[SPARK-26118][WEB UI] Introducing spark.ui.requestHeaderSize for setting HTTP requestHeaderSize

attilapiros · attilapiros · commit 9513b3f0de8d · 2018-11-22T03:22:56.000+01:00
Introducing spark.ui.requestHeaderSize for configuring Jetty's HTTP requestHeaderSize. This way long authorization field does not lead to HTTP 413. Manually with curl (which version must be at least 7.55). With the original default value (8k limit): ```bash $ ./sbin/start-history-server.sh starting org.apache.spark.deploy.history.HistoryServer, logging to /Users/attilapiros/github/spark/logs/spark-attilapiros-org.apache.spark.deploy.history.HistoryServer-1-apiros-MBP.lan.out $ echo -n "X-Custom-Header: " > cookie $ printf 'A%.0s' {1..9500} >> cookie $ curl -H cookie http://458apiros-MBP.lan:18080/ <h1>Bad Message 431</h1><pre>reason: Request Header Fields Too Large</pre> $ tail -1 /Users/attilapiros/github/spark/logs/spark-attilapiros-org.apache.spark.deploy.history.HistoryServer-1-apiros-MBP.lan.out 18/11/19 21:24:28 WARN HttpParser: Header is too large 8193>8192 ``` After: ```bash $ echo spark.ui.requestHeaderSize=10000 > history.properties $ ./sbin/start-history-server.sh --properties-file history.properties starting org.apache.spark.deploy.history.HistoryServer, logging to /Users/attilapiros/github/spark/logs/spark-attilapiros-org.apache.spark.deploy.history.HistoryServer-1-apiros-MBP.lan.out $ curl -H cookie http://458apiros-MBP.lan:18080/ <!DOCTYPE html><html> <head>... <link rel="shortcut icon" href="/static/spark-logo-77x50px-hd.png"></link> <title>History Server</title> </head> <body> ... ``` (cherry picked from commit ab61ddb)
diff --git a/core/src/main/scala/org/apache/spark/internal/config/package.scala b/core/src/main/scala/org/apache/spark/internal/config/package.scala
@@ -312,4 +312,11 @@ package object config {
         " service is disabled.")
       .bytesConf(ByteUnit.BYTE)
       .createWithDefault(Long.MaxValue)
+
+  private[spark] val UI_REQUEST_HEADER_SIZE =
+    ConfigBuilder("spark.ui.requestHeaderSize")
+      .doc("Value for HTTP request header size in bytes.")
+      .bytesConf(ByteUnit.BYTE)
+      .createWithDefaultString("8k")
+
 }
diff --git a/core/src/main/scala/org/apache/spark/ui/JettyUtils.scala b/core/src/main/scala/org/apache/spark/ui/JettyUtils.scala
@@ -40,6 +40,7 @@ import org.json4s.jackson.JsonMethods.{pretty, render}
 
 import org.apache.spark.{SecurityManager, SparkConf, SSLOptions}
 import org.apache.spark.internal.Logging
+import org.apache.spark.internal.config._
 import org.apache.spark.util.Utils
 
 /**
@@ -342,13 +343,15 @@ private[spark] object JettyUtils extends Logging {
 
         (connector, connector.getLocalPort())
       }
+      val httpConfig = new HttpConfiguration()
+      httpConfig.setRequestHeaderSize(conf.get(UI_REQUEST_HEADER_SIZE).toInt)
 
       // If SSL is configured, create the secure connector first.
       val securePort = sslOptions.createJettySslContextFactory().map { factory =>
         val securePort = sslOptions.port.getOrElse(if (port > 0) Utils.userPort(port, 400) else 0)
         val secureServerName = if (serverName.nonEmpty) s"$serverName (HTTPS)" else serverName
         val connectionFactories = AbstractConnectionFactory.getFactories(factory,
-          new HttpConnectionFactory())
+          new HttpConnectionFactory(httpConfig))
 
         def sslConnect(currentPort: Int): (ServerConnector, Int) = {
           newConnector(connectionFactories, currentPort)
@@ -363,7 +366,7 @@ private[spark] object JettyUtils extends Logging {
 
       // Bind the HTTP port.
       def httpConnect(currentPort: Int): (ServerConnector, Int) = {
-        newConnector(Array(new HttpConnectionFactory()), currentPort)
+        newConnector(Array(new HttpConnectionFactory(httpConfig)), currentPort)
       }
 
       val (httpConnector, httpPort) = Utils.startServiceOnPort[ServerConnector](port, httpConnect,
diff --git a/docs/configuration.md b/docs/configuration.md
@@ -801,6 +801,14 @@ Apart from these, the following properties are also available, and may be useful
     How many dead executors the Spark UI and status APIs remember before garbage collecting.
   </td>
 </tr>
+<tr>
+  <td><code>spark.ui.requestHeaderSize</code></td>
+  <td>8k</td>
+  <td>
+    The maximum allowed size for a HTTP request header, in bytes unless otherwise specified.
+    This setting applies for the Spark History Server too.
+  <td>
+</tr>
 </table>
 
 ### Compression and Serialization
