diff --git a/data/grid5000/sites/sophia/clusters/esterel6/esterel6.json b/data/grid5000/sites/sophia/clusters/esterel6/esterel6.json new file mode 100644 index 0000000000000000000000000000000000000000..a41b7b21cf7c25a767a5fc8149ecacbff3c42625 --- /dev/null +++ b/data/grid5000/sites/sophia/clusters/esterel6/esterel6.json @@ -0,0 +1,93 @@ +{ + "boot_type": "uefi", + "created_at": "Wed, 26 Feb 2025 00:00:00 GMT", + "exotic": false, + "kavlan": false, + "manufactured_at": "2017-04-18", + "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 E5-2650 v4, 12 cores/CPU, 4 GPUs GeForce GTX 1080 Ti, 64GB RAM, 1862GB HDD, 1 x 1Gb Ethernet, 1 x 40Gb InfiniBand", + "priority": 201804, + "queues": [ + "admin", + "testing" + ], + "redfish": true, + "type": "cluster", + "uid": "esterel6", + "warranty_end": "2022-04-18" +} \ No newline at end of file diff --git a/data/grid5000/sites/sophia/clusters/esterel6/nodes/esterel6-1.json b/data/grid5000/sites/sophia/clusters/esterel6/nodes/esterel6-1.json new file mode 100644 index 0000000000000000000000000000000000000000..c79c894f8c8eb6b629657c16c2fd117a3df21163 --- /dev/null +++ b/data/grid5000/sites/sophia/clusters/esterel6/nodes/esterel6-1.json @@ -0,0 +1,260 @@ +{ + "architecture": { + "cpu_core_numbering": "round-robin", + "nb_cores": 24, + "nb_procs": 2, + "nb_threads": 48, + "platform_type": "x86_64" + }, + "bios": { + "release_date": "10/18/2023", + "vendor": "Dell Inc.", + "version": "2.18.2" + }, + "bmc_version": "2.85.85.85", + "chassis": { + "manufactured_at": "2017-04-18", + "manufacturer": "Dell Inc.", + "name": "PowerEdge T630", + "serial": "9M2TYJ2", + "warranty_end": "2022-04-18" + }, + "exotic": false, + "gpu_devices": { + "nvidia0": { + "compute_capability": "6.1", + "cores": 3584, + "cpu_affinity": 0, + "device": "/dev/nvidia0", + "memory": 11811160064, + "microarchitecture": "Pascal", + "model": "GeForce GTX 1080 Ti", + "performance": { + "fp-16": 177200000000, + "fp-32": 11340000000000, + "fp-64": 354400000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "86.02.39.00.01", + "vendor": "Nvidia" + }, + "nvidia1": { + "compute_capability": "6.1", + "cores": 3584, + "cpu_affinity": 0, + "device": "/dev/nvidia1", + "memory": 11811160064, + "microarchitecture": "Pascal", + "model": "GeForce GTX 1080 Ti", + "performance": { + "fp-16": 177200000000, + "fp-32": 11340000000000, + "fp-64": 354400000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "86.02.39.00.01", + "vendor": "Nvidia" + }, + "nvidia2": { + "compute_capability": "6.1", + "cores": 3584, + "cpu_affinity": 1, + "device": "/dev/nvidia2", + "memory": 11811160064, + "microarchitecture": "Pascal", + "model": "GeForce GTX 1080 Ti", + "performance": { + "fp-16": 177200000000, + "fp-32": 11340000000000, + "fp-64": 354400000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "86.02.39.40.6B", + "vendor": "Nvidia" + }, + "nvidia3": { + "compute_capability": "6.1", + "cores": 3584, + "cpu_affinity": 1, + "device": "/dev/nvidia3", + "memory": 11811160064, + "microarchitecture": "Pascal", + "model": "GeForce GTX 1080 Ti", + "performance": { + "fp-16": 177200000000, + "fp-32": 11340000000000, + "fp-64": 354400000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "86.02.39.40.6B", + "vendor": "Nvidia" + } + }, + "main_memory": { + "ram_size": 68719476736 + }, + "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_b1", + "size": 17179869184, + "technology": "dram" + }, + { + "device": "dimm_b2", + "size": 17179869184, + "technology": "dram" + } + ], + "network_adapters": [ + { + "device": "eth0", + "driver": "igb", + "enabled": true, + "firmware_version": "1.67, 0x80000fae, 19.5.12", + "interface": "Ethernet", + "ip": "172.16.131.7", + "ip6": "2001:660:4406:800:4::7", + "kavlan": false, + "mac": "18:66:da:a6:f0:f1", + "management": false, + "model": "I350 Gigabit Network Connection", + "mountable": true, + "mounted": true, + "name": "enp1s0f0np0", + "network_address": "esterel6-1.sophia.grid5000.fr", + "rate": 