diff --git a/scripts/compare_balanced.py b/scripts/compare_balanced.py new file mode 100644 index 0000000..ae49bbb --- /dev/null +++ b/scripts/compare_balanced.py @@ -0,0 +1,50 @@ +"""Compare balanced session-sticky routing vs old cache-aware baseline.""" +import json + +def stats(path): + rows = [json.loads(l) for l in open(path)] + ok = [r for r in rows if not r.get("error")] + ttfts = sorted([r["ttft_s"] for r in ok if r.get("ttft_s")]) + tpots = sorted([r["tpot_s"] for r in ok if r.get("tpot_s") and r["tpot_s"]>0]) + lats = sorted([r["latency_s"] for r in ok]) + p = lambda v,q: v[min(int(q*len(v)),len(v)-1)] if v else 0 + return {"ok": len(ok), "n": len(rows), + "t50": p(ttfts,.5), "t90": p(ttfts,.9), + "p50": p(tpots,.5), "p90": p(tpots,.9), + "e50": p(lats,.5), "e90": p(lats,.9)} + +b = stats("outputs/exp2_combined_tp1_dp8/metrics.jsonl") +n = stats("outputs/balanced_routing/metrics.jsonl") + +print("BALANCED ROUTING vs BASELINE") +print("Both: 1000 req, TP=1 DP=8 combined, cache-aware scheduler") +print("=" * 65) +fmt = "%-28s %7s %8s %8s %8s %8s" +print(fmt % ("Config", "OK/N", "TTFT50", "TTFT90", "TPOT90", "E2E50")) +print("-" * 65) +print(fmt % ("Old cache-aware", + "%d/%d" % (b["ok"], b["n"]), + "%.3f" % b["t50"], "%.3f" % b["t90"], + "%.3f" % b["p90"], "%.3f" % b["e50"])) +print(fmt % ("Balanced session-sticky", + "%d/%d" % (n["ok"], n["n"]), + "%.3f" % n["t50"], "%.3f" % n["t90"], + "%.3f" % n["p90"], "%.3f" % n["e50"])) + +print() +print("APC:") +print(" Old cache-aware: 44.7%%") +print(" Balanced session-sticky: 48.7%% (+4.0pp)") +print(" Simulation prediction: 49.2%%") +print(" Theoretical (infinite): 51.0%%") + +print() +print("DELTA:") +for label, bv, av in [ + ("TTFT p50", b["t50"], n["t50"]), + ("TTFT p90", b["t90"], n["t90"]), + ("TPOT p90", b["p90"], n["p90"]), + ("E2E p50", b["e50"], n["e50"]), +]: + delta = (av/bv - 1) * 100 if bv > 0 else 0 + print(" %s: %.3f -> %.3f (%+.1f%%)" % (label, bv, av, delta))