Hi,
I thought I'd post my latest project. I use a bunch of Raspberry Pi compute modules as servers and decided to build myself a custom blade server to host them. This is replacing a bunch of old Intel rack mount servers on my home network - it's a lot less power hungry! It's been through a few iterations and is now working really well. This is the server:
It's a 2U rack mountable unit, in an off-the-shelf ABS case with some custom 3D printed parts. The server takes up to 10 of these blades:
It's got gigabit Ethernet, USB-A and HDMI on the front and an NVMe SSD slot on the board, along with an SD card slot and a battery backed real time clock. There's a little OLED on the front displaying information about the blade, including the name and IP address to make it easy to identify for maintenance. There's also an RP2040 on it for management.
The blades plug in to a custom backplane which provides power and centralised management. There's an LCD front panel providing basic tools for powering on and off blades and status information, and another compute module which acts as a management web server. It can be used to upload flash images to the blades via the backplane, and provides serial console access to the blades through the web interface.
I've been using this for a while now and was wondering if other folks out there are interested in it? It would be quite quick and easy for me to turn this into a product for sale if there was a market out there for it.
Please let me know any comments or suggestions you have, any feedback is appreciated!
Alastair
Kudos to you sir. I'm first to jump against RPi in homelab posts but this is on a whole other level. I think everyone would love a detailed explanation on it.
The Compute blade comes to mind and I'm drawing parallels between them. AFAIR, the compute blade does power and management over the front ethernet port. Which requires the PoE stuff to be there too. Does your backplane simplify the boards (and make it the project cheaper)?
Thanks, that's very kind. I've added some more detail on other replies and I think I'll do a full blog post in the next couple of days.
There are definitely parallels with the Compute Blade project but there are a few differences. My blades are a bit simpler, they don't have the TPM that the Compute Blade does, as I didn't have any real need for it. The CB also has a more dense number of blades in the 19" width. This was another design decision on my part, I quite liked the short depth case making the unit small and I wanted to make sure there was plenty of airflow for cooling (tbh I didn't need as much as I used!)
My unit is more focused on being like a traditional server unit, as that's what my use case was. Centralised power, centralised management and provisioning etc. You're correct, the Compute Blade uses PoE, and I did it through the backplane. My preference was for central management rather than per-blade, so that meant a backplane and it all flowed from there. It allows you to feed the USB and serial console into the management server which is great for provisioning and debugging. The displays are also born out of my days as a network infrastructure guy, where being able to see the server's name and IP address on the physical unit would have been a godsend when doing maintenance! So I guess the design differences between this and the Compute Blade are about my focus on more of a server use rather than general compute module.
I'd say it's probably a bit cheaper using a backplane than PoE. The PoE adds a bit to the cost of each blade which would soon multiply up, plus the additional cost of a PoE switch vs non-PoE. I'm using an off-the-shelf ATX PSU and these are made in such huge quantities that the price per watt is difficult to beat.