoad balancingPurposeDefinitionGeneral casesActive load balancingPassive load balancing
Special cases
Execution of a new task
CPU’s shut down or intentionally being IDLELimitation
Load Balance in Linux 2.6.32Slide22
LimitationGlobal Fairness Global Fairness는 여러 개의 CPU로 이루어진 SMP
에서 모든
task
가 자신의 weight에 비례해서 run-time을 보장받는 정도를 의미한다. SMP 환경에서 Run queue가 CPU
에 하나씩 있고
, Load Balance
는 각 Run queue의 load(sum of weight)만을 고려해서 task를 옮기므로 task가 자신의 weight에 비례한 시간을 못 받는 경우가 생긴다.
Example) Dual-core CPU
에 서로 같은
weight
를 갖는
task1, 2, 3
가 있을 때
CPU1
의
Run-queue
에는 task1이 있고, CPU2의 Run-queue에는 task2, task3
이 들어간다. 이 경우 load balance가 잘 일어나지 않으므로 서로 같은 weight를 갖고 있음에도 같은 run-time을 보장 받지 못한다.Load Balance in Linux 2.6.32Slide23
EndQ & A?CFS in Linux 2.6.37