MB5 PD ablation: controlled-variable reuse/conc redo + campaign tooling

Reuse and concurrency axes redone with proper controlled variables, plus
the orchestration used to run them on dash0:

- run_reuse_fixed.sh: hold REAL prefill work (delta) constant, vary only
  cached prefix -> reuse = C/(C+U). Supersedes old fig1 (which held
  input=8192 and sliced prefix out, confounding "more reuse" with "less
  prefill").
- run_conc.sh: agentic-corner config (in=32768, delta=512, reuse=0.984,
  out=128) that exposes PD's structural KV-transfer tax. Supersedes old fig3.
- run_campaign{,2,3}.sh, backfill_d2048o128.sh: serial campaign drivers
  (strictly one driver at a time), out=128 sweeps, PD wall-cap for
  collapse-draining high-reuse arms, and flaked-arm backfill.
- mb5_run_gpu.sh: per-config bring-up / replay / teardown orchestrator.
- plot_pd_crossover.py: render the reuse_compare figures from fig_agg dumps.
- fig_agg.py: tolerate null stats from fully-collapsed arms (0 successes
  write the stat keys as null; `dict.get(k, {})` returns null, not {}).

Data: fig1_reuse_fixed.json, fig1_reuse_d{1024,2048}_o128.json
Figs: reuse_compare_AB.png, reuse_compare_ABC.png

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

microbench/fresh_setup/backfill_d2048o128.sh

@@ -0,0 +1,35 @@
+#!/usr/bin/env bash
+# Backfill the d2048/o128 reuse arms that vLLM startup-flaked out (transient
+# "Engine core initialization failed", intermittent). Retry up to 4x each with a
+# clean teardown between attempts; HEALTH_MAX_TRIES=180 so a crashed launch fails
+# in ~6min (not 10) before retrying. Then re-aggregate the figure JSON.
+cd /home/admin/cpfs/wjh/agentic-kv-fresh
+export MB5_VENV=$PWD/.venv_dash0
+export HEALTH_MAX_TRIES=180
+VPY=$MB5_VENV/bin/python
+DELTA=2048; OL=128; N=8; THINK=0.5; TURNS=8; NSESS=48
+MISS="${MISS:-4096:6P+2D 18432:6P+2D 38912:8C-proxy 38912:6P+2D}"
+echo "=== BACKFILL START $(date) miss='$MISS' ==="
+for pc in $MISS; do
+  pfx=${pc%%:*}; cfg=${pc##*:}
+  tag="reuse_p${pfx}_d${DELTA}_o${OL}"; trace="traces_synth/${tag}.jsonl"
+  $VPY scripts/gen_synthetic_trace.py --out "$trace" --mode regular --qps "$NSESS" --duration-s 1 \
+     --turns "$TURNS" --prefix-len "$pfx" --delta-len "$DELTA" --output-len "$OL" --seed 42 >/dev/null 2>&1
+  dur=""; [ "$cfg" != "8C-proxy" ] && dur=500
+  ok=0
+  for attempt in 1 2 3 4; do
+    echo "[backfill] $tag $cfg attempt=$attempt $(date +%T)"
+    MB5_P_ROUTING=session MB5_COLO_ROUTING=session \
+      REPLAY_MAX_INFLIGHT=$N REPLAY_INTER_TURN_THINK_S=$THINK REPLAY_NO_REALIZED_PREFIX=1 REPLAY_MAX_DURATION="$dur" \
+      CONFIGS="$cfg" REPS=1 TRACE="$trace" RUN_TAG="$tag" \
+      bash scripts/mb5_run_gpu.sh >/dev/null 2>&1
+    if [ -f "mb5_runs/${tag}_${cfg}_rep1/replay_metrics.summary.json" ]; then
+      echo "  OK $cfg pfx=$pfx attempt=$attempt"; ok=1; break; fi
+    echo "  FAILED attempt=$attempt; cleanup+retry"
+    MB5_VENV=$PWD/.venv_dash0 bash scripts/mb5_launch.sh stop >/dev/null 2>&1; sleep 5
+  done
+  [ $ok = 0 ] && echo "[backfill] GAVE UP $tag $cfg"
+done
+dirs=(); for d in mb5_runs/reuse_*_d2048_o128_*_rep1; do [ -f "$d/replay_metrics.summary.json" ] && dirs+=("$d"); done
+$VPY scripts/fig_agg.py --json "${dirs[@]}" > analysis/mb5_pd_ablation/fig1_reuse_d2048_o128.json
+echo "=== BACKFILL DONE dirs=${#dirs[@]}/24 $(date) ==="

microbench/fresh_setup/fig_agg.py

@@ -100,11 +100,13 @@ def main():
             continue
         s = json.load(open(sp))
         arm, pg, dg, ports = arm_of(run.name)
-        lat = s.get("latency_stats_s", {})
+        # `or {}` because a fully-collapsed arm (0 successes) writes these as null,
-        ttft = s.get("ttft_stats_s", {})
+        # and dict.get(k, {}) returns null (not {}) when the key exists with value null.
-        tpot = s.get("tpot_stats_s", {})
+        lat = s.get("latency_stats_s") or {}
+        ttft = s.get("ttft_stats_s") or {}
+        tpot = s.get("tpot_stats_s") or {}
         wall = s.get("wall_clock_s") or 1.0
-        out = s.get("actual_output_tokens_stats", {})
+        out = s.get("actual_output_tokens_stats") or {}
         n = s.get("success_count", 0); req = s.get("request_count", 0)
         tot_out = out.get("count", 0) * out.get("mean", 0)
         tps = tot_out / wall

