Merge branch 'testing-esterel4' into 'master'

[sophia][esterel4] Add esterel4 to testing queue

See merge request !1145

data/grid5000/sites/sophia/clusters/esterel4/esterel4.json

+{
+  "boot_type": "bios",
+  "created_at": "Thu, 20 Mar 2025 00:00:00 GMT",
+  "exotic": false,
+  "kavlan": false,
+  "manufactured_at": "2016-06-08",
+  "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"
+      }
+    },
+    {
+      "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_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"
+      }
+    }
+  ],
+  "model": "Dell PowerEdge T630",
+  "nodes_count": 1,
+  "nodes_description": "2 CPUs Intel Xeon E5-2630 v4, 10 cores/CPU, 4 GPUs GeForce GTX TITAN X, 128GB RAM, 1862GB HDD, 1489GB HDD, 1 x 1Gb Ethernet, 1 x 40Gb InfiniBand",
+  "priority": 201706,
+  "queues": [
+    "admin",
+    "testing"
+  ],
+  "redfish": true,
+  "type": "cluster",
+  "uid": "esterel4",
+  "warranty_end": "2021-06-08"
+}
\ No newline at end of file

data/grid5000/sites/sophia/clusters/esterel4/nodes/esterel4-1.json

+{
+  "architecture": {
+    "cpu_core_numbering": "round-robin",
+    "nb_cores": 20,
+    "nb_procs": 2,
+    "nb_threads": 40,
+    "platform_type": "x86_64"
+  },
+  "bios": {
+    "release_date": "10/18/2023",
+    "vendor": "Dell Inc.",
+    "version": "2.18.2"
+  },
+  "bmc_version": "unknown",
+  "chassis": {
+    "manufactured_at": "2016-06-08",
+    "manufacturer": "Dell Inc.",
+    "name": "PowerEdge T630",
+    "serial": "HHTDDD2",
+    "warranty_end": "2021-06-08"
+  },
+  "exotic": false,
+  "gpu_devices": {
+    "nvidia0": {
+      "compute_capability": "5.2",
+      "cores": 3072,
+      "cpu_affinity": 0,
+      "device": "/dev/nvidia0",
+      "memory": 12884901888,
+      "microarchitecture": "Maxwell",
+      "model": "GeForce GTX TITAN X",
+      "performance": {
+        "fp-16": 0,
+        "fp-32": 66050000000000,
+        "fp-64": 206500000000
+      },
+      "power_default_limit": "250.00 W",
+      "vbios_version": "84.00.45.00.03",
+      "vendor": "Nvidia"
+    },
+    "nvidia1": {
+      "compute_capability": "5.2",
+      "cores": 3072,
+      "cpu_affinity": 0,
+      "device": "/dev/nvidia1",
+      "memory": 12884901888,
+      "microarchitecture": "Maxwell",
+      "model": "GeForce GTX TITAN X",
+      "performance": {
+        "fp-16": 0,
+        "fp-32": 66050000000000,
+        "fp-64": 206500000000
+      },
+      "power_default_limit": "250.00 W",
+      "vbios_version": "84.00.45.00.03",
+      "vendor": "Nvidia"
+    },
+    "nvidia2": {
+      "compute_capability": "5.2",
+      "cores": 3072,
+      "cpu_affinity": 1,
+      "device": "/dev/nvidia2",
+      "memory": 12884901888,
+      "microarchitecture": "Maxwell",
+      "model": "GeForce GTX TITAN X",
+      "performance": {
+        "fp-16": 0,
+        "fp-32": 66050000000000,
+        "fp-64": 206500000000
+      },
+      "power_default_limit": "250.00 W",
+      "vbios_version": "84.00.45.00.03",
+      "vendor": "Nvidia"
+    },
+    "nvidia3": {
+      "compute_capability": "5.2",
+      "cores": 3072,
+      "cpu_affinity": 1,
+      "device": "/dev/nvidia3",
+      "memory": 12884901888,
+      "microarchitecture": "Maxwell",
+      "model": "GeForce GTX TITAN X",
+      "performance": {
+        "fp-16": 0,
+        "fp-32": 66050000000000,
+        "fp-64": 206500000000
+      },
+      "power_default_limit": "250.00 W",
+      "vbios_version": "84.00.45.00.03",
+      "vendor": "Nvidia"
+    }
+  },
+  "main_memory": {
+    "ram_size": 137438953472
+  },
+  "management_tools": {
+    "bmc_vendor_tool": "racadm",
+    "ipmitool": {
+      "retries": 5
+    }
+  },
+  "memory_devices": [
+    {
+      "device": "dimm_a1",
+      "size": 17179869184,
+      "technology": "dram"
+    },
+    {
+      "device": "dimm_a2",
+      "size": 17179869184,
+      "technology": "dram"
+    },
+    {
+      "device": "dimm_a3",
+      "size": 17179869184,
+      "technology": "dram"
+    },
+    {
+      "device": "dimm_a4",
+      "size": 17179869184,
+      "technology": "dram"
+    },
+    {
+      "device": "dimm_b1",
+      "size": 17179869184,
+      "technology": "dram"
+    },
+    {
+      "device": "dimm_b2",
+      "size": 17179869184,
+      "technology": "dram"
+    },
+    {
+      "device": "dimm_b3",
