mirror of
https://github.com/clearml/clearml-helm-charts
synced 2025-04-17 01:31:13 +00:00
Compare commits
4 Commits
clearml-5.
...
clearml-5.
| Author | SHA1 | Date | |
|---|---|---|---|
|
a9d57db3a8 | ||
|
|
08b92ba622 | ||
|
|
5b77cf41c2 | ||
|
|
a6db8b4262 |
@@ -2,7 +2,7 @@ apiVersion: v2
|
||||
name: clearml-agent
|
||||
description: MLOps platform Task running agent
|
||||
type: application
|
||||
version: "3.6.0"
|
||||
version: "3.7.0"
|
||||
appVersion: "1.24"
|
||||
kubeVersion: ">= 1.21.0-0 < 1.27.0-0"
|
||||
home: https://clear.ml
|
||||
@@ -21,4 +21,4 @@ keywords:
|
||||
annotations:
|
||||
artifacthub.io/changes: |
|
||||
- kind: added
|
||||
description: support for priorityClass in task pod template
|
||||
description: support for existing rolebindings and clusterrolebindings
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# ClearML Kubernetes Agent
|
||||
|
||||
  
|
||||
  
|
||||
|
||||
MLOps platform Task running agent
|
||||
|
||||
@@ -30,7 +30,9 @@ Kubernetes: `>= 1.21.0-0 < 1.27.0-0`
|
||||
|
||||
| Key | Type | Default | Description |
|
||||
|-----|------|---------|-------------|
|
||||
| agentk8sglue | object | `{"affinity":{},"annotations":{},"apiServerUrlReference":"https://api.clear.ml","basePodTemplate":{"affinity":{},"annotations":{},"env":[],"fileMounts":[],"hostAliases":[],"initContainers":[],"labels":{},"nodeSelector":{},"priorityClassName":"","resources":{},"schedulerName":"","securityContext":{},"tolerations":[],"volumeMounts":[],"volumes":[]},"clearmlcheckCertificate":true,"containerCustomBashScript":"","customBashScript":"","debugMode":false,"defaultContainerImage":"ubuntu:18.04","extraEnvs":[],"fileMounts":[],"fileServerUrlReference":"https://files.clear.ml","image":{"repository":"allegroai/clearml-agent-k8s-base","tag":"1.24-21"},"labels":{},"nodeSelector":{},"queue":"default","replicaCount":1,"securityContext":{},"serviceExistingAccountName":"","taskAsJob":false,"tolerations":[],"volumeMounts":[],"volumes":[],"webServerUrlReference":"https://app.clear.ml"}` | This agent will spawn queued experiments in new pods, a good use case is to combine this with GPU autoscaling nodes. https://github.com/allegroai/clearml-agent/tree/master/docker/k8s-glue |
|
||||
| agentk8sglue | object | `{"additionalClusterRoleBindings":[],"additionalRoleBindings":[],"affinity":{},"annotations":{},"apiServerUrlReference":"https://api.clear.ml","basePodTemplate":{"affinity":{},"annotations":{},"env":[],"fileMounts":[],"hostAliases":[],"initContainers":[],"labels":{},"nodeSelector":{},"priorityClassName":"","resources":{},"schedulerName":"","securityContext":{},"tolerations":[],"volumeMounts":[],"volumes":[]},"clearmlcheckCertificate":true,"containerCustomBashScript":"","customBashScript":"","debugMode":false,"defaultContainerImage":"ubuntu:18.04","extraEnvs":[],"fileMounts":[],"fileServerUrlReference":"https://files.clear.ml","image":{"repository":"allegroai/clearml-agent-k8s-base","tag":"1.24-21"},"labels":{},"nodeSelector":{},"queue":"default","replicaCount":1,"securityContext":{},"serviceExistingAccountName":"","taskAsJob":false,"tolerations":[],"volumeMounts":[],"volumes":[],"webServerUrlReference":"https://app.clear.ml"}` | This agent will spawn queued experiments in new pods, a good use case is to combine this with GPU autoscaling nodes. https://github.com/allegroai/clearml-agent/tree/master/docker/k8s-glue |
|
||||
| agentk8sglue.additionalClusterRoleBindings | list | `[]` | additional existing ClusterRoleBindings |
|
||||
| agentk8sglue.additionalRoleBindings | list | `[]` | additional existing RoleBindings |
|
||||
| agentk8sglue.affinity | object | `{}` | affinity setup for Agent pod (example in values.yaml comments) |
|
||||
| agentk8sglue.annotations | object | `{}` | annotations setup for Agent pod (example in values.yaml comments) |
|
||||
| agentk8sglue.apiServerUrlReference | string | `"https://api.clear.ml"` | Reference to Api server url |
|
||||
|
||||
@@ -86,3 +86,33 @@ roleRef:
|
||||
kind: Role
|
||||
name: {{ include "clearmlAgent.name" . }}-kpa
|
||||
{{- end }}
|
||||
{{- range .Values.agentk8sglue.additionalClusterRoleBindings }}
|
||||
---
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRoleBinding
|
||||
metadata:
|
||||
name: {{ include "clearmlAgent.name" $ }}-kpa-{{ . }}
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: {{ include "clearmlAgent.serviceAccountName" $ }}
|
||||
namespace: {{ $.Release.Namespace }}
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: ClusterRole
|
||||
name: {{ . }}
|
||||
{{- end }}
|
||||
{{- range .Values.agentk8sglue.additionalRoleBindings }}
|
||||
---
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: RoleBinding
|
||||
metadata:
|
||||
name: {{ include "clearmlAgent.name" $ }}-kpa-{{ . }}
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: {{ include "clearmlAgent.serviceAccountName" $ }}
|
||||
namespace: {{ $.Release.Namespace }}
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: Role
|
||||
name: {{ . }}
|
||||
{{- end }}
|
||||
|
||||
@@ -81,6 +81,12 @@ agentk8sglue:
|
||||
securityContext: {}
|
||||
# runAsUser: 1001
|
||||
# fsGroup: 1001
|
||||
# -- additional existing ClusterRoleBindings
|
||||
additionalClusterRoleBindings: []
|
||||
# - privileged
|
||||
# -- additional existing RoleBindings
|
||||
additionalRoleBindings: []
|
||||
# - privileged
|
||||
# -- nodeSelector setup for Agent pod (example in values.yaml comments)
|
||||
nodeSelector: {}
|
||||
# fleet: agent-nodes
|
||||
|
||||
@@ -2,7 +2,7 @@ apiVersion: v2
|
||||
name: clearml
|
||||
description: MLOps platform
|
||||
type: application
|
||||
version: "5.8.0"
|
||||
version: "5.8.3"
|
||||
appVersion: "1.9.2"
|
||||
kubeVersion: ">= 1.21.0-0 < 1.27.0-0"
|
||||
home: https://clear.ml
|
||||
@@ -32,5 +32,5 @@ dependencies:
|
||||
condition: elasticsearch.enabled
|
||||
annotations:
|
||||
artifacthub.io/changes: |
|
||||
- kind: added
|
||||
description: filemount support for apps agent
|
||||
- kind: fixed
|
||||
description: force app agent update
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# ClearML Ecosystem for Kubernetes
|
||||
|
||||
  
