Two bugs caught by 8C smoke:
mb5_launch.sh
${env_bp_arg} expanded as a literal command line prefix doesn't work
when env_bp_arg is itself a variable — bash only treats VAR=val as
an env assignment if it sees the literal in the parsed command, not
after expansion. Fix: always export VLLM_MOONCAKE_BOOTSTRAP_PORT as
a literal, defaulting to 9999 when caller passed no port (consumer
mode ignores the var so the placeholder is harmless).
mb5_run.sh
replayer's actual CLI flags are --trace / --output / --endpoint /
--model, not the --*-path / --*-name variants I had. Plus dash1
has no `bc`; compute wall_clock_s via python instead.
Both fixed; 8C smoke (CONFIG=8C REPS=1 REQUEST_LIMIT=20) now runs
end-to-end in ~30 s:
- 8 vLLM kv_both instances on GPU 0-7 come up
- replayer round-robins 20 reqs across them
- MB5 instrumentation captures 8 snapshot files (one per EngineCore
PID), ranging 7-139 snapshots each = ~10 Hz throttle works
- plot_kv_pool_timeline.py renders the stacked-area + queue-depth
chart cleanly (figs/mb5_smoke/*.png)
Pipeline validated. Ready for the real PD-ratio sweep.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
125 lines
4.5 KiB
Bash
Executable File
125 lines
4.5 KiB
Bash
Executable File
#!/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: $(date +%Y%m%d_%H%M%S))
|
||
# REQUEST_LIMIT : optional, cap replay requests (default: none)
|
||
|
||
set -eo pipefail
|
||
|
||
FRESH_ROOT="/home/admin/cpfs/wjh/agentic-kv-fresh"
|
||
VENV="${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 "${replay_out}")"
|
||
local t0
|
||
t0=$(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${rep}_replay.log"
|
||
bash "${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}" > "${rundir}/wall_clock_s.txt"
|
||
|
||
# Stop launch (cleans up vllm + proxy; reverts patch on last call)
|
||
CONFIG="${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}"
|