You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@ambari.apache.org by ja...@apache.org on 2016/03/22 21:07:51 UTC
ambari git commit: AMBARI-15518. Fix the 'tez-interactive-site.xml'.
Added new properties,
fixed values of existing props. (Swapan Sridhar via Jaimin)
Repository: ambari
Updated Branches:
refs/heads/trunk 340f7ce6b -> 156370820
AMBARI-15518. Fix the 'tez-interactive-site.xml'. Added new properties, fixed values of existing props. (Swapan Sridhar via Jaimin)
Project: http://git-wip-us.apache.org/repos/asf/ambari/repo
Commit: http://git-wip-us.apache.org/repos/asf/ambari/commit/15637082
Tree: http://git-wip-us.apache.org/repos/asf/ambari/tree/15637082
Diff: http://git-wip-us.apache.org/repos/asf/ambari/diff/15637082
Branch: refs/heads/trunk
Commit: 1563708204eac4ec24ea43aa9d260d341bec97d1
Parents: 340f7ce
Author: Jaimin Jetly <ja...@hortonworks.com>
Authored: Tue Mar 22 13:07:07 2016 -0700
Committer: Jaimin Jetly <ja...@hortonworks.com>
Committed: Tue Mar 22 13:07:26 2016 -0700
----------------------------------------------------------------------
.../HIVE/configuration/tez-interactive-site.xml | 285 ++++++++++++++++++-
1 file changed, 282 insertions(+), 3 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/ambari/blob/15637082/ambari-server/src/main/resources/stacks/HDP/2.6/services/HIVE/configuration/tez-interactive-site.xml
----------------------------------------------------------------------
diff --git a/ambari-server/src/main/resources/stacks/HDP/2.6/services/HIVE/configuration/tez-interactive-site.xml b/ambari-server/src/main/resources/stacks/HDP/2.6/services/HIVE/configuration/tez-interactive-site.xml
index c4dee3e..b0eb5a6 100644
--- a/ambari-server/src/main/resources/stacks/HDP/2.6/services/HIVE/configuration/tez-interactive-site.xml
+++ b/ambari-server/src/main/resources/stacks/HDP/2.6/services/HIVE/configuration/tez-interactive-site.xml
@@ -22,241 +22,397 @@
<property>
<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.container.idle.release-timeout-max.millis</name>
<value>20000</value>
+ <description>The maximum amount of time to hold on to a container if no task can be assigned to it immediately. Only active when reuse is enabled.</description>
</property>
<property>
<name>tez.am.container.idle.release-timeout-min.millis</name>
<value>10000</value>
+ <description>The minimum amount of time to hold on to a container that is idle. Only active when reuse is enabled.</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.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.am.container.reuse.non-local-fallback.enabled</name>
<value>false</value>
+ <description>Whether to reuse containers for non-local tasks. Active only if reuse is enabled</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.launch.cluster-default.cmd-opts</name>
<value>-server -Djava.net.preferIPv4Stack=true -Dhdp.version=${hdp.version}</value>
+ <description>Cluster default Java options for the Tez AppMaster process. These will be prepended to the properties specified via tez.am.launch.cmd-opts</description>
</property>
<property>
<name>tez.am.launch.cmd-opts</name>
<value>-XX:+PrintGCDetails -verbose:gc -XX:+PrintGCTimeStamps -XX:+UseNUMA -XX:+UseG1GC -XX:+ResizeTLAB</value>
+ <description>Java options for the Tez AppMaster process. The Xmx value is derived based on tez.am.resource.memory.mb and is 80% of the value by default.
+ Used only if the value is not specified explicitly by the DAG definition.
+ </description>
</property>
<property>
<name>tez.am.launch.env</name>
<value>LD_LIBRARY_PATH=/usr/hdp/${hdp.version}/hadoop/lib/native:/usr/hdp/${hdp.version}/hadoop/lib/native/Linux-amd64-64</value>
+ <description>
+ Additional execution environment entries for tez. This is not an additive property. You must preserve the original value if
+ you want to have access to native libraries.