+      "size": 17179869184,
+      "technology": "dram"
+    },
+    {
+      "device": "dimm_b4",
+      "size": 17179869184,
+      "technology": "dram"
+    }
+  ],
+  "network_adapters": [
+    {
+      "device": "eth0",
+      "driver": "igb",
+      "enabled": true,
+      "firmware_version": "1.67, 0x80000fae, 19.5.12",
+      "interface": "Ethernet",
+      "ip": "172.16.131.4",
+      "ip6": "2001:660:4406:800:4::4",
+      "kavlan": false,
+      "mac": "18:66:da:55:21:c8",
+      "management": false,
+      "model": "I350 Gigabit Network Connection",
+      "mountable": true,
+      "mounted": true,
+      "name": "enp1s0f0np0",
+      "network_address": "esterel4-1.sophia.grid5000.fr",
+      "rate": 1000000000,
+      "sriov": false,
+      "sriov_totalvfs": 0,
+      "switch": "sw-6",
+      "switch_port": "1/1/3",
+      "vendor": "Intel"
+    },
+    {
+      "device": "eth1",
+      "driver": "igb",
+      "enabled": false,
+      "firmware_version": "1.67, 0x80000fae, 19.5.12",
+      "interface": "Ethernet",
+      "kavlan": false,
+      "mac": "18:66:da:55:21:c9",
+      "management": false,
+      "model": "I350 Gigabit Network Connection",
+      "mountable": false,
+      "mounted": false,
+      "name": "eno2",
+      "sriov": false,
+      "sriov_totalvfs": 0,
+      "vendor": "Intel"
+    },
+    {
+      "device": "ib0",
+      "driver": "mlx4_core",
+      "enabled": true,
+      "firmware_version": "2.35.5100",
+      "guid": "0xe41d2d030050b8c1",
+      "interface": "InfiniBand",
+      "ip": "172.18.131.4",
+      "kavlan": false,
+      "mac": "e4:1d:2d:03:00:50:b8:c1",
+      "management": false,
+      "model": "MT27500 Family [ConnectX-3]",
+      "mountable": true,
+      "mounted": true,
+      "name": "ibp130s0",
+      "netmask": "255.255.240.0",
+      "network_address": "esterel4-1-ib0.sophia.grid5000.fr",
+      "rate": 40000000000,
+      "sriov": false,
+      "sriov_totalvfs": 0,
+      "vendor": "Mellanox Technologies"
+    },
+    {
+      "device": "bmc",
+      "enabled": true,
+      "interface": "Ethernet",
+      "ip": "172.17.131.4",
+      "kavlan": false,
+      "mac": "18:66:da:55:21:ca",
+      "management": true,
+      "mountable": false,
+      "mounted": false,
+      "network_address": "esterel4-1-bmc.sophia.grid5000.fr"
+    }
+  ],
+  "nodeset": "esterel4",
+  "operating_system": {
+    "cstate_driver": "intel_idle",
+    "cstate_governor": "menu",
+    "ht_enabled": true,
+    "pstate_driver": "intel_cpufreq",
+    "pstate_governor": "performance",
+    "turboboost_enabled": true
+  },
+  "performance": {
+    "core_flops": 35200000000,
+    "node_flops": 704000000000
+  },
+  "processor": {
+    "cache_l1": null,
+    "cache_l1d": 32768,
+    "cache_l1i": 32768,
+    "cache_l2": 262144,
+    "cache_l3": 26214400,
+    "clock_speed": 2200000000,
+    "ht_capable": true,
+    "instruction_set": "x86-64",
+    "microarchitecture": "Haswell",
+    "microcode": "0xb000040",
+    "model": "Intel Xeon",
+    "other_description": "Intel(R) Xeon(R) CPU E5-2630 v4 @ 2.20GHz",
+    "vendor": "Intel",
+    "version": "E5-2630 v4"
+  },
+  "redfish": true,
+  "software": {
+    "forced-deployment-timestamp": 202007300948,
+    "postinstall-version": "1.2025032008",
+    "standard-environment": "debian11-x64-std"
+  },
+  "storage_devices": [
+    {
+      "by_id": "/dev/disk/by-id/wwn-0x61866da0578978001ef5b04c0f56fda4",
+      "by_path": "/dev/disk/by-path/pci-0000:03:00.0-scsi-0:2:0:0",
+      "firmware_version": 4.3,
+      "id": "disk0",
+      "interface": "SAS",
+      "model": "PERC H730 Adp",
+      "size": 1999307276288,
+      "storage": "HDD",
+      "vendor": "Dell"
+    },
+    {
+      "by_id": "/dev/disk/by-id/wwn-0x61866da0578978001efaccdb8e9c9a3e",
+      "by_path": "/dev/disk/by-path/pci-0000:03:00.0-scsi-0:2:1:0",
+      "firmware_version": 4.3,
+      "id": "disk1",
+      "interface": "SATA",
+      "model": "PERC H730 Adp",
+      "size": 1599741100032,
+      "storage": "HDD",
+      "vendor": "Dell"
+    }
+  ],
+  "supported_job_types": {
+    "besteffort": true,
+    "deploy": true,
+    "max_walltime": 0,
+    "queues": [
+      "admin",
+      "testing"
+    ],
+    "virtual": "ivt"
+  },
+  "type": "node",
+  "uid": "esterel4-1"
+}
\ No newline at end of file

