| 1 | { |
| 2 | "generated_at": "2026-02-07T22:04:51Z", |
| 3 | "method": "direct-dcgm-exporter-process-on-port-19400", |
| 4 | "total_fields": 623, |
| 5 | "profiles": [ |
| 6 | { |
| 7 | "profile": 1, |
| 8 | "original_fields_count": 127, |
| 9 | "startup_fail_fields_count": 2, |
| 10 | "startup_fail_fields": [ |
| 11 | "DCGM_FI_BIND_UNBIND_EVENT", |
| 12 | "DCGM_FI_LAST_NVSWITCH_FIELD_ID" |
| 13 | ], |
| 14 | "non_numeric_fields": [ |
| 15 | "DCGM_FI_DEV_MIG_GI_INFO", |
| 16 | "DCGM_FI_DEV_VGPU_PER_PROCESS_UTILIZATION" |
| 17 | ], |
| 18 | "numeric_seen_count": 53, |
| 19 | "remaining_after_startup_filter": 125 |
| 20 | }, |
| 21 | { |
| 22 | "profile": 2, |
| 23 | "original_fields_count": 127, |
| 24 | "startup_fail_fields_count": 4, |
| 25 | "startup_fail_fields": [ |
| 26 | "DCGM_FI_DEV_CPU_POWER_UTIL_CURRENT", |
| 27 | "DCGM_FI_DEV_CPU_TEMP_CRITICAL", |
| 28 | "DCGM_FI_DEV_NVLINK_GET_STATE", |
| 29 | "DCGM_FI_LAST_VGPU_FIELD_ID" |
| 30 | ], |
| 31 | "non_numeric_fields": [ |
| 32 | "DCGM_FI_DEV_CREATABLE_VGPU_TYPE_IDS", |
| 33 | "DCGM_FI_DEV_ENFORCED_POWER_PROFILE_MASK", |
| 34 | "DCGM_FI_DEV_REQUESTED_POWER_PROFILE_MASK", |
| 35 | "DCGM_FI_DEV_SUPPORTED_VGPU_TYPE_IDS", |
| 36 | "DCGM_FI_DEV_VGPU_INSTANCE_IDS" |
| 37 | ], |
| 38 | "numeric_seen_count": 46, |
| 39 | "remaining_after_startup_filter": 123 |
| 40 | }, |
| 41 | { |
| 42 | "profile": 3, |
| 43 | "original_fields_count": 127, |
| 44 | "startup_fail_fields_count": 6, |
| 45 | "startup_fail_fields": [ |
| 46 | "DCGM_FI_DEV_DIAG_NCCL_TESTS_RESULT", |
| 47 | "DCGM_FI_DEV_LAST_CONNECTX_FIELD_ID", |
| 48 | "DCGM_FI_DEV_MEMORY_UNREPAIRABLE_FLAG", |
| 49 | "DCGM_FI_DEV_NVLINK_PPCNT_IBPC_PORT_XMIT_WAIT", |
| 50 | "DCGM_FI_DEV_PCIE_COUNT_CORRECTABLE_ERRORS", |
| 51 | "DCGM_FI_IMEX_DAEMON_STATUS" |
| 52 | ], |
| 53 | "non_numeric_fields": [ |
| 54 | "DCGM_FI_DEV_CREATABLE_VGPU_TYPE_IDS", |
| 55 | "DCGM_FI_DEV_FBC_SESSIONS_INFO", |
| 56 | "DCGM_FI_DEV_VGPU_TYPE_CLASS" |
| 57 | ], |
| 58 | "numeric_seen_count": 52, |
| 59 | "remaining_after_startup_filter": 121 |
| 60 | }, |
| 61 | { |
| 62 | "profile": 4, |
| 63 | "original_fields_count": 127, |
| 64 | "startup_fail_fields_count": 5, |
| 65 | "startup_fail_fields": [ |
| 66 | "DCGM_FI_DEV_CPU_POWER_UTIL_CURRENT", |
| 67 | "DCGM_FI_DEV_FIRST_CONNECTX_FIELD_ID", |
| 68 | "DCGM_FI_DEV_NVLINK_ECC_DATA_ERROR_COUNT_TOTAL", |
| 69 | "DCGM_FI_FIRST_NVSWITCH_FIELD_ID", |
| 70 | "DCGM_FI_IMEX_DOMAIN_STATUS" |
| 71 | ], |
| 72 | "non_numeric_fields": [ |
| 73 | "DCGM_FI_DEV_FBC_STATS" |
| 74 | ], |
| 75 | "numeric_seen_count": 34, |
| 76 | "remaining_after_startup_filter": 122 |
| 77 | }, |
| 78 | { |
| 79 | "profile": 5, |
| 80 | "original_fields_count": 127, |
| 81 | "startup_fail_fields_count": 5, |
| 82 | "startup_fail_fields": [ |
| 83 | "DCGM_FI_DEV_CPU_TEMP_CRITICAL", |
| 84 | "DCGM_FI_DEV_FABRIC_HEALTH_MASK", |
| 85 | "DCGM_FI_DEV_FIRST_CONNECTX_FIELD_ID", |
| 86 | "DCGM_FI_DEV_GET_GPU_RECOVERY_ACTION", |
| 87 | "DCGM_FI_INTERNAL_FIELDS_0_END" |
| 88 | ], |
| 89 | "non_numeric_fields": [ |
| 90 | "DCGM_FI_DEV_ENC_STATS", |
| 91 | "DCGM_FI_DEV_ENFORCED_POWER_PROFILE_MASK", |
| 92 | "DCGM_FI_DEV_FBC_SESSIONS_INFO", |
| 93 | "DCGM_FI_DEV_FBC_STATS", |
| 94 | "DCGM_FI_DEV_MIG_ATTRIBUTES", |
| 95 | "DCGM_FI_DEV_VGPU_TYPE_LICENSE" |
| 96 | ], |
| 97 | "numeric_seen_count": 48, |
| 98 | "remaining_after_startup_filter": 122 |
| 99 | }, |
| 100 | { |
| 101 | "profile": 6, |
| 102 | "original_fields_count": 127, |
| 103 | "startup_fail_fields_count": 4, |
| 104 | "startup_fail_fields": [ |
| 105 | "DCGM_FI_DEV_DIAG_NCCL_TESTS_RESULT", |
| 106 | "DCGM_FI_DEV_LAST_CONNECTX_FIELD_ID", |
| 107 | "DCGM_FI_DEV_MEMORY_UNREPAIRABLE_FLAG", |
| 108 | "DCGM_FI_INTERNAL_FIELDS_0_START" |
| 109 | ], |
| 110 | "non_numeric_fields": [ |
| 111 | "DCGM_FI_DEV_MIG_ATTRIBUTES", |
| 112 | "DCGM_FI_DEV_MIG_CI_INFO", |
| 113 | "DCGM_FI_DEV_MIG_GI_INFO", |
| 114 | "DCGM_FI_DEV_PLATFORM_INFINIBAND_GUID", |
| 115 | "DCGM_FI_DEV_SUPPORTED_CLOCKS", |
| 116 | "DCGM_FI_DEV_VALID_POWER_PROFILE_MASK", |
| 117 | "DCGM_FI_GPU_TOPOLOGY_AFFINITY" |
| 118 | ], |
| 119 | "numeric_seen_count": 51, |
| 120 | "remaining_after_startup_filter": 123 |
| 121 | } |
| 122 | ], |
| 123 | "classification": { |
| 124 | "startup_fail_fields": [ |
| 125 | "DCGM_FI_BIND_UNBIND_EVENT", |
| 126 | "DCGM_FI_DEV_CPU_POWER_UTIL_CURRENT", |
| 127 | "DCGM_FI_DEV_CPU_TEMP_CRITICAL", |
| 128 | "DCGM_FI_DEV_DIAG_NCCL_TESTS_RESULT", |
| 129 | "DCGM_FI_DEV_FABRIC_HEALTH_MASK", |
| 130 | "DCGM_FI_DEV_FIRST_CONNECTX_FIELD_ID", |
| 131 | "DCGM_FI_DEV_GET_GPU_RECOVERY_ACTION", |
| 132 | "DCGM_FI_DEV_LAST_CONNECTX_FIELD_ID", |
