From 014e7eb51274b8a0a2de263c53d457021687d6da Mon Sep 17 00:00:00 2001 From: BERARD Benjamin <benjamin.berard@inria.fr> Date: Fri, 9 Jul 2021 15:10:08 +0200 Subject: [PATCH] [kwollect/neowise] Add neowise kwollect metrics --- .../sites/lyon/clusters/neowise/neowise.json | 1183 +++++++++++++++++ .../clusters/neowise/neowise_metrics.yaml | 835 ++++++++++++ 2 files changed, 2018 insertions(+) create mode 100644 input/grid5000/sites/lyon/clusters/neowise/neowise_metrics.yaml diff --git a/data/grid5000/sites/lyon/clusters/neowise/neowise.json b/data/grid5000/sites/lyon/clusters/neowise/neowise.json index f9ad8b20ce6..bdf4a25f349 100644 --- a/data/grid5000/sites/lyon/clusters/neowise/neowise.json +++ b/data/grid5000/sites/lyon/clusters/neowise/neowise.json @@ -3,6 +3,1189 @@ "exotic": true, "kavlan": true, "metrics": [ + { + "description": "Front node ambient temperature reported by BMC, in celsius", + "name": "bmc_ambient_temp_celsius", + "period": 5000, + "source": { + "id": 64, + "protocol": "ipmisensor" + } + }, + { + "description": "Power consumption of node reported by BMC, in watt", + "name": "bmc_node_power_watt", + "period": 5000, + "source": { + "id": 87, + "protocol": "ipmisensor" + } + }, + { + "description": "Current of 12V_RISER1 reported by BMC, in amp", + "labels": { + "id": "12v_riser1" + }, + "name": "bmc_other_current_amp", + "optional_period": 5000, + "period": 0, + "source": { + "id": 11, + "protocol": "ipmisensor" + } + }, + { + "description": "Current of 12V_RISER2 reported by BMC, in amp", + "labels": { + "id": "12v_riser2" + }, + "name": "bmc_other_current_amp", + "optional_period": 5000, + "period": 0, + "source": { + "id": 12, + "protocol": "ipmisensor" + } + }, + { + "description": "Current of 12V_GPU0 reported by BMC, in amp", + "labels": { + "id": "12v_gpu0" + }, + "name": "bmc_other_current_amp", + "optional_period": 5000, + "period": 0, + "source": { + "id": 13, + "protocol": "ipmisensor" + } + }, + { + "description": "Current of 12V_GPU1 reported by BMC, in amp", + "labels": { + "id": "12v_gpu1" + }, + "name": "bmc_other_current_amp", + "optional_period": 5000, + "period": 0, + "source": { + "id": 14, + "protocol": "ipmisensor" + } + }, + { + "description": "Current of 12V_GPU2 reported by BMC, in amp", + "labels": { + "id": "12v_gpu2" + }, + "name": "bmc_other_current_amp", + "optional_period": 5000, + "period": 0, + "source": { + "id": 16, + "protocol": "ipmisensor" + } + }, + { + "description": "Current of 12V_GPU3 reported by BMC, in amp", + "labels": { + "id": "12v_gpu3" + }, + "name": "bmc_other_current_amp", + "optional_period": 5000, + "period": 0, + "source": { + "id": 15, + "protocol": "ipmisensor" + } + }, + { + "description": "Current of 12V_GPU4 reported by BMC, in amp", + "labels": { + "id": "12v_gpu4" + }, + "name": "bmc_other_current_amp", + "optional_period": 5000, + "period": 0, + "source": { + "id": 18, + "protocol": "ipmisensor" + } + }, + { + "description": "Current of 12V_GPU5 reported by BMC, in amp", + "labels": { + "id": "12v_gpu5" + }, + "name": "bmc_other_current_amp", + "optional_period": 5000, + "period": 0, + "source": { + "id": 17, + "protocol": "ipmisensor" + } + }, + { + "description": "Current of 12V_GPU6 reported by BMC, in amp", + "labels": { + "id": "12v_gpu6" + }, + "name": "bmc_other_current_amp", + "optional_period": 5000, + "period": 0, + "source": { + "id": 19, + "protocol": "ipmisensor" + } + }, + { + "description": "Current of 12V_GPU7 reported by BMC, in amp", + "labels": { + "id": "12v_gpu7" + }, + "name": "bmc_other_current_amp", + "optional_period": 5000, + "period": 0, + "source": { + "id": 20, + "protocol": "ipmisensor" + } + }, + { + "description": "Current of 12V_ATX1 reported by BMC, in amp", + "labels": { + "id": "12v_atx1" + }, + "name": "bmc_other_current_amp", + "optional_period": 5000, + "period": 0, + "source": { + "id": 21, + "protocol": "ipmisensor" + } + }, + { + "description": "Current of 12V_ATX2 reported by BMC, in amp", + "labels": { + "id": "12v_atx2" + }, + "name": "bmc_other_current_amp", + "optional_period": 5000, + "period": 0, + "source": { + "id": 22, + "protocol": "ipmisensor" + } + }, + { + "description": "Current of 12V_MB reported by BMC, in amp", + "labels": { + "id": "12v_mb" + }, + "name": "bmc_other_current_amp", + "optional_period": 5000, + "period": 0, + "source": { + "id": 23, + "protocol": "ipmisensor" + } + }, + { + "description": "Current of 12V_PDB reported by BMC, in amp", + "labels": { + "id": "12v_pdb" + }, + "name": "bmc_other_current_amp", + "optional_period": 5000, + "period": 0, + "source": { + "id": 24, + "protocol": "ipmisensor" + } + }, + { + "description": "Current of 12V_FAN reported by BMC, in