psendyk commented on code in PR #6680:
URL: https://github.com/apache/hudi/pull/6680#discussion_r1023364717
##########
hudi-common/src/main/java/org/apache/hudi/BaseHoodieTableFileIndex.java:
##########
@@ -179,17 +175,94 @@ public void close() throws Exception {
resetTableMetadata(null);
}
+ protected String[] getPartitionColumns() {
+ return partitionColumns;
+ }
+
+ protected List<Path> getQueryPaths() {
+ return queryPaths;
+ }
+
+ /**
+ * Returns all partition paths matching the ones explicitly provided by the
query (if any)
+ */
protected List<PartitionPath> getAllQueryPartitionPaths() {
- List<String> queryRelativePartitionPaths = queryPaths.stream()
- .map(path -> FSUtils.getRelativePartitionPath(basePath, path))
- .collect(Collectors.toList());
+ if (cachedAllPartitionPaths == null) {
+ List<String> queryRelativePartitionPaths = queryPaths.stream()
+ .map(path -> FSUtils.getRelativePartitionPath(basePath, path))
+ .collect(Collectors.toList());
- // Load all the partition path from the basePath, and filter by the query
partition path.
- // TODO load files from the queryRelativePartitionPaths directly.
- List<String> matchedPartitionPaths = getAllPartitionPathsUnchecked()
- .stream()
- .filter(path ->
queryRelativePartitionPaths.stream().anyMatch(path::startsWith))
- .collect(Collectors.toList());
+ this.cachedAllPartitionPaths =
listPartitionPaths(queryRelativePartitionPaths);
+ }
+
+ return cachedAllPartitionPaths;
+ }
+
+ /**
+ * Returns all listed file-slices w/in the partition paths returned by
{@link #getAllQueryPartitionPaths()}
+ */
+ protected Map<PartitionPath, List<FileSlice>> getAllInputFileSlices() {
+ if (!areAllFileSlicesCached()) {
+ // Fetching file slices for partitions that have not been cached yet
+ List<PartitionPath> missingPartitions =
getAllQueryPartitionPaths().stream()
+ .filter(p -> !cachedAllInputFileSlices.containsKey(p))
+ .collect(Collectors.toList());
+
+ // NOTE: Individual partitions are always cached in full, therefore if
partition is cached
+ // it will hold all the file-slices residing w/in the partition
+
cachedAllInputFileSlices.putAll(loadFileSlicesForPartitions(missingPartitions));
+ }
+
+ return cachedAllInputFileSlices;
+ }
+
+ /**
+ * Get input file slice for the given partition. Will use cache directly if
it is computed before.
+ */
+ protected List<FileSlice> getInputFileSlices(PartitionPath partition) {
+ return cachedAllInputFileSlices.computeIfAbsent(partition,
+ p -> loadFileSlicesForPartitions(Collections.singletonList(p)).get(p));
+ }
+
+ private Map<PartitionPath, List<FileSlice>>
loadFileSlicesForPartitions(List<PartitionPath> partitions) {
+ Map<PartitionPath, FileStatus[]> partitionFiles = partitions.stream()
+ .collect(Collectors.toMap(p -> p, this::loadPartitionPathFiles));
+ HoodieTimeline activeTimeline = getActiveTimeline();
+ Option<HoodieInstant> latestInstant = activeTimeline.lastInstant();
+
+ FileStatus[] allFiles =
partitionFiles.values().stream().flatMap(Arrays::stream).toArray(FileStatus[]::new);
+ HoodieTableFileSystemView fileSystemView = new
HoodieTableFileSystemView(metaClient, activeTimeline, allFiles);
Review Comment:
And to add to this, I'm also seeing the same behavior in eager loading mode,
except it's much worse as it's listing all partitions in the table. So if I'm
correct, then this PR introduces a regression to all MT-based file listing.
When I use the previous implementation (0.12.0), the `files` partition is only
computed once.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
