Files
kuberay-images/Makefile
Billy D. cb80709d3d
Some checks failed
Build and Push Images / build-rdna2 (push) Failing after 4m3s
Build and Push Images / build-nvidia (push) Failing after 4m6s
Build and Push Images / build-strixhalo (push) Failing after 18s
Build and Push Images / build-intel (push) Failing after 21s
build: optimize Dockerfiles for production
- Use BuildKit syntax 1.7 with cache mounts for apt/uv
- Switch from pip to uv for 10-100x faster installs (ADR-0014)
- Add OCI Image Spec labels for container metadata
- Add HEALTHCHECK directives for orchestration
- Add .dockerignore to reduce context size
- Update Makefile with buildx and lint target
- Add retry logic to ray-entrypoint.sh

Refs: ADR-0012 (uv), ADR-0014 (Docker best practices)
2026-02-02 07:26:27 -05:00

115 lines
3.3 KiB
Makefile

# KubeRay Images Makefile
# Build and push GPU-specific Ray worker images
REGISTRY := git.daviestechlabs.io/daviestechlabs
TAG := latest
PLATFORM := linux/amd64
# Image names
IMAGES := ray-worker-nvidia ray-worker-rdna2 ray-worker-strixhalo ray-worker-intel
.PHONY: all build-all push-all clean help lint $(addprefix build-,$(IMAGES)) $(addprefix push-,$(IMAGES))
help:
@echo "KubeRay Images Build System"
@echo ""
@echo "Usage:"
@echo " make build-all Build all images"
@echo " make push-all Push all images to registry"
@echo " make build-nvidia Build NVIDIA worker image"
@echo " make build-rdna2 Build AMD RDNA2 worker image"
@echo " make build-strixhalo Build AMD Strix Halo worker image"
@echo " make build-intel Build Intel XPU worker image"
@echo " make push-nvidia Push NVIDIA worker image"
@echo " make lint Lint Dockerfiles with hadolint"
@echo " make TAG=v1.0.0 push-all Push with specific tag"
@echo ""
@echo "Environment:"
@echo " REGISTRY=$(REGISTRY)"
@echo " TAG=$(TAG)"
@echo " PLATFORM=$(PLATFORM)"
# Lint Dockerfiles with hadolint
lint:
@echo "Linting Dockerfiles..."
@command -v hadolint >/dev/null 2>&1 || { echo "hadolint not found, skipping..."; exit 0; }
hadolint dockerfiles/Dockerfile.ray-worker-nvidia
hadolint dockerfiles/Dockerfile.ray-worker-rdna2
hadolint dockerfiles/Dockerfile.ray-worker-strixhalo
hadolint dockerfiles/Dockerfile.ray-worker-intel
@echo "Lint passed!"
# Build targets using buildx for cache support
build-nvidia:
docker buildx build \
--platform $(PLATFORM) \
--tag $(REGISTRY)/ray-worker-nvidia:$(TAG) \
--file dockerfiles/Dockerfile.ray-worker-nvidia \
--load \
.
build-rdna2:
docker buildx build \
--platform $(PLATFORM) \
--tag $(REGISTRY)/ray-worker-rdna2:$(TAG) \
--file dockerfiles/Dockerfile.ray-worker-rdna2 \
--load \
.
build-strixhalo:
docker buildx build \
--platform $(PLATFORM) \
--tag $(REGISTRY)/ray-worker-strixhalo:$(TAG) \
--file dockerfiles/Dockerfile.ray-worker-strixhalo \
--load \
.
build-intel:
docker buildx build \
--platform $(PLATFORM) \
--tag $(REGISTRY)/ray-worker-intel:$(TAG) \
--file dockerfiles/Dockerfile.ray-worker-intel \
--load \
.
build-all: build-nvidia build-rdna2 build-strixhalo build-intel
@echo "All images built successfully"
# Push targets
push-nvidia:
docker push $(REGISTRY)/ray-worker-nvidia:$(TAG)
push-rdna2:
docker push $(REGISTRY)/ray-worker-rdna2:$(TAG)
push-strixhalo:
docker push $(REGISTRY)/ray-worker-strixhalo:$(TAG)
push-intel:
docker push $(REGISTRY)/ray-worker-intel:$(TAG)
push-all: push-nvidia push-rdna2 push-strixhalo push-intel
@echo "All images pushed successfully"
# Tag and push with both latest and version tag
release:
ifndef VERSION
$(error VERSION is not set. Usage: make VERSION=v1.0.0 release)
endif
@echo "Releasing version $(VERSION)"
$(MAKE) TAG=$(VERSION) build-all
$(MAKE) TAG=$(VERSION) push-all
$(MAKE) TAG=latest build-all
$(MAKE) TAG=latest push-all
# Login to registry
login:
docker login $(REGISTRY)
# Clean local images
clean:
-docker rmi $(REGISTRY)/ray-worker-nvidia:$(TAG)
-docker rmi $(REGISTRY)/ray-worker-rdna2:$(TAG)
-docker rmi $(REGISTRY)/ray-worker-strixhalo:$(TAG)
-docker rmi $(REGISTRY)/ray-worker-intel:$(TAG)