From 41794da8d785c6cc3af33f2f8084d250ec24e3b8 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 1/8] [sophia][esterel24] add basic configuration generated by
rake mass:create
---
.../sophia/clusters/esterel24/esterel24.json | 66 +++++++++
.../clusters/esterel24/nodes/esterel24-1.json | 128 ++++++++++++++++++
.../clusters/esterel24/nodes/esterel24-2.json | 128 ++++++++++++++++++
.../sophia/clusters/esterel24/esterel24.yaml | 41 ++++++
.../clusters/esterel24/esterel24_metrics.yaml | 40 ++++++
.../sophia/clusters/esterel24/nodes.yaml.erb | 82 +++++++++++
6 files changed, 485 insertions(+)
create mode 100644 data/grid5000/sites/sophia/clusters/esterel24/esterel24.json
create mode 100644 data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
create mode 100644 data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-2.json
create mode 100644 input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml
create mode 100644 input/grid5000/sites/sophia/clusters/esterel24/esterel24_metrics.yaml
create mode 100644 input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb
diff --git a/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json b/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json
new file mode 100644
index 00000000000..0bf2ac9216c
--- /dev/null
+++ b/data/grid5000/sites/sophia/clusters/esterel24/esterel24.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": 2,
+ "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": "esterel24",
+ "warranty_end": "1970-01-01"
+}
\ No newline at end of file
diff --git a/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
new file mode 100644
index 00000000000..98409fe662d
--- /dev/null
+++ b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.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": "172.16.131.30",
+ "ip6": "2001:660:4406:800:4::1e",
+ "kavlan": false,
+ "mac": "34:17:eb:e8:82:bb",
+ "management": false,
+ "mountable": true,
+ "mounted": true,
+ "name": "enp1s0f0np0",
+ "network_address": "esterel24-1.sophia.grid5000.fr",
+ "rate": 10000000000,
+ "switch": null,
+ "switch_port": null
+ },
+ {
+ "device": "bmc",
+ "enabled": true,
+ "interface": "Ethernet",
+ "ip": "172.17.131.30",
+ "kavlan": false,
+ "mac": "f4:02:70:9d:75:a2",
+ "management": true,
+ "mountable": false,
+ "mounted": false,
+ "network_address": "esterel24-1-bmc.sophia.grid5000.fr"
+ }
+ ],
+ "nodeset": "esterel24",
+ "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": "esterel24-1"
+}
\ No newline at end of file
diff --git a/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-2.json b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-2.json
new file mode 100644
index 00000000000..6a2ef342807
--- /dev/null
+++ b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-2.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": "172.16.131.31",
+ "ip6": "2001:660:4406:800:4::1f",
+ "kavlan": false,
+ "mac": "50:9a:4c:6c:38:af",
+ "management": false,
+ "mountable": true,
+ "mounted": true,
+ "name": "enp1s0f0np0",
+ "network_address": "esterel24-2.sophia.grid5000.fr",
+ "rate": 10000000000,
+ "switch": null,
+ "switch_port": null
+ },
+ {
+ "device": "bmc",
+ "enabled": true,
+ "interface": "Ethernet",
+ "ip": "172.17.131.31",
+ "kavlan": false,
+ "mac": "70:b5:e8:c9:ff:e2",
+ "management": true,
+ "mountable": false,
+ "mounted": false,
+ "network_address": "esterel24-2-bmc.sophia.grid5000.fr"
+ }
+ ],
+ "nodeset": "esterel24",
+ "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": "esterel24-2"
+}
\ No newline at end of file
diff --git a/input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml b/input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml
new file mode 100644
index 00000000000..09454b75df5
--- /dev/null
+++ b/input/grid5000/sites/sophia/clusters/esterel24/esterel24.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:
+ esterel24-[1-2]:
+ 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: esterel24
diff --git a/input/grid5000/sites/sophia/clusters/esterel24/esterel24_metrics.yaml b/input/grid5000/sites/sophia/clusters/esterel24/esterel24_metrics.yaml
new file mode 100644
index 00000000000..729e9beb582
--- /dev/null
+++ b/input/grid5000/sites/sophia/clusters/esterel24/esterel24_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/esterel24/nodes.yaml.erb b/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb
new file mode 100644
index 00000000000..01290256a74
--- /dev/null
+++ b/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb
@@ -0,0 +1,82 @@
+<%
+ # 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 = "esterel24"
+ nodes_number = 2 # Size of the cluster (number of nodes)
+ # MAC addresses declaration
+ mac_eth0_list = %w(
+34:17:eb:e8:82:bb
+50:9a:4c:6c:38:af
+ )
+ mac_bmc_list = %w(
+f4:02:70:9d:75:a2
+70:b5:e8:c9:ff:e2
+ )
+%>
+---
+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 003ca89c40a723264bea31d4b937a36046e6f252 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 2/8] [sophia][esterel24] fix ethernet production MAC address
---
.../sites/sophia/clusters/esterel24/nodes/esterel24-1.json | 4 ++--
.../sites/sophia/clusters/esterel24/nodes/esterel24-2.json | 4 ++--
.../grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb | 6 +++---
3 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
index 98409fe662d..a895b209d13 100644
--- a/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
+++ b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
@@ -44,7 +44,7 @@
"ip": "172.16.131.30",
"ip6": "2001:660:4406:800:4::1e",
"kavlan": false,
- "mac": "34:17:eb:e8:82:bb",
+ "mac": "f4:02:70:9d:75:92",
"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/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-2.json b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-2.json
