• Notice regarding image hosts and attachments. See here.

Reduce home server power usage - thoughts/suggestions

I think you'd a more detailed breakdown how how much power each part of the rig is consuming. Is it the system, the drives etc. By cost and energy.

That would inform you of where the break even put is in switching hardware is. I means how much money a different CPU would save. Moving to larger but fewer disks etc.

In theory you could switch to a Mac Mini and SSDs. But the price doesn't make sense.
 
Running headless will save you maybe 10watts plus the standby power of the monitor.
Moving to a 8 lane 3 gigabit HBA would save a fair chunk of power and may not impact the performance much depending on the array setup, but changing card could also be a royal PITA.
The PSU could also be worth looking at. HP usually want to upsell the higher efficiency units
 
My suspicion is that anything you do will end up being a rounding error at best.

If you *need* to change, sure look a little a power consumption etc. but if this is just an excersise in power reduction, any benefit you see will be miniscule.
Changing CPU will do nothing useful- downclocking and P-states has been a thing for a very long time. The power is used when it's doing something, not when it's idle.

An actual 10w at the wall power reduction will save you ~240w per day or 7.2kw per month.
Thats ~£2 if you're paying peak rate, or ~£24 pa.
 
You're running a full fat server at the end of the day. A lot of the suggestions in this thread are good, especially those about optimising power consumption via the OS. This is the most easiest and convenient way to save energy. Double check that all of the power saving features (like lowered C states, idle power down) are all working correctly.

Aside from that, you're looking at changing hardware which will far outweigh the cost of any savings, unless you were to drastically cut back on your footprint to something like a RPi.
 
My suspicion is that anything you do will end up being a rounding error at best.

If you *need* to change, sure look a little a power consumption etc. but if this is just an excersise in power reduction, any benefit you see will be miniscule.
Changing CPU will do nothing useful- downclocking and P-states has been a thing for a very long time. The power is used when it's doing something, not when it's idle.

An actual 10w at the wall power reduction will save you ~240w per day or 7.2kw per month.
Thats ~£2 if you're paying peak rate, or ~£24 pa.

Selling the graphics and 16e HBA cards would actually leave money over after buying a 3 gigabit single chip version.
 
You're running a full fat server at the end of the day. A lot of the suggestions in this thread are good, especially those about optimising power consumption via the OS. This is the most easiest and convenient way to save energy. Double check that all of the power saving features (like lowered C states, idle power down) are all working correctly.

Aside from that, you're looking at changing hardware which will far outweigh the cost of any savings, unless you were to drastically cut back on your footprint to something like a RPi.

It's technically not a server ;), it's a professional grade workstation that is power thirsty.

As others have said though, any tweaks you're just going to shave off a few watts here and there, but these workstations were just not built with efficiency in mind. Heck your average use is more than my entire house overnight and I run a rack with my 40Tb Synology, a HP Elitedesk, USG Pro and a US 24 port POE switch - which averages out about 125 watts.
 
It's technically not a server ;), it's a professional grade workstation that is power thirsty.

As others have said though, any tweaks you're just going to shave off a few watts here and there, but these workstations were just not built with efficiency in mind. Heck your average use is more than my entire house overnight and I run a rack with my 40Tb Synology, a HP Elitedesk, USG Pro and a US 24 port POE switch - which averages out about 125 watts.
I think he means server as a profession rather than product.

It could be you're better off offloading some of the services to a lower power device if it will let your bigger server enter lower power modes. but I doubt very much you'll save more than it costs unless it's a massive saving and very very cheap.
or if it's just "because you can" then go ham. with enough raspberry Pi's you can do pretty much anything!
 
I only have the 2 onboard NVMe drives in the Z6G4 chassis, all the mechanical drives are in an external case, connected through the HBA & expander card.

Actual cost (very roughly): 200W @28p/kwh for 19 hours & 6.5p/kwh for 5 hours a day = £1.13/day = a little over £400/year, but obviously not all this will be saved with any solution.
I was in a similar situation, I built a server with desktop components, HBA's, GPU and many HDDs/SSDs/NVMEs, but not matter what, 80W+ was the minimum idle..


With a little bit of rationalisation , I swapped to a dedicated NAS Appliance and am running
  • 2 x VMs (Win 11 and Home Assistant)
  • 35+ Docker Containers (including Plex, Jellyfin, Channels DVR, TVHeadend, Duplicacy (for backup), All the download/indexers including Gluetun VPN, etc, etc, etc)
  • Unraid OS.

I initially rationalised all that on 5 x 14TB HDDs, 1 x 4TB SSD and 2 x NVME to allow me to move to a 6 bay (+ 2 x NVME) NAS Appliance.
With careful thought, the main HDD Array is largely idle, only spun up if someone watches a movie/tv or listens to music, and then its a single disk, everything else is using cache either RAM, SSD or NVME..

Until very recently all that was in a Terramaster F6-424Max (6 Bay + 2 x NVME, i5-1235U 10C12T / 64GB RAM) and idle is 30-35W with everything running, and goes to 45-50W when people are accessing media.
This uses the iGPU for HW Transcoding, ML (for immich) etc, so ditched the full GPU.


I've just upgraded to a WTR Max (AMD 8845hs 8C/16T 6 Bay + 5 NVME), primarily as I started compiling more on the NAS and it has more cores/grunt..
Its not as energy efficient, but idles around 38-45W and is around 50-55W when people are accessing media.
The iGPU is more powerful than the Intel and I've got it doing the same transcoding/ML although support is lagging Intel, it's just about there.

I also use a JetKVM (isolated on an IoT VLAN) to save me having a monitor plugged in so I can reboot, go in the bios etc remotely.

The other thing to do is grab a free for life VM on Oracle (need to give them CC Details, but you don't be billed), I maxed out the 4 x ARM Cores + 24GB RAM / 120GB HDD space and run inconsequential dockers on that (behind a cloudlfare tunnel) and have that on my Tailscale tailnet so it can access my server (also on the Tailnet).. great for containers that are quite CPU intensive but don't need to be running locally in my house.. might as well use their electricity for free!
 
Last edited:
The other thing to do is grab a free for life VM on Oracle (need to give them CC Details, but you don't be billed), I maxed out the 4 x ARM Cores + 24GB RAM / 120GB HDD space and run inconsequential dockers on that (behind a cloudlfare tunnel) and have that on my Tailscale tailnet so it can access my server (also on the Tailnet).. great for containers that are quite CPU intensive but don't need to be running locally in my house.. might as well use their electricity for free!
Shhhh. Don't tell people about the free tin in OCI. You can also split that across multiple VMs. You don't have to have all of those resources under one VM. There is also a micro x86 VM available, and you can have two of those.

Buy a RPi. Probably sucks 10W peak and does everything any full fat server (meaning the role, before the ACKSHEWALLY crowd chime in) can do beyond transcoding/highly CPU intensive tasks.
 
I'm averaging around 80w running the kit below:
  • Intel i5-13500T
  • 64GB DDR4
  • 22TB + 12TB SATA
  • 2TB + 1TB + 1TB + 240GB SSD
  • 8 port 2.5Gb PoE switch
  • Enterprise WiFi AP
I'd like to reduce it but haven't found a cost effective solution.
 
Back
Top Bottom