keith-turner commented on a change in pull request #270: Support Accumulo
installs on Microsoft Azure
URL: https://github.com/apache/fluo-muchos/pull/270#discussion_r312981890
##########
File path: ansible/roles/hadoop/tasks/main.yml
##########
@@ -34,17 +34,52 @@
with_items:
- workers
when: hadoop_major_version == '3'
-- name: "copy spark yarn shuffle jar to hadoop lib"
- command: cp {{ spark_home }}/yarn/spark-{{ spark_version }}-yarn-shuffle.jar
{{ hadoop_home }}/share/hadoop/yarn/lib/ creates={{ hadoop_home
}}/share/hadoop/yarn/lib/spark-{{ spark_version }}-yarn-shuffle.jar
- when: "'spark' in groups"
+- name: "configure hadoop to send metrics"
+ template: src={{ item }} dest={{ hadoop_home }}/etc/hadoop/{{ item }}
+ with_items:
+ - hadoop-metrics2.properties
- name: "setup hadoop short circuit socket dir"
file: path=/var/lib/hadoop-hdfs state=directory owner={{ cluster_user }}
group={{ cluster_group }} mode=0755
become: yes
- name: "Configure hadoop log dir"
replace:
path: "{{ hadoop_home }}/etc/hadoop/hadoop-env.sh"
regexp: '.*export\s+HADOOP_LOG_DIR.*'
- replace: "export HADOOP_LOG_DIR={{ worker_data_dirs[0] }}/logs/hadoop"
+ replace: "export HADOOP_LOG_DIR={{ worker_data_dirs[1] }}/logs/hadoop"
+- name: "Configure max log size to 5g for Azure log analytics integration"
+ replace:
+ path: "{{ hadoop_home }}/etc/hadoop/log4j.properties"
+ regexp: 'hadoop.log.maxfilesize=256MB'
+ replace: "hadoop.log.maxfilesize=5g"
+ when: cluster_type == 'azure'
+- name: "Configure hadoop pid dir"
+ replace:
+ path: "{{ hadoop_home }}/etc/hadoop/hadoop-env.sh"
+ regexp: '.*export\s+HADOOP_PID_DIR.*'
+ replace: "export HADOOP_PID_DIR={{ worker_data_dirs[1] }}/hadoop"
+- name: "Configure namenode heap"
+ replace:
+ path: "{{ hadoop_home }}/etc/hadoop/hadoop-env.sh"
+ regexp: '.*export\s+HADOOP_NAMENODE_OPTS.*'
+ replace: "export HADOOP_NAMENODE_OPTS=\"-server -XX:ParallelGCThreads=8
-XX:+UseConcMarkSweepGC -XX:CMSInitiatingOccupancyFraction=70
-XX:+UseCMSInitiatingOccupancyOnly {{ namenode_heap }}
-Dhadoop.security.logger=${HADOOP_SECURITY_LOGGER:-INFO,RFAS}
-Dhdfs.audit.logger=${HDFS_AUDIT_LOGGER:-INFO,NullAppender} -verbose:gc
-XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xloggc:{{
worker_data_dirs[1] }}/logs/hadoop/gc.log-`date +'%Y%m%d%H%M'` -XX:ErrorFile={{
worker_data_dirs[1] }}/logs/hadoop/hs_err_pid%p.log
-XX:+HeapDumpOnOutOfMemoryError -XX:HeapDumpPath={{ worker_data_dirs[1]
}}/logs/hadoop\""
Review comment:
Recently I have been running test with JDK11 and I think it complains that
`-XX:+UseConcMarkSweepGC` is deprecated, but I am not completely sure.
Setting all of these options is very version specific to Hadoop and Java and
I worry about the maintenance cost of it. What were the benefits you gained
from these settings? Do you think those benefits are worth making it harder to
change Hadoop and JDK versions?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