index 6a2ef342807..c715dd57cde 100644
--- a/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-2.json
+++ b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-2.json
@@ -44,7 +44,7 @@
"ip": "172.16.131.31",
"ip6": "2001:660:4406:800:4::1f",
"kavlan": false,
- "mac": "50:9a:4c:6c:38:af",
+ "mac": "70:b5:e8:c9:ff:d2",
"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/esterel24/nodes.yaml.erb b/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb
index 01290256a74..983cbe9a325 100644
--- a/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb
+++ b/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb
@@ -1,13 +1,13 @@
<%
- # 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 = "esterel24"
nodes_number = 2 # Size of the cluster (number of nodes)
# MAC addresses declaration
mac_eth0_list = %w(
-34:17:eb:e8:82:bb
-50:9a:4c:6c:38:af
+f4:02:70:9d:75:92
+70:b5:e8:c9:ff:d2
)
mac_bmc_list = %w(
f4:02:70:9d:75:a2
--
GitLab
From e8072df35f6e44441444946f4d1fa0a303310e50 Mon Sep 17 00:00:00 2001
From: Nathan Paulin <nathan.paulin@inria.fr>
Date: Thu, 27 Mar 2025 13:12:55 +0100
Subject: [PATCH 3/8] [sophia][esterel24] add basic conf
---
.../sophia/clusters/esterel24/esterel24.json | 35 ++++-
.../clusters/esterel24/nodes/esterel24-1.json | 22 +--
.../clusters/esterel24/nodes/esterel24-2.json | 128 ------------------
.../sophia/clusters/esterel24/esterel24.yaml | 22 +--
.../clusters/esterel24/esterel24_metrics.yaml | 22 +++
.../sophia/clusters/esterel24/nodes.yaml.erb | 12 +-
6 files changed, 80 insertions(+), 161 deletions(-)
delete mode 100644 data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-2.json
diff --git a/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json b/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json
index 0bf2ac9216c..354759704c5 100644
--- a/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json
+++ b/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json
@@ -1,6 +1,6 @@
{
"boot_type": "uefi",
- "created_at": "Thu, 01 Jan 1970 00:00:00 GMT",
+ "created_at": "Thu, 27 Mar 2025 00:00:00 GMT",
"exotic": false,
"kavlan": false,
"manufactured_at": "1970-01-01",
@@ -49,11 +49,38 @@
"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": "Cluster Model",
- "nodes_count": 2,
- "nodes_description": "1 CPU Unknown vendor, 72 cores/CPU, 0GB RAM, 0GB SSD, 1 x 10Gb Ethernet",
+ "model": "Dell PowerEdge T640",
+ "nodes_count": 1,
+ "nodes_description": "1 CPU Intel Xeon Gold 6240R, 72 cores/CPU, 0GB RAM, 0GB SSD, 1 x 10Gb Ethernet",
"priority": 197001,
"queues": [
"admin",
diff --git a/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
index a895b209d13..45229384ccd 100644
--- a/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
+++ b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
@@ -23,7 +23,7 @@
"ram_size": 8
},
"management_tools": {
- "bmc_vendor_tool": "ipmitool",
+ "bmc_vendor_tool": "racadm",
"ipmitool": {
"retries": 5
}
@@ -44,7 +44,7 @@
"ip": "172.16.131.30",
"ip6": "2001:660:4406:800:4::1e",
"kavlan": false,
- "mac": "f4:02:70:9d:75:92",
+ "mac": "70:b5:e8:c9:ff:d2",
"management": false,
"mountable": true,
"mounted": true,
@@ -60,7 +60,7 @@
"interface": "Ethernet",
"ip": "172.17.131.30",
"kavlan": false,
- "mac": "f4:02:70:9d:75:a2",
+ "mac": "70:b5:e8:c9:ff:e2",
"management": true,
"mountable": false,
"mounted": false,
@@ -77,8 +77,8 @@
"turboboost_enabled": true
},
"performance": {
- "core_flops": 128,
- "node_flops": 9216
+ "core_flops": 76800000000,
+ "node_flops": 5529600000000
},
"processor": {
"cache_l1": null,
@@ -86,15 +86,15 @@
"cache_l1i": 8,
"cache_l2": 8,
"cache_l3": 8,
- "clock_speed": 8,
+ "clock_speed": 2400000000,
"ht_capable": true,
"instruction_set": "x86-64",
- "microarchitecture": "Haswell",
+ "microarchitecture": "Cascade Lake-SP",
"microcode": "0xd000001",
- "model": "Unknown",
- "other_description": "description",
- "vendor": "vendor",
- "version": "vendor"
+ "model": "Intel Xeon",
+ "other_description": "Intel(R) Xeon(R) Gold 6240R CPU @ 2.60GHz",
+ "vendor": "Intel",
+ "version": "Gold 6240R"
},
"redfish": true,
"software": {
diff --git a/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-2.json b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-2.json
deleted file mode 100644
index c715dd57cde..00000000000
--- a/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-2.json
+++ /dev/null
@@ -1,128 +0,0 @@
-{
- "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": "172.16.131.31",
- "ip6": "2001:660:4406:800:4::1f",
- "kavlan": false,
- "mac": "70:b5:e8:c9:ff:d2",
- "management": false,
- "mountable": true,
- "mounted": true,
- "name": "enp1s0f0np0",
- "network_address": "esterel24-2.sophia.grid5000.fr",
- "rate": 10000000000,
- "switch": null,
- "switch_port": null
- },
- {
- "device": "bmc",
- "enabled": true,
- "interface": "Ethernet",
- "ip": "172.17.131.31",
- "kavlan": false,
- "mac": "70:b5:e8:c9:ff:e2",
- "management": true,
- "mountable": false,
- "mounted": false,
- "network_address": "esterel24-2-bmc.sophia.grid5000.fr"
- }
- ],
- "nodeset": "esterel24",
- "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": "1.2025032008",
- "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": "esterel24-2"
-}
\ No newline at end of file
diff --git a/input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml b/input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml
index 09454b75df5..40e03b7b002 100644
--- a/input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml
+++ b/input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml
@@ -1,24 +1,24 @@
---
-model: Cluster Model # TODO: change this value.
