From c3f5e075335a65ea522b2f76716921ec056c52ed Mon Sep 17 00:00:00 2001
From: Patrick Wendell <pwendell@gmail.com>
Date: Sun, 2 Mar 2014 15:18:19 -0800
Subject: [PATCH] SPARK-1121: Include avro for yarn-alpha builds
This lets us explicitly include Avro based on a profile for 0.23.X
builds. It makes me sad how convoluted it is to express this logic
in Maven. @tgraves and @sryza curious if this works for you.
I'm also considering just reverting to how it was before. The only
real problem was that Spark advertised a dependency on Avro
even though it only really depends transitively on Avro through
other deps.
Author: Patrick Wendell <pwendell@gmail.com>
Closes #49 from pwendell/avro-build-fix and squashes the following commits:
8d6ee92 [Patrick Wendell] SPARK-1121: Add avro to yarn-alpha profile
---
bagel/pom.xml | 14 ++++++++++++++
core/pom.xml | 14 ++++++++++++++
docs/building-with-maven.md | 4 ----
examples/pom.xml | 14 ++++++++++++++
external/flume/pom.xml | 14 ++++++++++++++
external/kafka/pom.xml | 14 ++++++++++++++
external/mqtt/pom.xml | 14 ++++++++++++++
external/twitter/pom.xml | 14 ++++++++++++++
external/zeromq/pom.xml | 14 ++++++++++++++
graphx/pom.xml | 14 ++++++++++++++
mllib/pom.xml | 14 ++++++++++++++
pom.xml | 15 +++++++++++++++
repl/pom.xml | 14 ++++++++++++++
streaming/pom.xml | 14 ++++++++++++++
tools/pom.xml | 14 ++++++++++++++
yarn/alpha/pom.xml | 14 ++++++++++++++
yarn/pom.xml | 17 +++++++++--------
yarn/stable/pom.xml | 14 ++++++++++++++
18 files changed, 234 insertions(+), 12 deletions(-)
diff --git a/bagel/pom.xml b/bagel/pom.xml
index 355f437c5b..41aacbd88a 100644
--- a/bagel/pom.xml
+++ b/bagel/pom.xml
@@ -31,6 +31,20 @@
<name>Spark Project Bagel</name>
<url>http://spark.apache.org/</url>
+ <profiles>
+ <profile>
+ <!-- SPARK-1121: SPARK-1121: Adds an explicit dependency on Avro to work around
+ a Hadoop 0.23.X issue -->
+ <id>yarn-alpha</id>
+ <dependencies>
+ <dependency>
+ <groupId>org.apache.avro</groupId>
+ <artifactId>avro</artifactId>
+ </dependency>
+ </dependencies>
+ </profile>
+ </profiles>
+
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
diff --git a/core/pom.xml b/core/pom.xml
index 2afd250825..99c841472b 100644
--- a/core/pom.xml
+++ b/core/pom.xml
@@ -31,6 +31,20 @@
<name>Spark Project Core</name>
<url>http://spark.apache.org/</url>
+ <!-- SPARK-1121: SPARK-1121: Adds an explicit dependency on Avro to work around
+ a Hadoop 0.23.X issue -->
+ <profiles>
+ <profile>
+ <id>yarn-alpha</id>
+ <dependencies>
+ <dependency>
+ <groupId>org.apache.avro</groupId>
+ <artifactId>avro</artifactId>
+ </dependency>
+ </dependencies>
+ </profile>
+ </profiles>
+
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
diff --git a/docs/building-with-maven.md b/docs/building-with-maven.md
index 40cac8eb4f..ded1292688 100644
--- a/docs/building-with-maven.md
+++ b/docs/building-with-maven.md
@@ -76,7 +76,3 @@ The maven build includes support for building a Debian package containing the as
$ mvn -Pdeb -DskipTests clean package
The debian package can then be found under assembly/target. We added the short commit hash to the file name so that we can distinguish individual packages built for SNAPSHOT versions.
