H12SSL-I and sensors

Stofarius · Aug 19, 2023

Hi,

I managed to build a server with H12SSL-i and an EPYC 7513 CPU. When running the sensors command on Ubuntu, I get the following output:

Code:

sensors
ucsi_source_psy_0_00081-i2c-0-08
Adapter: NVIDIA GPU I2C adapter
in0:           0.00 V  (min =  +0.00 V, max =  +0.00 V)
curr1:         0.00 A  (max =  +0.00 A)

nvme-pci-0200
Adapter: PCI adapter
Composite:    +56.9°C  (low  =  -0.1°C, high = +76.8°C)
                       (crit = +78.8°C)
ERROR: Can't get value of subfeature temp3_min: I/O error
ERROR: Can't get value of subfeature temp3_max: I/O error
Sensor 2:     +60.9°C  (low  =  +0.0°C, high =  +0.0°C)

k10temp-pci-00c3
Adapter: PCI adapter
Tctl:         +82.9°C 
Tccd1:        +33.8°C 
Tccd3:        +34.0°C 
Tccd5:        +31.5°C 
Tccd7:        +34.0°C

I have 2 questions:

- Is that error from the nvme "normal"? What can I do to fix it.
- when in idle, the value for Tctl seems a little to high for me, am I wrong?

Thank you!

bitbckt · Aug 19, 2023

That does seem high. Here's a machine I have sitting here in my office with a H12SSL-i and 7B13 in it:

Code:

nvme-pci-0100
Adapter: PCI adapter
Composite:    +37.9°C  (low  = -20.1°C, high = +89.8°C)
                       (crit = +94.8°C)

k10temp-pci-00c3
Adapter: PCI adapter
Tctl:         +33.0°C 
Tccd1:        +32.8°C 
Tccd3:        +32.2°C 
Tccd5:        +33.0°C 
Tccd7:        +32.0°C

I'm not sure what to make of the NVMe error. It's also running pretty hot?

Stofarius · Aug 19, 2023

bitbckt said:
That does seem high. Here's a machine I have sitting here in my office with a H12SSL-i and 7B13 in it:

Code:

nvme-pci-0100 Adapter: PCI adapter Composite: +37.9°C (low = -20.1°C, high = +89.8°C) (crit = +94.8°C) k10temp-pci-00c3 Adapter: PCI adapter Tctl: +33.0°C Tccd1: +32.8°C Tccd3: +32.2°C Tccd5: +33.0°C Tccd7: +32.0°C

I'm not sure what to make of the NVMe error. It's also running pretty hot?

Thank you for your reply. Is your server sitting in a datacenter, cold room? My server is in my room, where I currently have 29C. But even so, the value for Tctl is big.

Also, the difference between Tctl and the other sensors is quite big for me.

In web interface of IPMI I see a value of around 36C for the CPU as I type, and 85C for Tctl. The OS is Ubuntu Server 22.04.

bitbckt · Aug 19, 2023

Stofarius said:
Is your server sitting in a datacenter, cold room?

No, this is a desktop machine sitting on the desk next to me. The ambient temperature is approximately 23C.

RolloZ170 · Aug 19, 2023

Stofarius said:
- when in idle, the value for Tctl seems a little to high for me, am I wrong?

known bug on Dell amd smc
there is a patch

Stofarius · Aug 19, 2023

RolloZ170 said:
known bug on Dell amd smc
there is a patch

Any link for that? The motherboard is brand new and has the latest version of bios as I'm aware. I did a search with google but couldn't find anything.

Thank you!

vvkvvk · Aug 20, 2023

I'm guessing you have Milan and kernel 6.2? Known issue: Re: k10temp show over 100 degrees temperature on EPYC Milan servers from DELL and SMC — Linux Kernel

E:
I have that too, and it's been fine.

