sskj/experiments/dsv4_h200_vllm_dspark_vs_default/run_bench.sh

#!/usr/bin/env bash
# vLLM+DSpark vs vLLM default controlled comparison on H200.
set -Eeuo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
EXPERIMENT_NAME="$(basename "$SCRIPT_DIR")"

# shellcheck source=/dev/null
source "${SCRIPT_DIR}/../../scripts/common/lib.sh"
# shellcheck source=/dev/null
source "${SCRIPT_DIR}/../../scripts/common/platform.sh"
# shellcheck source=/dev/null
source "${SCRIPT_DIR}/config.env"

RUN_ID="${RUN_ID:-$(date '+%Y%m%d-%H%M%S')}"
RESULT_BASE="${SCRIPT_DIR}/results"

log_dir_global="${RESULT_BASE}/${RUN_ID}/logs"
mkdir -p "$log_dir_global"
log_init "${log_dir_global}/orchestrator.log"

log "experiment=${EXPERIMENT_NAME}"
log "run_id=${RUN_ID}"
log "platform=${PLATFORM}"
log "hardware=${HARDWARE}"
log "dspark_model=${DSPARK_MODEL_PATH}"
log "default_model=${DEFAULT_MODEL_PATH}"

# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------

is_server_healthy() {
  local port="$1"
  curl --fail --silent --show-error --max-time 5 "http://127.0.0.1:${port}/health" >/dev/null 2>&1
}

stop_server() {
  local backend="$1"
  local pid_file="/data/user1/yy/${EXPERIMENT_NAME}_${backend}.pid"
  if [[ -f "$pid_file" ]]; then
    local pid
    pid="$(cat "$pid_file")"
    if kill -0 "$pid" 2>/dev/null; then
      log "stopping ${backend} server pid=${pid}"
      kill "$pid" 2>/dev/null || true
      sleep 5
      kill -9 "$pid" 2>/dev/null || true
    fi
    rm -f "$pid_file"
  fi
  sleep 2
}

start_server() {
  local backend="$1"
  local start_script port
  if [[ "$backend" == "dspark" ]]; then
    start_script="${DSPARK_START_SCRIPT}"
    port="$DSPARK_PORT"
  else
    start_script="${DEFAULT_START_SCRIPT}"
    port="$DEFAULT_PORT"
  fi

  log "starting ${backend} server with ${start_script}"
  bash "${start_script}" >> "${log_dir_global}/${backend}.server.outer.log" 2>&1

  if ! is_server_healthy "$port"; then
    log "error: ${backend} server failed to become healthy"
    return 1
  fi
  log "${backend} server is healthy on port ${port}"
}

run_warmup() {
  local backend="$1"
  local port
  if [[ "$backend" == "dspark" ]]; then
    port="$DSPARK_PORT"
  else
    port="$DEFAULT_PORT"
  fi

  log "warming up ${backend} (input=4000, output=512, num=2)"
  "${VENV_CLIENT}/bin/python" -m sglang.bench_serving \
    --backend vllm \
    --host 127.0.0.1 \
    --port "$port" \
    --dataset-name random \
    --random-input-len 4000 \
    --random-output-len 512 \
    --num-prompts 2 \
    --max-concurrency 1 \
    --request-rate 10000 \
    --output-file /tmp/${EXPERIMENT_NAME}_${backend}_warmup.jsonl \
    --output-details \
    > "${log_dir_global}/${backend}.warmup.log" 2>&1 || true
  log "warmup for ${backend} completed"
}

run_benchmark() {
  local backend="$1"
  local result_root="${RESULT_BASE}/${RUN_ID}/${backend}"
  local raw_dir="${result_root}/raw_outputs"
  local bench_log_dir="${result_root}/logs"

  mkdir -p "$raw_dir" "$bench_log_dir"

  local port
  if [[ "$backend" == "dspark" ]]; then
    port="$DSPARK_PORT"
  else
    port="$DEFAULT_PORT"
  fi

  log "===== ${backend} BENCHMARK START ====="

  stop_server "$backend"
  start_server "$backend"
  run_warmup "$backend"

  for scenario in "${SCENARIOS[@]}"; do
    read -r concurrency input_len output_len num_prompts <<< "$scenario"
    output_file="${raw_dir}/${backend}_$(date '+%m%d')_${concurrency}_${input_len}_${output_len}.jsonl"
    detail_log="${bench_log_dir}/${backend}_c${concurrency}_i${input_len}_o${output_len}.log"

    log "running ${backend} scenario: c=${concurrency} i=${input_len} o=${output_len} n=${num_prompts}"

