Merge branch 'master' into wip

data/grid5000/sites/rennes/clusters/abacus14/abacus14.json

+{
+  "boot_type": "bios",
+  "created_at": "Wed, 08 Nov 2023 00:00:00 GMT",
+  "exotic": false,
+  "kavlan": false,
+  "metrics": [
+    {
+      "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": "DELL C4140",
+  "queues": [
+    "testing",
+    "admin"
+  ],
+  "type": "cluster",
+  "uid": "abacus14"
+}
\ No newline at end of file

data/grid5000/sites/rennes/clusters/abacus14/nodes/abacus14-1.json

+{
+  "architecture": {
+    "cpu_core_numbering": "round-robin",
+    "nb_cores": 24,
+    "nb_procs": 2,
+    "nb_threads": 48,
+    "platform_type": "x86_64"
+  },
+  "bios": {
+    "release_date": "06/04/2023",
+    "vendor": "Dell Inc.",
+    "version": "2.19.1"
+  },
+  "bmc_version": "6.10.80.00",
+  "chassis": {
+    "manufacturer": "Dell Inc.",
+    "name": "PowerEdge C4140",
+    "serial": "2VXBRZ2"
+  },
+  "exotic": false,
+  "gpu_devices": {
+    "nvidia0": {
+      "compute_capability": "7.0",
+      "cores": 5120,
+      "cpu_affinity": 0,
+      "device": "/dev/nvidia0",
+      "memory": 34089205760,
+      "microarchitecture": "Volta",
+      "model": "Tesla V100-PCIE-32GB",
+      "performance": {
+        "fp-16": 28260000000000,
+        "fp-32": 14130000000000,
+        "fp-64": 7066000000000
+      },
+      "power_default_limit": "250.00 W",
+      "vbios_version": "88.00.7E.00.03",
+      "vendor": "Nvidia"
+    },
+    "nvidia1": {
+      "compute_capability": "7.0",
+      "cores": 5120,
+      "cpu_affinity": 0,
+      "device": "/dev/nvidia1",
+      "memory": 34089205760,
+      "microarchitecture": "Volta",
+      "model": "Tesla V100-PCIE-32GB",
+      "performance": {
+        "fp-16": 28260000000000,
+        "fp-32": 14130000000000,
+        "fp-64": 7066000000000
+      },
+      "power_default_limit": "250.00 W",
+      "vbios_version": "88.00.7E.00.03",
+      "vendor": "Nvidia"
+    },
+    "nvidia2": {
+      "compute_capability": "7.0",
+      "cores": 5120,
+      "cpu_affinity": 0,
+      "device": "/dev/nvidia2",
+      "memory": 34089205760,
+      "microarchitecture": "Volta",
+      "model": "Tesla V100-PCIE-32GB",
+      "performance": {
+        "fp-16": 28260000000000,
+        "fp-32": 14130000000000,
+        "fp-64": 7066000000000
+      },
+      "power_default_limit": "250.00 W",
+      "vbios_version": "88.00.7E.00.03",
+      "vendor": "Nvidia"
+    },
+    "nvidia3": {
+      "compute_capability": "7.0",
+      "cores": 5120,
+      "cpu_affinity": 0,
+      "device": "/dev/nvidia3",
+      "memory": 34089205760,
+      "microarchitecture": "Volta",
+      "model": "Tesla V100-PCIE-32GB",
+      "performance": {
+        "fp-16": 28260000000000,
+        "fp-32": 14130000000000,
+        "fp-64": 7066000000000
+      },
+      "power_default_limit": "250.00 W",
+      "vbios_version": "88.00.7E.00.03",
+      "vendor": "Nvidia"
+    }
+  },
+  "main_memory": {
+    "ram_size": 412316860416
+  },
+  "management_tools": {
+    "bmc_vendor_tool": "racadm",
+    "ipmitool": {
+      "retries": 5
+    }
+  },
+  "memory_devices": [
+    {
+      "device": "dimm_a1",
+      "size": 34359738368,
+      "technology": "dram"
+    },
+    {
+      "device": "dimm_a2",
+      "size": 34359738368,
+      "technology": "dram"
+    },
+    {
+      "device": "dimm_a3",
+      "size": 34359738368,
+      "technology": "dram"
+    },
+    {
+      "device": "dimm_a4",
+      "size": 34359738368,
+      "technology": "dram"
+    },
+    {
+      "device": "dimm_a5",
+      "size": 34359738368,
+      "technology": "dram"
+    },
+    {
+      "device": "dimm_a6",
+      "size": 34359738368,
+      "technology": "dram"
+    },
+    {
+      "device": "dimm_b1",
+      "size": 34359738368,
+      "technology": "dram"
+    },
+    {
+      "device": "dimm_b2",