| 133 | "DCGM_FI_DEV_MEMORY_UNREPAIRABLE_FLAG", |
| 134 | "DCGM_FI_DEV_NVLINK_ECC_DATA_ERROR_COUNT_TOTAL", |
| 135 | "DCGM_FI_DEV_NVLINK_GET_STATE", |
| 136 | "DCGM_FI_DEV_NVLINK_PPCNT_IBPC_PORT_XMIT_WAIT", |
| 137 | "DCGM_FI_DEV_PCIE_COUNT_CORRECTABLE_ERRORS", |
| 138 | "DCGM_FI_FIRST_NVSWITCH_FIELD_ID", |
| 139 | "DCGM_FI_IMEX_DAEMON_STATUS", |
| 140 | "DCGM_FI_IMEX_DOMAIN_STATUS", |
| 141 | "DCGM_FI_INTERNAL_FIELDS_0_END", |
| 142 | "DCGM_FI_INTERNAL_FIELDS_0_START", |
| 143 | "DCGM_FI_LAST_NVSWITCH_FIELD_ID", |
| 144 | "DCGM_FI_LAST_VGPU_FIELD_ID" |
| 145 | ], |
| 146 | "non_numeric_fields": [ |
| 147 | "DCGM_FI_DEV_CREATABLE_VGPU_TYPE_IDS", |
| 148 | "DCGM_FI_DEV_ENC_STATS", |
| 149 | "DCGM_FI_DEV_ENFORCED_POWER_PROFILE_MASK", |
| 150 | "DCGM_FI_DEV_FBC_SESSIONS_INFO", |
| 151 | "DCGM_FI_DEV_FBC_STATS", |
| 152 | "DCGM_FI_DEV_MIG_ATTRIBUTES", |
| 153 | "DCGM_FI_DEV_MIG_CI_INFO", |
| 154 | "DCGM_FI_DEV_MIG_GI_INFO", |
| 155 | "DCGM_FI_DEV_PLATFORM_INFINIBAND_GUID", |
| 156 | "DCGM_FI_DEV_REQUESTED_POWER_PROFILE_MASK", |
| 157 | "DCGM_FI_DEV_SUPPORTED_CLOCKS", |
| 158 | "DCGM_FI_DEV_SUPPORTED_VGPU_TYPE_IDS", |
| 159 | "DCGM_FI_DEV_VALID_POWER_PROFILE_MASK", |
| 160 | "DCGM_FI_DEV_VGPU_INSTANCE_IDS", |
| 161 | "DCGM_FI_DEV_VGPU_PER_PROCESS_UTILIZATION", |
| 162 | "DCGM_FI_DEV_VGPU_TYPE_CLASS", |
| 163 | "DCGM_FI_DEV_VGPU_TYPE_LICENSE", |
| 164 | "DCGM_FI_GPU_TOPOLOGY_AFFINITY" |
| 165 | ], |
| 166 | "numeric_seen_fields": [ |
| 167 | "DCGM_FI_DEV_ACCOUNTING_DATA", |
| 168 | "DCGM_FI_DEV_BAR1_FREE", |
| 169 | "DCGM_FI_DEV_BAR1_TOTAL", |
| 170 | "DCGM_FI_DEV_BAR1_USED", |
| 171 | "DCGM_FI_DEV_BOARD_LIMIT_VIOLATION", |
| 172 | "DCGM_FI_DEV_C2C_LINK_ERROR_INTR", |
| 173 | "DCGM_FI_DEV_C2C_LINK_ERROR_REPLAY", |
| 174 | "DCGM_FI_DEV_C2C_LINK_ERROR_REPLAY_B2B", |
| 175 | "DCGM_FI_DEV_C2C_LINK_POWER_STATE", |
| 176 | "DCGM_FI_DEV_CC_MODE", |
| 177 | "DCGM_FI_DEV_CLOCKS_EVENT_REASONS", |
| 178 | "DCGM_FI_DEV_CLOCKS_EVENT_REASON_HW_POWER_BRAKE_SLOWDOWN_NS", |
| 179 | "DCGM_FI_DEV_CLOCKS_EVENT_REASON_HW_THERM_SLOWDOWN_NS", |
| 180 | "DCGM_FI_DEV_CLOCKS_EVENT_REASON_SW_POWER_CAP_NS", |
| 181 | "DCGM_FI_DEV_CLOCKS_EVENT_REASON_SW_THERM_SLOWDOWN_NS", |
| 182 | "DCGM_FI_DEV_CLOCKS_EVENT_REASON_SYNC_BOOST_NS", |
| 183 | "DCGM_FI_DEV_COMPUTE_MODE", |
| 184 | "DCGM_FI_DEV_COUNT", |
| 185 | "DCGM_FI_DEV_CPU_AFFINITY_0", |
| 186 | "DCGM_FI_DEV_CPU_AFFINITY_1", |
| 187 | "DCGM_FI_DEV_CPU_AFFINITY_2", |
| 188 | "DCGM_FI_DEV_CPU_AFFINITY_3", |
| 189 | "DCGM_FI_DEV_CUDA_COMPUTE_CAPABILITY", |
| 190 | "DCGM_FI_DEV_DEC_UTIL", |
| 191 | "DCGM_FI_DEV_DIAG_CPU_EUD_RESULT", |
| 192 | "DCGM_FI_DEV_DIAG_DIAGNOSTIC_RESULT", |
| 193 | "DCGM_FI_DEV_DIAG_EUD_RESULT", |
| 194 | "DCGM_FI_DEV_DIAG_MEMORY_BANDWIDTH_RESULT", |
| 195 | "DCGM_FI_DEV_DIAG_MEMORY_RESULT", |
| 196 | "DCGM_FI_DEV_DIAG_MEMTEST_RESULT", |
| 197 | "DCGM_FI_DEV_DIAG_NVBANDWIDTH_RESULT", |
| 198 | "DCGM_FI_DEV_DIAG_PCIE_RESULT", |
| 199 | "DCGM_FI_DEV_DIAG_PULSE_TEST_RESULT", |
| 200 | "DCGM_FI_DEV_DIAG_SOFTWARE_RESULT", |
| 201 | "DCGM_FI_DEV_DIAG_STATUS", |
| 202 | "DCGM_FI_DEV_DIAG_TARGETED_POWER_RESULT", |
| 203 | "DCGM_FI_DEV_DIAG_TARGETED_STRESS_RESULT", |
| 204 | "DCGM_FI_DEV_ECC_DBE_AGG_TOTAL", |
| 205 | "DCGM_FI_DEV_ECC_DBE_VOL_TOTAL", |
| 206 | "DCGM_FI_DEV_ECC_SBE_AGG_TOTAL", |
| 207 | "DCGM_FI_DEV_ECC_SBE_VOL_TOTAL", |
| 208 | "DCGM_FI_DEV_ENC_UTIL", |
| 209 | "DCGM_FI_DEV_ENFORCED_POWER_LIMIT", |
| 210 | "DCGM_FI_DEV_FABRIC_CLIQUE_ID", |
| 211 | "DCGM_FI_DEV_FABRIC_MANAGER_STATUS", |
| 212 | "DCGM_FI_DEV_FAN_SPEED", |
| 213 | "DCGM_FI_DEV_FB_FREE", |
| 214 | "DCGM_FI_DEV_FB_RESERVED", |
| 215 | "DCGM_FI_DEV_FB_TOTAL", |
| 216 | "DCGM_FI_DEV_FB_USED", |
| 217 | "DCGM_FI_DEV_FB_USED_PERCENT", |
| 218 | "DCGM_FI_DEV_GPM_SUPPORT", |
| 219 | "DCGM_FI_DEV_GPU_MAX_OP_TEMP", |
| 220 | "DCGM_FI_DEV_GPU_NVLINK_ERRORS", |
| 221 | "DCGM_FI_DEV_GPU_TEMP", |
| 222 | "DCGM_FI_DEV_GPU_TEMP_LIMIT", |
| 223 | "DCGM_FI_DEV_GPU_UTIL", |
| 224 | "DCGM_FI_DEV_LOW_UTIL_VIOLATION", |
| 225 | "DCGM_FI_DEV_MAX_MEM_CLOCK", |
| 226 | "DCGM_FI_DEV_MAX_SM_CLOCK", |
| 227 | "DCGM_FI_DEV_MAX_VIDEO_CLOCK", |
| 228 | "DCGM_FI_DEV_MEMORY_TEMP", |
| 229 | "DCGM_FI_DEV_MEM_AFFINITY_0", |
| 230 | "DCGM_FI_DEV_MEM_AFFINITY_1", |
| 231 | "DCGM_FI_DEV_MEM_AFFINITY_2", |
| 232 | "DCGM_FI_DEV_MEM_AFFINITY_3", |
| 233 | "DCGM_FI_DEV_MEM_CLOCK", |
| 234 | "DCGM_FI_DEV_MEM_COPY_UTIL", |
| 235 | "DCGM_FI_DEV_MIG_MAX_SLICES", |
| 236 | "DCGM_FI_DEV_MIG_MODE", |
| 237 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_L0", |
| 238 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_L1", |
