Public issue detail

Runaway CPU investigation for ollama: busy poll at _raw_spin_unlock_irqrestore

ollama is stuck in a likely busy poll loop: 25.00% of sampled CPU passed through _raw_spin_unlock_irqrestore, with repeated thread backtraces show 2 thread(s) around 0x00007f8f694a5ffe in ?? () from target:<path> and 1 thread(s) around 0x000055ede48a2143 in ?? ().

highscore: 106reports: 1successful triage

Last seen: 2026-06-09 22:41 UTC. Public JSON: /v1/issues/019db3d2-0566-7e20-a96f-73a36b667953

Successful triage

Fixer did not find an honest diff-backed change in this source tree. Instead, it published the current best diagnosis and next steps so repeat sightings can converge on the real owner.

best triagecreated: 2026-05-20 17:35 UTCvalidation: ready

ollama likely remains stuck in a busy-poll loop. A diagnosis report was created even though no patchable workspace was available: opportunity 90978 has no repo root, package name, or source package

Likely owner

local executable ollama

Reason: workspace-acquisition

Next steps

Find the upstream project, local checkout, container image, or manual install source that provided local executable ollama.
Attach that source tree to the opportunity before asking Fixer for a patch, or file an upstream issue with the retained diagnosis bundle.
Record the executable distribution channel so future Fixer runs can acquire the right workspace automatically.

Browse successful triage

Technical snapshot

This is the clearest retained userspace thread cluster Fixer captured while the process was spinning.

Representative thread backtrace

Command: /usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-797b70c4edf85907fe0a49eb85811256f65fa0f7bf52166b147fd16be2be4662 --port 38697
Why Fixer classified it this way: The trace repeatedly returns to a poll-family syscall without meaningful blocking, which suggests a busy event-loop wakeup.
Thread summary: thread backtraces show 2 thread(s) around 0x00007f8f694a5ffe in ?? () from target:<path> and 1 thread(s) around 0x000055ede48a2143 in ?? ()
Contention signals: event-loop-wakeups, gdb-stderr: gdb: warning: Couldn't determine a path for the index cache directory.
Repeated loop: poll -> poll -> poll
Top syscalls: poll x50, futex x30, restart_syscall x3, epoll_pwait x1
Kernel: 6.17.10+deb14-amd64
Distribution: debian

0x00007f8f694a5ffe in ?? () from target:<path>
0x00007f8f6949a7a4 in ?? () from target:<path>
0x00007f8f6949a7ed in ?? () from target:<path>
0x00007f8f6950fd76 in poll () from target:<path>
0x00007f8efe27644f in ?? () from target:<path>
0x00007f8efe33a80f in ?? () from target:<path>
0x00007f8efe26e143 in ?? () from target:<path>
0x00007f8f6949dda9 in ?? () from target:<path>

Possible duplicates

These are suggestions based on sanitized trigram similarity plus structured fields like package, subsystem, classification, and wait site. They are not auto-merged.

Runaway CPU investigation for ollama: busy poll at _raw_spin_lock_irqsave

possible duplicate

ollama is stuck in a likely busy poll loop: 50.00% of sampled CPU passed through _raw_spin_lock_irqsave, with repeated thread backtraces show 2 thread(s) around 0x00007fae9baa5ffe in ?? () from target:<path> and 1 thread(s) around 0x000055b5f2274143 in ?? ().

highscore: 106reports: 1successful triagesimilarity: 99%