You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@ambari.apache.org by sw...@apache.org on 2014/02/11 22:29:48 UTC
git commit: AMBARI-4615. Update tez-site to reflect defaults based on
Tez source. (swagle)
Updated Branches:
refs/heads/trunk 91af8962d -> 19cc7ba62
AMBARI-4615. Update tez-site to reflect defaults based on Tez source. (swagle)
Project: http://git-wip-us.apache.org/repos/asf/ambari/repo
Commit: http://git-wip-us.apache.org/repos/asf/ambari/commit/19cc7ba6
Tree: http://git-wip-us.apache.org/repos/asf/ambari/tree/19cc7ba6
Diff: http://git-wip-us.apache.org/repos/asf/ambari/diff/19cc7ba6
Branch: refs/heads/trunk
Commit: 19cc7ba62e6f9f45deb0e1bcd0708d0e4f9c117f
Parents: 91af896
Author: Siddharth Wagle <sw...@hortonworks.com>
Authored: Tue Feb 11 13:17:07 2014 -0800
Committer: Siddharth Wagle <sw...@hortonworks.com>
Committed: Tue Feb 11 13:29:40 2014 -0800
----------------------------------------------------------------------
.../services/TEZ/configuration/tez-site.xml | 127 +++++++++++++------
1 file changed, 91 insertions(+), 36 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/ambari/blob/19cc7ba6/ambari-server/src/main/resources/stacks/HDP/2.1.1/services/TEZ/configuration/tez-site.xml
----------------------------------------------------------------------
diff --git a/ambari-server/src/main/resources/stacks/HDP/2.1.1/services/TEZ/configuration/tez-site.xml b/ambari-server/src/main/resources/stacks/HDP/2.1.1/services/TEZ/configuration/tez-site.xml
index 94642c7..2fb0f19 100644
--- a/ambari-server/src/main/resources/stacks/HDP/2.1.1/services/TEZ/configuration/tez-site.xml
+++ b/ambari-server/src/main/resources/stacks/HDP/2.1.1/services/TEZ/configuration/tez-site.xml
@@ -22,121 +22,176 @@
<property>
<name>tez.lib.uris</name>
<value>file:///usr/lib/tez/,file:///usr/lib/tez/lib/</value>
+ <description>The location of the Tez libraries which will be localized for DAGs</description>
</property>
<property>
<name>tez.am.log.level</name>
<value>INFO</value>
+ <description>Root Logging level passed to the Tez app master</description>
</property>
<property>
<name>tez.staging-dir</name>
<value>/tmp/${user.name}/staging</value>
+ <description>The staging dir used while submitting DAGs</description>
</property>
<property>
- <name>tez.slowstart-vertex-scheduler.min-src-fraction</name>
- <value>0.1</value>
+ <name>tez.am.resource.memory.mb</name>
+ <value>1536</value>
+ <description>The amount of memory to be used by the AppMaster</description>
</property>
+ <!-- tez picks the java opts from yarn.app.mapreduce.am.command-opts for MR tasks. Likewise for the AM memory MB -->
<property>
- <name>tez.slowstart-vertex-scheduler.max-src-fraction</name>
- <value>0.1</value>
+ <name>tez.am.java.opts</name>
+ <value>-server -Xmx1024m -Djava.net.preferIPv4Stack=true -XX:+UseNUMA -XX:+UseParallelGC</value>
+ <description>Java options for the Tez AppMaster process</description>
</property>
<property>
- <name>tez.am.am-rm.heartbeat.interval-ms.max</name>
- <value>250</value>
+ <name>tez.am.shuffle-vertex-manager.min-src-fraction</name>
+ <value>0.2</value>
+ <description>In case of a ScatterGather connection, the fraction of source tasks which should
+ complete before tasks for the current vertex are schedule
+ </description>
</property>
<property>
- <name>tez.runtime.broadcast.data-via-events.enabled</name>
- <value>true</value>
+ <name>tez.am.shuffle-vertex-manager.max-src-fraction</name>
+ <value>0.4</value>
+ <description>In case of a ScatterGather connection, once this fraction of source tasks have
+ completed, all tasks on the current vertex can be scheduled. Number of tasks ready for
+ scheduling on the current vertex scales linearly between min-fraction and max-fraction
+ </description>
</property>
<property>
- <name>tez.runtime.broadcast.data-via-events.max-size</name>
- <value>614400</value>
- </property>
-
- <property>
- <name>tez.am.aggressive.scheduling</name>
- <value>false</value>
+ <name>tez.am.am-rm.heartbeat.interval-ms.max</name>
+ <value>250</value>
+ <description>The maximum heartbeat interval between the AM and RM in milliseconds</description>
</property>
<property>
- <name>tez.am.resource.memory.mb</name>
- <value>1024</value>
+ <name>tez.am.grouping.split-waves</name>
+ <value>1.4</value>
+ <description>The multiplier for available queue capacity when determining number of tasks for
+ a Vertex. 1.4 with 100% queue available implies generating a number of tasks roughly equal
+ to 140% of the available containers on the queue