| 239 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_L10", |
| 240 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_L11", |
| 241 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_L12", |
| 242 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_L13", |
| 243 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_L14", |
| 244 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_L15", |
| 245 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_L16", |
| 246 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_L17", |
| 247 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_L2", |
| 248 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_L3", |
| 249 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_L4", |
| 250 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_L5", |
| 251 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_L6", |
| 252 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_L7", |
| 253 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_L8", |
| 254 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_L9", |
| 255 | "DCGM_FI_DEV_NVLINK_BANDWIDTH_TOTAL", |
| 256 | "DCGM_FI_DEV_NVLINK_COUNT_FEC_HISTORY_0", |
| 257 | "DCGM_FI_DEV_NVLINK_COUNT_FEC_HISTORY_1", |
| 258 | "DCGM_FI_DEV_NVLINK_COUNT_FEC_HISTORY_10", |
| 259 | "DCGM_FI_DEV_NVLINK_COUNT_FEC_HISTORY_11", |
| 260 | "DCGM_FI_DEV_NVLINK_COUNT_FEC_HISTORY_12", |
| 261 | "DCGM_FI_DEV_NVLINK_COUNT_FEC_HISTORY_13", |
| 262 | "DCGM_FI_DEV_NVLINK_COUNT_FEC_HISTORY_14", |
| 263 | "DCGM_FI_DEV_NVLINK_COUNT_FEC_HISTORY_15", |
| 264 | "DCGM_FI_DEV_NVLINK_COUNT_FEC_HISTORY_2", |
| 265 | "DCGM_FI_DEV_NVLINK_COUNT_FEC_HISTORY_3", |
| 266 | "DCGM_FI_DEV_NVLINK_COUNT_FEC_HISTORY_4", |
| 267 | "DCGM_FI_DEV_NVLINK_COUNT_FEC_HISTORY_5", |
| 268 | "DCGM_FI_DEV_NVLINK_COUNT_FEC_HISTORY_6", |
| 269 | "DCGM_FI_DEV_NVLINK_COUNT_FEC_HISTORY_7", |
| 270 | "DCGM_FI_DEV_NVLINK_COUNT_FEC_HISTORY_8", |
| 271 | "DCGM_FI_DEV_NVLINK_COUNT_FEC_HISTORY_9", |
| 272 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_L0", |
| 273 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_L1", |
| 274 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_L10", |
| 275 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_L11", |
| 276 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_L12", |
| 277 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_L13", |
| 278 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_L14", |
| 279 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_L15", |
| 280 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_L16", |
| 281 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_L17", |
| 282 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_L2", |
| 283 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_L3", |
| 284 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_L4", |
| 285 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_L5", |
| 286 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_L6", |
| 287 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_L7", |
| 288 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_L8", |
| 289 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_L9", |
| 290 | "DCGM_FI_DEV_NVLINK_RX_BANDWIDTH_TOTAL", |
| 291 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_L0", |
| 292 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_L1", |
| 293 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_L10", |
| 294 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_L11", |
| 295 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_L12", |
| 296 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_L13", |
| 297 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_L14", |
| 298 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_L15", |
| 299 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_L16", |
| 300 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_L17", |
| 301 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_L2", |
| 302 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_L3", |
| 303 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_L4", |
| 304 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_L5", |
| 305 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_L6", |
| 306 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_L7", |
| 307 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_L8", |
| 308 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_L9", |
| 309 | "DCGM_FI_DEV_NVLINK_TX_BANDWIDTH_TOTAL", |
| 310 | "DCGM_FI_DEV_NVML_INDEX", |
| 311 | "DCGM_FI_DEV_P2P_NVLINK_STATUS", |
| 312 | "DCGM_FI_DEV_PCIE_LINK_GEN", |
