big-data/hadoop
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

YARN-4857. Add missing default configuration regarding preemption of CapacityScheduler. Contributed by Kai Sasaki.

Browse Source
This commit is contained in:
Varun Vasudev 2016-03-31 14:05:49 +05:30
parent f1b8f6b2c1
commit 0064cba169
1 changed files with 58 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
hadoop-yarn-project/hadoop-yarn/hadoop-yarn-common/src/main/resources/yarn-default.xml
View File

@ -908,6 +908,64 @@
<value>600000</value> <value>600000</value>
</property> </property>
<property>
<description>
If true, run the policy but do not affect the cluster with preemption and kill events.
</description>
<name>yarn.resourcemanager.monitor.capacity.preemption.observe_only</name>
<value>false</value>
</property>
<property>
<description>
Time in milliseconds between invocations of this ProportionalCapacityPreemptionPolicy
policy.
</description>
<name>yarn.resourcemanager.monitor.capacity.preemption.monitoring_interval</name>
<value>3000</value>
</property>
<property>
<description>
Time in milliseconds between requesting a preemption from an application and killing
the container.
</description>
<name>yarn.resourcemanager.monitor.capacity.preemption.max_wait_before_kill</name>
<value>15000</value>
</property>
<property>
<description>
Maximum percentage of resources preempted in a single round. By controlling this valueone
can throttle the pace at which containers are reclaimed from the cluster. After computing
the total desired preemption, the policy scales it back within this limit.
</description>
<name>yarn.resourcemanager.monitor.capacity.preemption.total_preemption_per_round</name>
<value>0.1</value>
</property>
<property>
<description>
Maximum amount of resources above the target capacity ignored for preemption.
This defines a deadzone around the target capacity that helps prevent thrashing and
oscillations around the computed target balance. High values would slow the time to capacity
and (absent natural.completions) it might prevent convergence to guaranteed capacity.
</description>
<name>yarn.resourcemanager.monitor.capacity.preemption.max_ignored_over_capacity</name>
<value>0.1</value>
</property>
<property>
<description>
Given a computed preemption target, account for containers naturally expiring and preempt
only this percentage of the delta. This determines the rate of geometric convergence into
the deadzone (MAX_IGNORED_OVER_CAPACITY). For example, a termination factor of 0.5 will reclaim
almost 95% of resources within 5 * #WAIT_TIME_BEFORE_KILL, even absent natural termination.
</description>
<name>yarn.resourcemanager.monitor.capacity.preemption.natural_termination_factor</name>
<value>0.2</value>
</property>
<!-- Node Manager Configuration --> <!-- Node Manager Configuration -->
<property> <property>