mbproxy: add keepalive / connection monitoring

The DL205/DL260 ECOM emits no TCP keepalives, so an idle backend socket
can be silently dropped by a middlebox (switch, firewall, NAT) after
2-5 minutes. Enable OS SO_KEEPALIVE on backend and accepted upstream
sockets, and drive a periodic synthetic FC03 heartbeat on each idle
backend socket so a dead path is detected before a real client request
hits it. Controlled by Connection.Keepalive (ON by default).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Joseph Doherty
2026-05-15 09:40:54 -04:00
parent 7466a46aa7
commit 0868613890
25 changed files with 1135 additions and 25 deletions
@@ -141,6 +141,27 @@ internal static class ReloadValidator
errs.Add(
$"Connection.GracefulShutdownTimeoutMs must be > 0; got {next.Connection.GracefulShutdownTimeoutMs}.");
// ── 6. Keepalive section ──────────────────────────────────────────────
// Schema bounds are also checked in MbproxyOptionsValidator; re-checking here keeps
// the hot-reload gate self-contained. The cross-field rule (heartbeat interval must
// sit above the request timeout, or it would fire continuously) lives only here.
var ka = next.Connection.Keepalive;
if (ka.TcpIdleTimeMs <= 0)
errs.Add($"Connection.Keepalive.TcpIdleTimeMs must be > 0; got {ka.TcpIdleTimeMs}.");
if (ka.TcpProbeIntervalMs <= 0)
errs.Add($"Connection.Keepalive.TcpProbeIntervalMs must be > 0; got {ka.TcpProbeIntervalMs}.");
if (ka.TcpProbeCount <= 0)
errs.Add($"Connection.Keepalive.TcpProbeCount must be > 0; got {ka.TcpProbeCount}.");
if (ka.BackendHeartbeatProbeAddress is < 0 or > 65535)
errs.Add(
$"Connection.Keepalive.BackendHeartbeatProbeAddress must be in [0, 65535]; " +
$"got {ka.BackendHeartbeatProbeAddress}.");
if (ka.BackendHeartbeatIdleMs <= next.Connection.BackendRequestTimeoutMs)
errs.Add(
$"Connection.Keepalive.BackendHeartbeatIdleMs ({ka.BackendHeartbeatIdleMs}) must be greater " +
$"than Connection.BackendRequestTimeoutMs ({next.Connection.BackendRequestTimeoutMs}); " +
"a heartbeat interval at or below the request timeout would fire continuously.");
errors = errs;
return errs.Count == 0;
}