[wip] second design for metrics operator

.github/workflows/main.yaml

@@ -16,7 +16,7 @@ jobs:
     - name: Check Spelling
       uses: crate-ci/typos@7ad296c72fa8265059cc03d1eda562fbdfcd6df2 # v1.9.0
       with:
-        files: ./README.md ./config/samples ./docs/*.md ./docs/*/*.md
+        files: ./README.md ./docs/*.md ./docs/*/*.md ./docs/*/*/*.md
 
     - name: Lint and format Python code
       run: |
@@ -66,19 +66,19 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        test: [["perf-hello-world", "ghcr.io/converged-computing/metric-sysstat:latest", 60],               # performance test
-               ["io-host-volume", "ghcr.io/converged-computing/metric-sysstat:latest", 60],                 # storage test
-               ["io-fio", "ghcr.io/converged-computing/metric-fio:latest", 120],                            # storage test
-               ["io-ior", "ghcr.io/converged-computing/metric-ior:latest", 120],                            # storage test
-               # ["network-chatterbug", "ghcr.io/converged-computing/metric-chatterbug:latest", 120],         # network app test
-               ["app-nekbone", "ghcr.io/converged-computing/metric-nekbone:latest", 120],                   # standalone app test
-               # ["app-ldms", "ghcr.io/converged-computing/metric-ovis-hpc:latest", 120],                     # standalone app test
-               ["app-amg", "ghcr.io/converged-computing/metric-amg:latest", 120],                           # standalone app test
-               ["app-kripke", "ghcr.io/converged-computing/metric-kripke:latest", 120],                     # standalone app test
-               ["app-pennant", "ghcr.io/converged-computing/metric-pennant:latest", 120],                   # standalone app test
-               ["app-bdas", "ghcr.io/converged-computing/metric-bdas:latest", 120],                         # standalone app test
-               ["app-quicksilver", "ghcr.io/converged-computing/metric-quicksilver:latest", 120],           # standalone app test
-               ["app-lammps", "ghcr.io/converged-computing/metric-lammps:latest", 120]]                     # standalone app test
+        test: [["app-lammps", "ghcr.io/converged-computing/metric-lammps:latest", 120],
+               ["perf-hello-world", "ghcr.io/converged-computing/metric-sysstat:latest", 60],
+               ["io-host-volume", "ghcr.io/converged-computing/metric-sysstat:latest", 60],
+               ["io-fio", "ghcr.io/converged-computing/metric-fio:latest", 120],
+               ["io-ior", "ghcr.io/converged-computing/metric-ior:latest", 120],
+               ## ["network-chatterbug", "ghcr.io/converged-computing/metric-chatterbug:latest", 120],
+               ["app-nekbone", "ghcr.io/converged-computing/metric-nekbone:latest", 120],
+               ["app-ldms", "ghcr.io/converged-computing/metric-ovis-hpc:latest", 120],
+               ["app-amg", "ghcr.io/converged-computing/metric-amg:latest", 120],
+               ["app-kripke", "ghcr.io/converged-computing/metric-kripke:latest", 120],
+               ["app-pennant", "ghcr.io/converged-computing/metric-pennant:latest", 120],
+               ["app-bdas", "ghcr.io/converged-computing/metric-bdas:latest", 120],
+               ["app-quicksilver", "ghcr.io/converged-computing/metric-quicksilver:latest", 120]]
 
     steps:
     - name: Clone the code

.github/workflows/python.yaml

@@ -27,7 +27,7 @@ jobs:
       run: |
         export PATH="/usr/share/miniconda/bin:$PATH"
         source activate mo
-        cd sdk/python/v1alpha1
+        cd sdk/python/v1alpha2
         pip install .
         pip install seaborn pandas
 

.github/workflows/release.yaml

@@ -106,7 +106,7 @@ jobs:
       run: |
         export PATH="/usr/share/miniconda/bin:$PATH"
         source activate mo
-        cd sdk/python/v1alpha1/
+        cd sdk/python/v1alpha2/
         pip install -e .
         python setup.py sdist bdist_wheel
         cd dist

Makefile

@@ -323,7 +323,8 @@ helm: manifests kustomize helmify
 
 .PHONY: docs-data
 docs-data:
-	go run hack/docs-gen/main.go docs/_static/data/metrics.json
+	go run hack/metrics-gen/main.go docs/_static/data/metrics.json
+	go run hack/addons-gen/main.go docs/_static/data/addons.json
 
 .PHONY: pre-push
 pre-push: generate build-config-arm build-config docs-data

PROJECT

@@ -17,6 +17,6 @@ resources:
   controller: true
   domain: flux-framework.org
   kind: MetricSet
-  path: github.com/converged-computing/metrics-operator/api/v1alpha1
-  version: v1alpha1
+  path: github.com/converged-computing/metrics-operator/api/v1alpha2
+  version: v1alpha2
 version: "3"

README.md

@@ -12,6 +12,7 @@ To learn more:
 
 ## Dinosaur TODO
 
+- Figure out issue with errors.IsNotFound not working...
 - We need a way for the entrypoint command to monitor (based on the container) to differ (potentially)
 - For larger metric collections, we should have a log streaming mode (and not wait for Completed/Successful)
 - For services we are measuring, we likely need to be able to kill after N seconds (to complete job) or to specify the success policy on the metrics containers instead of the application

api/v1alpha1/groupversion_info.go → api/v1alpha2/groupversion_info.go

@@ -14,10 +14,10 @@ See the License for the specific language governing permissions and
 limitations under the License.
 */
 
-// Package v1alpha1 contains API Schema definitions for the  v1alpha1 API group
+// Package v1alpha2 contains API Schema definitions for the  v1alpha2 API group
 // +kubebuilder:object:generate=true
 // +groupName=flux-framework.org
-package v1alpha1
+package v1alpha2
 
 import (
 	"k8s.io/apimachinery/pkg/runtime/schema"
@@ -26,7 +26,7 @@ import (
 
 var (
 	// GroupVersion is group version used to register these objects
-	GroupVersion = schema.GroupVersion{Group: "flux-framework.org", Version: "v1alpha1"}
+	GroupVersion = schema.GroupVersion{Group: "flux-framework.org", Version: "v1alpha2"}
 
 	// SchemeBuilder is used to add go types to the GroupVersionKind scheme
 	SchemeBuilder = &scheme.Builder{GroupVersion: GroupVersion}