82599E/X520 Link status misdetection ESX 6.7

[MDKnk]

Hello,

our X520 Adapters sometimes do not detect the link down status when we do a switch reboot on ESX 6.7 which leads to loosing conectivity when data is transmitted over the down link of a redundant uplink in ESX 6.7.

It can be reproduced every 5-10 switch reboots. We involved server support, VMware support and switch support.

We tried driver 1.7.10, 1.7.20 and 1.8.7. With 1.8.7 we were not yet able to reproduce the issue - but according to release notes there was nothing fixed in that area. How can we find out if there were some internal changes which were not mentioned in the release notes?

Edit: We also tried different switches, notwork cards, switch firmwares and SFPs. It ONLY happens with these X520 network cards.

[AlfredoS_Intel]

Hi Mdknk,

Thank you for your patience in waiting for our update.

Our engineers are still checking on your concern, and while they are working on it, they have a couple of clarifications, and they are also needing more information from you.

They want to know your exact ESXi build, firmware and switch model. The reason why they are asking for it is they were not able to reproduce your issue with the following setup:

[20 Reboots]

ESXi 6.7 U3 (Build 14320388)

PF driver: 1.7.20

FW: 0x000161bf, 1.1824.0 (esxcli network nic get -n vmnicX)

Switch: Extreme X670G2-48x-4q, Software version 15.6.2.12

We look forward to your reply. Should we not get your reply, we will follow up after three business days.

Best Regards,

Alfred S

Intel® Customer Support

[MDKnk]

Hello,

Firmware Version: 0x8000014d

ESXi 16713306

Switch X695 30.7.1.1-patch1-23

Markus

[AlfredoS_Intel]

Hi Mdknk,

Thank you for your response and providing more details regarding the issue,

We will continue checking this and the information that provided is invaluable to us.

Please allow us some time to check on this. We hope for your understanding regarding this

We will get back to you no later than 3 business days from now.

Best Regards,

Alfred S

Intel® Customer Support 

[AlfredoS_Intel]

Hi Mdknk,

Thank you for waiting for our update.

We are humbly sorry for that time that it took to provide you with an answer.

Here is our answer to your question:

Details from our development team are as follows:

Root cause of issue found in code:

The link issue was caused by incorrect handling of interrupts in the driver. After a few months there was an attempt to fix this issue, however the patch introduced a PSOD. This change was quickly revisited and a new version of the driver fixed both issues (PSOD and link detection). With the newest version of the driver, in relation to interrupt handling, we do not currently see any issues.

Since you have confirmed that the issue was fixed please provide resolution on this bug to them.

Using the compatibility guide provided by VMWare, based on ESXi version, here are the drivers available for download.

VMWare Compatibility Guide for X520: https://www.vmware.com/resources/compatibility/search.php?deviceCategory=io&productid=13444&deviceCategory=io&details=1&partner=46&keyword=X520&deviceTypes=6&page=1&display_interval=10&sortColumn=Partner&sortOrder=Asc

ESXi 6.7: ixgben version 1.8.7

https://my.vmware.com/en/web/vmware/details?downloadGroup=DT-ESXI-65-INTEL-IXGBEN-187&productId=614

ESXi 7.0: https://my.vmware.com/en/web/vmware/downloads/details?downloadGroup=DT-ESXI70-INTEL-IXGBEN-1890&productId=974

We look forward to your assessment of our answers. Should we not get your reply, we will follow up after three business days.

Best Regards,

Alfred S

Intel Customer Support

[AlfredoS_Intel]

Hi Mdknk,

We are just following up.

It looks like you need more time to assess the answers that we have provided.

We will follow up again after 3 business days. Should we not hear from you, our system may automatically close the thread.

Best Regards,

Alfred S

Intel Customer Support

[AlfredoS_Intel]

Hi Mdknk,

We need to close this thread since we have not gotten a response from you: maybe because you are busy or preoccupied at the moment.

We hope that our answers were sufficient to address your concern.

We were waiting for your feedback since it is important for us to give you the right solution on your concern.

As much as we would like to continue assisting you, we need to close it to avoid overwhelming your inbox with notifications.

We hope for your consideration and understanding on this one.

If you need any additional information, please submit a new question as this thread will no longer being monitored.

Thank you for contacting Intel® and have a great week!

Best Regards,

Alfred S

Intel® Customer Support