-
-## A note about Hadoop version 0.23.x
-
-For building spark with hadoop 0.23.x and also yarn, you will have to manually add a dependency on avro (org.apache.avro, avro, 1.7.4).
diff --git a/examples/pom.xml b/examples/pom.xml
index d952e2ca4e..3aba343f4c 100644
--- a/examples/pom.xml
+++ b/examples/pom.xml
@@ -31,6 +31,20 @@
<name>Spark Project Examples</name>
<url>http://spark.apache.org/</url>
+ <profiles>
+ <profile>
+ <!-- SPARK-1121: SPARK-1121: Adds an explicit dependency on Avro to work around
+ a Hadoop 0.23.X issue -->
+ <id>yarn-alpha</id>
+ <dependencies>
+ <dependency>
+ <groupId>org.apache.avro</groupId>
+ <artifactId>avro</artifactId>
+ </dependency>
+ </dependencies>
+ </profile>
+ </profiles>
+
<repositories>
<repository>
<id>apache-repo</id>
diff --git a/external/flume/pom.xml b/external/flume/pom.xml
index bc00ab4573..8783aea3e4 100644
--- a/external/flume/pom.xml
+++ b/external/flume/pom.xml
@@ -31,6 +31,20 @@
<name>Spark Project External Flume</name>
<url>http://spark.apache.org/</url>
+ <profiles>
+ <profile>
+ <!-- SPARK-1121: SPARK-1121: Adds an explicit dependency on Avro to work around
+ a Hadoop 0.23.X issue -->
+ <id>yarn-alpha</id>
+ <dependencies>
+ <dependency>
+ <groupId>org.apache.avro</groupId>
+ <artifactId>avro</artifactId>
+ </dependency>
+ </dependencies>
+ </profile>
+ </profiles>
+
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
diff --git a/external/kafka/pom.xml b/external/kafka/pom.xml
index 979eb0ca62..79dc38f984 100644
--- a/external/kafka/pom.xml
+++ b/external/kafka/pom.xml
@@ -31,6 +31,20 @@
<name>Spark Project External Kafka</name>
<url>http://spark.apache.org/</url>
+ <profiles>
+ <profile>
+ <!-- SPARK-1121: SPARK-1121: Adds an explicit dependency on Avro to work around
+ a Hadoop 0.23.X issue -->
+ <id>yarn-alpha</id>
+ <dependencies>
+ <dependency>
+ <groupId>org.apache.avro</groupId>
+ <artifactId>avro</artifactId>
+ </dependency>
+ </dependencies>
+ </profile>
+ </profiles>
+
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
diff --git a/external/mqtt/pom.xml b/external/mqtt/pom.xml
index 2c476b402e..06c751df7f 100644
--- a/external/mqtt/pom.xml
+++ b/external/mqtt/pom.xml
@@ -31,6 +31,20 @@
<name>Spark Project External MQTT</name>
<url>http://spark.apache.org/</url>
+ <profiles>
+ <profile>
+ <!-- SPARK-1121: SPARK-1121: Adds an explicit dependency on Avro to work around
+ a Hadoop 0.23.X issue -->
+ <id>yarn-alpha</id>
+ <dependencies>
+ <dependency>
+ <groupId>org.apache.avro</groupId>
+ <artifactId>avro</artifactId>
+ </dependency>
+ </dependencies>
+ </profile>
+ </profiles>
+
<repositories>
<repository>
<id>mqtt-repo</id>
diff --git a/external/twitter/pom.xml b/external/twitter/pom.xml
index a443459594..37bb4fad64 100644
--- a/external/twitter/pom.xml
+++ b/external/twitter/pom.xml
@@ -31,6 +31,20 @@
<name>Spark Project External Twitter</name>
<url>http://spark.apache.org/</url>
+ <profiles>
+ <profile>
+ <!-- SPARK-1121: SPARK-1121: Adds an explicit dependency on Avro to work around
+ a Hadoop 0.23.X issue -->
+ <id>yarn-alpha</id>
+ <dependencies>
+ <dependency>
+ <groupId>org.apache.avro</groupId>
+ <artifactId>avro</artifactId>
+ </dependency>
+ </dependencies>
+ </profile>