data/grid5000/sites/sophia/network_equipments/sw-6.json

@@ -19,6 +19,10 @@
         {
         },
         {
+          "kind": "node",
+          "port": "eth0",
+          "snmp_name": "1/1/3",
+          "uid": "esterel4-1"
         },
         {
         },

data/grid5000/sites/sophia/network_equipments/swadmin-6.json

@@ -55,6 +55,9 @@
         {
         },
         {
+          "kind": "other",
+          "snmp_name": "1/1/11",
+          "uid": "esterel4-1-bmc"
         },
         {
         },

input/grid5000/dell-product-data.yaml

@@ -2238,6 +2238,12 @@ sites:
             chassis:
               manufactured_at: 2016-05-04
               warranty_end: 2021-05-04
+      esterel4:
+        nodes:
+          esterel4-1:
+            chassis:
+              manufactured_at: 2016-06-08
+              warranty_end: 2021-06-08
       esterel5:
         nodes:
           esterel5-1:

input/grid5000/disks.yaml

@@ -92,6 +92,7 @@ disk_vendor_model_mapping:
       - SSDSC2KG480G8R
       - SSDSC2KG960G8R
       - INTEL SSDSC2BB30
+      - INTEL SSDSC2BX01
     Hitachi:
       - HITACHI HUA7250S
     HP:

input/grid5000/ipv4.yaml

@@ -160,6 +160,7 @@ ipv4:
       sophia esterel2 ib0  0 0 3 1
       sophia esterel3 eth0 0 0 3 2
       sophia esterel4 eth0 0 0 3 3
+      sophia esterel4 ib0  0 0 3 3
       sophia esterel5 eth0 0 0 3 4
       sophia esterel5 ib0 0 0 3 4
       sophia esterel6 eth0 0 0 3 6

