mirror of
https://github.com/jmcorgan/fips.git
synced 2026-07-30 19:46:15 +00:00
Implement hop-by-hop ECN congestion signaling through the FMP layer, transport-level congestion detection via kernel drop counters, and chaos harness integration for end-to-end validation. FMP/session ECN plumbing: - Thread ce_flag parsed at link layer through dispatch_link_message, handle_session_datagram, handle_session_payload, and handle_encrypted_session_msg to session delivery - Replace hardcoded false in session-layer record_recv() with actual ce_flag, activating ecn_ce_count tracking in session MMP ECN congestion detection and CE relay: - Add EcnConfig (node.ecn.*) with configurable loss_threshold (5%) and etx_threshold (3.0) for transit congestion detection - Add send_encrypted_link_message_with_ce() that ORs FLAG_CE into FMP header flags; original method delegates with ce_flag=false - Compute outgoing_ce = incoming_ce || local congestion on next-hop link, enabling hop-by-hop CE relay through transit nodes IPv6 ECN-CE marking: - Mark ECN-CE (0b11) in IPv6 Traffic Class on received DataPackets before TUN delivery when FMP CE flag is set - Only marks ECN-capable packets (ECT(0)/ECT(1)); Not-ECT packets unchanged per RFC 3168 Transport congestion abstraction and UDP kernel drop detection: - Add TransportCongestion struct to transport layer for transport- agnostic local congestion indicators - Replace tokio::UdpSocket with AsyncFd<socket2::Socket> using libc::recvmsg() with ancillary data parsing - Enable SO_RXQ_OVFL for kernel receive buffer drop counter on every packet, wiring up previously-stubbed UdpStats.kernel_drops - Add TransportDropState for per-transport delta tracking with 1s tick sampling via sample_transport_congestion() - Extend detect_congestion() with transport kernel drop check alongside MMP loss metrics Congestion monitoring and control: - Add CongestionStats (ce_forwarded, ce_received, congestion_detected, kernel_drop_events) to NodeStats with snapshot serialization - Wire counters into forwarding path, session handler, and transport drop sampling with rate-limited warn logging (5s interval) - Expose congestion data in show_routing control query and ecn_ce_count in show_mmp peer entries - Add congestion counters to fipstop routing tab in two-column layout Chaos harness integration: - Add query_routing(), query_transports(), snapshot_all_congestion() to chaos control module - Add congestion/kernel-drop log analysis in logs module - Add congestion-stress scenario: 10-node tree, 1 Mbps bandwidth, 5-10% netem loss, heavy iperf3 traffic - Add IngressConfig for tc ingress policing with per-peer policer filters simulating upstream bandwidth bottlenecks - Add iperf3 JSON result capture to traffic manager for throughput measurement across scenarios - Add ECN A/B test scenarios (ecn-ab-on/off.yaml) with ingress policing and comparison script - Enable TCP ECN negotiation (tcp_ecn=1 sysctl) in container entrypoint for end-to-end CE propagation Tests: - 10 ECN unit/integration tests: mark_ipv6_ecn_ce variants, CE relay chain (3-node propagation), EcnConfig serde roundtrip - 3 transport drop congestion detection unit tests Documentation: - Update fips-mesh-layer.md: replace outdated CE Echo stub with full ECN Congestion Signaling section covering detection logic, CE relay, IPv6 marking, session tracking, and monitoring counters - Update fips-configuration.md: add node.ecn.* parameter table and ecn block in complete reference YAML - Update fips-transport-layer.md: add Congestion Reporting section with TransportCongestion struct, congestion() trait method, and per-transport status; document AsyncFd/recvmsg/SO_RXQ_OVFL in UDP - Update chaos README: add congestion/ECN scenario docs, ingress traffic control, and iperf3 JSON capture sections - Update README.md: add ECN to features list and "What works today"; update transport and tooling entries
128 lines
4.0 KiB
Bash
Executable File
128 lines
4.0 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# ECN A/B Throughput Test
