April 9, 2016

Solar cluster: Measuring for a cabinet

One elephant in the room, is how I’m going to store the system whilst in operation.

The obvious solution is some sort of metal cabinet with provision for 19″ rack mounting and DIN rail equipment. Question is, how big?

A big consideration here is thermal matters. When going flat out, there will be 100W-150W worth of thermal energy being dissipated in there. So room for convection currents is a must!

Some decent fans on the top to suck the hot air out would also be a good idea. Blowing up so that dust doesn’t get sucked down into the works.

I figured I’d sit everything sort-of in situ. I figured out that the DIN rail mounts don’t have to go on the bottom, with these cases, if you remove the front panel there’s four holes for mounting those same DIN rail mounts on the front. So that’s what I’ve done. I’ve now got a DIN rail spare for future expansion.

If I try to pack everything up as densely as possible (not wise), this is what it looks like:

There’s room there for possibly one more node to squeeze in there. I’d think that’d be pushing it however. 5 is probably a good number, meaning we can space the units out a bit to allow them to draw air in via the gaps.

On top of the units I have my two switches. The old Netcomm 24-port switch was retired from our network when a lightning strike to a neighbour’s tree an 8-port switch, my Yaesu FT-897D radio transceiver, some ports on a wireless 3G router/switch, and an ADSL router out. It also did damage some ports on the big Netcomm switch, so in short, I know it has issues.

Replacing its 3.3V PSU with one that steps down from 12V would cost me the price of a 16-port 10/100Mbps switch brand new.

When we replaced the switch (paid for by insurance) we decided to buy a 8-port and 16-port switch. The 16-port switch, retired due to an upgrade to gigabit, is sitting on top, and takes 12V 1A input. It’ll be perfect for the IPMI VLAN, where speed is not important. It also accepts the DC plugs I bought by mistake.

The 8-port one takes 7.5V 1A, so a little less convenient for this task, I’d need to make a DC-DC converter for it. Maybe later if this works.

So considering a cabinet for this, we have:

  • 5 nodes measuring 190mm in height: ~5 RU
  • A 24-port switch: 1 RU
  • A 16-port switch: 1 RU
  • Some power distribution electronics: 3RU

Yes, the battery and its charger is external to the cabinet.

Judging from this, the cabinet probably needs to be a 10RU or 12RU cabinet to give us space for mounting everything cleanly and to ensure good ventilation. Using 8-port IPMI switches and 24+2-port comms switches, that leaves us with sufficient port space for the 5 nodes and gives us one port left for a small in-chassis monitoring device and 4 ports left on the main switch for an uplink trunk.

You could conceptually then consider these as homogeneous building blocks for larger networks, using Ceph’s CRUSH maps to ensure copies get distributed amongst these “cabinets”.

Solar cluster: Alternate solution to the PicoPSU

So, I’ve been doing a bit of research about how I can stabilise the battery voltage which will drift between around 11V and 14.6V. It’s a deep-cycle type battery, so it’s actually capable of going down to 10V, but I really don’t want to push it that far.

Once I get below 12V, that’s the time to signal to the VM hosts to start hibernating the VMs and preparing for a blackout, until such time as the voltage picks back up again.

The rise above 13.5V is a challenge due to the PicoPSU limitations. @Vlad Conut rightly pointed out that the M3-ATX-HV PSUs sold by the same company would have been a better choice. For about $20 more, or an extra $100 for the cluster, I’d have something that’d work 6-30V. I’d still have to solve the problem with the switch, but it’d just be that one device, not 6.

Maybe it was because they were out of stock that I went the PicoPSU route, I also wasn’t sure about power demands, I knew the CPU needed 20W, but wasn’t sure about everything else. So I over-dimensioned everything. Hindsight is 20:20.

One option I considered was a regulator in front of each node. I had mentioned the LM7812 because I knew of it. I also knew it was a crap choice for this task, the 1.5V drop, with a 5A load would result in about 7.5W dissipated thermally. So 20W would jump to nearly 28W — not good.

That of course assumes a 7812 would handle 5A, which it won’t.

LDOs were the way to go for anything linear, otherwise I was looking at a switchmode power supply. The LM2576 has similar requirements to the LM7812, but is much more efficient being a buck converter. If 1.5V was fine, I’d be looking for a 5A-capable equivalent.

The other option would be to have one single power supply regulate power for all nodes. I mentioned in my previous log about the Redarc DC-DC power supply, and that is certainly still worthy of consideration. It is a single point of failure however, but then again, Redarc aren’t known for making crap, and the unit has a 2 year warranty anyway. I’d have downtime, but would not lose data if this went down.

@K.C. Lee pointed me to one LDO that would be a good candidate though, and is cheap enough to be worth the experiment: the Micrel MIC29750. 7.5A current, and comes in an adjustable form up to 16V. I’d imagine if I set this near 13.5V, it’d dissipate maybe 2.5W max at 5A, or 1W at 2A. Much better.

Not as good as Redarc’s solution of course, and that’s still an option, but cheap enough to try out.