From 3f5deb1060432d0279512b4a29c00362626d6bc8 Mon Sep 17 00:00:00 2001
From: PARISOT Clement <clement.parisot@inria.fr>
Date: Mon, 14 Oct 2024 17:38:57 +0200
Subject: [PATCH] [rennes] abacus - separate abacus-22 in 2 clusters
Signed-off-by: PARISOT Clement <clement.parisot@inria.fr>
---
data/grid5000/accesses/refrepo.json | 33 +++++++---
.../clusters/abacus22/nodes/abacus22-1.json | 2 +-
.../clusters/abacus22/nodes/abacus22-2.json | 2 +-
.../rennes/clusters/abacus23/abacus23.json | 64 +++++++++++++++++++
.../nodes/abacus23-1.json} | 11 ++--
.../swdc-a035-01-02-rba.json | 2 +-
input/grid5000/access/rennes.yaml | 4 +-
input/grid5000/ipv4.yaml | 1 +
.../rennes/clusters/abacus22/abacus22.yaml | 15 +----
.../rennes/clusters/abacus23/abacus23.yaml | 47 ++++++++++++++
.../clusters/abacus23/abacus23_metrics.yaml | 41 ++++++++++++
.../nodes/abacus23-1.yaml} | 2 +-
.../rennes/networks/swdc-a035-01-02-rba.yaml | 2 +-
lib/refrepo/valid/data/homogeneity.yaml.erb | 7 --
14 files changed, 192 insertions(+), 41 deletions(-)
create mode 100644 data/grid5000/sites/rennes/clusters/abacus23/abacus23.json
rename data/grid5000/sites/rennes/clusters/{abacus22/nodes/abacus22-3.json => abacus23/nodes/abacus23-1.json} (96%)
create mode 100644 input/grid5000/sites/rennes/clusters/abacus23/abacus23.yaml
create mode 100644 input/grid5000/sites/rennes/clusters/abacus23/abacus23_metrics.yaml
rename input/grid5000/sites/rennes/clusters/{abacus22/nodes/abacus22-3.yaml => abacus23/nodes/abacus23-1.yaml} (99%)
diff --git a/data/grid5000/accesses/refrepo.json b/data/grid5000/accesses/refrepo.json
index 1b64ca2575e..af0897d7132 100644
--- a/data/grid5000/accesses/refrepo.json
+++ b/data/grid5000/accesses/refrepo.json
@@ -99008,7 +99008,7 @@
"network_address": "abacus22-1-bmc.rennes.grid5000.fr"
}
],
- "nodeset": "abacus22-A",
+ "nodeset": "abacus22",
"performance": {
"core_flops": 42400000000,
"node_flops": 2035200000000
@@ -99252,7 +99252,7 @@
"network_address": "abacus22-2-bmc.rennes.grid5000.fr"
}
],
- "nodeset": "abacus22-A",
+ "nodeset": "abacus22",
"performance": {
"core_flops": 42400000000,
"node_flops": 2035200000000
@@ -99298,8 +99298,20 @@
}
],
"uid": "abacus22-2"
- },
- "abacus22-3": {
+ }
+ },
+ "queues": [
+ "admin",
+ "production"
+ ],
+ "uid": "abacus22"
+ },
+ "abacus23": {
+ "created_at": "Wed, 31 Jul 2024 00:00:00 GMT",
+ "manufactured_at": "2022-01-19",
+ "model": "ProLiant DL385 Gen10 Plus v2",
+ "nodes": {
+ "abacus23-1": {
"architecture": {
"cpu_core_numbering": "contiguous",
"nb_cores": 48,
@@ -99424,7 +99436,7 @@
"mountable": true,
"mounted": true,
"name": "ens10f0",
- "network_address": "abacus22-3.rennes.grid5000.fr",
+ "network_address": "abacus23-1.rennes.grid5000.fr",
"rate": 10000000000,
"sriov": true,
"sriov_totalvfs": 128,
@@ -99459,10 +99471,10 @@
"management": true,
"mountable": false,
"mounted": false,
- "network_address": "abacus22-3-bmc.rennes.grid5000.fr"
+ "network_address": "abacus23-1-bmc.rennes.grid5000.fr"
}
],
- "nodeset": "abacus22-B",
+ "nodeset": "abacus23",
"performance": {
"core_flops": 42400000000,
"node_flops": 2035200000000
@@ -99507,14 +99519,15 @@
"vendor": "HPE"
}
],
- "uid": "abacus22-3"
+ "uid": "abacus23-1"
}
