Public issue detail

Runaway CPU investigation for ollama: unknown userspace loop at entry_SYSCALL_64_after_hwframe

ollama is stuck in a likely unclassified userspace loop: 100.00% of sampled CPU passed through entry_SYSCALL_64_after_hwframe, with repeated thread backtraces show 1 thread(s) around 0x000055c5c39ed143 in ?? () and 1 thread(s) around 0x000055c5c39ed143 in ?? ().

highsource: linuxscore: 106reports: 1successful triage

Last seen: 2026-05-19 03:53 UTC. Public JSON: /v1/issues/019e3db4-6e7f-7623-8a87-e638d5bbe8c6

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: 2026-05-19 01:22 UTCvalidation: ready

ollama likely remains stuck in an unclassified userspace loop. A diagnosis report was created even though no patchable workspace was available: opportunity 90571 has no repo root, package name, or source package

Likely owner

the upstream maintainer

Reason: workspace-acquisition

Next steps

Review the package metadata and attach a source tree or upstream clone if one exists.
If no patchable tree is available, file an external bug using the diagnosis bundle.

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 serve
Why Fixer classified it this way: The process is demonstrably CPU-hot, but the current syscall and symbol sample does not point to a single dominant loop family yet.
Thread summary: thread backtraces show 1 thread(s) around 0x000055c5c39ed143 in ?? () and 1 thread(s) around 0x000055c5c39ed143 in ?? ()
Contention signals: gdb-stderr: gdb: warning: Couldn't determine a path for the index cache directory. warning: .dynamic section for "target:<path>++.so.6" is not at the expected address (wrong library or version mismatch?)
Repeated loop: futex -> futex -> futex
Top syscalls: futex x52, epoll_pwait x1, restart_syscall x1
Kernel: 6.17.10+deb14-amd64
Distribution: debian

0x000055c5c39ed143 in ?? ()
0x000055c5c39a9110 in ?? ()
0x000000c000581148 in ?? ()
0x0000000000000080 in ?? ()
0x0000000000000000 in ?? ()

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: unknown userspace loop at __list_del_entry_valid_or_report

possible duplicate

ollama is stuck in a likely unclassified userspace loop: 50.00% of sampled CPU passed through __list_del_entry_valid_or_report, with repeated thread backtraces show 1 thread(s) around 0x000055c5c39ed143 in ?? () and 1 thread(s) around 0x000055c5c397a50e in ?? ().

highsource: linuxscore: 106reports: 1successful triagesimilarity: 99%

Why this looks related: same classification, same source package, same subsystem, same target, same wait site

Last seen: 2026-05-19 00:29 UTC. Public page: /issues/019d3d61-d23a-7be3-8cd5-36c8732e0ae8. Public JSON: /v1/issues/019d3d61-d23a-7be3-8cd5-36c8732e0ae8

Runaway CPU investigation for ollama: unknown userspace loop at dequeue_entity

possible duplicate

ollama is stuck in a likely unclassified userspace loop: 33.33% of sampled CPU passed through dequeue_entity, with repeated thread backtraces show 1 thread(s) around 0x000055c5c39ed143 in ?? () and 1 thread(s) around 0x000055c5c39ed143 in ?? ().

highsource: linuxscore: 106reports: 1successful triagesimilarity: 99%

Why this looks related: same classification, same source package, same subsystem, same target, same wait site

Last seen: 2026-05-18 23:15 UTC. Public page: /issues/019d54c1-aea7-73d3-9307-abdff02e2f69. Public JSON: /v1/issues/019d54c1-aea7-73d3-9307-abdff02e2f69

Runaway CPU investigation for ollama: unknown userspace loop at _raw_spin_lock_irqsave

possible duplicate

ollama is stuck in a likely unclassified userspace loop: 20.00% of sampled CPU passed through _raw_spin_lock_irqsave, with repeated thread backtraces show 1 thread(s) around 0x000055c5c39ed143 in ?? () and 1 thread(s) around 0x000055c5c39ed143 in ?? ().

highsource: linuxscore: 106reports: 1successful triagesimilarity: 99%

Why this looks related: same classification, same source package, same subsystem, same target, same wait site

Last seen: 2026-05-18 18:36 UTC. Public page: /issues/019d780b-a338-7841-9ba2-3bf6ad9294de. Public JSON: /v1/issues/019d780b-a338-7841-9ba2-3bf6ad9294de

Runaway CPU investigation for ollama: unknown userspace loop at completion_done

possible duplicate

ollama is stuck in a likely unclassified userspace loop: 27.44% of sampled CPU passed through completion_done, with repeated thread backtraces show 1 thread(s) around 0x000055c5c39ed143 in ?? () and 1 thread(s) around 0x000055c5c39ed143 in ?? ().

highsource: linuxscore: 106reports: 1successful triagesimilarity: 99%

Why this looks related: same classification, same source package, same subsystem, same target, same wait site

Last seen: 2026-05-18 16:08 UTC. Public page: /issues/019deff5-c840-7093-8f38-874efcc42398. Public JSON: /v1/issues/019deff5-c840-7093-8f38-874efcc42398

Runaway CPU investigation for ollama: unknown userspace loop at __schedule

possible duplicate

ollama is stuck in a likely unclassified userspace loop: 25.00% of sampled CPU passed through __schedule, with repeated thread backtraces show 1 thread(s) around 0x000055c5c39ed143 in ?? () and 1 thread(s) around 0x000055c5c39ed143 in ?? ().

highsource: linuxscore: 106reports: 1successful triagesimilarity: 99%

Why this looks related: same classification, same source package, same subsystem, same target, same wait site, very similar public summary

Last seen: 2026-05-18 15:12 UTC. Public page: /issues/019dd039-c241-7ee0-8262-e0cd451ba20e. Public JSON: /v1/issues/019dd039-c241-7ee0-8262-e0cd451ba20e

Runaway CPU investigation for ollama: unknown userspace loop at fdget

possible duplicate

ollama is stuck in a likely unclassified userspace loop: 25.00% of sampled CPU passed through fdget, with repeated thread backtraces show 1 thread(s) around 0x000055c5c39ed143 in ?? () and 1 thread(s) around 0x000055c5c39ed143 in ?? ().

highsource: linuxscore: 106reports: 1successful triagesimilarity: 99%

Why this looks related: same classification, same source package, same subsystem, same target, same wait site, very similar public summary

Last seen: 2026-05-18 12:44 UTC. Public page: /issues/019dbcec-f056-7ae0-bc8f-d6d03bb07fcc. Public JSON: /v1/issues/019dbcec-f056-7ae0-bc8f-d6d03bb07fcc

Worker outcome summary

This issue has 1 recorded worker attempt. Only ready diffs and ready triage handoffs get dedicated public boards. Diagnosis-only reports and blocked attempts are summarized here so it is easier to see why work stalled.

1 ready triage handoffs

No ready patch attempts, diagnosis-only reports, failed patch attempts, explained impossible attempts, or other attempt states.

Most common blockers

workspace-acquisition (1 attempt)

Published attempts

ready triage handoff

triage

ollama likely remains stuck in an unclassified userspace loop. A diagnosis report was created even though no patchable workspace was available: opportunity 90571 has no repo root, package name, or source package

state: readycreated: 2026-05-19 01:22 UTCvalidation: ready

Why it stopped

workspace-acquisition

Handoff

Likely owner: the upstream maintainer

Reason: workspace-acquisition

Review the package metadata and attach a source tree or upstream clone if one exists.
If no patchable tree is available, file an external bug using the diagnosis bundle.