From 0f815b925e48ab4e5ac2080e5a32bc77a1dff8a1 Mon Sep 17 00:00:00 2001 From: Nicolas Perrin <nicolas.perrin@inria.fr> Date: Wed, 19 Mar 2025 14:52:04 +0100 Subject: [PATCH 1/9] [sophia][esterel22] add basic configuration generated by rake mass:create --- .../sophia/clusters/esterel22/esterel22.json | 66 +++++++++ .../clusters/esterel22/nodes/esterel22-1.json | 128 ++++++++++++++++++ .../sophia/clusters/esterel22/esterel22.yaml | 41 ++++++ .../clusters/esterel22/esterel22_metrics.yaml | 40 ++++++ .../sophia/clusters/esterel22/nodes.yaml.erb | 80 +++++++++++ 5 files changed, 355 insertions(+) create mode 100644 data/grid5000/sites/sophia/clusters/esterel22/esterel22.json create mode 100644 data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json create mode 100644 input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml create mode 100644 input/grid5000/sites/sophia/clusters/esterel22/esterel22_metrics.yaml create mode 100644 input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb diff --git a/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json b/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json new file mode 100644 index 00000000000..925071e50e4 --- /dev/null +++ b/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json @@ -0,0 +1,66 @@ +{ + "boot_type": "uefi", + "created_at": "Thu, 01 Jan 1970 00:00:00 GMT", + "exotic": false, + "kavlan": false, + "manufactured_at": "1970-01-01", + "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": "Cluster Model", + "nodes_count": 1, + "nodes_description": "1 CPU Unknown vendor, 72 cores/CPU, 0GB RAM, 0GB SSD, 1 x 10Gb Ethernet", + "priority": 197001, + "queues": [ + "admin", + "testing" + ], + "redfish": true, + "type": "cluster", + "uid": "esterel22", + "warranty_end": "1970-01-01" +} \ No newline at end of file diff --git a/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json b/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json new file mode 100644 index 00000000000..75f810e1ee1 --- /dev/null +++ b/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json @@ -0,0 +1,128 @@ +{ + "architecture": { + "cpu_core_numbering": "contiguous", + "nb_cores": 72, + "nb_procs": 1, + "nb_threads": 72, + "platform_type": "x86_64" + }, + "bios": { + "release_date": "01/01/2000", + "vendor": "Unknown", + "version": 1 + }, + "bmc_version": "v1", + "chassis": { + "manufactured_at": "1970-01-01", + "manufacturer": "Unknown", + "name": "Unknown", + "warranty_end": "1970-01-01" + }, + "exotic": false, + "main_memory": { + "ram_size": 8 + }, + "management_tools": { + "bmc_vendor_tool": "ipmitool", + "ipmitool": { + "retries": 5 + } + }, + "memory_devices": [ + { + "device": "dimm_proc 1 dimm 1", + "size": 8, + "technology": "dram" + } + ], + "network_adapters": [ + { + "device": "eth0", + "driver": "mlx_core", + "enabled": true, + "interface": "Ethernet", + "ip": "172.16.131.28", + "ip6": "2001:660:4406:800:4::1c", + "kavlan": false, + "mac": "34:17:eb:e8:83:84", + "management": false, + "mountable": true, + "mounted": true, + "name": "enp1s0f0np0", + "network_address": "esterel22-1.sophia.grid5000.fr", + "rate": 10000000000, + "switch": null, + "switch_port": null + }, + { + "device": "bmc", + "enabled": true, + "interface": "Ethernet", + "ip": "172.17.131.28", + "kavlan": false, + "mac": "f4:02:70:9d:f4:e8", + "management": true, + "mountable": false, + "mounted": false, + "network_address": "esterel22-1-bmc.sophia.grid5000.fr" + } + ], + "nodeset": "esterel22", + "operating_system": { + "cstate_driver": "unknown", + "cstate_governor": "unknown", + "ht_enabled": true, + "pstate_driver": "unknwon", + "pstate_governor": "unknown", + "turboboost_enabled": true + }, + "performance": { + "core_flops": 128, + "node_flops": 9216 + }, + "processor": { + "cache_l1": null, + "cache_l1d": 8, + "cache_l1i": 8, + "cache_l2": 8, + "cache_l3": 8, + "clock_speed": 8, + "ht_capable": true, + "instruction_set": "x86-64", + "microarchitecture": "Haswell", + "microcode": "0xd000001", + "model": "Unknown", + "other_description": "description", + "vendor": "vendor", + "version": "vendor" + }, + "redfish": true, + "software": { + "forced-deployment-timestamp": 202007300948, + "postinstall-version": "1.2025021810", + "standard-environment": "debian11-x64-std" + }, + "storage_devices": [ + { + "by_id": "", + "by_path": "/dev/disk/by-path/dummy", + "id": "disk0", + "interface": "SAS", + "model": "unknown", + "size": 8, + "storage": "SSD", + "vendor": "Unknown" + } + ], + "supported_job_types": { + "besteffort": true, + "deploy": true, + "max_walltime": 0, + "queues": [ + "admin", + "testing" + ] + }, + "type": "node", + "uid": "esterel22-1" +} \ No newline at end of file diff --git a/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml b/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml new file mode 100644 index 00000000000..fd0ec344fb0 --- /dev/null +++ b/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml @@ -0,0 +1,41 @@ +--- +model: Cluster Model # TODO: change this value. +created_at: 1970-01-01 # TODO: change this value +kavlan: false +boot_type: uefi # TODO: specify if 'uefi' (ideally) or 'bios' (legacy, if no other choice) +exotic: false # TODO: specify if 'true' or 'false' +queues: + - admin + - testing +nodes: + esterel22-1: + chassis: + manufactured_at: 1970-01-01 # TODO: if not Dell vendor, put date. if Dell, use rake gen:dell-product-data after g5k-checks import, and remove this line. + warranty_end: 1970-01-01 # TODO: if not Dell vendor, put date. if Dell, use rake gen:dell-product-data after g5k-checks import, and remove this line. + supported_job_types: + deploy: true + besteffort: true + max_walltime: 0 + processor: + microarchitecture: