SECURITY WARNING: Never run commands you don't understand. Always review code before execution. Use at your own risk.
FixMyError.net
Performance New Added 19 September 2026

Connections hang or reset with ListenOverflows increasing

The kernel finished the handshake but the application was too slow to call accept(), so the completed connection queue filled and further connections were dropped silently. Clients see a stall and then a timeout or a reset, and nothing appears in the application log because the connection never reached it.

Quick fix

Read the commands before running them. Anything that restarts a service, deletes data or changes permissions should be tried on a non-production system first.

Quick fix
# Drops are counted, not logged: check the counters before anything else
nstat -az | grep -E 'ListenOverflows|ListenDrops'

# Recv-Q on a listening socket is the current backlog, Send-Q is its limit
ss -lnt

# The effective backlog is the smaller of the two, so raising one alone does nothing
sysctl net.core.somaxconn
sudo sysctl -w net.core.somaxconn=4096
# then the listen() argument in the app: uvicorn --backlog, nginx listen backlog=, JVM ServerSocket

# A steadily rising counter is an application that cannot keep up,
# a burst at deploy time is usually a cold start blocking the accept loop
watch -n1 "nstat -az | grep ListenOverflows"

# SYN queue overflow is a different counter and a different fix
nstat -az | grep -i syncookies

How to diagnose Performance errors

Performance failures rarely produce an error message. They produce timeouts elsewhere. The three classic causes are stop-the-world garbage collection, thread pool starvation (all workers blocked on I/O so new requests queue), and event loop blocking in single-threaded runtimes. All three look identical from outside: latency climbs, then upstream timeouts fire. Distinguishing them requires looking inside the process.

If the quick fix above does not resolve it, work through these steps. They apply to this whole class of error, not just to this one message, which is usually what saves the time.

  1. Measure the p99, not the mean. Averages hide exactly the pauses that cause timeouts.
  2. For the JVM, enable GC logging (-Xlog:gc*) and correlate pause durations with latency spikes before tuning anything.
  3. For thread pools, log active versus queued task counts. A queue that grows while CPU is idle is starvation, and the fix is asynchronous I/O, not more threads.
  4. In Node.js, measure event loop lag directly (perf_hooks.monitorEventLoopDelay). Any synchronous work over a few milliseconds per request will show up here.
  5. Profile before optimising. pprof, async-profiler, py-spy and Chrome's profiler all point at the real hot path, which is rarely where intuition suggests.

Tools worth reaching for

  • async-profiler
  • go tool pprof
  • py-spy
  • perf_hooks.monitorEventLoopDelay
  • -Xlog:gc*

Authoritative references

Primary documentation for this error, worth reading before applying any fix in production.

man7.org docs.kernel.org

Related Performance errors

See all 9 Performance errors →

Browse other categories

Something missing or wrong?

This entry is maintained by hand. If the fix is out of date, incomplete, or you have a better one, email a correction and it will be reviewed.