},
"queues": [
"admin",
- "production"
+ "production",
+ "challenge"
],
- "uid": "abacus22"
+ "uid": "abacus23"
},
"abacus25": {
"created_at": "Mon, 05 Jun 2023 00:00:00 GMT",
diff --git a/data/grid5000/sites/rennes/clusters/abacus22/nodes/abacus22-1.json b/data/grid5000/sites/rennes/clusters/abacus22/nodes/abacus22-1.json
index ce303d87c64..14cb60573e0 100644
--- a/data/grid5000/sites/rennes/clusters/abacus22/nodes/abacus22-1.json
+++ b/data/grid5000/sites/rennes/clusters/abacus22/nodes/abacus22-1.json
@@ -218,7 +218,7 @@
"network_address": "abacus22-1-bmc.rennes.grid5000.fr"
}
],
- "nodeset": "abacus22-A",
+ "nodeset": "abacus22",
"operating_system": {
"cstate_driver": "acpi_idle",
"cstate_governor": "menu",
diff --git a/data/grid5000/sites/rennes/clusters/abacus22/nodes/abacus22-2.json b/data/grid5000/sites/rennes/clusters/abacus22/nodes/abacus22-2.json
index 8ee7ec25afc..c2ba2930f74 100644
--- a/data/grid5000/sites/rennes/clusters/abacus22/nodes/abacus22-2.json
+++ b/data/grid5000/sites/rennes/clusters/abacus22/nodes/abacus22-2.json
@@ -218,7 +218,7 @@
"network_address": "abacus22-2-bmc.rennes.grid5000.fr"
}
],
- "nodeset": "abacus22-A",
+ "nodeset": "abacus22",
"operating_system": {
"cstate_driver": "acpi_idle",
"cstate_governor": "menu",
diff --git a/data/grid5000/sites/rennes/clusters/abacus23/abacus23.json b/data/grid5000/sites/rennes/clusters/abacus23/abacus23.json
new file mode 100644
index 00000000000..c41da847269
--- /dev/null
+++ b/data/grid5000/sites/rennes/clusters/abacus23/abacus23.json
@@ -0,0 +1,64 @@
+{
+ "boot_type": "uefi",
+ "created_at": "Wed, 31 Jul 2024 00:00:00 GMT",
+ "exotic": false,
+ "kavlan": false,
+ "manufactured_at": "2022-01-19",
+ "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": "ProLiant DL385 Gen10 Plus v2",
+ "queues": [
+ "admin",
+ "production",
+ "challenge"
+ ],
+ "redfish": true,
+ "type": "cluster",
+ "uid": "abacus23",
+ "warranty_end": "2027-01-25"
+}
\ No newline at end of file
diff --git a/data/grid5000/sites/rennes/clusters/abacus22/nodes/abacus22-3.json b/data/grid5000/sites/rennes/clusters/abacus23/nodes/abacus23-1.json
similarity index 96%
rename from data/grid5000/sites/rennes/clusters/abacus22/nodes/abacus22-3.json
rename to data/grid5000/sites/rennes/clusters/abacus23/nodes/abacus23-1.json
index bd81fca4601..9134274821b 100644
--- a/data/grid5000/sites/rennes/clusters/abacus22/nodes/abacus22-3.json
+++ b/data/grid5000/sites/rennes/clusters/abacus23/nodes/abacus23-1.json
@@ -146,7 +146,7 @@
"mountable": true,
"mounted": true,
"name": "ens10f0",
- "network_address": "abacus22-3.rennes.grid5000.fr",
+ "network_address": "abacus23-1.rennes.grid5000.fr",
"rate": 10000000000,
"sriov": true,
"sriov_totalvfs": 128,
@@ -181,10 +181,10 @@
"management": true,
"mountable": false,
"mounted": false,
- "network_address": "abacus22-3-bmc.rennes.grid5000.fr"
+ "network_address": "abacus23-1-bmc.rennes.grid5000.fr"
}
],
- "nodeset": "abacus22-B",
+ "nodeset": "abacus23",
"operating_system": {
"cstate_driver": "acpi_idle",
"cstate_governor": "menu",
@@ -249,10 +249,11 @@
"max_walltime": 604800,
"queues": [
"admin",
- "production"
+ "production",
+ "challenge"
],
"virtual": "amd-v"
},