1000000000, + "sriov": false, + "sriov_totalvfs": 0, + "switch": "sw-6", + "switch_port": "1/1/16", + "vendor": "Intel" + }, + { + "device": "eth1", + "driver": "igb", + "enabled": false, + "firmware_version": "1.67, 0x80000fae, 19.5.12", + "interface": "Ethernet", + "kavlan": false, + "mac": "18:66:da:a6:f0:f2", + "management": false, + "model": "I350 Gigabit Network Connection", + "mountable": false, + "mounted": false, + "name": "eno2", + "sriov": false, + "sriov_totalvfs": 0, + "vendor": "Intel" + }, + { + "device": "ib0", + "driver": "ib_ipoib", + "enabled": true, + "firmware_version": "2.40.5000", + "guid": "0x248a070300ffd1c1", + "interface": "InfiniBand", + "ip": "172.18.131.7", + "kavlan": false, + "mac": "80:00:02:08:fe:80:00:00:00:00:00:00:24:8a:07:03:00:ff:d1:c1", + "management": false, + "model": "MT27500 Family [ConnectX-3]", + "mountable": true, + "mounted": true, + "name": "ibp130s0", + "netmask": "255.255.240.0", + "network_address": "esterel6-1-ib0.sophia.grid5000.fr", + "rate": 40000000000, + "sriov": false, + "sriov_totalvfs": 0, + "vendor": "Mellanox Technologies" + }, + { + "device": "bmc", + "enabled": true, + "interface": "Ethernet", + "ip": "172.17.131.7", + "kavlan": false, + "mac": "18:66:da:a6:f0:f3", + "management": true, + "mountable": false, + "mounted": false, + "network_address": "esterel6-1-bmc.sophia.grid5000.fr" + } + ], + "nodeset": "esterel6", + "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": 844800000000 + }, + "processor": { + "cache_l1": null, + "cache_l1d": 32768, + "cache_l1i": 32768, + "cache_l2": 262144, + "cache_l3": 31457280, + "clock_speed": 2200000000, + "ht_capable": true, + "instruction_set": "x86-64", + "microarchitecture": "Broadwell", + "microcode": "0xb000040", + "model": "Intel Xeon", + "other_description": "Intel(R) Xeon(R) CPU E5-2650 v4 @ 2.20GHz", + "vendor": "Intel", + "version": "E5-2650 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-0x61866da0a594e5002f66bf5e14ffcf3a", + "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" + } + ], + "supported_job_types": { + "besteffort": true, + "deploy": true, + "max_walltime": 0, + "queues": [ + "admin", + "testing" + ], + "virtual": "ivt" + }, + "type": "node", + "uid": "esterel6-1" +} \ No newline at end of file diff --git a/input/grid5000/dell-product-data.yaml b/input/grid5000/dell-product-data.yaml index 8365f2e7455b190a1b8f97fa1827416b7a8e91e7..1548aa6b2ed9724cea82ca144bc3ac94b8646eee 100644 --- a/input/grid5000/dell-product-data.yaml +++ b/input/grid5000/dell-product-data.yaml @@ -2266,6 +2266,12 @@ sites: chassis: manufactured_at: 2017-03-30 warranty_end: 2022-03-30 + esterel6: + nodes: + esterel6-1: + chassis: + manufactured_at: 2017-04-18 + warranty_end: 2022-04-18 esterel7: nodes: esterel7-1: diff --git a/input/grid5000/ipv4.yaml b/input/grid5000/ipv4.yaml index 1e8210b4134a0c89acc9c0e532533857b0ba7fb0..d61dbdd5f2dae5df3ee1d7dce4e2fde1d255f928 100644 --- a/input/grid5000/ipv4.yaml +++ b/input/grid5000/ipv4.yaml @@ -165,6 +165,7 @@ ipv4: sophia esterel5 eth0 0 0 3 4 sophia esterel5 ib0 0 0 3 4 sophia esterel6 eth0 0 0 3 6 + sophia esterel6 ib0 0 0 3 6 sophia esterel7 eth0 0 0 3 7 sophia esterel7 ib0 0 0 3 7 sophia esterel8 eth0 0 0 3 9 diff --git a/input/grid5000/sites/sophia/clusters/esterel6/esterel6.yaml b/input/grid5000/sites/sophia/clusters/esterel6/esterel6.yaml new file mode 100644 index 0000000000000000000000000000000000000000..a36710766dd951b3f20e59f4d38255e157322b92 --- /dev/null +++ b/input/grid5000/sites/sophia/clusters/esterel6/esterel6.yaml @@ -0,0 +1,46 @@ +--- +model: Dell PowerEdge T630 +created_at: 2025-02-26 +kavlan: false +boot_type: uefi +exotic: false +queues: + - admin + - testing +nodes: + esterel6-1: + supported_job_types: + deploy: true + besteffort: true + max_walltime: 0 + processor: + microarchitecture: Broadwell + clock_speed: 2200000000 + 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 + ib0: + mounted: true + enabled: true + mountable: true + netmask: 255.255.240.0 + storage_devices: + pci-0000:03:00.0-scsi-0:2:0:0: + id: disk0 + interface: SAS + software: + standard-environment: debian11-x64-std + management_tools: + bmc_vendor_tool: racadm + nodeset: esterel6 diff --git a/input/grid5000/sites/sophia/clusters/esterel6/esterel6_metrics.yaml b/input/grid5000/sites/sophia/clusters/esterel6/esterel6_metrics.yaml new file mode 100644 index 0000000000000000000000000000000000000000..a59d3e58fa6e79bb6cb8b10b5f983dfcdf43b110 --- /dev/null +++ b/input/grid5000/sites/sophia/clusters/esterel6/esterel6_metrics.yaml @@ -0,0 +1,64 @@ +--- +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 diff --git a/input/grid5000/sites/sophia/clusters/esterel6/nodes/esterel6-1.yaml b/input/grid5000/sites/sophia/clusters/esterel6/nodes/esterel6-1.yaml new file mode 100644 index 0000000000000000000000000000000000000000..cebecacb0b818653ceb4d96d903e940596603750 --- /dev/null +++ b/input/grid5000/sites/sophia/clusters/esterel6/nodes/esterel6-1.yaml @@ -0,0 +1,137 @@ +# Generated by g5k-checks (g5k-checks -m api) +--- +esterel6-1: + architecture: + cpu_core_numbering: round-robin + nb_cores: 24 + nb_procs: 2 + nb_threads: 48 + platform_type: x86_64 + bios: + release_date: 10/18/2023 + vendor: Dell Inc. + version: 2.18.2 + bmc_version: 2.85.85.85 + chassis: + manufacturer: Dell Inc. + name: PowerEdge T630 + serial: 9M2TYJ2 + gpu_devices: + nvidia0: + cpu_affinity: 0 + device: "/dev/nvidia0" + memory: 11811160064 + model: GeForce GTX 1080 Ti + power_default_limit: 250.00 W + vbios_version: 86.02.39.00.01 + vendor: Nvidia + nvidia1: + cpu_affinity: 0 + device: "/dev/nvidia1" + memory: 11811160064 + model: GeForce GTX 1080 Ti + power_default_limit: 250.00 W + vbios_version: 86.02.39.00.01 + vendor: Nvidia + nvidia2: + cpu_affinity: 1 + device: "/dev/nvidia2" + memory: 11811160064 + model: GeForce GTX 1080 Ti + power_default_limit: 250.00 W + vbios_version: 86.02.39.40.6B + vendor: Nvidia + nvidia3: + cpu_affinity: 1 + device: "/dev/nvidia3" + memory: 11811160064 + model: GeForce GTX 1080 Ti + power_default_limit: 250.00 W + vbios_version: 86.02.39.40.6B + vendor: Nvidia + main_memory: + ram_size: 68719476736 + memory_devices: + dimm_a1: + size: 17179869184 + technology: dram + dimm_a2: + size: 17179869184 + technology: dram + dimm_b1: + size: 17179869184 + technology: dram + dimm_b2: + size: 17179869184 + technology: dram + network_adapters: + bmc: + ip: 172.17.131.7 + mac: 18:66:da:a6:f0:f3 + management: true + eth0: + driver: igb + firmware_version: 1.67, 0x80000fae, 19.5.12 + interface: Ethernet + ip: 172.16.131.7 + mac: 18:66:da:a6:f0:f1 + 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:a6:f0:f2 + management: false + model: I350 Gigabit Network Connection + name: eno2 + sriov: false + sriov_totalvfs: 0 + vendor: Intel + ib0: + driver: ib_ipoib + firmware_version: 2.40.5000 + guid: '0x248a070300ffd1c1' + interface: InfiniBand + mac: 80:00:02:08:fe:80:00:00:00:00:00:00:24:8a:07:03:00:ff:d1: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: 31457280 + ht_capable: true + instruction_set: x86-64 + microcode: '0xb000040' + model: Intel Xeon + other_description: Intel(R) Xeon(R) CPU E5-2650 v4 @ 2.20GHz + vendor: Intel + version: E5-2650 v4 + storage_devices: + pci-0000:03:00.0-scsi-0:2:0:0: + by_id: "/dev/disk/by-id/wwn-0x61866da0a594e5002f66bf5e14ffcf3a" + 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 + supported_job_types: + virtual: ivt diff --git a/lib/refrepo/net_names_mapping.yaml b/lib/refrepo/net_names_mapping.yaml index 145cebec70dd1cab8889161bb0ee9de68bdeff7c..130141926d5d1302a0011bd1aae3d19ac72f46cf 100644 --- a/lib/refrepo/net_names_mapping.yaml +++ b/lib/refrepo/net_names_mapping.yaml @@ -418,6 +418,10 @@ esterel7: enp1s0f0np0: eth0 enp1s0f1: eth1 ibp130s0: ib0 +esterel6: + enp1s0f0np0: eth0 + eno2: eth1 + ibp130s0: ib0 esterel10: eno1: eth0 eno2: eth1