mirror of
https://github.com/clearml/clearml-helm-charts
synced 2025-04-17 01:31:13 +00:00
Compare commits
7 Commits
clearml-2.
...
clearml-2.
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
618a269c97 | ||
|
|
3f215d2d90 | ||
|
|
03223fc1c1 | ||
|
|
898089b7fb | ||
|
|
732bb970aa | ||
|
|
91d45281fa | ||
|
|
28b6e9f4e4 |
@@ -1,12 +1,8 @@
|
||||
# ClearML Helm Charts Library for Kubernetes
|
||||
|
||||
Helm charts provided by [Allegro AI](https://clear.ml), ready to launch on Kubernetes using [Kubernetes Helm](https://github.com/helm/helm).
|
||||
|
||||
## Auto-Magical Experiment Manager & Version Control for AI
|
||||
|
||||
[](https://img.shields.io/badge/license-SSPL-green.svg)
|
||||
[](https://img.shields.io/github/release-pre/allegroai/clearml-server.svg)
|
||||
[](https://img.shields.io/badge/status-beta-yellow.svg)
|
||||
Helm charts provided by [Allegro AI](https://clear.ml), ready to launch on Kubernetes using [Kubernetes Helm](https://github.com/helm/helm).
|
||||
|
||||
## Introduction
|
||||
|
||||
@@ -84,4 +80,4 @@ Additionally, you can always find us at *clearml@allegro.ai*
|
||||
**PRs are always welcomed** :heart: See more details in the ClearML [Guidelines for Contributing](https://github.com/allegroai/clearml-helm-charts/blob/main/CONTRIBUTING.md).
|
||||
|
||||
|
||||
_May the force (and the goddess of learning rates) be with you!_
|
||||
_May the force (and the goddess of learning rates) be with you!_
|
||||
|
||||
@@ -2,8 +2,8 @@ apiVersion: v2
|
||||
name: clearml
|
||||
description: MLOps platform
|
||||
type: application
|
||||
version: "2.0.0"
|
||||
appVersion: "1.1.0"
|
||||
version: "2.2.2"
|
||||
appVersion: "1.1.1"
|
||||
home: https://clear.ml
|
||||
icon: https://raw.githubusercontent.com/allegroai/clearml/master/docs/clearml-logo.svg
|
||||
sources:
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# ClearML Ecosystem for Kubernetes
|
||||
|
||||
  
|
||||
  
|
||||
|
||||
MLOps platform
|
||||
|
||||
@@ -131,6 +131,7 @@ For detailed instructions, see the [Optional Configuration](https://github.com/a
|
||||
| agentGroups.agent-group-cpu.queues | string | `"default"` | |
|
||||
| agentGroups.agent-group-cpu.replicaCount | int | `1` | |
|
||||
| agentGroups.agent-group-cpu.tolerations | list | `[]` | |
|
||||
| agentGroups.agent-group-cpu.updateStrategy | string | `"Recreate"` | |
|
||||
| agentGroups.agent-group-gpu.affinity | object | `{}` | |
|
||||
| agentGroups.agent-group-gpu.agentVersion | string | `""` | |
|
||||
| agentGroups.agent-group-gpu.awsAccessKeyId | string | `nil` | |
|
||||
@@ -153,6 +154,7 @@ For detailed instructions, see the [Optional Configuration](https://github.com/a
|
||||
| agentGroups.agent-group-gpu.queues | string | `"default"` | |
|
||||
| agentGroups.agent-group-gpu.replicaCount | int | `0` | |
|
||||
| agentGroups.agent-group-gpu.tolerations | list | `[]` | |
|
||||
| agentGroups.agent-group-gpu.updateStrategy | string | `"Recreate"` | |
|
||||
| agentservices.affinity | object | `{}` | |
|
||||
| agentservices.agentVersion | string | `""` | |
|
||||
