funman300
ed0ccb8c2b
Host-side ss cannot see the Python backend's connections: the responders run in a container, so a client session terminates at 172.20.0.2:42130 inside its namespace and the host only sees the NAT'd flow. 'ss | grep <client>' on the host therefore reports nothing while a session is very much alive. That produced a wrong precondition: 'no .105 Blaze session -- closed' was reported while FIFA was mid-session on Python, and gate 9 was armed against a client that had never exited. Python's own log had the answer -- it logs closes reliably and there was no close for that session. client-state.sh looks in both namespaces, reports Rust and Python separately, and exits non-zero while any session is live. An unreachable container counts as 'cannot confirm', not as 'clear'. Fourth measurement bug in this tooling, and the most consequential: the other three mis-COUNTED, this one mis-STATED a precondition and caused an action. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
82 lines
2.5 KiB
Bash
Executable File
82 lines
2.5 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Is the FIFA client currently connected to anything?
|
|
#
|
|
# client-state.sh [client-ip]
|
|
#
|
|
# WHY THIS EXISTS
|
|
#
|
|
# Host-side `ss` CANNOT see the Python backend's connections. The Python
|
|
# responders run inside a container, so a client session terminates at
|
|
# 172.20.0.2:42130 in the container's network namespace; the host only ever sees
|
|
# the NAT'd flow, and a plain `ss | grep <client>` on the host reports nothing.
|
|
#
|
|
# That produced a wrong precondition check: "no .105 Blaze session — closed" was
|
|
# reported while FIFA was mid-session on Python, and gate 9 was armed against a
|
|
# client that had never exited. Python's own log gave it away — it logs closes
|
|
# reliably (45 of them) and there was no close for that session.
|
|
#
|
|
# So this looks in BOTH namespaces, and reports the Rust sidecar and the Python
|
|
# container separately.
|
|
#
|
|
# Exit 0 when the client has no live session anywhere (safe to start a gate),
|
|
# 1 when it does.
|
|
set -uo pipefail
|
|
|
|
CLIENT="${1:-${OPENFUT_CLIENT_IP:-10.10.0.105}}"
|
|
CONTAINER="${OPENFUT_PY_CONTAINER:-openfut-fut-backend}"
|
|
live=0
|
|
|
|
decode_tcp() {
|
|
# /proc/net/tcp rows -> "local remote state", little-endian hex addresses.
|
|
python3 -c "
|
|
import sys
|
|
def d(x):
|
|
ip, port = x.split(':')
|
|
return '.'.join(str(int(ip[i:i+2], 16)) for i in (6, 4, 2, 0)) + ':' + str(int(port, 16))
|
|
for line in sys.stdin:
|
|
f = line.split()
|
|
if len(f) < 4 or not f[0].endswith(':'):
|
|
continue
|
|
try:
|
|
print(d(f[1]), d(f[2]), f[3])
|
|
except Exception:
|
|
pass
|
|
"
|
|
}
|
|
|
|
echo "client: $CLIENT"
|
|
|
|
# ---- Rust sidecar (host namespace)
|
|
rust="$(ss -tn state established 2>/dev/null | grep -F "$CLIENT" | grep -E ':42230' || true)"
|
|
if [[ -n "$rust" ]]; then
|
|
echo " RUST sidecar : LIVE session(s)"
|
|
sed 's/^/ /' <<<"$rust"
|
|
live=1
|
|
else
|
|
echo " RUST sidecar : none"
|
|
fi
|
|
|
|
# ---- Python backend (container namespace)
|
|
if docker exec "$CONTAINER" true 2>/dev/null; then
|
|
py="$(docker exec "$CONTAINER" cat /proc/net/tcp 2>/dev/null | decode_tcp \
|
|
| awk '$3=="01"' | grep -F "$CLIENT" || true)"
|
|
if [[ -n "$py" ]]; then
|
|
echo " PYTHON backend: LIVE session(s)"
|
|
awk '{printf " %-22s <- %-22s ESTABLISHED\n", $1, $2}' <<<"$py"
|
|
live=1
|
|
else
|
|
echo " PYTHON backend: none"
|
|
fi
|
|
else
|
|
echo " PYTHON backend: container '$CONTAINER' not reachable — CANNOT confirm"
|
|
live=1 # unknown is not the same as clear
|
|
fi
|
|
|
|
echo
|
|
if [[ $live -eq 0 ]]; then
|
|
echo "RESULT: no live client session — safe to begin a gate"
|
|
else
|
|
echo "RESULT: client still connected — close FIFA before starting a gate"
|
|
fi
|
|
exit $live
|