amp", + "labels": { + "id": "12v_fan" + }, + "name": "bmc_other_current_amp", + "optional_period": 5000, + "period": 0, + "source": { + "id": 25, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_12V_ATX1 reported by BMC, in volt", + "labels": { + "id": "p_12v_atx1" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 26, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_12V_ATX2 reported by BMC, in volt", + "labels": { + "id": "p_12v_atx2" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 27, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_12V_FAN reported by BMC, in volt", + "labels": { + "id": "p_12v_fan" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 28, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_12V_GPU0 reported by BMC, in volt", + "labels": { + "id": "p_12v_gpu0" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 29, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_12V_GPU1 reported by BMC, in volt", + "labels": { + "id": "p_12v_gpu1" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 30, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_12V_GPU2 reported by BMC, in volt", + "labels": { + "id": "p_12v_gpu2" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 32, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_12V_GPU3 reported by BMC, in volt", + "labels": { + "id": "p_12v_gpu3" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 31, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_12V_GPU4 reported by BMC, in volt", + "labels": { + "id": "p_12v_gpu4" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 34, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_12V_GPU5 reported by BMC, in volt", + "labels": { + "id": "p_12v_gpu5" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 33, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_12V_GPU6 reported by BMC, in volt", + "labels": { + "id": "p_12v_gpu6" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 35, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_12V_GPU7 reported by BMC, in volt", + "labels": { + "id": "p_12v_gpu7" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 36, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_12V_MB reported by BMC, in volt", + "labels": { + "id": "p_12v_mb" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 37, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_12V_PDB reported by BMC, in volt", + "labels": { + "id": "p_12v_pdb" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 38, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_12V_RISER1 reported by BMC, in volt", + "labels": { + "id": "p_12v_riser1" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 39, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_12V_RISER2 reported by BMC, in volt", + "labels": { + "id": "p_12v_riser2" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 40, + "protocol": "ipmisensor" + } + }, + { + "description": "Speed of Fan GPU_FAN12 reported by BMC, in rpm", + "labels": { + "fan": "gpu_fan12e" + }, + "name": "bmc_fan_speed_rpm", + "optional_period": 5000, + "period": 0, + "source": { + "id": 47, + "protocol": "ipmisensor" + } + }, + { + "description": "Speed of Fan GPU_FAN56 reported by BMC, in rpm", + "labels": { + "fan": "gpu_fan56e" + }, + "name": "bmc_fan_speed_rpm", + "optional_period": 5000, + "period": 0, + "source": { + "id": 48, + "protocol": "ipmisensor" + } + }, + { + "description": "Speed of Fan GPU_FAN12 reported by BMC, in rpm", + "labels": { + "fan": "gpu_fan12" + }, + "name": "bmc_fan_speed_rpm", + "optional_period": 5000, + "period": 0, + "source": { + "id": 41, + "protocol": "ipmisensor" + } + }, + { + "description": "Speed of Fan GPU_FAN34 reported by BMC, in rpm", + "labels": { + "fan": "gpu_fan34" + }, + "name": "bmc_fan_speed_rpm", + "optional_period": 5000, + "period": 0, + "source": { + "id": 45, + "protocol": "ipmisensor" + } + }, + { + "description": "Speed of Fan GPU_FAN56 reported by BMC, in rpm", + "labels": { + "fan": "gpu_fan56" + }, + "name": "bmc_fan_speed_rpm", + "optional_period": 5000, + "period": 0, + "source": { + "id": 42, + "protocol": "ipmisensor" + } + }, + { + "description": "Speed of Fan GPU_FAN78 reported by BMC, in rpm", + "labels": { + "fan": "gpu_fan78" + }, + "name": "bmc_fan_speed_rpm", + "optional_period": 5000, + "period": 0, + "source": { + "id": 46, + "protocol": "ipmisensor" + } + }, + { + "description": "Speed of Fan SYS_FAN1 reported by BMC, in rpm", + "labels": { + "fan": "sys_fan1" + }, + "name": "bmc_fan_speed_rpm", + "optional_period": 5000, + "period": 0, + "source": { + "id": 43, + "protocol": "ipmisensor" + } + }, + { + "description": "Speed of Fan SYS_FAN2 reported by BMC, in rpm", + "labels": { + "fan": "sys_fan2" + }, + "name": "bmc_fan_speed_rpm", + "optional_period": 5000, + "period": 