Just out of curiosity: Can you properly access Intel’s support websites when logged into your account?
Still no idea what’s going on there, some time ago I was at least able to check the drive’s SNs for warranty but at least for a week now even that has been impossible.
Tried multiple Windows, Linux, macOS machines and mobile devices, including mobile, cable and fiber ISPs.
Could finally create a support ticket with Intel a few minutes ago. I am curious how they’ll respond since I didn’t sugar-coat that third parties can recreate my issues and since the only thing in common in my two test scenarios is the P4500 I’m fairly certain that there is a general issue with this SSD model.
Oh, Jeez…
Got P4510 4 TB models for testing and the buggy AMD NVMe RAID0 array behavior persists, meaning the moment you create the array determines if the sequential read results are at least usable or complete trash.
Writing scales nicely with the P4510 that is a little faster than the P4500 but the best read values I got so far are around 4800 MB/s. As a reminder, with the previous P4500 drives there was a 1 in 50 (or so) chance to get an array with a little over 5000 MB/s.
The most consistent results (at least 4500 MB/s) are with 128 kB as the RAID0 stripe size with read cache enabled. With the default 256 kB stripe size I get mostly performance like this 
:
For reference the drives individually on the same PCIe interfaces as when used for an RAID array:
Based on disk selection and performance target, you are entering enterprise/business territory, where usually a raid controller is first chosen, then officially supported drives, not the other way around.
I understand that it sucks and it should work, but that is the reality, it does actually work but it needs optimization, controller vendors cannot test and optimize for every drive out there, neither could drive vendors do the same for every controller, all they can do is try to test and optimize for major operating systems when the drive is connected directly or through the basic passthrough controller, in case of sas/sata ports. So the industry standard is to lay the responsibility on the controller vendor, on the other hand they take responsibility only for drives they advertise as supported. It’s more or less similar to ram support on motherboards.
Other than that, you are mostly fighting windmills, your milage may vary.
You can always go the linux route and setup software raid, which I believe is better for many different reasons, including that it gives you better performance than lowend controllers anyway, even when they work correctly.
The Intel P4500/P4510 SSDs are on Broadcom’s QVL for the HBA 9400-8i8e.
Source: https://docs.broadcom.com/doc/HBA-94xx-OT
(The P4500 is to be removed in a revised list according to Broadcom’s Support, BUT the P4510 should have been fine, specifically asked them about this model)
By the look of it now I guess that Intel has messed something up in the SSD controller firmware (the P4510 and P4500 use the same controller) at least for some newer versions and since you cannot downgrade the firmware yourself as an end customer it’s a bit hard to trouble-shoot.
If that is the case, then Broadcom should take responsibility and make it work, even if it is intel’s fault and they changed something, as long as Broadcom advertises these drives as supported, then they should accommodate for any change through firmware update, especially that the drives still work fine in other setups. I shouldn’t be troubled as a customer with the difficulties they face.
The answer is to simply remove support rather than fix it? Man that is just obscene 
I’m curious how this story continues: Emailed Broadcom’s Support with the similarly low results for the P4510 today they themselves had claimed to be fine in the previous message (reminder: Also tested two different HBAs and four different Broadcom U.2 SSD cables, if that weren’t the case I’d suggest that I simply have defective components).
Since at least Intel still actively supports the P4510 (the P4500 is EOL) I hope they are going to investigate the real underlying issue, my gut says that both - the low AMD NVMe RAID0 read performance and the extremely low Broadcom HBA performance - have the same root cause in the depths of Intel’s firmware purgatory.
Oh, jeez #2
Took the P4510s back from the HBA to the direct motherboard PCIe interfaces to continue investigating.
The P4510s had been manufactured in 2019 according the Intel OEM box they came in so I also checked with the Intel Memory and Storage Tool if there’s an update for the firmware available.
