This is an automated email from the ASF dual-hosted git repository.
guoweima pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/flink.git
The following commit(s) were added to refs/heads/master by this push:
new d293577 [FLINK-22307][network] Increase the default value of data
writing cache size (not configurable) for sort-merge blocking shuffle
d293577 is described below
commit d29357791315ace0218308f9f96bf65c7c8079d7
Author: kevin.cyj <[email protected]>
AuthorDate: Thu Apr 15 23:36:07 2021 +0800
[FLINK-22307][network] Increase the default value of data writing cache
size (not configurable) for sort-merge blocking shuffle
Currently, the data writing cache of sort-merge blocking shuffle is 8M,
which can be not enough if data compression is enabled. This patch increases
the cache size to 16M which can improve the performance for high compression
ratio scenarios.
This closes #15651.
---
.../flink/runtime/io/network/partition/SortMergeResultPartition.java | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git
a/flink-runtime/src/main/java/org/apache/flink/runtime/io/network/partition/SortMergeResultPartition.java
b/flink-runtime/src/main/java/org/apache/flink/runtime/io/network/partition/SortMergeResultPartition.java
index db15bca..4442ca1 100644
---
a/flink-runtime/src/main/java/org/apache/flink/runtime/io/network/partition/SortMergeResultPartition.java
+++
b/flink-runtime/src/main/java/org/apache/flink/runtime/io/network/partition/SortMergeResultPartition.java
@@ -66,9 +66,9 @@ public class SortMergeResultPartition extends ResultPartition
{
/**
* Number of expected buffer size to allocate for data writing. Currently,
it is an empirical
- * value (8M) which can not be configured.
+ * value (16M) which can not be configured.
*/
- private static final int NUM_WRITE_BUFFER_BYTES = 8 * 1024 * 1024;
+ private static final int NUM_WRITE_BUFFER_BYTES = 16 * 1024 * 1024;
private final Object lock = new Object();
