diff options
| -rw-r--r-- | sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/Sink.scala | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/Sink.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/Sink.scala index 2571b59be5..d10cd3044e 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/Sink.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/Sink.scala @@ -31,8 +31,11 @@ trait Sink { * this method is called more than once with the same batchId (which will happen in the case of * failures), then `data` should only be added once. * - * Note: You cannot apply any operators on `data` except consuming it (e.g., `collect/foreach`). + * Note 1: You cannot apply any operators on `data` except consuming it (e.g., `collect/foreach`). * Otherwise, you may get a wrong result. + * + * Note 2: The method is supposed to be executed synchronously, i.e. the method should only return + * after data is consumed by sink successfully. */ def addBatch(batchId: Long, data: DataFrame): Unit } |