Merge branch 'hydra' into 'master'

Hydra

See merge request !994

data/grid5000/sites/lyon/clusters/hydra/hydra.json

@@ -2,10 +2,223 @@
   "boot_type": "uefi",
   "created_at": "Thu, 15 Feb 2024 00:00:00 GMT",
   "exotic": true,
-  "kavlan": false,
+  "kavlan": true,
   "manufactured_at": "2024-02-15",
   "metrics": [
-
+    {
+      "description": "Temperature of Inlet_0 reported by BMC, in celsius",
+      "labels": {
+        "id": "inlet_0"
+      },
+      "name": "bmc_other_temp_celsius",
+      "optional_period": 5000,
+      "period": 0,
+      "source": {
+        "id": 1,
+        "protocol": "ipmisensor"
+      }
+    },
+    {
+      "description": "Temperature of Inlet_1 reported by BMC, in celsius",
+      "labels": {
+        "id": "inlet_1"
+      },
+      "name": "bmc_other_temp_celsius",
+      "optional_period": 5000,
+      "period": 0,
+      "source": {
+        "id": 2,
+        "protocol": "ipmisensor"
+      }
+    },
+    {
+      "description": "Temperature of MB_0 reported by BMC, in celsius",
+      "labels": {
+        "id": "mb_0"
+      },
+      "name": "bmc_other_temp_celsius",
+      "optional_period": 5000,
+      "period": 0,
+      "source": {
+        "id": 3,
+        "protocol": "ipmisensor"
+      }
+    },
+    {
+      "description": "Temperature of MB_1 reported by BMC, in celsius",
+      "labels": {
+        "id": "mb_1"
+      },
+      "name": "bmc_other_temp_celsius",
+      "optional_period": 5000,
+      "period": 0,
+      "source": {
+        "id": 4,
+        "protocol": "ipmisensor"
+      }
+    },
+    {
+      "description": "Temperature of outlet reported by BMC, in celsius",
+      "labels": {
+        "id": "outlet"
+      },
+      "name": "bmc_other_temp_celsius",
+      "optional_period": 5000,
+      "period": 0,
+      "source": {
+        "id": 5,
+        "protocol": "ipmisensor"
+      }
+    },
+    {
+      "description": "Temperature of SCM reported by BMC, in celsius",
+      "labels": {
+        "id": "scm"
+      },
+      "name": "bmc_other_temp_celsius",
+      "optional_period": 5000,
+      "period": 0,
+      "source": {
+        "id": 6,
+        "protocol": "ipmisensor"
+      }
+    },
+    {
+      "description": "Temperature of Psu 0 reported by BMC, in celsius",
+      "labels": {
+        "psu": "0"
+      },
+      "name": "bmc_psu_temp_celsius",
+      "optional_period": 5000,
+      "period": 0,
+      "source": {
+        "id": 7,
+        "protocol": "ipmisensor"
+      }
+    },
+    {
+      "description": "Temperature of Psu 1 reported by BMC, in celsius",
+      "labels": {
+        "psu": "1"
+      },
+      "name": "bmc_psu_temp_celsius",
+      "optional_period": 5000,
+      "period": 0,
+      "source": {
+        "id": 8,
+        "protocol": "ipmisensor"
+      }
+    },
+    {
+      "description": "Voltage of P12V_STB reported by BMC, in volt",
+      "labels": {
+        "id": "p12v_stb"
+      },
+      "name": "bmc_other_voltage_volt",
+      "optional_period": 5000,
+      "period": 0,
+      "source": {
+        "id": 29,
+        "protocol": "ipmisensor"
+      }
+    },
+    {
+      "description": "Voltage of P5V_STB reported by BMC, in volt",
+      "labels": {
+        "id": "p5v_stb"
+      },
+      "name": "bmc_other_voltage_volt",
+      "optional_period": 5000,
+      "period": 0,
+      "source": {
+        "id": 30,
+        "protocol": "ipmisensor"
+      }
+    },
+    {
+      "description": "Voltage of P3V_BAT reported by BMC, in volt",
+      "labels": {
+        "id": "p3v_bat"
+      },
+      "name": "bmc_other_voltage_volt",
+      "optional_period": 5000,
+      "period": 0,
+      "source": {
+        "id": 34,
+        "protocol": "ipmisensor"
+      }
+    },
+    {
+      "description": "Usage of BMC_CPU_Util reported by BMC, in percent",
+      "labels": {
+        "id": "bmc_cpu_util"
+      },
+      "name": "bmc_other_usage_percent",
+      "optional_period": 5000,
+      "period": 0,
+      "source": {
+        "id": 78,
+        "protocol": "ipmisensor"
+      }
+    },
+    {
+      "description": "Usage of BMC_MEM_Util reported by BMC, in percent",
+      "labels": {
+        "id": "bmc_mem_util"
+      },
+      "name": "bmc_other_usage_percent",
+      "optional_period": 5000,
+      "period": 0,
+      "source": {
+        "id": 79,
+        "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_scaling_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"
+      }
+    }
   ],
   "model": "NVIDIA Grace Hopper",
   "priority": 202402,