|
||||
  
|
||||
|
||||
MLOps platform
|
||||
|
||||
|
||||
@@ -177,6 +177,17 @@ MongoDB Comnnection string
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
|
||||
{{/*
|
||||
MongoDB hotname
|
||||
*/}}
|
||||
{{- define "mongodb.hostname" -}}
|
||||
{{- if eq .Values.mongodb.architecture "standalone" }}
|
||||
{{- printf "%s" "mongodb" }}
|
||||
{{- else }}
|
||||
{{- printf "%s" "mongodb-headless" }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
|
||||
{{/*
|
||||
Redis Service name
|
||||
*/}}
|
||||
|
||||
@@ -61,7 +61,7 @@ spec:
|
||||
done ;
|
||||
{{- end }}
|
||||
{{- if .Values.mongodb.enabled }}
|
||||
while [ $(curl --telnet-option BOGUS --connect-timeout 2 -s "telnet://{{ .Release.Name }}-mongodb:27017" -o /dev/null; echo $?) -ne 49 ] ; do
|
||||
while [ $(curl --telnet-option BOGUS --connect-timeout 2 -s "telnet://{{ .Release.Name }}-{{ include "mongodb.hostname" . }}:27017" -o /dev/null; echo $?) -ne 49 ] ; do
|
||||
echo "waiting for mongodb" ;
|
||||
sleep 5 ;
|
||||
done ;
|
||||
|
||||
@@ -70,7 +70,7 @@ spec:
|
||||
value: "http://{{ include "fileserver.referenceName" . }}:{{ .Values.fileserver.service.port }}"
|
||||
- name: CLEARML_WEB_HOST
|
||||
value: "http://{{ include "webserver.referenceName" . }}:{{ .Values.webserver.service.port }}"
|
||||
- name: CLEARML_AGENT_DEFAULT_BASE_DOCKER
|
||||
- name: CLEARML_DOCKER_IMAGE
|
||||
value: "{{ .Values.enterpriseFeatures.clearmlApplications.basePodImage.repository }}:{{ .Values.enterpriseFeatures.clearmlApplications.basePodImage.tag }}"
|
||||
- name: CLEARML_WORKER_ID
|
||||
value: "apps-agent-1"
|
||||
@@ -83,6 +83,8 @@ spec:
|
||||
value: "apps_queue"
|
||||
- name: CLEARML_AGENT_DISABLE_SSH_MOUNT
|
||||
value: "1"
|
||||
- name: K8S_GLUE_POD_AGENT_INSTALL_ARGS
|
||||
value: " -U"
|
||||
- name: CLEARML_API_ACCESS_KEY
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
|
||||
Reference in New Issue
Block a user