You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@beam.apache.org by ec...@apache.org on 2019/09/27 08:58:10 UTC
[beam] 02/03: Improve performance of source: the mapper already
calls windowedValueCoder.decode,
no need to call it also in the Spark encoder
This is an automated email from the ASF dual-hosted git repository.
echauchot pushed a commit to branch spark-runner_structured-streaming
in repository https://gitbox.apache.org/repos/asf/beam.git
commit 97e8a19ef1c2c8d868a580d8a97ae41acaec2978
Author: Etienne Chauchot <ec...@apache.org>
AuthorDate: Thu Sep 19 17:20:31 2019 +0200
Improve performance of source: the mapper already calls windowedValueCoder.decode, no need to call it also in the Spark encoder
---
.../translation/batch/ReadSourceTranslatorBatch.java | 7 ++++---
.../translation/streaming/ReadSourceTranslatorStreaming.java | 5 +++--
2 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/runners/spark/src/main/java/org/apache/beam/runners/spark/structuredstreaming/translation/batch/ReadSourceTranslatorBatch.java b/runners/spark/src/main/java/org/apache/beam/runners/spark/structuredstreaming/translation/batch/ReadSourceTranslatorBatch.java
index 2dcf66f..c9a69d4 100644
--- a/runners/spark/src/main/java/org/apache/beam/runners/spark/structuredstreaming/translation/batch/ReadSourceTranslatorBatch.java
+++ b/runners/spark/src/main/java/org/apache/beam/runners/spark/structuredstreaming/translation/batch/ReadSourceTranslatorBatch.java
@@ -70,13 +70,14 @@ class ReadSourceTranslatorBatch<T>
.load();
// extract windowedValue from Row
- WindowedValue.FullWindowedValueCoder<T> windowedValueCoder = WindowedValue.FullWindowedValueCoder
- .of(source.getOutputCoder(), GlobalWindow.Coder.INSTANCE);
+ WindowedValue.FullWindowedValueCoder<T> windowedValueCoder =
+ WindowedValue.FullWindowedValueCoder.of(
+ source.getOutputCoder(), GlobalWindow.Coder.INSTANCE);
Dataset<WindowedValue<T>> dataset =
rowDataset.map(
RowHelpers.extractWindowedValueFromRowMapFunction(windowedValueCoder),
- EncoderHelpers.fromBeamCoder(windowedValueCoder));
+ EncoderHelpers.windowedValueEncoder());
PCollection<T> output = (PCollection<T>) context.getOutput();
context.putDataset(output, dataset);
diff --git a/runners/spark/src/main/java/org/apache/beam/runners/spark/structuredstreaming/translation/streaming/ReadSourceTranslatorStreaming.java b/runners/spark/src/main/java/org/apache/beam/runners/spark/structuredstreaming/translation/streaming/ReadSourceTranslatorStreaming.java
index 9e03d96..ea10272 100644
--- a/runners/spark/src/main/java/org/apache/beam/runners/spark/structuredstreaming/translation/streaming/ReadSourceTranslatorStreaming.java
+++ b/runners/spark/src/main/java/org/apache/beam/runners/spark/structuredstreaming/translation/streaming/ReadSourceTranslatorStreaming.java
@@ -71,8 +71,9 @@ class ReadSourceTranslatorStreaming<T>
.load();
// extract windowedValue from Row
- WindowedValue.FullWindowedValueCoder<T> windowedValueCoder = WindowedValue.FullWindowedValueCoder
- .of(source.getOutputCoder(), GlobalWindow.Coder.INSTANCE);
+ WindowedValue.FullWindowedValueCoder<T> windowedValueCoder =
+ WindowedValue.FullWindowedValueCoder.of(
+ source.getOutputCoder(), GlobalWindow.Coder.INSTANCE);
Dataset<WindowedValue<T>> dataset =
rowDataset.map(
RowHelpers.extractWindowedValueFromRowMapFunction(windowedValueCoder),