Open habahram opened 2 years ago
It seems the bucket codelab-iot-data-pipeline-sampleweatherdata does not exist.
When I run the job created in step 7, I get errors indicating that the bucket codelab-iot-data-pipeline-sampleweatherdata does not exist:
Error message from worker: java.io.IOException: Unable to match files in bucket codelab-iot-data-pipeline-sampleweatherdata, prefix . org.apache.beam.sdk.extensions.gcp.util.GcsUtil.listObjects(GcsUtil.java:355) org.apache.beam.sdk.extensions.gcp.util.GcsUtil.listObjects(GcsUtil.java:329) org.apache.beam.sdk.extensions.gcp.storage.GcsFileSystem.expand(GcsFileSystem.java:222) org.apache.beam.sdk.extensions.gcp.storage.GcsFileSystem.lambda$matchGlobs$0(GcsFileSystem.java:195) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.Iterators$6.transform(Iterators.java:785) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.TransformedIterator.next(TransformedIterator.java:47) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableList.copyOf(ImmutableList.java:273) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableList.copyOf(ImmutableList.java:234) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.FluentIterable.toList(FluentIterable.java:617) org.apache.beam.sdk.extensions.gcp.storage.GcsFileSystem.matchGlobs(GcsFileSystem.java:200) org.apache.beam.sdk.extensions.gcp.storage.GcsFileSystem.match(GcsFileSystem.java:101) org.apache.beam.sdk.io.FileSystems.match(FileSystems.java:125) org.apache.beam.sdk.io.FileSystems.match(FileSystems.java:146) org.apache.beam.sdk.io.FileSystems.match(FileSystems.java:158) org.apache.beam.sdk.io.FileIO$MatchAll$MatchPollFn.apply(FileIO.java:673) org.apache.beam.sdk.io.FileIO$MatchAll$MatchPollFn.apply(FileIO.java:667) org.apache.beam.sdk.transforms.Watch$WatchGrowthFn.process(Watch.java:910) Caused by: com.google.api.client.googleapis.json.GoogleJsonResponseException: 404 Not Found GET https://storage.googleapis.com/storage/v1/b/codelab-iot-data-pipeline-sampleweatherdata/o?maxResults=1024&prefix { "code" : 404, "errors" : [ { "domain" : "global", "message" : "The specified bucket does not exist.", "reason" : "notFound" } ], "message" : "The specified bucket does not exist." } com.google.api.client.googleapis.json.GoogleJsonResponseException.from(GoogleJsonResponseException.java:146) com.google.api.client.googleapis.services.json.AbstractGoogleJsonClientRequest.newExceptionOnError(AbstractGoogleJsonClientRequest.java:118) com.google.api.client.googleapis.services.json.AbstractGoogleJsonClientRequest.newExceptionOnError(AbstractGoogleJsonClientRequest.java:37) com.google.api.client.googleapis.services.AbstractGoogleClientRequest$1.interceptResponse(AbstractGoogleClientRequest.java:428) com.google.api.client.http.HttpRequest.execute(HttpRequest.java:1111) com.google.api.client.googleapis.services.AbstractGoogleClientRequest.executeUnparsed(AbstractGoogleClientRequest.java:514) com.google.api.client.googleapis.services.AbstractGoogleClientRequest.executeUnparsed(AbstractGoogleClientRequest.java:455) com.google.api.client.googleapis.services.AbstractGoogleClientRequest.execute(AbstractGoogleClientRequest.java:565) com.google.cloud.hadoop.util.ResilientOperation.retry(ResilientOperation.java:66) com.google.cloud.hadoop.util.ResilientOperation.retry(ResilientOperation.java:105) org.apache.beam.sdk.extensions.gcp.util.GcsUtil.listObjects(GcsUtil.java:351) org.apache.beam.sdk.extensions.gcp.util.GcsUtil.listObjects(GcsUtil.java:329) org.apache.beam.sdk.extensions