Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Improve] Speed up ClickhouseFile Local generate a mmap object #5822

Merged
merged 3 commits into from
Nov 16, 2023
+27 −7
Merged

[Improve] Speed up ClickhouseFile Local generate a mmap object #5822

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
bbd2eb7
fix-5819: 优化CK File模式写Local mmap 创建频繁,导致写入慢
Nov 9, 2023
194dce0
fix-5819: 优化CK File模式写Local mmap 创建频繁,导致写入慢
Nov 14, 2023
7a9c00a
fix-5819: code style
Nov 14, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 27 additions & 7 deletions .../apache/seatunnel/connectors/seatunnel/clickhouse/sink/file/ClickhouseFileSinkWriter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,6 +73,8 @@ public class ClickhouseFileSinkWriter
private final ClickhouseTable clickhouseTable;
private final Map<Shard, List<String>> shardLocalDataPaths;
private final Map<Shard, FileChannel> rowCache;
private final Map<Shard, MappedByteBuffer> bufferCache;
private final Integer bufferSize = 1024 * 128;

private final Map<Shard, String> shardTempFile;

Expand All @@ -91,6 +93,7 @@ public ClickhouseFileSinkWriter(FileReaderOption readerOption, SinkWriter.Contex
this.readerOption.getShardMetadata().getDatabase(),
this.readerOption.getShardMetadata().getTable());
rowCache = new HashMap<>(Common.COLLECTION_SIZE);
bufferCache = new HashMap<>(Common.COLLECTION_SIZE);
shardTempFile = new HashMap<>();
nodePasswordCheck();

Expand Down Expand Up @@ -141,7 +144,7 @@ public void write(SeaTunnelRow element) throws IOException {
e);
}
});
saveDataToFile(channel, element);
saveDataToFile(channel, element, shard);
}

private void nodePasswordCheck() {
Expand Down Expand Up @@ -209,7 +212,8 @@ public void close() throws IOException {
}
}

private void saveDataToFile(FileChannel fileChannel, SeaTunnelRow row) throws IOException {
private void saveDataToFile(FileChannel fileChannel, SeaTunnelRow row, Shard shard)
throws IOException {
String data =
this.readerOption.getFields().stream()
.map(
Expand All @@ -227,12 +231,28 @@ private void saveDataToFile(FileChannel fileChannel, SeaTunnelRow row) throws IO
})
.collect(Collectors.joining(readerOption.getFileFieldsDelimiter()))
+ "\n";

MappedByteBuffer buffer =
fileChannel.map(
FileChannel.MapMode.READ_WRITE,
fileChannel.size(),
data.getBytes(StandardCharsets.UTF_8).length);
buffer.put(data.getBytes(StandardCharsets.UTF_8));
bufferCache.computeIfAbsent(
shard,
k -> {
try {
return fileChannel.map(
FileChannel.MapMode.READ_WRITE, 0, bufferSize);
} catch (IOException e) {
throw new ClickhouseConnectorException(
CommonErrorCodeDeprecated.FILE_OPERATION_FAILED,
"data_local file write failed",
e);
}
});
byte[] byteData = data.getBytes(StandardCharsets.UTF_8);
if (buffer.position() + byteData.length > buffer.capacity()) {
buffer =
fileChannel.map(FileChannel.MapMode.READ_WRITE, fileChannel.size(), bufferSize);
bufferCache.put(shard, buffer);
}
buffer.put(byteData);
}

private List<String> generateClickhouseLocalFiles(String clickhouseLocalFileTmpFile)
Expand Down