Teamgroup NVMe SSD High Idle Power Draw

[jtabc]

I was testing two SSDs and I was surprised to see a large difference in idle power consumption between the two in an HP Elitedesk 800 G4 SFF PC with an i7 8700.

1. Samsung SM951 (256 GB)
2. Teamgroup MP33 (1 TB)

What I noticed was that when I had the Samsung drive in the system (with the OS installed on it), the entire system would idle at 5.5 watts (measured with a kill-a-watt from the wall). However, when I had the Teamgroup installed in place of the Samsung (also with the OS installed), the system would idle at 9.9 to 10.5 watts, which seems significantly higher.

Originally I thought this was because the Windows OS was installed on it and maybe the Teamgroup was having problems with that, so I tried it as a secondary drive being completely empty.

But when the Teamgroup was the empty secondary drive (the motherboard has 2 M.2 slots) and Windows was on the Samsung, the system was still idling at 9.9 to 10.5 watts, meaning that the Samsung was drawing so little power that I couldn't even measure it while the Teamgroup SSD seems to consistently be drawing 4 to 5 watts no matter what.

The Tom's hardware review suggests it should only be using about 0.4-0.5 watts at idle so something is clearly wrong.

I'd like to get the idle power draw on these down if possible (I have ten different machines with MP33s in them, so it adds up) but I don't know what to do. Any advice?

 

[jtabc]

I used smartmontools (smartctl) --capabilities to check the power states available for the Teamgroup SSD and this is what I found:

Supported Power States
St Op     Max   Active     Idle   RL RT WL WT  Ent_Lat  Ex_Lat
0 +     6.50W       -        -    0  0  0  0        0       0
1 +     5.80W       -        -    1  1  1  1        0       0
2 +     3.60W       -        -    2  2  2  2        0       0
3 -   0.7460W       -        -    3  3  3  3     5000   10000
4 -   0.7260W       -        -    4  4  4  4     8000   45000

For comparison, here is what the Samsung SM951 looks like:

Supported Power States
St Op     Max   Active     Idle   RL RT WL WT  Ent_Lat  Ex_Lat
0 +     9.00W       -        -    0  0  0  0        5       5
1 +     4.60W       -        -    1  1  1  1       30      30
2 +     3.80W       -        -    2  2  2  2      100     100
3 -   0.0700W       -        -    3  3  3  3      500    5000
4 -   0.0050W       -        -    4  4  4  4     2000   22000

So the maximum power consumption of the lower power states of the Teamgroup are significantly higher than the Samsung (0.74 vs 0.07 and 0.72 vs 0.005), but the actual power consumption I observed is still a lot higher than those values (4 to 5 watts compared to less than 1 as indicated by smartctl).

I guess the Teamgroup is getting stuck in state 1? I'm not sure why this would happen.

 

[thigobr]

PCIE ASPM might be disable for the drive (try lspci -vvv to check) which can forbid the CPU to enter the most deep power saving C6 state