Code:

$ uname -a
Linux hostname 6.2.0-26-generic #26-Ubuntu SMP PREEMPT_DYNAMIC Mon Jul 10 23:39:54 UTC 2023 x86_64 x86_64 x86_64 GNU/Linux

$ sensors k10temp-pci-00c3
k10temp-pci-00c3
Adapter: PCI adapter
Tctl:         +88.0°C
Tccd1:        +32.2°C
Tccd3:        +34.8°C
Tccd5:        +33.8°C
Tccd7:        +39.5°C

RolloZ170 · Aug 20, 2023

Stofarius said:
Any link for that? The motherboard is brand new and has the latest version of bios as I'm aware. I did a search with google but couldn't find anything.

Thank you!

note Tctl is offsetted and not the die temp. you can patch the kernel or ignore the faulty value.

Stofarius · Aug 20, 2023

Thank you,

Indeee I have Milan and kernel 6.2, i just installed Ubuntu server 22.04.3 lts

dnb · Aug 21, 2023

Stofarius said:
- Is that error from the nvme "normal"? What can I do to fix it.
- when in idle, the value for Tctl seems a little to high for me, am I wrong?

This motherboard allows you to query the temperature using the ipmitool sensor command. Even if you look at the sensors in the BMC web interface, you will see more than what is in your output.

Show me the output of the 'ipmitool sensor' command. I have many screenshots from my same system and we can compare the readings line by line. There is no need to use lm_sensors.

Attached screenshot shows output of 'ipmitool sensor' on h12ssl-i with epyc 7763 at idle.

Stofarius · Aug 22, 2023

dnb said:
This motherboard allows you to query the temperature using the ipmitool sensor command. Even if you look at the sensors in the BMC web interface, you will see more than what is in your output.

Show me the output of the 'ipmitool sensor' command. I have many screenshots from my same system and we can compare the readings line by line. There is no need to use lm_sensors.

Attached screenshot shows output of 'ipmitool sensor' on h12ssl-i with epyc 7763 at idle.

Hi,

Apologies for my delayed answer, here is my output:

dnb · Aug 22, 2023

I am attaching a new screenshot showing my sensors on H12SSL-I+EPYC 7763. These are the maximum temperatures reached at the peak of the mprime test. As you can see, VRMs under mprime load are close to your idle values (as I understand it), which means that your VRMs are somewhat high, although within the normal range.

But the most important thing that I could see from your screenshot is that FAN1 is free, not connected, which means that the processor fan is connected to the wrong connector or is powered directly from the power supply. My guess is that you should connect the CPU fan to the FAN1 header on the board. After that, let's look at the sensor results again. If it's still hot, you need to turn on the rest of the fans except for the processor to full, connecting them to the power supply and thereby removing some load from the board.

In my case, the CPU fan is SNK-P0064AP4. For the rest of the cooling, three AVC DS12025B12L fans are used, operating at a maximum speed of about 2200 rpm. The temperature in the room is about 23-24 degrees Celsius.

In my case, FAN1 is the only fan connected to the motherboard, while the rest are connected directly to the power supply via Noctua SATA->4-pin fan adapters.

Stofarius · Aug 22, 2023

Those were the readings after powering on the system. I'm attaching another screenshot now, with the current values. These seem to be a little bit lower.

I am going to stop the server and move the CPU fan to the FAN1.The temperature in my room is now 29 to 30 degrees Celsius. When my parrots are free in the room, I'm turning off the AC and during the summer is getting hot for some hours

I have 2 fans on my chassis and a cooler for the CPU which I bought from eBay, together with the rest of the components.

vvkvvk · Aug 22, 2023

Well, here's mine.

