Skip to content

[HUDI-5341] IncrementalCleaning consider later clustering #7401

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

Closed
zhuanshenbsj1 wants to merge 2 commits into from
Closed

[HUDI-5341] IncrementalCleaning consider later clustering #7401

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e52b948
IncrementalCleaning consider later clustering
zhuanshenbsj1 Dec 7, 2022
ff0887a
fix checkstyle error
zhuanshenbsj1 Dec 7, 2022
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
8 changes: 6 additions & 2 deletions ...ent/hudi-client-common/src/main/java/org/apache/hudi/table/action/clean/CleanPlanner.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -188,8 +188,12 @@ private List<String> getPartitionPathsForIncrementalCleaning(HoodieCleanMetadata
+ "since last cleaned at " + cleanMetadata.getEarliestCommitToRetain()
+ ". New Instant to retain : " + newInstantToRetain);
return hoodieTable.getCompletedCommitsTimeline().getInstantsAsStream().filter(
instant -> HoodieTimeline.compareTimestamps(instant.getTimestamp(), HoodieTimeline.GREATER_THAN_OR_EQUALS,
cleanMetadata.getEarliestCommitToRetain()) && HoodieTimeline.compareTimestamps(instant.getTimestamp(),
instant -> (HoodieTimeline.compareTimestamps(instant.getTimestamp(), HoodieTimeline.GREATER_THAN_OR_EQUALS,
cleanMetadata.getEarliestCommitToRetain())
|| (instant.getMarkerFileAccessTimestamp().isPresent()
&& (HoodieTimeline.compareTimestamps(instant.getMarkerFileAccessTimestamp().get(), HoodieTimeline.GREATER_THAN_OR_EQUALS,
cleanMetadata.getStartCleanTime()))))
&& HoodieTimeline.compareTimestamps(instant.getTimestamp(),
HoodieTimeline.LESSER_THAN, newInstantToRetain.get().getTimestamp())).flatMap(instant -> {
try {
if (HoodieTimeline.REPLACE_COMMIT_ACTION.equals(instant.getAction())) {
Expand Down
10 changes: 10 additions & 0 deletions hudi-common/src/main/java/org/apache/hudi/common/table/timeline/HoodieInstant.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,8 @@

package org.apache.hudi.common.table.timeline;

import org.apache.hudi.common.util.Option;

import org.apache.hadoop.fs.FileStatus;

import java.io.Serializable;
Expand Down Expand Up @@ -73,6 +75,7 @@ public enum State {
private State state = State.COMPLETED;
private String action;
private String timestamp;
private Option<String> markerFileAccessTimestamp;

/**
* Load the instant from the meta FileStatus.
Expand All @@ -82,6 +85,7 @@ public HoodieInstant(FileStatus fileStatus) {
String fileName = fileStatus.getPath().getName();
String fileExtension = getTimelineFileExtension(fileName);
timestamp = fileName.replace(fileExtension, "");
markerFileAccessTimestamp = Option.ofNullable(HoodieInstantTimeGenerator.parseTimeMillisToInstantTime(fileStatus.getAccessTime()));

// Next read the action for this marker
action = fileExtension.replaceFirst(".", "");
Expand All @@ -104,12 +108,14 @@ public HoodieInstant(boolean isInflight, String action, String timestamp) {
this.state = isInflight ? State.INFLIGHT : State.COMPLETED;
this.action = action;
this.timestamp = timestamp;
this.markerFileAccessTimestamp = Option.ofNullable(null);
}

public HoodieInstant(State state, String action, String timestamp) {
this.state = state;
this.action = action;
this.timestamp = timestamp;
this.markerFileAccessTimestamp = Option.ofNullable(null);
}

public boolean isCompleted() {
Expand All @@ -132,6 +138,10 @@ public String getTimestamp() {
return timestamp;
}

public Option<String> getMarkerFileAccessTimestamp() {
return markerFileAccessTimestamp;
}

/**
* Get the filename for this instant.
*/
Expand Down
9 changes: 9 additions & 0 deletions ...ommon/src/main/java/org/apache/hudi/common/table/timeline/HoodieInstantTimeGenerator.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,6 +81,15 @@ public static String createNewInstantTime(long milliseconds) {
});
}

public static String parseTimeMillisToInstantTime(long milliseconds) {
try {
Date d = new Date(milliseconds);
return MILLIS_INSTANT_TIME_FORMATTER.format(convertDateToTemporalAccessor(d));
} catch (DateTimeParseException e) {
throw e;
}
}

public static Date parseDateFromInstantTime(String timestamp) throws ParseException {
try {
// Enables backwards compatibility with non-millisecond granularity instants
Expand Down