    "${VENV_CLIENT}/bin/python" -m sglang.bench_serving \
      --backend vllm \
      --host 127.0.0.1 \
      --port "$port" \
      --dataset-name random \
      --random-input-len "$input_len" \
      --random-output-len "$output_len" \
      --num-prompts "$num_prompts" \
      --max-concurrency "$concurrency" \
      --request-rate 10000 \
      --output-file "$output_file" \
      --output-details \
      > "$detail_log" 2>&1 || {
        log "ERROR: ${backend} scenario c=${concurrency} i=${input_len} o=${output_len} failed; see ${detail_log}"
        continue
      }

    log "finished ${backend} scenario: output=${output_file}"
  done

  stop_server "$backend"
  log "===== ${backend} BENCHMARK DONE ====="
}

parse_backend() {
  local backend="$1"
  local result_root="${RESULT_BASE}/${RUN_ID}/${backend}"
  log "parsing ${backend} results in ${result_root}"
  "${VENV_CLIENT}/bin/python" "${SCRIPT_DIR}/parse_backend.py" "$result_root" --backend "$backend" \
    >> "${result_root}/logs/parse.log" 2>&1 || {
      log "WARNING: parser failed for ${backend}; see ${result_root}/logs/parse.log"
    }
}

write_backend_metadata() {
  local backend="$1"
  local result_root="${RESULT_BASE}/${RUN_ID}/${backend}"
  ensure_result_root "$result_root"
  local meta_json="${result_root}/results.json"

  local model_path env_path engine
  if [[ "$backend" == "dspark" ]]; then
    model_path="$DSPARK_MODEL_PATH"
    env_path="$VENV_VLLM_DSPARK"
    engine="vllm-dspark"
  else
    model_path="$DEFAULT_MODEL_PATH"
    env_path="$VENV_VLLM"
    engine="vllm-default"
  fi

  write_metadata_json \
    "$meta_json" \
    "${EXPERIMENT_NAME}_${backend}" \
    "$RUN_ID" \
    "$model_path" \
    "vllm" \
    "$engine" \
    "$HARDWARE" \
    "$ACCELERATOR" \
    "$CHIP" \
    "experiments/${EXPERIMENT_NAME}/run_bench.sh" \
    "$env_path" \
    "H200 ${engine} TP=8 benchmark for TTFT comparison"

  # Embed config.
  "${VENV_CLIENT}/bin/python" - "$meta_json" "$backend" <<'PY'
import json
import sys

path, backend = sys.argv[1], sys.argv[2]
with open(path, "r", encoding="utf-8") as f:
    data = json.load(f)

data["config"] = {
    "tp": 8,
    "cuda_visible_devices": "0,1,2,3,4,5,6,7",
    "max_model_len": 32768,
    "max_num_seqs": 256,
    "backend": backend,
}
with open(path, "w", encoding="utf-8") as f:
    json.dump(data, f, indent=2, ensure_ascii=False)
PY
}

# ---------------------------------------------------------------------------
# Main
# ---------------------------------------------------------------------------

# Cleanup.
stop_server dspark
stop_server default

write_backend_metadata dspark
write_backend_metadata default

# Run DSpark.
run_benchmark dspark
parse_backend dspark

# Run default vLLM.
run_benchmark default
parse_backend default

# Generate comparison.
log "generating comparison report"
"${VENV_CLIENT}/bin/python" "${SCRIPT_DIR}/compare.py" \
  --dspark "${RESULT_BASE}/${RUN_ID}/dspark" \
  --default "${RESULT_BASE}/${RUN_ID}/default" \
  --output "${RESULT_BASE}/${RUN_ID}/comparison.md" \
  >> "${log_dir_global}/compare.log" 2>&1 || {
    log "WARNING: comparison script failed; see ${log_dir_global}/compare.log"
  }

log "all results saved to ${RESULT_BASE}/${RUN_ID}"