Haswell # TODO: replace with microarch name. + clock_speed: 8 # TODO: Replace with clock speed. + network_adapters: + bmc: + interface: Ethernet + enabled: true + mountable: false + mounted: false + eth0: + enabled: true + mountable: true + mounted: true + storage_devices: + disk0: # This field will have to be renamed later. + id: disk0 + interface: SAS + by_path: "/dev/disk/by-path/dummy" # this path will have to change later. + software: + standard-environment: debian11-x64-std # TODO: check that architecture is OK + management_tools: + bmc_vendor_tool: ipmitool # TODO: replace with bmc_vendor_tool (ipmitool, racadm) + nodeset: esterel22 diff --git a/input/grid5000/sites/sophia/clusters/esterel22/esterel22_metrics.yaml b/input/grid5000/sites/sophia/clusters/esterel22/esterel22_metrics.yaml new file mode 100644 index 00000000000..729e9beb582 --- /dev/null +++ b/input/grid5000/sites/sophia/clusters/esterel22/esterel22_metrics.yaml @@ -0,0 +1,40 @@ +--- +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 diff --git a/input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb b/input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb new file mode 100644 index 00000000000..f70df1a0ba2 --- /dev/null +++ b/input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb @@ -0,0 +1,80 @@ +<% + # File generated by 'rake mass:create SRC=doc/sophia-clusters-mass-create-tmp.csv + # If changes are needed, it might be better to edit the source data and regenerate using 'rake mass:create' + + cluster_name = "esterel22" + nodes_number = 1 # Size of the cluster (number of nodes) + # MAC addresses declaration + mac_eth0_list = %w( +34:17:eb:e8:83:84 + ) + mac_bmc_list = %w( +f4:02:70:9d:f4:e8 + ) +%> +--- +nodes: +<% (1..nodes_number).each { |i| %> + <%= cluster_name %>-<%= i %>: + architecture: + nb_procs: 1 # Fake data, will be replaced by g5k-checks + nb_cores: 72 # Fake data, will be replaced by g5k-checks + nb_threads: 72 # Fake data, will be replaced by g5k-checks + platform_type: x86_64 # Fake data, will be replaced by g5k-checks + cpu_core_numbering: contiguous # Fake data, will be replaced by g5k-checks + bios: + release_date: 01/01/2000 # Fake date, will be replaced by g5k-checks + vendor: Unknown # Fake vendor, will be replaced by g5k-checks + version: 1 # Fake version, will be replaced by g5k-checks + bmc_version: v1 # Fake version, will be replaced by g5k-checks + chassis: + manufacturer: Unknown # Fake manufacturer, will be replaced by g5k-checks + name: Unknown # Fake name, will be replaced by g5k-checks + main_memory: + ram_size: 8 # Fake size, will be replaced by g5k-checks + memory_devices: + dimm: + size: 8 # Fake size, will be replaced by g5k-checks + technology: dram # Common memory technology, will be replaced by g5k-checks + processor: + model: Unknown # Fake model name, will be replaced by g5k-checks + other_description: description # Fake description, will be replaced by g5k-checks + vendor: vendor # Fake vendor, will be replaced by g5k-checks + version: vendor # Fake version, will be replaced by g5k-checks + cache_l1d: 8 # Fake cache, will be replaced by g5k-checks + cache_l1i: 8 # Fake cache, will be replaced by g5k-checks + cache_l2: 8 # Fake cache, will be replaced by g5k-checks + cache_l3: 8 # Fake cache, will be replaced by g5k-checks + instruction_set: x86-64 # Common instruction set, will be replaced by g5k-checks + microcode: "0xd000001" # Fake microcode, will be replaced by g5k-checks + ht_capable: true # Default ht capable value, will be replaced by g5k-checks + main_memory: + ram_size: 8 # Fake ram size, will be replaced by g5k-checks + memory_devices: + dimm_proc 1 dimm 1: # Fake dimm name, will be replaced by g5k-checks + size: 8 # Fake dimm size, will be replaced by g5k-checks + technology: dram # Default dimm technology, will be replaced by g5k-checks + operating_system: + cstate_driver: unknown # Fake driver, will be replaced by g5k-checks + cstate_governor: unknown # Fake governor, will be replaced by g5k-checks + ht_enabled: true # common value for hyper threading, will be replaced by g5k-checks + pstate_driver: unknwon # Fake driver, will be replaced by g5k-checks + pstate_governor: unknown # Fake driver, will be replaced by g5k-checks + turboboost_enabled: true # Default value for turboboost, will be replaced by g5k-checks + network_adapters: + bmc: + management: true + mac: <%= mac_bmc_list[i - 1] %> + eth0: + interface: Ethernet + management: false + driver: mlx_core # Fake data, will be replaced by g5k-checks + name: enp1s0f0np0 # Fake data, will be replaced by g5k-checks + rate: 10000000000 # Fake data, will be replaced by g5k-checks + mac: <%= mac_eth0_list[i - 1] %> + storage_devices: + disk0: + storage: SSD # Fake data, will be replaced by g5k-checks + model: unknown # Fake data, will be replaced by g5k-checks + size: 8 # Fake data, will be replaced by g5k-checks +<% } %> -- GitLab From a65ea663ca28032f3ad77a49cb3c0cd0748c5d02 Mon Sep 17 00:00:00 2001 From: Nicolas Perrin <nicolas.perrin@inria.fr> Date: Thu, 20 Mar 2025 14:45:07 +0100 Subject: [PATCH 2/9] [sophia][esterel22] fix ethernet production MAC address --- .../sites/sophia/clusters/esterel22/nodes/esterel22-1.json | 4 ++-- input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json b/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json index 75f810e1ee1..f778691b1be 100644 --- a/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json +++ b/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json @@ -44,7 +44,7 @@ "ip": "172.16.131.28", "ip6": "2001:660:4406:800:4::1c", "kavlan": false, - "mac": "34:17:eb:e8:83:84", + "mac": "f4:02:70:9d:f4:d8", "management": false, "mountable": true, "mounted": true, @@ -99,7 +99,7 @@ "redfish": true, "software": { "forced-deployment-timestamp": 202007300948, - "postinstall-version": "1.2025021810", + "postinstall-version": "1.2025032008", "standard-environment": "debian11-x64-std" }, "storage_devices": [ diff --git a/input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb b/input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb index f70df1a0ba2..08c87e83c8f 100644 --- a/input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb +++ b/input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb @@ -1,12 +1,12 @@ <% - # File generated by 'rake mass:create SRC=doc/sophia-clusters-mass-create-tmp.csv + # File generated by 'rake mass:create SRC=doc/sophia-clusters-mass-create-new-final.csv # If changes are needed, it might be better to edit the source data and regenerate using 'rake mass:create' cluster_name = "esterel22" nodes_number = 1 # Size of the cluster (number of nodes) # MAC addresses declaration mac_eth0_list = %w( -34:17:eb:e8:83:84 +f4:02:70:9d:f4:d8 ) mac_bmc_list = %w( f4:02:70:9d:f4:e8 -- GitLab From 6b87759172c069acfaae88191a189f85c30091c5 Mon Sep 17 00:00:00 2001 From: Hugo Dominois <hugo.dominois@inria.fr> Date: Tue, 8 Apr 2025 09:47:58 +0200 Subject: [PATCH 3/9] [sophia][esterel22] Add network description --- .../sites/sophia/clusters/esterel22/nodes/esterel22-1.json | 4 ++-- data/grid5000/sites/sophia/network_equipments/sw-2.json | 4 ++++ data/grid5000/sites/sophia/network_equipments/swadmin-2.json | 3 +++ input/grid5000/sites/sophia/networks/sw-2.yaml | 2 ++ input/grid5000/sites/sophia/networks/swadmin-2.yaml | 3 +++ 5 files changed, 14 insertions(+), 2 deletions(-) diff --git a/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json b/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json index f778691b1be..1c8f6244551 100644 --- a/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json +++ b/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json @@ -51,8 +51,8 @@ "name": "enp1s0f0np0", "network_address": "esterel22-1.sophia.grid5000.fr", "rate": 10000000000, - "switch": null, - "switch_port": null + "switch": "sw-2", + "switch_port": "1/1/32" }, { "device": "bmc", diff --git a/data/grid5000/sites/sophia/network_equipments/sw-2.json b/data/grid5000/sites/sophia/network_equipments/sw-2.json index 463d63f8c53..b2c6c7b666a 100644 --- a/data/grid5000/sites/sophia/network_equipments/sw-2.json +++ b/data/grid5000/sites/sophia/network_equipments/sw-2.json @@ -111,6 +111,10 @@ { }, { + "kind": "node", + "port": "eth0", + "snmp_name": "1/1/32", + "uid": "esterel22-1" }, { "kind": "node", diff --git a/data/grid5000/sites/sophia/network_equipments/swadmin-2.json b/data/grid5000/sites/sophia/network_equipments/swadmin-2.json index 99360916c89..e318bbd9b47 100644 --- a/data/grid5000/sites/sophia/network_equipments/swadmin-2.json +++ b/data/grid5000/sites/sophia/network_equipments/swadmin-2.json @@ -71,6 +71,9 @@ "uid": "esterel32-1-bmc" }, { + "kind": "other", + "snmp_name": "1/1/13", + "uid": "esterel22-1-bmc" }, { }, diff --git a/input/grid5000/sites/sophia/networks/sw-2.yaml b/input/grid5000/sites/sophia/networks/sw-2.yaml index baf2898fccc..cb4d63f1f17 100644 --- a/input/grid5000/sites/sophia/networks/sw-2.yaml +++ b/input/grid5000/sites/sophia/networks/sw-2.yaml @@ -48,6 +48,8 @@ sw-2: uid: esterel26-1 18: uid: esterel32-1 + 32: + uid: esterel22-1 33: uid: esterel10-2 port: eth1 diff --git a/input/grid5000/sites/sophia/networks/swadmin-2.yaml b/input/grid5000/sites/sophia/networks/swadmin-2.yaml index 5bc03730674..52ed2520a98 100644 --- a/input/grid5000/sites/sophia/networks/swadmin-2.yaml +++ b/input/grid5000/sites/sophia/networks/swadmin-2.yaml @@ -50,6 +50,9 @@ swadmin-2: 12: uid: esterel32-1-bmc kind: other + 13: + uid: esterel22-1-bmc + kind: other 25: uid: sw-2 kind: switch -- GitLab From 43f13395014a69b730a477febc171996233ecdbd Mon Sep 17 00:00:00 2001 From: Hugo Dominois <hugo.dominois@inria.fr> Date: Tue, 8 Apr 2025 10:57:46 +0200 Subject: [PATCH 4/9] [sophia][esterel22] Add by-path configuration --- .../sites/sophia/clusters/esterel22/esterel22.json | 2 +- .../sophia/clusters/esterel22/nodes/esterel22-1.json | 12 +++++++++++- .../sites/sophia/clusters/esterel22/esterel22.yaml | 4 ++++ .../sites/sophia/clusters/esterel22/nodes.yaml.erb | 6 ++++++ 4 files changed, 22 insertions(+), 2 deletions(-) diff --git a/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json b/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json index 925071e50e4..71411b81815 100644 --- a/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json +++ b/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json @@ -53,7 +53,7 @@ ], "model": "Cluster Model", "nodes_count": 1, - "nodes_description": "1 CPU Unknown vendor, 72 cores/CPU, 0GB RAM, 0GB SSD, 1 x 10Gb Ethernet", + "nodes_description": "1 CPU Unknown vendor, 72 cores/CPU, 0GB RAM, 2x0GB SSD, 1 x 10Gb Ethernet", "priority": 197001, "queues": [ "admin", diff --git a/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json b/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json index 1c8f6244551..5ae485c3408 100644 --- a/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json +++ b/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json @@ -105,13 +105,23 @@ "storage_devices": [ { "by_id": "", - "by_path": "/dev/disk/by-path/dummy", + "by_path": "/dev/disk/by-path/pci-0000:19:00.0-scsi-0:2:0:0", "id": "disk0", "interface": "SAS", "model": "unknown", "size": 8, "storage": "SSD", "vendor": "Unknown" + }, + { + "by_id": "", + "by_path": "/dev/disk/by-path/pci-0000:19:00.0-scsi-0:2:1:0", + "id": "disk1", + "interface": "SAS", + "model": "unknown", + "size": 8, + "storage": "SSD", + "vendor": "Unknown" } ], "supported_job_types": { diff --git a/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml b/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml index fd0ec344fb0..69cab4048fd 100644 --- a/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml +++ b/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml @@ -34,6 +34,10 @@ nodes: id: disk0 interface: SAS by_path: "/dev/disk/by-path/dummy" # this path will have to change later. + disk1: + id: disk1 + interface: SAS + by_path: "/dev/disk/by-path/dummy" software: standard-environment: debian11-x64-std # TODO: check that architecture is OK management_tools: diff --git a/input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb b/input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb index 08c87e83c8f..c40c912294f 100644 --- a/input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb +++ b/input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb @@ -77,4 +77,10 @@ nodes: storage: SSD # Fake data, will be replaced by g5k-checks model: unknown # Fake data, will be replaced by g5k-checks size: 8 # Fake data, will be replaced by g5k-checks + by_path: "/dev/disk/by-path/pci-0000:19:00.0-scsi-0:2:0:0" + disk1: + storage: SSD + model: unknown + size: 8 + by_path: "/dev/disk/by-path/pci-0000:19:00.0-scsi-0:2:1:0" <% } %> -- GitLab From 97e6a5f2e270bf294f2cba03402725373b9549e6 Mon Sep 17 00:00:00 2001 From: Hugo Dominois <hugo.dominois@inria.fr> Date: Wed, 9 Apr 2025 09:17:55 +0200 Subject: [PATCH 5/9] [sophia][esterel22] Change the disk by-path for valid:duplicates --- input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml | 4 ++-- input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb | 2 -- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml b/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml index 69cab4048fd..253bc917772 100644 --- a/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml +++ b/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml @@ -33,11 +33,11 @@ nodes: disk0: # This field will have to be renamed later. id: disk0 interface: SAS - by_path: "/dev/disk/by-path/dummy" # this path will have to change later. + by_path: "/dev/disk/by-path/pci-0000:19:00.0-scsi-0:2:0:0" # this path will have to change later. disk1: id: disk1 interface: SAS - by_path: "/dev/disk/by-path/dummy" + by_path: "/dev/disk/by-path/pci-0000:19:00.0-scsi-0:2:1:0" software: standard-environment: debian11-x64-std # TODO: check that architecture is OK management_tools: diff --git a/input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb b/input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb index c40c912294f..69b873848de 100644 --- a/input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb +++ b/input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb @@ -77,10 +77,8 @@ nodes: storage: SSD # Fake data, will be replaced by g5k-checks model: unknown # Fake data, will be replaced by g5k-checks size: 8 # Fake data, will be replaced by g5k-checks - by_path: "/dev/disk/by-path/pci-0000:19:00.0-scsi-0:2:0:0" disk1: storage: SSD model: unknown size: 8 - by_path: "/dev/disk/by-path/pci-0000:19:00.0-scsi-0:2:1:0" <% } %> -- GitLab From bc539c1ab92d2761da55fb40fbf2b8aa2b5448ce Mon Sep 17 00:00:00 2001 From: Hugo Dominois <hugo.dominois@inria.fr> Date: Wed, 9 Apr 2025 10:34:45 +0200 Subject: [PATCH 6/9] [sophia][esterel22] First g5k-checks-imports --- .../sophia/clusters/esterel22/esterel22.json | 8 +- .../clusters/esterel22/nodes/esterel22-1.json | 261 +++++++++++++++--- input/grid5000/dell-product-data.yaml | 12 +- input/grid5000/ipv4.yaml | 1 + .../sophia/clusters/esterel22/esterel22.yaml | 31 ++- .../sophia/clusters/esterel22/nodes.yaml.erb | 84 ------ .../clusters/esterel22/nodes/esterel22-1.yaml | 168 +++++++++++ lib/refrepo/net_names_mapping.yaml | 4 + 8 files changed, 419 insertions(+), 150 deletions(-) delete mode 100644 input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb create mode 100644 input/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.yaml diff --git a/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json b/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json index 71411b81815..33a37da92c8 100644 --- a/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json +++ b/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json @@ -1,6 +1,6 @@ { "boot_type": "uefi", - "created_at": "Thu, 01 Jan 1970 00:00:00 GMT", + "created_at": "Wed, 09 Apr 2025 00:00:00 GMT", "exotic": false, "kavlan": false, "manufactured_at": "1970-01-01", @@ -51,10 +51,10 @@ } } ], - "model": "Cluster Model", + "model": "Dell PowerEdge T640", "nodes_count": 1, - "nodes_description": "1 CPU Unknown vendor, 72 cores/CPU, 0GB RAM, 2x0GB SSD, 1 x 10Gb Ethernet", - "priority": 197001, + "nodes_description": "2 CPUs Intel Xeon Gold 6240, 18 cores/CPU, 4 GPUs Quadro RTX 6000, 384GB RAM, 558GB HDD, 3575GB HDD, 1 x 1Gb Ethernet, 1 x 40Gb InfiniBand", + "priority": 197101, "queues": [ "admin", "testing" diff --git a/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json b/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json index 5ae485c3408..67d709fdba7 100644 --- a/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json +++ b/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json @@ -1,58 +1,228 @@ { "architecture": { - "cpu_core_numbering": "contiguous", - "nb_cores": 72, - "nb_procs": 1, + "cpu_core_numbering": "round-robin", + "nb_cores": 36, + "nb_procs": 2, "nb_threads": 72, "platform_type": "x86_64" }, "bios": { - "release_date": "01/01/2000", - "vendor": "Unknown", - "version": 1 + "release_date": "01/09/2025", + "vendor": "Dell