Gahow Wang
547611e022
D2: run_benchmark.sh and run_experiments.sh still pass --time-scale and --max-inflight-sessions to the replayer, but those flags were removed when the project moved to trace-driven dispatch. The scripts cannot run as-is. D3: ~25 ad-hoc analyze_* / compare_* / profile_* / final_* scripts and a handful of single-experiment run_*.sh point at /home/admin/cpfs paths, deleted output directories, or a sampled trace file that no longer exists. Keep them in scripts/legacy/ for historical reference; the scripts that remain in scripts/ (analyze_trace, analyze_breakdown, analyze_cache_hit, analyze_eviction, compare_results, compute_roofline, sample_trace, analyze_agentic_patterns, simulate_cache_policies, plus launch_*.sh, gpu_monitor.sh, bench.sh) cover the current workflow. Adds scripts/legacy/README.md to document the archival policy.
51 lines
1.8 KiB
Python
51 lines
1.8 KiB
Python
"""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))
|