| 313 | "DCGM_FI_DEV_PCIE_LINK_WIDTH", |
| 314 | "DCGM_FI_DEV_PCIE_MAX_LINK_GEN", |
| 315 | "DCGM_FI_DEV_PCIE_MAX_LINK_WIDTH", |
| 316 | "DCGM_FI_DEV_PCIE_REPLAY_COUNTER", |
| 317 | "DCGM_FI_DEV_PCI_COMBINED_ID", |
| 318 | "DCGM_FI_DEV_PCI_SUBSYS_ID", |
| 319 | "DCGM_FI_DEV_PERSISTENCE_MODE", |
| 320 | "DCGM_FI_DEV_PLATFORM_CHASSIS_SLOT_NUMBER", |
| 321 | "DCGM_FI_DEV_PLATFORM_HOST_ID", |
| 322 | "DCGM_FI_DEV_PLATFORM_MODULE_ID", |
| 323 | "DCGM_FI_DEV_PLATFORM_PEER_TYPE", |
| 324 | "DCGM_FI_DEV_PLATFORM_TRAY_INDEX", |
| 325 | "DCGM_FI_DEV_POWER_MGMT_LIMIT", |
| 326 | "DCGM_FI_DEV_POWER_MGMT_LIMIT_DEF", |
| 327 | "DCGM_FI_DEV_POWER_MGMT_LIMIT_MAX", |
| 328 | "DCGM_FI_DEV_POWER_MGMT_LIMIT_MIN", |
| 329 | "DCGM_FI_DEV_POWER_USAGE", |
| 330 | "DCGM_FI_DEV_POWER_USAGE_INSTANT", |
| 331 | "DCGM_FI_DEV_POWER_VIOLATION", |
| 332 | "DCGM_FI_DEV_PSTATE", |
| 333 | "DCGM_FI_DEV_PWR_SMOOTHING_ACTIVE_PRESET_PROFILE", |
| 334 | "DCGM_FI_DEV_PWR_SMOOTHING_ADMIN_OVERRIDE_PERCENT_TMP_FLOOR", |
| 335 | "DCGM_FI_DEV_PWR_SMOOTHING_ADMIN_OVERRIDE_RAMP_DOWN_HYST_VAL", |
| 336 | "DCGM_FI_DEV_PWR_SMOOTHING_ADMIN_OVERRIDE_RAMP_DOWN_RATE", |
| 337 | "DCGM_FI_DEV_PWR_SMOOTHING_ADMIN_OVERRIDE_RAMP_UP_RATE", |
| 338 | "DCGM_FI_DEV_PWR_SMOOTHING_APPLIED_TMP_CEIL", |
| 339 | "DCGM_FI_DEV_PWR_SMOOTHING_APPLIED_TMP_FLOOR", |
| 340 | "DCGM_FI_DEV_PWR_SMOOTHING_ENABLED", |
| 341 | "DCGM_FI_DEV_PWR_SMOOTHING_HW_CIRCUITRY_PERCENT_LIFETIME_REMAINING", |
| 342 | "DCGM_FI_DEV_PWR_SMOOTHING_IMM_RAMP_DOWN_ENABLED", |
| 343 | "DCGM_FI_DEV_PWR_SMOOTHING_MAX_NUM_PRESET_PROFILES", |
| 344 | "DCGM_FI_DEV_PWR_SMOOTHING_MAX_PERCENT_TMP_FLOOR_SETTING", |
| 345 | "DCGM_FI_DEV_PWR_SMOOTHING_MIN_PERCENT_TMP_FLOOR_SETTING", |
| 346 | "DCGM_FI_DEV_PWR_SMOOTHING_PRIV_LVL", |
| 347 | "DCGM_FI_DEV_PWR_SMOOTHING_PROFILE_PERCENT_TMP_FLOOR", |
| 348 | "DCGM_FI_DEV_PWR_SMOOTHING_PROFILE_RAMP_DOWN_HYST_VAL", |
| 349 | "DCGM_FI_DEV_PWR_SMOOTHING_PROFILE_RAMP_DOWN_RATE", |
| 350 | "DCGM_FI_DEV_PWR_SMOOTHING_PROFILE_RAMP_UP_RATE", |
| 351 | "DCGM_FI_DEV_RELIABILITY_VIOLATION", |
| 352 | "DCGM_FI_DEV_SHUTDOWN_TEMP", |
| 353 | "DCGM_FI_DEV_SLOWDOWN_TEMP", |
| 354 | "DCGM_FI_DEV_SM_CLOCK", |
| 355 | "DCGM_FI_DEV_SYNC_BOOST_VIOLATION", |
| 356 | "DCGM_FI_DEV_THERMAL_VIOLATION", |
| 357 | "DCGM_FI_DEV_TOTAL_APP_CLOCKS_VIOLATION", |
| 358 | "DCGM_FI_DEV_TOTAL_BASE_CLOCKS_VIOLATION", |
| 359 | "DCGM_FI_DEV_TOTAL_ENERGY_CONSUMPTION", |
| 360 | "DCGM_FI_DEV_VGPU_ENC_SESSIONS_INFO", |
| 361 | "DCGM_FI_DEV_VGPU_ENC_STATS", |
| 362 | "DCGM_FI_DEV_VGPU_FBC_SESSIONS_INFO", |
| 363 | "DCGM_FI_DEV_VGPU_FBC_STATS", |
| 364 | "DCGM_FI_DEV_VGPU_FRAME_RATE_LIMIT", |
| 365 | "DCGM_FI_DEV_VGPU_INSTANCE_LICENSE_STATE", |
| 366 | "DCGM_FI_DEV_VGPU_LICENSE_STATUS", |
| 367 | "DCGM_FI_DEV_VGPU_MEMORY_USAGE", |
| 368 | "DCGM_FI_DEV_VGPU_PCI_ID", |
| 369 | "DCGM_FI_DEV_VGPU_TYPE", |
| 370 | "DCGM_FI_DEV_VGPU_UTILIZATIONS", |
| 371 | "DCGM_FI_DEV_VGPU_VM_GPU_INSTANCE_ID", |
| 372 | "DCGM_FI_DEV_VIDEO_CLOCK", |
| 373 | "DCGM_FI_DEV_VIRTUAL_MODE", |
| 374 | "DCGM_FI_DEV_XID_ERRORS", |
| 375 | "DCGM_FI_FIRST_VGPU_FIELD_ID", |
| 376 | "DCGM_FI_GPU_TOPOLOGY_NVLINK", |
| 377 | "DCGM_FI_GPU_TOPOLOGY_PCI", |
| 378 | "DCGM_FI_PROF_DRAM_ACTIVE", |
| 379 | "DCGM_FI_PROF_GR_ENGINE_ACTIVE", |
| 380 | "DCGM_FI_PROF_NVLINK_RX_BYTES", |
| 381 | "DCGM_FI_PROF_NVLINK_TX_BYTES", |
| 382 | "DCGM_FI_PROF_PCIE_RX_BYTES", |
| 383 | "DCGM_FI_PROF_PCIE_TX_BYTES", |
| 384 | "DCGM_FI_PROF_PIPE_FP16_ACTIVE", |
| 385 | "DCGM_FI_PROF_PIPE_FP32_ACTIVE", |
| 386 | "DCGM_FI_PROF_PIPE_FP64_ACTIVE", |
| 387 | "DCGM_FI_PROF_PIPE_TENSOR_ACTIVE", |
| 388 | "DCGM_FI_PROF_SM_ACTIVE", |
| 389 | "DCGM_FI_PROF_SM_OCCUPANCY", |
| 390 | "DCGM_FI_SYNC_BOOST" |
| 391 | ], |
| 392 | "unseen_fields": [ |
| 393 | "DCGM_FI_CUDA_DRIVER_VERSION", |
| 394 | "DCGM_FI_DEV_APP_MEM_CLOCK", |
| 395 | "DCGM_FI_DEV_APP_SM_CLOCK", |
| 396 | "DCGM_FI_DEV_AUTOBOOST", |
| 397 | "DCGM_FI_DEV_BANKS_REMAP_ROWS_AVAIL_HIGH", |
| 398 | "DCGM_FI_DEV_BANKS_REMAP_ROWS_AVAIL_LOW", |
| 399 | "DCGM_FI_DEV_BANKS_REMAP_ROWS_AVAIL_MAX", |
| 400 | "DCGM_FI_DEV_BANKS_REMAP_ROWS_AVAIL_NONE", |
| 401 | "DCGM_FI_DEV_BANKS_REMAP_ROWS_AVAIL_PARTIAL", |
| 402 | "DCGM_FI_DEV_BRAND", |
| 403 | "DCGM_FI_DEV_C2C_LINK_COUNT", |
| 404 | "DCGM_FI_DEV_C2C_LINK_STATUS", |
| 405 | "DCGM_FI_DEV_C2C_MAX_BANDWIDTH", |
| 406 | "DCGM_FI_DEV_CONNECTX_ACTIVE_PCIE_LINK_SPEED", |
| 407 | "DCGM_FI_DEV_CONNECTX_ACTIVE_PCIE_LINK_WIDTH", |
| 408 | "DCGM_FI_DEV_CONNECTX_CORRECTABLE_ERR_MASK", |
| 409 | "DCGM_FI_DEV_CONNECTX_CORRECTABLE_ERR_STATUS", |
| 410 | "DCGM_FI_DEV_CONNECTX_DEVICE_TEMPERATURE", |
| 411 | "DCGM_FI_DEV_CONNECTX_EXPECT_PCIE_LINK_SPEED", |
