Add full latency grid (mean/p50/p90/p99 × TTFT/TPOT/E2E) as f6 companion

The headline f6_e2e_latency_bars only shows p90, hiding three regimes:
  - mean: unified dominates (3.3s TTFT, 7.0s E2E vs sticky 5.6s / 12.1s)
  - p50: sticky and unified are tied on first-turn TTFT (0.5s each) —
    sticky's first turn of each session is free, after which queues
    accumulate. Unified beats sticky everywhere else.
  - p99: tail amplification reveals unified's biggest gap —
    TTFT 42.3s vs sticky 74.1s; E2E 68.8s vs sticky 139.7s.

The 12-panel figure is the honest full picture; the 3-panel headline
stays for slide-friendly summary.

- analysis/characterization/window_1_results/raw_stats/{policy}.json:
  cached ttft/tpot/e2e {mean,p50,p90,p99} pulled from dash0
  /home/admin/cpfs/wjh/agentic-kv/outputs/b3_sweep_20260525_095043/
  (b3_policy_comparison.json doesn't record mean, only percentiles).
- analysis/characterization/render_window1_figures.py:
  new fig_b3_latency_full_grid renders the 4×3 grid from the cache.
- figs/f6_e2e_latency_full_grid.png: 12-panel companion.
- PAPER_OUTLINE.md §5.2: both figures embedded; main table column
  renamed from "Hotspot idx" to "Worker p90 (median / max)" to match
  the new metric convention.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
2026-05-27 11:15:18 +08:00
parent 5e6e98aee7
commit 922d79ac95
7 changed files with 145 additions and 4 deletions

View File

@@ -241,13 +241,17 @@ KV transfer 发生在触发该 migration 的 request 的 critical path 上,但
### §5.2 End-to-end Performance
**Figure 6: End-to-end performance** (PARTIAL PD-disagg )
**Figure 6 (headline, p90 only)** (PARTIAL PD-disagg )
![F6 E2E latency bars — 5 policies](figs/f6_e2e_latency_bars.png)
![F6 E2E latency bars — 4 policies, p90 only](figs/f6_e2e_latency_bars.png)
> **🚧 TBD (NEW DATA)**:上图缺 `static PD-disagg` 那一列EAR 列也是 TBD需 migration validation。要再补一张同样格式但包含全 6 个 baseline 的图。
**Figure 6 full (mean / p50 / p90 / p99 × TTFT / TPOT / E2E)** 数据完备
| Scheduler | TTFT p50 | TTFT p90 | TPOT p90 | APC | Hotspot idx | Wall-clock factor |
![F6 full latency grid — 4 percentiles × 3 metrics](figs/f6_e2e_latency_full_grid.png)
> **🚧 TBD (NEW DATA)**:两张图都缺 `static PD-disagg` 那一列EAR 列也是 TBD需 migration validation。要再补同样格式但包含全 6 个 baseline 的版本。Headline 图用 p90 一行进 main paper完整 grid 可进附录或 supplementary。
| Scheduler | TTFT p50 | TTFT p90 | TPOT p90 | APC | Worker p90 (median / max) | Wall-clock factor |
|---|---|---|---|---|---|---|
| load-balance | TBD | TBD | TBD | TBD | TBD | TBD |
| LMetric | TBD | TBD | TBD | 56.9% | 6.53 | ~8x |