microbench/fresh_setup/mb5_run_gpu.sh

@@ -0,0 +1,144 @@
+#!/usr/bin/env bash
+# Orchestrator for MB5: for each CONFIG × rep, bring up the stack, run a
+# trace replay against it, collect KV snapshots and replayer metrics,
+# tear down.
+#
+# Designed to be run on dash1 (or any host with cpfs mounted at
+# /home/admin/cpfs/wjh/).
+#
+# Env vars (with defaults):
+#   CONFIGS    : space-separated MB5 configs (default: "8C 6P+2D 4P+4D 2P+6D")
+#   REPS       : reps per config (default: 3)
+#   TRACE      : trace JSONL path
+#                (default: /home/admin/cpfs/wjh/agentic-kv/traces/w600_r0.0015_st30.jsonl)
+#   RUN_TAG    : output root tag (default: $(date +%Y%m%d_%H%M%S))
+#   REQUEST_LIMIT : optional, cap replay requests (default: none)
+
+set -eo pipefail
+
+FRESH_ROOT="/home/admin/cpfs/wjh/agentic-kv-fresh"
+# MB5_VENV lets a second host use an isolated venv clone (see mb5_launch.sh).
+VENV="${MB5_VENV:-${FRESH_ROOT}/.venv}"
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+LAUNCH="${SCRIPT_DIR}/mb5_launch.sh"
+REPLAYER_DIR="${FRESH_ROOT}/replayer"
+
+CONFIGS="${CONFIGS:-8C 6P+2D 4P+4D 2P+6D}"
+REPS="${REPS:-3}"
+TRACE="${TRACE:-/home/admin/cpfs/wjh/agentic-kv/traces/w600_r0.0015_st30.jsonl}"
+RUN_TAG="${RUN_TAG:-$(date +%Y%m%d_%H%M%S)}"
+MODEL_NAME="${MODEL_NAME:-/home/admin/cpfs/wjh/models/Qwen/Qwen3-Coder-30B-A3B-Instruct}"
+REQUEST_LIMIT_ARG=""
+if [ -n "${REQUEST_LIMIT:-}" ]; then
+    REQUEST_LIMIT_ARG="--request-limit ${REQUEST_LIMIT}"
+fi
+
+OUT_ROOT="${FRESH_ROOT}/mb5_runs/${RUN_TAG}"
+mkdir -p "${OUT_ROOT}"
+echo "[mb5-run] RUN_TAG=${RUN_TAG}"
+echo "[mb5-run] OUT_ROOT=${OUT_ROOT}"
+echo "[mb5-run] CONFIGS=${CONFIGS}"
+echo "[mb5-run] REPS=${REPS}"
+echo "[mb5-run] TRACE=${TRACE}"
+
+run_one() {
+    local config="$1" rep="$2"
+    local label="${RUN_TAG}_${config}_rep${rep}"
+    local rundir="${FRESH_ROOT}/mb5_runs/${label}"
+    echo ""
+    echo "======== ${config} rep${rep} ========"
+
+    # Launch
+    if ! CONFIG="${config}" RUN_LABEL="${RUN_TAG}_${config}_rep${rep}" \
+            bash "${LAUNCH}" start > "${OUT_ROOT}/${config}_rep${rep}_launch.log" 2>&1; then
+        echo "[mb5-run] LAUNCH FAILED for ${config} rep${rep}; see ${OUT_ROOT}/${config}_rep${rep}_launch.log"
+        return 1
+    fi
+
+    # Extract ENDPOINTS line emitted by mb5_launch.sh
+    local endpoints
+    endpoints=$(grep "^ENDPOINTS=" "${OUT_ROOT}/${config}_rep${rep}_launch.log" | tail -1 | cut -d= -f2-)
+    if [ -z "${endpoints}" ]; then
+        echo "[mb5-run] ERROR: no ENDPOINTS in launch log"
+        bash "${LAUNCH}" stop > /dev/null 2>&1 || true
+        return 1
+    fi
+    echo "[mb5-run] endpoints: ${endpoints}"
+
+    # Replay
+    source "${VENV}/bin/activate"
+    local replay_out="${rundir}/replay_metrics.jsonl"
+    mkdir -p "$(dirname "${replay_out}")"
+    # per-GPU utilization timeseries over the replay window (2s sampling)
+    bash "${FRESH_ROOT}/microbench/fresh_setup/gpu_monitor.sh" "${rundir}/gpu_util.csv" 2 >/dev/null 2>&1 &
+    local GPU_MON=$!
+    local t0
+    t0=$(date +%s.%N)
+    if ! PYTHONPATH="${FRESH_ROOT}" python -m replayer \
+            --endpoint "${endpoints}" \
+            --trace "${TRACE}" \
+            --output "${replay_out}" \
+            --model "${MODEL_NAME}" \
+            ${REQUEST_LIMIT_ARG} \
+            > "${OUT_ROOT}/${config}_rep${rep}_replay.log" 2>&1; then
+        local t1
+        t1=$(date +%s.%N)
+        local wall=$(python -c "print(${t1} - ${t0})")
+        echo "[mb5-run] REPLAY FAILED after ${wall} s; see ${OUT_ROOT}/${config}_rep${rep}_replay.log"
+        kill "${GPU_MON}" 2>/dev/null || true
+        bash "${LAUNCH}" stop > /dev/null 2>&1 || true
+        return 1
+    fi
+    local t1
+    t1=$(date +%s.%N)
+    local wall_clock_s
+    wall_clock_s=$(python -c "print(${t1} - ${t0})")
+    echo "[mb5-run] replay done in ${wall_clock_s}s"
+    echo "${wall_clock_s}" > "${rundir}/wall_clock_s.txt"
+    kill "${GPU_MON}" 2>/dev/null || true
+    printf '{"t_start_unix":%s,"t_end_unix":%s}\n' "${t0}" "${t1}" > "${rundir}/run_window.json"
+
+    # Per-instance prefix-cache counters, scraped from each backend BEFORE
+    # teardown. For PD this is the only honest reuse signal: producer ports
+    # (the low ones) show cross-turn prefix-cache hits; the consumer's
+    # per-request cached_tokens is meaningless (it counts transferred KV).
+    {
+        for p in 8000 8001 8002 8003 8004 8005 8006 8007; do
+            m=$(curl -s --noproxy '*' "http://127.0.0.1:${p}/metrics" 2>/dev/null) || continue
+            q=$(printf '%s' "$m" | awk '/^vllm:prefix_cache_queries_total/{print $2; exit}')
+            h=$(printf '%s' "$m" | awk '/^vllm:prefix_cache_hits_total/{print $2; exit}')
+            [ -n "${q}" ] && echo "port=${p} queries=${q} hits=${h}"
+        done
+    } > "${rundir}/instance_apc.txt" 2>/dev/null || true
+
+    # Stop launch (cleans up vllm + proxy; reverts patch on last call)
+    CONFIG="${config}" RUN_LABEL="${RUN_TAG}_${config}_rep${rep}" \
+        bash "${LAUNCH}" stop > "${OUT_ROOT}/${config}_rep${rep}_stop.log" 2>&1 || true
+
+    sleep 10  # cooldown so GPUs settle before next config
+    echo "[mb5-run] DONE ${config} rep${rep}"
+}
+
+# Quick check that the launch script and replayer are reachable
+if [ ! -f "${LAUNCH}" ]; then echo "missing ${LAUNCH}"; exit 1; fi
+if [ ! -d "${REPLAYER_DIR}" ]; then echo "missing ${REPLAYER_DIR}"; exit 1; fi
+if [ ! -f "${TRACE}" ]; then echo "missing trace ${TRACE}"; exit 1; fi
+
+# Iterate
+failures=0
+for config in ${CONFIGS}; do
+    for ((rep=1; rep<=REPS; rep++)); do
+        if ! run_one "${config}" "${rep}"; then
+            failures=$((failures+1))
+        fi
+    done
+done
+
+# Final patch revert (defensive — mb5_launch.sh stop also reverts)
+python "${SCRIPT_DIR}/instrument_kv_snapshot.py" --revert --venv "${VENV}" 2>/dev/null || true
+
+echo ""
+echo "======== ALL CONFIGS DONE ========"
+echo "failures: ${failures}"
+echo "results under: ${FRESH_ROOT}/mb5_runs/${RUN_TAG}_*"
+echo "to plot:  python plot_kv_pool_timeline.py --run-tag ${RUN_TAG}"

