mirror of
https://github.com/mulgadc/spinifex.git
synced 2026-10-19 19:01:42 +00:00
Josh Siviour
6879a3425a
* feat(gpu): Ubuntu NVIDIA GPU node image + GPU AMI selection Epic A of GPU passthrough to EKS pods / ECS task containers. - Add gpu-vendor AMI tag constants + GPUVendorForType/IsGPUTypeName helpers (instance-family prefix -> vendor from knownGPUModels). - EKS + ECS worker AMI resolution branches to a GPU-tagged node image for GPU instance types; no fallback to the driverless image (hard error instead). - Exclude gpu-vendor-tagged AMIs from the plain (non-GPU) lookup so a newer GPU AMI cannot hijack ordinary nodes (managed-by tag is shared; filters have no negation, so exclude client-side). - NodegroupRecord caches GPUEnabled/GPUVendor from InstanceTypes. - Catalog entries spinifex-eks-node-gpu / spinifex-ecs-node-gpu (dual-tagged). - New Ubuntu 26.04 GPU node images (eks-node-gpu, ecs-agent-gpu): reuse the proven DKMS -server driver recipe (drop Docker CE + dev payload), add nvidia-container-toolkit, OpenRC->systemd port of the worker/agent service subset, udev EBS by-id bridge, nvidia modules-load, first-boot CDI generation. - build-system-image.sh: SYSTEM_TAG supports multiple space-separated tags. * build: allow SYSTEM_IMAGE_BUILD_DIR override for image build dir Ubuntu GPU images are 16G; a RAM-backed /tmp tmpfs is too small to hold the qcow2 + expanded raw. Default stays /tmp; SYSTEM_IMAGE_BUILD_DIR redirects the build onto a real disk.
23 lines
808 B
Desktop File
23 lines
808 B
Desktop File
[Unit]
|
|
Description=Spinifex ECS container-instance agent
|
|
# Resolves host identity from IMDSv2, registers + heartbeats + polls task
|
|
# assignments through the AWS gateway over TLS+SigV4 (no NATS), and pulls
|
|
# task images through containerd.
|
|
Requires=containerd.service
|
|
After=containerd.service ecs-ca-install.service network-online.target mulga-cdi-generate.service
|
|
Wants=network-online.target
|
|
|
|
[Service]
|
|
Type=simple
|
|
# Static config (gateway URL, CA, region, cluster, seeded IAM creds,
|
|
# containerd socket) comes from /etc/spinifex-ecs/agent.env, dropped by
|
|
# cloud-init at launch. Absent file is tolerated — the agent falls back to
|
|
# its built-in defaults.
|
|
EnvironmentFile=-/etc/spinifex-ecs/agent.env
|
|
ExecStart=/usr/local/bin/ecs-agent
|
|
Restart=on-failure
|
|
RestartSec=5
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target
|