feat: use SLF4J with Spark default backend for logging #69
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,7 @@ | ||
| rootLogger.level = debug | ||
| rootLogger.appenderRef.console.ref = console | ||
|
|
||
| appender.console.type = Console | ||
| appender.console.name = console | ||
| appender.console.layout.type = PatternLayout | ||
| appender.console.layout.pattern = %d{HH:mm:ss.SSS} %-5level %logger{20} - %msg%n | ||
|
There was a problem hiding this comment.
The file ends without a trailing newline (indicated by |
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -21,6 +21,7 @@ import api.submit.Queue | |
| import com.fasterxml.jackson.databind.{DeserializationFeature, ObjectMapper} | ||
| import com.fasterxml.jackson.dataformat.yaml.YAMLFactory | ||
| import com.fasterxml.jackson.module.scala.DefaultScalaModule | ||
| import org.slf4j.{Logger, LoggerFactory} | ||
|
|
||
| import scala.concurrent.{ExecutionContext, Future} | ||
| import scala.concurrent.duration._ | ||
|
|
@@ -46,6 +47,7 @@ object JobSetStatus { | |
| * Armada server URL (default: "localhost:30002") | ||
| */ | ||
| class ArmadaClient(armadaUrl: String = "localhost:30002") { | ||
| private val logger = LoggerFactory.getLogger(getClass) | ||
| private val processTimeout = DefaultProcessTimeout | ||
|
|
||
| private val yamlMapper = { | ||
|
|
@@ -94,12 +96,12 @@ class ArmadaClient(armadaUrl: String = "localhost:30002") { | |
| def ensureQueueExists(name: String)(implicit ec: ExecutionContext): Future[Unit] = { | ||
| getQueue(name).flatMap { | ||
| case Some(_) => | ||
| logger.info(s"[QUEUE] Queue $name already exists") | ||
| Future.successful(()) | ||
| case None => | ||
| logger.info(s"[QUEUE] Creating queue $name...") | ||
| createQueue(name).flatMap { _ => | ||
| logger.info(s"[QUEUE] Waiting for queue $name to become available...") | ||
| Future { | ||
| var attempts = 0 | ||
| val maxAttempts = 30 | ||
|
|
@@ -110,12 +112,12 @@ class ArmadaClient(armadaUrl: String = "localhost:30002") { | |
| queueFound = getQueueSync(name).isDefined | ||
| attempts += 1 | ||
| if (!queueFound && attempts % 5 == 0) { | ||
| logger.info(s"[QUEUE] Still waiting for queue $name... (${attempts}s)") | ||
| } | ||
| } | ||
|
|
||
| if (queueFound) { | ||
| logger.info(s"[QUEUE] Queue $name is ready") | ||
| } else { | ||
| throw new RuntimeException(s"Queue $name not available after $attempts seconds") | ||
| } | ||
|
|
@@ -164,7 +166,7 @@ class ArmadaClient(armadaUrl: String = "localhost:30002") { | |
| val elapsed = (System.currentTimeMillis() - startTime) / 1000 | ||
| // Log progress periodically for long-running jobs | ||
| if (elapsed % ProgressLogInterval.toSeconds == 0 && elapsed > 0) { | ||
| logger.info(s"Still monitoring job - elapsed: ${elapsed}s") | ||
| } | ||
| } | ||
| } | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -22,6 +22,7 @@ import org.scalatest.funsuite.AnyFunSuite | |
| import org.scalatest.matchers.should.Matchers | ||
| import org.scalatest.concurrent.{Eventually, ScalaFutures} | ||
| import org.scalatest.time.{Seconds, Span} | ||
| import org.slf4j.LoggerFactory | ||
|
|
||
| import java.util.Properties | ||
| import scala.concurrent.ExecutionContext.Implicits.global | ||
|
|
@@ -34,6 +35,8 @@ class ArmadaSparkE2E | |
| with ScalaFutures | ||
| with Eventually { | ||
|
|
||
| private val logger = LoggerFactory.getLogger(getClass) | ||
|
|
||
| implicit override val patienceConfig: PatienceConfig = PatienceConfig( | ||
| timeout = Span(300, Seconds), | ||
| interval = Span(2, Seconds) | ||
|
|
@@ -72,14 +75,14 @@ class ArmadaSparkE2E | |
