YARN-3375. NodeHealthScriptRunner.shouldRun() check is performing 3 times for starting NodeHealthScriptRunner (Devaraj K via wangda)
(cherry picked from commit 71f4de220c
)
This commit is contained in:
parent
02e650248d
commit
4e77ee2f6f
|
@ -214,11 +214,6 @@ public class NodeHealthScriptRunner extends AbstractService {
|
||||||
*/
|
*/
|
||||||
@Override
|
@Override
|
||||||
protected void serviceStart() throws Exception {
|
protected void serviceStart() throws Exception {
|
||||||
// if health script path is not configured don't start the thread.
|
|
||||||
if (!shouldRun(nodeHealthScript)) {
|
|
||||||
LOG.info("Not starting node health monitor");
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
nodeHealthScriptScheduler = new Timer("NodeHealthMonitor-Timer", true);
|
nodeHealthScriptScheduler = new Timer("NodeHealthMonitor-Timer", true);
|
||||||
// Start the timer task immediately and
|
// Start the timer task immediately and
|
||||||
// then periodically at interval time.
|
// then periodically at interval time.
|
||||||
|
@ -232,9 +227,6 @@ public class NodeHealthScriptRunner extends AbstractService {
|
||||||
*/
|
*/
|
||||||
@Override
|
@Override
|
||||||
protected void serviceStop() {
|
protected void serviceStop() {
|
||||||
if (!shouldRun(nodeHealthScript)) {
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
if (nodeHealthScriptScheduler != null) {
|
if (nodeHealthScriptScheduler != null) {
|
||||||
nodeHealthScriptScheduler.cancel();
|
nodeHealthScriptScheduler.cancel();
|
||||||
}
|
}
|
||||||
|
|
|
@ -254,6 +254,9 @@ Release 2.8.0 - UNRELEASED
|
||||||
YARN-3097. Logging of resource recovery on NM restart has redundancies
|
YARN-3097. Logging of resource recovery on NM restart has redundancies
|
||||||
(Eric Payne via jlowe)
|
(Eric Payne via jlowe)
|
||||||
|
|
||||||
|
YARN-3375. NodeHealthScriptRunner.shouldRun() check is performing 3 times for
|
||||||
|
starting NodeHealthScriptRunner. (Devaraj K via wangda)
|
||||||
|
|
||||||
Release 2.7.1 - UNRELEASED
|
Release 2.7.1 - UNRELEASED
|
||||||
|
|
||||||
INCOMPATIBLE CHANGES
|
INCOMPATIBLE CHANGES
|
||||||
|
|
|
@ -21,7 +21,6 @@ package org.apache.hadoop.yarn.server.nodemanager;
|
||||||
import org.apache.hadoop.conf.Configuration;
|
import org.apache.hadoop.conf.Configuration;
|
||||||
import org.apache.hadoop.service.CompositeService;
|
import org.apache.hadoop.service.CompositeService;
|
||||||
import org.apache.hadoop.util.NodeHealthScriptRunner;
|
import org.apache.hadoop.util.NodeHealthScriptRunner;
|
||||||
import org.apache.hadoop.yarn.conf.YarnConfiguration;
|
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* The class which provides functionality of checking the health of the node and
|
* The class which provides functionality of checking the health of the node and
|
||||||
|
@ -44,8 +43,7 @@ public class NodeHealthCheckerService extends CompositeService {
|
||||||
|
|
||||||
@Override
|
@Override
|
||||||
protected void serviceInit(Configuration conf) throws Exception {
|
protected void serviceInit(Configuration conf) throws Exception {
|
||||||
if (NodeHealthScriptRunner.shouldRun(
|
if (nodeHealthScriptRunner != null) {
|
||||||
conf.get(YarnConfiguration.NM_HEALTH_CHECK_SCRIPT_PATH))) {
|
|
||||||
addService(nodeHealthScriptRunner);
|
addService(nodeHealthScriptRunner);
|
||||||
}
|
}
|
||||||
addService(dirsHandler);
|
addService(dirsHandler);
|
||||||
|
|
|
@ -210,7 +210,9 @@ public class NodeManager extends CompositeService
|
||||||
String nodeHealthScript =
|
String nodeHealthScript =
|
||||||
conf.get(YarnConfiguration.NM_HEALTH_CHECK_SCRIPT_PATH);
|
conf.get(YarnConfiguration.NM_HEALTH_CHECK_SCRIPT_PATH);
|
||||||
if(!NodeHealthScriptRunner.shouldRun(nodeHealthScript)) {
|
if(!NodeHealthScriptRunner.shouldRun(nodeHealthScript)) {
|
||||||
LOG.info("Abey khali");
|
LOG.info("Node Manager health check script is not available "
|
||||||
|
+ "or doesn't have execute permission, so not "
|
||||||
|
+ "starting the node health script runner.");
|
||||||
return null;
|
return null;
|
||||||
}
|
}
|
||||||
long nmCheckintervalTime = conf.getLong(
|
long nmCheckintervalTime = conf.getLong(
|
||||||
|
|
Loading…
Reference in New Issue