You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@parquet.apache.org by GitBox <gi...@apache.org> on 2020/12/16 03:15:01 UTC
[GitHub] [parquet-mr] StefanXiepj commented on a change in pull request #849: PARQUET-1954: TCP connection leak in parquet dump
StefanXiepj commented on a change in pull request #849:
URL: https://github.com/apache/parquet-mr/pull/849#discussion_r543875687
##########
File path: parquet-tools/src/main/java/org/apache/parquet/tools/command/DumpCommand.java
##########
@@ -165,48 +165,47 @@ public static void dump(PrettyPrintWriter out, ParquetMetadata meta, MessageType
ParquetFileReader freader = null;
if (showmd) {
+ long group = 0;
+ for (BlockMetaData block : blocks) {
try {
- long group = 0;
- for (BlockMetaData block : blocks) {
- if (group != 0) out.println();
- out.format("row group %d%n", group++);
- out.rule('-');
-
-
- List<ColumnChunkMetaData> ccmds = block.getColumns();
- if (showColumns != null) {
- ccmds = new ArrayList<ColumnChunkMetaData>();
- for (ColumnChunkMetaData ccmd : block.getColumns()) {
- String path = Joiner.on('.').skipNulls().join(ccmd.getPath().toArray());
- if (showColumns.contains(path)) {
- ccmds.add(ccmd);
- }
- }
- }
-
- MetadataUtils.showDetails(out, ccmds);
+ if (group != 0)
+ out.println();
+ out.format("row group %d%n", group++);
+ out.rule('-');
+
+ List<ColumnChunkMetaData> ccmds = block.getColumns();
+ if (showColumns != null) {
+ ccmds = new ArrayList<ColumnChunkMetaData>();
+ for (ColumnChunkMetaData ccmd : block.getColumns()) {
+ String path = Joiner.on('.').skipNulls().join(ccmd.getPath().toArray());
+ if (showColumns.contains(path)) {
+ ccmds.add(ccmd);
+ }
+ }
+ }
- List<BlockMetaData> rblocks = Collections.singletonList(block);
- freader = new ParquetFileReader(
- conf, meta.getFileMetaData(), inpath, rblocks, columns);
- PageReadStore store = freader.readNextRowGroup();
- while (store != null) {
- out.incrementTabLevel();
- for (ColumnDescriptor column : columns) {
- out.println();
- dump(out, store, column);
- }
- out.decrementTabLevel();
+ MetadataUtils.showDetails(out, ccmds);
- store = freader.readNextRowGroup();
- }
- out.flushColumns();
+ List<BlockMetaData> rblocks = Collections.singletonList(block);
+ freader = new ParquetFileReader(conf, meta.getFileMetaData(), inpath, rblocks, columns);
+ PageReadStore store = freader.readNextRowGroup();
+ while (store != null) {
+ out.incrementTabLevel();
+ for (ColumnDescriptor column : columns) {
+ out.println();
+ dump(out, store, column);
}
+ out.decrementTabLevel();
+
+ store = freader.readNextRowGroup();
+ }
+ out.flushColumns();
} finally {
- if (freader != null) {
- freader.close();
- }
+ if (freader != null) {
+ freader.close();
Review comment:
This is the memory used before and after fix this bug:
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org