Skip to content

Read all row group metadata only when position column is projected #1716

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

Merged
rdblue merged 2 commits into from
Nov 7, 2020
Merged

Read all row group metadata only when position column is projected #1716

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f0faa61
Read all row group metadata only when position column is projected
chenjunjiedada Nov 4, 2020
55bb184
address comments
chenjunjiedada Nov 6, 2020
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
13 changes: 9 additions & 4 deletions parquet/src/main/java/org/apache/iceberg/parquet/ReadConf.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@
import java.util.Set;
import java.util.function.Function;
import java.util.stream.Collectors;
import org.apache.iceberg.MetadataColumns;
import org.apache.iceberg.Schema;
import org.apache.iceberg.exceptions.RuntimeIOException;
import org.apache.iceberg.expressions.Expression;
Expand Down Expand Up @@ -87,10 +88,10 @@ class ReadConf<T> {

this.rowGroups = reader.getRowGroups();
this.shouldSkip = new boolean[rowGroups.size()];
this.startRowPositions = new long[rowGroups.size()];

// Fetch all row groups starting positions to compute the row offsets of the filtered row groups
Map<Long, Long> offsetToStartPos = generateOffsetToStartPos();
this.startRowPositions = new long[rowGroups.size()];
Map<Long, Long> offsetToStartPos = generateOffsetToStartPos(expectedSchema);

ParquetMetricsRowGroupFilter statsFilter = null;
ParquetDictionaryRowGroupFilter dictFilter = null;
Expand All @@ -102,7 +103,7 @@ class ReadConf<T> {
long computedTotalValues = 0L;
for (int i = 0; i < shouldSkip.length; i += 1) {
BlockMetaData rowGroup = rowGroups.get(i);
startRowPositions[i] = offsetToStartPos.get(rowGroup.getStartingPos());
startRowPositions[i] = offsetToStartPos == null ? 0 : offsetToStartPos.get(rowGroup.getStartingPos());
boolean shouldRead = filter == null || (
statsFilter.shouldRead(typeWithIds, rowGroup) &&
dictFilter.shouldRead(typeWithIds, rowGroup, reader.getDictionaryReader(rowGroup)));
Expand Down Expand Up @@ -166,7 +167,11 @@ boolean[] shouldSkip() {
return shouldSkip;
}

private Map<Long, Long> generateOffsetToStartPos() {
private Map<Long, Long> generateOffsetToStartPos(Schema schema) {
if (schema.findField(MetadataColumns.ROW_POSITION.fieldId()) == null) {
return null;
}

try (ParquetFileReader fileReader = newReader(file, ParquetReadOptions.builder().build())) {
Map<Long, Long> offsetToStartPos = new HashMap<>();

Expand Down