github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #5720] ollama-docker-app using 100% without reason in idle state #3562

New Issue
Closed
opened 2026-04-12 14:17:16 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 14:17:16 -05:00
Owner
Copy Link

Originally created by @jan-panoch on GitHub (Jul 16, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5720

What is the issue?

we are runnig ollama with docker and container ollama-docker-app-1 in idletime is consuming 100% cpu without reason. no always, but occasionally. restart helps.

the olllama docker stack is started using docker compose file https://github.com/valiantlynx/ollama-docker/blob/main/docker-compose-ollama-gpu.yaml

when i look into container ollama-docker-app-1 i see 2 python processes using 100% cpu - id 13 and id 43. here is pstree:

uvicorn(1)─┬─python(7)
├─python(8)─┬─{python}(17)
│ ├─{python}(18)
│ ├─{python}(20)
│ └─{python}(21)
├─python(13)─┬─{python}(15)
│ ├─{python}(16)
│ ├─{python}(19)
│ └─{python}(43)
└─{uvicorn}(9)

here are cmdlines of bad processes:

root@ce73cb00b056:/code# cat /proc/13/cmdline
/usr/local/bin/python/usr/local/lib/python3.11/site-packages/debugpy/adapter--for-server60015--host0.0.0.0--port5678--server-access-token69fbba1e901ac3b269a1f62151fd6306108d2e5cc5300616cd4574282cfd4a56root@ce73cb00b056:/code# cat /proc/43/cmdline
/usr/local/bin/python/usr/local/lib/python3.11/site-packages/debugpy/adapter--for-server60015--host0.0.0.0--port5678--server-access-token69fbba1e901ac3b269a1f62151fd6306108d2e5cc5300616cd4574282

here is strace:

root@ce73cb00b056:/code# strace -p 13
strace: Process 13 attached
futex(0x5604f9e11fc0, FUTEX_WAIT_BITSET_PRIVATE|FUTEX_CLOCK_REALTIME, 0, NULL, FUTEX_BITSET_MATCH_ANY^Cstrace: Process 13 detached
<detached ...>

and

root@ce73cb00b056:/code# strace -p 43
strace: Process 43 attached
recvfrom(9, "", 1, 0, NULL, NULL) = 0
recvfrom(9, "", 1, 0, NULL, NULL) = 0
recvfrom(9, "", 1, 0, NULL, NULL) = 0
recvfrom(9, "", 1, 0, NULL, NULL) = 0
recvfrom(9, "", 1, 0, NULL, NULL) = 0
recvfrom(9, "", 1, 0, NULL, NULL) = 0
recvfrom(9, "", 1, 0, NULL, NULL) = 0
recvfrom(9, "", 1, 0, NULL, NULL) = 0
recvfrom(9, "", 1, 0, NULL, NULL) = 0
....
....
....
....
...until break

any ideas?

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.2.5

Originally created by @jan-panoch on GitHub (Jul 16, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5720 ### What is the issue? we are runnig ollama with docker and container ollama-docker-app-1 in idletime is consuming 100% cpu without reason. no always, but occasionally. restart helps. the olllama docker stack is started using docker compose file https://github.com/valiantlynx/ollama-docker/blob/main/docker-compose-ollama-gpu.yaml when i look into container ollama-docker-app-1 i see 2 python processes using 100% cpu - id 13 and id 43. here is pstree: uvicorn(1)─┬─python(7) ├─python(8)─┬─{python}(17) │ ├─{python}(18) │ ├─{python}(20) │ └─{python}(21) ├─python(13)─┬─{python}(15) │ ├─{python}(16) │ ├─{python}(19) │ └─{python}(43) └─{uvicorn}(9) here are cmdlines of bad processes: root@ce73cb00b056:/code# cat /proc/13/cmdline /usr/local/bin/python/usr/local/lib/python3.11/site-packages/debugpy/adapter--for-server60015--host0.0.0.0--port5678--server-access-token69fbba1e901ac3b269a1f62151fd6306108d2e5cc5300616cd4574282cfd4a56root@ce73cb00b056:/code# cat /proc/43/cmdline /usr/local/bin/python/usr/local/lib/python3.11/site-packages/debugpy/adapter--for-server60015--host0.0.0.0--port5678--server-access-token69fbba1e901ac3b269a1f62151fd6306108d2e5cc5300616cd4574282 here is strace: root@ce73cb00b056:/code# strace -p 13 strace: Process 13 attached futex(0x5604f9e11fc0, FUTEX_WAIT_BITSET_PRIVATE|FUTEX_CLOCK_REALTIME, 0, NULL, FUTEX_BITSET_MATCH_ANY^Cstrace: Process 13 detached <detached ...> and root@ce73cb00b056:/code# strace -p 43 strace: Process 43 attached recvfrom(9, "", 1, 0, NULL, NULL) = 0 recvfrom(9, "", 1, 0, NULL, NULL) = 0 recvfrom(9, "", 1, 0, NULL, NULL) = 0 recvfrom(9, "", 1, 0, NULL, NULL) = 0 recvfrom(9, "", 1, 0, NULL, NULL) = 0 recvfrom(9, "", 1, 0, NULL, NULL) = 0 recvfrom(9, "", 1, 0, NULL, NULL) = 0 recvfrom(9, "", 1, 0, NULL, NULL) = 0 recvfrom(9, "", 1, 0, NULL, NULL) = 0 .... .... .... .... ...until break any ideas? ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.2.5
GiteaMirror added the bug label 2026-04-12 14:17:16 -05:00
GiteaMirror commented 2026-04-12 14:17:19 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 16, 2024):

Should probably be filed in https://github.com/valiantlynx/ollama-docker/issues. Those processes are listening on port 5678, which according to docker-compose-ollama-gpu.yaml is the app service, which is not part of the ollama project.

<!-- gh-comment-id:2230468268 --> @rick-github commented on GitHub (Jul 16, 2024): Should probably be filed in https://github.com/valiantlynx/ollama-docker/issues. Those processes are listening on port 5678, which according to docker-compose-ollama-gpu.yaml is the `app` service, which is not part of the ollama project.
GiteaMirror commented 2026-04-12 14:17:19 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jul 23, 2024):

Agreed, this doesn't seem to be a defect from Ollama itself. If you can create an isolated repro scenario showing it is an ollama defect, please share the details and I'll reopen the issue.

<!-- gh-comment-id:2244030653 --> @dhiltgen commented on GitHub (Jul 23, 2024): Agreed, this doesn't seem to be a defect from Ollama itself. If you can create an isolated repro scenario showing it is an ollama defect, please share the details and I'll reopen the issue.
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 bug
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#3562
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?