+ Used only if the value is not specified explicitly by the DAG definition.
+ </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.am.max.app.attempts</name>
<value>2</value>
+ <description>Specifies the total number of time the app master will run in case recovery is triggered</description>
</property>
<property>
<name>tez.am.maxtaskfailures.per.node</name>
<value>10</value>
+ <description>The maximum number of allowed task attempt failures on a node before
+ it gets marked as blacklisted
+ </description>
</property>
<property>
<name>tez.am.resource.memory.mb</name>
- <value>512</value>
+ <value>341</value>
+ <description>The amount of memory to be used by the AppMaster</description>
+ <value-attributes>
+ <type>int</type>
+ </value-attributes>
</property>
<property>
<name>tez.am.tez-ui.history-url.template</name>
<value>__HISTORY_URL_BASE__?viewPath=%2F%23%2Ftez-app%2F__APPLICATION_ID__</value>
+ <description>Template to generate the History URL for a particular Tez Application.
+ Template replaces __APPLICATION_ID__ with the actual applicationId and
+ __HISTORY_URL_BASE__ with the value from the tez.tez-ui.history-url.base config property
+ </description>
</property>
<property>
<name>tez.am.view-acls</name>
<value>*</value>
+ <description>AM view ACLs. This allows the specified users/groups to view the status of the AM and all DAGs that run within this AM.
+ Value format: Comma separated list of users, followed by whitespace, followed by a comma separated list of groups.
+ </description>
+ <value-attributes>
+ <empty-value-valid>true</empty-value-valid>
+ </value-attributes>
</property>
<property>
<name>tez.cluster.additional.classpath.prefix</name>
<value>/usr/hdp/${hdp.version}/hadoop/lib/hadoop-lzo-0.6.0.${hdp.version}.jar:/etc/hadoop/conf/secure</value>
+ <description></description>
</property>
<property>
<name>tez.counters.max</name>
<value>5000</value>
+ <description>The number of allowed counters for the executing DAG</description>
</property>
<property>
<name>tez.counters.max.groups</name>
<value>1000</value>
+ <description>The number of allowed counter groups for the executing DAG</description>
</property>
<property>
<name>tez.generate.debug.artifacts</name>
<value>false</value>
+ <description>Generate debug artifacts such as a text representation of the submitted DAG plan</description>
</property>
<property>
<name>tez.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.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.grouping.split-waves</name>
<value>1.7</value>
+ <description>The multiplier for available queue capacity when determining number of tasks for
+ a Vertex. 1.7 with 100% queue available implies generating a number of tasks roughly equal
+ to 170% of the available containers on the queue
+ </description>
</property>
<property>
<name>tez.history.logging.service.class</name>
<value>org.apache.tez.dag.history.logging.ats.ATSV15HistoryLoggingService</value>
+ <description>The class to be used for logging history data.
+ Set to org.apache.tez.dag.history.logging.impl.SimpleHistoryLoggingService to log to the filesystem specified by ${fs.defaultFS}
+ </description>
</property>
<property>
<name>tez.lib.uris</name>
- <value>/hdp/apps/${hdp.version}/tez/tez.tar.gz</value>
+ <value>/hdp/apps/${hdp.version}/tez_hive2/tez.tar.gz</value>
+ <description>Comma-delimited list of the location of the Tez libraries which will be localized for DAGs.
+ Specifying a single .tar.gz or .tgz assumes that a compressed version of the tez libs is being used. This is uncompressed into a tezlibs directory when running containers, and tezlibs/;tezlibs/lib/ are added to the classpath (after . and .*).
+ If multiple files are specified - files are localized as regular files, contents of directories are localized as regular files (non-recursive).