-created_at: 1970-01-01 # TODO: change this value
+model: Dell PowerEdge T640
+created_at: 2025-03-27
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
nodes:
- esterel24-[1-2]:
+ esterel24-1:
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.
+ manufactured_at: 1970-01-01
+ warranty_end: 1970-01-01
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.
+ microarchitecture: Cascade Lake-SP
+ clock_speed: 2_400_000_000
network_adapters:
bmc:
interface: Ethernet
@@ -35,7 +35,7 @@ nodes:
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
+ standard-environment: debian11-x64-std
management_tools:
- bmc_vendor_tool: ipmitool # TODO: replace with bmc_vendor_tool (ipmitool, racadm)
+ bmc_vendor_tool: racadm
nodeset: esterel24
diff --git a/input/grid5000/sites/sophia/clusters/esterel24/esterel24_metrics.yaml b/input/grid5000/sites/sophia/clusters/esterel24/esterel24_metrics.yaml
index 729e9beb582..fc4d71df1e4 100644
--- a/input/grid5000/sites/sophia/clusters/esterel24/esterel24_metrics.yaml
+++ b/input/grid5000/sites/sophia/clusters/esterel24/esterel24_metrics.yaml
@@ -38,3 +38,25 @@ metrics:
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
diff --git a/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb b/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb
index 983cbe9a325..7a1726c538c 100644
--- a/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb
+++ b/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb
@@ -3,14 +3,12 @@
# If changes are needed, it might be better to edit the source data and regenerate using 'rake mass:create'
cluster_name = "esterel24"
- nodes_number = 2 # Size of the cluster (number of nodes)
+ nodes_number = 1 # Size of the cluster (number of nodes)
# MAC addresses declaration
mac_eth0_list = %w(
-f4:02:70:9d:75:92
70:b5:e8:c9:ff:d2
)
mac_bmc_list = %w(
-f4:02:70:9d:75:a2
70:b5:e8:c9:ff:e2
)
%>
@@ -39,10 +37,10 @@ nodes:
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
+ model: Intel Xeon # Fake model name, will be replaced by g5k-checks
+ other_description: Intel(R) Xeon(R) Gold 6240R CPU @ 2.60GHz # Fake description, will be replaced by g5k-checks
+ vendor: Intel # Fake vendor, will be replaced by g5k-checks
+ version: Gold 6240R # 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
--
GitLab
From 0b94f13b1102bf2ab7f47226e9b8f0851e48405b Mon Sep 17 00:00:00 2001
From: Nathan Paulin <nathan.paulin@inria.fr>
Date: Thu, 27 Mar 2025 13:18:20 +0100
Subject: [PATCH 4/8] [sophia][esterel24] fix ipv4
---
.../sites/sophia/clusters/esterel24/nodes/esterel24-1.json | 6 +++---
input/grid5000/ipv4.yaml | 2 +-
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
index 45229384ccd..502658dba4a 100644
--- a/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
+++ b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
@@ -41,8 +41,8 @@
"driver": "mlx_core",
"enabled": true,
"interface": "Ethernet",
- "ip": "172.16.131.30",
- "ip6": "2001:660:4406:800:4::1e",
+ "ip": "172.16.131.31",
+ "ip6": "2001:660:4406:800:4::1f",
"kavlan": false,
"mac": "70:b5:e8:c9:ff:d2",
"management": false,
@@ -58,7 +58,7 @@
"device": "bmc",
"enabled": true,
"interface": "Ethernet",
- "ip": "172.17.131.30",
+ "ip": "172.17.131.31",
"kavlan": false,
"mac": "70:b5:e8:c9:ff:e2",
"management": true,
diff --git a/input/grid5000/ipv4.yaml b/input/grid5000/ipv4.yaml
index cf1fe88e88a..8fb758decd3 100644
--- a/input/grid5000/ipv4.yaml
+++ b/input/grid5000/ipv4.yaml
@@ -186,7 +186,7 @@ ipv4:
sophia esterel21 eth0 0 0 3 26
sophia esterel22 eth0 0 0 3 27
sophia esterel23 eth0 0 0 3 28
- sophia esterel24 eth0 0 0 3 29
+ sophia esterel24 eth0 0 0 3 30
sophia esterel25 eth0 0 0 3 31
sophia esterel26 eth0 0 0 3 32
sophia esterel26 ib0 0 0 3 32
--
GitLab
From 8d97e54349901d85933ac8796d61e540ba0980e1 Mon Sep 17 00:00:00 2001
From: Nathan Paulin <nathan.paulin@inria.fr>
Date: Fri, 28 Mar 2025 09:38:44 +0100
Subject: [PATCH 5/8] [sophia][esterel24] add network topology description in
refrepo
---
.../grid5000/sites/sophia/clusters/esterel24/esterel24.json | 2 +-
.../sites/sophia/clusters/esterel24/nodes/esterel24-1.json | 6 +++---