+      "size": 34359738368,
+      "technology": "dram"
+    },
+    {
+      "device": "dimm_b3",
+      "size": 34359738368,
+      "technology": "dram"
+    },
+    {
+      "device": "dimm_b4",
+      "size": 34359738368,
+      "technology": "dram"
+    },
+    {
+      "device": "dimm_b5",
+      "size": 34359738368,
+      "technology": "dram"
+    },
+    {
+      "device": "dimm_b6",
+      "size": 34359738368,
+      "technology": "dram"
+    }
+  ],
+  "network_adapters": [
+    {
+      "device": "eth0",
+      "driver": "i40e",
+      "enabled": true,
+      "firmware_version": "9.20 0x8000d969 22.0.9",
+      "interface": "Ethernet",
+      "ip": "172.16.109.14",
+      "ip6": "2001:660:4406:700:e::e",
+      "kavlan": false,
+      "mac": "e4:43:4b:94:95:32",
+      "management": false,
+      "model": "Ethernet Controller X710 for 10GbE SFP+",
+      "mountable": true,
+      "mounted": true,
+      "name": "eno1",
+      "network_address": "abacus14-1.rennes.grid5000.fr",
+      "rate": 10000000000,
+      "sriov": false,
+      "sriov_totalvfs": 0,
+      "switch": null,
+      "switch_port": null,
+      "vendor": "Intel"
+    },
+    {
+      "device": "eth1",
+      "driver": "i40e",
+      "enabled": false,
+      "firmware_version": "9.20 0x8000d969 22.0.9",
+      "interface": "Ethernet",
+      "kavlan": false,
+      "mac": "e4:43:4b:94:95:34",
+      "management": false,
+      "model": "Ethernet Controller X710 for 10GbE SFP+",
+      "mountable": false,
+      "mounted": false,
+      "name": "eno2",
+      "sriov": false,
+      "sriov_totalvfs": 0,
+      "vendor": "Intel"
+    },
+    {
+      "device": "bmc",
+      "enabled": true,
+      "interface": "Ethernet",
+      "ip": "172.17.109.14",
+      "kavlan": false,
+      "mac": "f4:02:70:b3:e4:9a",
+      "management": true,
+      "mountable": false,
+      "mounted": false,
+      "network_address": "abacus14-1-bmc.rennes.grid5000.fr"
+    }
+  ],
+  "operating_system": {
+    "cstate_driver": "intel_idle",
+    "cstate_governor": "menu",
+    "ht_enabled": true,
+    "pstate_driver": "intel_pstate",
+    "pstate_governor": "performance",
+    "turboboost_enabled": true
+  },
+  "performance": {
+    "core_flops": 42400000000,
+    "node_flops": 1017600000000
+  },
+  "processor": {
+    "cache_l1": null,
+    "cache_l1d": 32768,
+    "cache_l1i": 32768,
+    "cache_l2": 1048576,
+    "cache_l3": 17301504,
+    "clock_speed": 2650000000,
+    "ht_capable": true,
+    "instruction_set": "x86-64",
+    "microarchitecture": "Zen 3",
+    "microcode": "0x5003604",
+    "model": "Intel Xeon",
+    "other_description": "Intel(R) Xeon(R) Silver 4214 CPU @ 2.20GHz",
+    "vendor": "Intel",
+    "version": "Silver 4214"
+  },
+  "software": {
+    "forced-deployment-timestamp": 202007300948,
+    "postinstall-version": "1.2023092009",
+    "standard-environment": "debian11-x64-std"
+  },
+  "storage_devices": [
+    {
+      "by_id": "/dev/disk/by-id/wwn-0x500a075122839c36",
+      "by_path": "/dev/disk/by-path/pci-0000:04:00.0-ata-1",
+      "firmware_version": "D0DE013",
+      "id": "disk0",
+      "interface": "SATA",
+      "model": "MTFDDAV240TCB",
+      "size": 240057409536,
+      "storage": "SSD",
+      "vendor": "Micron"
+    },
+    {
+      "by_id": "/dev/disk/by-id/wwn-0x500a075122839c30",
+      "by_path": "/dev/disk/by-path/pci-0000:04:00.0-ata-2",
+      "firmware_version": "D0DE013",
+      "id": "disk1",
+      "interface": "SATA",
+      "model": "MTFDDAV240TCB",
+      "size": 240057409536,
+      "storage": "SSD",
+      "vendor": "Micron"
+    }
+  ],
+  "supported_job_types": {
+    "besteffort": true,
+    "deploy": true,
+    "max_walltime": 0,
+    "queues": [
+      "testing",
+      "admin"
+    ],
+    "virtual": "ivt"
+  },
+  "type": "node",
+  "uid": "abacus14-1"
+}
\ No newline at end of file