.gcp.storage.GcsFileSystem.expand(GcsFileSystem.java:222) org.apache.beam.sdk.extensions.gcp.storage.GcsFileSystem.lambda$matchGlobs$0(GcsFileSystem.java:195) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.Iterators$6.transform(Iterators.java:785) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.TransformedIterator.next(TransformedIterator.java:47) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableList.copyOf(ImmutableList.java:273) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableList.copyOf(ImmutableList.java:234) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.FluentIterable.toList(FluentIterable.java:617) org.apache.beam.sdk.extensions.gcp.storage.GcsFileSystem.matchGlobs(GcsFileSystem.java:200) org.apache.beam.sdk.extensions.gcp.storage.GcsFileSystem.match(GcsFileSystem.java:101) org.apache.beam.sdk.io.FileSystems.match(FileSystems.java:125) org.apache.beam.sdk.io.FileSystems.match(FileSystems.java:146) org.apache.beam.sdk.io.FileSystems.match(FileSystems.java:158) org.apache.beam.sdk.io.FileIO$MatchAll$MatchPollFn.apply(FileIO.java:673) org.apache.beam.sdk.io.FileIO$MatchAll$MatchPollFn.apply(FileIO.java:667) org.apache.beam.sdk.transforms.Watch$WatchGrowthFn.process(Watch.java:910) org.apache.beam.sdk.transforms.Watch$WatchGrowthFn$DoFnInvoker.invokeProcessElement(Unknown Source) org.apache.beam.runners.dataflow.worker.repackaged.org.apache.beam.runners.core.OutputAndTimeBoundedSplittableProcessElementInvoker.invokeProcessElement(OutputAndTimeBoundedSplittableProcessElementInvoker.java:123) org.apache.beam.runners.dataflow.worker.repackaged.org.apache.beam.runners.core.SplittableParDoViaKeyedWorkItems$ProcessFn.processElement(SplittableParDoViaKeyedWorkItems.java:523) org.apache.beam.runners.dataflow.worker.repackaged.org.apache.beam.runners.core.SplittableParDoViaKeyedWorkItems$ProcessFn$DoFnInvoker.invokeProcessElement(Unknown Source) org.apache.beam.runners.dataflow.worker.repackaged.org.apache.beam.runners.core.SimpleDoFnRunner.invokeProcessElement(SimpleDoFnRunner.java:232) org.apache.beam.runners.dataflow.worker.repackaged.org.apache.beam.runners.core.SimpleDoFnRunner.processElement(SimpleDoFnRunner.java:188) org.apache.beam.runners.dataflow.worker.DataflowProcessFnRunner.processElement(DataflowProcessFnRunner.java:63) org.apache.beam.runners.dataflow.worker.SimpleParDoFn.processElement(SimpleParDoFn.java:339) org.apache.beam.runners.dataflow.worker.util.common.worker.ParDoOperation.process(ParDoOperation.java:44) org.apache.beam.runners.dataflow.worker.util.common.worker.OutputReceiver.process(OutputReceiver.java:49) org.apache.beam.runners.dataflow.worker.util.common.worker.ReadOperation.runReadLoop(ReadOperation.java:212) org.apache.beam.runners.dataflow.worker.util.common.worker.ReadOperation.start(ReadOperation.java:163) org.apache.beam.runners.dataflow.worker.util.common.worker.MapTaskExecutor.execute(MapTaskExecutor.java:92) org.apache.beam.runners.dataflow.worker.StreamingDataflowWorker.process(StreamingDataflowWorker.java:1435) org.apache.beam.runners.dataflow.worker.StreamingDataflowWorker.access$1100(StreamingDataflowWorker.java:165) org.apache.beam.runners.dataflow.worker.StreamingDataflowWorker$7.run(StreamingDataflowWorker.java:1111) java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128) java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628) java.base/java.lang.Thread.run(Thread.java:834)
It seems the bucket codelab-iot-data-pipeline-sampleweatherdata does not exist.