data/grid5000/sites/sophia/network_equipments/sw-5.json | 4 ++++
.../grid5000/sites/sophia/network_equipments/swadmin-5.json | 3 +++
.../grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb | 2 +-
input/grid5000/sites/sophia/networks/sw-5.yaml | 2 ++
input/grid5000/sites/sophia/networks/swadmin-5.yaml | 3 +++
7 files changed, 17 insertions(+), 5 deletions(-)
diff --git a/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json b/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json
index 354759704c5..d74b5a994bd 100644
--- a/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json
+++ b/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json
@@ -80,7 +80,7 @@
],
"model": "Dell PowerEdge T640",
"nodes_count": 1,
- "nodes_description": "1 CPU Intel Xeon Gold 6240R, 72 cores/CPU, 0GB RAM, 0GB SSD, 1 x 10Gb Ethernet",
+ "nodes_description": "1 CPU Intel Xeon Gold 6240R, 72 cores/CPU, 0GB RAM, 0GB SSD, 1 x 1Gb Ethernet",
"priority": 197001,
"queues": [
"admin",
diff --git a/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
index 502658dba4a..bdd7d799b2b 100644
--- a/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
+++ b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
@@ -50,9 +50,9 @@
"mounted": true,
"name": "enp1s0f0np0",
"network_address": "esterel24-1.sophia.grid5000.fr",
- "rate": 10000000000,
- "switch": null,
- "switch_port": null
+ "rate": 1000000000,
+ "switch": "sw-5",
+ "switch_port": "1/1/1"
},
{
"device": "bmc",
diff --git a/data/grid5000/sites/sophia/network_equipments/sw-5.json b/data/grid5000/sites/sophia/network_equipments/sw-5.json
index 373b150f9a2..ff5287d6bff 100644
--- a/data/grid5000/sites/sophia/network_equipments/sw-5.json
+++ b/data/grid5000/sites/sophia/network_equipments/sw-5.json
@@ -11,6 +11,10 @@
{
},
{
+ "kind": "node",
+ "port": "eth0",
+ "snmp_name": "1/1/1",
+ "uid": "esterel24-1"
},
{
},
diff --git a/data/grid5000/sites/sophia/network_equipments/swadmin-5.json b/data/grid5000/sites/sophia/network_equipments/swadmin-5.json
index 6a43eab206b..cdd1d663c9f 100644
--- a/data/grid5000/sites/sophia/network_equipments/swadmin-5.json
+++ b/data/grid5000/sites/sophia/network_equipments/swadmin-5.json
@@ -11,6 +11,9 @@
{
},
{
+ "kind": "other",
+ "snmp_name": "1/1/1",
+ "uid": "esterel24-1-bmc"
},
{
},
diff --git a/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb b/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb
index 7a1726c538c..b5a4f38f2b6 100644
--- a/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb
+++ b/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb
@@ -70,7 +70,7 @@ nodes:
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
+ rate: 1000000000 # Fake data, will be replaced by g5k-checks
mac: <%= mac_eth0_list[i - 1] %>
storage_devices:
disk0:
diff --git a/input/grid5000/sites/sophia/networks/sw-5.yaml b/input/grid5000/sites/sophia/networks/sw-5.yaml
index 77e36ca0993..5e917fc2260 100644
--- a/input/grid5000/sites/sophia/networks/sw-5.yaml
+++ b/input/grid5000/sites/sophia/networks/sw-5.yaml
@@ -14,6 +14,8 @@ sw-5:
rate: 1000000000
kind: node
ports:
+ 1:
+ uid: esterel24-1
25:
uid: gw
kind: router
diff --git a/input/grid5000/sites/sophia/networks/swadmin-5.yaml b/input/grid5000/sites/sophia/networks/swadmin-5.yaml
index 49fea65be49..b7f8a6dd894 100644
--- a/input/grid5000/sites/sophia/networks/swadmin-5.yaml
+++ b/input/grid5000/sites/sophia/networks/swadmin-5.yaml
@@ -14,6 +14,9 @@ swadmin-5:
rate: 1000000000
kind: node
ports:
+ 1:
+ uid: esterel24-1-bmc
+ kind: other
25:
uid: sw-5
kind: switch
--
GitLab
From 9b811b6687eae9d8870972a46c46a6cd19963b00 Mon Sep 17 00:00:00 2001
From: Nathan Paulin <nathan.paulin@inria.fr>
Date: Fri, 28 Mar 2025 13:39:28 +0100
Subject: [PATCH 6/8] [sophia][esterel24] Switch boot_mode to BIOS
---
data/grid5000/sites/sophia/clusters/esterel24/esterel24.json | 2 +-
input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json b/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json
index d74b5a994bd..b6d29e3ffb3 100644
--- a/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json
+++ b/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json
