diff --git a/docs/configuration.md b/docs/configuration.md
index 099972ca1a..685101ea5c 100644
--- a/docs/configuration.md
+++ b/docs/configuration.md
@@ -371,6 +371,16 @@ Apart from these, the following properties are also available, and may be useful
     map-side aggregation and there are at most this many reduce partitions.
   </td>
 </tr>
+<tr>
+  <td><code>spark.shuffle.blockTransferService</code></td>
+  <td>netty</td>
+  <td>
+    Implementation to use for transferring shuffle and cached blocks between executors. There
+    are two implementations available: <code>netty</code> and <code>nio</code>. Netty-based
+    block transfer is intended to be simpler but equally efficient and is the default option
+    starting in 1.2.
+  </td>
+</tr>
 </table>
 
 #### Spark UI