AI/rocm-systems
2
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

RDC module framework

Browse Source 
The framework is required for RAS integration. When the RAS fields
need to be retrieved, the framework will load the RAS library at run time,
and then call the RAS function to retrieve RAS metrics.

* The RdcModuleMgr will be used to manage different modules. RDC
  only has the telemetry module now.
* When RDCTelemetryModule is loaded, it will load the RAS library.
  It will also call rdc_telemetry_fields_query() defined in the RAS
  library for the list of fields RAS supported.
* The RdcSmiLib is a wrapper for the rocm_msi_lib to provide the
  interface required by the RDCTelemetryModule.
* The RdcWatchTable will use the RdcModuleMgr to get the
  RDCTelemetryModule to bulk fetch mulitple fields.
* The RdcTelemetryModule will dispatch those fields to different
  library: RdcSmiLib or RdcRasLib.

The watch() and unwatch() in the RDCTelemetryModule will been implemented
at the next task.

Change-Id: I81b01d5b52d1ea3cdcec7c09af86b6622dd5899e
This commit is contained in:
Bill(Shuzhou) Liu committed 2020-09-02 14:46:40 -04:00
1 parent bf412e3f76
commit ba35cdcfe2
19 files changed
+934 -72
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

common/rdc_field_data.data
+12 -12
View File
@@ -29,21 +29,21 @@ THE SOFTWARE.
// 4 bool do or do not display in rdci
// rdc_field_t Description rdci label To Display
// =========== =========== ========= ==========
FLD_DESC_ENT(RDC_FI_INVALID, "Unknown/Invalid field", "INVALID", true)
FLD_DESC_ENT(RDC_FI_INVALID, "Unknown/Invalid field", "INVALID", false)
FLD_DESC_ENT(RDC_FI_GPU_COUNT, "GPU count in the system", "GPU_COUNT", true)
FLD_DESC_ENT(RDC_FI_DEV_NAME, "Name of the device", "DEV_NAME", true)
FLD_DESC_ENT(RDC_FI_GPU_CLOCK, "Current GPU clock frequencies.", "GPU_CLOCK", true)
FLD_DESC_ENT(RDC_FI_MEM_CLOCK, "Current Memory clock frequencies.", "MEM_CLOCK", true)
FLD_DESC_ENT(RDC_FI_MEMORY_TEMP, "Memory temperature in millidegrees Celsius.", "MEMORY_TEMP", true)
FLD_DESC_ENT(RDC_FI_GPU_TEMP, "GPU temperature in millidegrees Celsius.", "GPU_TEMP", true)
FLD_DESC_ENT(RDC_FI_POWER_USAGE, "Power usage in microwatts.", "POWER_USAGE", true)
FLD_DESC_ENT(RDC_FI_PCIE_TX, "PCIe Tx utilization in bytes/second.", "PCIE_TX", true)
FLD_DESC_ENT(RDC_FI_PCIE_RX, "PCIe Rx utilization in bytes/second.", "PCIE_RX", true)
FLD_DESC_ENT(RDC_FI_GPU_UTIL, "GPU busy percentage.", "GPU_UTIL", true)
FLD_DESC_ENT(RDC_FI_GPU_MEMORY_USAGE, "Memory usage of the GPU instance in bytes.", "GPU_MEMORY_USAGE", true)
FLD_DESC_ENT(RDC_FI_GPU_CLOCK, "Current GPU clock frequencies", "GPU_CLOCK", true)
FLD_DESC_ENT(RDC_FI_MEM_CLOCK, "Current Memory clock frequencies", "MEM_CLOCK", true)
FLD_DESC_ENT(RDC_FI_MEMORY_TEMP, "Memory temperature in millidegrees Celsius", "MEMORY_TEMP", true)
FLD_DESC_ENT(RDC_FI_GPU_TEMP, "GPU temperature in millidegrees Celsius", "GPU_TEMP", true)
FLD_DESC_ENT(RDC_FI_POWER_USAGE, "Power usage in microwatts", "POWER_USAGE", true)
FLD_DESC_ENT(RDC_FI_PCIE_TX, "PCIe Tx utilization in bytes/second", "PCIE_TX", true)
FLD_DESC_ENT(RDC_FI_PCIE_RX, "PCIe Rx utilization in bytes/second", "PCIE_RX", true)
FLD_DESC_ENT(RDC_FI_GPU_UTIL, "GPU busy percentage", "GPU_UTIL", true)
FLD_DESC_ENT(RDC_FI_GPU_MEMORY_USAGE, "Memory usage of the GPU instance in bytes", "GPU_MEMORY_USAGE", true)
FLD_DESC_ENT(RDC_FI_GPU_MEMORY_TOTAL, "Total memory of the GPU instance", "GPU_MEMORY_TOTAL", true)
FLD_DESC_ENT(RDC_FI_ECC_CORRECT_TOTAL, "Accumulated correctable ECC errors.", "ECC_CORRECT", true)
FLD_DESC_ENT(RDC_FI_ECC_UNCORRECT_TOTAL, "Accumulated uncorrectable ECC errors.", "ECC_UNCORRECT", true)
FLD_DESC_ENT(RDC_FI_ECC_CORRECT_TOTAL, "Accumulated correctable ECC errors", "ECC_CORRECT", true)
FLD_DESC_ENT(RDC_FI_ECC_UNCORRECT_TOTAL, "Accumulated uncorrectable ECC errors", "ECC_UNCORRECT", true)
FLD_DESC_ENT(RDC_EVNT_XGMI_0_NOP_TX, "NOPs sent to neighbor 0", "XGMI_NOP_0", false)
FLD_DESC_ENT(RDC_EVNT_XGMI_0_REQ_TX, "Outgoing requests to neighbor 0", "XGMI_REQ_0", false)