Intel Tech Support - Urgent - Please Help with Intel RST Corrupting SSDs

[Michael4000]

We have a problem with Intel RST corrupting SSDs, and RAID 1 failing.  Computers don't boot, drives unrecognized, RAID 1 broken.

I have multiple HP Z2 G9 computers with Western Digital SN850 SSDs and Samsung Evo 990 SSDs that are being corrupted by Intel RST.  Another person on this forum has the same SSD corruption issue.

Can we please get some help from Intel, and have Intel investigate this?  

I would like to get someone from Intel who really wants to fix this, and put in the work.

[Michael4000]

Patience has run out.

No response for a month and half.  No updates.  Obviously no one is working on this.

This is really degrading my trust in Intel.

[Ernesto_C_Intel1]

Hi @Michael4000,

Thank you for you patience. Intel is currently coordinating with HP regarding the issue you've encountered. 

1) Have your organization contacted HP regarding this issue before contacting us? If yes - let me know so I can contact you via email to discuss their findings internally.

2) May I know the current drive failure rate of the "Boot Device not found" error

3) May I know if the HP Z2 G9 originally came with a different NVMe drive and if it was subsequently replaced with WD or Samsung NVMe drives? 

I need more time to coordinate your concern but knowing this information is crucial for our investigation to address the corrupted drives. 

Regards, 

Ernesto C.

Intel Customer Support Engineer

[Michael4000]

Yes, we have contact HP, but they do not have a solution for the Intel RST failure.

Failure rate of "Boot Device Not Found" is unknown, but likely on the order of 50%.  The "Unrecognized" disk failure rate in the Intel RST program is 100%.

It came with one 500 GB drive from HP.  We needed RAID 1 and larger drives so we replaced them with WD and Samsung drives.

[Ernesto_C_Intel1]

Hi @Michael4000,

I wanted to follow up on our recent conversation regarding Intel RST corrupting your drives. Your insights were invaluable, and I am keen to ensure we address any concerns or questions you might have.

If you need more time to review the details or prefer to discuss the matter internally, please let me know. I am here to assist you whenever you're ready to continue our discussion.

Feel free to reach out via email if you have any questions or require further clarification. Your satisfaction is our priority, and I am committed to supporting you in any way possible.

Thank you for your attention, and I look forward to hearing from you soon.

Regards, 

Ernesto C. 

Intel Customer Support Engineer

[f1technology]

Hi @Ernesto_C_Intel1 

Was there a resolution to this? Are you able to share the details you are referring to if they were provided from the Intel side?

[Michael4000]

There is no solution to this yet.  I'm not sure why Intel would expect the customer to come up with a solution.  I'm surprised Intel isn't investigating this, and working on a solution.

[Ernesto_C_Intel1]

Hi @f1technology, 

Thank you for posting on this thread. I would like to ask if you are experiencing the same issue on this thread as well? 

If yes, I would like to confirm if you are also using an HP Elite 900 G9 SFF or an HP Z2 G9? 

Regards, 

Ernesto C.

Intel Customer Support Engineer

[f1technology]

Hi @Ernesto_C_Intel1 

The problems we have are with the HP Elite 900 G9 SFF when combined with Samsung 990 Pro 4TB NVMe storage. The issue does not occur with the Samsung 980 Pro 2TB when used in the same configuration in the same computer. The issue can be replicated across 3 x HP Elite 900 G9 SFF systems at my end and @Michael4000 can replicate it across 12 x HP Z2 G9.

As @Michael4000 reports it isn't limited to the Samsung product, the issue occurs with the Western Digital NVMe storage too.

Because this fault kills the storage we are limited in recording logs.

The problem doesn't occur when we disabled Intel VMD (disabling RAID1).

While it might be a HP problem, it may even be a problem with the newer drives from two manufacturers it seems quite possible there is a problem with Intel VMD and\or Intel RST. I've also seen reports in forums of this behaviour with these drives and Intel VMD \ Intel RST on computers that aren't from HP, hence why I think it might be an intel problem.

My next option is to try a different storage controller but I'd prefer it if the onboard Intel one worked.

[Ernesto_C_Intel1]

Hi @f1technology, 

Thank you for your prompt response. Our team have contacted the HP Service Center, and based on their response to us is that they have not received any previous reports similar to what @Michael4000 is experiencing.

Considering the situation it is best to contact HP Service Center, as the entire system is manufactured by HP. Intel is unable to pinpoint the exact cause, and the system event log indicates a NEW SMART event detected, suggesting imminent hardware failures beyond just overheating.

Once the HP Service Center receives the report, they will triage the issue and collaborate with Intel.

I understand that the general perception of this thread is dedicated issue raised by @Michael4000 but it would be best if you create a separate thread or contact Intel Customer Support directly and refer back to this thread. 

Regards, 

Ernesto C. 

Intel Customer Support Engineer