input/grid5000/sites/rennes/clusters/abacus14/abacus14.yaml

+model: DELL C4140
+created_at: 2023-11-08
+kavlan: false
+boot_type: bios
+exotic: false
+queues:
+  - testing
+  - admin
+nodes:
+  abacus14-1:
+    supported_job_types:
+      deploy: true
+      besteffort: true
+      max_walltime: 0
+    processor:
+      microarchitecture: Zen 3
+      clock_speed: 2650000000
+    software:
+      standard-environment: debian11-x64-std
+    management_tools:
+      bmc_vendor_tool: racadm
+    network_adapters:
+      bmc:
+        interface: Ethernet
+        enabled: true
+        mountable: false
+        mounted: false
+      eth0:
+        enabled: true
+        mountable: true
+        mounted: true
+      eth1:
+        enabled: false
+        mountable: false
+        mounted: false
+    storage_devices:
+      pci-0000:04:00.0-ata-1:
+        id: disk0
+        interface: SATA
+      pci-0000:04:00.0-ata-2:
+        id: disk1
+        interface: SATA

input/grid5000/sites/rennes/clusters/abacus14/abacus14_metrics.yaml

+---
+metrics:
+  - 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/sites/rennes/clusters/abacus14/nodes/abacus14-1.yaml

+# Generated by g5k-checks (g5k-checks -m api)
+---
+abacus14-1:
+  architecture:
+    cpu_core_numbering: round-robin
+    nb_cores: 24
+    nb_procs: 2
+    nb_threads: 48
+    platform_type: x86_64
+  bios:
+    release_date: 06/04/2023
+    vendor: Dell Inc.
+    version: 2.19.1
+  bmc_version: 6.10.80.00
+  chassis:
+    manufacturer: Dell Inc.
+    name: PowerEdge C4140
+    serial: 2VXBRZ2
+  gpu_devices:
+    nvidia0:
+      cpu_affinity: 0
+      device: "/dev/nvidia0"
+      memory: 34089205760
+      model: Tesla V100-PCIE-32GB
+      power_default_limit: 250.00 W
+      vbios_version: 88.00.7E.00.03
+      vendor: Nvidia
+    nvidia1:
+      cpu_affinity: 0
+      device: "/dev/nvidia1"
+      memory: 34089205760
+      model: Tesla V100-PCIE-32GB
+      power_default_limit: 250.00 W
+      vbios_version: 88.00.7E.00.03
+      vendor: Nvidia
+    nvidia2:
+      cpu_affinity: 0
+      device: "/dev/nvidia2"
+      memory: 34089205760
+      model: Tesla V100-PCIE-32GB
+      power_default_limit: 250.00 W
+      vbios_version: 88.00.7E.00.03
+      vendor: Nvidia
+    nvidia3:
+      cpu_affinity: 0
+      device: "/dev/nvidia3"
+      memory: 34089205760
+      model: Tesla V100-PCIE-32GB
+      power_default_limit: 250.00 W
+      vbios_version: 88.00.7E.00.03
+      vendor: Nvidia
+  main_memory:
+    ram_size: 412316860416
+  memory_devices:
+    dimm_a1:
+      size: 34359738368
+      technology: dram
+    dimm_a2:
+      size: 34359738368
+      technology: dram
+    dimm_a3:
+      size: 34359738368
+      technology: dram
+    dimm_a4:
+      size: 34359738368
+      technology: dram
+    dimm_a5:
+      size: 34359738368
+      technology: dram
+    dimm_a6:
+      size: 34359738368
