Github user squito commented on a diff in the pull request:
https://github.com/apache/spark/pull/4435#discussion_r27992507
--- Diff:
core/src/main/scala/org/apache/spark/status/api/v1/OneStageResource.scala ---
@@ -0,0 +1,192 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.spark.status.api.v1
+
+import javax.ws.rs._
+import javax.ws.rs.core.MediaType
+
+import org.apache.spark.SparkException
+import org.apache.spark.scheduler.StageInfo
+import org.apache.spark.ui.jobs.JobProgressListener
+import org.apache.spark.ui.jobs.UIData.StageUIData
+import org.apache.spark.util.SparkEnum
+
+@Produces(Array(MediaType.APPLICATION_JSON))
+private[v1] class OneStageResource(uiRoot: UIRoot) {
+
+ @GET
+ @Path("")
+ def stageData(
+ @PathParam("appId") appId: String,
+ @PathParam("stageId") stageId: Int
+ ): Seq[StageData] = {
+ forStage(appId, stageId){ (listener,stageAttempts) =>
+ stageAttempts.map { case (status, stageInfo) =>
+ val stageUiData = listener.synchronized {
+ listener.stageIdToData.get((stageInfo.stageId,
stageInfo.attemptId)).
+ getOrElse(throw new SparkException("failed to get full stage
data for stage: " +
+ stageInfo.stageId + ":" + stageInfo.attemptId)
+ )
+ }
+ AllStagesResource.stageUiToStageData(status, stageInfo,
stageUiData,
+ includeDetails = true)
+ }
+ }
+ }
+
+ @GET
+ @Path("/{attemptId: \\d+}")
+ def oneAttemptData(
+ @PathParam("appId") appId: String,
+ @PathParam("stageId") stageId: Int,
+ @PathParam("attemptId") attemptId: Int
+ ): StageData = {
+ forStageAttempt(appId, stageId, attemptId) { case (status, stageInfo,
stageUiData) =>
+ AllStagesResource.stageUiToStageData(status, stageInfo, stageUiData,
+ includeDetails = true)
+ }
+ }
+
+ @GET
+ @Path("/{attemptId: \\d+}/taskSummary")
+ def stageData(
+ @PathParam("appId") appId: String,
+ @PathParam("stageId") stageId: Int,
+ @PathParam("attemptId") attemptId: Int,
+ @DefaultValue("0.05,0.25,0.5,0.75,0.95") @QueryParam("quantiles")
quantileString: String
--- End diff --
I ran into a couple of limitations w/ `List[X]`. (a) I found the longer
URLs annoying `?quantile=0.01&quantile=0.05&quantile=0.25...` (b) I couldn't do
nice error handling if parsing failed for individual `X`s (c) couldn't figure
out how to specify a default with multiple values (which kinda makes sense,
since its not clear what the behavior should be if the user added another value
in that case).
(c) is pretty important in this case. I am tempted to drop use of
`List[X]` in the other places if we want consistency -- also I could put in
better error handling.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
