ESXi hostd service might stop responding when there is an IO failure on the storage side

Products

• VMware

Issue/Introduction

Symptoms:

• One or more ESXi hosts become unmanageble
• The host(s) are disconnected from the vCenter
• In the /var/log/hostd.log file, you see entries similar to:

2016-08-28T08:33:17.030Z [53180B70 warning 'ThreadPool'] Thread pool usage : Total:[Working: 22/74 (Running: 23)] Task:[Working: 22/22 (Peak: 22), Queued: 2 (Peak: 2)]
2016-08-28T08:53:39.515Z [534C8B70 warning 'ThreadPool'] Thread pool usage : Total:[Working: 22/74 (Running: 27)] Task:[Working: 22/22 (Peak: 22), Queued: 16 (Peak: 29)]Note: The preceding log excerpts are only examples. Date, time, and environmental variables may vary depending on your environment.

Note: The preceding log excerpts are only examples. Date, time, and environmental variables may vary depending on your environment.

Cause

This issue occurs when there is an IO failure on the storage side where VMs are provisioned with LSI Virtual Controller and have memory over-commit.

Resolution

This issue is resolved in ESXi 5.5 Patch 10, available at VMware Patch Downloads. For more information on downloading patch, see How to download patches in Customer Connect (1021623) and VMware ESXi 5.5, Patch Release ESXi550-201612001 (2147788).

Additional Information

当存储端发生 IO 故障时，ESXi hostd 服务可能会停止响应