Author: jdcryans
Date: Wed Nov 24 18:19:43 2010
New Revision: 1038745
URL: http://svn.apache.org/viewvc?rev=1038745&view=rev
Log:
HBASE-3273 Set the ZK default timeout to 3 minutes
Modified:
hbase/branches/0.90/CHANGES.txt
hbase/branches/0.90/src/docbkx/book.xml
hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/master/HMaster.java
hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/master/HMasterCommandLine.java
hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/zookeeper/HQuorumPeer.java
hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/zookeeper/ZKUtil.java
hbase/branches/0.90/src/main/resources/hbase-default.xml
Modified: hbase/branches/0.90/CHANGES.txt
URL:
http://svn.apache.org/viewvc/hbase/branches/0.90/CHANGES.txt?rev=1038745&r1=1038744&r2=1038745&view=diff
==============================================================================
--- hbase/branches/0.90/CHANGES.txt (original)
+++ hbase/branches/0.90/CHANGES.txt Wed Nov 24 18:19:43 2010
@@ -1175,6 +1175,7 @@ Release 0.90.0 - Unreleased
HBASE-3230 Refresh our hadoop jar and update zookeeper to
just-released 3.3.2
HBASE-3231 Update to zookeeper 3.3.2.
+ HBASE-3273 Set the ZK default timeout to 3 minutes
NEW FEATURES
Modified: hbase/branches/0.90/src/docbkx/book.xml
URL:
http://svn.apache.org/viewvc/hbase/branches/0.90/src/docbkx/book.xml?rev=1038745&r1=1038744&r2=1038745&view=diff
==============================================================================
--- hbase/branches/0.90/src/docbkx/book.xml (original)
+++ hbase/branches/0.90/src/docbkx/book.xml Wed Nov 24 18:19:43 2010
@@ -299,7 +299,10 @@ Usually you'll want to use the latest ve
in branch-0.20-append to see list of patches involved.</para>
<para>HBase bundles the Apache branch-0.20-append Hadoop.
Replace the Hadoop jar bundled with HBase with that you have
- installed on your cluster to avoid version mismatch issues.
+ installed on your cluster to avoid version mismatch issues;
+ for example, versions of CDH do not have HDFS-724 whereas
+ Hadoops branch-0.20-append branch does have HDFS-724. This
+ patch changes the RPC version because protocol was changed.
</para>
</section>
<section xml:id="ssh"> <title>ssh</title>
@@ -984,6 +987,28 @@ to ensure well-formedness of your docume
</section>
<section xml:id="recommended_configurations"><title>Recommended
Configuations</title>
+ <section
xml:id="zookeeper.session.timeout"><title><varname>zookeeper.session.timeout</varname></title>
+ <para>The default timeout is three minutes (specified in
milliseconds). This means
+ that if a server crashes, it will be three minutes before the
Master notices
+ the crash and starts recovery. You might like to tune the
timeout down to
+ a minute or even less so the Master notices failures the sooner.
+ Before changing this value, be sure you have your JVM garbage
collection
+ configuration under control otherwise, a long garbage collection
that lasts
+ beyond the zookeeper session timeout will take out
+ your RegionServer (You might be fine with this -- you probably
want recovery to start
+ on the server if a RegionServer has been in GC for a long period of
time).</para>
+
+ <para>To change this configuration, edit
<filename>hbase-site.xml</filename>,
+ copy the changed file around the cluster and restart.</para>
+
+ <para>We set this value high to save our having to field noob
questions up on the mailing lists asking
+ why a RegionServer went down during a massive import. The usual
cause is that their JVM is untuned and
+ they are running into long GC pauses. Our thinking is that
+ while users are getting familiar with HBase, we'd save them
having to know all of its
+ intricacies. Later when they've built some confidence, then
they can play
+ with configuration such as this.
+ </para>
+ </section>
<section xml:id="big_memory">
<title>Configuration for large memory machines</title>
<para>
Modified:
hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/master/HMaster.java
URL:
http://svn.apache.org/viewvc/hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/master/HMaster.java?rev=1038745&r1=1038744&r2=1038745&view=diff
==============================================================================
---
hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/master/HMaster.java
(original)
+++
hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/master/HMaster.java
Wed Nov 24 18:19:43 2010
@@ -238,7 +238,7 @@ implements HMasterInterface, HMasterRegi
while (!amm.isActiveMaster()) {
LOG.debug("Waiting for master address ZNode to be written " +
"(Also watching cluster state node)");
- Thread.sleep(c.getInt("zookeeper.session.timeout", 60 * 1000));
+ Thread.sleep(c.getInt("zookeeper.session.timeout", 180 * 1000));
}
}
Modified:
hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/master/HMasterCommandLine.java
URL:
http://svn.apache.org/viewvc/hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/master/HMasterCommandLine.java?rev=1038745&r1=1038744&r2=1038745&view=diff
==============================================================================
---
hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/master/HMasterCommandLine.java
(original)
+++
hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/master/HMasterCommandLine.java
Wed Nov 24 18:19:43 2010
@@ -121,7 +121,6 @@ public class HMasterCommandLine extends
if (zkClientPort == 0) {
throw new IOException("No config value for
hbase.zookeeper.property.clientPort");
}
-
zooKeeperCluster.setTickTime(conf.getInt("hbase.zookeeper.property.tickTime",
3000));
zooKeeperCluster.setClientPort(zkClientPort);
int clientPort = zooKeeperCluster.startup(zkDataPath);
if (clientPort != zkClientPort) {
Modified:
hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/zookeeper/HQuorumPeer.java
URL:
http://svn.apache.org/viewvc/hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/zookeeper/HQuorumPeer.java?rev=1038745&r1=1038744&r2=1038745&view=diff
==============================================================================
---
hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/zookeeper/HQuorumPeer.java
(original)
+++
hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/zookeeper/HQuorumPeer.java
Wed Nov 24 18:19:43 2010
@@ -125,6 +125,10 @@ public class HQuorumPeer {
}
}
+ // Set the max session timeout from the provided client-side timeout
+ properties.setProperty("maxSessionTimeout",
+ conf.get("zookeeper.session.timeout", "180000"));
+
if (myId == -1) {
throw new IOException("Could not find my address: " + myAddress +
" in list of ZooKeeper quorum servers");
Modified:
hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/zookeeper/ZKUtil.java
URL:
http://svn.apache.org/viewvc/hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/zookeeper/ZKUtil.java?rev=1038745&r1=1038744&r2=1038745&view=diff
==============================================================================
---
hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/zookeeper/ZKUtil.java
(original)
+++
hbase/branches/0.90/src/main/java/org/apache/hadoop/hbase/zookeeper/ZKUtil.java
Wed Nov 24 18:19:43 2010
@@ -91,7 +91,7 @@ public class ZKUtil {
if(ensemble == null) {
throw new IOException("Unable to determine ZooKeeper ensemble");
}
- int timeout = conf.getInt("zookeeper.session.timeout", 60 * 1000);
+ int timeout = conf.getInt("zookeeper.session.timeout", 180 * 1000);
LOG.debug(descriptor + " opening connection to ZooKeeper with ensemble (" +
ensemble + ")");
return new ZooKeeper(ensemble, timeout, watcher);
Modified: hbase/branches/0.90/src/main/resources/hbase-default.xml
URL:
http://svn.apache.org/viewvc/hbase/branches/0.90/src/main/resources/hbase-default.xml?rev=1038745&r1=1038744&r2=1038745&view=diff
==============================================================================
--- hbase/branches/0.90/src/main/resources/hbase-default.xml (original)
+++ hbase/branches/0.90/src/main/resources/hbase-default.xml Wed Nov 24
18:19:43 2010
@@ -444,7 +444,7 @@
</property>
<property>
<name>zookeeper.session.timeout</name>
- <value>60000</value>
+ <value>180000</value>
<description>ZooKeeper session timeout.
HBase passes this to the zk quorum as suggested maximum time for a
session. See
http://hadoop.apache.org/zookeeper/docs/current/zookeeperProgrammers.html#ch_zkSessions