Inc.", + "version": "2.23.0" }, - "bmc_version": "v1", + "bmc_version": "7.00", "chassis": { "manufactured_at": "1970-01-01", - "manufacturer": "Unknown", - "name": "Unknown", + "manufacturer": "Dell Inc.", + "name": "PowerEdge T640", + "serial": "1D58RZ2", "warranty_end": "1970-01-01" }, "exotic": false, + "gpu_devices": { + "nvidia0": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 0, + "device": "/dev/nvidia0", + "memory": 24159191040, + "microarchitecture": "Turing", + "model": "Quadro RTX 6000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "260.00 W", + "vbios_version": "90.02.15.00.04", + "vendor": "Nvidia" + }, + "nvidia1": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 0, + "device": "/dev/nvidia1", + "memory": 24159191040, + "microarchitecture": "Turing", + "model": "Quadro RTX 6000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "260.00 W", + "vbios_version": "90.02.15.00.04", + "vendor": "Nvidia" + }, + "nvidia2": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 1, + "device": "/dev/nvidia2", + "memory": 24159191040, + "microarchitecture": "Turing", + "model": "Quadro RTX 6000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "260.00 W", + "vbios_version": "90.02.15.00.04", + "vendor": "Nvidia" + }, + "nvidia3": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 1, + "device": "/dev/nvidia3", + "memory": 24159191040, + "microarchitecture": "Turing", + "model": "Quadro RTX 6000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "260.00 W", + "vbios_version": "90.02.15.00.04", + "vendor": "Nvidia" + } + }, "main_memory": { - "ram_size": 8 + "ram_size": 412316860416 }, "management_tools": { - "bmc_vendor_tool": "ipmitool", + "bmc_vendor_tool": "racadm", "ipmitool": { "retries": 5 } }, "memory_devices": [ { - "device": "dimm_proc 1 dimm 1", - "size": 8, + "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": "mlx_core", + "driver": "bnxt_en", "enabled": true, + "firmware_version": "232.0.156.9/pkg 23.21.13.39", "interface": "Ethernet", "ip": "172.16.131.28", "ip6": "2001:660:4406:800:4::1c", "kavlan": false, "mac": "f4:02:70:9d:f4:d8", "management": false, + "model": "BCM57416 NetXtreme-E Dual-Media 10G RDMA Ethernet Controller", "mountable": true, "mounted": true, "name": "enp1s0f0np0", "network_address": "esterel22-1.sophia.grid5000.fr", - "rate": 10000000000, + "rate": 1000000000, + "sriov": false, + "sriov_totalvfs": 0, "switch": "sw-2", - "switch_port": "1/1/32" + "switch_port": "1/1/32", + "vendor": "Broadcom Inc. and subsidiaries" + }, + { + "device": "eth1", + "driver": "bnxt_en", + "enabled": false, + "firmware_version": "232.0.156.9/pkg 23.21.13.39", + "interface": "Ethernet", + "kavlan": false, + "mac": "f4:02:70:9d:f4:d9", + "management": false, + "model": "BCM57416 NetXtreme-E Dual-Media 10G RDMA Ethernet Controller", + "mountable": false, + "mounted": false, + "name": "eno2np1", + "sriov": false, + "sriov_totalvfs": 0, + "vendor": "Broadcom Inc. and subsidiaries" + }, + { + "device": "ib0", + "driver": "mlx4_core", + "enabled": true, + "firmware_version": "2.42.5000", + "guid": "0xb8599f0300a0d111", + "interface": "InfiniBand", + "ip": "172.18.131.28", + "kavlan": false, + "mac": "b8:59:9f:03:00:a0:d1:11", + "management": false, + "model": "MT27500 Family [ConnectX-3]", + "mountable": true, + "mounted": true, + "name": "ibp137s0", + "netmask": "255.255.240.0", + "network_address": "esterel22-1-ib0.sophia.grid5000.fr", + "rate": 40000000000, + "sriov": false, + "sriov_totalvfs": 0, + "vendor": "Mellanox Technologies" }, { "device": "bmc", @@ -69,32 +239,32 @@ ], "nodeset": "esterel22", "operating_system": { - "cstate_driver": "unknown", - "cstate_governor": "unknown", + "cstate_driver": "intel_idle", + "cstate_governor": "menu", "ht_enabled": true, - "pstate_driver": "unknwon", - "pstate_governor": "unknown", + "pstate_driver": "intel_pstate", + "pstate_governor": "performance", "turboboost_enabled": true }, "performance": { - "core_flops": 128, - "node_flops": 9216 + "core_flops": 83200000000, + "node_flops": 2995200000000 }, "processor": { "cache_l1": null, - "cache_l1d": 8, - "cache_l1i": 8, - "cache_l2": 8, - "cache_l3": 8, - "clock_speed": 8, + "cache_l1d": 32768, + "cache_l1i": 32768, + "cache_l2": 1048576, + "cache_l3": 25952256, + "clock_speed": 2600000000, "ht_capable": true, "instruction_set": "x86-64", - "microarchitecture": "Haswell", - "microcode": "0xd000001", - "model": "Unknown", - "other_description": "description", - "vendor": "vendor", - "version": "vendor" + "microarchitecture": "Cascade Lake-SP", + "microcode": "0x5003801", + "model": "Intel Xeon", + "other_description": "Intel(R) Xeon(R) Gold 6240 CPU @ 2.60GHz", + "vendor": "Intel", + "version": "Gold 6240" }, "redfish": true, "software": { @@ -104,24 +274,26 @@ }, "storage_devices": [ { - "by_id": "", + "by_id": "/dev/disk/by-id/wwn-0x64cd98f094f41d002566cb7511b3990e", "by_path": "/dev/disk/by-path/pci-0000:19:00.0-scsi-0:2:0:0", + "firmware_version": 4.3, "id": "disk0", "interface": "SAS", - "model": "unknown", - "size": 8, - "storage": "SSD", - "vendor": "Unknown" + "model": "PERC H730P Adp", + "size": 599550590976, + "storage": "HDD", + "vendor": "Dell" }, { - "by_id": "", + "by_id": "/dev/disk/by-id/wwn-0x64cd98f094f41d002566d27306fac4a7", "by_path": "/dev/disk/by-path/pci-0000:19:00.0-scsi-0:2:1:0", + "firmware_version": 4.3, "id": "disk1", "interface": "SAS", - "model": "unknown", - "size": 8, - "storage": "SSD", - "vendor": "Unknown" + "model": "PERC H730P Adp", + "size": 3838627020800, + "storage": "HDD", + "vendor": "Dell" } ], "supported_job_types": { @@ -131,7 +303,8 @@ "queues": [ "admin", "testing" - ] + ], + "virtual": "ivt" }, "type": "node", "uid": "esterel22-1" diff --git a/input/grid5000/dell-product-data.yaml b/input/grid5000/dell-product-data.yaml