+ </profiles>
+
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
diff --git a/external/zeromq/pom.xml b/external/zeromq/pom.xml
index a40e55876e..65ec0e26da 100644
--- a/external/zeromq/pom.xml
+++ b/external/zeromq/pom.xml
@@ -31,6 +31,20 @@
<name>Spark Project External ZeroMQ</name>
<url>http://spark.apache.org/</url>
+ <profiles>
+ <profile>
+ <!-- SPARK-1121: SPARK-1121: Adds an explicit dependency on Avro to work around
+ a Hadoop 0.23.X issue -->
+ <id>yarn-alpha</id>
+ <dependencies>
+ <dependency>
+ <groupId>org.apache.avro</groupId>
+ <artifactId>avro</artifactId>
+ </dependency>
+ </dependencies>
+ </profile>
+ </profiles>
+
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
diff --git a/graphx/pom.xml b/graphx/pom.xml
index 2b4d674221..5b54dd27ef 100644
--- a/graphx/pom.xml
+++ b/graphx/pom.xml
@@ -31,6 +31,20 @@
<name>Spark Project GraphX</name>
<url>http://spark-project.org/</url>
+ <profiles>
+ <profile>
+ <!-- SPARK-1121: SPARK-1121: Adds an explicit dependency on Avro to work around
+ a Hadoop 0.23.X issue -->
+ <id>yarn-alpha</id>
+ <dependencies>
+ <dependency>
+ <groupId>org.apache.avro</groupId>
+ <artifactId>avro</artifactId>
+ </dependency>
+ </dependencies>
+ </profile>
+ </profiles>
+
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
diff --git a/mllib/pom.xml b/mllib/pom.xml
index c0e745dadb..760a2a85d5 100644
--- a/mllib/pom.xml
+++ b/mllib/pom.xml
@@ -31,6 +31,20 @@
<name>Spark Project ML Library</name>
<url>http://spark.apache.org/</url>
+ <profiles>
+ <profile>
+ <!-- SPARK-1121: SPARK-1121: Adds an explicit dependency on Avro to work around
+ a Hadoop 0.23.X issue -->
+ <id>yarn-alpha</id>
+ <dependencies>
+ <dependency>
+ <groupId>org.apache.avro</groupId>
+ <artifactId>avro</artifactId>
+ </dependency>
+ </dependencies>
+ </profile>
+ </profiles>
+
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
diff --git a/pom.xml b/pom.xml
index 7e04efaa9c..7e28d7c194 100644
--- a/pom.xml
+++ b/pom.xml
@@ -425,6 +425,21 @@
</exclusion>
</exclusions>
</dependency>
+ <dependency>
+ <groupId>org.apache.avro</groupId>
+ <artifactId>avro</artifactId>
+ <version>1.7.4</version>
+ <exclusions>
+ <exclusion>
+ <groupId>org.jboss.netty</groupId>
+ <artifactId>netty</artifactId>
+ </exclusion>
+ <exclusion>
+ <groupId>io.netty</groupId>
+ <artifactId>netty</artifactId>
+ </exclusion>
+ </exclusions>
+ </dependency>
<dependency>
<groupId>net.java.dev.jets3t</groupId>
<artifactId>jets3t</artifactId>
diff --git a/repl/pom.xml b/repl/pom.xml
index 3a6baf5c42..aa01a17602 100644
--- a/repl/pom.xml
+++ b/repl/pom.xml
@@ -31,6 +31,20 @@
<name>Spark Project REPL</name>
<url>http://spark.apache.org/</url>
+ <!-- SPARK-1121: SPARK-1121: Adds an explicit dependency on Avro to work around
+ a Hadoop 0.23.X issue -->
+ <profiles>
+ <profile>
+ <id>yarn-alpha</id>
+ <dependencies>
+ <dependency>
+ <groupId>org.apache.avro</groupId>
+ <artifactId>avro</artifactId>
+ </dependency>
+ </dependencies>
+ </profile>
+ </profiles>
+
<properties>
<deb.install.path>/usr/share/spark</deb.install.path>
<deb.user>root</deb.user>
diff --git a/streaming/pom.xml b/streaming/pom.xml
index 1f3366e25f..91d6a1375a 100644
--- a/streaming/pom.xml