Yes, there was and I updated the drives without any issues. Also secure-erased them afterwards to give them a fresh start and now the SSDs’ performance connected to the motherboard directly is worse than before:
Shipped with old firmware version VDV10131 - performance numbers:
Updated to current firmware version VDV10170 - performance numbers:
The performance connected to the HBA 9400-8i8e is pretty much unchanged.
NOW WITH ADDITIONAL BUGS:
When AMD NVMe RAID is disabled in the UEFI options of the ASUS Pro WS X570-ACE (UEFI 1302), the P4510 continue to show up fine.
If AMD NVMe RAID is enabled in the very same UEFI options, the SSDs now no longer show up in the UEFI
This stuff keeps on giving…
No news from Broadcom
Intel doesn’t seem interested in going down the rabbit hole even though the still supported P4510 appears to be also affected.
Downgrading the P4510’s firmware version isn’t possible “due to security reasons”, offered to test older firmware versions since a firmware update had a measurable (negative) effect on the drives’s performance.
Weekly support experience update:
a) Broadcom’s support tested Intel P4510 and P4610 SSDs, their sequential read results are far below what the SSDs could handle though not as bad as mine:
P4510/1TB (Spec: ca. 2850 MB/s read, 1100 MB/s write (SEQ1MQ8T1):
P4610/1.6TB (Spec: ca. 3200 MB/s read, 2100 MB/s write (SEQ1MQ8T1):
The support contact guy emailing me also told me that “Broadcom is stopping to verify drives and the drives’ manufactures are to test them themselves and are to just send the results to Broadcom”.
What a great development…
b) Intel’s support isn’t that engaged, I suspect that “We have received your concerns and will relay them to our experts who will analyze them.” was the last thing I’ll ever hear from them after I had notified them that the non-EOL P4510 is showing similar issues to the EOL P4500.
c) A little bit frustrated I’ve also opened a support ticket with AMD, I hope that they’ll at least glance over this niche of a niche use case using DC U.2 SSDs with an X570 chipset AMD RAID array in Windows.
So they basically form the decision:
“Problem verified, accurate, but won’t fix” and then just close the tickets?
Might need some large hitters to push for change?
Otherwise they’re like “meh, smol user, who cares?”
Great customer support.
Eh they said they would fix it at least, better then fuck off or pay me or we “couldn’t replicate” etc
If its not fixed in like 6 months then maybe
I just re-checked all emails with Intel’s support; they asked for various information but have never actually confirmed anything in writing 
The only statement is “we have received your concerns”.
My cynical gut says that they don’t care, I hope I’m wrong
Don’t keep your hopes up in when it comes to Intel. They just blame the other (Microsoft, in my case, in regards to graphics drivers).
I hope that Broadcom is actually serious about diagnosing this dispite the less than engaged reactions so far.
My reasoning is that these Intel “Datacenter” drives with a “reliable track record” let Broadcom’s HBAs look much worse than they are (as is seen when using them with Optanes SSDs).
Minor update from AMD’s side:
“The feedback from the Raid software team was to try then next driver once it becomes available on the AMD website. Currently there is no ETA for when this driver will become available, so please check back periodically for the updated driver. Once it is ready, it will be posted to AMD.com.”
Don’t quite know if they have really addressed this issue or if the response (after a few weeks) is more or less a general statement.
Does anybody know something specific of upcoming AMD RAID driver releases?
Personally kind of hoped for today/July 7th since the current version is out since November 2019 and they could have used the launch of the XT CPU line to update the official driver releases on AMD.com…
Minor (major?) update from Intel:
They’re now offering a refund for the drives
Hilariously, the P4510 no longer work with AMD NVMe RAID enabled at all, don’t know what exactly triggered it and tried multiple motherboard models.
The SSDs disappear from Windows Device Manager as soon as the AMD RAID drivers are installed
RAIDXpert2 also does not recognize the two P4510 SSDs, there are 2 similar error messages:
Event 1041: Device Error on Controller 1 Channel 17.
Event 1041: Device Error on Controller 0 Channel 17.
This topic was automatically closed 273 days after the last reply. New replies are no longer allowed.