microbench/fresh_setup/plot_pd_crossover.py

@@ -0,0 +1,184 @@
+"""Render the three PD-vs-colo crossover figures from fig_agg JSON dumps.
+
+Inputs (produced by `fig_agg.py --json`):
+  analysis/mb5_pd_ablation/fig1_reuse_fixed.json  reuse axis (N=8, FIXED real
+        prefill delta=2048; vary cached prefix -> reuse = pfx/(pfx+delta).
+        Controlled-variable: real new-prefill work is constant across the sweep,
+        only the cached fraction (and total context) grows. Supersedes the old
+        fig1.json, which held input=8192 and sliced prefix out of it so delta
+        shrank 15x as reuse rose — a confound, not a pure reuse axis.)
+  analysis/mb5_pd_ablation/fig2.json   shape axis   (N=8, reuse~70%)
+  analysis/mb5_pd_ablation/fig3_conc32k.json  concurrency (in32768/out128,
+        reuse~0.984 = 32256 resident + 512 real new-prefill per turn; retuned
+        2026-05-31 to the agentic corner so PD pays the full-context per-turn
+        KV-transfer tax while colo keeps it resident; vary N by step 8 up to the
+        mean-E2E<=10s SLO ceiling)
+
+Each figure overlays colo + the three PD ratios and marks the PD-best advantage.
+All three share the corrected (uncontaminated, e13391e-gated-off) stack.
+"""
+from __future__ import annotations
+
+import json
+import re
+from pathlib import Path
+
+import matplotlib
+matplotlib.use("Agg")
+import matplotlib.pyplot as plt
+
+ROOT = Path(__file__).resolve().parents[2]
+DATA = ROOT / "analysis" / "mb5_pd_ablation"
+OUT = ROOT / "figs" / "mb5_pd_ablation"
+OUT.mkdir(parents=True, exist_ok=True)
+
+PD_ARMS = ["2P+6D", "4P+4D", "6P+2D"]
+STYLE = {
+    "colo":  dict(color="k",        marker="o", lw=2.4, ls="-",  label="colo (8×kv_both)"),
+    "2P+6D": dict(color="#1f77b4",  marker="s", lw=1.6, ls="--", label="PD 2P+6D"),
+    "4P+4D": dict(color="#2ca02c",  marker="^", lw=1.6, ls="--", label="PD 4P+4D"),
+    "6P+2D": dict(color="#ff7f0e",  marker="v", lw=1.6, ls="--", label="PD 6P+2D"),
+}
+
+
+def load(name):
+    return json.load(open(DATA / name))
+
+
+def by_axis(rows, keyfn):
+    """Group rows -> {axis_val: {arm: row}}."""
+    out = {}
+    for r in rows:
+        k = keyfn(r["name"])
+        if k is None:
+            continue
+        out.setdefault(k, {})[r["arm"]] = r
+    return out
+
+
+def pd_best(armmap, metric="e2e_p90"):
+    vals = [(a, armmap[a][metric]) for a in PD_ARMS
+            if a in armmap and armmap[a].get(metric) is not None]
+    return min(vals, key=lambda t: t[1]) if vals else (None, None)
+
+
+def series(grp, xs, arm, metric):
+    return [grp[x][arm].get(metric) if arm in grp[x] else None for x in xs]
+
+
+# ---------- Fig 1: reuse axis ----------
+def _reuse_pct(name):
+    """Reuse % from a `reuse_p{pfx}_d{delta}_{arm}` run name: pfx/(pfx+delta)."""
+    m = re.search(r"_p(\d+)_d(\d+)", name)
+    if not m:
+        return None
+    pfx, delta = int(m.group(1)), int(m.group(2))
+    return round(pfx / (pfx + delta) * 100)
+
+
+def fig_reuse():
+    g = by_axis(load("fig1_reuse_fixed.json"), _reuse_pct)
+    xs = sorted(g)
+    reuse = xs
+    fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(11, 4.2))
+    for arm in ["colo", *PD_ARMS]:
+        ax1.plot(reuse, series(g, xs, arm, "e2e_p90"), **STYLE[arm])
+    ax1.set_xlabel("intra-session KV reuse (%)  [fixed real prefill, delta=2048]")
+    ax1.set_ylabel("E2E latency p90 (s)")
+    ax1.set_title("(a) E2E-p90 vs reuse  (N=8, delta=2048/out256)")
+    ax1.legend(fontsize=8); ax1.grid(alpha=.3)
+
+    adv, putil = [], []
+    for x in xs:
+        co = g[x]["colo"]["e2e_p90"]; _, b = pd_best(g[x])
+        adv.append(co / b if b else None)
+        a = pd_best(g[x])[0]
+        putil.append(g[x][a].get("pu") if a else None)
+    ax2.plot(reuse, adv, color="purple", marker="D", lw=2, label="PD-best advantage (colo/PD)")
+    ax2.axhline(1.0, color="grey", ls=":", lw=1)
+    ax2.set_xlabel("intra-session KV reuse (%)"); ax2.set_ylabel("advantage  (>1 = PD wins)")
+    ax2b = ax2.twinx()
+    ax2b.plot(reuse, putil, color="brown", marker="x", lw=1.4, ls="-.", label="PD-best prefill-GPU util")
+    ax2b.set_ylabel("prefill-GPU util (%)", color="brown"); ax2b.tick_params(axis="y", colors="brown")
+    ax2.set_title("(b) advantage erodes; prefill GPUs go idle")
+    l1, la1 = ax2.get_legend_handles_labels(); l2, la2 = ax2b.get_legend_handles_labels()
+    ax2.legend(l1 + l2, la1 + la2, fontsize=8, loc="center right"); ax2.grid(alpha=.3)
