[Feature][Log]console metrics log for pd disaggregation

[CSWYF3634076]

Motivation

Fix the issue where node D prints prefill logs in the PD disaggregation

Modifications

add console metrics log for pd disaggregation

Usage or Command

no

Accuracy Tests

no

Checklist

• Add at least a tag in the PR title.
  • Tag list: [[FDConfig],[APIServer],[Engine], [Scheduler], [PD Disaggregation], [Executor], [Graph Optimization], [Speculative Decoding], [RL], [Models], [Quantization], [Loader], [OP], [KVCache], [DataProcessor], [BugFix], [Docs], [CI], [Optimization], [Feature], [Benchmark], [Others], [XPU], [HPU], [GCU], [DCU], [Iluvatar], [Metax]]
  • You can add new tags based on the PR content, but the semantics must be clear.
• Format your code, run pre-commit before commit.
• Add unit tests. Please write the reason in this PR if no unit tests.
• Provide accuracy results.
• If the current PR is submitting to the release branch, make sure the PR has been submitted to the develop branch, then cherry-pick it to the release branch with the [Cherry-Pick] PR tag.

[PaddlePaddle-bot]

🤖 Paddle-CI-Agent | pr_review | 2026-05-18 16:56:42

📋 Review 摘要

PR 概述：修复 PD 分离场景下 Decode 节点控制台日志误打 "Prefill batch" 的问题，新增 log_decode_bootstrap_batch 方法，并在两类日志中统一携带 splitwise_role 字段
变更范围：fastdeploy/engine/sched/（scheduler_metrics_logger、resource_manager_v1）、fastdeploy/engine/common_engine.py
影响面 Tag：[PD Disaggregation] [Engine] [Scheduler]

问题

级别	文件	概述
📝 PR 规范	—	标题包含非官方 Tag [Log]，且 [Feature] 与 Motivation 中描述的"修复问题"语义不符
❓ 疑问	—	_log_console_scheduler_metrics 仅在 resource_manager_v1.py 中修改，是否存在 v0 或其他版本 ResourceManager 含相同逻辑未同步

📝 PR 规范检查

标题 [Feature][Log]console metrics log for pd disaggregation 存在两处问题：

1. [Log] 不在官方 Tag 列表中；与已有的 [PD Disaggregation] 官方 Tag 语义高度重叠，建议替换为官方 Tag
2. Motivation 描述的是"修复 Decode 节点打印错误日志"的问题，使用 [Feature] 不如 [BugFix] 准确

标题建议（可直接复制）：

• [BugFix][PD Disaggregation] Fix decode node printing prefill logs in console metrics

PR 描述结构完整，各 section 均有内容，无需改动。

总体评价

实现简洁清晰：通过 splitwise_role 路由日志函数，并以 _log_prefill_like_batch 内部方法消除重复代码，逻辑正确、单测覆盖充分。建议确认是否有其他版本 ResourceManager（如 v0）需同步相同修复。

[PaddlePaddle-bot]

🤖 Paddle-CI-Agent | ci_status_monitor | 2026-05-18 19:59:15

CI报告基于以下代码生成（30分钟更新一次）:

• PR commit: 60d522f
• Merge base: 12c6ae0 (branch: develop)
• 查看完整 Diff
• CI 详情

---

1 任务总览

⏳ Required 任务进行中：1 个 Required 任务仍在运行，请等待完成后确认合并。

总执行（rerun次数）	总任务	✅ 通过	❌ 失败	⏳ 运行中	⏸️ 等待中	跳过
35(0)	35	33	1	1	0	0

2 任务状态汇总

2.1 Required任务 : 9/10 通过

必选任务阻塞合并，失败需优先处理。

状态	任务	耗时	根因	修复建议	日志	重跑
⏳	xpu_4cards_case_test / run_xpu_4cards_cases	-	运行中	-	Job	-
✅	其余 9 个必选任务通过	-	-	-	-	-

2.2 可选任务 — 24/25 通过

可选任务不阻塞合并，失败仅供参考。

状态	任务	耗时	日志	重跑
❌	Run iluvatar Tests / run_iluvatar_cases	17m40s	Job	-
✅	其余 24 个可选任务通过	-	-	-

---

3 失败详情（仅 required）

无

[codecov-commenter]

Codecov Report

❌ Patch coverage is 90.00000% with 1 line in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@12c6ae0). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
fastdeploy/engine/sched/resource_manager_v1.py	66.66%	0 Missing and 1 partial ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #7843   +/-   ##
==========================================
  Coverage           ?   63.38%           
==========================================
  Files              ?      462           
  Lines              ?    64311           
  Branches           ?     9858           
==========================================
  Hits               ?    40762           
  Misses             ?    20779           
  Partials           ?     2770           

Flag	Coverage Δ
GPU	72.51% <90.00%> (?)
XPU	7.13% <40.00%> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[paddle-bot]

Thanks for your contribution!

[gongshaotian]

LGTM