index 234b29ea306..6b9a796987b 100644 --- a/input/grid5000/dell-product-data.yaml +++ b/input/grid5000/dell-product-data.yaml @@ -2296,18 +2296,18 @@ sites: chassis: manufactured_at: 2016-06-06 warranty_end: 2021-06-06 - esterel4: - nodes: - esterel4-1: - chassis: - manufactured_at: 2016-06-08 - warranty_end: 2021-06-08 esterel32: nodes: esterel32-1: chassis: manufactured_at: 2020-08-09 warranty_end: 2027-08-10 + esterel4: + nodes: + esterel4-1: + chassis: + manufactured_at: 2016-06-08 + warranty_end: 2021-06-08 esterel5: nodes: esterel5-1: diff --git a/input/grid5000/ipv4.yaml b/input/grid5000/ipv4.yaml index f132573b973..a28d0cf9e02 100644 --- a/input/grid5000/ipv4.yaml +++ b/input/grid5000/ipv4.yaml @@ -188,6 +188,7 @@ ipv4: sophia esterel20 eth0 0 0 3 24 sophia esterel21 eth0 0 0 3 26 sophia esterel22 eth0 0 0 3 27 + sophia esterel22 ib0 0 0 3 27 sophia esterel23 eth0 0 0 3 28 sophia esterel24 eth0 0 0 3 30 sophia esterel24 ib0 0 0 3 30 diff --git a/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml b/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml index 253bc917772..4dc9908f48b 100644 --- a/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml +++ b/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml @@ -1,9 +1,9 @@ --- -model: Cluster Model # TODO: change this value. -created_at: 1970-01-01 # TODO: change this value +model: Dell PowerEdge T640 +created_at: 2025-04-09 kavlan: false -boot_type: uefi # TODO: specify if 'uefi' (ideally) or 'bios' (legacy, if no other choice) -exotic: false # TODO: specify if 'true' or 'false' +boot_type: uefi +exotic: false queues: - admin - testing @@ -17,8 +17,8 @@ nodes: besteffort: true max_walltime: 0 processor: - microarchitecture: Haswell # TODO: replace with microarch name. - clock_speed: 8 # TODO: Replace with clock speed. + microarchitecture: Cascade Lake-SP + clock_speed: 2600000000 network_adapters: bmc: interface: Ethernet @@ -29,17 +29,24 @@ nodes: 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: - disk0: # This field will have to be renamed later. + pci-0000:19:00.0-scsi-0:2:0:0: id: disk0 interface: SAS - by_path: "/dev/disk/by-path/pci-0000:19:00.0-scsi-0:2:0:0" # this path will have to change later. - disk1: + pci-0000:19:00.0-scsi-0:2:1:0: id: disk1 interface: SAS - by_path: "/dev/disk/by-path/pci-0000:19:00.0-scsi-0:2:1:0" software: - standard-environment: debian11-x64-std # TODO: check that architecture is OK + standard-environment: debian11-x64-std management_tools: - bmc_vendor_tool: ipmitool # TODO: replace with bmc_vendor_tool (ipmitool, racadm) + bmc_vendor_tool: racadm nodeset: esterel22 diff --git a/input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb b/input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb deleted file mode 100644 index 69b873848de..00000000000 --- a/input/grid5000/sites/sophia/clusters/esterel22/nodes.yaml.erb +++ /dev/null @@ -1,84 +0,0 @@ -<% - # File generated by 'rake mass:create SRC=doc/sophia-clusters-mass-create-new-final.csv - # If changes are needed, it might be better to edit the source data and regenerate using 'rake mass:create' - - cluster_name = "esterel22" - nodes_number = 1 # Size of the cluster (number of nodes) - # MAC addresses declaration - mac_eth0_list = %w( -f4:02:70:9d:f4:d8 - ) - mac_bmc_list = %w( -f4:02:70:9d:f4:e8 - ) -%> ---- -nodes: -<% (1..nodes_number).each { |i| %> - <%= cluster_name %>-<%= i %>: - architecture: - nb_procs: 1 # Fake data, will be replaced by g5k-checks - nb_cores: 72 # Fake data, will be replaced by g5k-checks - nb_threads: 72 # Fake data, will be replaced by g5k-checks - platform_type: x86_64 # Fake data, will be replaced by g5k-checks - cpu_core_numbering: contiguous # Fake data, will be replaced by g5k-checks - bios: - release_date: 01/01/2000 # Fake date, will be replaced by g5k-checks - vendor: Unknown # Fake vendor, will be replaced by g5k-checks - version: 1 # Fake version, will be replaced by g5k-checks - bmc_version: v1 # Fake version, will be replaced by g5k-checks - chassis: - manufacturer: Unknown # Fake manufacturer, will be replaced by g5k-checks - name: Unknown # Fake name, will be replaced by g5k-checks - main_memory: - ram_size: 8 # Fake size, will be replaced by g5k-checks - memory_devices: - dimm: - size: 8 # Fake size, will be replaced by g5k-checks - technology: dram # Common memory technology, will be replaced by g5k-checks - processor: - model: Unknown # Fake model name, will be replaced by g5k-checks - other_description: description # Fake description, will be replaced by g5k-checks - vendor: vendor # Fake vendor, will be replaced by g5k-checks - version: vendor # Fake version, will be replaced by g5k-checks - cache_l1d: 8 # Fake cache, will be replaced by g5k-checks - cache_l1i: 8 # Fake cache, will be replaced by g5k-checks - cache_l2: 8 # Fake cache, will be replaced by g5k-checks - cache_l3: 8 # Fake cache, will be replaced by g5k-checks - instruction_set: x86-64 # Common instruction set, will be replaced by g5k-checks - microcode: "0xd000001" # Fake microcode, will be replaced by g5k-checks - ht_capable: true # Default ht capable value, will be replaced by g5k-checks - main_memory: - ram_size: 8 # Fake ram size, will be replaced by g5k-checks - memory_devices: - dimm_proc 1 dimm 1: # Fake dimm name, will be replaced by g5k-checks - size: 8 # Fake dimm size, will be replaced by g5k-checks - technology: dram # Default dimm technology, will be replaced by g5k-checks - operating_system: - cstate_driver: unknown # Fake driver, will be replaced by g5k-checks - cstate_governor: unknown # Fake governor, will be replaced by g5k-checks - ht_enabled: true # common value for hyper threading, will be replaced by g5k-checks - pstate_driver: unknwon # Fake driver, will be replaced by g5k-checks - pstate_governor: unknown # Fake driver, will be replaced by g5k-checks - turboboost_enabled: true # Default value for turboboost, will be replaced by g5k-checks - network_adapters: - bmc: - management: true - mac: <%= mac_bmc_list[i - 1] %> - eth0: - interface: Ethernet - management: false - driver: mlx_core # Fake data, will be replaced by g5k-checks - name: enp1s0f0np0 # Fake data, will be replaced by g5k-checks - rate: 10000000000 # Fake data, will be replaced by g5k-checks - mac: <%= mac_eth0_list[i - 1] %> - storage_devices: - disk0: - storage: SSD # Fake data, will be replaced by g5k-checks - model: unknown # Fake data, will be replaced by g5k-checks - size: 8 # Fake data, will be replaced by g5k-checks - disk1: - storage: SSD - model: unknown - size: 8 -<% } %> diff --git a/input/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.yaml b/input/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.yaml new file mode 100644 index 00000000000..8c5f57de423 --- /dev/null +++ b/input/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.yaml @@ -0,0 +1,168 @@ +# Generated by g5k-checks (g5k-checks -m api) +--- +esterel22-1: + architecture: + cpu_core_numbering: round-robin + nb_cores: 36 + nb_procs: 2 + nb_threads: 72 + platform_type: x86_64 + bios: + release_date: 01/09/2025 + vendor: Dell Inc. + version: 2.23.0 + bmc_version: '7.00' + chassis: + manufacturer: Dell Inc. + name: PowerEdge T640 + serial: 1D58RZ2 + gpu_devices: + nvidia0: + cpu_affinity: 0 + device: "/dev/nvidia0" + memory: 24159191040 + model: Quadro RTX 6000 + power_default_limit: 260.00 W + vbios_version: 90.02.15.00.04 + vendor: Nvidia + nvidia1: + cpu_affinity: 0 + device: "/dev/nvidia1" + memory: 24159191040 + model: Quadro RTX 6000 + power_default_limit: 260.00 W + vbios_version: 90.02.15.00.04 + vendor: Nvidia + nvidia2: + cpu_affinity: 1 + device: "/dev/nvidia2" + memory: 24159191040 + model: Quadro RTX 6000 + power_default_limit: 260.00 W + vbios_version: 90.02.15.00.04 + vendor: Nvidia + nvidia3: + cpu_affinity: 1 + device: "/dev/nvidia3" + memory: 24159191040 + model: Quadro RTX 6000 + power_default_limit: 260.00 W + vbios_version: 90.02.15.00.04 + 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: 172.17.131.28 + mac: f4:02:70:9d:f4:e8 + management: true + eth0: + driver: bnxt_en + firmware_version: 232.0.156.9/pkg 23.21.13.39 + interface: Ethernet + ip: 172.16.131.28 + mac: f4:02:70:9d:f4:d8 + management: false + model: BCM57416 NetXtreme-E Dual-Media 10G RDMA Ethernet Controller + name: enp1s0f0np0 + rate: 1000000000 + sriov: false + sriov_totalvfs: 0 + vendor: Broadcom Inc. and subsidiaries + eth1: + driver: bnxt_en + firmware_version: 232.0.156.9/pkg 23.21.13.39 + interface: Ethernet + mac: f4:02:70:9d:f4:d9 + management: false + model: BCM57416 NetXtreme-E Dual-Media 10G RDMA Ethernet Controller + name: eno2np1 + sriov: false + sriov_totalvfs: 0 + vendor: Broadcom Inc. and subsidiaries + ib0: + driver: mlx4_core + firmware_version: 2.42.5000 + guid: '0xb8599f0300a0d111' + interface: InfiniBand + mac: b8:59:9f:03:00:a0:d1:11 + management: false + model: MT27500 Family [ConnectX-3] + name: ibp137s0 + 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_pstate + pstate_governor: performance + turboboost_enabled: true + processor: + cache_l1d: 32768 + cache_l1i: 32768 + cache_l2: 1048576 + cache_l3: 25952256 + ht_capable: true + instruction_set: x86-64 + microcode: '0x5003801' + model: Intel Xeon + other_description: Intel(R) Xeon(R) Gold 6240 CPU @ 2.60GHz + vendor: Intel + version: Gold 6240 + storage_devices: + pci-0000:19:00.0-scsi-0:2:0:0: + by_id: "/dev/disk/by-id/wwn-0x64cd98f094f41d002566cb7511b3990e" + by_path: "/dev/disk/by-path/pci-0000:19:00.0-scsi-0:2:0:0" + firmware_version: 4.3 + model: PERC H730P Adp + size: 599550590976 + storage: HDD + pci-0000:19:00.0-scsi-0:2:1:0: + by_id: "/dev/disk/by-id/wwn-0x64cd98f094f41d002566d27306fac4a7" + by_path: "/dev/disk/by-path/pci-0000:19:00.0-scsi-0:2:1:0" + firmware_version: 4.3 + model: PERC H730P Adp + size: 3838627020800 + storage: HDD + supported_job_types: + virtual: ivt diff --git a/lib/refrepo/net_names_mapping.yaml b/lib/refrepo/net_names_mapping.yaml index b8fd058e387..53a83a26985 100644 --- a/lib/refrepo/net_names_mapping.yaml +++ b/lib/refrepo/net_names_mapping.yaml @@ -447,6 +447,10 @@ esterel12: eno1: eth0 eno2: eth1 ibp130s0: ib0 +esterel22: + enp1s0f0np0: eth0 + eno2np1: eth1 + ibp137s0: ib0 esterel24: enp1s0f0np0: eth0 eno2np1: eth1 -- GitLab From 5e3d7c51f9619f54bf6bae573ea43f6459cf2519 Mon Sep 17 00:00:00 2001 From: Hugo Dominois <hugo.dominois@inria.fr> Date: Wed, 9 Apr 2025 10:49:30 +0200 Subject: [PATCH 7/9] [sophia][esterel22] Second g5k-checks-import and Dell warranty --- .../sites/sophia/clusters/esterel22/esterel22.json | 6 +++--- .../sophia/clusters/esterel22/nodes/esterel22-1.json | 10 ++++------ input/grid5000/dell-product-data.yaml | 6 ++++++ .../sites/sophia/clusters/esterel22/esterel22.yaml | 3 --- .../sophia/clusters/esterel22/nodes/esterel22-1.yaml | 7 +++---- 5 files changed, 16 insertions(+), 16 deletions(-) diff --git a/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json b/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json index 33a37da92c8..33f9b78a809 100644 --- a/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json +++ b/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json @@ -3,7 +3,7 @@ "created_at": "Wed, 09 Apr 2025 00:00:00 GMT", "exotic": false, "kavlan": false, - "manufactured_at": "1970-01-01", + "manufactured_at": "2019-10-07", "metrics": [ { "description": "Default subset of metrics from Prometheus Node Exporter", @@ -54,7 +54,7 @@ "model": "Dell PowerEdge T640", "nodes_count": 1, "nodes_description": "2 CPUs Intel Xeon Gold 6240, 18 cores/CPU, 4 GPUs Quadro RTX 6000, 384GB RAM, 558GB HDD, 3575GB HDD, 1 x 1Gb Ethernet, 1 x 40Gb InfiniBand", - "priority": 197101, + "priority": 202010, "queues": [ "admin", "testing" @@ -62,5 +62,5 @@ "redfish": true, "type": "cluster", "uid": "esterel22", - "warranty_end": "1970-01-01" + "warranty_end": "2026-10-08" } \ No newline at end of file diff --git a/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json b/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json index 67d709fdba7..d885741be05 100644 --- a/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json +++ b/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json @@ -11,13 +11,13 @@ "vendor": "Dell Inc.", "version": "2.23.0" }, - "bmc_version": "7.00", + "bmc_version": "7.00.00.181", "chassis": { - "manufactured_at": "1970-01-01", + "manufactured_at": "2019-10-07", "manufacturer": "Dell Inc.", "name": "PowerEdge T640", "serial": "1D58RZ2", - "warranty_end": "1970-01-01" + "warranty_end": "2026-10-08" }, "exotic": false, "gpu_devices": { @@ -216,12 +216,10 @@ "model": "MT27500 Family [ConnectX-3]", "mountable": true, "mounted": true, - "name": "ibp137s0", + "name": "ib0", "netmask": "255.255.240.0", "network_address": "esterel22-1-ib0.sophia.grid5000.fr", "rate": 40000000000, - "sriov": false, - "sriov_totalvfs": 0, "vendor": "Mellanox Technologies" }, { diff --git a/input/grid5000/dell-product-data.yaml b/input/grid5000/dell-product-data.yaml index 6b9a796987b..83c2e2e57c1 100644 --- a/input/grid5000/dell-product-data.yaml +++ b/input/grid5000/dell-product-data.yaml @@ -2278,6 +2278,12 @@ sites: chassis: manufactured_at: 2016-05-04 warranty_end: 2021-05-04 + esterel22: + nodes: + esterel22-1: + chassis: + manufactured_at: 2019-10-07 + warranty_end: 2026-10-08 esterel24: nodes: esterel24-1: diff --git a/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml b/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml index 4dc9908f48b..991cb6b5858 100644 --- a/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml +++ b/input/grid5000/sites/sophia/clusters/esterel22/esterel22.yaml @@ -9,9 +9,6 @@ queues: - testing nodes: esterel22-1: - chassis: - manufactured_at: 1970-01-01 # TODO: if not Dell vendor, put date. if Dell, use rake gen:dell-product-data after g5k-checks import, and remove this line. - warranty_end: 1970-01-01 # TODO: if not Dell vendor, put date. if Dell, use rake gen:dell-product-data after g5k-checks import, and remove this line. supported_job_types: deploy: true besteffort: true diff --git a/input/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.yaml b/input/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.yaml index 8c5f57de423..28471e05571 100644 --- a/input/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.yaml +++ b/input/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.yaml @@ -11,7 +11,7 @@ esterel22-1: release_date: 01/09/2025 vendor: Dell Inc. version: 2.23.0 - bmc_version: '7.00' + bmc_version: 7.00.00.181 chassis: manufacturer: Dell Inc. name: PowerEdge T640 @@ -122,13 +122,12 @@ esterel22-1: firmware_version: 2.42.5000 guid: '0xb8599f0300a0d111' interface: InfiniBand + ip: 172.18.131.28 mac: b8:59:9f:03:00:a0:d1:11 management: false model: MT27500 Family [ConnectX-3] - name: ibp137s0 + name: ib0 rate: 40000000000 - sriov: false - sriov_totalvfs: 0 vendor: Mellanox Technologies operating_system: cstate_driver: intel_idle -- GitLab From 4988728266f9a3583ea84435f573be641fdba742 Mon Sep 17 00:00:00 2001 From: Hugo Dominois <hugo.dominois@inria.fr> Date: Wed, 9 Apr 2025 11:19:17 +0200 Subject: [PATCH 8/9] [sophia][esterel22] Add GPU metrics --- .../sites/sophia/clusters/esterel22/esterel22.json | 10 ++++++++++ .../sophia/clusters/esterel22/esterel22_metrics.yaml | 7 +++++++ 2 files changed, 17 insertions(+) diff --git a/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json b/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json index 33f9b78a809..af32d53411c 100644 --- a/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json +++ b/data/grid5000/sites/sophia/clusters/esterel22/esterel22.json @@ -49,6 +49,16 @@ "port": 9100, "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 T640", diff --git a/input/grid5000/sites/sophia/clusters/esterel22/esterel22_metrics.yaml b/input/grid5000/sites/sophia/clusters/esterel22/esterel22_metrics.yaml index 729e9beb582..5fafdb330db 100644 --- a/input/grid5000/sites/sophia/clusters/esterel22/esterel22_metrics.yaml +++ b/input/grid5000/sites/sophia/clusters/esterel22/esterel22_metrics.yaml @@ -38,3 +38,10 @@ metrics: source: protocol: prometheus port: 9100 + - name: prom_nvgpu_all_metrics + description: All metrics from Prometheus Nvidia DCGM Exporter + period: 0 + optional_period: 15000 + source: + protocol: prometheus + port: 9400 -- GitLab From 6e0f25280bb04661c38d00c7eba39408dc92c325 Mon Sep 17 00:00:00 2001 From: Hugo Dominois <hugo.dominois@inria.fr> Date: Tue, 15 Apr 2025 09:47:50 +0200 Subject: [PATCH 9/9] [sophia][esterel22] Update postinstall --- .../sites/sophia/clusters/esterel22/nodes/esterel22-1.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json b/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json index d885741be05..33a09c0cc57 100644 --- a/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json +++ b/data/grid5000/sites/sophia/clusters/esterel22/nodes/esterel22-1.json @@ -267,7 +267,7 @@ "redfish": true, "software": { "forced-deployment-timestamp": 202007300948, - "postinstall-version": "1.2025032008", + "postinstall-version": "1.2025040409", "standard-environment": "debian11-x64-std" }, "storage_devices": [ -- GitLab