0, + "source": { + "id": 44, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of Cpu 0 reported by BMC, in celsius", + "labels": { + "cpu": "0" + }, + "name": "bmc_cpu_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 50, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of Dimm G0 reported by BMC, in celsius", + "labels": { + "dimm": "g0" + }, + "name": "bmc_dimm_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 51, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of Dimm G1 reported by BMC, in celsius", + "labels": { + "dimm": "g1" + }, + "name": "bmc_dimm_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 52, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of CPU0_DTS reported by BMC, in celsius", + "labels": { + "id": "cpu0_dts" + }, + "name": "bmc_other_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 53, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of Gpu 0 reported by BMC, in celsius", + "labels": { + "gpu": "0" + }, + "name": "bmc_gpu_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 54, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of Gpu 1 reported by BMC, in celsius", + "labels": { + "gpu": "1" + }, + "name": "bmc_gpu_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 55, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of Gpu 2 reported by BMC, in celsius", + "labels": { + "gpu": "2" + }, + "name": "bmc_gpu_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 56, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of Gpu 3 reported by BMC, in celsius", + "labels": { + "gpu": "3" + }, + "name": "bmc_gpu_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 57, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of Gpu 4 reported by BMC, in celsius", + "labels": { + "gpu": "4" + }, + "name": "bmc_gpu_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 58, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of Gpu 5 reported by BMC, in celsius", + "labels": { + "gpu": "5" + }, + "name": "bmc_gpu_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 59, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of Gpu 6 reported by BMC, in celsius", + "labels": { + "gpu": "6" + }, + "name": "bmc_gpu_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 60, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of Gpu 7 reported by BMC, in celsius", + "labels": { + "gpu": "7" + }, + "name": "bmc_gpu_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 61, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of M2_G0_AMB_TEMP reported by BMC, in celsius", + "labels": { + "id": "m2_g0_amb_temp" + }, + "name": "bmc_other_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 62, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of HDD_TEMP reported by BMC, in celsius", + "labels": { + "id": "hdd_temp" + }, + "name": "bmc_other_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 63, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of MB_TEMP1 reported by BMC, in celsius", + "labels": { + "id": "mb_temp1" + }, + "name": "bmc_other_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 65, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of MB_TEMP2 reported by BMC, in celsius", + "labels": { + "id": "mb_temp2" + }, + "name": "bmc_other_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 66, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of NVMeG0_TEMP reported by BMC, in celsius", + "labels": { + "id": "nvmeg0_temp" + }, + "name": "bmc_other_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 67, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_12V reported by BMC, in volt", + "labels": { + "id": "p_12v" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 70, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_1V2 reported by BMC, in volt", + "labels": { + "id": "p_1v2" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 71, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P0_VDD_18_DUAL reported by BMC, in volt", + "labels": { + "id": "p0_vdd_18_dual" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 72, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P0_VDD_18 reported by BMC, in volt", + "labels": { + "id": "p0_vdd_18" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 73, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P0_VPP_ABCD_SUS reported by BMC, in volt", + "labels": { + "id": "p0_vpp_abcd_sus" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 74, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P0_VPP_EFGH_SUS reported by BMC, in volt", + "labels": { + "id": "p0_vpp_efgh_sus" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 75, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_3V3 reported by BMC, in volt", + "labels": { + "id": "p_3v3" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 76, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_5V reported by BMC, in volt", + "labels": { + "id": "p_5v" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 77, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_5V_STBY reported by BMC, in volt", + "labels": { + "id": "p_5v_stby" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 78, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P_VBAT reported by BMC, in volt", + "labels": { + "id": "p_vbat" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 79, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of SOC_VDDCR reported by BMC, in volt", + "labels": { + "id": "soc_vddcr" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 80, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P0_VDDCR_CPU reported by BMC, in volt", + "labels": { + "id": "p0_vddcr_cpu" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 81, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of SOC_VDDCR_DUAL reported by BMC, in volt", + "labels": { + "id": "soc_vddcr_dual" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 82, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P0_VDDIO_ABCD reported by BMC, in volt", + "labels": { + "id": "p0_vddio_abcd" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 83, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of P0_VDDIO_EFGH reported by BMC, in volt", + "labels": { + "id": "p0_vddio_efgh" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 84, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of PDB_TEMP1 reported by BMC, in celsius", + "labels": { + "id": "pdb_temp1" + }, + "name": "bmc_other_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 85, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of PDB_TEMP2 reported by BMC, in celsius", + "labels": { + "id": "pdb_temp2" + }, + "name": "bmc_other_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 86, + "protocol": "ipmisensor" + } + }, + { + "description": "Current of VR_P0_IOUT reported by BMC, in amp", + "labels": { + "id": "vr_p0_iout" + }, + "name": "bmc_other_current_amp", + "optional_period": 5000, + "period": 0, + "source": { + "id": 88, + "protocol": "ipmisensor" + } + }, + { + "description": "Current of VR_DIMMG0_IOUT reported by BMC, in amp", + "labels": { + "id": "vr_dimmg0_iout" + }, + "name": "bmc_other_current_amp", + "optional_period": 5000, + "period": 0, + "source": { + "id": 89, + "protocol": "ipmisensor" + } + }, + { + "description": "Current of VR_DIMMG1_IOUT reported by BMC, in amp", + "labels": { + "id": "vr_dimmg1_iout" + }, + "name": "bmc_other_current_amp", + "optional_period": 5000, + "period": 0, + "source": { + "id": 90, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of VR_P0_TEMP reported by BMC, in celsius", + "labels": { + "id": "vr_p0_temp" + }, + "name": "bmc_other_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 91, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of Dimm G0 reported by BMC, in celsius", + "labels": { + "dimm": "vr_dimmg0" + }, + "name": "bmc_other_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 92, + "protocol": "ipmisensor" + } + }, + { + "description": "Temperature of Dimm G1 reported by BMC, in celsius", + "labels": { + "dimm": "vr_dimmg1" + }, + "name": "bmc_other_temp_celsius", + "optional_period": 5000, + "period": 0, + "source": { + "id": 93, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of VR_P0_VIN reported by BMC, in volt", + "labels": { + "id": "vr_p0_vin" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 94, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of VR_DIMMG0_VIN reported by BMC, in volt", + "labels": { + "id": "vr_dimmg0_vin" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 95, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of VR_DIMMG1_VIN reported by BMC, in volt", + "labels": { + "id": "vr_dimmg1_vin" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 96, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of VR_P0_VOUT reported by BMC, in volt", + "labels": { + "id": "vr_p0_vout" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 97, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of VR_DIMMG0_VOUT reported by BMC, in volt", + "labels": { + "id": "vr_dimmg0_vout" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 98, + "protocol": "ipmisensor" + } + }, + { + "description": "Voltage of VR_DIMMG1_VOUT reported by BMC, in volt", + "labels": { + "id": "vr_dimmg1_vout" + }, + "name": "bmc_other_voltage_volt", + "optional_period": 5000, + "period": 0, + "source": { + "id": 99, + "protocol": "ipmisensor" + } + }, + { + "description": "Default subset of metrics from Prometheus Node Exporter", + "name": "prom_default_metrics", + "optional_period": 15000, + "period": 