| 412 | "DCGM_FI_DEV_CONNECTX_EXPECT_PCIE_LINK_WIDTH", |
| 413 | "DCGM_FI_DEV_CONNECTX_HEALTH", |
| 414 | "DCGM_FI_DEV_CONNECTX_UNCORRECTABLE_ERR_MASK", |
| 415 | "DCGM_FI_DEV_CONNECTX_UNCORRECTABLE_ERR_SEVERITY", |
| 416 | "DCGM_FI_DEV_CONNECTX_UNCORRECTABLE_ERR_STATUS", |
| 417 | "DCGM_FI_DEV_CORRECTABLE_REMAPPED_ROWS", |
| 418 | "DCGM_FI_DEV_CPU_CLOCK_CURRENT", |
| 419 | "DCGM_FI_DEV_CPU_MODEL", |
| 420 | "DCGM_FI_DEV_CPU_POWER_LIMIT", |
| 421 | "DCGM_FI_DEV_CPU_TEMP_CURRENT", |
| 422 | "DCGM_FI_DEV_CPU_TEMP_WARNING", |
| 423 | "DCGM_FI_DEV_CPU_UTIL_IRQ", |
| 424 | "DCGM_FI_DEV_CPU_UTIL_NICE", |
| 425 | "DCGM_FI_DEV_CPU_UTIL_SYS", |
| 426 | "DCGM_FI_DEV_CPU_UTIL_TOTAL", |
| 427 | "DCGM_FI_DEV_CPU_UTIL_USER", |
| 428 | "DCGM_FI_DEV_CPU_VENDOR", |
| 429 | "DCGM_FI_DEV_CUDA_VISIBLE_DEVICES_STR", |
| 430 | "DCGM_FI_DEV_ECC_CURRENT", |
| 431 | "DCGM_FI_DEV_ECC_DBE_AGG_CBU", |
| 432 | "DCGM_FI_DEV_ECC_DBE_AGG_DEV", |
| 433 | "DCGM_FI_DEV_ECC_DBE_AGG_L1", |
| 434 | "DCGM_FI_DEV_ECC_DBE_AGG_L2", |
| 435 | "DCGM_FI_DEV_ECC_DBE_AGG_REG", |
| 436 | "DCGM_FI_DEV_ECC_DBE_AGG_SHM", |
| 437 | "DCGM_FI_DEV_ECC_DBE_AGG_SRM", |
| 438 | "DCGM_FI_DEV_ECC_DBE_AGG_TEX", |
| 439 | "DCGM_FI_DEV_ECC_DBE_VOL_CBU", |
| 440 | "DCGM_FI_DEV_ECC_DBE_VOL_DEV", |
| 441 | "DCGM_FI_DEV_ECC_DBE_VOL_L1", |
| 442 | "DCGM_FI_DEV_ECC_DBE_VOL_L2", |
| 443 | "DCGM_FI_DEV_ECC_DBE_VOL_REG", |
| 444 | "DCGM_FI_DEV_ECC_DBE_VOL_SHM", |
| 445 | "DCGM_FI_DEV_ECC_DBE_VOL_SRM", |
| 446 | "DCGM_FI_DEV_ECC_DBE_VOL_TEX", |
| 447 | "DCGM_FI_DEV_ECC_INFOROM_VER", |
| 448 | "DCGM_FI_DEV_ECC_PENDING", |
| 449 | "DCGM_FI_DEV_ECC_SBE_AGG_CBU", |
| 450 | "DCGM_FI_DEV_ECC_SBE_AGG_DEV", |
| 451 | "DCGM_FI_DEV_ECC_SBE_AGG_L1", |
| 452 | "DCGM_FI_DEV_ECC_SBE_AGG_L2", |
| 453 | "DCGM_FI_DEV_ECC_SBE_AGG_REG", |
| 454 | "DCGM_FI_DEV_ECC_SBE_AGG_SHM", |
| 455 | "DCGM_FI_DEV_ECC_SBE_AGG_SRM", |
| 456 | "DCGM_FI_DEV_ECC_SBE_AGG_TEX", |
| 457 | "DCGM_FI_DEV_ECC_SBE_VOL_CBU", |
| 458 | "DCGM_FI_DEV_ECC_SBE_VOL_DEV", |
| 459 | "DCGM_FI_DEV_ECC_SBE_VOL_L1", |
| 460 | "DCGM_FI_DEV_ECC_SBE_VOL_L2", |
| 461 | "DCGM_FI_DEV_ECC_SBE_VOL_REG", |
| 462 | "DCGM_FI_DEV_ECC_SBE_VOL_SHM", |
| 463 | "DCGM_FI_DEV_ECC_SBE_VOL_SRM", |
| 464 | "DCGM_FI_DEV_ECC_SBE_VOL_TEX", |
| 465 | "DCGM_FI_DEV_FABRIC_CLUSTER_UUID", |
| 466 | "DCGM_FI_DEV_FABRIC_MANAGER_ERROR_CODE", |
| 467 | "DCGM_FI_DEV_INFOROM_CONFIG_CHECK", |
| 468 | "DCGM_FI_DEV_INFOROM_CONFIG_VALID", |
| 469 | "DCGM_FI_DEV_INFOROM_IMAGE_VER", |
| 470 | "DCGM_FI_DEV_MEM_MAX_OP_TEMP", |
| 471 | "DCGM_FI_DEV_MINOR_NUMBER", |
| 472 | "DCGM_FI_DEV_MODULE_POWER_UTIL_CURRENT", |
| 473 | "DCGM_FI_DEV_NAME", |
| 474 | "DCGM_FI_DEV_NVLINK_COUNT_EFFECTIVE_BER", |
| 475 | "DCGM_FI_DEV_NVLINK_COUNT_EFFECTIVE_BER_FLOAT", |
| 476 | "DCGM_FI_DEV_NVLINK_COUNT_EFFECTIVE_ERRORS", |
| 477 | "DCGM_FI_DEV_NVLINK_COUNT_LINK_RECOVERY_EVENTS", |
| 478 | "DCGM_FI_DEV_NVLINK_COUNT_LINK_RECOVERY_FAILED_EVENTS", |
| 479 | "DCGM_FI_DEV_NVLINK_COUNT_LINK_RECOVERY_SUCCESSFUL_EVENTS", |
| 480 | "DCGM_FI_DEV_NVLINK_COUNT_LOCAL_LINK_INTEGRITY_ERRORS", |
| 481 | "DCGM_FI_DEV_NVLINK_COUNT_RX_BUFFER_OVERRUN_ERRORS", |
| 482 | "DCGM_FI_DEV_NVLINK_COUNT_RX_BYTES", |
| 483 | "DCGM_FI_DEV_NVLINK_COUNT_RX_ERRORS", |
| 484 | "DCGM_FI_DEV_NVLINK_COUNT_RX_GENERAL_ERRORS", |
| 485 | "DCGM_FI_DEV_NVLINK_COUNT_RX_MALFORMED_PACKET_ERRORS", |
| 486 | "DCGM_FI_DEV_NVLINK_COUNT_RX_PACKETS", |
| 487 | "DCGM_FI_DEV_NVLINK_COUNT_RX_REMOTE_ERRORS", |
| 488 | "DCGM_FI_DEV_NVLINK_COUNT_RX_SYMBOL_ERRORS", |
| 489 | "DCGM_FI_DEV_NVLINK_COUNT_SYMBOL_BER", |
| 490 | "DCGM_FI_DEV_NVLINK_COUNT_SYMBOL_BER_FLOAT", |
| 491 | "DCGM_FI_DEV_NVLINK_COUNT_TX_BYTES", |
| 492 | "DCGM_FI_DEV_NVLINK_COUNT_TX_DISCARDS", |
| 493 | "DCGM_FI_DEV_NVLINK_COUNT_TX_PACKETS", |
| 494 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L0", |
| 495 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L1", |
| 496 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L10", |
| 497 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L11", |
| 498 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L12", |
| 499 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L13", |
| 500 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L14", |
| 501 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L15", |
| 502 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L16", |
| 503 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L17", |
| 504 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L2", |
| 505 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L3", |
| 506 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L4", |
