s0nskar commented on code in PR #3132:
URL: https://github.com/apache/celeborn/pull/3132#discussion_r1978709680
##########
worker/src/test/scala/org/apache/celeborn/service/deploy/cluster/ReadWriteTestWithFailures.scala:
##########
@@ -0,0 +1,112 @@
+package org.apache.celeborn.service.deploy.cluster
+
+import org.apache.celeborn.client.read.MetricsCallback
+import org.apache.celeborn.client.{LifecycleManager, ShuffleClientImpl}
+import org.apache.celeborn.common.CelebornConf
+import org.apache.celeborn.common.identity.UserIdentifier
+import org.apache.celeborn.common.internal.Logging
+import org.apache.celeborn.common.protocol.CompressionCodec
+import org.apache.celeborn.service.deploy.MiniClusterFeature
+import org.junit.Assert
+import org.scalatest.BeforeAndAfterAll
+import org.scalatest.funsuite.AnyFunSuite
+
+import java.io.ByteArrayOutputStream
+import java.nio.charset.StandardCharsets
+import java.util
+import java.util.UUID
+import java.util.concurrent.atomic.AtomicLong
+
+class ReadWriteTestWithFailures extends AnyFunSuite
+ with Logging with MiniClusterFeature with BeforeAndAfterAll {
+
+ var masterPort = 0
+
+ override def beforeAll(): Unit = {
+ logInfo("test initialized , setup Celeborn mini cluster")
+ val (m, _) = setupMiniClusterWithRandomPorts(workerConf =
Map("celeborn.shuffle.chunk.size" -> "100B",
+ "celeborn.worker.flusher.buffer.size" -> "10B"))
+ masterPort = m.conf.masterPort
+ }
+
+ override def afterAll(): Unit = {
+ logInfo("all test complete , stop Celeborn mini cluster")
+ shutdownMiniCluster()
+ }
+
+ test(s"test MiniCluster with connection resets, ensure no duplicate reads") {
Review Comment:
Can we add a negative case to show that there will be duplicated reads if
feature is disable. Also, a case where replication is enabled.
##########
common/src/main/scala/org/apache/celeborn/common/CelebornConf.scala:
##########
@@ -4691,6 +4692,15 @@ object CelebornConf extends Logging {
.bytesConf(ByteUnit.BYTE)
.createWithDefaultString("64k")
+ val WORKER_PARTITION_READER_CHECKPOINT_ENABLE: ConfigEntry[Boolean] =
+ buildConf("celeborn.worker.partition.reader.checkpointEnabled")
+ .categories("client")
+ .version("0.5.0")
Review Comment:
```suggestion
.version("0.6.0")
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
