-
-
Notifications
You must be signed in to change notification settings - Fork 80.7k
[Bug] v2026.5.22 启动后 Gateway CPU 持续 100%+，导致请求延迟飙升 50-100 倍 #86512
Copy link
Copy link
Closed
Labels
P1High-priority user-facing bug, regression, or broken workflow.High-priority user-facing bug, regression, or broken workflow.clawsweeper:linked-pr-openClawSweeper found an open linked pull request for this issue.ClawSweeper found an open linked pull request for this issue.clawsweeper:needs-live-reproClawSweeper needs live local, crabbox, or manual validation to confirm this issue.ClawSweeper needs live local, crabbox, or manual validation to confirm this issue.clawsweeper:needs-maintainer-reviewClawSweeper marked this issue as needing maintainer review before automation.ClawSweeper marked this issue as needing maintainer review before automation.clawsweeper:needs-product-decisionClawSweeper marked this issue as needing a product or behavior decision.ClawSweeper marked this issue as needing a product or behavior decision.clawsweeper:no-new-fix-prClawSweeper does not recommend queueing a new automated fix PR for this issue.ClawSweeper does not recommend queueing a new automated fix PR for this issue.impact:auth-providerAuth, provider routing, model choice, or SecretRef resolution may break.Auth, provider routing, model choice, or SecretRef resolution may break.impact:crash-loopCrash, hang, restart loop, or process-level availability failure.Crash, hang, restart loop, or process-level availability failure.issue-rating: 🐚 platinum hermitGood issue quality with a plausible reproduction path needing some confirmation.Good issue quality with a plausible reproduction path needing some confirmation.staleMarked as stale due to inactivityMarked as stale due to inactivity
Description
Metadata
Metadata
Assignees
Labels
P1High-priority user-facing bug, regression, or broken workflow.High-priority user-facing bug, regression, or broken workflow.clawsweeper:linked-pr-openClawSweeper found an open linked pull request for this issue.ClawSweeper found an open linked pull request for this issue.clawsweeper:needs-live-reproClawSweeper needs live local, crabbox, or manual validation to confirm this issue.ClawSweeper needs live local, crabbox, or manual validation to confirm this issue.clawsweeper:needs-maintainer-reviewClawSweeper marked this issue as needing maintainer review before automation.ClawSweeper marked this issue as needing maintainer review before automation.clawsweeper:needs-product-decisionClawSweeper marked this issue as needing a product or behavior decision.ClawSweeper marked this issue as needing a product or behavior decision.clawsweeper:no-new-fix-prClawSweeper does not recommend queueing a new automated fix PR for this issue.ClawSweeper does not recommend queueing a new automated fix PR for this issue.impact:auth-providerAuth, provider routing, model choice, or SecretRef resolution may break.Auth, provider routing, model choice, or SecretRef resolution may break.impact:crash-loopCrash, hang, restart loop, or process-level availability failure.Crash, hang, restart loop, or process-level availability failure.issue-rating: 🐚 platinum hermitGood issue quality with a plausible reproduction path needing some confirmation.Good issue quality with a plausible reproduction path needing some confirmation.staleMarked as stale due to inactivityMarked as stale due to inactivity
Type
Fields
Priority
None yet
版本信息
问题描述
升级到 v2026.5.22 后，Gateway 进程持续占用 100%+ CPU（单核满载），导致所有 API 请求延迟飙升 50-100 倍。
实测数据
根因分析
v2026.5.22 新增的 "provider auth-state pre-warming" 特性在启动时预热所有模型提供商，导致 Gateway 启动后持续数分钟占满单核 CPU。Release notes 描述此特性可在热路径上将 per-call 成本从 ~20s 降至 ~5ms（4100x 提升），但预热过程本身的 CPU 开销抵消了这一收益。
影响
降级后
降级到 v2026.5.12 后，Gateway CPU 立即回落到 ~5%，所有延迟恢复正常。
建议