data/grid5000/sites/lyon/clusters/hydra/nodes/hydra-1.json

@@ -20,6 +20,50 @@
     "warranty_end": "2027-02-15"
   },
   "exotic": true,
+  "kavlan": {
+    "eth0": {
+      "kavlan-1": "192.168.201.1",
+      "kavlan-11": "10.7.214.1",
+      "kavlan-12": "10.11.214.1",
+      "kavlan-13": "10.15.214.1",
+      "kavlan-14": "10.19.214.1",
+      "kavlan-16": "10.27.214.1",
+      "kavlan-17": "10.31.214.1",
+      "kavlan-18": "10.35.214.1",
+      "kavlan-2": "192.168.217.1",
+      "kavlan-20": "10.43.214.1",
+      "kavlan-21": "10.47.214.1",
+      "kavlan-3": "192.168.233.1",
+      "kavlan-4": "10.12.9.1",
+      "kavlan-5": "10.12.73.1",
+      "kavlan-6": "10.12.137.1",
+      "kavlan-7": "10.12.201.1",
+      "kavlan-8": "10.13.9.1",
+      "kavlan-9": "10.13.73.1"
+    }
+  },
+  "kavlan6": {
+    "eth0": {
+      "kavlan-1": "2001:660:4406:480:a::1",
+      "kavlan-11": "2001:660:4406:1a0:40a::1",
+      "kavlan-12": "2001:660:4406:2a0:40a::1",
+      "kavlan-13": "2001:660:4406:4a0:40a::1",
+      "kavlan-14": "2001:660:4406:5a0:40a::1",
+      "kavlan-16": "2001:660:4406:7a0:40a::1",
+      "kavlan-17": "2001:660:4406:9a0:40a::1",
+      "kavlan-18": "2001:660:4406:8a0:40a::1",
+      "kavlan-2": "2001:660:4406:481:a::1",
+      "kavlan-20": "2001:660:4406:3a0:40a::1",
+      "kavlan-21": "2001:660:4406:6a0:40a::1",
+      "kavlan-3": "2001:660:4406:482:a::1",
+      "kavlan-4": "2001:660:4406:490:a::1",
+      "kavlan-5": "2001:660:4406:491:a::1",
+      "kavlan-6": "2001:660:4406:492:a::1",
+      "kavlan-7": "2001:660:4406:493:a::1",
+      "kavlan-8": "2001:660:4406:494:a::1",
+      "kavlan-9": "2001:660:4406:495:a::1"
+    }
+  },
   "main_memory": {
     "ram_size": 515396075520
   },
@@ -45,7 +89,7 @@
       "interface": "Ethernet",
       "ip": "172.16.57.1",
       "ip6": "2001:660:4406:400:a::1",
-      "kavlan": false,
+      "kavlan": true,
       "mac": "a0:88:c2:98:fc:82",
       "management": false,
       "model": "MT2910 Family [ConnectX-7]",

