[CASSANDRA-19785] Possible memory leak in BTree.FastBuilder

• Type: Bug
• Status: Resolved
• Priority: Normal
• Resolution: Fixed
• Fix Version/s: 4.0.14, 4.1.7, 5.0.1, 5.1-alpha1, 5.1
• Component/s: Legacy/Core
• Bug Category: Degradation - Resource Management
• Severity: Normal
• Complexity: Normal
• Discovered By: User Report
• Platform: All
• Since Version: NA

Source Control Link

https://github.com/apache/cassandra/commit/2842c01ce7eaeb6e72a63435075cc282a1cdd2db

Test and Documentation Plan

run CI

• Assignee: Benedict Elliott Smith
• Reporter: Paul Chandler

Authors

Benedict Elliott Smith

Reviewers

Branimir Lambov

• Created: 19/Jul/24 07:48
• Updated: 5 days ago 13:25
• Resolved: 16/Sep/24 17:28

Description

We are having a problem with the heap growing in size, This is a large cluster > 1,000 nodes across a large number of dc’s. This is running version 4.0.11.

 

Each node has a 32GB heap, and the amount used continues to grow until it reaches 30GB, it then struggles with multiple Full GC pauses, as can be seen here:

We took 2 heap dumps on one node a few days after it was restarted, and the heap had grown by 2.7GB

 

9^th July

11^th July

This can be seen as mainly an increase of memory used by FastThreadLocalThread, increasing from 5.92GB to 8.53GB

Looking deeper into this it can be seen that the growing heap is contained within the threads for the MutationStage, Native-transport-Requests, ReadStage etc. We would expect the memory used within these threads to be short lived, and not grow as time goes on.  We recently increased the size of theses threadpools, and that has increased the size of the problem.

 

Top memory usage for FastThreadLocalThread

9^th July

11^th July

This has led us to investigate whether there could be a memory leak, and we have found the following issues within the retained references in BTree.FastBuilder objects. The issue appears to stem from the reset() method, which does not properly clear all buffers.  We are not really sure how the BTree.FastBuilder works, but this this is our analysis of where a leak might occur.

 

Specifically:

Leaf Buffer Not Being Cleared:
When leaf().count is 0, the statement Arrays.fill(leaf().buffer, 0, leaf().count, null); does not clear the buffer because the end index is 0. This leaves the buffer with references to potentially large objects, preventing garbage collection and increasing heap usage.

Branch inUse Property:
If the inUse property of the branch is set to false elsewhere in the code, the while loop while (branch != null && branch.inUse) does not execute, resulting in uncleared branch buffers and retained references.

 

This is based on the following observations:

    Heap Dumps: Analysis of heap dumps shows that leaf().count is often 0, and as a result, the buffer is not being cleared, leading to high heap utilization.

    Remote Debugging: Debugging sessions indicate that the drain() method sets count to 0, and the inUse flag for the parent branch is set to false, preventing the while loop in reset() from clearing the branch buffers.

 

Issue Links

• is duplicated by: CASSANDRA-19942 Pooled BTree.FastBuilder keeps references to data after reset
• links to: GitHub Pull Request #3480