AI/rocm-systems
2
0
Förgrening 0
Kod Ärenden Pull-förfrågningar Actions Packages Projekt Släpp Wiki Aktiviteter

[SWDEV-230863] Improve the functionality of RdcSmiHealth module.

Bläddra i källkod 
Memory check:get the threshold of retired page number
EEPROM check:read and verify the checksum
Power/Thermal check: power/thermal throttle status counter

Signed-off-by: Meng Li <li.meng@amd.com>
Change-Id: Id2c751416eb5bf007e6e1da8dc05966a6ba1324e
This commit is contained in:
limeng12
2025-01-09 13:52:56 +08:00
committad av Meng, Li (Jassmine)
förälder 83f36f1673
incheckning 016a1d9d39
11 ändrade filer med 307 tillägg och 72 borttagningar
Download Patch File Download Diff File Expand all files Collapse all files
example/health_example.cc
+11 -3
Visa fil
@@ -45,6 +45,12 @@ rdc_status_t get_watches(rdc_handle_t rdc_handle, rdc_gpu_group_t group_id) {
<< std::setw(50) << std::left << ((components & RDC_HEALTH_WATCH_XGMI) ? on : off).c_str() << "|\n";
std::cout << "|" << std::setw(20) << std::left << " Memory" << "| "
<< std::setw(50) << std::left << ((components & RDC_HEALTH_WATCH_MEM) ? on : off).c_str() << "|\n";
std::cout << "|" << std::setw(20) << std::left << " EEPROM" << "| "
<< std::setw(50) << std::left << ((components & RDC_HEALTH_WATCH_EEPROM) ? on : off).c_str() << "|\n";
std::cout << "|" << std::setw(20) << std::left << " Thermal" << "| "
<< std::setw(50) << std::left << ((components & RDC_HEALTH_WATCH_THERMAL) ? on : off).c_str() << "|\n";
std::cout << "|" << std::setw(20) << std::left << " Power" << "| "
<< std::setw(50) << std::left << ((components & RDC_HEALTH_WATCH_POWER) ? on : off).c_str() << "|\n";
std::cout << "+--------------------+" //"-" width :20
<< "---------------------------------------------------+\n"; //-" width :51
}
@@ -79,8 +85,8 @@ std::string component_string(rdc_health_system_t component) {
case RDC_HEALTH_WATCH_MEM:
return "Memory system: ";
case RDC_HEALTH_WATCH_INFOROM:
return "Inforom system: ";
case RDC_HEALTH_WATCH_EEPROM:
return "EEPROM system: ";
case RDC_HEALTH_WATCH_THERMAL:
return "Thermal system:";
@@ -280,7 +286,9 @@ int main(int, char**) {
// (3) set health watches.
unsigned int components;
components = RDC_HEALTH_WATCH_PCIE | RDC_HEALTH_WATCH_XGMI | RDC_HEALTH_WATCH_MEM;
components = RDC_HEALTH_WATCH_PCIE | RDC_HEALTH_WATCH_XGMI | RDC_HEALTH_WATCH_MEM
| RDC_HEALTH_WATCH_EEPROM | RDC_HEALTH_WATCH_THERMAL
| RDC_HEALTH_WATCH_POWER;
result = rdc_health_set(rdc_handle, group_id, components);
if (result != RDC_ST_OK) {
std::cout << "Error setting health watches. Return: " << rdc_status_string(result)