Public issue detail

Runaway CPU investigation for python3.13: unknown userspace loop at _PyEval_EvalFrameDefault

python3.13 is stuck in a likely unclassified userspace loop: 22.73% of sampled CPU passed through _PyEval_EvalFrameDefault, with repeated no dominant syscall sample was captured.

highpackage: python3.13-minimalsource: python3.13score: 106reports: 2

Last seen: 2026-05-02 00:35 UTC. Public JSON: /v1/issues/019d3a01-5de6-7581-9470-f0e29db1b7e8

Technical snapshot

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

Representative thread backtrace

  • 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.
  • Hot path: _PyEval_EvalFrameDefault (22.73% sampled CPU)
  • Package: python3.13-minimal 3.13.12-1
  • Kernel: 6.17.10+deb14-amd64
  • Distribution: debian

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.

python3.13 is stuck in a likely busy poll loop: 50.00% of sampled CPU passed through _PyEval_EvalFrameDefault, with repeated thread backtraces show 1 thread(s) around 0x00007f091ce537d2 in ?? () from target:<path>.

highpackage: python3.13-minimalsource: python3.13score: 106reports: 2patch attempt readysimilarity: 84%

Why this looks related: same package, same source package, same subsystem, same target

Last seen: 2026-07-02 23:40 UTC. Public page: /issues/019dda71-4897-7d62-853d-31f4899d9f8e. Public JSON: /v1/issues/019dda71-4897-7d62-853d-31f4899d9f8e

python3.13 is stuck in a likely busy poll loop: 7.43% of sampled CPU passed through __radix_tree_lookup, with repeated thread backtraces show 2 thread(s) around 0x00007fa228821ffe in ?? () from target:<path> and 1 thread(s) around 0x00007fa228821ffe in ?? () from target:<path>.

highpackage: python3.13-minimalsource: python3.13score: 106reports: 1similarity: 66%

Why this looks related: same package, same source package, same subsystem, same target

Last seen: 2026-07-05 13:59 UTC. Public page: /issues/019f2bc3-de08-7860-a55b-b87e802981f1. Public JSON: /v1/issues/019f2bc3-de08-7860-a55b-b87e802981f1

python3.13 is stuck in a likely busy poll loop: 100.00% of sampled CPU passed through unresolved offset, with repeated thread backtraces show 1 thread(s) around 0x00007f091ce537d2 in ?? () from target:<path>.

highpackage: python3.13-minimalsource: python3.13score: 106reports: 2similarity: 64%

Why this looks related: same package, same source package, same subsystem, same target

Last seen: 2026-07-02 03:18 UTC. Public page: /issues/019dc2a0-9ae7-7f42-8f59-415fe22abe51. Public JSON: /v1/issues/019dc2a0-9ae7-7f42-8f59-415fe22abe51

python3.13 is stuck in a likely busy poll loop: 6.41% of sampled CPU passed through unresolved offset, with repeated thread backtraces show 1 thread(s) around 0x00007fdd05c9b72e in ?? () and 1 thread(s) around 0x00007fdd05c9b72e in ?? ().

highpackage: python3.13-minimalsource: python3.13score: 106reports: 3patch attempt readysimilarity: 63%

Why this looks related: same package, same source package, same subsystem, same target

Last seen: 2026-07-09 19:56 UTC. Public page: /issues/019d7cef-46dd-7541-b939-9ba6872fbf76. Public JSON: /v1/issues/019d7cef-46dd-7541-b939-9ba6872fbf76

python3.13 is stuck in a likely busy poll loop: 15.28% of sampled CPU passed through unresolved offset, with repeated thread backtraces show 2 thread(s) around 0x00007f35495474be in ?? () from target:<path> and 1 thread(s) around 0x000000000057151f in _PyEval_EvalFrameDefault ().

highpackage: python3.13-minimalsource: python3.13score: 106reports: 2successful triagesimilarity: 63%

Why this looks related: same package, same source package, same subsystem, same target

Last seen: 2026-07-07 10:15 UTC. Public page: /issues/019dd98b-0e1d-76e3-9171-f0f72c689536. Public JSON: /v1/issues/019dd98b-0e1d-76e3-9171-f0f72c689536

python3.13 is stuck in a likely dbus spin loop: 3.95% of sampled CPU passed through unresolved offset, with repeated thread backtraces show 2 thread(s) around 0x00007f2de17b84be in ?? () from target:<path> and 1 thread(s) around 0x00007f2de17b84be in ?? () from target:<path>.

highpackage: python3.13-minimalsource: python3.13score: 106reports: 1similarity: 62%

Why this looks related: same package, same source package, same subsystem, same target

Last seen: 2026-07-06 13:45 UTC. Public page: /issues/019f357c-d6d6-7f61-9f19-fde577e0ce21. Public JSON: /v1/issues/019f357c-d6d6-7f61-9f19-fde577e0ce21

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 failed patch attempts

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

Most common blockers

  • patch proposal did not complete cleanly (1 attempt)

Published attempts

failed patch attempt

patch

python3.13 likely remains stuck in an unclassified userspace loop. The diagnosis was captured, but the patch proposal did not complete cleanly.

state: failedcreated: 2026-03-29 14:39 UTCvalidation: failed

Why it stopped

patch proposal did not complete cleanly

Collected context

  • This older failed attempt predates structured patch failure capture, so Fixer only retained the diagnosis and workspace context.
  • Subsystem: runaway-process
  • Diagnosis family: unknown-userspace-loop
  • Hot path: __strcmp_avx2
  • Source package: glibc
  • Workspace source: debian-source
  • Workspace acquisition: Fetched Debian source package via apt-get source.
  • Homepage: https://www.gnu.org/software/libc/libc.html

The process is demonstrably CPU-hot, but the current syscall and symbol sample does not point to a single dominant loop family yet.