| 507 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L5", |
| 508 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L6", |
| 509 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L7", |
| 510 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L8", |
| 511 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_L9", |
| 512 | "DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_TOTAL", |
| 513 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L0", |
| 514 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L1", |
| 515 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L10", |
| 516 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L11", |
| 517 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L12", |
| 518 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L13", |
| 519 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L14", |
| 520 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L15", |
| 521 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L16", |
| 522 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L17", |
| 523 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L2", |
| 524 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L3", |
| 525 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L4", |
| 526 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L5", |
| 527 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L6", |
| 528 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L7", |
| 529 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L8", |
| 530 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_L9", |
| 531 | "DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_TOTAL", |
| 532 | "DCGM_FI_DEV_NVLINK_ERROR_DL_CRC", |
| 533 | "DCGM_FI_DEV_NVLINK_ERROR_DL_RECOVERY", |
| 534 | "DCGM_FI_DEV_NVLINK_ERROR_DL_REPLAY", |
| 535 | "DCGM_FI_DEV_NVLINK_PPCNT_PHYSICAL_LINK_DOWN_COUNTER", |
| 536 | "DCGM_FI_DEV_NVLINK_PPCNT_PHYSICAL_SUCCESSFUL_RECOVERY_EVENTS", |
| 537 | "DCGM_FI_DEV_NVLINK_PPCNT_PLR_RCV_CODES", |
| 538 | "DCGM_FI_DEV_NVLINK_PPCNT_PLR_RCV_CODE_ERR", |
| 539 | "DCGM_FI_DEV_NVLINK_PPCNT_PLR_RCV_UNCORRECTABLE_CODE", |
| 540 | "DCGM_FI_DEV_NVLINK_PPCNT_PLR_SYNC_EVENTS", |
| 541 | "DCGM_FI_DEV_NVLINK_PPCNT_PLR_XMIT_CODES", |
| 542 | "DCGM_FI_DEV_NVLINK_PPCNT_PLR_XMIT_RETRY_CODES", |
| 543 | "DCGM_FI_DEV_NVLINK_PPCNT_PLR_XMIT_RETRY_EVENTS", |
| 544 | "DCGM_FI_DEV_NVLINK_PPCNT_RECOVERY_TIME_BETWEEN_LAST_TWO", |
| 545 | "DCGM_FI_DEV_NVLINK_PPCNT_RECOVERY_TIME_SINCE_LAST", |
| 546 | "DCGM_FI_DEV_NVLINK_PPCNT_RECOVERY_TOTAL_SUCCESSFUL_EVENTS", |
| 547 | "DCGM_FI_DEV_NVLINK_PPRM_OPER_RECOVERY", |
| 548 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L0", |
| 549 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L1", |
| 550 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L10", |
| 551 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L11", |
| 552 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L12", |
| 553 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L13", |
| 554 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L14", |
| 555 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L15", |
| 556 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L16", |
| 557 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L17", |
| 558 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L2", |
| 559 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L3", |
| 560 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L4", |
| 561 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L5", |
| 562 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L6", |
| 563 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L7", |
| 564 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L8", |
| 565 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_L9", |
| 566 | "DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_TOTAL", |
| 567 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L0", |
| 568 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L1", |
| 569 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L10", |
| 570 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L11", |
| 571 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L12", |
| 572 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L13", |
| 573 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L14", |
| 574 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L15", |
| 575 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L16", |
| 576 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L17", |
| 577 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L2", |