+ </description>
</property>
<property>
<name>tez.runtime.compress</name>
<value>true</value>
+ <description>Whether intermediate data should be compressed or not</description>
</property>
<property>
<name>tez.runtime.compress.codec</name>
<value>org.apache.hadoop.io.compress.SnappyCodec</value>
+ <description>The coded to be used if compressing intermediate data. Only
+ applicable if tez.runtime.compress is enabled
+ </description>
</property>
<property>
<name>tez.runtime.convert.user-payload.to.history-text</name>
<value>false</value>
+ <description>Whether to publish configuration information to History logger</description>
</property>
<property>
<name>tez.runtime.io.sort.mb</name>
<value>102</value>
+ <description>The size of the sort buffer when output needs to be sorted</description>
+ <value-attributes>
+ <type>int</type>
+ <unit>MB</unit>
+ </value-attributes>
+ <depends-on>
+ <property>
+ <type>tez-site</type>
+ <name>tez.runtime.sorter.class</name>
+ </property>
+ </depends-on>
</property>
<property>
<name>tez.runtime.optimize.local.fetch</name>
<value>true</value>
+ <description>If the shuffle input is on the local host bypass the http fetch and access the files directly.</description>
+ <value-attributes>
+ <type>boolean</type>
+ </value-attributes>
</property>
<property>
<name>tez.runtime.pipelined.sorter.sort.threads</name>
<value>2</value>
+ <description>Tez runtime pipelined sorter sort threads</description>
+ <value-attributes>
+ <type>int</type>
+ </value-attributes>
+ <depends-on>
+ <property>
+ <type>tez-site</type>
+ <name>tez.runtime.sorter.class</name>
+ </property>
+ </depends-on>
</property>
<property>
<name>tez.runtime.sorter.class</name>
<value>PIPELINED</value>
+ <description>Which sorter implementation to use</description>
+ <value-attributes>
+ <type>value-list</type>
+ <entries>
+ <entry>
+ <value>PIPELINED</value>
+ <label>Pipelined Sorter</label>
+ </entry>
+ <entry>
+ <value>LEGACY</value>
+ <label>Legacy Sorter</label>
+ </entry>
+ </entries>
+ <selection-cardinality>1</selection-cardinality>
+ </value-attributes>
</property>
<property>
<name>tez.runtime.unordered.output.buffer.size-mb</name>
<value>19</value>
+ <description>The size of the buffer when output does not require to be sorted</description>
+ <depends-on>
+ <property>
+ <type>tez-site</type>
+ <name>tez.task.resource.memory.mb</name>
+ </property>
+ </depends-on>
</property>
<property>
<name>tez.session.am.dag.submit.timeout.secs</name>
<value>600</value>
+ <description>Time (in seconds) for which the Tez AM should wait for a DAG to be submitted
+ before shutting down
+ </description>
</property>
<property>
<name>tez.session.client.timeout.secs</name>
<value>-1</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.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.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.staging-dir</name>
<value>/tmp/${user.name}/staging</value>
+ <description>The staging dir used while submitting DAGs</description>
</property>
<property>
<name>tez.task.am.heartbeat.counter.interval-ms.max</name>
<value>4000</value>
+ <description>Time interval at which task counters are sent to the AM</description>
</property>
<property>
<name>tez.task.generate.counters.per.io</name>
<value>true</value>
+ <description>Whether to generate counters on a per-edge basis for a Tez DAG. Helpful for in-depth analysis.</description>
+ <value-attributes>
+ <type>boolean</type>
+ </value-attributes>
</property>
<property>
<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>
<property>
<name>tez.task.launch.cluster-default.cmd-opts</name>
<value>-server -Djava.net.preferIPv4Stack=true -Dhdp.version=${hdp.version}</value>
+ <description>Cluster default Java options for tasks. These will be prepended to the properties specified via tez.task.launch.cmd-opts</description>
</property>
<property>
<name>tez.task.launch.cmd-opts</name>
<value>-XX:+PrintGCDetails -verbose:gc -XX:+PrintGCTimeStamps -XX:+UseNUMA -XX:+UseG1GC -XX:+ResizeTLAB</value>
+ <description>Java options for tasks. The Xmx value is derived based on tez.task.resource.memory.mb and is 80% of this value by default.