"type": "node",
- "uid": "abacus22-3"
+ "uid": "abacus23-1"
}
\ No newline at end of file
diff --git a/data/grid5000/sites/rennes/network_equipments/swdc-a035-01-02-rba.json b/data/grid5000/sites/rennes/network_equipments/swdc-a035-01-02-rba.json
index fa2080c1327..bf7153ea660 100644
--- a/data/grid5000/sites/rennes/network_equipments/swdc-a035-01-02-rba.json
+++ b/data/grid5000/sites/rennes/network_equipments/swdc-a035-01-02-rba.json
@@ -9231,7 +9231,7 @@
"kind": "node",
"port": "eth0",
"snmp_name": "Eth1/4601",
- "uid": "abacus22-3"
+ "uid": "abacus23-1"
},
{
"kind": "node",
diff --git a/input/grid5000/access/rennes.yaml b/input/grid5000/access/rennes.yaml
index 9b804a1b9bc..c072a706651 100644
--- a/input/grid5000/access/rennes.yaml
+++ b/input/grid5000/access/rennes.yaml
@@ -52,7 +52,7 @@ abacus5: &sirocco-exclusive
p1: [sirocco, '@admin']
besteffort: ['@inria_group', '@other_groups_with_access']
abacus20: *sirocco-exclusive
-abacus22-A: *sirocco-exclusive
+abacus22: *sirocco-exclusive
## INTUIDOC
abacus11:
@@ -72,7 +72,7 @@ abacus17:
besteffort: ['@inria_group', '@other_groups_with_access']
## CIDRE
-abacus22-B:
+abacus23:
p1: [cidre, '@admin']
besteffort: ['@inria_group', '@other_groups_with_access']
diff --git a/input/grid5000/ipv4.yaml b/input/grid5000/ipv4.yaml
index c6cd1a570fc..d2021c4b14a 100644
--- a/input/grid5000/ipv4.yaml
+++ b/input/grid5000/ipv4.yaml
@@ -84,6 +84,7 @@ ipv4:
rennes abacus20 eth0 0 0 13 19
rennes abacus21 eth0 0 0 13 20
rennes abacus22 eth0 0 0 13 21
+ rennes abacus23 eth0 0 0 13 23
rennes abacus25 eth0 0 0 13 24
rennes roazhon1 eth1 0 0 14 0
rennes roazhon2 eth0 0 0 14 1
diff --git a/input/grid5000/sites/rennes/clusters/abacus22/abacus22.yaml b/input/grid5000/sites/rennes/clusters/abacus22/abacus22.yaml
index e0992d53361..3f2a94355d5 100644
--- a/input/grid5000/sites/rennes/clusters/abacus22/abacus22.yaml
+++ b/input/grid5000/sites/rennes/clusters/abacus22/abacus22.yaml
@@ -7,7 +7,7 @@ queues:
- admin
- production
nodes:
- abacus22-[1-3]:
+ abacus22-[1-2]:
supported_job_types:
deploy: true
besteffort: true
@@ -37,11 +37,10 @@ nodes:
pci-0000:64:00.0-scsi-0:1:0:0:
id: disk0
interface: SATA
- abacus22-[1-2]:
chassis:
manufactured_at: 2022-01-14
warranty_end: 2027-01-20
- nodeset: abacus22-A
+ nodeset: abacus22
abacus22-1:
storage_devices:
pci-0000:64:00.0-sas-0x50000f0b019454a2-lun-0:
@@ -52,12 +51,4 @@ nodes:
pci-0000:64:00.0-sas-0x50000f0b01945482-lun-0:
id: disk1
interface: SAS
- abacus22-3:
- chassis:
- manufactured_at: 2022-01-19
- warranty_end: 2027-01-25
- storage_devices:
- pci-0000:64:00.0-sas-0x50000f0b01938442-lun-0:
- id: disk1
- interface: SAS
- nodeset: abacus22-B
+
diff --git a/input/grid5000/sites/rennes/clusters/abacus23/abacus23.yaml b/input/grid5000/sites/rennes/clusters/abacus23/abacus23.yaml
new file mode 100644
index 00000000000..68faeb73f7e
--- /dev/null
+++ b/input/grid5000/sites/rennes/clusters/abacus23/abacus23.yaml
@@ -0,0 +1,47 @@
+model: ProLiant DL385 Gen10 Plus v2
+created_at: 2024-07-31
+kavlan: false
+boot_type: uefi
+exotic: false
+queues:
+ - admin
+ - production
+ - challenge
+nodes:
+ abacus23-1:
+ supported_job_types:
+ deploy: true
+ besteffort: true
+ max_walltime: 604800