@@ -1,5 +1,5 @@
{
- "boot_type": "uefi",
+ "boot_type": "bios",
"created_at": "Thu, 27 Mar 2025 00:00:00 GMT",
"exotic": false,
"kavlan": false,
diff --git a/input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml b/input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml
index 40e03b7b002..3a6b36cadfc 100644
--- a/input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml
+++ b/input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml
@@ -2,7 +2,7 @@
model: Dell PowerEdge T640
created_at: 2025-03-27
kavlan: false
-boot_type: uefi
+boot_type: bios
exotic: false
queues:
- admin
--
GitLab
From 6a200c59d4a56d1ec8beb18ed279fa75bd68088c Mon Sep 17 00:00:00 2001
From: Nathan Paulin <nathan.paulin@inria.fr>
Date: Mon, 31 Mar 2025 10:09:12 +0200
Subject: [PATCH 7/8] [sophia][esterel24] Determine disk paths
---
.../sites/sophia/clusters/esterel24/esterel24.json | 2 +-
.../sophia/clusters/esterel24/nodes/esterel24-1.json | 12 +++++++++++-
.../sites/sophia/clusters/esterel24/esterel24.yaml | 6 +++++-
.../sites/sophia/clusters/esterel24/nodes.yaml.erb | 4 ++++
4 files changed, 21 insertions(+), 3 deletions(-)
diff --git a/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json b/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json
index b6d29e3ffb3..85d53e93c74 100644
--- a/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json
+++ b/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json
@@ -80,7 +80,7 @@
],
"model": "Dell PowerEdge T640",
"nodes_count": 1,
- "nodes_description": "1 CPU Intel Xeon Gold 6240R, 72 cores/CPU, 0GB RAM, 0GB SSD, 1 x 1Gb Ethernet",
+ "nodes_description": "1 CPU Intel Xeon Gold 6240R, 72 cores/CPU, 0GB RAM, 2x0GB SSD, 1 x 1Gb Ethernet",
"priority": 197001,
"queues": [
"admin",
diff --git a/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
index bdd7d799b2b..921f8fd40ca 100644
--- a/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
+++ b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.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-0:2:63:0",
+ "id": "disk1",
+ "interface": "SATA",
+ "model": "unknown",
+ "size": 8,
+ "storage": "SSD",
+ "vendor": "Unknown"
}
],
"supported_job_types": {
diff --git a/input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml b/input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml
index 3a6b36cadfc..660cea1240e 100644
--- a/input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml
+++ b/input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml
@@ -33,7 +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"
+ disk1: # This field will have to be renamed later.
+ id: disk1
+ interface: SATA
+ by_path: "/dev/disk/by-path/pci-0000:19:00.0-scsi-0:2:63:0"
software:
standard-environment: debian11-x64-std
management_tools:
diff --git a/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb b/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb
index b5a4f38f2b6..30e7eacc6ed 100644
--- a/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb
+++ b/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb
@@ -77,4 +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
+ disk1:
+ 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 6586704a062ea6a99bdec77c431b87bbe14e8edd Mon Sep 17 00:00:00 2001
From: Nathan Paulin <nathan.paulin@inria.fr>
Date: Mon, 31 Mar 2025 14:14:05 +0200
Subject: [PATCH 8/8] [sophia][esterel24] Add predictable network interfaces
mapping + Dell warranty
---
.../sophia/clusters/esterel24/esterel24.json | 8 +-
.../clusters/esterel24/nodes/esterel24-1.json | 249 +++++++++++++++---
input/grid5000/dell-product-data.yaml | 6 +
input/grid5000/ipv4.yaml | 1 +
.../sophia/clusters/esterel24/esterel24.yaml | 13 +-
.../clusters/esterel24/esterel24_ib.yaml | 9 +
.../sophia/clusters/esterel24/nodes.yaml.erb | 84 ------
.../clusters/esterel24/nodes/esterel24-1.yaml | 168 ++++++++++++
lib/refrepo/net_names_mapping.yaml | 4 +
9 files changed, 408 insertions(+), 134 deletions(-)
create mode 100644 input/grid5000/sites/sophia/clusters/esterel24/esterel24_ib.yaml
