Update MEETING.md + PAPER_OUTLINE.md with connector_tax substrate validation

2026-05-27 trace-replay A/B/C (commit ef9e010) shows the kv_both substrate
is net positive on current codebase, not just neutral:
  - TTFT p90: 11.97s plain → 9.74s kv_both (−18.6%) → 7.58s with DR-fix (−36.6%)

This reverses the elastic_migration_v2 paper's +45% kv_both penalty claim
and removes the primary cause of the 4 prior migration reverts.

Reframes EAR Pillar 2 from "DEFERRED" to "PARTIAL" — substrate verified,
e2e strategy-layer validation (trigger thresholds + target selection in
the dispatch-coupling feedback loop) remains as the only open risk.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
2026-05-27 09:17:31 +08:00
parent ef9e0102ec
commit 18f1bd4240
2 changed files with 22 additions and 11 deletions

View File

@@ -63,9 +63,16 @@ APC 拉到 77-79%(接近上界),但 hotspot index 翻倍sticky 2.73、u
session load-balance 分配 host后续 turn sessionhost binding 路由
这就是当前 `unified` 算法hybrid LMetric + high-cache affinityAPC 79.4%达到上界 97%。
**Pillar 2 — Hot-triggered session migration实证待补**
**Pillar 2 — Hot-triggered session migrationend-to-end 实证待补substrate 已验证**
host `pending_prefill_tokens > T_hot`把整个 session KV 通过 mooncake `kv_connector` migrate 到更轻 instancesession binding 更新后续 turn 路由到新 host
> 🆕 **2026-05-27 数据**commit `ef9e010`):之前认为是 migration blocker 的 `kv_both` substrate overhead 已经不存在。在 8×TP1 trace replay 上 A/B/C 对比:
> - plain unified: TTFT p90 = 11.97s
> - unified + `kv_both`(未 DR-fix: 9.74s**18.6%** vs plain
> - unified + `kv_both` + DR-fix: 7.58s**36.6%** vs plain
>
> 即原 elastic_migration_v2 论文里 "+45% kv_both penalty" 已 obsolete当前 substrate 是 **net positive**connector mode 的 `delay_free_blocks=True` 在 93% intra-session-reuse trace 上把跨 turn cache hit 窗口拉长。Migration 之前 4 次 revert 的主因消失。
关键 design
- Target 选择用 **observable pending prefill tokens****不用** cost-model prediction实测 mooncake cost model 误差 10-21x绕过
- Per-session cooldown thrashing
@@ -83,6 +90,7 @@ APC 拉到 77-79%(接近上界),但 hotspot index 翻倍sticky 2.73、u
- Pillar 1 affinity routing 已实现并测过current `unified` 算法
- Dispatch coupling Little's Law 形式化推导
- `replayer/replay.py` patched 输出 `amplification`
- 🆕 **kv_both substrate validation**commit `ef9e010`trace replay A/B/C 证明 substrate 已经是 net positiveTTFT p90 18.6% / DR-fix 36.6% vs plain +45% penalty obsolete
### 🟢 不依赖 migration 可以现在做
@@ -91,17 +99,17 @@ APC 拉到 77-79%(接近上界),但 hotspot index 翻倍sticky 2.73、u
3. λ / skew / KV pool 三轴 sensitivity
4. Draft §1-§4 正文数据已齐
### 🚧 待 migration validation
### 🚧 待 migration end-to-end validation
- §4.3 migration mechanism `connector_tax` DR-fix 之上重测
- §4.3 migration mechanism e2e trigger + target selection 实验substrate 已通只缺策略层
- Full ablationmigration-only + both
- §5.6 migration microbench
### 风险
- Migration 之前 4 次尝试`6b255fa`, `e991960/5772149`, `cc6e562`, `4c583f2`都被 transfer overhead 吞掉而 revert
- 最近 DR-fix `build_connector_meta` slope +81 -0.7 μs/1k blocks**未在 trace replay 上验证**
- migration validation failpaper pivot "affinity-only is enough" —— 仍然能发强度降一档
- Migration 之前 4 次尝试`6b255fa`, `e991960/5772149`, `cc6e562`, `4c583f2`都被 transfer overhead 吞掉而 revert —— **该 overhead 已在 2026-05-27 验证不再存在**substrate net positive
- 仍未直接验证 e2e migration 策略层trigger + target 选择能在反馈环里产生正收益中间还有"决策错误 + cooldown thrashing"两类风险独立于 substrate
- 即便 migration e2e marginalaffinity-only pillar 的实证已经独立成立paper 至少有 strong-affinity storyline 可写
---