| sparkVersion = finalSparkVersion | ||
| ) | ||
|
|
||
| logger.info(s"Test configuration loaded: $baseConfig") | ||
|
|
||
| // Verify Armada cluster is ready before running tests | ||
| val clusterReadyTimeout = ClusterReadyTimeout.toSeconds.toInt | ||
| val testQueueName = s"${baseConfig.baseQueueName}-cluster-check-${System.currentTimeMillis()}" | ||
|
|
||
| logger.info(s"[CLUSTER-CHECK] Verifying Armada cluster readiness...") | ||
| logger.info(s"[CLUSTER-CHECK] Will retry for up to $clusterReadyTimeout seconds") | ||
|
|
||
| val startTime = System.currentTimeMillis() | ||
| var clusterReady = false | ||
|
|
@@ -88,29 +91,33 @@ class ArmadaSparkE2E | |
|
|
||
| while (!clusterReady && (System.currentTimeMillis() - startTime) < clusterReadyTimeout * 1000) { | ||
| attempts += 1 | ||
| logger.info( | ||
| s"[CLUSTER-CHECK] Attempt #$attempts - Creating and verifying test queue: $testQueueName" | ||
| ) | ||
|
|
||
| try { | ||
| armadaClient.ensureQueueExists(testQueueName).futureValue | ||
| logger.info( | ||
| s"[CLUSTER-CHECK] Queue creation and verification succeeded - cluster is ready!" | ||
| ) | ||
| clusterReady = true | ||
|
|
||
| try { | ||
| armadaClient.deleteQueue(testQueueName).futureValue | ||
| logger.info(s"[CLUSTER-CHECK] Test queue cleaned up") | ||
| } catch { | ||
| case _: Exception => // Ignore cleanup failures | ||
| } | ||
| } catch { | ||
| case ex: Exception => | ||
| lastError = Some(ex) | ||
| val elapsed = (System.currentTimeMillis() - startTime) / 1000 | ||
| logger.info( | ||
| s"[CLUSTER-CHECK] Attempt #$attempts failed after ${elapsed}s: ${ex.getMessage}" | ||
| ) | ||
|
|
||
| if ((System.currentTimeMillis() - startTime) < clusterReadyTimeout * 1000) { | ||
| logger.info( | ||
| s"[CLUSTER-CHECK] Waiting ${ClusterCheckRetryDelay.toSeconds} seconds before retry..." | ||
| ) | ||
| Thread.sleep(ClusterCheckRetryDelay.toMillis) | ||
|
|
@@ -126,7 +133,7 @@ class ArmadaSparkE2E | |
| ) | ||
| } | ||
|
|
||
| logger.info( | ||
| s"[CLUSTER-CHECK] Cluster verified ready after $totalTime seconds ($attempts attempts)" | ||
| ) | ||
| } | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -22,6 +22,7 @@ import scala.concurrent.{Future, ExecutionContext, blocking} | |
| import scala.concurrent.duration._ | ||
| import scala.sys.process._ | ||
| import scala.util.{Failure, Success, Try} | ||
| import org.slf4j.{Logger, LoggerFactory} | ||
|
|
||
| case class ProcessResult( | ||
| exitCode: Int, | ||
|
|
@@ -31,6 +32,7 @@ case class ProcessResult( | |
| ) | ||
|
|
||
| object ProcessExecutor { | ||
| private val logger = LoggerFactory.getLogger(getClass) | ||
|
|
||
| /** Execute command and always return ProcessResult, even on failure */ | ||
| def executeWithResult(command: Seq[String], timeout: Duration): ProcessResult = { | ||
|
|
@@ -42,14 +44,14 @@ object ProcessExecutor { | |
| stdout.append(line).append("\n") | ||
| // Print docker/spark-submit output in real-time for debugging | ||
| if (command.headOption.contains("docker") && line.nonEmpty) { | ||
| logger.info(s"[SPARK-SUBMIT] $line") | ||
| } | ||
| }, | ||
| line => { | ||
| stderr.append(line).append("\n") | ||
| // Print docker/spark-submit errors in real-time for debugging | ||
| if (command.headOption.contains("docker") && line.nonEmpty) { | ||
| logger.info(s"[SPARK-SUBMIT] $line") | ||
| } | ||
| } | ||
| ) | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -17,11 +17,13 @@ | |
|
|
||
| package org.apache.spark.deploy.armada.e2e | ||
|
|
||
| import org.slf4j.{Logger, LoggerFactory} | ||