| agentservices.awsAccessKeyId | string | `nil` | |
|
||||
@@ -183,7 +185,7 @@ For detailed instructions, see the [Optional Configuration](https://github.com/a
|
||||
| apiserver.extraEnvs | list | `[]` | |
|
||||
| apiserver.image.pullPolicy | string | `"IfNotPresent"` | |
|
||||
| apiserver.image.repository | string | `"allegroai/clearml"` | |
|
||||
| apiserver.image.tag | string | `"1.1.0"` | |
|
||||
| apiserver.image.tag | string | `"1.1.1"` | |
|
||||
| apiserver.livenessDelay | int | `60` | |
|
||||
| apiserver.nodeSelector | object | `{}` | |
|
||||
| apiserver.podAnnotations | object | `{}` | |
|
||||
@@ -239,7 +241,7 @@ For detailed instructions, see the [Optional Configuration](https://github.com/a
|
||||
| fileserver.extraEnvs | list | `[]` | |
|
||||
| fileserver.image.pullPolicy | string | `"IfNotPresent"` | |
|
||||
| fileserver.image.repository | string | `"allegroai/clearml"` | |
|
||||
| fileserver.image.tag | string | `"1.1.0"` | |
|
||||
| fileserver.image.tag | string | `"1.1.1"` | |
|
||||
| fileserver.nodeSelector | object | `{}` | |
|
||||
| fileserver.podAnnotations | object | `{}` | |
|
||||
| fileserver.replicaCount | int | `1` | |
|
||||
@@ -252,6 +254,9 @@ For detailed instructions, see the [Optional Configuration](https://github.com/a
|
||||
| ingress.annotations | object | `{}` | |
|
||||
| ingress.enabled | bool | `false` | |
|
||||
| ingress.host | string | `""` | |
|
||||
| ingress.hostPrefixApi | string | `"api."` | |
|
||||
| ingress.hostPrefixApp | string | `"app."` | |
|
||||
| ingress.hostPrefixFiles | string | `"files."` | |
|
||||
| ingress.name | string | `"clearml-server-ingress"` | |
|
||||
| ingress.tls.secretName | string | `""` | |
|
||||
| mongodb.architecture | string | `"standalone"` | |
|
||||
@@ -278,7 +283,7 @@ For detailed instructions, see the [Optional Configuration](https://github.com/a
|
||||
| webserver.extraEnvs | list | `[]` | |
|
||||
| webserver.image.pullPolicy | string | `"IfNotPresent"` | |
|
||||
| webserver.image.repository | string | `"allegroai/clearml"` | |
|
||||
| webserver.image.tag | string | `"1.1.0"` | |
|
||||
| webserver.image.tag | string | `"1.1.1"` | |
|
||||
| webserver.nodeSelector | object | `{}` | |
|
||||
| webserver.podAnnotations | object | `{}` | |
|
||||
| webserver.replicaCount | int | `1` | |
|
||||
|
||||
@@ -95,3 +95,48 @@ Create the name of the service account to use
|
||||
{{- default "default" .Values.serviceAccount.name }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
|
||||
{{/*
|
||||
Create the name of the App service to use
|
||||
*/}}
|
||||
{{- define "clearml.serviceApp" -}}
|
||||
{{- if .Values.ingress.enabled }}
|
||||
{{- if .Values.ingress.tls.secretName }}
|
||||
{{- printf "%s%s%s" "https://" .Values.ingress.hostPrefixApp .Values.ingress.host }}
|
||||
{{- else }}
|
||||
{{- printf "%s%s%s" "http://" .Values.ingress.hostPrefixApp .Values.ingress.host }}
|
||||
{{- end }}
|
||||
{{- else }}
|
||||
{{- printf "%s%s%s%s" "http://" (include "clearml.fullname" .) "-webserver:" (.Values.webserver.service.port | quote) }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
