nvidia-gpu: add Power Sensor PeakReading Property
Add support for Sensor Properties PeakReading and PeakRedingTime.
Current Limitation -
The ResetMetrics action is currently not supported for Redfish URIs in
bmcweb. As a result, the ability to clear PeakReading values for GPU
Power Sensors has not been implemented.
Future Consideration -
If ResetMetrics action support is added to bmcweb in the future, the
corresponding functionality will also need to be implemented in the
dbus-sensor application to ensure full compatibility.
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
```
root@gb200nvl-obmc:~# busctl introspect xyz.openbmc_project.GpuSensor /xyz/openbmc_project/sensors/power/NVIDIA_GB200_GPU_0_Power_0
NAME TYPE SIGNATURE RESULT/VALUE FLAGS
org.freedesktop.DBus.Introspectable interface - - -
.Introspect method - s -
org.freedesktop.DBus.Peer interface - - -
.GetMachineId method - s -
.Ping method - - -
org.freedesktop.DBus.Properties interface - - -
.Get method ss v -
.GetAll method s a{sv} -
.Set method ssv - -
.PropertiesChanged signal sa{sv}as - -
xyz.openbmc_project.Association.Definitions interface - - -
.Associations property a(sss) 1 "chassis" "all_sensors" "/xyz/openb... emits-change
xyz.openbmc_project.Sensor.Value interface - - -
.MaxValue property d 5000 emits-change
.MinValue property d 0 emits-change
.Unit property s "xyz.openbmc_project.Sensor.Value.Uni... emits-change
.Value property d 29.194 emits-change writable
xyz.openbmc_project.Sensor.ValueMutability interface - - -
.Mutable property b true emits-change
xyz.openbmc_project.State.Decorator.Availability interface - - -
.Available property b true emits-change writable
xyz.openbmc_project.State.Decorator.OperationalStatus interface - - -
.Functional property b true emits-change
xyz.openbmc_project.Telemetry.Report interface - - -
.Readings property (ta(ssdt)) 0 1 "PeakReading" "" 80.933 0 emits-change
```
Change-Id: I0a4f7eb0a5db688f32bf80954839140da9bb7e2a
Signed-off-by: Harshit Aghera <haghera@nvidia.com>
diff --git a/src/nvidia-gpu/NvidiaGpuMctpVdm.hpp b/src/nvidia-gpu/NvidiaGpuMctpVdm.hpp
index 19b9929..1e8e986 100644
--- a/src/nvidia-gpu/NvidiaGpuMctpVdm.hpp
+++ b/src/nvidia-gpu/NvidiaGpuMctpVdm.hpp
@@ -40,6 +40,7 @@
GET_TEMPERATURE_READING = 0x00,
READ_THERMAL_PARAMETERS = 0x02,
GET_CURRENT_POWER_DRAW = 0x03,
+ GET_MAX_OBSERVED_POWER = 0x04,
GET_CURRENT_ENERGY_COUNTER = 0x06,
GET_INVENTORY_INFORMATION = 0x0C,
GET_VOLTAGE = 0x0F,
@@ -114,7 +115,7 @@
using ReadThermalParametersRequest = GetNumericSensorReadingRequest;
-struct GetCurrentPowerDrawRequest
+struct GetPowerDrawRequest
{
ocp::accelerator_management::CommonRequest hdr;
uint8_t sensorId;
@@ -137,7 +138,7 @@
int32_t threshold;
} __attribute__((packed));
-struct GetCurrentPowerDrawResponse
+struct GetPowerDrawResponse
{
ocp::accelerator_management::CommonResponse hdr;
uint32_t power;
@@ -194,14 +195,13 @@
ocp::accelerator_management::CompletionCode& cc, uint16_t& reasonCode,
int32_t& threshold);
-int encodeGetCurrentPowerDrawRequest(uint8_t instanceId, uint8_t sensorId,
- uint8_t averagingInterval,
- std::span<uint8_t> buf);
+int encodeGetPowerDrawRequest(
+ PlatformEnvironmentalCommands commandCode, uint8_t instanceId,
+ uint8_t sensorId, uint8_t averagingInterval, std::span<uint8_t> buf);
-int decodeGetCurrentPowerDrawResponse(
- std::span<const uint8_t> buf,
- ocp::accelerator_management::CompletionCode& cc, uint16_t& reasonCode,
- uint32_t& power);
+int decodeGetPowerDrawResponse(std::span<const uint8_t> buf,
+ ocp::accelerator_management::CompletionCode& cc,
+ uint16_t& reasonCode, uint32_t& power);
int encodeGetCurrentEnergyCounterRequest(uint8_t instanceId, uint8_t sensorId,
std::span<uint8_t> buf);