Public issue detail

Runaway CPU investigation for ollama: unknown userspace loop at unresolved offset in ollama

ollama is stuck in a likely unclassified userspace loop: 14.08% of sampled CPU passed through unresolved offset, with repeated thread backtraces show 1 thread(s) around 0x000055c5c39ed143 in ?? () and 1 thread(s) around 0x000055c5c39ed143 in ?? ().

highscore: 106reports: 2

Last seen: 2026-05-16 01:30 UTC. Public JSON: /v1/issues/019dd7a7-430c-79a0-bc5b-7549a044b3fc

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 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 subsystem, same target, same wait site, very similar public summary

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 subsystem, same target, same wait site, very similar public summary

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 subsystem, same target, same wait site, very similar public summary

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 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 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

Runaway CPU investigation for ollama: unknown userspace loop at alloc_pages_noprof

possible duplicate

ollama is stuck in a likely unclassified userspace loop: 25.00% of sampled CPU passed through alloc_pages_noprof, 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 subsystem, same target, same wait site, very similar public summary

Last seen: 2026-05-18 09:01 UTC. Public page: /issues/019e3a1e-754b-7412-98c3-2dd07204d546. Public JSON: /v1/issues/019e3a1e-754b-7412-98c3-2dd07204d546

Published attempts

No public attempts have been published for this issue yet.