+    fig.suptitle("Fig 1 — Reuse axis (fixed real prefill delta=2048): PD's edge vs rising cache reuse",
+                 fontsize=11, y=1.02)
+    fig.tight_layout(); p = OUT / "fig1_reuse_axis.png"; fig.savefig(p, dpi=130, bbox_inches="tight")
+    print("wrote", p)
+
+
+# ---------- Fig 2: shape axis ----------
+def fig_shape():
+    g = by_axis(load("fig2.json"),
+                lambda n: ((int(m.group(1)), int(m.group(2)))
+                           if (m := re.search(r"_in(\d+)_out(\d+)_", n)) else None))
+    xs = sorted(g, key=lambda t: t[0])  # ascending input
+    labels = [f"in{i}\nout{o}" for i, o in xs]
+    xi = list(range(len(xs)))
+    fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(11, 4.2))
+    for arm in ["colo", *PD_ARMS]:
+        ax1.plot(xi, series(g, xs, arm, "e2e_p90"), **STYLE[arm])
+    ax1.set_xticks(xi); ax1.set_xticklabels(labels, fontsize=7)
+    ax1.set_xlabel("shape  (decode-heavy → prefill-heavy)"); ax1.set_ylabel("E2E latency p90 (s)")
+    ax1.set_title("(a) E2E-p90 vs shape  (N=8, reuse~70%)")
+    ax1.legend(fontsize=8); ax1.grid(alpha=.3)
+
+    adv, comp = [], []
+    for x in xs:
+        co = g[x]["colo"]["e2e_p90"]; a, b = pd_best(g[x])
+        adv.append(co / b if b else None)
+        # completion of the worst PD arm (exposes catastrophic ratio)
+        worst = min((g[x][arm]["n"] / g[x][arm]["req"]) for arm in PD_ARMS if arm in g[x])
+        comp.append(worst * 100)
+    ax2.plot(xi, adv, color="purple", marker="D", lw=2, label="PD-best advantage (colo/PD)")
+    ax2.axhline(1.0, color="grey", ls=":", lw=1)
+    ax2.set_xticks(xi); ax2.set_xticklabels(labels, fontsize=7)
+    ax2.set_xlabel("shape"); ax2.set_ylabel("advantage  (>1 = PD wins)")
+    ax2b = ax2.twinx()
+    ax2b.plot(xi, comp, color="red", marker="x", lw=1.4, ls="-.", label="worst-PD-arm completion %")
+    ax2b.set_ylabel("worst PD completion (%)", color="red"); ax2b.tick_params(axis="y", colors="red")
+    ax2b.set_ylim(80, 101)
+    ax2.set_title("(b) advantage peaks mid-sweep; wrong ratio catastrophic at prefill extreme")
+    l1, la1 = ax2.get_legend_handles_labels(); l2, la2 = ax2b.get_legend_handles_labels()
+    ax2.legend(l1 + l2, la1 + la2, fontsize=8, loc="lower left"); ax2.grid(alpha=.3)
+    fig.suptitle("Fig 2 — Shape axis: PD wins decode-heavy, ties prefill-heavy; optimal ratio rotates",
+                 fontsize=11, y=1.02)
+    fig.tight_layout(); p = OUT / "fig2_shape_axis.png"; fig.savefig(p, dpi=130, bbox_inches="tight")
+    print("wrote", p)
+
+
+# ---------- Fig 3: concurrency axis ----------
+def fig_conc():
+    g = by_axis(load("fig3_conc32k.json"),
+                lambda n: (int(m.group(1)) if (m := re.search(r"_N(\d+)_", n)) else None))
+    xs = sorted(g)
+    fig, axes = plt.subplots(1, 3, figsize=(15, 4.2))
+    ax1, ax2, ax3 = axes
+    for arm in ["colo", *PD_ARMS]:
+        ax1.plot(xs, series(g, xs, arm, "e2e_mean"), **STYLE[arm])
+    ax1.axhline(10.0, color="red", ls=":", lw=1, label="SLO (mean E2E 10s)")
+    ax1.set_yscale("log"); ax1.set_xticks(xs); ax1.set_xticklabels(xs, fontsize=7)
+    ax1.set_xlabel("concurrent sessions N"); ax1.set_ylabel("E2E latency mean (s, log)")
+    ax1.set_title("(a) mean-E2E vs concurrency"); ax1.legend(fontsize=8); ax1.grid(alpha=.3, which="both")
+
+    for arm in ["colo", *PD_ARMS]:
+        ax2.plot(xs, series(g, xs, arm, "tps"), **STYLE[arm])
+    ax2.set_xticks(xs); ax2.set_xticklabels(xs, fontsize=7)
+    ax2.set_xlabel("concurrent sessions N"); ax2.set_ylabel("throughput (tok/s)")
+    ax2.set_title("(b) TPS: colo scales, PD plateaus/drops"); ax2.legend(fontsize=8); ax2.grid(alpha=.3)
+
+    for arm in ["colo", *PD_ARMS]:
+        ax3.plot(xs, [v * 100 if v is not None else None for v in series(g, xs, arm, "apc")], **STYLE[arm])
+    ax3.set_xticks(xs); ax3.set_xticklabels(xs, fontsize=7)
+    ax3.set_xlabel("concurrent sessions N"); ax3.set_ylabel("producer prefix-cache hit-rate (%)")
+    ax3.set_title("(c) APC vs concurrency"); ax3.legend(fontsize=8); ax3.grid(alpha=.3)
+    fig.suptitle("Fig 3 — Concurrency axis (in32768/out128, reuse~0.984): sweep N by 8 to the 10s-SLO ceiling",
+                 fontsize=11, y=1.02)
+    fig.tight_layout(); p = OUT / "fig3_concurrency_axis.png"; fig.savefig(p, dpi=130, bbox_inches="tight")
+    print("wrote", p)
+
+
+if __name__ == "__main__":
+    fig_reuse(); fig_shape(); fig_conc()

