[SPARK-4236] Cleanup removed applications' files in shuffle service

This relies on a hook from whoever is hosting the shuffle service to invoke removeApplication() when the application is completed. Once invoked, we will clean up all the executors' shuffle directories we know about.

Author: Aaron Davidson <aaron@databricks.com>

Closes #3126 from aarondav/cleanup and squashes the following commits:

33a64a9 [Aaron Davidson] Missing brace
e6e428f [Aaron Davidson] Address comments
16a0d27 [Aaron Davidson] Cleanup
e4df3e7 [Aaron Davidson] [SPARK-4236] Cleanup removed applications' files in shuffle service

1 files changed, 59 insertions, 0 deletions

diff --git a/network/common/src/main/java/org/apache/spark/network/util/JavaUtils.java b/network/common/src/main/java/org/apache/spark/network/util/JavaUtils.java
index 2856d1c8c9..75c4a3981a 100644
--- a/network/common/src/main/java/org/apache/spark/network/util/JavaUtils.java
+++ b/network/common/src/main/java/org/apache/spark/network/util/JavaUtils.java
@@ -22,16 +22,22 @@ import java.nio.ByteBuffer;
 import java.io.ByteArrayInputStream;
 import java.io.ByteArrayOutputStream;
 import java.io.Closeable;
+import java.io.File;
 import java.io.IOException;
 import java.io.ObjectInputStream;
 import java.io.ObjectOutputStream;
 
+import com.google.common.base.Preconditions;
 import com.google.common.io.Closeables;
 import com.google.common.base.Charsets;
 import io.netty.buffer.Unpooled;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 
+/**
+ * General utilities available in the network package. Many of these are sourced from Spark's
+ * own Utils, just accessible within this package.
+ */
 public class JavaUtils {
   private static final Logger logger = LoggerFactory.getLogger(JavaUtils.class);
 
@@ -93,4 +99,57 @@ public class JavaUtils {
   public static String bytesToString(ByteBuffer b) {
     return Unpooled.wrappedBuffer(b).toString(Charsets.UTF_8);
   }
+
+  /*
+   * Delete a file or directory and its contents recursively.
+   * Don't follow directories if they are symlinks.
+   * Throws an exception if deletion is unsuccessful.
+   */
+  public static void deleteRecursively(File file) throws IOException {
+    if (file == null) { return; }
+
+    if (file.isDirectory() && !isSymlink(file)) {
+      IOException savedIOException = null;
+      for (File child : listFilesSafely(file)) {
+        try {
+          deleteRecursively(child);
+        } catch (IOException e) {
+          // In case of multiple exceptions, only last one will be thrown
+          savedIOException = e;
+        }
+      }
+      if (savedIOException != null) {
+        throw savedIOException;
+      }
+    }
+
+    boolean deleted = file.delete();
+    // Delete can also fail if the file simply did not exist.
+    if (!deleted && file.exists()) {
+      throw new IOException("Failed to delete: " + file.getAbsolutePath());
+    }
+  }
+
+  private static File[] listFilesSafely(File file) throws IOException {
+    if (file.exists()) {
+      File[] files = file.listFiles();
+      if (files == null) {
+        throw new IOException("Failed to list files for dir: " + file);
+      }
+      return files;
+    } else {
+      return new File[0];
+    }
+  }
+
+  private static boolean isSymlink(File file) throws IOException {
+    Preconditions.checkNotNull(file);
+    File fileInCanonicalDir = null;
+    if (file.getParent() == null) {
+      fileInCanonicalDir = file;
+    } else {
+      fileInCanonicalDir = new File(file.getParentFile().getCanonicalFile(), file.getName());
+    }
+    return !fileInCanonicalDir.getCanonicalFile().equals(fileInCanonicalDir.getAbsoluteFile());
+  }
 }