+      technology: dram
+    dimm_b1:
+      size: 34359738368
+      technology: dram
+    dimm_b2:
+      size: 34359738368
+      technology: dram
+    dimm_b3:
+      size: 34359738368
+      technology: dram
+    dimm_b4:
+      size: 34359738368
+      technology: dram
+    dimm_b5:
+      size: 34359738368
+      technology: dram
+    dimm_b6:
+      size: 34359738368
+      technology: dram
+  network_adapters:
+    bmc:
+      ip: 172.17.109.14
+      mac: f4:02:70:b3:e4:9a
+      management: true
+    eth0:
+      driver: i40e
+      firmware_version: 9.20 0x8000d969 22.0.9
+      interface: Ethernet
+      ip: 172.16.109.14
+      mac: e4:43:4b:94:95:32
+      management: false
+      model: Ethernet Controller X710 for 10GbE SFP+
+      name: eno1
+      rate: 10000000000
+      sriov: false
+      sriov_totalvfs: 0
+      vendor: Intel
+    eth1:
+      driver: i40e
+      firmware_version: 9.20 0x8000d969 22.0.9
+      interface: Ethernet
+      mac: e4:43:4b:94:95:34
+      management: false
+      model: Ethernet Controller X710 for 10GbE SFP+
+      name: eno2
+      sriov: false
+      sriov_totalvfs: 0
+      vendor: Intel
+  operating_system:
+    cstate_driver: intel_idle
+    cstate_governor: menu
+    ht_enabled: true
+    pstate_driver: intel_pstate
+    pstate_governor: performance
+    turboboost_enabled: true
+  processor:
+    cache_l1d: 32768
+    cache_l1i: 32768
+    cache_l2: 1048576
+    cache_l3: 17301504
+    ht_capable: true
+    instruction_set: x86-64
+    microcode: '0x5003604'
+    model: Intel Xeon
+    other_description: Intel(R) Xeon(R) Silver 4214 CPU @ 2.20GHz
+    vendor: Intel
+    version: Silver 4214
+  storage_devices:
+    pci-0000:04:00.0-ata-1:
+      by_id: "/dev/disk/by-id/wwn-0x500a075122839c36"
+      by_path: "/dev/disk/by-path/pci-0000:04:00.0-ata-1"
+      firmware_version: D0DE013
+      model: MTFDDAV240TCB
+      size: 240057409536
+      storage: SSD
+    pci-0000:04:00.0-ata-2:
+      by_id: "/dev/disk/by-id/wwn-0x500a075122839c30"
+      by_path: "/dev/disk/by-path/pci-0000:04:00.0-ata-2"
+      firmware_version: D0DE013
+      model: MTFDDAV240TCB
+      size: 240057409536
+      storage: SSD
+  supported_job_types:
+    virtual: ivt

lib/refrepo/net_names_mapping.yaml

@@ -27,6 +27,9 @@ abacus10:
   enp137s0f1: eth1
   eno1np0: eth2
   eno2np1: eth3
+abacus14:
+  eno1: eth0
+  eno2: eth1
 abacus16:
   eno1: eth0
   eno2: eth1

lib/refrepo/valid/oar-properties.rb

@@ -92,7 +92,7 @@ module RefRepo::Valid::OarProperties
         nbcores = nbcores.first
 
         if host_resources.length != nbcores
-          puts "ERROR: invalid number of resources for #{host}. should be nbcores."
+          puts "ERROR: invalid number of resources for #{host}. should be nbcores. (host_resources.length=#{host_resources.length} ; nbcores=#{nbcores})"
           ret = false
         end