Robert RappandClaude Opus 5.5
908c698589
ci / test (push) Failing after 27s
proxmox.yaml mit gelesenen PCI-IDs/IOMMU-Gruppen, eine GPU-VM pro Knoten mit allen Karten, DHCP, Templates je Knoten. pve-host nur für GPU-Knoten: vfio-pci-IDs auf dem Knoten gelesen, softdeps, sysfb aus, initramfs- Handler, Vendor-Snippet für den Gast-Agenten, Replikation erst wenn der Container existiert. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
34 lines
2.7 KiB
YAML
34 lines
2.7 KiB
YAML
# Proxmox-Zielbild für "knaster" (Eingabe für platform/proxmox/tofu und ansible).
|
||
# Stand 12.10.2026: echte Knoten pve44–pve61. PCI-Adressen, IDs und IOMMU-Gruppen per
|
||
# `pvesh get /nodes/<knoten>/hardware/pci` gelesen. Gäste vorerst per DHCP (D5 zurückgestellt).
|
||
cluster:
|
||
endpoint: https://192.168.100.210:8006/
|
||
storage_iso: local
|
||
bridge: vmbr0
|
||
gateway: 192.168.100.1
|
||
dns: 192.168.100.120
|
||
ssh_public_key_file: ~/.ssh/id_ed25519.pub # Schlüssel auf dem Steuerrechner ops
|
||
lxc_template: debian-13-standard_13.6-1_amd64.tar.zst
|
||
# Ubuntu-24.04-Cloud-Image-Template je Knoten (VMIDs sind clusterweit eindeutig)
|
||
templates: {pve44: 9044, pve46: 9046, pve48: 9048, pve52: 9052}
|
||
|
||
pci_mappings: # Proxmox Resource Mappings (Datacenter → Resource Mappings → PCI)
|
||
gpu-m4000-pve44: {node: pve44, path: "0000:01:00", id: "10de:13f1", subsystem_id: "10de:1153", iommu_group: 1}
|
||
gpu-p2000-pve44: {node: pve44, path: "0000:02:00", id: "10de:1c30", subsystem_id: "10de:11b3", iommu_group: 8}
|
||
gpu-m4000-pve46: {node: pve46, path: "0000:01:00", id: "10de:13f1", subsystem_id: "10de:1153", iommu_group: 1}
|
||
gpu-p2000-pve46: {node: pve46, path: "0000:02:00", id: "10de:1c30", subsystem_id: "10de:11b3", iommu_group: 8}
|
||
gpu-m4000-pve48: {node: pve48, path: "0000:01:00", id: "10de:13f1", subsystem_id: "10de:1153", iommu_group: 1}
|
||
gpu-p2000-pve48: {node: pve48, path: "0000:02:00", id: "10de:1c30", subsystem_id: "10de:11b3", iommu_group: 8}
|
||
gpu-m4000-pve52: {node: pve52, path: "0000:01:00", id: "10de:13f1", subsystem_id: "10de:1153", iommu_group: 1}
|
||
|
||
vms: # eine GPU-VM pro Knoten mit allen Karten des Knotens (D2)
|
||
gpu-pve44: {node: pve44, vmid: 244, cores: 4, memory_mb: 12288, disk_gb: 40, models_disk_gb: 60, storage: local-lvm, gpus: [gpu-m4000-pve44, gpu-p2000-pve44], ip: dhcp, driver_generation: legacy}
|
||
gpu-pve46: {node: pve46, vmid: 246, cores: 4, memory_mb: 12288, disk_gb: 40, models_disk_gb: 60, storage: local-lvm, gpus: [gpu-m4000-pve46, gpu-p2000-pve46], ip: dhcp, driver_generation: legacy}
|
||
gpu-pve48: {node: pve48, vmid: 248, cores: 4, memory_mb: 12288, disk_gb: 40, models_disk_gb: 60, storage: local-lvm, gpus: [gpu-m4000-pve48, gpu-p2000-pve48], ip: dhcp, driver_generation: legacy}
|
||
gpu-pve52: {node: pve52, vmid: 252, cores: 4, memory_mb: 12288, disk_gb: 40, models_disk_gb: 60, storage: local-lvm, gpus: [gpu-m4000-pve52], ip: dhcp, driver_generation: legacy}
|
||
|
||
containers: # Infrastruktur als LXC (ADR-0001), HA + ZFS-Replikation (ADR-0002)
|
||
infra: {node: pve44, vmid: 101, cores: 4, memory_mb: 8192, disk_gb: 60, storage: tank, ip: dhcp, ha: true, replicate_to: [pve52, pve48]}
|
||
|
||
replication_schedule: "*/15"
|