microbench/fresh_setup/run_campaign.sh

@@ -0,0 +1,26 @@
+#!/usr/bin/env bash
+# Unattended serial PD-ablation campaign: reuse sweep -> conc sweep.
+# STRICTLY one driver at a time (the hard lesson): each inner driver brings up and
+# tears down its own vLLM per config via scripts/mb5_run_gpu.sh, and the two sweeps
+# run sequentially (reuse fully finishes + tears down before conc starts). We verify
+# GPUs are clear between sweeps. NO set -e here: a sub-sweep nonzero must NOT skip the
+# other sweep; rc is captured and reported. Detached launch writes a DONE marker.
+cd /home/admin/cpfs/wjh/agentic-kv-fresh
+export MB5_VENV="${MB5_VENV:-/home/admin/cpfs/wjh/agentic-kv-fresh/.venv_dash0}"
+FS=microbench/fresh_setup
+
+echo "=== CAMPAIGN START $(date) ==="
+
+echo "=== [1/2] REUSE SWEEP (fixed real prefill delta=2048, out=256, reuse 20-95%, N=8) $(date) ==="
+bash "$FS/run_reuse_fixed.sh"; rc_reuse=$?
+echo "=== reuse sweep rc=$rc_reuse $(date) ==="
+
+sleep 15
+echo "--- GPU mem after reuse sweep (expect ~0 before conc) ---"
+nvidia-smi --query-gpu=index,memory.used --format=csv,noheader | head -8
+
+echo "=== [2/2] CONC SWEEP (in=32768 reuse=0.984, balanced N grid 8 16 32 48 64 96 128) $(date) ==="
+NLIST="8 16 32 48 64 96 128" bash "$FS/run_conc.sh"; rc_conc=$?
+echo "=== conc sweep rc=$rc_conc $(date) ==="
+
+echo "=== CAMPAIGN DONE reuse_rc=$rc_reuse conc_rc=$rc_conc $(date) ==="

