when cluster stopped and romove server from cluster which contains meta region,
then restart cluster master break down.
------------------------------------------------------------------------------------------------------------------------
Key: HBASE-3867
URL: https://issues.apache.org/jira/browse/HBASE-3867
Project: HBase
Issue Type: Bug
Components: master
Affects Versions: 0.90.2, 0.90.1
Reporter: Liu Jia
Priority: Critical
When cluster stopped and romove server from cluster which contains meta region,
then restart cluster,
>From the following code throws "NoRouteToHostException"
package org.apache.hadoop.hbase.catalog;
public class CatalogTracker
private HRegionInterface getMetaServerConnection(boolean refresh)
throws IOException, InterruptedException {
synchronized (metaAvailable) {
if (metaAvailable.get()) {
HRegionInterface current = getCachedConnection(metaLocation);
if (!refresh) {
return current;
}
if (verifyRegionLocation(current, this.metaLocation, META_REGION)) {
return current;
}
resetMetaLocation();
}
HRegionInterface rootConnection = getRootServerConnection();
if (rootConnection == null) {
return null;
}
HServerAddress newLocation = MetaReader.readMetaLocation(rootConnection);
if (newLocation == null) {
return null;
}
////////the following line throws the exception
HRegionInterface newConnection = getCachedConnection(newLocation);
if (verifyRegionLocation(newConnection, this.metaLocation, META_REGION)) {
setMetaLocation(newLocation);
return newConnection;
}
return null;
}
}
/////////////the following method don't handle the exception.
public class CatalogTracker
public boolean verifyMetaRegionLocation(final long timeout)
throws InterruptedException, IOException {
return getMetaServerConnection(true) != null;
}
//////////////////master call the CatalogTracker's method and don't handle the
problem too.
package org.apache.hadoop.hbase.master;
public class HMaster
int assignRootAndMeta()
throws InterruptedException, IOException, KeeperException {
int assigned = 0;
long timeout = this.conf.getLong("hbase.catalog.verification.timeout",
1000);
// Work on ROOT region. Is it in zk in transition?
boolean rit = this.assignmentManager.
processRegionInTransitionAndBlockUntilAssigned(HRegionInfo.ROOT_REGIONINFO);
if (!catalogTracker.verifyRootRegionLocation(timeout)) {
this.assignmentManager.assignRoot();
this.catalogTracker.waitForRoot();
assigned++;
}
LOG.info("-ROOT- assigned=" + assigned + ", rit=" + rit +
", location=" + catalogTracker.getRootLocation());
// Work on meta region
rit = this.assignmentManager.
processRegionInTransitionAndBlockUntilAssigned(HRegionInfo.FIRST_META_REGIONINFO);
///////////////////////////////
when restart cluster master break down here.
////////////////////////////////
if (!this.catalogTracker.verifyMetaRegionLocation(timeout)) {
this.assignmentManager.assignMeta();
this.catalogTracker.waitForMeta();
// Above check waits for general meta availability but this does not
// guarantee that the transition has completed
this.assignmentManager.waitForAssignment(HRegionInfo.FIRST_META_REGIONINFO);
assigned++;
}
LOG.info(".META. assigned=" + assigned + ", rit=" + rit +
", location=" + catalogTracker.getMetaLocation());
return assigned;
}
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