input/grid5000/sites/sophia/clusters/esterel4/esterel4.yaml

+---
+model: Dell PowerEdge T630
+created_at: 2025-03-20
+kavlan: false
+boot_type: bios
+exotic: false
+queues:
+  - admin
+  - testing
+nodes:
+  esterel4-1:
+    supported_job_types:
+      deploy: true
+      besteffort: true
+      max_walltime: 0
+    processor:
+      microarchitecture: Haswell
+      clock_speed: 2_200_000_000
+    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-0000:03:00.0-scsi-0:2:0:0:
+        id: disk0
+        interface: SAS
+      pci-0000:03:00.0-scsi-0:2:1:0:
+        id: disk1
+        interface: SATA
+    software:
+      standard-environment: debian11-x64-std
+    management_tools:
+      bmc_vendor_tool: racadm
+    nodeset: esterel4

input/grid5000/sites/sophia/clusters/esterel4/esterel4_ib.yaml

+---
+nodes:
+  esterel4-1:
+    network_adapters:
+      ib0:
+        enabled: true
+        mountable: true
+        mounted: true
+        netmask: 255.255.240.0
\ No newline at end of file

input/grid5000/sites/sophia/clusters/esterel4/esterel4_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
+
+  - 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_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
\ No newline at end of file

input/grid5000/sites/sophia/clusters/esterel4/nodes/esterel4-1.yaml

+# Generated by g5k-checks (g5k-checks -m api)
+---
+esterel4-1:
+  architecture:
+    cpu_core_numbering: round-robin
+    nb_cores: 20
+    nb_procs: 2
+    nb_threads: 40
+    platform_type: x86_64
+  bios:
+    release_date: 10/18/2023
+    vendor: Dell Inc.
+    version: 2.18.2
+  bmc_version: unknown
+  chassis:
+    manufacturer: Dell Inc.
+    name: PowerEdge T630
+    serial: HHTDDD2
+  gpu_devices:
+    nvidia0:
+      cpu_affinity: 0
+      device: "/dev/nvidia0"
+      memory: 12884901888
+      model: GeForce GTX TITAN X
+      power_default_limit: 250.00 W
+      vbios_version: 84.00.45.00.03
+      vendor: Nvidia
+    nvidia1:
+      cpu_affinity: 0
+      device: "/dev/nvidia1"
+      memory: 12884901888
+      model: GeForce GTX TITAN X
+      power_default_limit: 250.00 W
+      vbios_version: 84.00.45.00.03
+      vendor: Nvidia
+    nvidia2:
+      cpu_affinity: 1
+      device: "/dev/nvidia2"
+      memory: 12884901888
+      model: GeForce GTX TITAN X
+      power_default_limit: 250.00 W
+      vbios_version: 84.00.45.00.03
+      vendor: Nvidia
+    nvidia3:
+      cpu_affinity: 1
+      device: "/dev/nvidia3"
+      memory: 12884901888
+      model: GeForce GTX TITAN X
+      power_default_limit: 250.00 W
+      vbios_version: 84.00.45.00.03
+      vendor: Nvidia
+  main_memory:
+    ram_size: 137438953472
+  memory_devices:
+    dimm_a1:
+      size: 17179869184
+      technology: dram
+    dimm_a2:
+      size: 17179869184
+      technology: dram
+    dimm_a3:
+      size: 17179869184
+      technology: dram
+    dimm_a4:
+      size: 17179869184
+      technology: dram
+    dimm_b1:
+      size: 17179869184
+      technology: dram
+    dimm_b2:
+      size: 17179869184
+      technology: dram
+    dimm_b3:
+      size: 17179869184
+      technology: dram
+    dimm_b4:
+      size: 17179869184
+      technology: dram
+  network_adapters:
+    bmc:
+      ip: 172.17.131.4
+      mac: 18:66:da:55:21:ca
+      management: true
+    eth0:
+      driver: igb
+      firmware_version: 1.67, 0x80000fae, 19.5.12
+      interface: Ethernet
+      ip: 172.16.131.4
+      mac: 18:66:da:55:21:c8
+      management: false
+      model: I350 Gigabit Network Connection
+      name: enp1s0f0np0
+      rate: 1000000000
+      sriov: false
+      sriov_totalvfs: 0
+      vendor: Intel
+    eth1:
+      driver: igb
+      firmware_version: 1.67, 0x80000fae, 19.5.12
+      interface: Ethernet
+      mac: 18:66:da:55:21:c9
+      management: false
+      model: I350 Gigabit Network Connection
+      name: eno2
+      sriov: false
+      sriov_totalvfs: 0
+      vendor: Intel
+    ib0:
+      driver: mlx4_core
+      firmware_version: 2.35.5100
+      guid: '0xe41d2d030050b8c1'
+      interface: InfiniBand
+      mac: e4:1d:2d:03:00:50:b8:c1
+      management: false
+      model: MT27500 Family [ConnectX-3]
+      name: ibp130s0
+      rate: 40000000000
+      sriov: false
+      sriov_totalvfs: 0
+      vendor: Mellanox Technologies
+  operating_system:
+    cstate_driver: intel_idle
+    cstate_governor: menu
+    ht_enabled: true
+    pstate_driver: intel_cpufreq
+    pstate_governor: performance
+    turboboost_enabled: true
+  processor:
+    cache_l1d: 32768
+    cache_l1i: 32768
+    cache_l2: 262144
+    cache_l3: 26214400
+    ht_capable: true
+    instruction_set: x86-64
+    microcode: '0xb000040'
+    model: Intel Xeon
+    other_description: Intel(R) Xeon(R) CPU E5-2630 v4 @ 2.20GHz
+    vendor: Intel
+    version: E5-2630 v4
+  storage_devices:
+    pci-0000:03:00.0-scsi-0:2:0:0:
+      by_id: "/dev/disk/by-id/wwn-0x61866da0578978001ef5b04c0f56fda4"
+      by_path: "/dev/disk/by-path/pci-0000:03:00.0-scsi-0:2:0:0"
+      firmware_version: 4.3
+      model: PERC H730 Adp
+      size: 1999307276288
+      storage: HDD
+    pci-0000:03:00.0-scsi-0:2:1:0:
+      by_id: "/dev/disk/by-id/wwn-0x61866da0578978001efaccdb8e9c9a3e"
+      by_path: "/dev/disk/by-path/pci-0000:03:00.0-scsi-0:2:1:0"
+      firmware_version: 4.3
+      model: PERC H730 Adp
+      size: 1599741100032
+      storage: HDD
+  supported_job_types:
+    virtual: ivt