microbench/fresh_setup/run_campaign2.sh

@@ -0,0 +1,26 @@
+#!/usr/bin/env bash
+# Campaign 2 (2026-05-31): two extra reuse sweeps at out=128 (user request:
+# delta=1024/out=128 and delta=2048/out=128), then the capped conc restart.
+# STRICTLY one driver at a time; reuse sweeps run uncapped (mild collapse, matches
+# the existing d2048/o256 sweep), conc runs with the PD-arm wall-cap. NO set -e.
+cd /home/admin/cpfs/wjh/agentic-kv-fresh
+export MB5_VENV="${MB5_VENV:-/home/admin/cpfs/wjh/agentic-kv-fresh/.venv_dash0}"
+FS=microbench/fresh_setup
+
+echo "=== CAMPAIGN2 START $(date) ==="
+
+echo "=== [1/3] REUSE delta=1024 out=128 (reuse 0.33-0.97) $(date) ==="
+DELTA=1024 OL=128 bash "$FS/run_reuse_fixed.sh"; rc1=$?
+echo "=== reuse d1024 o128 rc=$rc1 $(date) ==="
+sleep 12; nvidia-smi --query-gpu=index,memory.used --format=csv,noheader | head -8
+
+echo "=== [2/3] REUSE delta=2048 out=128 (reuse 0.20-0.95) $(date) ==="
+DELTA=2048 OL=128 bash "$FS/run_reuse_fixed.sh"; rc2=$?
+echo "=== reuse d2048 o128 rc=$rc2 $(date) ==="
+sleep 12; nvidia-smi --query-gpu=index,memory.used --format=csv,noheader | head -8
+
+echo "=== [3/3] CONC capped (PD wall=${CONC_PD_MAXDUR:-600}s, colo uncapped), N 8..128 $(date) ==="
+NLIST="8 16 32 48 64 96 128" bash "$FS/run_conc.sh"; rc3=$?
+echo "=== conc rc=$rc3 $(date) ==="
+
+echo "=== CAMPAIGN2 DONE reuse_d1024_o128=$rc1 reuse_d2048_o128=$rc2 conc=$rc3 $(date) ==="

microbench/fresh_setup/run_campaign3.sh

@@ -0,0 +1,20 @@
+#!/usr/bin/env bash
+# Campaign 3 (2026-05-31): the uncapped d2048/o128 reuse sweep stalled on a
+# collapse-draining high-reuse PD arm (4P+4D @ reuse 0.90, ~1 req/several-min).
+# Finish it by re-running ONLY the high-reuse points (0.90, 0.95) WITH the PD
+# wall-cap (low-reuse arms already completed and are cap-insensitive). Then run
+# the capped conc sweep. STRICTLY serial. NO set -e.
+cd /home/admin/cpfs/wjh/agentic-kv-fresh
+export MB5_VENV="${MB5_VENV:-/home/admin/cpfs/wjh/agentic-kv-fresh/.venv_dash0}"
+FS=microbench/fresh_setup
+echo "=== CAMPAIGN3 START $(date) ==="
+
+echo "=== [1/2] finish reuse d2048/o128: re-run pts pfx=18432,38912 (PD capped 500s) $(date) ==="
+DELTA=2048 OL=128 PFXS="18432 38912" REUSE_PD_MAXDUR=500 bash "$FS/run_reuse_fixed.sh"; rc1=$?
+echo "=== reuse d2048 o128 finish rc=$rc1 $(date) ==="
+sleep 12; nvidia-smi --query-gpu=index,memory.used --format=csv,noheader | head -8
+
+echo "=== [2/2] CONC capped (PD wall=600s, colo uncapped), N 8..128 $(date) ==="
+NLIST="8 16 32 48 64 96 128" CONC_PD_MAXDUR=600 bash "$FS/run_conc.sh"; rc2=$?
+echo "=== conc rc=$rc2 $(date) ==="
+echo "=== CAMPAIGN3 DONE reuse_finish=$rc1 conc=$rc2 $(date) ==="

