github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #10599] [MERGED] sched: fix race leading to orphaned runners #44540

New Issue
Closed
opened 2026-04-24 23:59:42 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-24 23:59:42 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/10599
Author: @dhiltgen
Created: 5/6/2025
Status: ✅ Merged
Merged: 5/7/2025
Merged by: @dhiltgen

Base: main ← Head: sched_log

📝 Commits (1)

  • 19f7c50 sched: fix race leading to orphaned runners

📊 Changes

2 files changed (+40 additions, -20 deletions)

View changed files

📝 llm/server.go (+3 -3)
📝 server/sched.go (+37 -17)

📄 Description

If a model is loading, and the request context is canceled during the load by a client closing the connection, and another request is inbound for the same model with a different configuration (context size, etc.) thus requiring a reload, two unload events can be in flight. The first shuts down the original model load, but the second one caused the loss of the new reloading runner reference, thus triggering the leak.

The primary fix is detecting the duplicate unload and ignoring the second instance. The load routine is also hardened to ensure we detect clobbering an already present runner and unload it with a warning.

Fixes #10433

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/10599 **Author:** [@dhiltgen](https://github.com/dhiltgen) **Created:** 5/6/2025 **Status:** ✅ Merged **Merged:** 5/7/2025 **Merged by:** [@dhiltgen](https://github.com/dhiltgen) **Base:** `main` ← **Head:** `sched_log` --- ### 📝 Commits (1) - [`19f7c50`](https://github.com/ollama/ollama/commit/19f7c507506fb44833dfd6f72f20674a1530e5a5) sched: fix race leading to orphaned runners ### 📊 Changes **2 files changed** (+40 additions, -20 deletions) <details> <summary>View changed files</summary> 📝 `llm/server.go` (+3 -3) 📝 `server/sched.go` (+37 -17) </details> ### 📄 Description If a model is loading, and the request context is canceled during the load by a client closing the connection, and another request is inbound for the same model with a different configuration (context size, etc.) thus requiring a reload, two unload events can be in flight. The first shuts down the original model load, but the second one caused the loss of the new reloading runner reference, thus triggering the leak. The primary fix is detecting the duplicate unload and ignoring the second instance. The load routine is also hardened to ensure we detect clobbering an already present runner and unload it with a warning. Fixes #10433 --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-24 23:59:42 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#44540
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?