When I run the job created in step 7, I get errors indicating that the bucket codelab-iot-data-pipeline-sampleweatherdata does not exist:
Error message from worker: java.io.IOException: Unable to match files in bucket codelab-iot-data-pipeline-sampleweatherdata, prefix . org.apache.beam.sdk.extensions.gcp.util.GcsUtil.listObjects(GcsUtil.java:355) org.apache.beam.sdk.extensions.gcp.util.GcsUtil.listObjects(GcsUtil.java:329) org.apache.beam.sdk.extensions.gcp.storage.GcsFileSystem.expand(GcsFileSystem.java:222) org.apache.beam.sdk.extensions.gcp.storage.GcsFileSystem.lambda$matchGlobs$0(GcsFileSystem.java:195) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.Iterators$6.transform(Iterators.java:785) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.TransformedIterator.next(TransformedIterator.java:47) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableList.copyOf(ImmutableList.java:273) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableList.copyOf(ImmutableList.java:234) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.FluentIterable.toList(FluentIterable.java:617) org.apache.beam.sdk.extensions.gcp.storage.GcsFileSystem.matchGlobs(GcsFileSystem.java:200) org.apache.beam.sdk.extensions.gcp.storage.GcsFileSystem.match(GcsFileSystem.java:101) org.apache.beam.sdk.io.FileSystems.match(FileSystems.java:125) org.apache.beam.sdk.io.FileSystems.match(FileSystems.java:146) org.apache.beam.sdk.io.FileSystems.match(FileSystems.java:158) org.apache.beam.sdk.io.FileIO$MatchAll$MatchPollFn.apply(FileIO.java:673) org.apache.beam.sdk.io.FileIO$MatchAll$MatchPollFn.apply(FileIO.java:667) org.apache.beam.sdk.transforms.Watch$WatchGrowthFn.process(Watch.java:910) Caused by: com.google.api.client.googleapis.json.GoogleJsonResponseException: 404 Not Found GET https://storage.googleapis.com/storage/v1/b/codelab-iot-data-pipeline-sampleweatherdata/o?maxResults=1024&prefix { "code" : 404, "errors" : [ { "domain" : "global", "message" : "The specified bucket does not exist.", "reason" : "notFound" } ], "message" : "The specified bucket does not exist." } com.google.api.client.googleapis.json.GoogleJsonResponseException.from(GoogleJsonResponseException.java:146) com.google.api.client.googleapis.services.json.AbstractGoogleJsonClientRequest.newExceptionOnError(AbstractGoogleJsonClientRequest.java:118) com.google.api.client.googleapis.services.json.AbstractGoogleJsonClientRequest.newExceptionOnError(AbstractGoogleJsonClientRequest.java:37) com.google.api.client.googleapis.services.AbstractGoogleClientRequest$1.interceptResponse(AbstractGoogleClientRequest.java:428) com.google.api.client.http.HttpRequest.execute(HttpRequest.java:1111) com.google.api.client.googleapis.services.AbstractGoogleClientRequest.executeUnparsed(AbstractGoogleClientRequest.java:514) com.google.api.client.googleapis.services.AbstractGoogleClientRequest.executeUnparsed(AbstractGoogleClientRequest.java:455) com.google.api.client.googleapis.services.AbstractGoogleClientRequest.execute(AbstractGoogleClientRequest.java:565) com.google.cloud.hadoop.util.ResilientOperation.retry(ResilientOperation.java:66) com.google.cloud.hadoop.util.ResilientOperation.retry(ResilientOperation.java:105) org.apache.beam.sdk.extensions.gcp.util.GcsUtil.listObjects(GcsUtil.java:351) org.apache.beam.sdk.extensions.gcp.util.GcsUtil.listObjects(GcsUtil.java:329) org.apache.beam.sdk.extensions.gcp.storage.GcsFileSystem.expand(GcsFileSystem.java:222) org.apache.beam.sdk.extensions.gcp.storage.GcsFileSystem.lambda$matchGlobs$0(GcsFileSystem.java:195) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.Iterators$6.transform(Iterators.java:785) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.TransformedIterator.next(TransformedIterator.java:47) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableList.copyOf(ImmutableList.java:273) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.ImmutableList.copyOf(ImmutableList.java:234) org.apache.beam.vendor.guava.v26_0_jre.com.google.common.collect.FluentIterable.toList(FluentIterable.java:617) org.apache.beam.sdk.extensions.gcp.storage.GcsFileSystem.matchGlobs(GcsFileSystem.java:200) org.apache.beam.sdk.extensions.gcp.storage.GcsFileSystem.match(GcsFileSystem.java:101) org.apache.beam.sdk.io.FileSystems.match(FileSystems.java:125) org.apache.beam.sdk.io.FileSystems.match(FileSystems.java:146) org.apache.beam.sdk.io.FileSystems.match(FileSystems.java:158) org.apache.beam.sdk.io.FileIO$MatchAll$MatchPollFn.apply(FileIO.java:673) org.apache.beam.sdk.io.FileIO$MatchAll$MatchPollFn.apply(FileIO.java:667) org.apache.beam.sdk.transforms.Watch$WatchGrowthFn.process(Watch.java:910) org.apache.beam.sdk.transforms.Watch$WatchGrowthFn$DoFnInvoker.invokeProcessElement(Unknown Source) org.apache.beam.runners.dataflow.worker.repackaged.org.apache.beam.runners.core.OutputAndTimeBoundedSplittableProcessElementInvoker.invokeProcessElement(OutputAndTimeBoundedSplittableProcessElementInvoker.java:123) org.apache.beam.runners.dataflow.worker.repackaged.org.apache.beam.runners.core.SplittableParDoViaKeyedWorkItems$ProcessFn.processElement(SplittableParDoViaKeyedWorkItems.java:523) org.apache.beam.runners.dataflow.worker.repackaged.org.apache.beam.runners.core.SplittableParDoViaKeyedWorkItems$ProcessFn$DoFnInvoker.invokeProcessElement(Unknown Source) org.apache.beam.runners.dataflow.worker.repackaged.org.apache.beam.runners.core.SimpleDoFnRunner.invokeProcessElement(SimpleDoFnRunner.java:232) org.apache.beam.runners.dataflow.worker.repackaged.org.apache.beam.runners.core.SimpleDoFnRunner.processElement(SimpleDoFnRunner.java:188) org.apache.beam.runners.dataflow.worker.DataflowProcessFnRunner.processElement(DataflowProcessFnRunner.java:63) org.apache.beam.runners.dataflow.worker.SimpleParDoFn.processElement(SimpleParDoFn.java:339) org.apache.beam.runners.dataflow.worker.util.common.worker.ParDoOperation.process(ParDoOperation.java:44) org.apache.beam.runners.dataflow.worker.util.common.worker.OutputReceiver.process(OutputReceiver.java:49) org.apache.beam.runners.dataflow.worker.util.common.worker.ReadOperation.runReadLoop(ReadOperation.java:212) org.apache.beam.runners.dataflow.worker.util.common.worker.ReadOperation.start(ReadOperation.java:163) org.apache.beam.runners.dataflow.worker.util.common.worker.MapTaskExecutor.execute(MapTaskExecutor.java:92) org.apache.beam.runners.dataflow.worker.StreamingDataflowWorker.process(StreamingDataflowWorker.java:1435) org.apache.beam.runners.dataflow.worker.StreamingDataflowWorker.access$1100(StreamingDataflowWorker.java:165) org.apache.beam.runners.dataflow.worker.StreamingDataflowWorker$7.run(StreamingDataflowWorker.java:1111) java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128) java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628) java.base/java.lang.Thread.run(Thread.java:834)