+ Used only if the value is not specified explicitly by the DAG definition.
+ </description>
</property>
<property>
<name>tez.task.launch.env</name>
<value>LD_LIBRARY_PATH=/usr/hdp/${hdp.version}/hadoop/lib/native:/usr/hdp/${hdp.version}/hadoop/lib/native/Linux-amd64-64</value>
+ <description>
+ Additional execution environment entries for tez. This is not an additive property. You must preserve the original value if
+ you want to have access to native libraries.
+ Used only if the value is not specified explicitly by the DAG definition.
+ </description>
</property>
<property>
<name>tez.task.max-events-per-heartbeat</name>
<value>500</value>
+ <description>Maximum number of of events to fetch from the AM by the tasks in a single heartbeat.</description>
</property>
<property>
<name>tez.task.resource.memory.mb</name>
- <value>256</value>
+ <value>341</value>
+ <description>The amount of memory to be used by launched tasks.
+ Used only if the value is not specified explicitly by the DAG definition.
+ </description>
+ <depends-on>
+ <property>
+ <type>yarn-site</type>
+ <name>yarn.scheduler.minimum-allocation-mb</name>
+ </property>
+ <property>
+ <type>yarn-site</type>
+ <name>yarn.scheduler.maximum-allocation-mb</name>
+ </property>
+ </depends-on>
</property>
<property>
<name>tez.tez-ui.history-url.base</name>
<value>http://c7001.ambari.apache.org:8080/#/main/views/TEZ/0.7.0.2.3.4.0-1310/TEZ_CLUSTER_INSTANCE</value>
+ <description>Tez UI history URL</description>
</property>
<property>
<name>tez.use.cluster.hadoop-libs</name>
<value>false</value>
+ <description>This being true implies that the deployment is relying on hadoop jars being available on the cluster on all nodes.</description>
</property>
<!-- Old settings - potentially useful to change values for LLAP -->
@@ -283,6 +439,129 @@
<value>true</value>
</property>
+ <!-- Added by as part of inheritance from upper Stacks. -->
+ <property>
+ <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. The -Xmx parameter value is generally 0.8 times tez.am.resource.memory.mb config.</description>
+ </property>
+
+ <property>
+ <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.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.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>
+ <value-attributes>
+ <type>float</type>
+ </value-attributes>
+ </property>
+
+ <property>
+ <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>
+ <value-attributes>
+ <type>int</type>
+ </value-attributes>
+ </property>
+
+ <property>
+ <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>
+ <value-attributes>
+ <type>int</type>
+ </value-attributes>
+ </property>
+
+ <property>
+ <name>tez.am.container.session.delay-allocation-millis</name>
+ <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.env</name>
+ <value>LD_LIBRARY_PATH=/usr/lib/hadoop/lib/native:/usr/lib/hadoop/lib/native/Linux-amd64-64</value>
+ <description>
+ Additional execution environment entries for tez. This is not an additive property. You must preserve the original value if
+ you want to have access to native libraries.
+ </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-output.should-compress</name>
+ <value>false</value>
+ <description>Whether intermediate output should be compressed or not</description>
+ <value-attributes>
+ <type>boolean</type>
+ </value-attributes>
+ </property>
+
+ <property>
+ <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.intermediate-input.is-compressed</name>
+ <value>false</value>
+ <description>Whether intermediate input is compressed</description>
+ <value-attributes>
+ <type>boolean</type>
+ </value-attributes>
+ </property>
+
+ <property>
+ <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.</description>
+ </property>
+
+ <!-- Configuration for ATS integration -->
+
+ <property>
+ <name>tez.yarn.ats.enabled</name>
+ <value>true</value>
+ <description>Whether to send history events to YARN Application Timeline Server</description>
+ </property>
+
<!-- End of old settings -->
<!-- New Settings -->