input/grid5000/sites/sophia/networks/sw-6.yaml

@@ -16,6 +16,8 @@ sw-6:
       ports:
         1:
           uid: esterel2-1
+        3:
+          uid: esterel4-1
         13:
           uid: esterel1-1
         14:

input/grid5000/sites/sophia/networks/swadmin-6.yaml

@@ -38,6 +38,9 @@ swadmin-6:
         9:
           uid: esterel2-1-bmc
           kind: other
+        11:
+          uid: esterel4-1-bmc
+          kind: other
         25:
           uid: sw-6
           kind: switch

lib/refrepo/gpu_ref.rb

@@ -140,6 +140,18 @@ class GPURef
         'fp-64' => 342900000000,
       },
     },
+    'GeForce GTX TITAN X' => {
+      'cores'              => 3072,
+      'compute_capability' => '5.2',
+      'short_name'         => 'GTX TITAN X',
+      'alias'              => 'gtxtitanx',
+      'microarchitecture'  => 'Maxwell',
+      'performance'        => {
+        'fp-16' => 0,
+        'fp-32' => 66050000000000,
+        'fp-64' => 206500000000,
+      },
+    },
     'Tesla K40m' => {
       'cores'              => 2880,
       'compute_capability' => '3.5',

lib/refrepo/net_names_mapping.yaml

@@ -398,6 +398,10 @@ esterel1:
   eno3: eth2
   eno4: eth3
   ibp131s0: ib0
+esterel4:
+  enp1s0f0np0: eth0
+  eno2: eth1
+  ibp130s0: ib0
 esterel5:
   eno1: eth0
   eno2: eth1