|
||||
{{/*
|
||||
Create the name of the Api service to use
|
||||
*/}}
|
||||
{{- define "clearml.serviceApi" -}}
|
||||
{{- if .Values.ingress.enabled }}
|
||||
{{- if .Values.ingress.tls.secretName }}
|
||||
{{- printf "%s%s%s" "https://" .Values.ingress.hostPrefixApi .Values.ingress.host }}
|
||||
{{- else }}
|
||||
{{- printf "%s%s%s" "http://" .Values.ingress.hostPrefixApi .Values.ingress.host }}
|
||||
{{- end }}
|
||||
{{- else }}
|
||||
{{- printf "%s%s%s%s" "http://" (include "clearml.fullname" .) "-apiserver:" (.Values.apiserver.service.port | quote) }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
|
||||
{{/*
|
||||
Create the name of the Files service to use
|
||||
*/}}
|
||||
{{- define "clearml.serviceFiles" -}}
|
||||
{{- if .Values.ingress.enabled }}
|
||||
{{- if .Values.ingress.tls.secretName }}
|
||||
{{- printf "%s%s%s" "https://" .Values.ingress.hostPrefixFiles .Values.ingress.host }}
|
||||
{{- else }}
|
||||
{{- printf "%s%s%s" "http://" .Values.ingress.hostPrefixFiles .Values.ingress.host }}
|
||||
{{- end }}
|
||||
{{- else }}
|
||||
{{- printf "%s%s%s%s" "http://" (include "clearml.fullname" .) "-fileserver:" (.Values.fileserver.service.port | quote) }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
|
||||
@@ -9,6 +9,8 @@ metadata:
|
||||
{{- include "clearml.labels" $ | nindent 4 }}
|
||||
spec:
|
||||
replicas: {{ .replicaCount }}
|
||||
strategy:
|
||||
type: {{ .updateStrategy }}
|
||||
selector:
|
||||
matchLabels:
|
||||
{{- include "clearml.selectorLabelsAgent" $ | nindent 6 }}
|
||||
@@ -38,7 +40,7 @@ spec:
|
||||
- -c
|
||||
- >
|
||||
set -x;
|
||||
while [ $(curl -sw '%{http_code}' "http://{{ include "clearml.fullname" $ }}-apiserver:{{ $.Values.apiserver.service.port }}/debug.ping" -o /dev/null) -ne 200 ] ; do
|
||||
while [ $(curl -sw '%{http_code}' "{{ include "clearml.serviceApi" $ }}/debug.ping" -o /dev/null) -ne 200 ] ; do
|
||||
echo "waiting for apiserver" ;
|
||||
sleep 5 ;
|
||||
done
|
||||
@@ -54,11 +56,11 @@ spec:
|
||||
{{ .nvidiaGpusPerAgent }}
|
||||
env:
|
||||
- name: CLEARML_API_HOST
|
||||
value: 'http://{{ include "clearml.fullname" $ }}-apiserver:{{ $.Values.apiserver.service.port }}'
|
||||
value: {{ include "clearml.serviceApi" $ }}
|
||||
- name: CLEARML_WEB_HOST
|
||||
value: 'http://{{ include "clearml.fullname" $ }}-webserver:{{ $.Values.webserver.service.port }}'
|
||||
value: {{ include "clearml.serviceApp" $ }}
|
||||
- name: CLEARML_FILES_HOST
|
||||
value: 'http://{{ include "clearml.fullname" $ }}-fileserver:{{ $.Values.fileserver.service.port }}'
|
||||
value: {{ include "clearml.serviceFiles" $ }}
|
||||
- name: CLEARML_AGENT_GIT_USER
|
||||
value: {{ .clearmlGitUser}}
|
||||
- name: CLEARML_AGENT_GIT_PASS
|
||||
@@ -91,6 +93,13 @@ spec:
|
||||
python3 -m pip install -U pip ;
|
||||
python3 -m pip install clearml-agent{{ .agentVersion}} ;
|
||||
CLEARML_AGENT_K8S_HOST_MOUNT=/root/.clearml:/root/.clearml clearml-agent daemon --queue {{ .queues}}"
|
||||
{{ if .clearmlConfig }}
|
||||
volumeMounts:
|
||||
- name: agent-clearml-conf-volume