Code:

$ sudo ipmitool sensor
CPU Temp         | 39,000     | degrees C  | ok    | 5,000     | 5,000     | na        | na        | 100,000   | 100,000
System Temp      | 34,000     | degrees C  | ok    | 5,000     | 5,000     | na        | na        | 85,000    | 90,000
Peripheral Temp  | 39,000     | degrees C  | ok    | 5,000     | 5,000     | na        | na        | 85,000    | 90,000
M2_SSD1 Temp     | na         |            | na    | na        | na        | na        | na        | na        | na
M2_SSD2 Temp     | na         |            | na    | na        | na        | na        | na        | na        | na
CPU_VRM Temp     | 45,000     | degrees C  | ok    | 5,000     | 5,000     | na        | na        | 100,000   | 105,000
SOC_VRM Temp     | 45,000     | degrees C  | ok    | 5,000     | 5,000     | na        | na        | 100,000   | 105,000
VRMABCD Temp     | 44,000     | degrees C  | ok    | 5,000     | 5,000     | na        | na        | 100,000   | 105,000
VRMEFGH Temp     | 52,000     | degrees C  | ok    | 5,000     | 5,000     | na        | na        | 100,000   | 105,000
P1_DIMMA~D Temp  | 48,000     | degrees C  | ok    | 5,000     | 5,000     | na        | na        | 85,000    | 90,000
P1_DIMME~H Temp  | 54,000     | degrees C  | ok    | 5,000     | 5,000     | na        | na        | 85,000    | 90,000
FAN1             | 700,000    | RPM        | ok    | 0,000     | 140,000   | na        | na        | 35560,000 | 35700,000
FAN2             | 700,000    | RPM        | ok    | 0,000     | 140,000   | na        | na        | 35560,000 | 35700,000
FAN3             | 700,000    | RPM        | ok    | 0,000     | 140,000   | na        | na        | 35560,000 | 35700,000
FAN4             | na         |            | na    | na        | na        | na        | na        | na        | na
FAN5             | na         |            | na    | na        | na        | na        | na        | na        | na
FANA             | na         |            | na    | na        | na        | na        | na        | na        | na
FANB             | na         |            | na    | na        | na        | na        | na        | na        | na
12V              | 11,856     | Volts      | ok    | 9,680     | 9,936     | na        | na        | 14,480    | 14,736
5VCC             | 5,020      | Volts      | ok    | 3,940     | 4,030     | na        | na        | 5,920     | 6,010
3.3VCC           | 3,259      | Volts      | ok    | 2,613     | 2,681     | na        | na        | 3,922     | 3,990
VBAT             | 0x4        | discrete   | 0x0400| na        | na        | na        | na        | na        | na
VDDCR            | 1,237      | Volts      | ok    | 0,400     | 0,499     | na        | na        | 1,732     | 1,804
VMEMABCD         | 1,207      | Volts      | ok    | 0,979     | 1,003     | na        | na        | 1,465     | 1,489
VMEMEFGH         | 1,214      | Volts      | ok    | 0,976     | 0,997     | na        | na        | 1,466     | 1,487
VDD_5_DUAL       | 5,129      | Volts      | ok    | 4,019     | 4,139     | na        | na        | 6,029     | 6,149
VDD_33_DUAL      | 3,259      | Volts      | ok    | 2,613     | 2,681     | na        | na        | 3,922     | 3,990
SOCRUN           | 0,819      | Volts      | ok    | 0,297     | 0,489     | na        | na        | 1,143     | 1,341
SOCDUAL          | 0,893      | Volts      | ok    | 0,711     | 0,725     | na        | na        | 1,068     | 1,082
Chassis Intru    | 0x0        | discrete   | 0x0000| na        | na        | na        | na        | na        | na

I run stupid gaming maglev fans with RGB and external fan controller. You know, for home portion of the homelab.

Stofarius · Aug 22, 2023

I moved the CPU fan to FAN1, still 28C in my room. Most probably I need to change the chassis fans, as those are quite old (around 10 years), and maybe I can find something more powerful at the same dimension.

