Skip to content

RocketMQ Netty NioSocketChannel stuck on read fd 0 #10246

@ChangingFond

Description

@ChangingFond

Before Creating the Bug Report

  • I found a bug, not just asking a question, which should be created in GitHub Discussions.

  • I have searched the GitHub Issues and GitHub Discussions of this repository and believe that this is not a duplicate.

  • I have confirmed that this bug belongs to the current repository, not other repositories of RocketMQ.

Runtime platform environment

Both CentOS and OpenEuler met

RocketMQ version

RocketMQ 4.9.x

JDK Version

OpenJDK 17.0.2, we use ZGC.

Describe the Bug

We met a extremely strange problem in rocketmq, a netty workerGroup thread hung on sun.nio.ch.SocketDispatcher.read0(workerGroup thread we set 3), then this server's 1/3 another tcp events can't be processed. See details in netty/netty#15746, I wonder if anyone met this.

Image

Then we rollback our production cluster to rocketmq 4.8 & jdk 8, problem is not reproduced.

Environment: rocketmq 4.9.4 on jdk 17.0.2

Steps to Reproduce

we dont't know how to reproduce

What Did You Expect to See?

What Did You See Instead?

Additional Context

No response

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions