[SPARK-3996]: Shade Jetty in Spark deliverables

(v2 of this patch with a fix that was only relevant for the maven build). This patch piggy-back's on vanzin's work to simplify the Guava shading, and adds Jetty as a shaded library in Spark. Other than adding Jetty, it consilidates the <artifactSet>'s into the root pom. I found it was a bit easier to follow that way, since you don't need to look into child pom's to find out specific artifact sets included in shading. Author: Patrick Wendell <patrick@databricks.com> Closes apache#4285 from pwendell/jetty and squashes the following commits: d3e7f4e [Patrick Wendell] Fix for shaded deps causing compile errors 19f0710 [Patrick Wendell] More code review feedback 961452d [Patrick Wendell] Responding to feedback from Marcello 6df25ca [Patrick Wendell] [WIP] [SPARK-3996]: Shade Jetty in Spark deliverables
matadorhong · Feb 2, 2015 · a15f6e3 · a15f6e3
1 parent 859f724
commit a15f6e3
Show file tree

Hide file tree

Showing 6 changed files with 95 additions and 15 deletions.
diff --git a/bin/compute-classpath.sh b/bin/compute-classpath.sh
@@ -50,8 +50,8 @@ fi
 if [ -n "$SPARK_PREPEND_CLASSES" ]; then
   echo "NOTE: SPARK_PREPEND_CLASSES is set, placing locally compiled Spark"\
     "classes ahead of assembly." >&2
+  # Spark classes
   CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SPARK_SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/core/target/jars/*"
   CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SPARK_SCALA_VERSION/classes"
@@ -63,6 +63,8 @@ if [ -n "$SPARK_PREPEND_CLASSES" ]; then
   CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/sql/hive-thriftserver/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/yarn/stable/target/scala-$SPARK_SCALA_VERSION/classes"
+  # Jars for shaded deps in their original form (copied here during build)
+  CLASSPATH="$CLASSPATH:$FWDIR/core/target/jars/*"
 fi
 
 # Use spark-assembly jar from either RELEASE or assembly directory

diff --git a/core/pom.xml b/core/pom.xml
@@ -94,22 +94,35 @@
       <groupId>org.apache.curator</groupId>
       <artifactId>curator-recipes</artifactId>
     </dependency>
+
+    <!-- Jetty dependencies promoted to compile here so they are shaded
+         and inlined into spark-core jar -->
     <dependency>
       <groupId>org.eclipse.jetty</groupId>
       <artifactId>jetty-plus</artifactId>
+      <scope>compile</scope>
     </dependency>
     <dependency>
       <groupId>org.eclipse.jetty</groupId>
       <artifactId>jetty-security</artifactId>
+      <scope>compile</scope>
     </dependency>
     <dependency>
       <groupId>org.eclipse.jetty</groupId>
       <artifactId>jetty-util</artifactId>
+      <scope>compile</scope>
     </dependency>
     <dependency>
       <groupId>org.eclipse.jetty</groupId>
       <artifactId>jetty-server</artifactId>
+      <scope>compile</scope>
     </dependency>
+    <dependency>
+      <groupId>org.eclipse.jetty</groupId>
+      <artifactId>jetty-http</artifactId>
+      <scope>compile</scope>
+    </dependency>
+
     <dependency>
       <groupId>org.apache.commons</groupId>
       <artifactId>commons-lang3</artifactId>
@@ -348,19 +361,24 @@
         <groupId>org.apache.maven.plugins</groupId>
         <artifactId>maven-dependency-plugin</artifactId>
         <executions>
+          <!-- When using SPARK_PREPEND_CLASSES Spark classes compiled locally don't use
+               shaded deps. So here we store jars in their original form which are added
+               when the classpath is computed. -->
           <execution>
             <id>copy-dependencies</id>
             <phase>package</phase>
             <goals>
               <goal>copy-dependencies</goal>
             </goals>
-            <configuration>
+           <configuration>
               <outputDirectory>${project.build.directory}</outputDirectory>
               <overWriteReleases>false</overWriteReleases>
               <overWriteSnapshots>false</overWriteSnapshots>
               <overWriteIfNewer>true</overWriteIfNewer>
               <useSubDirectoryPerType>true</useSubDirectoryPerType>
-              <includeArtifactIds>guava</includeArtifactIds>
+              <includeArtifactIds>
+                guava,jetty-io,jetty-http,jetty-plus,jetty-util,jetty-server
+              </includeArtifactIds>
               <silent>true</silent>
             </configuration>
           </execution>

