nvidia-gpu: add TLimit sensor
This commit introduces a new thermal limit (TLimit) sensor for the GPU,
enhancing the existing temperature monitoring capabilities.
Tested: Build an image for gb200nvl-obmc machine with the following
patches cherry picked. This patches are needed to enable the mctp stack.
https://gerrit.openbmc.org/c/openbmc/openbmc/+/79422
```
$ curl -s -k -u 'root:0penBmc' https://10.137.203.137/redfish/v1/Chassis/NVIDIA_GB200_1/Sensors/temperature_NVIDIA_GB200_GPU_0_TEMP_1
{
"@odata.id": "/redfish/v1/Chassis/NVIDIA_GB200_1/Sensors/temperature_NVIDIA_GB200_GPU_0_TEMP_1",
"@odata.type": "#Sensor.v1_2_0.Sensor",
"Id": "temperature_NVIDIA_GB200_GPU_0_TEMP_1",
"Name": "NVIDIA GB200 GPU 0 TEMP 1",
"Reading": 57.3984375,
"ReadingRangeMax": 127.0,
"ReadingRangeMin": -128.0,
"ReadingType": "Temperature",
"ReadingUnits": "Cel",
"Status": {
"Health": "OK",
"State": "Enabled"
}
}%
```
Change-Id: Ib8e0ef93a4acbb8870671665b098fb61d0205cb2
Signed-off-by: Harshit Aghera <haghera@nvidia.com>
diff --git a/src/nvidia-gpu/NvidiaGpuSensor.hpp b/src/nvidia-gpu/NvidiaGpuSensor.hpp
index 25fe069..1e21f4d 100644
--- a/src/nvidia-gpu/NvidiaGpuSensor.hpp
+++ b/src/nvidia-gpu/NvidiaGpuSensor.hpp
@@ -20,17 +20,20 @@
#include <string>
#include <vector>
+constexpr uint8_t gpuTempSensorId{0};
+constexpr uint8_t gpuTLimitSensorId{2};
+
struct NvidiaGpuTempSensor :
public Sensor,
public std::enable_shared_from_this<NvidiaGpuTempSensor>
{
public:
- NvidiaGpuTempSensor(std::shared_ptr<sdbusplus::asio::connection>& conn,
- mctp::MctpRequester& mctpRequester,
- const std::string& name,
- const std::string& sensorConfiguration, uint8_t eid,
- sdbusplus::asio::object_server& objectServer,
- std::vector<thresholds::Threshold>&& thresholdData);
+ NvidiaGpuTempSensor(
+ std::shared_ptr<sdbusplus::asio::connection>& conn,
+ mctp::MctpRequester& mctpRequester, const std::string& name,
+ const std::string& sensorConfiguration, uint8_t eid, uint8_t sensorId,
+ sdbusplus::asio::object_server& objectServer,
+ std::vector<thresholds::Threshold>&& thresholdData);
~NvidiaGpuTempSensor() override;