github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-08-30 17:25:30 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

[GH-ISSUE #19843] issue: Intermittent Performance Degradation #73620

New Issue
Closed
opened 2026-05-13 06:01:27 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-13 06:01:27 -05:00
Owner
Copy Link
Copy Source

Originally created by @gneuli on GitHub (Dec 9, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/19843

Check Existing Issues

  • I have searched for any existing and/or related issues.
  • I have searched for any existing and/or related discussions.
  • I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
  • I am using the latest version of Open WebUI.

Installation Method

Other

Open WebUI Version

v0.6.40

Ollama Version (if applicable)

No response

Operating System

Red Hat CoreOS (Kubernetes Cluster Installation)

Browser (if applicable)

No response

Confirmation

  • I have read and followed all instructions in README.md.
  • I am using the latest version of both Open WebUI and Ollama.
  • I have included the browser console logs.
  • I have included the Docker container logs.
  • I have provided every relevant configuration, setting, and environment variable used in my setup.
  • I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
  • I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
  • Start with the initial platform/version/OS and dependencies used,
  • Specify exact install/launch/configure commands,
  • List URLs visited, user input (incl. example values/emails/passwords if needed),
  • Describe all options and toggles enabled or changed,
  • Include any files or environmental changes,
  • Identify the expected and actual result at each stage,
  • Ensure any reasonably skilled user can follow and hit the same issue.

Expected Behavior

Consistently fast and responsive performance for all operations.

Actual Behavior

We are experiencing intermittent and temporary performance degradation with our Open WebUI deployment that tremendously slows down the whole application (sometimes to the point of being unresponsive). These incidents occur almost daily, typically during peak usage periods. The root cause has not yet been identified, and our attempts at mitigation have only partially improved the situation.

Observed behavior:

  • Open WebUI becomes very slow, affecting not only chat responses but also other interactions such as logging in.
  • The OpenAI API in the background does not experience latency or downtime during these periods.
  • Performance issues affects the whole application and e.g. some users also report an empty model list during and shortly after the slowdowns.
  • The application recovers on its own after a certain period without any intervention (usually around 1h).

Relevant configuration changes:
We have tried to optimize the configuration according to the recommendations in the documentation, e.g.

  • THREAD_POOL_SIZE set to several thousand
  • ENABLE_ASYNC_EMBEDDING disabled
  • Initially used a Redis Sentinel setup but switched to Redis Cluster when issues started
  • Generously scaled up all resources related to Open WebUI and its components (replicas, CPU, memory)

What we’ve tried so far:

  • Monitoring infrastructure resources during incidents — no obvious exhaustion found.
  • Verified OpenAI API stays responsive during degraded periods.
  • Adjusted environment variables as mentioned above.
  • Scaled resources further without eliminating the problem.

Request for guidance:
We are seeking input on:

  1. Recommended detailed debugging steps for tracking down performance bottlenecks in Open WebUI.
  2. Any known causes that could result in temporary large slowdowns affecting the whole application, even when infrastructure appears healthy.
  3. How to determine whether the issue is with Open WebUI itself or an infrastructure-related problem.

Any help in narrowing down this issue and identifying root causes would be greatly appreciated.

Steps to Reproduce

Deployment & setup:

  • Kubernetes-based deployment using helm-charts running on an Openshift cluster. Open Webui is scaled up to use several pods, all of which are far away from reaching their limits related to CPU of memory.
  • Using Qdrant vector DB (with ENABLE_QDRANT_MULTITENANCY_MODE enabled) and Redis Cluster
  • High number of users and significant traffic load.
  • Resources have been scaled up considerably to handle expected demand.
  • No pod restarts or container crashes occur during the incidents.
  • Works normally most of the time, but occasionally suffers significant temporary performance impact.

Logs & Screenshots

Setting loging level to Debug was of limited help so far due to the massive amount of logs.