data/grid5000/sites/lyon/clusters/hydra/nodes/hydra-2.json

@@ -20,6 +20,50 @@
     "warranty_end": "2027-02-15"
   },
   "exotic": true,
+  "kavlan": {
+    "eth0": {
+      "kavlan-1": "192.168.201.2",
+      "kavlan-11": "10.7.214.2",
+      "kavlan-12": "10.11.214.2",
+      "kavlan-13": "10.15.214.2",
+      "kavlan-14": "10.19.214.2",
+      "kavlan-16": "10.27.214.2",
+      "kavlan-17": "10.31.214.2",
+      "kavlan-18": "10.35.214.2",
+      "kavlan-2": "192.168.217.2",
+      "kavlan-20": "10.43.214.2",
+      "kavlan-21": "10.47.214.2",
+      "kavlan-3": "192.168.233.2",
+      "kavlan-4": "10.12.9.2",
+      "kavlan-5": "10.12.73.2",
+      "kavlan-6": "10.12.137.2",
+      "kavlan-7": "10.12.201.2",
+      "kavlan-8": "10.13.9.2",
+      "kavlan-9": "10.13.73.2"
+    }
+  },
+  "kavlan6": {
+    "eth0": {
+      "kavlan-1": "2001:660:4406:480:a::2",
+      "kavlan-11": "2001:660:4406:1a0:40a::2",
+      "kavlan-12": "2001:660:4406:2a0:40a::2",
+      "kavlan-13": "2001:660:4406:4a0:40a::2",
+      "kavlan-14": "2001:660:4406:5a0:40a::2",
+      "kavlan-16": "2001:660:4406:7a0:40a::2",
+      "kavlan-17": "2001:660:4406:9a0:40a::2",
+      "kavlan-18": "2001:660:4406:8a0:40a::2",
+      "kavlan-2": "2001:660:4406:481:a::2",
+      "kavlan-20": "2001:660:4406:3a0:40a::2",
+      "kavlan-21": "2001:660:4406:6a0:40a::2",
+      "kavlan-3": "2001:660:4406:482:a::2",
+      "kavlan-4": "2001:660:4406:490:a::2",
+      "kavlan-5": "2001:660:4406:491:a::2",
+      "kavlan-6": "2001:660:4406:492:a::2",
+      "kavlan-7": "2001:660:4406:493:a::2",
+      "kavlan-8": "2001:660:4406:494:a::2",
+      "kavlan-9": "2001:660:4406:495:a::2"
+    }
+  },
   "main_memory": {
     "ram_size": 515396075520
   },
@@ -45,7 +89,7 @@
       "interface": "Ethernet",
       "ip": "172.16.57.2",
       "ip6": "2001:660:4406:400:a::2",
-      "kavlan": false,
+      "kavlan": true,
       "mac": "a0:88:c2:98:6c:a0",
       "management": false,
       "model": "MT2910 Family [ConnectX-7]",

data/grid5000/sites/lyon/clusters/hydra/nodes/hydra-3.json

@@ -20,6 +20,50 @@
     "warranty_end": "2027-02-15"
   },
   "exotic": true,
+  "kavlan": {
+    "eth0": {
+      "kavlan-1": "192.168.201.3",
+      "kavlan-11": "10.7.214.3",
+      "kavlan-12": "10.11.214.3",
+      "kavlan-13": "10.15.214.3",
+      "kavlan-14": "10.19.214.3",
+      "kavlan-16": "10.27.214.3",
+      "kavlan-17": "10.31.214.3",
+      "kavlan-18": "10.35.214.3",
+      "kavlan-2": "192.168.217.3",
+      "kavlan-20": "10.43.214.3",
+      "kavlan-21": "10.47.214.3",
+      "kavlan-3": "192.168.233.3",
+      "kavlan-4": "10.12.9.3",
+      "kavlan-5": "10.12.73.3",
+      "kavlan-6": "10.12.137.3",
+      "kavlan-7": "10.12.201.3",
+      "kavlan-8": "10.13.9.3",
+      "kavlan-9": "10.13.73.3"
+    }
+  },
+  "kavlan6": {
+    "eth0": {
+      "kavlan-1": "2001:660:4406:480:a::3",
+      "kavlan-11": "2001:660:4406:1a0:40a::3",
+      "kavlan-12": "2001:660:4406:2a0:40a::3",
+      "kavlan-13": "2001:660:4406:4a0:40a::3",
+      "kavlan-14": "2001:660:4406:5a0:40a::3",
+      "kavlan-16": "2001:660:4406:7a0:40a::3",
+      "kavlan-17": "2001:660:4406:9a0:40a::3",
+      "kavlan-18": "2001:660:4406:8a0:40a::3",
+      "kavlan-2": "2001:660:4406:481:a::3",
+      "kavlan-20": "2001:660:4406:3a0:40a::3",
+      "kavlan-21": "2001:660:4406:6a0:40a::3",
+      "kavlan-3": "2001:660:4406:482:a::3",
+      "kavlan-4": "2001:660:4406:490:a::3",
+      "kavlan-5": "2001:660:4406:491:a::3",
+      "kavlan-6": "2001:660:4406:492:a::3",
+      "kavlan-7": "2001:660:4406:493:a::3",
+      "kavlan-8": "2001:660:4406:494:a::3",
+      "kavlan-9": "2001:660:4406:495:a::3"
+    }
+  },
   "main_memory": {
     "ram_size": 515396075520
   },
@@ -45,7 +89,7 @@
       "interface": "Ethernet",
       "ip": "172.16.57.3",
       "ip6": "2001:660:4406:400:a::3",
-      "kavlan": false,
+      "kavlan": true,
       "mac": "a0:88:c2:99:18:42",
       "management": false,
       "model": "MT2910 Family [ConnectX-7]",

