Compatibility of non-genuine HDDs with Dell Poweredge R760 servers

I work a lot with Dell server equipment. There are times when it is necessary to choose equipment not from Dell. When the buyer sets requirements for server components based on software, budget and performance.

For many years I have encountered some strange behavior in the Dell Poweredge family of servers when using non-genuine hard drives. This article will tell you which drives work without problems and vice versa.

My tests were conducted with a Dell Poweredge R760 server. I bet this problem will occur on other servers. Your server may be a different version, if you find any information to add, please email me and I will update the article.

Server symptoms
On Dell Poweredge servers of different generations that I have tested (this may apply to others) with the Perc H755 built-in RAID controller, some hard drives will make the system behave strangely. At the same time, Dell's original server drives work without any problems. If you connect a non-Dell drive, for example, a drive from your SATA PC, it will most likely work just fine for the most part - the system will recognize it, read, format, write, ... and you may think that everything is fine with the server. But if you sit next to the server in a quiet room, some drives will cause the following:

All fans will operate almost at the limit, "buzzing like a jet engine."
The system will think that the HDDs are overheating.
The server may shut down and reboot to protect itself from high disk temperatures.

The disks show that they are overheating, third-party manufacturers, which, judging by the readings, are overheating. If you remove the disk, you can feel the warm surface, but even so it is clear that the declared 61C is not true. In fact, the readings of the thermal sensors are erroneous.

Dell has a lot of documentation on the temperature sensors in the various R750 server variants. None of the documentation shows the physical location of sensor 29 on the motherboard. Hypothetically, I believe that the value shown on sensor 29 is nothing more than the maximum value reported by the drives themselves via SMART or some other parameter. If a situation arises where a drive does not report a temperature parameter, then the Dell server operates on the GIGO principle (GarbageIn, GarbageOut).

It seems that the Dell server is reading the temperature parameter and causing the fans to spin abnormally fast in an attempt to cool the system. Theoretically, of course, it is possible to reflash the server firmware and fix the situation, but Dell will not fix this issue for servers that are already out of support or very close to it.

This way, we can do our best to document which drives are causing problems and which are working well.

For lack of a better term, I'm going to call these symptoms "Thermal Runaway," even though the temperature may be perfectly fine.

Drives that cause the "Thermal Runaway" problem:

How can we help?

Server Solutions sells Dell PowerEdge R760 and Dell PowerEdge R760xs servers throughout Ukraine, our clients include small, medium and large businesses. If you or your company needs advice and the purchase of quality server equipment, then you should contact us.