CODAIT
spark strucutred stream with cos source use stocator fail by connection time out from pool
I use spark structured streaming to list cos bucket , streaming will exit sometimes for the following reason, I use stocator 1.0.36 version, spark2.4.4: com.amazonaws.SdkClientException: Unable to execute HTTP request: Timeout waiting for connection from pool at com.amazonaws.http.AmazonHttpClient$RequestExecutor.handleRetryableException(AmazonHttpClient.java:1175) at com.amazonaws.http.AmazonHttpClient$RequestExecutor.executeHelper(AmazonHttpClient.java:1121) at com.amazonaws.http.AmazonHttpClient$RequestExecutor.doExecute(AmazonHttpClient.java:770) at com.amazonaws.http.AmazonHttpClient$RequestExecutor.executeWithTimer(AmazonHttpClient.java:744) at com.amazonaws.http.AmazonHttpClient$RequestExecutor.execute(AmazonHttpClient.java:726) at com.amazonaws.http.AmazonHttpClient$RequestExecutor.access$500(AmazonHttpClient.java:686) at com.amazonaws.http.AmazonHttpClient$RequestExecutionBuilderImpl.execute(AmazonHttpClient.java:668) at com.amazonaws.http.AmazonHttpClient.execute(AmazonHttpClient.java:532) at com.amazonaws.http.AmazonHttpClient.execute(AmazonHttpClient.java:512) at com.amazonaws.services.s3.AmazonS3Client.invoke(AmazonS3Client.java:4921) at com.amazonaws.services.s3.AmazonS3Client.invoke(AmazonS3Client.java:4867) at com.amazonaws.services.s3.AmazonS3Client.invoke(AmazonS3Client.java:4861) at com.amazonaws.services.s3.AmazonS3Client.listObjects(AmazonS3Client.java:880) at com.ibm.stocator.fs.cos.COSAPIClient.internalList(COSAPIClient.java:875) at com.ibm.stocator.fs.cos.COSAPIClient.list(COSAPIClient.java:845) at com.ibm.stocator.fs.ObjectStoreFileSystem.listStatus(ObjectStoreFileSystem.java:392) at com.ibm.stocator.fs.common.ObjectStoreGlobber.listStatus(ObjectStoreGlobber.java:80) at com.ibm.stocator.fs.common.ObjectStoreGlobber.glob(ObjectStoreGlobber.java:162) at com.ibm.stocator.fs.ObjectStoreFileSystem.globStatus(ObjectStoreFileSystem.java:546) at org.apache.spark.deploy.SparkHadoopUtil.globPath(SparkHadoopUtil.scala:245) at org.apache.spark.deploy.SparkHadoopUtil.globPathIfNecessary(SparkHadoopUtil.scala:255) at org.apache.spark.sql.execution.streaming.FileStreamSource.allFilesUsingInMemoryFileIndex(FileStreamSource.scala:191) at org.apache.spark.sql.execution.streaming.FileStreamSource.fetchAllFiles(FileStreamSource.scala:233) at org.apache.spark.sql.execution.streaming.FileStreamSource.fetchMaxOffset(FileStreamSource.scala:111) at org.apache.spark.sql.execution.streaming.FileStreamSource.getOffset(FileStreamSource.scala:251) at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$constructNextBatch$1$$anonfun$5$$anonfun$apply$9.apply(MicroBatchExecution.scala:345) at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$constructNextBatch$1$$anonfun$5$$anonfun$apply$9.apply(MicroBatchExecution.scala:345) at org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:351) at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58) at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$constructNextBatch$1$$anonfun$5.apply(MicroBatchExecution.scala:344) at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$constructNextBatch$1$$anonfun$5.apply(MicroBatchExecution.scala:341) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) at scala.collection.TraversableLike$class.map(TraversableLike.scala:234) at scala.collection.AbstractTraversable.map(Traversable.scala:104) at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$constructNextBatch$1.apply$mcZ$sp(MicroBatchExecution.scala:341) at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$constructNextBatch$1.apply(MicroBatchExecution.scala:337) at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$constructNextBatch$1.apply(MicroBatchExecution.scala:337) at org.apache.spark.sql.execution.streaming.MicroBatchExecution.withProgressLocked(MicroBatchExecution.scala:557) at org.apache.spark.sql.execution.streaming.MicroBatchExecution.org$apache$spark$sql$execution$streaming$MicroBatchExecution$$constructNextBatch(MicroBatchExecution.scala:337) at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply$mcV$sp(MicroBatchExecution.scala:183) at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply(MicroBatchExecution.scala:166) at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply(MicroBatchExecution.scala:166) at org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:351) at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58) at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1.apply$mcZ$sp(MicroBatchExecution.scala:166) at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:56) at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:160) at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:281) at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:193) Caused by: org.apache.http.conn.ConnectionPoolTimeoutException: Timeout waiting for connection from pool at org.apache.http.impl.conn.PoolingHttpClientConnectionManager.leaseConnection(PoolingHttpClientConnectionManager.java:314) at org.apache.http.impl.conn.PoolingHttpClientConnectionManager$1.get(PoolingHttpClientConnectionManager.java:280) at sun.reflect.GeneratedMethodAccessor174.invoke(Unknown Source) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at com.amazonaws.http.conn.ClientConnectionRequestFactory$Handler.invoke(ClientConnectionRequestFactory.java:70) at com.amazonaws.http.conn.$Proxy8.get(Unknown Source) at org.apache.http.impl.execchain.MainClientExec.execute(MainClientExec.java:190) at org.apache.http.impl.execchain.ProtocolExec.execute(ProtocolExec.java:186) at org.apache.http.impl.client.InternalHttpClient.doExecute(InternalHttpClient.java:185) at org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:83) at org.apache.http.impl.client.CloseableHttpClient.execute(CloseableHttpClient.java:56) at com.amazonaws.http.apache.client.impl.SdkHttpClient.execute(SdkHttpClient.java:72) at com.amazonaws.http.AmazonHttpClient$RequestExecutor.executeOneRequest(AmazonHttpClient.java:1297) at com.amazonaws.http.AmazonHttpClient$RequestExecutor.executeHelper(AmazonHttpClient.java:1113)
@student2028 have you tried to change default configuration values? https://github.com/CODAIT/stocator#cos-connector-optional-configuration-tuning there pool size, connection timeouts,etc.
@gilv Thanks, I refer the default value, the default value is very large now, fs.cos.threads.max 10 fs.cos.connection.maximum 10000 fs.cos.attempts.maximum 20 fs.cos.connection.timeout 800000 do you have any suggestion?