[GitHub] HeartSaVioR commented on a change in pull request #23260: [SPARK-26311][YARN] New feature: custom log URL for stdout/stderr

[GitBox <gi...@apache.org>]

HeartSaVioR commented on a change in pull request #23260: [SPARK-26311][YARN] New feature: custom log URL for stdout/stderr
URL: https://github.com/apache/spark/pull/23260#discussion_r247335594
 
 

 ##########
 File path: resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ExecutorRunnable.scala
 ##########
 @@ -246,13 +253,57 @@ private[yarn] class ExecutorRunnable(
       sys.env.get("SPARK_USER").foreach { user =>
         val containerId = ConverterUtils.toString(c.getId)
         val address = c.getNodeHttpAddress
-        val baseUrl = s"$httpScheme$address/node/containerlogs/$containerId/$user"
 
-        env("SPARK_LOG_URL_STDERR") = s"$baseUrl/stderr?start=-4096"
-        env("SPARK_LOG_URL_STDOUT") = s"$baseUrl/stdout?start=-4096"
+        val customLogUrl = sparkConf.get(config.CUSTOM_LOG_URL)
+
+        val envNameToFileNameMap = Map("SPARK_LOG_URL_STDERR" -> "stderr",
+          "SPARK_LOG_URL_STDOUT" -> "stdout")
+        val logUrls = ExecutorRunnable.buildLogUrls(customLogUrl, httpScheme, address,
+          clusterId, containerId, user, envNameToFileNameMap)
+        logUrls.foreach { case (envName, url) =>
+          env(envName) = url
+        }
       }
     }
 
     env
   }
 }
+
+private[yarn] object ExecutorRunnable {
+  def buildLogUrls(
+      logUrlPattern: String,
+      httpScheme: String,
+      nodeHttpAddress: String,
+      clusterId: Option[String],
+      containerId: String,
+      user: String,
+      envNameToFileNameMap: Map[String, String]): Map[String, String] = {
+    val optionalPathVariable: Map[String, Option[String]] = Map("{{ClusterId}}" -> clusterId)
+    val pathVariables: Map[String, String] = Map("{{HttpScheme}}" -> httpScheme,
 
 Review comment:
   My intention was to separate parameters by `mandatory` and `optional`. Mandatory parameters should be available for all the cases, whereas optional parameters are available only when Hadoop/YARN has configured like that.

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org