|
|
#
|
|
# Runs two identical chaos scenarios — one with ECN enabled, one disabled —
|
|
# and compares iperf3 throughput and congestion counter results.
|
|
#
|
|
# Usage: ./ecn-ab-test.sh [--seed N] [--duration N]
|
|
|
|
set -euo pipefail
|
|
cd "$(dirname "$0")"
|
|
|
|
EXTRA_ARGS=()
|
|
while [[ $# -gt 0 ]]; do
|
|
case "$1" in
|
|
--seed|--duration)
|
|
EXTRA_ARGS+=("$1" "$2"); shift 2 ;;
|
|
*)
|
|
echo "Unknown arg: $1"; exit 1 ;;
|
|
esac
|
|
done
|
|
|
|
echo "=== ECN A/B Throughput Test ==="
|
|
echo ""
|
|
|
|
# --- Run A: ECN ON ---
|
|
echo "--- Phase A: ECN ENABLED ---"
|
|
sudo python3 -m sim scenarios/ecn-ab-on.yaml "${EXTRA_ARGS[@]}" || true
|
|
echo ""
|
|
|
|
# --- Run B: ECN OFF ---
|
|
echo "--- Phase B: ECN DISABLED ---"
|
|
sudo python3 -m sim scenarios/ecn-ab-off.yaml "${EXTRA_ARGS[@]}" || true
|
|
echo ""
|
|
|
|
# --- Compare results ---
|
|
echo "=== Results ==="
|
|
echo ""
|
|
|
|
python3 - <<'PYEOF'
|
|
import json
|
|
import os
|
|
import sys
|
|
|
|
def load_results(path):
|
|
if not os.path.exists(path):
|
|
return []
|
|
with open(path) as f:
|
|
return json.load(f)
|
|
|
|
def extract_throughput(results):
|
|
"""Extract per-session throughput in Mbps from iperf3 JSON."""
|
|
sessions = []
|
|
for r in results:
|
|
meta = r.get("_meta", {})
|
|
end = r.get("end", {})
|
|
# sum_sent / sum_received contain aggregate stats
|
|
sent = end.get("sum_sent", {})
|
|
recv = end.get("sum_received", {})
|
|
sent_mbps = sent.get("bits_per_second", 0) / 1e6
|
|
recv_mbps = recv.get("bits_per_second", 0) / 1e6
|
|
sessions.append({
|
|
"client": meta.get("client", "?"),
|
|
"server": meta.get("server", "?"),
|
|
"sent_mbps": sent_mbps,
|
|
"recv_mbps": recv_mbps,
|
|
})
|
|
return sessions
|
|
|
|
def load_congestion(path):
|
|
if not os.path.exists(path):
|
|
return {}
|
|
with open(path) as f:
|
|
return json.load(f)
|
|
|
|
def print_sessions(label, sessions):
|
|
# Filter out incomplete sessions (killed at teardown, no valid data)
|
|
valid = [s for s in sessions if s["recv_mbps"] > 0]
|
|
incomplete = len(sessions) - len(valid)
|
|
if not valid:
|
|
print(f" {label}: no completed iperf3 sessions ({incomplete} incomplete)")
|
|
return 0
|
|
print(f" {label}:")
|
|
total_sent = 0
|
|
total_recv = 0
|
|
for s in valid:
|
|
print(f" {s['client']:>4} -> {s['server']:<4} "
|
|
f"sent={s['sent_mbps']:7.2f} Mbps recv={s['recv_mbps']:7.2f} Mbps")
|
|
total_sent += s["sent_mbps"]
|
|
total_recv += s["recv_mbps"]
|
|
n = len(valid)
|
|
print(f" {'':>14} avg sent={total_sent/n:7.2f} Mbps avg recv={total_recv/n:7.2f} Mbps")
|
|
print(f" {'':>14} completed={n} incomplete={incomplete}")
|
|
return total_recv / n
|
|
|
|
on_results = load_results("sim-results/ecn-ab-on/iperf3-results.json")
|
|
off_results = load_results("sim-results/ecn-ab-off/iperf3-results.json")
|
|
|
|
on_sessions = extract_throughput(on_results)
|
|
off_sessions = extract_throughput(off_results)
|
|
|
|
print("Throughput:")
|
|
avg_on = print_sessions("ECN ON", on_sessions) or 0
|
|
print()
|
|
avg_off = print_sessions("ECN OFF", off_sessions) or 0
|
|
print()
|
|
|
|
if avg_on and avg_off:
|
|
delta_pct = ((avg_on - avg_off) / avg_off) * 100
|
|
print(f" Delta: ECN ON vs OFF = {delta_pct:+.1f}% avg recv throughput")
|
|
print()
|
|
|
|
# Congestion counters
|
|
print("Congestion Counters (final snapshot):")
|
|
for label, path in [("ECN ON", "sim-results/ecn-ab-on/congestion-snapshot-final.json"),
|
|
("ECN OFF", "sim-results/ecn-ab-off/congestion-snapshot-final.json")]:
|
|
snap = load_congestion(path)
|
|
if not snap:
|
|
print(f" {label}: no snapshot")
|
|
continue
|
|
totals = {"ce_forwarded": 0, "ce_received": 0, "congestion_detected": 0, "kernel_drop_events": 0}
|
|
for node_id, data in sorted(snap.items()):
|
|
cong = data.get("congestion", {})
|
|
for k in totals:
|
|
totals[k] += cong.get(k, 0)
|
|
print(f" {label}: ce_fwd={totals['ce_forwarded']} ce_recv={totals['ce_received']} "
|
|
f"cong_detect={totals['congestion_detected']} kern_drops={totals['kernel_drop_events']}")
|
|
PYEOF
|