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Keep them in scripts/legacy/ for historical reference; the scripts that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

@@ -0,0 +1,77 @@
+#!/bin/bash
+# Run the full benchmark suite: sample trace → replay against vLLM → collect metrics.
+#
+# Prerequisites:
+#   - vLLM server running (use scripts/launch_vllm.sh)
+#   - Sampled trace file exists (or will be created)
+#
+# Usage:
+#   bash scripts/run_benchmark.sh [--endpoint URL] [--tag NAME]
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PROJECT_DIR="$(dirname "$SCRIPT_DIR")"
+cd "$PROJECT_DIR"
+
+# Defaults
+TRACE_INPUT="${TRACE_INPUT:-$HOME/ali-trace/trace-glm5.1-formatted/051315-051317.jsonl}"
+ENDPOINT="${ENDPOINT:-http://localhost:8000}"
+TAG="${TAG:-default}"
+TARGET_REQUESTS="${TARGET_REQUESTS:-5000}"
+TIME_SCALE="${TIME_SCALE:-1.0}"
+MAX_INFLIGHT="${MAX_INFLIGHT:-32}"
+SEED="${SEED:-42}"
+
+# Parse args
+while [[ $# -gt 0 ]]; do
+    case "$1" in
+        --endpoint) ENDPOINT="$2"; shift 2 ;;
+        --tag) TAG="$2"; shift 2 ;;
+        --target-requests) TARGET_REQUESTS="$2"; shift 2 ;;
+        --time-scale) TIME_SCALE="$2"; shift 2 ;;
+        --max-inflight) MAX_INFLIGHT="$2"; shift 2 ;;
+        *) echo "Unknown arg: $1"; exit 1 ;;
+    esac
+done
+
+SAMPLED_TRACE="traces/sampled_${TARGET_REQUESTS}req_seed${SEED}.jsonl"
+OUTPUT_DIR="outputs/${TAG}_$(date +%Y%m%d_%H%M%S)"
+
+echo "=== Benchmark: tag=$TAG ==="
+echo "  Trace: $TRACE_INPUT"
+echo "  Endpoint: $ENDPOINT"
+echo "  Target requests: $TARGET_REQUESTS"
+echo "  Time scale: $TIME_SCALE"
+echo "  Max inflight sessions: $MAX_INFLIGHT"
+
+# Step 1: Sample trace (if not already done)
+if [ ! -f "$SAMPLED_TRACE" ]; then
+    echo ""
+    echo "=== Step 1: Sampling trace ==="
+    python scripts/sample_trace.py \
+        --input "$TRACE_INPUT" \
+        --output "$SAMPLED_TRACE" \
+        --target-requests "$TARGET_REQUESTS" \
+        --seed "$SEED"
+else
+    echo ""
+    echo "=== Step 1: Using existing sampled trace: $SAMPLED_TRACE ==="
+fi
+
+# Step 2: Run replay
+echo ""
+echo "=== Step 2: Replaying trace ==="
+mkdir -p "$OUTPUT_DIR"
+python -m replayer \
+    --trace "$SAMPLED_TRACE" \
+    --output "$OUTPUT_DIR/metrics.jsonl" \
+    --endpoint "$ENDPOINT" \
+    --time-scale "$TIME_SCALE" \
+    --max-inflight-sessions "$MAX_INFLIGHT" \
+    -v
+
+echo ""
+echo "=== Done ==="
+echo "  Metrics: $OUTPUT_DIR/metrics.jsonl"
+echo "  Summary: $OUTPUT_DIR/metrics.summary.json"