microbench/fresh_setup/run_conc.sh

@@ -0,0 +1,70 @@
+#!/usr/bin/env bash
+# Concurrency axis, agentic-corner config. Supersedes old fig3 (in~8192/out256).
+# RETUNED 2026-05-31 for realism (C2): hold total context in=32768 but shrink the
+# real per-turn new-prefill to delta=512 and push reuse to 0.984 (real agentic
+# reuse ->99.6%). prefix 32256 + delta 512. out=128. This is the corner that
+# exposes PD's structural tax: colo keeps the 32k resident KV local, but PD must
+# KV-transfer the whole 32k context every turn even though only 512 tokens are new
+# (C2 PD-tax ~250-450x). Sweep closed-loop N by step 8 up to mean-E2E<=SLO ceiling.
+# Wiring per memory project-mb5-pd-ablation-wiring: .venv_dash0, traces_synth/,
+# CONFIG 8C-proxy + PD, MB5_P_ROUTING=session + MB5_COLO_ROUTING=session,
+# N=REPLAY_MAX_INFLIGHT closed loop + REPLAY_INTER_TURN_THINK_S,
+# REPLAY_NO_REALIZED_PREFIX=1. RUN ONLY ONE DRIVER AT A TIME (shared GPUs/ports).
+set -eo pipefail
+cd /home/admin/cpfs/wjh/agentic-kv-fresh
+export MB5_VENV="${MB5_VENV:-/home/admin/cpfs/wjh/agentic-kv-fresh/.venv_dash0}"
+VPY="$MB5_VENV/bin/python"
+
+PFX="${PFX:-32256}"; DELTA="${DELTA:-512}"; OL="${OL:-128}"   # reuse=0.984, in=32768
+THINK="${THINK:-0.5}"; TURNS="${TURNS:-8}"
+NSTART="${NSTART:-8}"; NSTEP="${NSTEP:-8}"; NMAX="${NMAX:-128}"
+NLIST="${NLIST:-}"            # explicit N grid (overrides NSTART/STEP/MAX), e.g. "8 16 32 48 64 96 128"
+CONC_PD_MAXDUR="${CONC_PD_MAXDUR:-600}"   # wall-deadline (s) for PD arms only; bounds collapsed-arm
+                                          # drain (un-run turns = failures). colo (8C-proxy) runs UNCAPPED
+                                          # so the headline reference is always fully measured.
+SLO="${SLO:-10.0}"
+SESS_PER_N="${SESS_PER_N:-4}"
+CFGS="${CFGS:-8C-proxy 2P+6D 4P+4D 6P+2D}"
+ONLY_N="${ONLY_N:-}"
+
+run_N() {
+    local N="$1"; local sess=$(( SESS_PER_N * N ))
+    local tag="conc32k_N${N}"; local trace="traces_synth/${tag}.jsonl"
+    "$VPY" scripts/gen_synthetic_trace.py --out "$trace" --mode regular \
+        --qps "$sess" --duration-s 1 --turns "$TURNS" \
+        --prefix-len "$PFX" --delta-len "$DELTA" --output-len "$OL" --seed 42 >/dev/null
+    echo "[conc32k] N=$N sess=$sess in=$((PFX+DELTA)) out=$OL -> $trace"
+    for cfg in $CFGS; do
+        echo "  -> $cfg"
+        local dur=""; [ "$cfg" != "8C-proxy" ] && dur="$CONC_PD_MAXDUR"   # colo uncapped
+        MB5_P_ROUTING=session MB5_COLO_ROUTING=session \
+            REPLAY_MAX_INFLIGHT="$N" REPLAY_INTER_TURN_THINK_S="$THINK" REPLAY_NO_REALIZED_PREFIX=1 \
+            REPLAY_MAX_DURATION="$dur" \
+            CONFIGS="$cfg" REPS=1 TRACE="$trace" RUN_TAG="$tag" \
+            bash scripts/mb5_run_gpu.sh >/dev/null 2>&1 || echo "    [warn] ${tag}_${cfg} failed" >&2
+    done
+    local d="mb5_runs/${tag}_8C-proxy_rep1"
+    if [ -f "$d/replay_metrics.summary.json" ]; then
+        "$VPY" scripts/fig_agg.py --json "$d" 2>/dev/null \
+          | "$VPY" -c "import sys,json;r=json.load(sys.stdin);print(r[0].get('e2e_mean') if r else 'nan')"
+    else echo nan; fi
+}
+
+if [ -n "$ONLY_N" ]; then
+    echo "[conc32k] SMOKE N=$ONLY_N cfgs='$CFGS'"
+    t0=$(date +%s); m=$(run_N "$ONLY_N"); t1=$(date +%s)
+    echo "[conc32k] SMOKE N=$ONLY_N colo mean-E2E=${m}s wall=$(( t1 - t0 ))s; compare:"
+    "$VPY" scripts/fig_agg.py mb5_runs/conc32k_N${ONLY_N}_*_rep1 2>&1
+    exit 0
+fi
+
+if [ -n "$NLIST" ]; then NSEQ="$NLIST"; else NSEQ=$(seq "$NSTART" "$NSTEP" "$NMAX"); fi
+for N in $NSEQ; do
+    echo "[conc32k] === N=$N ==="
+    m=$(run_N "$N"); echo "[conc32k] N=$N colo mean-E2E=${m}s"
+    over=$("$VPY" -c "print(1 if float('${m}')>${SLO} else 0)" 2>/dev/null || echo 0)
+    [ "$over" = "1" ] && { echo "[conc32k] colo crossed SLO ${SLO}s at N=$N -> stop"; break; }
+done
+dirs=(); for d in mb5_runs/conc32k_N*_rep1; do [ -d "$d" ] && dirs+=("$d"); done
+"$VPY" scripts/fig_agg.py --json "${dirs[@]}" > analysis/mb5_pd_ablation/fig3_conc32k.json
+echo "[conc32k] done -> analysis/mb5_pd_ablation/fig3_conc32k.json (${#dirs[@]} dirs)"