| 578 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L3", |
| 579 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L4", |
| 580 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L5", |
| 581 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L6", |
| 582 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L7", |
| 583 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L8", |
| 584 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_L9", |
| 585 | "DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_TOTAL", |
| 586 | "DCGM_FI_DEV_NVSWITCH_CURRENT_IDDQ", |
| 587 | "DCGM_FI_DEV_NVSWITCH_CURRENT_IDDQ_DVDD", |
| 588 | "DCGM_FI_DEV_NVSWITCH_CURRENT_IDDQ_REV", |
| 589 | "DCGM_FI_DEV_NVSWITCH_DEVICE_UUID", |
| 590 | "DCGM_FI_DEV_NVSWITCH_FATAL_ERRORS", |
| 591 | "DCGM_FI_DEV_NVSWITCH_LINK_CRC_ERRORS", |
| 592 | "DCGM_FI_DEV_NVSWITCH_LINK_CRC_ERRORS_LANE0", |
| 593 | "DCGM_FI_DEV_NVSWITCH_LINK_CRC_ERRORS_LANE1", |
| 594 | "DCGM_FI_DEV_NVSWITCH_LINK_CRC_ERRORS_LANE2", |
| 595 | "DCGM_FI_DEV_NVSWITCH_LINK_CRC_ERRORS_LANE3", |
| 596 | "DCGM_FI_DEV_NVSWITCH_LINK_CRC_ERRORS_LANE4", |
| 597 | "DCGM_FI_DEV_NVSWITCH_LINK_CRC_ERRORS_LANE5", |
| 598 | "DCGM_FI_DEV_NVSWITCH_LINK_CRC_ERRORS_LANE6", |
| 599 | "DCGM_FI_DEV_NVSWITCH_LINK_CRC_ERRORS_LANE7", |
| 600 | "DCGM_FI_DEV_NVSWITCH_LINK_DEVICE_LINK_ID", |
| 601 | "DCGM_FI_DEV_NVSWITCH_LINK_DEVICE_LINK_SID", |
| 602 | "DCGM_FI_DEV_NVSWITCH_LINK_ECC_ERRORS", |
| 603 | "DCGM_FI_DEV_NVSWITCH_LINK_ECC_ERRORS_LANE0", |
| 604 | "DCGM_FI_DEV_NVSWITCH_LINK_ECC_ERRORS_LANE1", |
| 605 | "DCGM_FI_DEV_NVSWITCH_LINK_ECC_ERRORS_LANE2", |
| 606 | "DCGM_FI_DEV_NVSWITCH_LINK_ECC_ERRORS_LANE3", |
| 607 | "DCGM_FI_DEV_NVSWITCH_LINK_ECC_ERRORS_LANE4", |
| 608 | "DCGM_FI_DEV_NVSWITCH_LINK_ECC_ERRORS_LANE5", |
| 609 | "DCGM_FI_DEV_NVSWITCH_LINK_ECC_ERRORS_LANE6", |
| 610 | "DCGM_FI_DEV_NVSWITCH_LINK_ECC_ERRORS_LANE7", |
| 611 | "DCGM_FI_DEV_NVSWITCH_LINK_FATAL_ERRORS", |
| 612 | "DCGM_FI_DEV_NVSWITCH_LINK_FLIT_ERRORS", |
| 613 | "DCGM_FI_DEV_NVSWITCH_LINK_ID", |
| 614 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_COUNT_VC0", |
| 615 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_COUNT_VC1", |
| 616 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_COUNT_VC2", |
| 617 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_COUNT_VC3", |
| 618 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_HIGH_VC0", |
| 619 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_HIGH_VC1", |
| 620 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_HIGH_VC2", |
| 621 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_HIGH_VC3", |
| 622 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_LOW_VC0", |
| 623 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_LOW_VC1", |
| 624 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_LOW_VC2", |
| 625 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_LOW_VC3", |
| 626 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_MEDIUM_VC0", |
| 627 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_MEDIUM_VC1", |
| 628 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_MEDIUM_VC2", |
| 629 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_MEDIUM_VC3", |
| 630 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_PANIC_VC0", |
| 631 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_PANIC_VC1", |
| 632 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_PANIC_VC2", |
| 633 | "DCGM_FI_DEV_NVSWITCH_LINK_LATENCY_PANIC_VC3", |
| 634 | "DCGM_FI_DEV_NVSWITCH_LINK_NON_FATAL_ERRORS", |
| 635 | "DCGM_FI_DEV_NVSWITCH_LINK_RECOVERY_ERRORS", |
| 636 | "DCGM_FI_DEV_NVSWITCH_LINK_REMOTE_PCIE_BUS", |
| 637 | "DCGM_FI_DEV_NVSWITCH_LINK_REMOTE_PCIE_DEVICE", |
| 638 | "DCGM_FI_DEV_NVSWITCH_LINK_REMOTE_PCIE_DOMAIN", |
| 639 | "DCGM_FI_DEV_NVSWITCH_LINK_REMOTE_PCIE_FUNCTION", |
| 640 | "DCGM_FI_DEV_NVSWITCH_LINK_REPLAY_ERRORS", |
| 641 | "DCGM_FI_DEV_NVSWITCH_LINK_STATUS", |
| 642 | "DCGM_FI_DEV_NVSWITCH_LINK_THROUGHPUT_RX", |
| 643 | "DCGM_FI_DEV_NVSWITCH_LINK_THROUGHPUT_TX", |
| 644 | "DCGM_FI_DEV_NVSWITCH_LINK_TYPE", |
| 645 | "DCGM_FI_DEV_NVSWITCH_NON_FATAL_ERRORS", |
| 646 | "DCGM_FI_DEV_NVSWITCH_PCIE_BUS", |
| 647 | "DCGM_FI_DEV_NVSWITCH_PCIE_DEVICE", |
| 648 | "DCGM_FI_DEV_NVSWITCH_PCIE_DOMAIN", |
| 649 | "DCGM_FI_DEV_NVSWITCH_PCIE_FUNCTION", |
| 650 | "DCGM_FI_DEV_NVSWITCH_PHYS_ID", |
| 651 | "DCGM_FI_DEV_NVSWITCH_POWER_DVDD", |
| 652 | "DCGM_FI_DEV_NVSWITCH_POWER_HVDD", |
| 653 | "DCGM_FI_DEV_NVSWITCH_POWER_VDD", |
| 654 | "DCGM_FI_DEV_NVSWITCH_RESET_REQUIRED", |
| 655 | "DCGM_FI_DEV_NVSWITCH_TEMPERATURE_CURRENT", |
| 656 | "DCGM_FI_DEV_NVSWITCH_TEMPERATURE_LIMIT_SHUTDOWN", |
