Gahow Wang
67fcec7933
cache_aware_proxy: add lmetric_decode_weight (decode-load penalty in the LMetric fallback score) and a v3 anti-hotspot recent-migration penalty (effective_load = num_req + recent-migration count over a sliding window), preventing back-to-back migration clustering. UNIFIED_ABLATION.md documents the A (overload_factor=1.3) + B' (decode-weight, max(num_req,1)) + RaceFix sweep: A+B'+RaceFix reaches TTFT p90 7770ms, beating v3 PD-sep migration by ~20%. Runners/analyzer for the b3 trace replay included. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
57 lines
1.7 KiB
Bash
57 lines
1.7 KiB
Bash
#!/usr/bin/env bash
|
|
# Single-policy trace replay for unified, with tunable overload-factor.
|
|
# Used to test direction A: does tightening affinity overflow improve unified?
|
|
#
|
|
# Usage:
|
|
# OVERLOAD_FACTOR=1.3 bash run_unified_ablation.sh
|
|
# OVERLOAD_FACTOR=1.0 bash run_unified_ablation.sh
|
|
#
|
|
# Output: $PROJ_DIR/outputs/unified_of${OF}_${DATE}/unified/
|
|
|
|
set -uo pipefail
|
|
|
|
PROJ_DIR="${PROJ_DIR:-/home/admin/cpfs/wjh/agentic-kv}"
|
|
TRACE="${TRACE:-$PROJ_DIR/traces/w600_r0.0015_st30.jsonl}"
|
|
OF="${OVERLOAD_FACTOR:-1.3}"
|
|
LMW="${LMETRIC_DECODE_WEIGHT:-0.0}"
|
|
TAG_DEFAULT="of${OF/./}"
|
|
if [ "$(printf '%s' "$LMW" | grep -v '^0\.\?0*$' || true)" != "" ]; then
|
|
TAG_DEFAULT="${TAG_DEFAULT}_lmw${LMW/./}"
|
|
fi
|
|
TAG="${TAG:-$TAG_DEFAULT}"
|
|
DATE="$(date +%Y%m%d_%H%M)"
|
|
OUTROOT="${OUTROOT:-$PROJ_DIR/outputs/unified_${TAG}_${DATE}}"
|
|
|
|
mkdir -p "$OUTROOT"
|
|
echo "=== unified ablation: overload_factor=$OF ==="
|
|
echo "Trace : $TRACE"
|
|
echo "Out : $OUTROOT"
|
|
echo ""
|
|
|
|
cleanup() {
|
|
pkill -9 -f cache_aware_proxy 2>/dev/null || true
|
|
pkill -9 -f "vllm serve" 2>/dev/null || true
|
|
pkill -9 -f "EngineCore" 2>/dev/null || true
|
|
sleep 3
|
|
}
|
|
trap cleanup EXIT
|
|
cleanup
|
|
|
|
cfg_dir="$OUTROOT/unified"
|
|
mkdir -p "$cfg_dir"
|
|
|
|
export EXTRA_PROXY_ARGS="--overload-factor $OF --lmetric-decode-weight $LMW"
|
|
|
|
echo ""
|
|
echo "====== unified ; overload_factor=$OF lmetric_decode_weight=$LMW ======"
|
|
bash "$PROJ_DIR/scripts/b3_isolated_policy.sh" "unified" "$TRACE" "$cfg_dir" \
|
|
2>&1 | tee "$cfg_dir/orchestrator.log" | tail -30
|
|
|
|
pkill -9 -f cache_aware_proxy 2>/dev/null || true
|
|
pkill -9 -f "vllm serve" 2>/dev/null || true
|
|
pkill -9 -f "EngineCore" 2>/dev/null || true
|
|
sleep 5
|
|
|
|
echo ""
|
|
echo "Done. Artifacts: $OUTROOT/unified/metrics.jsonl"
|