delete mode 100644 input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb
create mode 100644 input/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.yaml
diff --git a/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json b/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json
index 85d53e93c74..1c87d5f6c5e 100644
--- a/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json
+++ b/data/grid5000/sites/sophia/clusters/esterel24/esterel24.json
@@ -3,7 +3,7 @@
"created_at": "Thu, 27 Mar 2025 00:00:00 GMT",
"exotic": false,
"kavlan": false,
- "manufactured_at": "1970-01-01",
+ "manufactured_at": "2020-09-27",
"metrics": [
{
"description": "Default subset of metrics from Prometheus Node Exporter",
@@ -80,8 +80,8 @@
],
"model": "Dell PowerEdge T640",
"nodes_count": 1,
- "nodes_description": "1 CPU Intel Xeon Gold 6240R, 72 cores/CPU, 0GB RAM, 2x0GB SSD, 1 x 1Gb Ethernet",
- "priority": 197001,
+ "nodes_description": "2 CPUs Intel Xeon Gold 6240R, 24 cores/CPU, 4 GPUs Quadro RTX 8000, 384GB RAM, 558GB HDD, 4468GB HDD, 1 x 1Gb Ethernet, 1 x 40Gb InfiniBand",
+ "priority": 202109,
"queues": [
"admin",
"testing"
@@ -89,5 +89,5 @@
"redfish": true,
"type": "cluster",
"uid": "esterel24",
- "warranty_end": "1970-01-01"
+ "warranty_end": "2027-09-29"
}
\ No newline at end of file
diff --git a/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
index 921f8fd40ca..93ddce97287 100644
--- a/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
+++ b/data/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.json
@@ -1,26 +1,97 @@
{
"architecture": {
- "cpu_core_numbering": "contiguous",
- "nb_cores": 72,
- "nb_procs": 1,
- "nb_threads": 72,
+ "cpu_core_numbering": "round-robin",
+ "nb_cores": 48,
+ "nb_procs": 2,
+ "nb_threads": 96,
"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": "7.00.00.181",
"chassis": {
- "manufactured_at": "1970-01-01",
- "manufacturer": "Unknown",
- "name": "Unknown",
- "warranty_end": "1970-01-01"
+ "manufactured_at": "2020-09-27",
+ "manufacturer": "Dell Inc.",
+ "name": "PowerEdge T640",
+ "serial": "F51GY63",
+ "warranty_end": "2027-09-29"
},
"exotic": false,
+ "gpu_devices": {
+ "nvidia0": {
+ "compute_capability": "7.5",
+ "cores": 4608,
+ "cpu_affinity": 0,
+ "device": "/dev/nvidia0",
+ "memory": 48318382080,
+ "microarchitecture": "Turing",
+ "model": "Quadro RTX 8000",
+ "performance": {
+ "fp-16": 32620000000000,
+ "fp-32": 16310000000000,
+ "fp-64": 510000000000
+ },
+ "power_default_limit": "250.00 W",
+ "vbios_version": "90.02.4E.00.03",
+ "vendor": "Nvidia"
+ },
+ "nvidia1": {
+ "compute_capability": "7.5",
+ "cores": 4608,
+ "cpu_affinity": 0,
+ "device": "/dev/nvidia1",
+ "memory": 48318382080,
+ "microarchitecture": "Turing",
+ "model": "Quadro RTX 8000",
+ "performance": {
+ "fp-16": 32620000000000,
+ "fp-32": 16310000000000,
+ "fp-64": 510000000000
+ },
+ "power_default_limit": "250.00 W",
+ "vbios_version": "90.02.4E.00.03",
+ "vendor": "Nvidia"
+ },
+ "nvidia2": {
+ "compute_capability": "7.5",
+ "cores": 4608,
+ "cpu_affinity": 1,
+ "device": "/dev/nvidia2",
+ "memory": 48318382080,
+ "microarchitecture": "Turing",
+ "model": "Quadro RTX 8000",
+ "performance": {
+ "fp-16": 32620000000000,
+ "fp-32": 16310000000000,
+ "fp-64": 510000000000
+ },
+ "power_default_limit": "250.00 W",
+ "vbios_version": "90.02.4E.00.03",
+ "vendor": "Nvidia"
+ },
+ "nvidia3": {
+ "compute_capability": "7.5",
+ "cores": 4608,
+ "cpu_affinity": 1,
+ "device": "/dev/nvidia3",
+ "memory": 48318382080,
+ "microarchitecture": "Turing",
+ "model": "Quadro RTX 8000",
+ "performance": {
+ "fp-16": 32620000000000,
+ "fp-32": 16310000000000,
+ "fp-64": 510000000000
+ },
+ "power_default_limit": "250.00 W",
+ "vbios_version": "90.02.4E.00.03",
+ "vendor": "Nvidia"
+ }
+ },
"main_memory": {
- "ram_size": 8
+ "ram_size": 412316860416
},
"management_tools": {
"bmc_vendor_tool": "racadm",
@@ -30,29 +101,126 @@
},
"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": "218.0.219.13/pkg 21.85.21.92",
"interface": "Ethernet",
"ip": "172.16.131.31",
"ip6": "2001:660:4406:800:4::1f",
"kavlan": false,
"mac": "70:b5:e8:c9:ff:d2",
"management": false,