diff --git a/network/common/pom.xml b/network/common/pom.xml
@@ -101,18 +101,6 @@
           </execution>
         </executions>
       </plugin>
-      <plugin>
-        <groupId>org.apache.maven.plugins</groupId>
-        <artifactId>maven-shade-plugin</artifactId>
-        <configuration>
-          <shadedArtifactAttached>false</shadedArtifactAttached>
-          <artifactSet>
-            <includes>
-              <include>com.google.guava:guava</include>
-            </includes>
-          </artifactSet>
-        </configuration>
-      </plugin>
     </plugins>
   </build>
 </project>
diff --git a/pom.xml b/pom.xml
@@ -337,32 +337,48 @@
           </exclusion>
         </exclusions>
       </dependency>
+
+      <!-- Shaded deps marked as provided. These are promoted to compile scope
+           in the modules where we want the shaded classes to appear in the
+           associated jar. -->
+      <dependency>
+        <groupId>org.eclipse.jetty</groupId>
+        <artifactId>jetty-http</artifactId>
+        <version>${jetty.version}</version>
+        <scope>provided</scope>
+      </dependency>
       <dependency>
         <groupId>org.eclipse.jetty</groupId>
         <artifactId>jetty-util</artifactId>
         <version>${jetty.version}</version>
+        <scope>provided</scope>
       </dependency>
       <dependency>
         <groupId>org.eclipse.jetty</groupId>
         <artifactId>jetty-security</artifactId>
         <version>${jetty.version}</version>
+        <scope>provided</scope>
       </dependency>
       <dependency>
         <groupId>org.eclipse.jetty</groupId>
         <artifactId>jetty-plus</artifactId>
         <version>${jetty.version}</version>
+        <scope>provided</scope>
       </dependency>
       <dependency>
         <groupId>org.eclipse.jetty</groupId>
         <artifactId>jetty-server</artifactId>
         <version>${jetty.version}</version>
+        <scope>provided</scope>
       </dependency>
       <dependency>
         <groupId>com.google.guava</groupId>
         <artifactId>guava</artifactId>
         <version>14.0.1</version>
         <scope>provided</scope>
       </dependency>
+      <!-- End of shaded deps -->
+
       <dependency>
         <groupId>org.apache.commons</groupId>
         <artifactId>commons-lang3</artifactId>
@@ -1276,10 +1292,26 @@
           <shadedArtifactAttached>false</shadedArtifactAttached>
           <artifactSet>
             <includes>
+              <!-- At a minimum we must include this to force effective pom generation -->
               <include>org.spark-project.spark:unused</include>
+
+              <include>org.eclipse.jetty:jetty-io</include>
+              <include>org.eclipse.jetty:jetty-http</include>
+              <include>org.eclipse.jetty:jetty-plus</include>
+              <include>org.eclipse.jetty:jetty-security</include>
+              <include>org.eclipse.jetty:jetty-util</include>
+              <include>org.eclipse.jetty:jetty-server</include>
+              <include>com.google.guava:guava</include>
             </includes>
           </artifactSet>
           <relocations>
+            <relocation>
+              <pattern>org.eclipse.jetty</pattern>
+              <shadedPattern>org.spark-project.jetty</shadedPattern>
+              <includes>
+                <include>org.eclipse.jetty.**</include>
+              </includes>
+            </relocation>
             <relocation>
               <pattern>com.google.common</pattern>
               <shadedPattern>org.spark-project.guava</shadedPattern>

diff --git a/repl/pom.xml b/repl/pom.xml
@@ -87,6 +87,30 @@
       <artifactId>scalacheck_${scala.binary.version}</artifactId>
       <scope>test</scope>
     </dependency>
+
+    <!-- Explicit listing of transitive deps that are shaded. Otherwise, odd compiler crashes. -->
+    <dependency>
+      <groupId>org.eclipse.jetty</groupId>
+      <artifactId>jetty-server</artifactId>
+    </dependency>
+    <dependency>
+      <groupId>org.eclipse.jetty</groupId>
+      <artifactId>jetty-plus</artifactId>
+    </dependency>
+    <dependency>
+      <groupId>org.eclipse.jetty</groupId>
+      <artifactId>jetty-util</artifactId>
+    </dependency>
+    <dependency>
+      <groupId>org.eclipse.jetty</groupId>
+      <artifactId>jetty-http</artifactId>
+    </dependency>
+    <!-- End of shaded deps. -->
+
+    <dependency>
+      <groupId>org.scala-lang</groupId>
+      <artifactId>scala-library</artifactId>
+    </dependency>
   </dependencies>
   <build>
     <outputDirectory>target/scala-${scala.binary.version}/classes</outputDirectory>

diff --git a/streaming/pom.xml b/streaming/pom.xml
@@ -40,6 +40,8 @@
       <artifactId>spark-core_${scala.binary.version}</artifactId>
       <version>${project.version}</version>
     </dependency>
+
+    <!-- Explicit listing of transitive deps that are shaded. Otherwise, odd compiler crashes. -->
     <dependency>
       <groupId>com.google.guava</groupId>
       <artifactId>guava</artifactId>
@@ -48,6 +50,20 @@
       <groupId>org.eclipse.jetty</groupId>
       <artifactId>jetty-server</artifactId>
     </dependency>
+    <dependency>
+      <groupId>org.eclipse.jetty</groupId>
+      <artifactId>jetty-plus</artifactId>
+    </dependency>
+    <dependency>
+      <groupId>org.eclipse.jetty</groupId>
+      <artifactId>jetty-util</artifactId>
+    </dependency>
+    <dependency>
+      <groupId>org.eclipse.jetty</groupId>
+      <artifactId>jetty-http</artifactId>
+    </dependency>
+    <!-- End of shaded deps. -->
+
     <dependency>
       <groupId>org.scala-lang</groupId>
       <artifactId>scala-library</artifactId>