Files
agentic-pd-hybrid/scripts/sweep_e4_pressured.sh
Claude Code Agent f6d6dc01ea feat(cli): per-role --mem-fraction-static + use in E4-pressured
E4-v1 / v2 / pressured-v1 all failed to fire admission rejections in
this workload because the default 0.6 mem-fraction-static gives
288K-token kv_pool per decoder, more than enough to absorb the
50-session trace even at concurrency=32.

This commit adds:
  --decode-mem-fraction-static  (overrides per-decode SGLang arg)
  --prefill-mem-fraction-static (symmetric for completeness)

Plumbed via topology.{decode,prefill}_extra_server_args. The
pressured sweep now uses --decode-mem-fraction-static 0.4 which
shrinks decoder kv_pool to ~192K tokens — should force enough
admission rejections to actually exercise the D→P snapshot path.
2026-05-13 10:43:26 +08:00

91 lines
3.3 KiB
Bash
Executable File

#!/usr/bin/env bash
# E4-pressured — same as E4 but tuned to force admission rejections so the
# D→P snapshot fast-path actually fires.
#
# Key delta vs sweep_e4_kvc_v2_d_to_p_sync.sh:
# --kvcache-migration-reject-threshold 1 (was 3)
# After ONE rejection the policy migrates the session to a different
# D, which in turn triggers _invoke_kvcache_seeded_router → D→P sync.
# --decode-mem-fraction-static 0.4
# Plumbed through cli.py → topology.decode_extra_server_args →
# launcher. Shrinks per-decode KV pool, forcing admit_direct_append
# to reject more often.
#
# Hypotheses (same as docs/E4_PROTOCOL_ZH.md but in a stressed regime):
# H1' E4-pressured TTFT p99 ≤ E1 TTFT p99
# H2' D→P snapshot succeeds for ≥ 20% of reseed-triggering requests
# H3' D→P-pushed-then-cache-hit reduces re-prefill segment of reseed
# path TTFT measurably
set -euo pipefail
cd "$(dirname "$0")/.."
if [ -z "${CUDA_HOME:-}" ]; then
echo "ERROR: CUDA_HOME not set. Source scripts/setup_env.sh first." >&2
exit 1
fi
MODEL=${MODEL:-/mnt/models/Qwen/Qwen3-30B-A3B-Instruct-2507}
TRACE=${TRACE:-outputs/inferact_50sess.jsonl}
OUTPUT=${OUTPUT:-outputs/e4p_kvc_v2_d_to_p_sync_pressured_50sess}
IB_DEVICE=${IB_DEVICE:-mlx5_60}
LOAD_FLOOR_BONUS=${LOAD_FLOOR_BONUS:-200}
REJECT_THRESHOLD=${REJECT_THRESHOLD:-1}
MEM_FRACTION=${MEM_FRACTION:-0.5}
if [ ! -f "$TRACE" ]; then
echo "ERROR: trace not found at $TRACE" >&2
exit 1
fi
mkdir -p "$OUTPUT"
LOG="$OUTPUT/sweep.log"
log() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] $*" | tee -a "$LOG"; }
log "=== E4-pressured: KVC v2 + RDMA + load-floor K=$LOAD_FLOOR_BONUS + D→P sync + reject_threshold=$REJECT_THRESHOLD + mem_fraction=$MEM_FRACTION ==="
log "MODEL=$MODEL"
log "TRACE=$TRACE ($(wc -l < $TRACE) requests)"
log "OUTPUT=$OUTPUT"
label=e4p_kvc_v2_d_to_p_sync_run1
log "=== [E4p] $label starting ==="
uv run --no-sync python -m agentic_pd_hybrid.cli benchmark-live \
--trace "$TRACE" \
--output-root "$OUTPUT" \
--mechanism kvcache-centric \
--policy kv-aware \
--model-path "$MODEL" \
--prefill-workers 1 --decode-workers 3 \
--prefill-tp-size 1 --decode-tp-size 1 \
--prefill-gpu-ids 0 --decode-gpu-ids 1,2,3 \
--transfer-backend mooncake \
--force-rdma --ib-device "$IB_DEVICE" \
--gpu-budget 4 \
--time-scale 1 \
--session-sample-rate 1.0 \
--target-duration-s 100000 \
--concurrency-limit 32 \
--timeout-s 1800 \
--request-timeout-s 300 \
--kvcache-admission-mode worker \
--kvcache-seed-min-turn-id 1 \
--kvcache-seed-max-inflight-decode -1 \
--kvcache-prefill-backup-policy release-after-transfer \
--kvcache-prefill-priority-eviction \
--kvcache-migration-reject-threshold "$REJECT_THRESHOLD" \
--kvcache-direct-max-uncached-tokens 8192 \
--kvcache-load-floor-bonus "$LOAD_FLOOR_BONUS" \
--decode-mem-fraction-static "${DECODE_MEM_FRAC:-0.4}" \
--enable-d-to-p-sync 2>&1 | tee -a "$LOG"
run_dir=$(ls -td "$OUTPUT"/kvcache-centric-*/ 2>/dev/null | head -1)
log "=== [E4p] $label COMPLETED, artifacts at $run_dir ==="
if [ -f "$run_dir/request-metrics.jsonl.summary.json" ]; then
cp "$run_dir/request-metrics.jsonl.summary.json" "$OUTPUT/${label}_summary.json"
cp "$run_dir/request-metrics.jsonl" "$OUTPUT/${label}_metrics.jsonl"
log "=== summary saved to $OUTPUT/${label}_summary.json ==="
fi