#!/usr/bin/env bash
# Single vLLM warmup, multiple smoke-test iterations under varying load.
#
# Each iteration uses a distinct --prefix-base to avoid prefix-cache pollution
# from prior iterations. We sweep noise levels 0, 8, 32, 64 to see at which
# point the migration cache becomes invisible to the follow-up.

set -uo pipefail

PROJ_DIR="${PROJ_DIR:-/home/admin/cpfs/wjh/agentic-kv}"
MODEL="${MODEL:-/home/admin/cpfs/wjh/models/Qwen/Qwen3-Coder-30B-A3B-Instruct}"
VENV="$PROJ_DIR/.venv/bin"
LOGS_DIR="${LOGS_DIR:-$PROJ_DIR/outputs/smoke_sweep_$(date +%Y%m%d_%H%M%S)}"
mkdir -p "$LOGS_DIR"

cleanup() {
    echo "[sweep] cleaning up vLLM..."
    pkill -9 -f "vllm serve" 2>/dev/null || true
    pkill -9 -f "EngineCore" 2>/dev/null || true
    sleep 2
}
trap cleanup EXIT
cleanup

echo "[sweep] starting 2 vLLM kv_both on GPU 0,1"
for i in 0 1; do
    port=$((8000 + i))
    bp=$((8998 + i))
    master=$((29500 + i))
    PYTHONHASHSEED=42 \
    VLLM_MOONCAKE_BOOTSTRAP_PORT=$bp \
    CUDA_VISIBLE_DEVICES=$i \
    MASTER_PORT=$master \
    nohup "$VENV/vllm" serve "$MODEL" \
        --host 0.0.0.0 --port "$port" \
        --tensor-parallel-size 1 \
        --trust-remote-code --enable-prefix-caching \
        --dtype auto --gpu-memory-utilization 0.9 \
        --max-model-len 200000 \
        --kv-transfer-config '{"kv_connector":"MooncakeConnector","kv_role":"kv_both"}' \
        --enable-prompt-tokens-details \
        > "$LOGS_DIR/vllm_inst_${i}_gpu${i}.log" 2>&1 &
    disown
    sleep 2
done

echo "[sweep] waiting for health ..."
for port in 8000 8001; do
    tries=0
    while ! curl -sf "http://127.0.0.1:$port/health" >/dev/null 2>&1; do
        tries=$((tries+1))
        if [ $tries -gt 180 ]; then echo "[sweep] FATAL: $port not ready"; exit 1; fi
        sleep 2
    done
    echo "  port=$port ready"
done

base=100
for noise in 0 8 32 64 128; do
    echo ""
    echo "============================================"
    echo "[sweep] iteration noise=$noise prefix_base=$base"
    echo "============================================"
    "$VENV/python" "$PROJ_DIR/microbench/connector_tax/cache_sweep/smoke_test_migrate_cache.py" \
        --src-port 8000 --dst-port 8001 \
        --src-bp 8998 --dst-bp 8999 \
        --noise-reqs "$noise" \
        --prefix-base "$base" \
        2>&1 | tee "$LOGS_DIR/iter_noise${noise}.log" | tail -25
    base=$((base + 100000))
done

echo ""
echo "[sweep] all iterations done; logs in $LOGS_DIR"