Additional Information

No response

Originally created by @gneuli on GitHub (Dec 9, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/19843 ### Check Existing Issues - [x] I have searched for any existing and/or related issues. - [x] I have searched for any existing and/or related discussions. - [x] I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!). - [x] I am using the latest version of Open WebUI. ### Installation Method Other ### Open WebUI Version v0.6.40 ### Ollama Version (if applicable) _No response_ ### Operating System Red Hat CoreOS (Kubernetes Cluster Installation) ### Browser (if applicable) _No response_ ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have included the browser console logs. - [x] I have included the Docker container logs. - [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.** - [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc). - [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps: - Start with the initial platform/version/OS and dependencies used, - Specify exact install/launch/configure commands, - List URLs visited, user input (incl. example values/emails/passwords if needed), - Describe all options and toggles enabled or changed, - Include any files or environmental changes, - Identify the expected and actual result at each stage, - Ensure any reasonably skilled user can follow and hit the same issue. ### Expected Behavior Consistently fast and responsive performance for all operations. ### Actual Behavior We are experiencing intermittent and temporary performance degradation with our Open WebUI deployment that tremendously slows down the whole application (sometimes to the point of being unresponsive). These incidents occur almost daily, typically during peak usage periods. The root cause has not yet been identified, and our attempts at mitigation have only partially improved the situation. **Observed behavior:** - Open WebUI becomes very slow, affecting not only chat responses but also other interactions such as logging in. - The OpenAI API in the background does not experience latency or downtime during these periods. - Performance issues affects the whole application and e.g. some users also report an empty model list during and shortly after the slowdowns. - The application recovers on its own after a certain period without any intervention (usually around 1h). **Relevant configuration changes:** We have tried to optimize the configuration according to the recommendations in the documentation, e.g. - **THREAD_POOL_SIZE** set to several thousand - **ENABLE_ASYNC_EMBEDDING** disabled - Initially used a Redis Sentinel setup but switched to Redis Cluster when issues started - Generously scaled up all resources related to Open WebUI and its components (replicas, CPU, memory) **What we’ve tried so far:** - Monitoring infrastructure resources during incidents — no obvious exhaustion found. - Verified OpenAI API stays responsive during degraded periods. - Adjusted environment variables as mentioned above. - Scaled resources further without eliminating the problem. **Request for guidance:** We are seeking input on: 1. Recommended detailed debugging steps for tracking down performance bottlenecks in Open WebUI. 2. Any known causes that could result in temporary large slowdowns affecting the whole application, even when infrastructure appears healthy. 3. How to determine whether the issue is with Open WebUI itself or an infrastructure-related problem. Any help in narrowing down this issue and identifying root causes would be greatly appreciated. ### Steps to Reproduce Deployment & setup: - Kubernetes-based deployment using helm-charts running on an Openshift cluster. Open Webui is scaled up to use several pods, all of which are far away from reaching their limits related to CPU of memory. - Using Qdrant vector DB (with ENABLE_QDRANT_MULTITENANCY_MODE enabled) and Redis Cluster - High number of users and significant traffic load. - Resources have been scaled up considerably to handle expected demand. - No pod restarts or container crashes occur during the incidents. - Works normally most of the time, but occasionally suffers significant temporary performance impact. ### Logs & Screenshots Setting loging level to Debug was of limited help so far due to the massive amount of logs. ### Additional Information _No response_
GiteaMirror added the bug label 2026-05-13 06:01:27 -05:00
GiteaMirror commented 2026-05-13 06:01:30 -05:00
Author
Owner
Copy Link
Copy Source

@owui-terminator[bot] commented on GitHub (Dec 9, 2025):

🔍 Similar Issues Found

I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:

  1. #19064 issue: Potential Root Cause for Data Loss (Multi-Device) and Performance Issues (Multimodal)
    by 2erTwo6 • Nov 09, 2025 • bug

  2. #19496 issue: 500 internal server error appears in v0.6.40
    by cloudtuotuo • Nov 26, 2025 • bug

  3. #19777 issue:
    by Yaute7 • Dec 05, 2025 • bug

  4. #19563 issue:
    by naruto7g • Nov 28, 2025 • bug

  5. #19211 issue:
    by Byrnes9 • Nov 16, 2025 • bug

Show 5 more related issues

  1. #19438 issue: Icon loading regression
    by JoelShepard • Nov 24, 2025 • bug

  2. #19007 issue: Performance regression in Open WebUI v0.6.36 – noticeable slowdown with local models
    by manhtv46k55 • Nov 07, 2025 • bug

