feat(helm): In helm add update strategy value for deployments.

.github/workflows/kubernetes-charts-build.yaml

@@ -1,11 +1,19 @@
 name: Kubernetes - Lint, Test, and Publish Helm Charts
 
-on: pull_request
+on:
+  push:
+    branches: [ main ]
+    pull_request:
+      paths:
+      - 'deployment/kubernetes/**'
+      - '.github/workflows/kubernetes**'
+    tags:
+      - 'v*.*.*'  # e.g., v0.1.1
+
 defaults:
   run:
     working-directory: ./deployment/kubernetes
 
-
 jobs:
   helm-lint-test:
     runs-on: ubuntu-latest
@@ -17,9 +25,9 @@ jobs:
           fetch-depth: 0
 
       - name: Set up Helm
-        uses: azure/setup-helm@v4.2.0
+        uses: azure/setup-helm@v4.3.0
         with:
-          version: v3.17.0
+          version: v3.18.3
 
       - uses: actions/setup-python@v5.3.0
         with:

.github/workflows/observability-docker.yml

@@ -2,8 +2,11 @@ name: ci-build
 
 on:
   push:
-    branches:
-      - '**'
+    branches: [ main ]
+    pull_request:
+      paths:
+      - 'observability/**'
+      - '.github/workflows/observability**'
     tags:
       - 'v*.*.*'  # e.g., v0.1.1
 

deployment/kubernetes/charts/medcat-service-helm/templates/deployment.yaml

@@ -11,6 +11,7 @@ spec:
   selector:
     matchLabels:
       {{- include "medcat-service.selectorLabels" . | nindent 6 }}
+  strategy: {{ toYaml .Values.updateStrategy | nindent 4 }}
   template:
     metadata:
       {{- with .Values.podAnnotations }}

deployment/kubernetes/charts/medcat-service-helm/values.yaml

@@ -31,6 +31,19 @@ env:
   # DEID_MODE: true
   # DEID_REDACT: true
 
+  # Set SERVER_GUNICORN_MAX_REQUESTS to a high number instead of the default 1000. Trust k8s instead to restart pod when needed.
+  SERVER_GUNICORN_MAX_REQUESTS: 1000000
+
+  # Recommended env vars to set to try to limit to 1 CPU for scaling
+  # OMP_NUM_THREADS: "1"
+  # OPENBLAS_NUM_THREADS: "1"
+  # MKL_NUM_THREADS: "1"
+  # VECLIB_MAXIMUM_THREADS: "1"
+  # NUMEXPR_NUM_THREADS: "1"
+  # TOKENIZERS_PARALLELISM: "false"
+  # PYTORCH_ENABLE_MPS_FALLBACK: "1"
+  # SERVER_GUNICORN_EXTRA_ARGS: "--worker-connections 1 --backlog 1"
+
 # Enable downloading of public models using wget on startup. Model will be downloaded to /models/<name> and used for APP_MEDCAT_MODEL_PACK
 model: {}
   # Public URL to download a model pack from
@@ -44,6 +57,14 @@ imagePullSecrets: []
 nameOverride: ""
 fullnameOverride: ""
 
+updateStrategy:
+  # Used for Kubernetes deployment .spec.strategy.type. Allowed values are "Recreate" or "RollingUpdate".
+  type: RollingUpdate
+  # RollingUpdate default options example
+  # rollingUpdate:
+  #   maxSurge: 25%
+  #   maxUnavailable: 25%
+
 # This section builds out the service account more information can be found here: https://kubernetes.io/docs/concepts/security/service-accounts/
 serviceAccount:
   # Specifies whether a service account should be created
@@ -108,11 +129,11 @@ resources: {}
   # resources, such as Minikube. If you do want to specify resources, uncomment the following
   # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
   # limits:
-  #   cpu: 100m
-  #   memory: 128Mi
+  #   cpu: 2 # Note one general k8s recommendation is to leave CPU limit unset
+  #   memory: 4Gi
   # requests:
-  #   cpu: 100m
-  #   memory: 128Mi
+  #   cpu: 1
+  #   memory: 2Gi
 
 # This is to setup the liveness and readiness probes more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/
 livenessProbe:
@@ -129,6 +150,7 @@ startupProbe:
     port: http
   failureThreshold: 30
   periodSeconds: 10
+  initialDelaySeconds: 2
 
 # This section is for setting up autoscaling more information can be found here: https://kubernetes.io/docs/concepts/workloads/autoscaling/
 autoscaling:

deployment/kubernetes/charts/medcat-trainer-helm/templates/medcat-trainer-deployment.yaml

@@ -13,6 +13,7 @@ spec:
     matchLabels:
       {{- include "medcat-trainer-helm.selectorLabels" . | nindent 6 }}
       app.kubernetes.io/component: medcat-trainer
+  strategy: {{ toYaml .Values.updateStrategy | nindent 4 }}
   template:
     metadata:
       {{- with .Values.podAnnotations }}

deployment/kubernetes/charts/medcat-trainer-helm/templates/nginx-deployment.yaml

@@ -13,6 +13,7 @@ spec:
     matchLabels:
       {{- include "medcat-trainer-helm.selectorLabels" . | nindent 6 }}
       app.kubernetes.io/component: nginx
+  strategy: {{ toYaml .Values.nginxUpdateStrategy | nindent 4 }}
   template:
     metadata:
       {{- with .Values.podAnnotations }}

deployment/kubernetes/charts/medcat-trainer-helm/values.yaml

@@ -111,6 +111,14 @@ imagePullSecrets: []
 nameOverride: ""
 fullnameOverride: ""
 
+updateStrategy:
+  # Used for Kubernetes deployment .spec.strategy.type. Allowed values are "Recreate" or "RollingUpdate".
+  type: RollingUpdate
+
+nginxUpdateStrategy:
+  # Used for Kubernetes deployment .spec.strategy.type. Allowed values are "Recreate" or "RollingUpdate".
+  type: RollingUpdate
+
 # This section builds out the service account more information can be found here: https://kubernetes.io/docs/concepts/security/service-accounts/
 serviceAccount:
   # Specifies whether a service account should be created