+ "model": "BCM57416 NetXtreme-E Dual-Media 10G RDMA Ethernet Controller",
"mountable": true,
"mounted": true,
"name": "enp1s0f0np0",
"network_address": "esterel24-1.sophia.grid5000.fr",
"rate": 1000000000,
+ "sriov": false,
+ "sriov_totalvfs": 0,
"switch": "sw-5",
- "switch_port": "1/1/1"
+ "switch_port": "1/1/1",
+ "vendor": "Broadcom Inc. and subsidiaries"
+ },
+ {
+ "device": "eth1",
+ "driver": "bnxt_en",
+ "enabled": false,
+ "firmware_version": "218.0.219.13/pkg 21.85.21.92",
+ "interface": "Ethernet",
+ "kavlan": false,
+ "mac": "70:b5:e8:c9:ff:d3",
+ "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": "2.7.626",
+ "guid": "0x0002c903000ceab3",
+ "interface": "InfiniBand",
+ "ip": "172.18.131.31",
+ "kavlan": false,
+ "mac": "00:02:c9:03:00:0c:ea:b3",
+ "management": false,
+ "model": "MT25408A0-FCC-QI ConnectX, Dual Port 40Gb/s InfiniBand / 10GigE Adapter IC with PCIe 2.0 x8 5.0GT/s Interface",
+ "mountable": true,
+ "mounted": true,
+ "name": "ib0",
+ "netmask": "255.255.240.0",
+ "network_address": "esterel24-1-ib0.sophia.grid5000.fr",
+ "rate": 40000000000,
+ "vendor": "Mellanox Technologies"
},
{
"device": "bmc",
@@ -69,30 +237,30 @@
],
"nodeset": "esterel24",
"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": 76800000000,
- "node_flops": 5529600000000
+ "node_flops": 3686400000000
},
"processor": {
"cache_l1": null,
- "cache_l1d": 8,
- "cache_l1i": 8,
- "cache_l2": 8,
- "cache_l3": 8,
+ "cache_l1d": 32768,
+ "cache_l1i": 32768,
+ "cache_l2": 1048576,
+ "cache_l3": 37486592,
"clock_speed": 2400000000,
"ht_capable": true,
"instruction_set": "x86-64",
"microarchitecture": "Cascade Lake-SP",
- "microcode": "0xd000001",
+ "microcode": "0x5003801",
"model": "Intel Xeon",
- "other_description": "Intel(R) Xeon(R) Gold 6240R CPU @ 2.60GHz",
+ "other_description": "Intel(R) Xeon(R) Gold 6240R CPU @ 2.40GHz",
"vendor": "Intel",
"version": "Gold 6240R"
},
@@ -104,24 +272,26 @@
},
"storage_devices": [
{
- "by_id": "",
+ "by_id": "/dev/disk/by-id/wwn-0x62cea7f06670a0002790bcc0151d50db",
"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-0x62cea7f06670a0002790bca813ab564d",
"by_path": "/dev/disk/by-path/pci-0000:19:00.0-scsi-0:2:63:0",
+ "firmware_version": 4.3,
"id": "disk1",
"interface": "SATA",
- "model": "unknown",
- "size": 8,
- "storage": "SSD",
- "vendor": "Unknown"
+ "model": "PERC H730P Adp",
+ "size": 4798283776000,
+ "storage": "HDD",
+ "vendor": "Dell"
}
],
"supported_job_types": {
@@ -131,7 +301,8 @@
"queues": [
"admin",
"testing"
- ]
+ ],
+ "virtual": "ivt"
},
"type": "node",
"uid": "esterel24-1"
diff --git a/input/grid5000/dell-product-data.yaml b/input/grid5000/dell-product-data.yaml
index 1eb3f12701d..da54453f07d 100644
--- a/input/grid5000/dell-product-data.yaml
+++ b/input/grid5000/dell-product-data.yaml
@@ -2256,6 +2256,12 @@ sites:
chassis:
manufactured_at: 2016-05-04
warranty_end: 2021-05-04
+ esterel24:
+ nodes:
+ esterel24-1:
+ chassis:
+ manufactured_at: 2020-09-27
+ warranty_end: 2027-09-29
esterel26:
nodes:
esterel26-1:
diff --git a/input/grid5000/ipv4.yaml b/input/grid5000/ipv4.yaml
index 8fb758decd3..ae244138df0 100644
--- a/input/grid5000/ipv4.yaml
+++ b/input/grid5000/ipv4.yaml
@@ -187,6 +187,7 @@ ipv4:
sophia esterel22 eth0 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
sophia esterel25 eth0 0 0 3 31
sophia esterel26 eth0 0 0 3 32
sophia esterel26 ib0 0 0 3 32
diff --git a/input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml b/input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml
index 660cea1240e..13fe3464753 100644
--- a/input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml
+++ b/input/grid5000/sites/sophia/clusters/esterel24/esterel24.yaml
@@ -9,9 +9,6 @@ queues:
- testing
nodes:
esterel24-1:
- chassis:
- manufactured_at: 1970-01-01
- warranty_end: 1970-01-01
supported_job_types:
deploy: true
besteffort: true
@@ -29,15 +26,17 @@ nodes:
enabled: true
mountable: true
mounted: true
+ eth1:
+ enabled: false
+ mountable: false
+ mounted: false
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"
- disk1: # This field will have to be renamed later.
