langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 12:05:30 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

The workflow node status is always running #12898

New Issue
Closed
opened 2026-02-21 19:09:34 -05:00 by yindo · 3 comments
yindo commented 2026-02-21 19:09:34 -05:00
Owner
Copy Link
Copy Source

Originally created by @ys97105 on GitHub (Apr 14, 2025).

Self Checks

  • This is only for bug report, if you would like to ask a question, please head to Discussions.
  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
  • [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:)
  • Please do not modify this template :) and fill in all the required fields.

Dify version

1.0.1

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

I used apifox to stress test /chat-messages, with 50 concurrent users.
The following phenomena occurred:

  1. The status of the conversation log is always running
  2. The node status is always running
  3. Clicking the tracking button shows a blank

Image

Image

✔️ Expected Behavior

Workflow is running normally

❌ Actual Behavior

The workflow_runs table is not updated properly

Originally created by @ys97105 on GitHub (Apr 14, 2025). ### Self Checks - [x] This is only for bug report, if you would like to ask a question, please head to [Discussions](https://github.com/langgenius/dify/discussions/categories/general). - [x] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify/issues), including closed ones. - [x] I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)). - [x] [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:) - [x] Please do not modify this template :) and fill in all the required fields. ### Dify version 1.0.1 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce I used apifox to stress test /chat-messages, with 50 concurrent users. The following phenomena occurred: 1. The status of the conversation log is always running 2. The node status is always running 3. Clicking the tracking button shows a blank ![Image](https://github.com/user-attachments/assets/f29747a6-75de-4581-aede-21d52e5bd498) ![Image](https://github.com/user-attachments/assets/4553318f-24ad-483b-a50b-7f1aaaf6693e) ### ✔️ Expected Behavior Workflow is running normally ### ❌ Actual Behavior The workflow_runs table is not updated properly
yindo added the 🐞 bug🌊 feat:workflow labels 2026-02-21 19:09:34 -05:00
yindo closed this issue 2026-02-21 19:09:34 -05:00
yindo commented 2026-02-21 19:09:35 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Apr 14, 2025):

Hello @ys97105! I'm Dosu, here to assist you with any bugs or questions you have while we wait for a human maintainer. Let's tackle this together!

I found a similar unsolved discussion titled "What if my task keeps running and can't stop" which might be related to your issue [1].

Regarding your issue, there are several potential factors to consider:

  1. Workflow Node Status Update Conditions: The workflow node status is updated based on specific conditions such as successful execution, failed execution, running, exception, or retry. If the node is stuck in the "running" status, it might be due to an error not being properly caught or handled [2].

  2. Concurrency Handling: Dify uses a rate limiting mechanism and Celery for task management. High concurrency, like your stress test with 50 concurrent users, might lead to issues if the system's rate limits or worker configurations are not properly set. Ensure that the CELERY_WORKER_AMOUNT is configured to handle the load without causing workers to become unresponsive [3][4].

  3. Timeout Settings: Check the timeout settings for HTTP nodes, as these could affect the status of workflow nodes if they exceed the configured timeouts. Adjust the timeout settings in your .env file and restart your Docker containers to apply the changes [5].

These areas might help you diagnose and resolve the issue with the workflow node status being stuck in "running."

To continue talking to Dosu, mention @dosu.

Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other

@dosubot[bot] commented on GitHub (Apr 14, 2025): <!-- Greeting --> Hello @ys97105! I'm [Dosu](https://dosu.dev), here to assist you with any bugs or questions you have while we wait for a human maintainer. Let's tackle this together! <!-- Answer --> I found a similar unsolved discussion titled "[What if my task keeps running and can't stop](https://github.com/langgenius/dify/discussions/15833)" which might be related to your issue <sup>[[1]](https://github.com/langgenius/dify/discussions/15833)</sup>. Regarding your issue, there are several potential factors to consider: 1. **Workflow Node Status Update Conditions**: The workflow node status is updated based on specific conditions such as successful execution, failed execution, running, exception, or retry. If the node is stuck in the "running" status, it might be due to an error not being properly caught or handled <sup>[[2]](https://github.com/langgenius/dify/blob/main/api/core/workflow/nodes/code/code_node.py)</sup>. 2. **Concurrency Handling**: Dify uses a rate limiting mechanism and Celery for task management. High concurrency, like your stress test with 50 concurrent users, might lead to issues if the system's rate limits or worker configurations are not properly set. Ensure that the `CELERY_WORKER_AMOUNT` is configured to handle the load without causing workers to become unresponsive <sup>[[3]](https://github.com/langgenius/dify/blob/main/api/core/app/features/rate_limiting/rate_limit.py)</sup><sup>[[4]](https://github.com/langgenius/dify/issues/12325)</sup>. 3. **Timeout Settings**: Check the timeout settings for HTTP nodes, as these could affect the status of workflow nodes if they exceed the configured timeouts. Adjust the timeout settings in your `.env` file and restart your Docker containers to apply the changes <sup>[[5]](https://github.com/langgenius/dify/issues/12098)</sup>. These areas might help you diagnose and resolve the issue with the workflow node status being stuck in "running." <!-- Dosu Comment Footer --> *To continue talking to [Dosu](https://dosu.dev), mention @dosu.* --- <sup>Help Dosu learn! Give it feedback: [Great Response](https://app.dosu.dev/response-feedback/1504986f-df94-4cfa-8b16-a26c62c5c4ee?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/1504986f-df94-4cfa-8b16-a26c62c5c4ee?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/1504986f-df94-4cfa-8b16-a26c62c5c4ee?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/1504986f-df94-4cfa-8b16-a26c62c5c4ee?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/1504986f-df94-4cfa-8b16-a26c62c5c4ee?feedback_type=hallucination) | [Bug Report](https://app.dosu.dev/response-feedback/1504986f-df94-4cfa-8b16-a26c62c5c4ee?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/1504986f-df94-4cfa-8b16-a26c62c5c4ee?feedback_type=other)</sup>
yindo commented 2026-02-21 19:09:35 -05:00
Author
Owner
Copy Link
Copy Source

@crazywoola commented on GitHub (Apr 14, 2025):

This has been fixed, will be released later.

@crazywoola commented on GitHub (Apr 14, 2025): This has been fixed, will be released later.
yindo commented 2026-02-21 19:09:35 -05:00
Author
Owner
Copy Link
Copy Source

@aniya105 commented on GitHub (Apr 14, 2025):

This has been fixed, will be released later.

@crazywoola May I ask which PR has fixed this issue

@aniya105 commented on GitHub (Apr 14, 2025): > This has been fixed, will be released later. @crazywoola May I ask which PR has fixed this issue
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Knowledge Pipeline
Proposal
WIP
cloud
dependencies
feat:webapp
good first issue
outdated
performance
pull-request
Mirrored from GitHub Pull Request
 python:uv
refactor
size:L
stale
status: accepting prs
status: blocked
status: in discussion
stt & tts
vulnerablity
web
wont-fix
🌊 feat:workflow
🌚 invalid
🐞 bug
👻 feat:rag
💪 enhancement
📚 documentation
🔨 feat:tools
🙋‍♂️ question
🙏 help wanted
🤔 cant-reproduce
🤖 feat:agent
No Label 🌊 feat:workflow 🐞 bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#12898
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?