data/grid5000/sites/lyon/clusters/hydra/nodes/hydra-4.json

@@ -20,6 +20,50 @@
     "warranty_end": "2027-02-15"
   },
   "exotic": true,
+  "kavlan": {
+    "eth0": {
+      "kavlan-1": "192.168.201.4",
+      "kavlan-11": "10.7.214.4",
+      "kavlan-12": "10.11.214.4",
+      "kavlan-13": "10.15.214.4",
+      "kavlan-14": "10.19.214.4",
+      "kavlan-16": "10.27.214.4",
+      "kavlan-17": "10.31.214.4",
+      "kavlan-18": "10.35.214.4",
+      "kavlan-2": "192.168.217.4",
+      "kavlan-20": "10.43.214.4",
+      "kavlan-21": "10.47.214.4",
+      "kavlan-3": "192.168.233.4",
+      "kavlan-4": "10.12.9.4",
+      "kavlan-5": "10.12.73.4",
+      "kavlan-6": "10.12.137.4",
+      "kavlan-7": "10.12.201.4",
+      "kavlan-8": "10.13.9.4",
+      "kavlan-9": "10.13.73.4"
+    }
+  },
+  "kavlan6": {
+    "eth0": {
+      "kavlan-1": "2001:660:4406:480:a::4",
+      "kavlan-11": "2001:660:4406:1a0:40a::4",
+      "kavlan-12": "2001:660:4406:2a0:40a::4",
+      "kavlan-13": "2001:660:4406:4a0:40a::4",
+      "kavlan-14": "2001:660:4406:5a0:40a::4",
+      "kavlan-16": "2001:660:4406:7a0:40a::4",
+      "kavlan-17": "2001:660:4406:9a0:40a::4",
+      "kavlan-18": "2001:660:4406:8a0:40a::4",
+      "kavlan-2": "2001:660:4406:481:a::4",
+      "kavlan-20": "2001:660:4406:3a0:40a::4",
+      "kavlan-21": "2001:660:4406:6a0:40a::4",
+      "kavlan-3": "2001:660:4406:482:a::4",
+      "kavlan-4": "2001:660:4406:490:a::4",
+      "kavlan-5": "2001:660:4406:491:a::4",
+      "kavlan-6": "2001:660:4406:492:a::4",
+      "kavlan-7": "2001:660:4406:493:a::4",
+      "kavlan-8": "2001:660:4406:494:a::4",
+      "kavlan-9": "2001:660:4406:495:a::4"
+    }
+  },
   "main_memory": {
     "ram_size": 515396075520
   },
@@ -45,7 +89,7 @@
       "interface": "Ethernet",
       "ip": "172.16.57.4",
       "ip6": "2001:660:4406:400:a::4",
-      "kavlan": false,
+      "kavlan": true,
       "mac": "a0:88:c2:99:19:02",
       "management": false,
       "model": "MT2910 Family [ConnectX-7]",

input/grid5000/sites/lyon/clusters/hydra/hydra.yaml

 ---
 model: NVIDIA Grace Hopper
 created_at: 2024-02-15
-kavlan: false
+kavlan: true
 boot_type: uefi
 exotic: true
 queues:

