Public issue detail

Runaway CPU investigation for sshd-auth: unknown userspace loop at unresolved offset in sshd-auth

sshd-auth is stuck in a likely unclassified userspace loop: 100.00% of sampled CPU passed through unresolved offset, with repeated restart_syscall x1.

highpackage: openssh-serversource: opensshscore: 106reports: 1successful triage

Last seen: 2026-05-07 17:51 UTC. Public JSON: /v1/issues/019e0204-2523-7f73-8ec7-86c718857ae2

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: 2026-05-10 21:03 UTCvalidation: ready

sshd-auth likely remains stuck in an unclassified userspace loop. Fixer produced a diagnosis report and intentionally skipped an automatic package patch attempt because the evidence is not specific enough to choose a safe source change.

Likely owner

external dependency or workload outside the current source tree

Reason: weak-unknown-runaway-evidence

Next steps

  • Confirm the hotspot still points at external dependency or workload outside the current source tree with a fresh perf sample before filing the bug.
  • Capture the actual hot backend or child process rather than the parent service wrapper if the issue recurs.
  • Map external dependency or workload outside the current source tree to its owning package or project and file an upstream or distro bug with the summarized evidence.
  • If the owner is still unclear, collect another short strace plus `/proc/<pid>/maps` at the moment of the spike.

Technical snapshot

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

Representative thread backtrace

  • Command: sshd-auth: root [net]
  • 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.
  • Wait site: hrtimer_nanosleep
  • Hot path: unresolved offset (100.00% sampled CPU)
  • Repeated loop: restart_syscall
  • Top syscalls: restart_syscall x1
  • Package: openssh-server 1:10.3p1-1
  • Kernel: 6.17.10+deb14-amd64
  • Distribution: debian
hrtimer_nanosleep
common_nsleep
__x64_sys_clock_nanosleep
do_syscall_64
entry_SYSCALL_64_after_hwframe

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.

sshd-auth is stuck in a likely busy poll loop: 100.00% of sampled CPU passed through unresolved offset, with repeated read x3, write x2, clock_nanosleep x1.

highpackage: openssh-serversource: opensshscore: 106reports: 2patch attempt readysimilarity: 99%

Why this looks related: same package, same source package, same stack or hot path signature, same subsystem, same target

Last seen: 2026-05-19 02:02 UTC. Public page: /issues/019e1519-78c6-7813-bebb-aeb6177e1897. Public JSON: /v1/issues/019e1519-78c6-7813-bebb-aeb6177e1897

sshd-session is stuck in a likely unclassified userspace loop: 100.00% of sampled CPU passed through unresolved offset, with repeated thread backtraces show 1 thread(s) around 0x00007f13c609a7d2 in ?? () from target:<path>.

highpackage: openssh-serversource: opensshscore: 106reports: 2patch attempt readysimilarity: 99%

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

Last seen: 2026-05-14 22:18 UTC. Public page: /issues/019d4084-f5b8-7803-9286-8acd4581d8b7. Public JSON: /v1/issues/019d4084-f5b8-7803-9286-8acd4581d8b7

sshd-auth is stuck in a likely unclassified userspace loop: 100.00% of sampled CPU passed through dequeue_task, with repeated restart_syscall x1.

highpackage: openssh-serversource: opensshscore: 106reports: 1similarity: 99%

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

Last seen: 2026-05-19 03:16 UTC. Public page: /issues/019e3e09-5d4a-7d31-befb-93b419bb1a2e. Public JSON: /v1/issues/019e3e09-5d4a-7d31-befb-93b419bb1a2e

sshd-auth is stuck in a likely unclassified userspace loop: 100.00% of sampled CPU passed through update_cfs_group, with repeated restart_syscall x1.

highpackage: openssh-serversource: opensshscore: 106reports: 1successful triagesimilarity: 99%

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

Last seen: 2026-05-19 00:29 UTC. Public page: /issues/019e39a7-acec-7e33-a7c7-a6cc343e4456. Public JSON: /v1/issues/019e39a7-acec-7e33-a7c7-a6cc343e4456

sshd-auth is stuck in a likely unclassified userspace loop: 50.00% of sampled CPU passed through cfree, with repeated restart_syscall x1.

highpackage: openssh-serversource: opensshscore: 106reports: 1successful triagesimilarity: 99%

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

Last seen: 2026-05-18 05:37 UTC. Public page: /issues/019e381f-de92-7bc1-aa2f-447d68e2f337. Public JSON: /v1/issues/019e381f-de92-7bc1-aa2f-447d68e2f337

sshd-auth is stuck in a likely unclassified userspace loop: 100.00% of sampled CPU passed through nf_conntrack_tcp_packet, with repeated restart_syscall x1.

highpackage: openssh-serversource: opensshscore: 106reports: 1successful triagesimilarity: 99%

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

Last seen: 2026-05-16 04:55 UTC. Public page: /issues/019e2c8c-71b2-7410-b0fd-4588b13c156a. Public JSON: /v1/issues/019e2c8c-71b2-7410-b0fd-4588b13c156a

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

  • weak-unknown-runaway-evidence (1 attempt)

Published attempts

ready triage handoff

triage

sshd-auth likely remains stuck in an unclassified userspace loop. Fixer produced a diagnosis report and intentionally skipped an automatic package patch attempt because the evidence is not specific enough to choose a safe source change.

state: readycreated: 2026-05-10 21:03 UTCvalidation: ready

Why it stopped

weak-unknown-runaway-evidence

Handoff

Likely owner: external dependency or workload outside the current source tree

Reason: weak-unknown-runaway-evidence

  • Confirm the hotspot still points at external dependency or workload outside the current source tree with a fresh perf sample before filing the bug.
  • Capture the actual hot backend or child process rather than the parent service wrapper if the issue recurs.
  • Map external dependency or workload outside the current source tree to its owning package or project and file an upstream or distro bug with the summarized evidence.
  • If the owner is still unclear, collect another short strace plus `/proc/<pid>/maps` at the moment of the spike.