diff options
author | Shixiong Zhu <shixiong@databricks.com> | 2016-11-30 16:18:53 -0800 |
---|---|---|
committer | Shixiong Zhu <shixiong@databricks.com> | 2016-11-30 16:18:53 -0800 |
commit | c4979f6ea8ed44fd87ded3133efa6df39d4842c3 (patch) | |
tree | 481132adf681b5295e076056da5e4fcd29b4295c /core/src/main/scala/org | |
parent | 93e9d880bf8a144112d74a6897af4e36fcfa5807 (diff) | |
download | spark-c4979f6ea8ed44fd87ded3133efa6df39d4842c3.tar.gz spark-c4979f6ea8ed44fd87ded3133efa6df39d4842c3.tar.bz2 spark-c4979f6ea8ed44fd87ded3133efa6df39d4842c3.zip |
[SPARK-18655][SS] Ignore Structured Streaming 2.0.2 logs in history server
## What changes were proposed in this pull request?
As `queryStatus` in StreamingQueryListener events was removed in #15954, parsing 2.0.2 structured streaming logs will throw the following errror:
```
[info] com.fasterxml.jackson.databind.exc.UnrecognizedPropertyException: Unrecognized field "queryStatus" (class org.apache.spark.sql.streaming.StreamingQueryListener$QueryTerminatedEvent), not marked as ignorable (2 known properties: "id", "exception"])
[info] at [Source: {"Event":"org.apache.spark.sql.streaming.StreamingQueryListener$QueryTerminatedEvent","queryStatus":{"name":"query-1","id":1,"timestamp":1480491532753,"inputRate":0.0,"processingRate":0.0,"latency":null,"sourceStatuses":[{"description":"FileStreamSource[file:/Users/zsx/stream]","offsetDesc":"#0","inputRate":0.0,"processingRate":0.0,"triggerDetails":{"latency.getOffset.source":"1","triggerId":"1"}}],"sinkStatus":{"description":"FileSink[/Users/zsx/stream2]","offsetDesc":"[#0]"},"triggerDetails":{}},"exception":null}; line: 1, column: 521] (through reference chain: org.apache.spark.sql.streaming.QueryTerminatedEvent["queryStatus"])
[info] at com.fasterxml.jackson.databind.exc.UnrecognizedPropertyException.from(UnrecognizedPropertyException.java:51)
[info] at com.fasterxml.jackson.databind.DeserializationContext.reportUnknownProperty(DeserializationContext.java:839)
[info] at com.fasterxml.jackson.databind.deser.std.StdDeserializer.handleUnknownProperty(StdDeserializer.java:1045)
[info] at com.fasterxml.jackson.databind.deser.BeanDeserializerBase.handleUnknownProperty(BeanDeserializerBase.java:1352)
[info] at com.fasterxml.jackson.databind.deser.BeanDeserializerBase.handleUnknownProperties(BeanDeserializerBase.java:1306)
[info] at com.fasterxml.jackson.databind.deser.BeanDeserializer._deserializeUsingPropertyBased(BeanDeserializer.java:453)
[info] at com.fasterxml.jackson.databind.deser.BeanDeserializerBase.deserializeFromObjectUsingNonDefault(BeanDeserializerBase.java:1099)
...
```
This PR just ignores such errors and adds a test to make sure we can read 2.0.2 logs.
## How was this patch tested?
`query-event-logs-version-2.0.2.txt` has all types of events generated by Structured Streaming in Spark 2.0.2. `testQuietly("ReplayListenerBus should ignore broken event jsons generated in 2.0.2")` verified we can load them without any error.
Author: Shixiong Zhu <shixiong@databricks.com>
Closes #16085 from zsxwing/SPARK-18655.
Diffstat (limited to 'core/src/main/scala/org')
-rw-r--r-- | core/src/main/scala/org/apache/spark/scheduler/ReplayListenerBus.scala | 7 |
1 files changed, 7 insertions, 0 deletions
diff --git a/core/src/main/scala/org/apache/spark/scheduler/ReplayListenerBus.scala b/core/src/main/scala/org/apache/spark/scheduler/ReplayListenerBus.scala index 0bd5a6bc59..08e05ae0c0 100644 --- a/core/src/main/scala/org/apache/spark/scheduler/ReplayListenerBus.scala +++ b/core/src/main/scala/org/apache/spark/scheduler/ReplayListenerBus.scala @@ -22,6 +22,7 @@ import java.io.{InputStream, IOException} import scala.io.Source import com.fasterxml.jackson.core.JsonParseException +import com.fasterxml.jackson.databind.exc.UnrecognizedPropertyException import org.json4s.jackson.JsonMethods._ import org.apache.spark.internal.Logging @@ -87,6 +88,12 @@ private[spark] class ReplayListenerBus extends SparkListenerBus with Logging { // Ignore events generated by Structured Streaming in Spark 2.0.0 and 2.0.1. // It's safe since no place uses them. logWarning(s"Dropped incompatible Structured Streaming log: $currentLine") + case e: UnrecognizedPropertyException if e.getMessage != null && e.getMessage.startsWith( + "Unrecognized field \"queryStatus\" " + + "(class org.apache.spark.sql.streaming.StreamingQueryListener$") => + // Ignore events generated by Structured Streaming in Spark 2.0.2 + // It's safe since no place uses them. + logWarning(s"Dropped incompatible Structured Streaming log: $currentLine") case jpe: JsonParseException => // We can only ignore exception from last line of the file that might be truncated // the last entry may not be the very last line in the event log, but we treat it |