From 193215201cfff5f686a70d5054c0a3a3d91d25a6 Mon Sep 17 00:00:00 2001 From: Bo Cui Date: Mon, 28 Feb 2022 10:45:28 +0800 Subject: [PATCH] [MINOR] Change MINI_BATCH_SIZE to 2048 (#4862) ParquetColumnarRowSplitReader#batchSize is 2048, so Changing MINI_BATCH_SIZE to 2048 will reduce memory cache. --- .../main/java/org/apache/hudi/source/StreamReadOperator.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hudi-flink/src/main/java/org/apache/hudi/source/StreamReadOperator.java b/hudi-flink/src/main/java/org/apache/hudi/source/StreamReadOperator.java index 0f3d7de1d..c3f43422f 100644 --- a/hudi-flink/src/main/java/org/apache/hudi/source/StreamReadOperator.java +++ b/hudi-flink/src/main/java/org/apache/hudi/source/StreamReadOperator.java @@ -64,7 +64,7 @@ public class StreamReadOperator extends AbstractStreamOperator private static final Logger LOG = LoggerFactory.getLogger(StreamReadOperator.class); - private static final int MINI_BATCH_SIZE = 1000; + private static final int MINI_BATCH_SIZE = 2048; // It's the same thread that runs this operator and checkpoint actions. Use this executor to schedule only // splits for subsequent reading, so that a new checkpoint could be triggered without blocking a long time