ESXi 5.5 and Emulex OneConnect 10Gb NIC

*** English Version ***

You are using HP ProLiant BL460c G7 or Gen8, ESXi version is 5.5, NIC is Emulex chipset. You are using driver version 10.x.x.x. You may experience the host randomly lost connectivity on vCenter Server, host status show “No responding”. You cannot ping any virtual machine hosted on the blade. High pause frame is observed on HP virtual connect model down links after problem occurred. And you see similar error in vmkernel logs:

2013-11-19T15:49:12.395Z cpu2:33376)WARNING: elxnet: elxnet_detectDumpUe:238: 0000:005:00.0: UE Detected!
2013-11-19T15:49:12.396Z cpu2:33376)elxnet: elxnet_detectDumpUe:249: 0000:005:00.0: Forcing Link Down as Unrecoverable Error detected in chip/fw.

Congratulation! You are hitting a Emulex driver bug. This bug is not fixed so far. But HP is working on release a new driver to fix it. I’ll update this article when I get HP responding.

Temporarily, you can disable elxnet driver and re-enable legacy be2net driver if you installed ESXi by  HP customized  image, try run following commands to disable/enable drivers. If not,  you should install legacy be2net driver manually then run following commands.

esxcli system module set –enabled=false –module=elxnet
esxcli system module set –enabled=true –module=be2net

Update 6/9/2017:

HPE released an advisory about  this issue: ProLiant G7 Series Servers -VMWare ESXi 5.5 and 6.0 Host Loses Connection to the Network After Updating the Adapter Driver Using The Service Pack for ProLiant

Firmware can be download from here.

Driver can  be download from here.

Update 9/9/2015:

I still observed NIC driver crash by below driver and firmware combo. It’s not so much like previouse combos, but I want to permanently fix it. HP again told me the issue was fixed on following combo. You will see error message on vmkernel.log after update to that combo if you are using HP customized ISO. You have to update HP ESXi 5.5 Management Bundle to 2.3-1. Please refer to community post VMkernel warning message :”WARNING: VmkMgmtSyncEventIoctl – unable to validate header”.

Emulex driver 10.5.65.4

HP Emulex network adapter firmware 10.5.65.21

Update 5/20/2015:

Emulex & HP released new firmware eventually to fix the problem. You must install following driver and firmware both on your ESXi server to make it stable. Community users also feedback it’s stable version.

Emulex driver 10.4.255.13

HP Emulex network adapter firmware 10.2.477.10

*** Chinese Version ***

如果你的ESXi 5.5跑在HP ProLiant BL460c G7 or Gen8上,网卡是Emulex的,并且使用的10.x.x.x版本的网卡驱动程序,可能会出现ESXi主机随机和vCenter Server失去联系 ,ESXi主机显示 “无响应”状态。无法ping该主机上的虚拟机,并且在HP virtual connect 模块的服务器口上可以观察到大量的Pause Frame。vmkernel日志有如下信息:

2013-11-19T15:49:12.395Z cpu2:33376)WARNING: elxnet: elxnet_detectDumpUe:238: 0000:005:00.0: UE Detected!
2013-11-19T15:49:12.396Z cpu2:33376)elxnet: elxnet_detectDumpUe:249: 0000:005:00.0: Forcing Link Down as Unrecoverable Error detected in chip/fw.

恭喜你!这是一个Emulex驱动bug。据我所知此bug暂时还没有修复,但是HP正在准备发布一个新的版本修复此问题。如果我收到消息会更新本文。

如果你的ESXi使用的是HP定制的光盘安装,可以暂时尝试禁用elxnet驱动,启用旧的be2net驱动,命令如下。如果不是用的HP定制光盘安装,则需要先安装be2net驱动,然后再尝试如下命令。

esxcli system module set –enabled=false –module=elxnet
esxcli system module set –enabled=true –module=be2net

2015/9/9更新:

5月20日更新的驱动和固件版本组合并不能完全修复该问题,只是降低了出现频率。HP再次建议升级到以下组合修复这个问题。此组合安装后可能会导致vmkernel.log里出现大量的错误提示 ,这需要通过升级HP ESXi 5.5 Management Bundle到2.3-1来解决。

Emulex driver 10.5.65.4

HP Emulex network adapter firmware 10.5.65.21

2015/5/20更新:

Emulex 和 HP 最终发布了新的固件和驱动修复此问题。请安装以下驱动和固件。社区用户也反馈这各版本看起来是稳定的。

Emulex driver 10.4.255.13

HP Emulex network adapter firmware 10.2.477.10