+++ b/streaming/pom.xml
@@ -31,6 +31,20 @@
<name>Spark Project Streaming</name>
<url>http://spark.apache.org/</url>
+ <profiles>
+ <profile>
+ <!-- SPARK-1121: SPARK-1121: Adds an explicit dependency on Avro to work around
+ a Hadoop 0.23.X issue -->
+ <id>yarn-alpha</id>
+ <dependencies>
+ <dependency>
+ <groupId>org.apache.avro</groupId>
+ <artifactId>avro</artifactId>
+ </dependency>
+ </dependencies>
+ </profile>
+ </profiles>
+
<repositories>
<repository>
<id>apache-repo</id>
diff --git a/tools/pom.xml b/tools/pom.xml
index 67f2d780f3..b8dd255d40 100644
--- a/tools/pom.xml
+++ b/tools/pom.xml
@@ -30,6 +30,20 @@
<name>Spark Project Tools</name>
<url>http://spark.apache.org/</url>
+ <!-- SPARK-1121: SPARK-1121: Adds an explicit dependency on Avro to work around
+ a Hadoop 0.23.X issue -->
+ <profiles>
+ <profile>
+ <id>yarn-alpha</id>
+ <dependencies>
+ <dependency>
+ <groupId>org.apache.avro</groupId>
+ <artifactId>avro</artifactId>
+ </dependency>
+ </dependencies>
+ </profile>
+ </profiles>
+
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
diff --git a/yarn/alpha/pom.xml b/yarn/alpha/pom.xml
index e076ca1d44..bfe12ecec0 100644
--- a/yarn/alpha/pom.xml
+++ b/yarn/alpha/pom.xml
@@ -24,6 +24,20 @@
<relativePath>../pom.xml</relativePath>
</parent>
+ <profiles>
+ <profile>
+ <!-- SPARK-1121: SPARK-1121: Adds an explicit dependency on Avro to work around
+ a Hadoop 0.23.X issue -->
+ <id>yarn-alpha</id>
+ <dependencies>
+ <dependency>
+ <groupId>org.apache.avro</groupId>
+ <artifactId>avro</artifactId>
+ </dependency>
+ </dependencies>
+ </profile>
+ </profiles>
+
<groupId>org.apache.spark</groupId>
<artifactId>spark-yarn-alpha_2.10</artifactId>
<packaging>jar</packaging>
diff --git a/yarn/pom.xml b/yarn/pom.xml
index be51679292..35e31760c1 100644
--- a/yarn/pom.xml
+++ b/yarn/pom.xml
@@ -52,14 +52,6 @@
<artifactId>hadoop-client</artifactId>
<version>${yarn.version}</version>
</dependency>
- <dependency>
- <groupId>org.apache.avro</groupId>
- <artifactId>avro</artifactId>
- </dependency>
- <dependency>
- <groupId>org.apache.avro</groupId>
- <artifactId>avro-ipc</artifactId>
- </dependency>
<dependency>
<groupId>org.scalatest</groupId>
<artifactId>scalatest_${scala.binary.version}</artifactId>
@@ -78,6 +70,15 @@
<modules>
<module>alpha</module>
</modules>
+
+ <!-- SPARK-1121: SPARK-1121: Adds an explicit dependency on Avro to work around
+ a Hadoop 0.23.X issue -->
+ <dependencies>
+ <dependency>
+ <groupId>org.apache.avro</groupId>
+ <artifactId>avro</artifactId>
+ </dependency>
+ </dependencies>
</profile>
<profile>
diff --git a/yarn/stable/pom.xml b/yarn/stable/pom.xml
index 0780f251b5..9d68603251 100644
--- a/yarn/stable/pom.xml
+++ b/yarn/stable/pom.xml
@@ -24,6 +24,20 @@
<relativePath>../pom.xml</relativePath>
</parent>
+ <profiles>
+ <profile>
+ <!-- SPARK-1121: SPARK-1121: Adds an explicit dependency on Avro to work around
+ a Hadoop 0.23.X issue -->
+ <id>yarn-alpha</id>
+ <dependencies>
+ <dependency>
+ <groupId>org.apache.avro</groupId>
+ <artifactId>avro</artifactId>
+ </dependency>
+ </dependencies>
+ </profile>
+ </profiles>
+
<groupId>org.apache.spark</groupId>
<artifactId>spark-yarn_2.10</artifactId>
<packaging>jar</packaging>
--
GitLab