  3. #19314 issue: cannot persist docling parameters
    by Elettrotecnica • Nov 20, 2025 • bug

  4. #18145 issue: 0.6.33 regression
    by Ark-Levy • Oct 08, 2025 • bug

  5. #19047 issue: followup questions sometimes fail to generate
    by avidwriter • Nov 08, 2025 • bug

💡 Tips:

  • If this is a duplicate, please consider closing this issue and adding any additional details to the existing one
  • If you found a solution in any of these issues, please share it here to help others

This comment was generated automatically by a bot. Please react with a 👍 if this comment was helpful, or a 👎 if it was not.

<!-- gh-comment-id:3631852602 --> @owui-terminator[bot] commented on GitHub (Dec 9, 2025): 🔍 **Similar Issues Found** I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions: 1. [#19064](https://github.com/open-webui/open-webui/issues/19064) **issue: Potential Root Cause for Data Loss (Multi-Device) and Performance Issues (Multimodal)** *by 2erTwo6 • Nov 09, 2025 • `bug`* 2. [#19496](https://github.com/open-webui/open-webui/issues/19496) **issue: 500 internal server error appears in v0.6.40** *by cloudtuotuo • Nov 26, 2025 • `bug`* 3. [#19777](https://github.com/open-webui/open-webui/issues/19777) **issue:** *by Yaute7 • Dec 05, 2025 • `bug`* 4. [#19563](https://github.com/open-webui/open-webui/issues/19563) **issue:** *by naruto7g • Nov 28, 2025 • `bug`* 5. [#19211](https://github.com/open-webui/open-webui/issues/19211) **issue:** *by Byrnes9 • Nov 16, 2025 • `bug`* <details> <summary>Show 5 more related issues</summary> 6. [#19438](https://github.com/open-webui/open-webui/issues/19438) **issue: Icon loading regression** *by JoelShepard • Nov 24, 2025 • `bug`* 7. [#19007](https://github.com/open-webui/open-webui/issues/19007) **issue: Performance regression in Open WebUI v0.6.36 – noticeable slowdown with local models** *by manhtv46k55 • Nov 07, 2025 • `bug`* 8. [#19314](https://github.com/open-webui/open-webui/issues/19314) **issue: cannot persist docling parameters** *by Elettrotecnica • Nov 20, 2025 • `bug`* 9. [#18145](https://github.com/open-webui/open-webui/issues/18145) **issue: 0.6.33 regression** *by Ark-Levy • Oct 08, 2025 • `bug`* 10. [#19047](https://github.com/open-webui/open-webui/issues/19047) **issue: followup questions sometimes fail to generate** *by avidwriter • Nov 08, 2025 • `bug`* </details> --- 💡 **Tips:** - If this is a duplicate, please consider closing this issue and adding any additional details to the existing one - If you found a solution in any of these issues, please share it here to help others *This comment was generated automatically by a bot.* Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
GiteaMirror commented 2026-05-13 06:01:30 -05:00
Author
Owner
Copy Link
Copy Source

@Classic298 commented on GitHub (Dec 9, 2025):

Setting log level to debug will make performance much worse. Speaking of personal experiences here.

Set it to WARNING instead.

Also pls share all env vars you have set and their respective values and give a detailed setup overview.

Not just "we scaled resources" or "we use kubernetes".

What main database do you use?

And much more. A lot of details missing. And please don't open this in the issues, this belongs to discussions.

<!-- gh-comment-id:3632201109 --> @Classic298 commented on GitHub (Dec 9, 2025): Setting log level to debug will make performance much worse. Speaking of personal experiences here. Set it to WARNING instead. Also pls share all env vars you have set and their respective values and give a detailed setup overview. Not just "we scaled resources" or "we use kubernetes". What main database do you use? And much more. A lot of details missing. And please don't open this in the issues, this belongs to discussions.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No labels bug
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
GiteaMirror ninjasurge (Kaehlen Rog)
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#73620