From 3f37354daae7703779b767b22e5328dc13fa65c6 Mon Sep 17 00:00:00 2001
From: yliu <yliu@apache.org>
Date: Wed, 21 Jan 2015 00:57:51 +0800
Subject: [PATCH] HDFS-7623. Add htrace configuration properties to
 core-default.xml and update user doc about how to enable htrace. (yliu)

---
 .../src/main/resources/core-default.xml       | 24 ++++++++++++++++++
 .../hadoop-common/src/site/apt/Tracing.apt.vm | 25 ++++++++++++++-----
 hadoop-hdfs-project/hadoop-hdfs/CHANGES.txt   |  3 +++
 3 files changed, 46 insertions(+), 6 deletions(-)

diff --git a/hadoop-common-project/hadoop-common/src/main/resources/core-default.xml b/hadoop-common-project/hadoop-common/src/main/resources/core-default.xml
index 4ba2e5ad61b..4a9c3da0390 100644
--- a/hadoop-common-project/hadoop-common/src/main/resources/core-default.xml
+++ b/hadoop-common-project/hadoop-common/src/main/resources/core-default.xml
@@ -1646,4 +1646,28 @@ for ldap providers in the same way as above does.
   </description>
 </property>
 
+<property>
+  <name>hadoop.htrace.sampler</name>
+  <value>NeverSampler</value>
+  <description>
+    Configure the samplers for HTrace, the value can be NeverSampler,
+    AlwaysSampler or ProbabilitySampler. NeverSampler: HTrace is OFF 
+    for all spans; AlwaysSampler: HTrace is ON for all spans;
+    ProbabilitySampler: HTrace is ON for some percentage% of top-level 
+    spans.
+  </description>
+</property>
+
+<property>
+  <name>hadoop.htrace.spanreceiver.classes</name>
+  <value></value>
+  <description>
+    A comma separated list of the fully-qualified class name of classes 
+    implementing SpanReceiver. The tracing system works by collecting 
+    information in structs called 'Spans'. It is up to you to choose 
+    how you want to receive this information by implementing the 
+    SpanReceiver interface.
+  </description>
+</property>
+
 </configuration>
diff --git a/hadoop-common-project/hadoop-common/src/site/apt/Tracing.apt.vm b/hadoop-common-project/hadoop-common/src/site/apt/Tracing.apt.vm
index 9eda2208ba5..f04da337af5 100644
--- a/hadoop-common-project/hadoop-common/src/site/apt/Tracing.apt.vm
+++ b/hadoop-common-project/hadoop-common/src/site/apt/Tracing.apt.vm
@@ -16,19 +16,32 @@
   ---
   ${maven.build.timestamp}
 
-Enabling Dapper-like Tracing in HDFS
+Enabling Dapper-like Tracing in Hadoop
 
 %{toc|section=1|fromDepth=0}
 
-* {Dapper-like Tracing in HDFS}
+* {Dapper-like Tracing in Hadoop}
 
 ** HTrace
 
   {{{https://issues.apache.org/jira/browse/HDFS-5274}HDFS-5274}}
   added support for tracing requests through HDFS,
-  using the open source tracing library, {{{https://github.com/cloudera/htrace}HTrace}}.
+  using the open source tracing library, {{{https://git-wip-us.apache.org/repos/asf/incubator-htrace.git}Apache HTrace}}.
   Setting up tracing is quite simple, however it requires some very minor changes to your client code.
 
+** Samplers
+  Configure the samplers in <<<core-site.xml>>> property: <<<hadoop.htrace.sampler>>>.
+  The value can be NeverSampler, AlwaysSampler or ProbabilitySampler. NeverSampler: HTrace is OFF 
+  for all spans; AlwaysSampler: HTrace is ON for all spans; ProbabilitySampler: HTrace is ON for 
+  some percentage% of top-level spans.
+
++----
+  <property>
+    <name>hadoop.htrace.sampler</name>
+    <value>NeverSampler</value>
+  </property>
++----
+
 ** SpanReceivers
 
   The tracing system works by collecting information in structs called 'Spans'.
@@ -42,7 +55,7 @@ public void receiveSpan(Span span);
   Configure what SpanReceivers you'd like to use
   by putting a comma separated list of the fully-qualified class name of
   classes implementing SpanReceiver
-  in <<<hdfs-site.xml>>> property: <<<hadoop.htrace.spanreceiver.classes>>>.
+  in <<<core-site.xml>>> property: <<<hadoop.htrace.spanreceiver.classes>>>.
 
 +----
   <property>
@@ -83,11 +96,11 @@ public void receiveSpan(Span span);
   $ git clone https://github.com/cloudera/htrace
   $ cd htrace/htrace-zipkin
   $ mvn compile assembly:single
-  $ cp target/htrace-zipkin-*-jar-with-dependencies.jar $HADOOP_HOME/share/hadoop/hdfs/lib/
+  $ cp target/htrace-zipkin-*-jar-with-dependencies.jar $HADOOP_HOME/share/hadoop/common/lib/
 +----
 
   The sample configuration for <<<ZipkinSpanReceiver>>> is shown below.
-  By adding these to <<<hdfs-site.xml>>> of NameNode and DataNodes,
+  By adding these to <<<core-site.xml>>> of NameNode and DataNodes,
   <<<ZipkinSpanReceiver>>> is initialized on the startup.
   You also need this configuration on the client node in addition to the servers.
 
diff --git a/hadoop-hdfs-project/hadoop-hdfs/CHANGES.txt b/hadoop-hdfs-project/hadoop-hdfs/CHANGES.txt
index dc78530f8a2..53a23fd1826 100644
--- a/hadoop-hdfs-project/hadoop-hdfs/CHANGES.txt
+++ b/hadoop-hdfs-project/hadoop-hdfs/CHANGES.txt
@@ -258,6 +258,9 @@ Release 2.7.0 - UNRELEASED
 
     HDFS-7640. Print NFS Client in the NFS log. (Brandon Li via wheat9)
 
+    HDFS-7623. Add htrace configuration properties to core-default.xml and
+    update user doc about how to enable htrace. (yliu)
+
   OPTIMIZATIONS
 
     HDFS-7454. Reduce memory footprint for AclEntries in NameNode.