scripts: archive obsolete one-off shell/python scripts to legacy/ (D2, D3)

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Keep them in scripts/legacy/ for historical reference; the scripts that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.

scripts/legacy/compare_p2p.py

@@ -0,0 +1,59 @@
+"""Compare P2P offload vs baseline."""
+import json, csv, statistics, os
+
+def lat(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)}
+
+def gpu(path):
+    if not os.path.exists(path): return 0
+    rows = list(csv.DictReader(open(path)))
+    vals = [float(r["util_pct"]) for r in rows]
+    return statistics.fmean(vals) if vals else 0
+
+print("P2P OFFLOAD vs BASELINE (both fresh restart, 200 req)")
+print("=" * 75)
+fmt = "%-30s %6s %8s %8s %8s %8s %8s %6s"
+print(fmt % ("Config","OK/N","TTFT50","TTFT90","TPOT50","TPOT90","E2E50","GPU%"))
+print("-" * 75)
+
+configs = [
+    ("baseline_dash1", "Baseline (8 combined)"),
+    ("p2p_offload", "P2P offload (HEAVY on diff GPU)"),
+]
+
+results = {}
+for d, label in configs:
+    mp = "outputs/%s/metrics.jsonl" % d
+    if not os.path.exists(mp):
+        print("  %s: NOT FOUND" % mp)
+        continue
+    s = lat(mp)
+    g = gpu("outputs/%s/gpu_util.csv" % d)
+    results[d] = s
+    print(fmt % (label, "%d/%d" % (s["ok"],s["n"]),
+        "%.3f" % s["t50"], "%.3f" % s["t90"],
+        "%.3f" % s["p50"], "%.3f" % s["p90"],
+        "%.3f" % s["e50"], "%.1f" % g))
+
+if "baseline_dash1" in results and "p2p_offload" in results:
+    b = results["baseline_dash1"]
+    a = results["p2p_offload"]
+    print()
+    print("DELTA (P2P vs Baseline):")
+    for label, bv, av in [
+        ("TTFT p50", b["t50"], a["t50"]),
+        ("TTFT p90", b["t90"], a["t90"]),
+        ("TPOT p90", b["p90"], a["p90"]),
+        ("E2E p50", b["e50"], a["e50"]),
+    ]:
+        d = (av/bv-1)*100 if bv > 0 else 0
+        print("  %s: %.3f -> %.3f (%+.1f%%)" % (label, bv, av, d))