Merge pull request #52 from gleanerio/dev

Dev

.github/workflows/contanerize.yaml

@@ -9,8 +9,11 @@ on:
     branches:
       - main
       - dev
+      - dv_dev
       - dev_eco
-    #  - dev_dagster142
+      - v0_generated_code
+      - 133_dev_sitemaps
+      - 151-integrate-community-stats-codes
     tags:
       - "v*.*.*"
 
@@ -154,7 +157,44 @@ jobs:
             type=ref,event=branch
             type=semver,pattern={{version}}
             type=sha
-
+  build_code_workflows:
+    name: Dockerize  Scheduler Workflows base
+    runs-on: ubuntu-latest
+    #strategy:
+      #matrix:
+       # project: [ "eco" ]
+        #project: [ "eco", "iow", "oih" ]
+        #platform: ["linux/amd64","linux/arm64"]
+        #platform: ["linux/amd64"] #linux/arm64 issues with building
+    steps:
+      - name: Set variables
+        run: |
+            REGISTRY_IMAGE=nsfearthcube/dagster-gleanerio-workflows
+            echo "REGISTRY_IMAGE=$REGISTRY_IMAGE" >> $GITHUB_ENV
+        working-directory:  /
+      - name: Checkout Repo
+        uses: actions/checkout@v3
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+      - name: Login to DockerHub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v4
+        with:
+          images:  ${{ env.REGISTRY_IMAGE }}
+          flavor: |
+            latest=true
+          tags: |
+            type=ref,event=tag
+            type=ref,event=branch
+            type=semver,pattern={{version}}
+            type=sha
 #      - name: Set up Python 3.10
 #        uses: actions/setup-python@v4
 #        with:
@@ -201,7 +241,7 @@ jobs:
           build-args:
             implnet=${{ matrix.project }}
           #file: ./dagster/implnets/build/Dockerfile
-          file: ./build/Dockerfile_code
+          file: ./build/Dockerfile_workflows
           context:  "{{defaultContext}}:dagster/implnets"
           tags: ${{ steps.meta.outputs.tags }}
 #          tags: nsfearthcube/ec_facets_client:latest

.gitignore

@@ -8,3 +8,10 @@ venv/**
 /dagster/.telemetry/
 /dagster/.telemetry/
 .env
+
+/dagster/implnets/generatedCode/implnet-*/output/
+
+/dagster/implnets/deployment/prod.env
+
+**/tmp**
+/dagster/dagster_home/

NOTES.md

@@ -1,5 +1,8 @@
 # Notes
 
+need to do dynamic ops.assets
+https://medium.com/@thegreat.rashid83/dagster-sensors-partition-c7a5205d4c0d
+
 ## Development
 
 At the top level (dagster/implents) you can run 
@@ -28,3 +31,11 @@ will run just the task, and in editable form, i think.
 ## Some articles to review
 
 [Medium on Dagster with configurable API and asset examples](https://medium.com/@alexandreguitton_12701/notes-1-2-dagster-data-orchestrator-hands-on-2af6772b13d9)
+
+## Troubleshooting.
+Keep the python versions in the DOCKER definitions in sync. GRPCC can be finicky
+
+aka:
+
+`FROM python:3.11-slim`
+

README.md

@@ -10,5 +10,8 @@ structured data on the web.
 
 Details of the approach can be found in the [github io](https://earthcube.github.io/scheduler/).
 
