Skip to content

initial tboard support #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 3 commits into
base: codeflare
Choose a base branch
from
Draft

initial tboard support #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0d9d0b1
feat: added mlflow server
atinsood Jul 21, 2022
2f0f683
initial tboard support
atinsood Jul 22, 2022
2059402
Merge branch 'codeflare' into tboard_support
atinsood Jul 22, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
53 changes: 53 additions & 0 deletions deploy/charts/ray/templates/operator_cluster_scoped.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,6 +83,53 @@ spec:
spec:
serviceAccountName: ray-operator-serviceaccount
containers:
{{- if (.Values.tensorboard.enable) }}
- name: tensorboard
command: ["/bin/sh", "-c"]
args: ["tensorboard --logdir", {{ .Values.tensorboard.path }}]
imagePullPolicy: IfNotPresent
image: guidebooks/tensorboard
env:
- name: TBOARD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
- name: AWS_ACCESS_KEY_ID
valueFrom:
secretKeyRef:
name: {{ .Values.tensorboard.secret }}
key: S3_ACCESS_KEY_ID
- name: AWS_SECRET_ACCESS_KEY
valueFrom:
secretKeyRef:
name: {{ .Values.tensorboard.secret }}
key: S3_SECRET_ACCESS_KEY
- name: AWS_REGION
valueFrom:
secretKeyRef:
name: {{ .Values.tensorboard.secret }}
key: S3_REGION
resources:
requests:
cpu: 1
memory: 2Gi
#ephemeral-storage: 1Gi
limits:
memory: 4Gi
cpu: 2
ports:
- name: tboard
containerPort: 6006
protocol: TCP
livenessProbe:
httpGet:
path: /
port: tboard
readinessProbe:
httpGet:
path: /
port: tboard
{{- end }}
- name: mlflow-server
imagePullPolicy: IfNotPresent
image: guidebooks/mlflow
Expand Down Expand Up @@ -132,4 +179,10 @@ spec:
protocol: TCP
port: 9080
targetPort: http
{{- if (.Values.tensorboard.enable) }}
- name: tboard
protocol: TCP
port: 6066
targetPort: tboard
{{- end }}
{{- end }}
55 changes: 55 additions & 0 deletions deploy/charts/ray/templates/operator_namespaced.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,6 +69,7 @@ apiVersion: apps/v1
kind: Deployment
metadata:
name: monitoring
namespace: {{ .Values.operatorNamespace }}
spec:
replicas: 1
selector:
Expand All @@ -83,6 +84,53 @@ spec:
spec:
serviceAccountName: ray-operator-serviceaccount
containers:
{{- if (.Values.tensorboard.enable) }}
- name: tensorboard
command: ["/bin/sh", "-c"]
args: ["tensorboard --logdir", {{ .Values.tensorboard.path }}]
imagePullPolicy: IfNotPresent
image: guidebooks/tensorboard
env:
- name: TBOARD_NAMESPACE
valueFrom:
fieldRef:
fieldPath: metadata.namespace
- name: AWS_ACCESS_KEY_ID
valueFrom:
secretKeyRef:
name: {{ .Values.tensorboard.secret }}
key: S3_ACCESS_KEY_ID
- name: AWS_SECRET_ACCESS_KEY
valueFrom:
secretKeyRef:
name: {{ .Values.tensorboard.secret }}
key: S3_SECRET_ACCESS_KEY
- name: AWS_REGION
valueFrom:
secretKeyRef:
name: {{ .Values.tensorboard.secret }}
key: S3_REGION
resources:
requests:
cpu: 1
memory: 2Gi
#ephemeral-storage: 1Gi
limits:
memory: 4Gi
cpu: 2
ports:
- name: tboard
containerPort: 6006
protocol: TCP
livenessProbe:
httpGet:
path: /
port: tboard
readinessProbe:
httpGet:
path: /
port: tboard
{{- end }}
- name: mlflow-server
imagePullPolicy: IfNotPresent
image: guidebooks/mlflow
Expand Down Expand Up @@ -122,6 +170,7 @@ apiVersion: v1
kind: Service
metadata:
name: monitoring-service
namespace: {{ .Values.operatorNamespace }}
spec:
selector:
component: mlflow
Expand All @@ -131,4 +180,10 @@ spec:
protocol: TCP
port: 9080
targetPort: http
{{- if (.Values.tensorboard.enable) }}
- name: tboard
protocol: TCP
port: 6066
targetPort: tboard
{{- end }}
{{- end }}
3 changes: 3 additions & 0 deletions deploy/charts/ray/values.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,3 +109,6 @@ operatorNamespace: default
# by the operator. In other words, the images specified under the fields `operatorImage` and `image`
# should carry matching Ray versions.
operatorImage: rayproject/ray:latest

# non ray related values, specific to monitoring
tensorboard.enable: false