+ pci-0000:19:00.0-scsi-0:2:63:0:
id: disk1
interface: SATA
- by_path: "/dev/disk/by-path/pci-0000:19:00.0-scsi-0:2:63:0"
software:
standard-environment: debian11-x64-std
management_tools:
diff --git a/input/grid5000/sites/sophia/clusters/esterel24/esterel24_ib.yaml b/input/grid5000/sites/sophia/clusters/esterel24/esterel24_ib.yaml
new file mode 100644
index 00000000000..b85e9214f5d
--- /dev/null
+++ b/input/grid5000/sites/sophia/clusters/esterel24/esterel24_ib.yaml
@@ -0,0 +1,9 @@
+---
+nodes:
+ esterel24-1:
+ network_adapters:
+ ib0:
+ enabled: true
+ mountable: true
+ mounted: true
+ netmask: 255.255.240.0
\ No newline at end of file
diff --git a/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb b/input/grid5000/sites/sophia/clusters/esterel24/nodes.yaml.erb
deleted file mode 100644
index 30e7eacc6ed..00000000000
--- a/input/grid5000/sites/sophia/clusters/esterel24/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 = "esterel24"
- nodes_number = 1 # Size of the cluster (number of nodes)
- # MAC addresses declaration
- mac_eth0_list = %w(
-70:b5:e8:c9:ff:d2
- )
- mac_bmc_list = %w(
-70:b5:e8:c9:ff:e2
- )
-%>
----
-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: Intel Xeon # Fake model name, will be replaced by g5k-checks
- other_description: Intel(R) Xeon(R) Gold 6240R CPU @ 2.60GHz # Fake description, will be replaced by g5k-checks
- vendor: Intel # Fake vendor, will be replaced by g5k-checks
- version: Gold 6240R # 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: 1000000000 # 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 # 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
-<% } %>
diff --git a/input/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.yaml b/input/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.yaml
new file mode 100644
index 00000000000..e8bf70e7e4c
--- /dev/null
+++ b/input/grid5000/sites/sophia/clusters/esterel24/nodes/esterel24-1.yaml
@@ -0,0 +1,168 @@
+# Generated by g5k-checks (g5k-checks -m api)
+---
+esterel24-1:
+ architecture:
+ cpu_core_numbering: round-robin
+ nb_cores: 48
+ nb_procs: 2
+ nb_threads: 96
+ platform_type: x86_64
+ bios:
+ release_date: 01/09/2025
+ vendor: Dell Inc.
+ version: 2.23.0
+ bmc_version: 7.00.00.181
+ chassis:
+ manufacturer: Dell Inc.
+ name: PowerEdge T640
+ serial: F51GY63
+ gpu_devices:
+ nvidia0:
+ cpu_affinity: 0
+ device: "/dev/nvidia0"
+ memory: 48318382080
+ model: Quadro RTX 8000
+ power_default_limit: 250.00 W
+ vbios_version: 90.02.4E.00.03
+ vendor: Nvidia
+ nvidia1:
+ cpu_affinity: 0
+ device: "/dev/nvidia1"
+ memory: 48318382080
+ model: Quadro RTX 8000
+ power_default_limit: 250.00 W
+ vbios_version: 90.02.4E.00.03
+ vendor: Nvidia
+ nvidia2:
+ cpu_affinity: 1
+ device: "/dev/nvidia2"
+ memory: 48318382080
+ model: Quadro RTX 8000
+ power_default_limit: 250.00 W
+ vbios_version: 90.02.4E.00.03
+ vendor: Nvidia
+ nvidia3:
+ cpu_affinity: 1
+ device: "/dev/nvidia3"
+ memory: 48318382080
+ model: Quadro RTX 8000
+ power_default_limit: 250.00 W
+ vbios_version: 90.02.4E.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: 172.17.131.31
+ mac: 70:b5:e8:c9:ff:e2
+ management: true
+ eth0:
+ driver: bnxt_en
+ firmware_version: 218.0.219.13/pkg 21.85.21.92
+ interface: Ethernet
+ ip: 172.16.131.31
+ mac: 70:b5:e8:c9:ff:d2
+ 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: 218.0.219.13/pkg 21.85.21.92
+ interface: Ethernet
+ mac: 70:b5:e8:c9:ff:d3
+ 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: 2.7.626
+ guid: '0x0002c903000ceab3'
+ interface: InfiniBand
+ ip: 172.18.131.31
+ mac: 00:02:c9:03:00:0c:ea:b3
+ management: false
+ model: MT25408A0-FCC-QI ConnectX, Dual Port 40Gb/s InfiniBand / 10GigE Adapter
+ IC with PCIe 2.0 x8 5.0GT/s Interface
+ name: ib0
+ rate: 40000000000
+ 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: 37486592
+ ht_capable: true
+ instruction_set: x86-64
+ microcode: '0x5003801'
+ model: Intel Xeon
+ other_description: Intel(R) Xeon(R) Gold 6240R CPU @ 2.40GHz
+ vendor: Intel
+ version: Gold 6240R
+ storage_devices:
+ pci-0000:19:00.0-scsi-0:2:0:0:
+ by_id: "/dev/disk/by-id/wwn-0x62cea7f06670a0002790bcc0151d50db"
+ 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-0:2:63:0:
+ by_id: "/dev/disk/by-id/wwn-0x62cea7f06670a0002790bca813ab564d"
+ by_path: "/dev/disk/by-path/pci-0000:19:00.0-scsi-0:2:63:0"
+ firmware_version: 4.3
+ model: PERC H730P Adp
+ size: 4798283776000
+ storage: HDD
+ supported_job_types:
+ virtual: ivt
diff --git a/lib/refrepo/net_names_mapping.yaml b/lib/refrepo/net_names_mapping.yaml
index 27ec4ca9e74..cf1c3c7dd9e 100644
--- a/lib/refrepo/net_names_mapping.yaml
+++ b/lib/refrepo/net_names_mapping.yaml
@@ -431,6 +431,10 @@ esterel10:
enp1s0f0: eth0
enp1s0f1: eth1
ibp130s0: ib0
+esterel24:
+ enp1s0f0np0: eth0
+ eno2np1: eth1
+ ibp137s0: ib0
esterel26:
enp1s0f0np0: eth0
eno2np1: eth1
--
GitLab