Code:

CPU Temp         | 35.000     | degrees C  | ok    | 5.000     | 5.000     | na        | na        | 100.000   | 100.000   
System Temp      | 40.000     | degrees C  | ok    | 5.000     | 5.000     | na        | na        | 85.000    | 90.000   
Peripheral Temp  | 43.000     | degrees C  | ok    | 5.000     | 5.000     | na        | na        | 85.000    | 90.000   
M2_SSD1 Temp     | na         |            | na    | na        | na        | na        | na        | na        | na       
M2_SSD2 Temp     | na         |            | na    | na        | na        | na        | na        | na        | na       
CPU_VRM Temp     | 46.000     | degrees C  | ok    | 5.000     | 5.000     | na        | na        | 100.000   | 105.000   
SOC_VRM Temp     | 43.000     | degrees C  | ok    | 5.000     | 5.000     | na        | na        | 100.000   | 105.000   
VRMABCD Temp     | 47.000     | degrees C  | ok    | 5.000     | 5.000     | na        | na        | 100.000   | 105.000   
VRMEFGH Temp     | 48.000     | degrees C  | ok    | 5.000     | 5.000     | na        | na        | 100.000   | 105.000   
P1_DIMMA~D Temp  | 45.000     | degrees C  | ok    | 5.000     | 5.000     | na        | na        | 85.000    | 90.000   
P1_DIMME~H Temp  | 42.000     | degrees C  | ok    | 5.000     | 5.000     | na        | na        | 85.000    | 90.000   
FAN1             | 1120.000   | RPM        | ok    | 280.000   | 420.000   | na        | na        | 35560.000 | 35700.000
FAN2             | na         |            | na    | na        | na        | na        | na        | na        | na       
FAN3             | 840.000    | RPM        | ok    | 280.000   | 420.000   | na        | na        | 35560.000 | 35700.000
FAN4             | 840.000    | RPM        | ok    | 280.000   | 420.000   | na        | na        | 35560.000 | 35700.000
FAN5             | na         |            | na    | na        | na        | na        | na        | na        | na       
FANA             | na         |            | na    | na        | na        | na        | na        | na        | na       
FANB             | na         |            | na    | na        | na        | na        | na        | na        | na       
12V              | 11.984     | Volts      | ok    | 9.680     | 9.936     | na        | na        | 14.480    | 14.736   
5VCC             | 4.900      | Volts      | ok    | 3.940     | 4.030     | na        | na        | 5.920     | 6.010     
3.3VCC           | 3.293      | Volts      | ok    | 2.613     | 2.681     | na        | na        | 3.922     | 3.990     
VBAT             | 0x4        | discrete   | 0x0400| na        | na        | na        | na        | na        | na       
VDDCR            | 0.814      | Volts      | ok    | 0.400     | 0.499     | na        | na        | 1.732     | 1.804     
VMEMABCD         | 1.219      | Volts      | ok    | 0.979     | 1.003     | na        | na        | 1.465     | 1.489     
VMEMEFGH         | 1.221      | Volts      | ok    | 0.976     | 0.997     | na        | na        | 1.466     | 1.487     
VDD_5_DUAL       | 5.039      | Volts      | ok    | 4.019     | 4.139     | na        | na        | 6.029     | 6.149     
VDD_33_DUAL      | 3.310      | Volts      | ok    | 2.613     | 2.681     | na        | na        | 3.922     | 3.990     
SOCRUN           | 0.855      | Volts      | ok    | 0.297     | 0.489     | na        | na        | 1.143     | 1.341     
SOCDUAL          | 0.893      | Volts      | ok    | 0.711     | 0.725     | na        | na        | 1.068     | 1.082     
Chassis Intru    | 0x0        | discrete   | 0x0000| na        | na        | na        | na        | na        | na

Search

H12SSL-I and sensors

Stofarius

Member

bitbckt

will google compiler errors for scotch

Stofarius

Member

bitbckt

will google compiler errors for scotch

RolloZ170

Well-Known Member

Stofarius

Member

vvkvvk

Member

RolloZ170

Well-Known Member

Stofarius

Member

dnb

Member

Attachments

Stofarius

Member

Attachments

dnb

Member

Attachments

Stofarius

Member

Attachments

vvkvvk

Member

Stofarius

Member