-
Notifications
You must be signed in to change notification settings - Fork 25.3k
Introduce compute listener #110400
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.
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
Merged
Introduce compute listener #110400
Changes from all commits
Commits
Show all changes
5 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,5 @@ | ||
| pr: 110400 | ||
| summary: Introduce compute listener | ||
| area: ES|QL | ||
| type: bug | ||
| issues: [] |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
112 changes: 112 additions & 0 deletions
112
...lugin/esql/compute/src/main/java/org/elasticsearch/compute/operator/FailureCollector.java
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,112 @@ | ||
| /* | ||
| * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one | ||
| * or more contributor license agreements. Licensed under the Elastic License | ||
| * 2.0; you may not use this file except in compliance with the Elastic License | ||
| * 2.0. | ||
| */ | ||
|
|
||
| package org.elasticsearch.compute.operator; | ||
|
|
||
| import org.elasticsearch.ElasticsearchException; | ||
| import org.elasticsearch.ExceptionsHelper; | ||
| import org.elasticsearch.common.util.concurrent.ConcurrentCollections; | ||
| import org.elasticsearch.tasks.TaskCancelledException; | ||
| import org.elasticsearch.transport.TransportException; | ||
|
|
||
| import java.util.List; | ||
| import java.util.Queue; | ||
| import java.util.concurrent.atomic.AtomicInteger; | ||
|
|
||
| /** | ||
| * {@code FailureCollector} is responsible for collecting exceptions that occur in the compute engine. | ||
| * The collected exceptions are categorized into task-cancelled and non-task-cancelled exceptions. | ||
| * To limit memory usage, this class collects only the first 10 exceptions in each category by default. | ||
| * When returning the accumulated failure to the caller, this class prefers non-task-cancelled exceptions | ||
| * over task-cancelled ones as they are more useful for diagnosing issues. | ||
| */ | ||
| public final class FailureCollector { | ||
| private final Queue<Exception> cancelledExceptions = ConcurrentCollections.newQueue(); | ||
| private final AtomicInteger cancelledExceptionsCount = new AtomicInteger(); | ||
|
|
||
| private final Queue<Exception> nonCancelledExceptions = ConcurrentCollections.newQueue(); | ||
| private final AtomicInteger nonCancelledExceptionsCount = new AtomicInteger(); | ||
|
|
||
| private final int maxExceptions; | ||
| private volatile boolean hasFailure = false; | ||
| private Exception finalFailure = null; | ||
|
|
||
| public FailureCollector() { | ||
| this(10); | ||
| } | ||
|
|
||
| public FailureCollector(int maxExceptions) { | ||
| if (maxExceptions <= 0) { | ||
| throw new IllegalArgumentException("maxExceptions must be at least one"); | ||
| } | ||
| this.maxExceptions = maxExceptions; | ||
| } | ||
|
|
||
| public void unwrapAndCollect(Exception originEx) { | ||
| final Exception e = originEx instanceof TransportException | ||
| ? (originEx.getCause() instanceof Exception cause ? cause : new ElasticsearchException(originEx.getCause())) | ||
| : originEx; | ||
| if (ExceptionsHelper.unwrap(e, TaskCancelledException.class) != null) { | ||
| if (cancelledExceptionsCount.incrementAndGet() <= maxExceptions) { | ||
| cancelledExceptions.add(e); | ||
| } | ||
| } else { | ||
| if (nonCancelledExceptionsCount.incrementAndGet() <= maxExceptions) { | ||
| nonCancelledExceptions.add(e); | ||
| } | ||
| } | ||
| hasFailure = true; | ||
| } | ||
|
|
||
| /** | ||
| * @return {@code true} if any failure has been collected, {@code false} otherwise | ||
| */ | ||
| public boolean hasFailure() { | ||
| return hasFailure; | ||
| } | ||
|
|
||
| /** | ||
| * Returns the accumulated failure, preferring non-task-cancelled exceptions over task-cancelled ones. | ||
| * Once this method builds the failure, incoming failures are discarded. | ||
| * | ||
| * @return the accumulated failure, or {@code null} if no failure has been collected | ||
| */ | ||
| public Exception getFailure() { | ||
| if (hasFailure == false) { | ||
| return null; | ||
| } | ||
| synchronized (this) { | ||
| if (finalFailure == null) { | ||
| finalFailure = buildFailure(); | ||
| } | ||
| return finalFailure; | ||
| } | ||
| } | ||
|
|
||
| private Exception buildFailure() { | ||
| assert hasFailure; | ||
| assert Thread.holdsLock(this); | ||
| int total = 0; | ||
| Exception first = null; | ||
| for (var exceptions : List.of(nonCancelledExceptions, cancelledExceptions)) { | ||
| for (Exception e : exceptions) { | ||
| if (first == null) { | ||
| first = e; | ||
| total++; | ||
| } else if (first != e) { | ||
| first.addSuppressed(e); | ||
| total++; | ||
| } | ||
| if (total >= maxExceptions) { | ||
| return first; | ||
| } | ||
| } | ||
| } | ||
| assert first != null; | ||
| return first; | ||
| } | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
getAndUpdateis documented as requiring a side-effect-free function because it'll be retried sometimes. I think this is safe, but it's not really side effect free. Maybe it'd be more readable if we used an atomicarray or something. Either way, I spent a while reading this code and thinking about it, but I don't think the performance is all that critical here because it's deep into exception path.