| import scala.collection.mutable | ||
| import scala.concurrent.duration._ | ||
|
|
||
| /** Simple pod monitoring that captures logs and events on failure */ | ||
| class SimplePodMonitor(namespace: String) { | ||
| private val logger = LoggerFactory.getLogger(getClass) | ||
| private val capturedLogs = mutable.ArrayBuffer[String]() | ||
|
|
||
| /** Check if any pods have failed and capture their logs if so */ | ||
|
|
@@ -45,7 +47,7 @@ class SimplePodMonitor(namespace: String) { | |
| val failedPodName = failedPods.head.split("\\s+").head | ||
|
|
||
| // Immediately capture logs for the failed pod | ||
| logger.info(s"[MONITOR] Pod $failedPodName failed, capturing logs...") | ||
| try { | ||
| val logsCmd = Seq( | ||
| "kubectl", | ||
|
|
@@ -58,8 +60,8 @@ class SimplePodMonitor(namespace: String) { | |
| ) | ||
| val logsResult = ProcessExecutor.executeWithResult(logsCmd, 10.seconds) | ||
| if (logsResult.exitCode == 0 && logsResult.stdout.nonEmpty) { | ||
| logger.info(s"[MONITOR] Pod $failedPodName logs:") | ||
| logger.info(logsResult.stdout) | ||
| } | ||
|
|
||
| // Also try to describe the pod | ||
|
|
@@ -69,33 +71,33 @@ class SimplePodMonitor(namespace: String) { | |
| val lines = describeResult.stdout.split("\n") | ||
| val eventsIndex = lines.indexWhere(_.contains("Events:")) | ||
| if (eventsIndex >= 0) { | ||
| logger.info(s"[MONITOR] Pod $failedPodName events:") | ||
| logger.info(lines.slice(eventsIndex, eventsIndex + 20).mkString("\n")) | ||
| } | ||
| } | ||
| } catch { | ||
| case e: Exception => | ||
| logger.info(s"[MONITOR] Failed to capture logs for $failedPodName: ${e.getMessage}") | ||
| } | ||
|
|
||
| Some(s"Pod $failedPodName failed in namespace $namespace") | ||
| } else { | ||
| None | ||
| } | ||
| } else { | ||
| logger.info(s"[MONITOR] Failed to get pods: ${podsResult.stderr}") | ||
| None | ||
| } | ||
| } catch { | ||
| case e: Exception => | ||
| logger.info(s"[MONITOR] Error checking pods: ${e.getMessage}") | ||
| None | ||
| } | ||
| } | ||
|
|
||
| /** Capture all logs and events for debugging */ | ||
| def captureDebugInfo(): Unit = { | ||
| logger.debug(s"Capturing debug info for namespace $namespace") | ||
|
|
||
| try { | ||
| val podsCmd = Seq("kubectl", "get", "pods", "-n", namespace, "-o", "name") | ||
|
|
@@ -107,7 +109,7 @@ class SimplePodMonitor(namespace: String) { | |
|
|
||
| podNames.foreach { podName => | ||
| try { | ||
| logger.debug(s"Capturing logs for pod $podName") | ||
|
|
||
| val logsCmd = Seq( | ||
| "kubectl", | ||
|
|
@@ -150,7 +152,7 @@ class SimplePodMonitor(namespace: String) { | |
| } | ||
| } catch { | ||
| case e: Exception => | ||
| logger.error(s"Failed to capture info for pod $podName: ${e.getMessage}") | ||
| } | ||
| } | ||
| } | ||
|
|
@@ -163,16 +165,16 @@ class SimplePodMonitor(namespace: String) { | |
|
|
||
| } catch { | ||
| case e: Exception => | ||
| logger.error(s"Failed to capture debug info: ${e.getMessage}") | ||
| } | ||
| } | ||
|
|
||
| /** Print all captured logs */ | ||
| def printCapturedLogs(): Unit = { | ||
| if (capturedLogs.nonEmpty) { | ||
| logger.info(s"\n========== DEBUG INFO FOR NAMESPACE: $namespace ==========") | ||
| capturedLogs.foreach(logger.info) | ||
| logger.info(s"========== END DEBUG INFO ==========\n") | ||
| } | ||
| } | ||
| } | ||
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
spark-core). Declaringslf4j-apiat the defaultcompilescope is unnecessary — usingprovidedmakes the intent explicit and mirrors how the other Spark dependencies are declared, while still being available for compilation.