input/grid5000/sites/lyon/clusters/hydra/hydra_metrics.yaml

+---
+metrics:
+
+  - name: bmc_other_temp_celsius
+    labels: {"id": "inlet_0"}
+    description: Temperature of Inlet_0 reported by BMC, in celsius
+    period: 0
+    optional_period: 5000
+    source:
+      protocol: ipmisensor
+      id: 1 #Temp_Inlet_0
+
+  - name: bmc_other_temp_celsius
+    labels: {"id": "inlet_1"}
+    description: Temperature of Inlet_1 reported by BMC, in celsius
+    period: 0
+    optional_period: 5000
+    source:
+      protocol: ipmisensor
+      id: 2 #Temp_Inlet_1
+
+  - name: bmc_other_temp_celsius
+    labels: {"id": "mb_0"}
+    description: Temperature of MB_0 reported by BMC, in celsius
+    period: 0
+    optional_period: 5000
+    source:
+      protocol: ipmisensor
+      id: 3 #Temp_MB_0
+
+  - name: bmc_other_temp_celsius
+    labels: {"id": "mb_1"}
+    description: Temperature of MB_1 reported by BMC, in celsius
+    period: 0
+    optional_period: 5000
+    source:
+      protocol: ipmisensor
+      id: 4 #Temp_MB_1
+
+  - name: bmc_other_temp_celsius
+    labels: {"id": "outlet"}
+    description: Temperature of outlet reported by BMC, in celsius
+    period: 0
+    optional_period: 5000
+    source:
+      protocol: ipmisensor
+      id: 5 #Temp_outlet
+
+  - name: bmc_other_temp_celsius
+    labels: {"id": "scm"}
+    description: Temperature of SCM reported by BMC, in celsius
+    period: 0
+    optional_period: 5000
+    source:
+      protocol: ipmisensor
+      id: 6 #Temp_SCM
+
+  - name: bmc_psu_temp_celsius
+    labels: {"psu": "0"}
+    description: Temperature of Psu 0 reported by BMC, in celsius
+    period: 0
+    optional_period: 5000
+    source:
+      protocol: ipmisensor
+      id: 7 #Temp_PSU0
+
+  - name: bmc_psu_temp_celsius
+    labels: {"psu": "1"}
+    description: Temperature of Psu 1 reported by BMC, in celsius
+    period: 0
+    optional_period: 5000
+    source:
+      protocol: ipmisensor
+      id: 8 #Temp_PSU1
+
+  - name: bmc_other_voltage_volt
+    labels: {"id": "p12v_stb"}
+    description: Voltage of P12V_STB reported by BMC, in volt
+    period: 0
+    optional_period: 5000
+    source:
+      protocol: ipmisensor
+      id: 29 #Volt_P12V_STB
+
+  - name: bmc_other_voltage_volt
+    labels: {"id": "p5v_stb"}
+    description: Voltage of P5V_STB reported by BMC, in volt
+    period: 0
+    optional_period: 5000
+    source:
+      protocol: ipmisensor
+      id: 30 #Volt_P5V_STB
+
+  - name: bmc_other_voltage_volt
+    labels: {"id": "p3v_bat"}
+    description: Voltage of P3V_BAT reported by BMC, in volt
+    period: 0
+    optional_period: 5000
+    source:
+      protocol: ipmisensor
+      id: 34 #Volt_P3V_BAT
+
+  - name: bmc_other_usage_percent
+    labels: {"id": "bmc_cpu_util"}
+    description: Usage of BMC_CPU_Util reported by BMC, in percent
+    period: 0
+    optional_period: 5000
+    source:
+      protocol: ipmisensor
+      id: 78 #BMC_CPU_Util
+
+  - name: bmc_other_usage_percent
+    labels: {"id": "bmc_mem_util"}
+    description: Usage of BMC_MEM_Util reported by BMC, in percent
+    period: 0
+    optional_period: 5000
+    source:
+      protocol: ipmisensor
+      id: 79 #BMC_MEM_Util
+
+  - 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_scaling_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

input/grid5000/vlans.yaml

@@ -90,6 +90,7 @@ vlans:
       local lyon pyxis eth0 0 0 6 0
       local lyon neowise eth0 0 0 7 0
       local lyon sirius eth0 0 0 8 0
+      local lyon hydra eth0 0 0 9 0
       local nancy gros eth0 0 0 0 0
       local nancy gros eth1 0 0 1 0
       local nancy gres eth0 0 0 2 0
@@ -149,6 +150,7 @@ vlans:
       global nancy gratouille eth0 0 0 19 14
       global lyon neowise eth0 0 0 20 0
       global lyon sirius eth0 0 0 21 0
+      global lyon hydra eth0 0 0 22 0
       global nancy grvingt eth0 0 0 24 0
       global nancy gres eth0 0 0 25 0
       global nancy grdix eth0 0 0 25 10
@@ -208,6 +210,7 @@ vlans:
       routed lyon pyxis eth0 0 12 6 0
       routed lyon neowise eth0 0 12 7 0
       routed lyon sirius eth0 0 12 8 0
+      routed lyon hydra eth0 0 12 9 0
       routed nancy gros eth0 0 16 0 0
       routed nancy gros eth1 0 16 1 0
       routed nancy grvingt eth0 0 16 3 0