+ </description>
</property>
<property>
- <name>tez.am.java.opts</name>
- <value>-server -Xmx1024m -Djava.net.preferIPv4Stack=true -XX:+PrintGCDetails -verbose:gc -XX:+PrintGCTimeStamps -XX:+UseNUMA -XX:+UseParallelGC</value>
+ <name>tez.am.grouping.min-size</name>
+ <value>16777216</value>
+ <description>Lower bound on the size (in bytes) of a grouped split, to avoid generating
+ too many splits
+ </description>
</property>
<property>
- <name>tez.am.grouping.split-waves</name>
- <value>1.7</value>
+ <name>tez.am.grouping.max-size</name>
+ <value>1073741824</value>
+ <description>Upper bound on the size (in bytes) of a grouped split, to avoid generating
+ excessively large split
+ </description>
</property>
<property>
<name>tez.am.container.reuse.enabled</name>
<value>true</value>
+ <description>Configuration to specify whether container should be reused</description>
</property>
<property>
<name>tez.am.container.reuse.rack-fallback.enabled</name>
<value>true</value>
+ <description>Whether to reuse containers for rack local tasks. Active only if reuse is enabled
+ </description>
</property>
<property>
<name>tez.am.container.reuse.non-local-fallback.enabled</name>
<value>true</value>
+ <description>Whether to reuse containers for non-local tasks. Active only if reuse is enabled
+ </description>
</property>
<property>
<name>tez.am.container.session.delay-allocation-millis</name>
- <value>300000</value>
+ <value>10000</value>
+ <!-- TODO This value may change -->
+ <description>The amount of time to hold on to a container if no task can be assigned to
+ it immediately. Only active when reuse is enabled. Set to -1 to never release a container
+ in a session
+ </description>
</property>
<property>
<name>tez.am.container.reuse.locality.delay-allocation-millis</name>
<value>250</value>
+ <description>The amount of time to wait before assigning a container to the next level of
+ locality. NODE -> RACK -> NON_LOCAL
+ </description>
</property>
<property>
- <name>tez.runtime.intermediate-output.should-compress</name>
- <value>true</value>
+ <name>tez.task.get-task.sleep.interval-ms.max</name>
+ <value>200</value>
+ <description>The maximum amount of time, in seconds, to wait before a task asks an AM for
+ another task
+ </description>
</property>
+ <!-- Client Submission timeout value when submitting DAGs to a session -->
<property>
- <name>tez.runtime.intermediate-output.compress.codec</name>
- <value>org.apache.hadoop.io.compress.DefaultCodec</value>
+ <name>tez.session.client.timeout.secs</name>
+ <value>60</value>
+ <description>Time (in seconds) to wait for AM to come up when trying to submit a DAG from
+ the client
+ </description>
</property>
<property>
- <name>tez.runtime.intermdiate-input.is-compressed</name>
- <value>true</value>
+ <name>tez.session.am.dag.submit.timeout.secs</name>
+ <value>300</value>
+ <description>Time (in seconds) for which the Tez AM should wait for a DAG to be submitted
+ before shutting down
+ </description>
</property>
+
+ <!-- Configuration for runtime components -->
+
+ <!-- These properties can be set on a per edge basis by configuring the payload for each
+ edge independently. -->
+
<property>
- <name>tez.runtime.intermediate-input.compress.codec</name>
- <value>org.apache.hadoop.io.compress.DefaultCodec</value>
+ <name>tez.runtime.intermediate-output.should-compress</name>
+ <value>false</value>
+ <description>Whether intermediate output should be compressed or not</description>
</property>
<property>
- <name>tez.task.get-task.sleep.interval-ms.max</name>
- <value>100</value>
+ <name>tez.runtime.intermediate-output.compress.codec</name>
+ <value>org.apache.hadoop.io.compress.SnappyCodec</value>
+ <description>The coded to be used if compressing intermediate output. Only
+ applicable if tez.runtime.intermediate-output.should-compress is enabled.
+ </description>
</property>
<property>
- <name>tez.runtime.job.counters.max</name>
- <value>5000</value>
+ <name>tez.runtime.intermediate-input.is-compressed</name>
+ <value>false</value>
+ <description>Whether intermediate input is compressed</description>
</property>
<property>
- <name>tez.runtime.job.counters.groups.max</name>
- <value>5000</value>
+ <name>tez.runtime.intermediate-input.compress.codec</name>
+ <value>org.apache.hadoop.io.compress.SnappyCodec</value>
+ <description>The coded to be used when reading intermediate compressed input.
+ Only applicable if tez.runtime.intermediate-input.is-compressed is enabled.
</property>
</configuration>
\ No newline at end of file