P2: all routing policies read real state via eff_ accessors + ablation harness
InstanceState.eff_{num_requests,pending_prefill,ongoing_decode,ongoing_tokens}
= max(shadow, real) when feed fresh (fixes 30s-stale under-count, keeps
in-flight RaceFix), plus real-only r_max_prefill_remaining / r_kv_used_frac.
Wired into load_only, lmetric, sticky, unified(_kv_both), unified_v3, and
snapshot logging. Feed off => identical to before. run_v3_trace.sh gains ES=1
toggle (always deploys enhanced proxy); run_ablation_es.sh runs each config
ES0-vs-ES1 to test whether real state changes policy performance/ranking.
All unit-tested without GPU.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
@@ -26,6 +26,9 @@ MC_FILE="$VLLM_ROOT/distributed/kv_transfer/kv_connector/v1/mooncake/mooncake_co
|
||||
PROXY_FILE="$PROJ_DIR/scripts/cache_aware_proxy.py"
|
||||
LW_CONN="${LW_CONN:-/tmp/mooncake_connector.LAYERWISE.py}"
|
||||
WM_PROXY="${WM_PROXY:-/tmp/cache_aware_proxy.WRITEMODE.py}"
|
||||
ES_INSTR="$PROJ_DIR/microbench/connector_tax/layerwise/instrument_engine_state.py"
|
||||
ES="${ES:-0}" # 1 = enable real engine-state feed (P2)
|
||||
ES_DIR="/dev/shm/agentic_engine_state_${TAG}"
|
||||
|
||||
mkdir -p "$OUTROOT"
|
||||
cfg_dir="$OUTROOT/unified_v3"; mkdir -p "$cfg_dir"
|
||||
@@ -38,7 +41,9 @@ restore() {
|
||||
cp -f "$MC_FILE.ORIG_BACKUP" "$MC_FILE"
|
||||
cp -f "$PROXY_FILE.ORIG_BACKUP" "$PROXY_FILE"
|
||||
"$PYTHON" "$DR_FIX" --revert --vllm-root "$VLLM_ROOT" 2>/dev/null || true
|
||||
echo "[restore] connector+proxy reset to ORIG, DR-fix reverted"
|
||||
"$PYTHON" "$ES_INSTR" --revert --venv "$VENV" 2>/dev/null || true
|
||||
rm -rf "$ES_DIR" 2>/dev/null || true
|
||||
echo "[restore] connector+proxy reset to ORIG, DR-fix + ES-patch reverted"
|
||||
}
|
||||
cleanup() {
|
||||
pkill -9 -f cache_aware_proxy 2>/dev/null || true
|
||||
@@ -51,21 +56,32 @@ trap cleanup EXIT
|
||||
pkill -9 -f "vllm serve" 2>/dev/null || true; sleep 3
|
||||
restore # start from clean
|
||||
|
||||
echo "=== v3 trace ($MODE) -> $OUTROOT ==="
|
||||
echo "=== v3 trace (mode=$MODE es=$ES tag=$TAG) -> $OUTROOT ==="
|
||||
# Always deploy the enhanced proxy (write-mode + engine-state, both env/flag
|
||||
# gated; with feed off + write-mode off it behaves identically to stock).
|
||||
cp -f "$WM_PROXY" "$PROXY_FILE"
|
||||
if [ "$MODE" = "layerwise" ]; then
|
||||
cp -f "$LW_CONN" "$MC_FILE"
|
||||
cp -f "$WM_PROXY" "$PROXY_FILE"
|
||||
"$PYTHON" -c "import ast; ast.parse(open('$MC_FILE').read()); ast.parse(open('$PROXY_FILE').read()); print('[deploy] LAYERWISE conn + WRITEMODE proxy AST OK')" || exit 1
|
||||
export MOONCAKE_LAYERWISE=1
|
||||
export EAR_WRITE_MODE=1
|
||||
fi
|
||||
"$PYTHON" -c "import ast; ast.parse(open('$MC_FILE').read()); ast.parse(open('$PROXY_FILE').read()); print('[deploy] proxy + connector AST OK')" || exit 1
|
||||
|
||||
PROXY_ES_ARG=""
|
||||
if [ "$ES" = "1" ]; then
|
||||
echo "[ES] apply engine-state patch + enable feed at $ES_DIR"
|
||||
"$PYTHON" "$ES_INSTR" --apply --venv "$VENV"
|
||||
mkdir -p "$ES_DIR"
|
||||
export AGENTIC_ENGINE_STATE_URI="file://$ES_DIR"
|
||||
PROXY_ES_ARG="--engine-state-uri file://$ES_DIR"
|
||||
fi
|
||||
|
||||
echo "[DR-fix] apply"
|
||||
"$PYTHON" "$DR_FIX" --apply --vllm-root "$VLLM_ROOT"
|
||||
export VLLM_MOONCAKE_DISABLE_DIRECT_READ_SYNC=1
|
||||
|
||||
echo "[run] $POLICY AB=[$AB_FLAGS] (MOONCAKE_LAYERWISE=${MOONCAKE_LAYERWISE:-0} EAR_WRITE_MODE=${EAR_WRITE_MODE:-0})"
|
||||
EXTRA_PROXY_ARGS="$AB_FLAGS" bash "$PROJ_DIR/scripts/b3_isolated_policy.sh" "$POLICY" "$TRACE" "$cfg_dir" \
|
||||
EXTRA_PROXY_ARGS="$AB_FLAGS $PROXY_ES_ARG" bash "$PROJ_DIR/scripts/b3_isolated_policy.sh" "$POLICY" "$TRACE" "$cfg_dir" \
|
||||
2>&1 | tee "$cfg_dir/orchestrator.log" | tail -20
|
||||
|
||||
pkill -9 -f cache_aware_proxy 2>/dev/null || true
|
||||
|
||||
Reference in New Issue
Block a user