Public issue detail

Runaway CPU investigation for postgres: socket churn at unresolved offset in postgres

postgres is stuck in a likely socket churn loop: 1.90% of sampled CPU passed through unresolved offset, with repeated thread backtraces show 1 thread(s) around 0x00007f1303299687 in __GI__IO_flush_all () from target:<path>.

highscore: 106reports: 1

Last seen: 2026-10-19 03:26 UTC. Public JSON: /v1/issues/019f7962-c828-7c50-8189-f439a8864601

Technical snapshot

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

Representative thread backtrace

  • Command: /usr/lib/postgresql/16/bin/postgres -D /tmp/postgis-pg16.kwrMxX/data -F -h -p 32825 -k /tmp/postgis-pg16.kwrMxX/socket -c fsync=off -c full_page_writes=off -c synchronous_commit=off
  • Why Fixer classified it this way: The trace is dominated by socket syscalls, which suggests the process is rapidly retrying or churning through network or IPC work.
  • Thread summary: thread backtraces show 1 thread(s) around 0x00007f1303299687 in __GI__IO_flush_all () from target:<path>
  • Contention signals: event-loop-wakeups, gdb-stderr: gdb: warning: Couldn't determine a path for the index cache directory. warning: Target and debugger are in different PID namespaces; thread lists and other data are likely unreliable. Connect to gdbserver inside the container. warning: Expected absolute pathname for libpthread in the inferior, but got target:<path> warning: Unable to find libthread_db matching inferior's thread library, thread debugging will not be available.
  • Repeated loop: write -> write -> write
  • Top syscalls: write x11200, read x6727, mmap x5642, recvfrom x3422
  • Kernel: 7.1.8+deb14.1-amd64
  • Distribution: debian
0x00007f1303299687 in __GI__IO_flush_all () from target:<path>
0x00007f13032996ad in __GI__IO_flush_all () from target:<path>
0x00007f130331aa6d in epoll_wait () from target:<path>
0x0000564149873f5b in WaitEventSetWait ()
0x000056414980c745 in ?? ()
0x000056414980f47c in PostmasterMain ()
0x00005641495344ec in main ()

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 postgres: socket churn at unresolved offset in libc-2.31.so

possible duplicate

postgres is stuck in a likely socket churn loop: 5.58% of sampled CPU passed through unresolved offset, with repeated thread backtraces show 1 thread(s) around 0x00007f66a2df719a in select () from target:<path>.

highscore: 106reports: 1similarity: 99%

Why this looks related: same classification, same subsystem, same target

Last seen: 2026-10-02 18:22 UTC. Public page: /issues/019f8e36-ec1d-76d3-b8ef-a76be89f2c5a. Public JSON: /v1/issues/019f8e36-ec1d-76d3-b8ef-a76be89f2c5a

Runaway CPU investigation for postgres: socket churn at next_uptodate_folio

possible duplicate

postgres is stuck in a likely socket churn loop: 1.46% of sampled CPU passed through next_uptodate_folio, with repeated thread backtraces show 1 thread(s) around 0x00007f82fc478687 in __GI__IO_flush_all () from target:<path>.

highpackage: postgresql-18source: linuxscore: 106reports: 1similarity: 97%

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

Last seen: 2026-10-16 07:15 UTC. Public page: /issues/019f777c-b6c6-73c1-9b2a-9e06e91c6ca9. Public JSON: /v1/issues/019f777c-b6c6-73c1-9b2a-9e06e91c6ca9

Runaway CPU investigation for postgres: socket churn at _dl_map_new_object

possible duplicate

postgres is stuck in a likely socket churn loop: 3.49% of sampled CPU passed through _dl_map_new_object, with repeated thread backtraces show 1 thread(s) around 0x00007f912645c687 in __GI__IO_flush_all () from target:<path>.

highpackage: postgresql-18source: postgresql-18score: 106reports: 1similarity: 97%

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

Last seen: 2026-10-17 07:40 UTC. Public page: /issues/019f9db1-7511-7382-938c-68a2e3e906c8. Public JSON: /v1/issues/019f9db1-7511-7382-938c-68a2e3e906c8

Runaway CPU investigation for postgres: socket churn at hash_search_with_hash_value

possible duplicate

postgres is stuck in a likely socket churn loop: 3.62% of sampled CPU passed through hash_search_with_hash_value, with repeated thread backtraces show 1 thread(s) around 0x00007f1f311da687 in __GI__IO_flush_all () from target:<path>.

highpackage: postgresql-14source: postgresql-14score: 106reports: 1similarity: 95%

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

Last seen: 2026-10-21 04:00 UTC. Public page: /issues/019d8b2f-863a-7af0-92eb-7ce77dd04988. Public JSON: /v1/issues/019d8b2f-863a-7af0-92eb-7ce77dd04988

Runaway CPU investigation for postgres: file not found retry at unresolved offset in postgres

possible duplicate

postgres is stuck in a likely file not found retry loop: 3.98% of sampled CPU passed through unresolved offset, with repeated thread backtraces show 1 thread(s) around 0x00007f7805be2687 in __GI__IO_flush_all () from target:<path>.

highscore: 106reports: 1similarity: 80%

Why this looks related: same subsystem, same target

Last seen: 2026-10-13 06:22 UTC. Public page: /issues/019f77a0-05cc-7ca2-84d1-d756b2e2db54. Public JSON: /v1/issues/019f77a0-05cc-7ca2-84d1-d756b2e2db54

Runaway CPU investigation for postgres: timer churn at start_dl_timer

possible duplicate

postgres is stuck in a likely timer churn loop: 100.00% of sampled CPU passed through start_dl_timer, with repeated thread backtraces show 1 thread(s) around 0x00007f322d29a7d2 in ?? () from target:<path>.

highpackage: postgresql-18source: postgresql-18score: 106reports: 2similarity: 76%

Why this looks related: same subsystem, same target, same wait site

Last seen: 2026-10-22 20:40 UTC. Public page: /issues/019e5d7e-79c8-70a3-bcbd-6d4643b9285a. Public JSON: /v1/issues/019e5d7e-79c8-70a3-bcbd-6d4643b9285a

Published attempts

No public attempts have been published for this issue yet.

Quarantine stays on by default so the public queue is harder to spam.