+NOTE: Generate code brach v0_generated_code branch
+This is the original code that utilized a generate code approach to build the workflows. 
+v0_generated_code is where gleaner and nabu config file updates should be done when using the original code
 
 

dagster/dagster_home/.gitkeep

@@ -0,0 +1 @@
+This is a place where dagster.yamls can be kept for runs

dagster/dagster_home/dagster.yaml

@@ -0,0 +1,23 @@
+local_artifact_storage:
+  module: dagster.core.storage.root
+  class: LocalArtifactStorage
+  config:
+    base_dir: /Users/valentin/development/dev_earthcube/scheduler/dagster/dagster_home/
+run_coordinator:
+  module: dagster.core.run_coordinator
+  class: QueuedRunCoordinator
+  config:
+    max_concurrent_runs: 6
+    # getting tags by copying from UI
+    tag_concurrency_limits:
+      - key: "ingest"
+        value: "docker"
+        limit: 3
+      - key: "ingest"
+        value: "report"
+        limit: 2
+      - key: "tenant_load"
+        value: "graph"
+        limit: 1
+telemetry:
+  enabled: false

dagster/implnets/Makefile

@@ -2,6 +2,14 @@
 .SHELLFLAGS += -e
 VERSION :=`cat VERSION`
 
+# ----  workflows  ----
+# no code generation is neede for workflows
+
+wf-build:
+	podman build  --tag="docker.io/fils/dagster_wf:$(VERSION)"  --build-arg implnet=eco --file=./build/Dockerfile_workflows .
+
+wf-push:
+	podman push docker.io/fils/dagster_wf:$(VERSION)
 
 # ----  ECO  ----
 

dagster/implnets/VERSION

@@ -1 +1 @@
-0.0.67
+0.1.0

dagster/implnets/build/Dockerfile_code

@@ -12,10 +12,11 @@ RUN mkdir -p /usr/src/app/workflows
 
 RUN pip install --upgrade pip
 ## this is a base for the project. Build this 'layer' first
-COPY ./requirements_code.txt requirements.txt
+COPY ./requirements.txt requirements.txt
 RUN pip install -r requirements.txt
 
 # this add the code
+# this is only needed because we generate the code with pygen. otherwise added in compose-project.yaml docker compose
 COPY . scheduler
 COPY ./configs/${implnet}/gleanerconfig.yaml scheduler/gleanerconfig.yaml
 

dagster/implnets/build/Dockerfile_local

@@ -25,4 +25,4 @@ WORKDIR /usr/src/app
 ENV DAGSTER_HOME=/usr/src/app
 
 
-CMD ["dagster-webserver", "-w", "./project/${implnet}/workspace.yaml", "-h", "0.0.0.0", "-p", "3000"]
+CMD [ "dagster", "api","grpc", "-h", "0.0.0.0", "-p", "4000", "-m", "workflows.tasks.tasks",  "-d", "/usr/src/app/"]

dagster/implnets/build/Dockerfile_workflows

@@ -0,0 +1,43 @@
+FROM python:3.11-slim
+
+
+# this file no longer needs to generate code. It will just include the base
+# it will run ingest by default
+# we may want to get an unreleased version of code, so this is needed
+
+RUN apt-get update && apt-get install -y git
+RUN pip install --upgrade pip
+RUN apt-get install -y  gcc musl-dev python3-dev
+#RUN apt-get install libffi-dev
+# Read the ARG implnet to set who to build for.
+
+# docker buildandpush pulls the repo, so we need to put the code at a different location
+# this fails becaus the dagster/implnets files are not in the docker
+ARG implnet=eco
+
+RUN mkdir -p /usr/src/app/workflows
+
+
+## this is a base for the project. Build this 'layer' first
+COPY ./requirements.txt requirements.txt
+RUN pip install -r requirements.txt
+
+# this add the code
+COPY . scheduler
+#COPY ./configs/${implnet}/gleanerconfig.yaml scheduler/gleanerconfig.yaml
+
+COPY ./deployment/dagster.yaml /usr/src/app/
+
+WORKDIR scheduler
+
+
+COPY ./workflows/ /usr/src/app/workflows
+
+
+
+# Change working directory
+WORKDIR /usr/src/app
+ENV DAGSTER_HOME=/usr/src/app
+
+
+CMD [ "dagster", "api","grpc", "-h", "0.0.0.0", "-p", "4000", "-m", "workflows.tasks.tasks",  "-d", "/usr/src/app/"]