microbench/fresh_setup/run_reuse_fixed.sh

@@ -0,0 +1,72 @@
+#!/usr/bin/env bash
+# Reuse axis, DONE RIGHT (controlled variable). Supersedes old fig1.
+#   Hold REAL (uncached) prefill work constant: --delta-len = U fixed.
+#   Vary only --prefix-len = C -> reuse = C/(C+U). Context grows with reuse but
+#   the tokens that must actually be prefilled each turn stays = U.
+# Old fig1 held input=8192 and sliced prefix out of it, so delta shrank 15x as
+# reuse rose -> confounded "more reuse" with "less prefill". This fixes that.
+#
+# Wiring matches the corrected MB5 stack (see memory project-mb5-pd-ablation-wiring):
+#   .venv_dash0, traces_synth/, CONFIG 8C-proxy + PD, MB5_P_ROUTING=session,
+#   N injected via REPLAY_MAX_INFLIGHT (closed loop) + REPLAY_INTER_TURN_THINK_S,
+#   REPLAY_NO_REALIZED_PREFIX=1 (reuse governed by hash_ids, required for this sweep).
+set -eo pipefail
+cd /home/admin/cpfs/wjh/agentic-kv-fresh
+export MB5_VENV="${MB5_VENV:-/home/admin/cpfs/wjh/agentic-kv-fresh/.venv_dash0}"
+VPY="$MB5_VENV/bin/python"
+
+DELTA="${DELTA:-2048}"        # fixed real prefill per turn (USER-CHOSEN)
+OL="${OL:-256}"
+N="${N:-8}"
+THINK="${THINK:-0.5}"
+TURNS="${TURNS:-8}"
+NSESS="${NSESS:-48}"          # number of sessions (closed-loop: arrival rate is
+                             # irrelevant, only the count matters; ~6 waves at N=8)
+PFXS="${PFXS:-512 2048 4096 8192 18432 38912}"   # reuse .20 .50 .67 .80 .90 .95
+CFGS="${CFGS:-8C-proxy 2P+6D 4P+4D 6P+2D}"
+REUSE_PD_MAXDUR="${REUSE_PD_MAXDUR:-500}"   # wall-deadline (s) for PD arms only (colo uncapped):
+                                            # bounds the collapse-drain that stalls high-reuse PD arms
+                                            # (un-run turns = failures, honest completion%). 0/empty = off.
+ONLY_PFX="${ONLY_PFX:-}"     # smoke a single prefix then exit
+
+run_point() {  # <pfx>
+    local pfx="$1"
+    local reuse; reuse=$(python3 -c "print(f'{$pfx/($pfx+$DELTA):.3f}')")
+    local tag="reuse_p${pfx}_d${DELTA}_o${OL}"   # _o${OL} so different output lens don't collide
+    local trace="traces_synth/${tag}.jsonl"
+    # Closed-loop: pass NSESS as qps with duration 1 so n_sessions = NSESS
+    # exactly (gen_regular: n_sessions = int(duration_s * session_qps)).
+    "$VPY" scripts/gen_synthetic_trace.py --out "$trace" --mode regular \
+        --qps "$NSESS" --duration-s 1 --turns "$TURNS" \
+        --prefix-len "$pfx" --delta-len "$DELTA" --output-len "$OL" --seed 42 >/dev/null
+    echo "[reuse] pfx=$pfx delta=$DELTA reuse=$reuse in=$((pfx+DELTA)) -> $trace"
+    for cfg in $CFGS; do
+        echo "  -> $cfg"
+        # Both routings set to session so BOTH colo (kv_both) and PD producers
+        # pin a session's turns to one instance and reuse its prefix cache — the
+        # fair cache-aware comparison. P_ROUTING is ignored by colo, COLO_ROUTING
+        # by PD, so setting both is harmless and symmetric.
+        local dur=""; [ "$cfg" != "8C-proxy" ] && dur="$REUSE_PD_MAXDUR"   # colo uncapped
+        MB5_P_ROUTING=session MB5_COLO_ROUTING=session \
+            REPLAY_MAX_INFLIGHT="$N" REPLAY_INTER_TURN_THINK_S="$THINK" \
+            REPLAY_NO_REALIZED_PREFIX=1 REPLAY_MAX_DURATION="$dur" \
+            CONFIGS="$cfg" REPS=1 TRACE="$trace" RUN_TAG="$tag" \
+            bash scripts/mb5_run_gpu.sh >/dev/null 2>&1 || echo "    [warn] $cfg failed" >&2
+    done
+}
+
+if [ -n "$ONLY_PFX" ]; then
+    echo "[reuse] SMOKE pfx=$ONLY_PFX cfgs='$CFGS'"
+    t0=$(date +%s); run_point "$ONLY_PFX"; t1=$(date +%s)
+    echo "[reuse] SMOKE done wall=$(( t1 - t0 ))s; compare:"
+    "$VPY" scripts/fig_agg.py mb5_runs/reuse_p${ONLY_PFX}_d${DELTA}_o${OL}_*_rep1
+    exit 0
+fi
+
+for pfx in $PFXS; do run_point "$pfx"; done
+# Aggregate ONLY this sweep's dirs (matched by delta+output) so the three
+# reuse figures (d2048/o256, d1024/o128, d2048/o128) never cross-contaminate.
+dirs=(); for d in mb5_runs/reuse_*_d${DELTA}_o${OL}_*_rep1; do [ -d "$d" ] && dirs+=("$d"); done
+OUTJSON="analysis/mb5_pd_ablation/fig1_reuse_d${DELTA}_o${OL}.json"
+"$VPY" scripts/fig_agg.py --json "${dirs[@]}" > "$OUTJSON"
+echo "[reuse] done -> $OUTJSON (${#dirs[@]} dirs)"