| 657 | "DCGM_FI_DEV_NVSWITCH_TEMPERATURE_LIMIT_SLOWDOWN", |
| 658 | "DCGM_FI_DEV_NVSWITCH_THROUGHPUT_RX", |
| 659 | "DCGM_FI_DEV_NVSWITCH_THROUGHPUT_TX", |
| 660 | "DCGM_FI_DEV_NVSWITCH_VOLTAGE_MVOLT", |
| 661 | "DCGM_FI_DEV_OEM_INFOROM_VER", |
| 662 | "DCGM_FI_DEV_PCIE_RX_THROUGHPUT", |
| 663 | "DCGM_FI_DEV_PCIE_TX_THROUGHPUT", |
| 664 | "DCGM_FI_DEV_PCI_BUSID", |
| 665 | "DCGM_FI_DEV_PLATFORM_CHASSIS_SERIAL_NUMBER", |
| 666 | "DCGM_FI_DEV_POWER_INFOROM_VER", |
| 667 | "DCGM_FI_DEV_RETIRED_DBE", |
| 668 | "DCGM_FI_DEV_RETIRED_PENDING", |
| 669 | "DCGM_FI_DEV_RETIRED_SBE", |
| 670 | "DCGM_FI_DEV_ROW_REMAP_FAILURE", |
| 671 | "DCGM_FI_DEV_ROW_REMAP_PENDING", |
| 672 | "DCGM_FI_DEV_SERIAL", |
| 673 | "DCGM_FI_DEV_SUPPORTED_TYPE_INFO", |
| 674 | "DCGM_FI_DEV_SYSIO_POWER_UTIL_CURRENT", |
| 675 | "DCGM_FI_DEV_THRESHOLD_SRM", |
| 676 | "DCGM_FI_DEV_UNCORRECTABLE_REMAPPED_ROWS", |
| 677 | "DCGM_FI_DEV_UUID", |
| 678 | "DCGM_FI_DEV_VBIOS_VERSION", |
| 679 | "DCGM_FI_DEV_VGPU_DRIVER_VERSION", |
| 680 | "DCGM_FI_DEV_VGPU_TYPE_INFO", |
| 681 | "DCGM_FI_DEV_VGPU_TYPE_NAME", |
| 682 | "DCGM_FI_DEV_VGPU_UUID", |
| 683 | "DCGM_FI_DEV_VGPU_VM_ID", |
| 684 | "DCGM_FI_DEV_VGPU_VM_NAME", |
| 685 | "DCGM_FI_DRIVER_VERSION", |
| 686 | "DCGM_FI_NVML_VERSION", |
| 687 | "DCGM_FI_PROCESS_NAME", |
| 688 | "DCGM_FI_PROF_C2C_RX_ALL_BYTES", |
| 689 | "DCGM_FI_PROF_C2C_RX_DATA_BYTES", |
| 690 | "DCGM_FI_PROF_C2C_TX_ALL_BYTES", |
| 691 | "DCGM_FI_PROF_C2C_TX_DATA_BYTES", |
| 692 | "DCGM_FI_PROF_HOSTMEM_CACHE_HIT", |
| 693 | "DCGM_FI_PROF_HOSTMEM_CACHE_MISS", |
| 694 | "DCGM_FI_PROF_NVDEC0_ACTIVE", |
| 695 | "DCGM_FI_PROF_NVDEC1_ACTIVE", |
| 696 | "DCGM_FI_PROF_NVDEC2_ACTIVE", |
| 697 | "DCGM_FI_PROF_NVDEC3_ACTIVE", |
| 698 | "DCGM_FI_PROF_NVDEC4_ACTIVE", |
| 699 | "DCGM_FI_PROF_NVDEC5_ACTIVE", |
| 700 | "DCGM_FI_PROF_NVDEC6_ACTIVE", |
| 701 | "DCGM_FI_PROF_NVDEC7_ACTIVE", |
| 702 | "DCGM_FI_PROF_NVJPG0_ACTIVE", |
| 703 | "DCGM_FI_PROF_NVJPG1_ACTIVE", |
| 704 | "DCGM_FI_PROF_NVJPG2_ACTIVE", |
| 705 | "DCGM_FI_PROF_NVJPG3_ACTIVE", |
| 706 | "DCGM_FI_PROF_NVJPG4_ACTIVE", |
| 707 | "DCGM_FI_PROF_NVJPG5_ACTIVE", |
| 708 | "DCGM_FI_PROF_NVJPG6_ACTIVE", |
| 709 | "DCGM_FI_PROF_NVJPG7_ACTIVE", |
| 710 | "DCGM_FI_PROF_NVLINK_L0_RX_BYTES", |
| 711 | "DCGM_FI_PROF_NVLINK_L0_TX_BYTES", |
| 712 | "DCGM_FI_PROF_NVLINK_L10_RX_BYTES", |
| 713 | "DCGM_FI_PROF_NVLINK_L10_TX_BYTES", |
| 714 | "DCGM_FI_PROF_NVLINK_L11_RX_BYTES", |
| 715 | "DCGM_FI_PROF_NVLINK_L11_TX_BYTES", |
| 716 | "DCGM_FI_PROF_NVLINK_L12_RX_BYTES", |
| 717 | "DCGM_FI_PROF_NVLINK_L12_TX_BYTES", |
| 718 | "DCGM_FI_PROF_NVLINK_L13_RX_BYTES", |
| 719 | "DCGM_FI_PROF_NVLINK_L13_TX_BYTES", |
| 720 | "DCGM_FI_PROF_NVLINK_L14_RX_BYTES", |
| 721 | "DCGM_FI_PROF_NVLINK_L14_TX_BYTES", |
| 722 | "DCGM_FI_PROF_NVLINK_L15_RX_BYTES", |
| 723 | "DCGM_FI_PROF_NVLINK_L15_TX_BYTES", |
| 724 | "DCGM_FI_PROF_NVLINK_L16_RX_BYTES", |
| 725 | "DCGM_FI_PROF_NVLINK_L16_TX_BYTES", |
| 726 | "DCGM_FI_PROF_NVLINK_L17_RX_BYTES", |
| 727 | "DCGM_FI_PROF_NVLINK_L17_TX_BYTES", |
| 728 | "DCGM_FI_PROF_NVLINK_L1_RX_BYTES", |
| 729 | "DCGM_FI_PROF_NVLINK_L1_TX_BYTES", |
| 730 | "DCGM_FI_PROF_NVLINK_L2_RX_BYTES", |
| 731 | "DCGM_FI_PROF_NVLINK_L2_TX_BYTES", |
| 732 | "DCGM_FI_PROF_NVLINK_L3_RX_BYTES", |
| 733 | "DCGM_FI_PROF_NVLINK_L3_TX_BYTES", |
| 734 | "DCGM_FI_PROF_NVLINK_L4_RX_BYTES", |
| 735 | "DCGM_FI_PROF_NVLINK_L4_TX_BYTES", |
| 736 | "DCGM_FI_PROF_NVLINK_L5_RX_BYTES", |
| 737 | "DCGM_FI_PROF_NVLINK_L5_TX_BYTES", |
| 738 | "DCGM_FI_PROF_NVLINK_L6_RX_BYTES", |
| 739 | "DCGM_FI_PROF_NVLINK_L6_TX_BYTES", |
| 740 | "DCGM_FI_PROF_NVLINK_L7_RX_BYTES", |
| 741 | "DCGM_FI_PROF_NVLINK_L7_TX_BYTES", |
| 742 | "DCGM_FI_PROF_NVLINK_L8_RX_BYTES", |
| 743 | "DCGM_FI_PROF_NVLINK_L8_TX_BYTES", |
| 744 | "DCGM_FI_PROF_NVLINK_L9_RX_BYTES", |
| 745 | "DCGM_FI_PROF_NVLINK_L9_TX_BYTES", |
| 746 | "DCGM_FI_PROF_NVOFA0_ACTIVE", |
| 747 | "DCGM_FI_PROF_NVOFA1_ACTIVE", |
| 748 | "DCGM_FI_PROF_PEERMEM_CACHE_HIT", |
| 749 | "DCGM_FI_PROF_PEERMEM_CACHE_MISS", |
| 750 | "DCGM_FI_PROF_PIPE_INT_ACTIVE", |
| 751 | "DCGM_FI_PROF_PIPE_TENSOR_DFMA_ACTIVE", |
| 752 | "DCGM_FI_PROF_PIPE_TENSOR_HMMA_ACTIVE", |
| 753 | "DCGM_FI_PROF_PIPE_TENSOR_IMMA_ACTIVE" |
| 754 | ] |
| 755 | }, |
| 756 | "unresolved_profiles": [], |
| 757 | "validated_on": "2026-02-08", |
| 758 | "environment": { |
| 759 | "gpu_model": "NVIDIA GeForce RTX 5090", |
| 760 | "driver_version": "590.48.01", |
| 761 | "dcgm_exporter_version": "4.4.1-4.5.2", |
| 762 | "test_method": "direct dcgm-exporter process on port 19400, fieldtest.csv in /var/snap/dcgm/common" |
| 763 | } |
| 764 | } |