+ processor:
+ microarchitecture: Zen 3
+ clock_speed: 2650000000
+ software:
+ standard-environment: debian11-x64-std
+ management_tools:
+ bmc_vendor_tool: ipmitool
+ network_adapters:
+ bmc:
+ interface: Ethernet
+ enabled: true
+ mountable: false
+ mounted: false
+ eth0:
+ enabled: true
+ mountable: true
+ mounted: true
+ eth1:
+ enabled: false
+ mountable: false
+ mounted: false
+ storage_devices:
+ pci-0000:64:00.0-scsi-0:1:0:0:
+ id: disk0
+ interface: SATA
+ pci-0000:64:00.0-sas-0x50000f0b01938442-lun-0:
+ id: disk1
+ interface: SAS
+ chassis:
+ manufactured_at: 2022-01-19
+ warranty_end: 2027-01-25
+ nodeset: abacus23
diff --git a/input/grid5000/sites/rennes/clusters/abacus23/abacus23_metrics.yaml b/input/grid5000/sites/rennes/clusters/abacus23/abacus23_metrics.yaml
new file mode 100644
index 00000000000..1b7527d9fcc
--- /dev/null
+++ b/input/grid5000/sites/rennes/clusters/abacus23/abacus23_metrics.yaml
@@ -0,0 +1,41 @@
+---
+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/rennes/clusters/abacus22/nodes/abacus22-3.yaml b/input/grid5000/sites/rennes/clusters/abacus23/nodes/abacus23-1.yaml
similarity index 99%
rename from input/grid5000/sites/rennes/clusters/abacus22/nodes/abacus22-3.yaml
rename to input/grid5000/sites/rennes/clusters/abacus23/nodes/abacus23-1.yaml
index df3b5e50696..1d4067bd761 100644
--- a/input/grid5000/sites/rennes/clusters/abacus22/nodes/abacus22-3.yaml
+++ b/input/grid5000/sites/rennes/clusters/abacus23/nodes/abacus23-1.yaml
@@ -1,6 +1,6 @@
# Generated by g5k-checks (g5k-checks -m api)
---
-abacus22-3:
+abacus23-1:
architecture:
cpu_core_numbering: contiguous
nb_cores: 48
diff --git a/input/grid5000/sites/rennes/networks/swdc-a035-01-02-rba.yaml b/input/grid5000/sites/rennes/networks/swdc-a035-01-02-rba.yaml
index 55f37a7cd7a..bbfa36f2657 100644
--- a/input/grid5000/sites/rennes/networks/swdc-a035-01-02-rba.yaml
+++ b/input/grid5000/sites/rennes/networks/swdc-a035-01-02-rba.yaml
@@ -22,7 +22,7 @@ swdc-a035-01-02-rba:
45_02: # physically on interface 1/45 of swdc-a035-02-rba only
uid: abacus25-3
46_01: # physically on interface 1/46 of swdc-a035-01-rba only
- uid: abacus22-3
+ uid: abacus23-1
46_02: # physically on interface 1/46 of swdc-a035-02-rba only
uid: abacus25-4
47_01: # physically on interface 1/47 of swdc-a035-01-rba only
diff --git a/lib/refrepo/valid/data/homogeneity.yaml.erb b/lib/refrepo/valid/data/homogeneity.yaml.erb
index 8f09716ff19..2a1f06d58dc 100644
--- a/lib/refrepo/valid/data/homogeneity.yaml.erb
+++ b/lib/refrepo/valid/data/homogeneity.yaml.erb
@@ -382,13 +382,6 @@ rennes:
- ~network_adapters.eth1.firmware_version
- -storage_devices.pci-0000:64:00.0-sas-0x50000f0b019454a2-lun-0
- +storage_devices.pci-0000:64:00.0-sas-0x50000f0b01945482-lun-0
- abacus22-3:
- - ~network_adapters.eth0.firmware_version
- - ~network_adapters.eth1.firmware_version
- - -gpu_devices.nvidia1
- - -gpu_devices.nvidia2
- - -storage_devices.pci-0000:64:00.0-sas-0x50000f0b01945482-lun-0
- - +storage_devices.pci-0000:64:00.0-sas-0x50000f0b01938442-lun-0
abacus25-3:
- ~storage_devices.pci-0000:64:00.0-scsi-0:2:1:0.model
- ~storage_devices.pci-0000:64:00.0-scsi-0:2:1:0.firmware_version
--
GitLab