0, + "source": { + "id": [ + "node_boot_time_seconds", + "node_cpu_frequency_hertz", + "node_cpu_seconds_total", + "node_filesystem_free_bytes", + "node_filesystem_size_bytes", + "node_load1", + "node_load15", + "node_load5", + "node_memory_Buffers_bytes", + "node_memory_Cached_bytes", + "node_memory_MemAvailable_bytes", + "node_memory_MemFree_bytes", + "node_memory_MemTotal_bytes", + "node_memory_Shmem_bytes", + "node_memory_SwapFree_bytes", + "node_memory_SwapTotal_bytes", + "node_network_receive_bytes_total", + "node_network_receive_packets_total", + "node_network_transmit_bytes_total", + "node_network_transmit_packets_total", + "node_procs_blocked", + "node_procs_running", + "kwollect_custom" + ], + "port": 9100, + "protocol": "prometheus" + } + }, + { + "description": "All metrics from Prometheus Node Exporter", + "name": "prom_all_metrics", + "optional_period": 15000, + "period": 0, + "source": { + "port": 9100, + "protocol": "prometheus" + } + }, + { + "description": "Default subset of metrics from Prometheus Nvidia DCGM Exporter", + "name": "prom_nvgpu_default_metrics", + "optional_period": 15000, + "period": 0, + "source": { + "id": [ + "DCGM_FI_DEV_SM_CLOCK", + "DCGM_FI_DEV_MEM_CLOCK", + "DCGM_FI_DEV_GPU_TEMP", + "DCGM_FI_DEV_POWER_USAGE", + "DCGM_FI_DEV_GPU_UTIL", + "DCGM_FI_DEV_MEM_COPY_UTIL" + ], + "port": 9400, + "protocol": "prometheus" + } + }, + { + "description": "All metrics from Prometheus Nvidia DCGM Exporter", + "name": "prom_nvgpu_all_metrics", + "optional_period": 15000, + "period": 0, + "source": { + "port": 9400, + "protocol": "prometheus" + } + }, { "description": "Input byte counter for the network device port", "labels": { diff --git a/input/grid5000/sites/lyon/clusters/neowise/neowise_metrics.yaml b/input/grid5000/sites/lyon/clusters/neowise/neowise_metrics.yaml new file mode 100644 index 00000000000..a81d591601f --- /dev/null +++ b/input/grid5000/sites/lyon/clusters/neowise/neowise_metrics.yaml @@ -0,0 +1,835 @@ +--- +metrics: + + - name: bmc_ambient_temp_celsius + description: Front node ambient temperature reported by BMC, in celsius + period: 5000 + source: + protocol: ipmisensor + id: 64 #INLET_AIR_TEMP + + - name: bmc_node_power_watt + description: Power consumption of node reported by BMC, in watt + period: 5000 + source: + protocol: ipmisensor + id: 87 #SYS_POWER + + - name: bmc_other_current_amp + labels: {"id": "12v_riser1"} + description: Current of 12V_RISER1 reported by BMC, in amp + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 11 #12V_RISER1 + + - name: bmc_other_current_amp + labels: {"id": "12v_riser2"} + description: Current of 12V_RISER2 reported by BMC, in amp + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 12 #12V_RISER2 + + - name: bmc_other_current_amp + labels: {"id": "12v_gpu0"} + description: Current of 12V_GPU0 reported by BMC, in amp + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 13 #12V_GPU0 + + - name: bmc_other_current_amp + labels: {"id": "12v_gpu1"} + description: Current of 12V_GPU1 reported by BMC, in amp + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 14 #12V_GPU1 + + - name: bmc_other_current_amp + labels: {"id": "12v_gpu2"} + description: Current of 12V_GPU2 reported by BMC, in amp + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 16 #12V_GPU2 + + - name: bmc_other_current_amp + labels: {"id": "12v_gpu3"} + description: Current of 12V_GPU3 reported by BMC, in amp + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 15 #12V_GPU3 + + - name: bmc_other_current_amp + labels: {"id": "12v_gpu4"} + description: Current of 12V_GPU4 reported by BMC, in amp + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 18 #12V_GPU4 + + - name: bmc_other_current_amp + labels: {"id": "12v_gpu5"} + description: Current of 12V_GPU5 reported by BMC, in amp + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 17 #12V_GPU5 + + - name: bmc_other_current_amp + labels: {"id": "12v_gpu6"} + description: Current of 12V_GPU6 reported by BMC, in amp + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 19 #12V_GPU6 + + - name: bmc_other_current_amp + labels: {"id": "12v_gpu7"} + description: Current of 12V_GPU7 reported by BMC, in amp + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 20 #12V_GPU7 + + - name: bmc_other_current_amp + labels: {"id": "12v_atx1"} + description: Current of 12V_ATX1 reported by BMC, in amp + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 21 #12V_ATX1 + + - name: bmc_other_current_amp + labels: {"id": "12v_atx2"} + description: Current of 12V_ATX2 reported by BMC, in amp + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 22 #12V_ATX2 + + - name: bmc_other_current_amp + labels: {"id": "12v_mb"} + description: Current of 12V_MB reported by BMC, in amp + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 23 #12V_MB + + - name: bmc_other_current_amp + labels: {"id": "12v_pdb"} + description: Current of 12V_PDB reported by BMC, in amp + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 24 #12V_PDB + + - name: bmc_other_current_amp + labels: {"id": "12v_fan"} + description: Current of 12V_FAN reported by BMC, in amp + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 25 #12V_FAN + + - name: bmc_other_voltage_volt + labels: {"id": "p_12v_atx1"} + description: Voltage of P_12V_ATX1 reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 26 #P_12V_ATX1 + + - name: bmc_other_voltage_volt + labels: {"id": "p_12v_atx2"} + description: Voltage of P_12V_ATX2 reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 27 #P_12V_ATX2 + + - name: bmc_other_voltage_volt + labels: {"id": "p_12v_fan"} + description: Voltage of P_12V_FAN reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 28 #P_12V_FAN + + - name: bmc_other_voltage_volt + labels: {"id": "p_12v_gpu0"} + description: Voltage of P_12V_GPU0 reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 29 #P_12V_GPU0 + + - name: bmc_other_voltage_volt + labels: {"id": "p_12v_gpu1"} + description: Voltage of P_12V_GPU1 reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 30 #P_12V_GPU1 + + - name: bmc_other_voltage_volt + labels: {"id": "p_12v_gpu2"} + description: Voltage of P_12V_GPU2 reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 32 #P_12V_GPU2 + + - name: bmc_other_voltage_volt + labels: {"id": "p_12v_gpu3"} + description: Voltage of P_12V_GPU3 reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 31 #P_12V_GPU3 + + - name: bmc_other_voltage_volt + labels: {"id": "p_12v_gpu4"} + description: Voltage of P_12V_GPU4 reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 34 #P_12V_GPU4 + + - name: bmc_other_voltage_volt + labels: {"id": "p_12v_gpu5"} + description: Voltage of P_12V_GPU5 reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 33 #P_12V_GPU5 + + - name: bmc_other_voltage_volt + labels: {"id": "p_12v_gpu6"} + description: Voltage of P_12V_GPU6 reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 35 #P_12V_GPU6 + + - name: bmc_other_voltage_volt + labels: {"id": "p_12v_gpu7"} + description: Voltage of P_12V_GPU7 reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 36 #P_12V_GPU7 + + - name: bmc_other_voltage_volt + labels: {"id": "p_12v_mb"} + description: Voltage of P_12V_MB reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 37 #P_12V_MB + + - name: bmc_other_voltage_volt + labels: {"id": "p_12v_pdb"} + description: Voltage of P_12V_PDB reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 38 #P_12V_PDB + + - name: bmc_other_voltage_volt + labels: {"id": "p_12v_riser1"} + description: Voltage of P_12V_RISER1 reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 39 #P_12V_RISER1 + + - name: bmc_other_voltage_volt + labels: {"id": "p_12v_riser2"} + description: Voltage of P_12V_RISER2 reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 40 #P_12V_RISER2 + + - name: bmc_fan_speed_rpm + labels: {"fan": "gpu_fan12e"} + description: Speed of Fan GPU_FAN12 reported by BMC, in rpm + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 47 #GPU_FAN12E + + - name: bmc_fan_speed_rpm + labels: {"fan": "gpu_fan56e"} + description: Speed of Fan GPU_FAN56 reported by BMC, in rpm + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 48 #GPU_FAN56E + + - name: bmc_fan_speed_rpm + labels: {"fan": "gpu_fan12"} + description: Speed of Fan GPU_FAN12 reported by BMC, in rpm + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 41 #GPU_FAN12 + + - name: bmc_fan_speed_rpm + labels: {"fan": "gpu_fan34"} + description: Speed of Fan GPU_FAN34 reported by BMC, in rpm + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 45 #GPU_FAN34 + + - name: bmc_fan_speed_rpm + labels: {"fan": "gpu_fan56"} + description: Speed of Fan GPU_FAN56 reported by BMC, in rpm + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 42 #GPU_FAN56 + + - name: bmc_fan_speed_rpm + labels: {"fan": "gpu_fan78"} + description: Speed of Fan GPU_FAN78 reported by BMC, in rpm + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 46 #GPU_FAN78 + + - name: bmc_fan_speed_rpm + labels: {"fan": "sys_fan1"} + description: Speed of Fan SYS_FAN1 reported by BMC, in rpm + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 43 #SYS_FAN1 + + - name: bmc_fan_speed_rpm + labels: {"fan": "sys_fan2"} + description: Speed of Fan SYS_FAN2 reported by BMC, in rpm + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 44 #SYS_FAN2 + + - name: bmc_cpu_temp_celsius + labels: {"cpu": "0"} + description: Temperature of Cpu 0 reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 50 #CPU0_TEMP + + - name: bmc_dimm_temp_celsius + labels: {"dimm": "g0"} + description: Temperature of Dimm G0 reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 51 #DIMMG0_TEMP + + - name: bmc_dimm_temp_celsius + labels: {"dimm": "g1"} + description: Temperature of Dimm G1 reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 52 #DIMMG1_TEMP + + - name: bmc_other_temp_celsius + labels: {"id": "cpu0_dts"} + description: Temperature of CPU0_DTS reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 53 #CPU0_DTS + + - name: bmc_gpu_temp_celsius + labels: {"gpu": "0"} + description: Temperature of Gpu 0 reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 54 #GPU0_PROC + + - name: bmc_gpu_temp_celsius + labels: {"gpu": "1"} + description: Temperature of Gpu 1 reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 55 #GPU1_PROC + + - name: bmc_gpu_temp_celsius + labels: {"gpu": "2"} + description: Temperature of Gpu 2 reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 56 #GPU2_PROC + + - name: bmc_gpu_temp_celsius + labels: {"gpu": "3"} + description: Temperature of Gpu 3 reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 57 #GPU3_PROC + + - name: bmc_gpu_temp_celsius + labels: {"gpu": "4"} + description: Temperature of Gpu 4 reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 58 #GPU4_PROC + + - name: bmc_gpu_temp_celsius + labels: {"gpu": "5"} + description: Temperature of Gpu 5 reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 59 #GPU5_PROC + + - name: bmc_gpu_temp_celsius + labels: {"gpu": "6"} + description: Temperature of Gpu 6 reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 60 #GPU6_PROC + + - name: bmc_gpu_temp_celsius + labels: {"gpu": "7"} + description: Temperature of Gpu 7 reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 61 #GPU7_PROC + + - name: bmc_other_temp_celsius + labels: {"id": "m2_g0_amb_temp"} + description: Temperature of M2_G0_AMB_TEMP reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 62 #M2_G0_AMB_TEMP + + - name: bmc_other_temp_celsius + labels: {"id": "hdd_temp"} + description: Temperature of HDD_TEMP reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 63 #HDD_TEMP + + - name: bmc_other_temp_celsius + labels: {"id": "mb_temp1"} + description: Temperature of MB_TEMP1 reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 65 #MB_TEMP1 + + - name: bmc_other_temp_celsius + labels: {"id": "mb_temp2"} + description: Temperature of MB_TEMP2 reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 66 #MB_TEMP2 + + - name: bmc_other_temp_celsius + labels: {"id": "nvmeg0_temp"} + description: Temperature of NVMeG0_TEMP reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 67 #NVMeG0_TEMP + + - name: bmc_other_voltage_volt + labels: {"id": "p_12v"} + description: Voltage of P_12V reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 70 #P_12V + + - name: bmc_other_voltage_volt + labels: {"id": "p_1v2"} + description: Voltage of P_1V2 reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 71 #P_1V2 + + - name: bmc_other_voltage_volt + labels: {"id": "p0_vdd_18_dual"} + description: Voltage of P0_VDD_18_DUAL reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 72 #P0_VDD_18_DUAL + + - name: bmc_other_voltage_volt + labels: {"id": "p0_vdd_18"} + description: Voltage of P0_VDD_18 reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 73 #P0_VDD_18 + + - name: bmc_other_voltage_volt + labels: {"id": "p0_vpp_abcd_sus"} + description: Voltage of P0_VPP_ABCD_SUS reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 74 #P0_VPP_ABCD_SUS + + - name: bmc_other_voltage_volt + labels: {"id": "p0_vpp_efgh_sus"} + description: Voltage of P0_VPP_EFGH_SUS reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 75 #P0_VPP_EFGH_SUS + + - name: bmc_other_voltage_volt + labels: {"id": "p_3v3"} + description: Voltage of P_3V3 reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 76 #P_3V3 + + - name: bmc_other_voltage_volt + labels: {"id": "p_5v"} + description: Voltage of P_5V reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 77 #P_5V + + - name: bmc_other_voltage_volt + labels: {"id": "p_5v_stby"} + description: Voltage of P_5V_STBY reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 78 #P_5V_STBY + + - name: bmc_other_voltage_volt + labels: {"id": "p_vbat"} + description: Voltage of P_VBAT reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 79 #P_VBAT + + - name: bmc_other_voltage_volt + labels: {"id": "soc_vddcr"} + description: Voltage of SOC_VDDCR reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 80 #SOC_VDDCR + + - name: bmc_other_voltage_volt + labels: {"id": "p0_vddcr_cpu"} + description: Voltage of P0_VDDCR_CPU reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 81 #P0_VDDCR_CPU + + - name: bmc_other_voltage_volt + labels: {"id": "soc_vddcr_dual"} + description: Voltage of SOC_VDDCR_DUAL reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 82 #SOC_VDDCR_DUAL + + - name: bmc_other_voltage_volt + labels: {"id": "p0_vddio_abcd"} + description: Voltage of P0_VDDIO_ABCD reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 83 #P0_VDDIO_ABCD + + - name: bmc_other_voltage_volt + labels: {"id": "p0_vddio_efgh"} + description: Voltage of P0_VDDIO_EFGH reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 84 #P0_VDDIO_EFGH + + - name: bmc_other_temp_celsius + labels: {"id": "pdb_temp1"} + description: Temperature of PDB_TEMP1 reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 85 #PDB_TEMP1 + + - name: bmc_other_temp_celsius + labels: {"id": "pdb_temp2"} + description: Temperature of PDB_TEMP2 reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 86 #PDB_TEMP2 + + - name: bmc_other_current_amp + labels: {"id": "vr_p0_iout"} + description: Current of VR_P0_IOUT reported by BMC, in amp + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 88 #VR_P0_IOUT + + - name: bmc_other_current_amp + labels: {"id": "vr_dimmg0_iout"} + description: Current of VR_DIMMG0_IOUT reported by BMC, in amp + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 89 #VR_DIMMG0_IOUT + + - name: bmc_other_current_amp + labels: {"id": "vr_dimmg1_iout"} + description: Current of VR_DIMMG1_IOUT reported by BMC, in amp + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 90 #VR_DIMMG1_IOUT + + - name: bmc_other_temp_celsius + labels: {"id": "vr_p0_temp"} + description: Temperature of VR_P0_TEMP reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 91 #VR_P0_TEMP + + - name: bmc_other_temp_celsius + labels: {"dimm": "vr_dimmg0"} + description: Temperature of Dimm G0 reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 92 #VR_DIMMG0_TEMP + + - name: bmc_other_temp_celsius + labels: {"dimm": "vr_dimmg1"} + description: Temperature of Dimm G1 reported by BMC, in celsius + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 93 #VR_DIMMG1_TEMP + + - name: bmc_other_voltage_volt + labels: {"id": "vr_p0_vin"} + description: Voltage of VR_P0_VIN reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 94 #VR_P0_VIN + + - name: bmc_other_voltage_volt + labels: {"id": "vr_dimmg0_vin"} + description: Voltage of VR_DIMMG0_VIN reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 95 #VR_DIMMG0_VIN + + - name: bmc_other_voltage_volt + labels: {"id": "vr_dimmg1_vin"} + description: Voltage of VR_DIMMG1_VIN reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 96 #VR_DIMMG1_VIN + + - name: bmc_other_voltage_volt + labels: {"id": "vr_p0_vout"} + description: Voltage of VR_P0_VOUT reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 97 #VR_P0_VOUT + + - name: bmc_other_voltage_volt + labels: {"id": "vr_dimmg0_vout"} + description: Voltage of VR_DIMMG0_VOUT reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 98 #VR_DIMMG0_VOUT + + - name: bmc_other_voltage_volt + labels: {"id": "vr_dimmg1_vout"} + description: Voltage of VR_DIMMG1_VOUT reported by BMC, in volt + period: 0 + optional_period: 5000 + source: + protocol: ipmisensor + id: 99 #VR_DIMMG1_VOUT + + - name: prom_default_metrics + description: Default subset of metrics from Prometheus Node Exporter + period: 0 + optional_period: 15000 + source: + protocol: prometheus + port: 9100 + id: + - node_boot_time_seconds + - node_cpu_frequency_hertz + - node_cpu_seconds_total + - node_filesystem_free_bytes + - node_filesystem_size_bytes + - node_load1 + - node_load15 + - node_load5 + - node_memory_Buffers_bytes + - node_memory_Cached_bytes + - node_memory_MemAvailable_bytes + - node_memory_MemFree_bytes + - node_memory_MemTotal_bytes + - node_memory_Shmem_bytes + - node_memory_SwapFree_bytes + - node_memory_SwapTotal_bytes + - node_network_receive_bytes_total + - node_network_receive_packets_total + - node_network_transmit_bytes_total + - node_network_transmit_packets_total + - node_procs_blocked + - node_procs_running + - kwollect_custom + + - name: prom_all_metrics + description: All metrics from Prometheus Node Exporter + period: 0 + optional_period: 15000 + source: + protocol: prometheus + port: 9100 + + - name: prom_nvgpu_default_metrics + description: Default subset of metrics from Prometheus Nvidia DCGM Exporter + period: 0 + optional_period: 15000 + source: + protocol: prometheus + port: 9400 + id: + - DCGM_FI_DEV_SM_CLOCK + - DCGM_FI_DEV_MEM_CLOCK + - DCGM_FI_DEV_GPU_TEMP + - DCGM_FI_DEV_POWER_USAGE + - DCGM_FI_DEV_GPU_UTIL + - DCGM_FI_DEV_MEM_COPY_UTIL + + - name: prom_nvgpu_all_metrics + description: All metrics from Prometheus Nvidia DCGM Exporter + period: 0 + optional_period: 15000 + source: + protocol: prometheus + port: 9400 -- GitLab