|
||||
mountPath: /root/clearml.conf
|
||||
subPath: clearml.conf
|
||||
readOnly: true
|
||||
{{- end }}
|
||||
{{- with .nodeSelector }}
|
||||
nodeSelector:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
|
||||
@@ -30,7 +30,7 @@ spec:
|
||||
- -c
|
||||
- >
|
||||
set -x;
|
||||
while [ $(curl -sw '%{http_code}' "http://{{ include "clearml.fullname" . }}-apiserver:{{ .Values.apiserver.service.port }}/debug.ping" -o /dev/null) -ne 200 ] ; do
|
||||
while [ $(curl -sw '%{http_code}' "{{ include "clearml.serviceApi" $ }}/debug.ping" -o /dev/null) -ne 200 ] ; do
|
||||
echo "waiting for apiserver" ;
|
||||
sleep 5 ;
|
||||
done
|
||||
@@ -42,7 +42,7 @@ spec:
|
||||
- name: CLEARML_HOST_IP
|
||||
value: {{ .Values.agentservices.clearmlHostIp }}
|
||||
- name: CLEARML_API_HOST
|
||||
value: "http://{{ include "clearml.fullname" . }}-apiserver:{{ .Values.apiserver.service.port }}"
|
||||
value: {{ include "clearml.serviceApi" $ }}
|
||||
- name: CLEARML_WEB_HOST
|
||||
value: {{ .Values.agentservices.clearmlWebHost }}
|
||||
- name: CLEARML_FILES_HOST
|
||||
|
||||
33
charts/clearml/templates/ingress-api.yaml
Normal file
33
charts/clearml/templates/ingress-api.yaml
Normal file
@@ -0,0 +1,33 @@
|
||||
{{- if .Values.ingress.enabled -}}
|
||||
{{- $fullName := include "clearml.fullname" . -}}
|
||||
{{- if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion -}}
|
||||
apiVersion: networking.k8s.io/v1beta1
|
||||
{{- else -}}
|
||||
apiVersion: extensions/v1beta1
|
||||
{{- end }}
|
||||
kind: Ingress
|
||||
metadata:
|
||||
name: {{ $fullName }}-api
|
||||
labels:
|
||||
{{- include "clearml.labels" . | nindent 4 }}
|
||||
{{- with .Values.ingress.annotations }}
|
||||
annotations:
|
||||
{{- toYaml . | nindent 4 }}
|
||||
{{- end }}
|
||||
spec:
|
||||
{{- if .Values.ingress.tls.secretName }}
|
||||
tls:
|
||||
- hosts:
|
||||
- "{{ .Values.ingress.hostPrefixApi }}{{ .Values.ingress.host }}"
|
||||
secretName: {{ .Values.ingress.tls.secretName }}
|
||||
{{- end }}
|
||||
rules:
|
||||
- host: "{{ .Values.ingress.hostPrefixApi }}{{ .Values.ingress.host }}"
|
||||
http:
|
||||
paths:
|
||||
- path: "/"
|
||||
pathType: Prefix
|
||||
backend:
|
||||
serviceName: {{ include "clearml.fullname" . }}-apiserver
|
||||
servicePort: {{ .Values.apiserver.service.port }}
|
||||
{{- end }}
|
||||
33
charts/clearml/templates/ingress-app.yaml
Normal file
33
charts/clearml/templates/ingress-app.yaml
Normal file
@@ -0,0 +1,33 @@
|
||||
{{- if .Values.ingress.enabled -}}
|
||||
{{- $fullName := include "clearml.fullname" . -}}
|
||||
{{- if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion -}}
|
||||
apiVersion: networking.k8s.io/v1beta1
|
||||
{{- else -}}
|
||||
apiVersion: extensions/v1beta1
|
||||
{{- end }}
|
||||
kind: Ingress
|
||||
metadata:
|
||||
name: {{ $fullName }}-app
|
||||
labels:
|
||||
{{- include "clearml.labels" . | nindent 4 }}
|
||||
{{- with .Values.ingress.annotations }}
|
||||
annotations:
|
||||
{{- toYaml . | nindent 4 }}
|
||||
{{- end }}
|
||||
spec:
|
||||
{{- if .Values.ingress.tls.secretName }}
|
||||
tls:
|
||||
- hosts:
|
||||
- "{{ .Values.ingress.hostPrefixApp }}{{ .Values.ingress.host }}"
|
||||
secretName: {{ .Values.ingress.tls.secretName }}
|
||||
{{- end }}
|
||||
rules:
|
||||
- host: "{{ .Values.ingress.hostPrefixApp }}{{ .Values.ingress.host }}"
|
||||
http:
|
||||
paths:
|
||||
- path: "/"
|
||||
pathType: Prefix
|
||||
backend:
|
||||
serviceName: {{ include "clearml.fullname" . }}-webserver
|
||||
servicePort: {{ .Values.webserver.service.port }}
|
||||
{{- end }}
|
||||
@@ -7,7 +7,7 @@ apiVersion: extensions/v1beta1
|
||||
{{- end }}
|
||||
kind: Ingress
|
||||
metadata:
|
||||
name: {{ $fullName }}
|
||||
name: {{ $fullName }}-files
|
||||
labels:
|
||||
{{- include "clearml.labels" . | nindent 4 }}
|
||||
{{- with .Values.ingress.annotations }}
|
||||
@@ -18,30 +18,15 @@ spec:
|
||||
{{- if .Values.ingress.tls.secretName }}
|
||||
tls:
|
||||
- hosts:
|
||||
- "app.{{ .Values.ingress.host }}"
|
||||
- "files.{{ .Values.ingress.host }}"
|
||||
- "api.{{ .Values.ingress.host }}"
|
||||
- "{{ .Values.ingress.hostPrefixFiles }}{{ .Values.ingress.host }}"
|
||||
secretName: {{ .Values.ingress.tls.secretName }}
|
||||
{{- end }}
|
||||
rules:
|
||||
- host: "app.{{ .Values.ingress.host }}"
|
||||
- host: "{{ .Values.ingress.hostPrefixFiles }}{{ .Values.ingress.host }}"
|
||||
http:
|
||||
paths:
|
||||
- path: "/*"
|
||||
backend:
|
||||
serviceName: {{ include "clearml.fullname" . }}-webserver
|
||||
servicePort: {{ .Values.webserver.service.port }}
|
||||
- host: "api.{{ .Values.ingress.host }}"
|
||||
http:
|
||||
paths:
|
||||
- path: "/*"
|
||||
backend:
|
||||
serviceName: {{ include "clearml.fullname" . }}-apiserver
|
||||
servicePort: {{ .Values.apiserver.service.port }}
|
||||
- host: "files.{{ .Values.ingress.host }}"
|
||||
http:
|
||||
paths:
|
||||
- path: "/*"
|
||||
- path: "/"
|
||||
pathType: Prefix
|
||||
backend:
|
||||
serviceName: {{ include "clearml.fullname" . }}-fileserver
|
||||
servicePort: {{ .Values.fileserver.service.port }}
|
||||
@@ -5,6 +5,9 @@ ingress:
|
||||
name: clearml-server-ingress
|
||||
annotations: {}
|
||||
host: ""
|
||||
hostPrefixApp: "app."
|
||||
hostPrefixApi: "api."
|
||||
hostPrefixFiles: "files."
|
||||
tls:
|
||||
secretName: ""
|
||||
|
||||
@@ -26,7 +29,7 @@ apiserver:
|
||||
image:
|
||||
repository: "allegroai/clearml"
|
||||
pullPolicy: IfNotPresent
|
||||
tag: "1.1.0"
|
||||
tag: "1.1.1"
|
||||
|
||||
extraEnvs: []
|
||||
|
||||
@@ -67,7 +70,7 @@ fileserver:
|
||||
image:
|
||||
repository: "allegroai/clearml"
|
||||
pullPolicy: IfNotPresent
|
||||
tag: "1.1.0"
|
||||
tag: "1.1.1"
|
||||
|
||||
extraEnvs: []
|
||||
|
||||
@@ -108,7 +111,7 @@ webserver:
|
||||
image:
|
||||
repository: "allegroai/clearml"
|
||||
pullPolicy: IfNotPresent
|
||||
tag: "1.1.0"
|
||||
tag: "1.1.1"
|
||||
|
||||
podAnnotations: {}
|
||||
|
||||
@@ -183,6 +186,7 @@ agentGroups:
|
||||
agent-group-cpu:
|
||||
name: agent-group-cpu
|
||||
replicaCount: 1
|
||||
updateStrategy: Recreate
|
||||
nvidiaGpusPerAgent: 0
|
||||
agentVersion: "" # if set, it *MUST* include comparison operator (e.g. ">=0.16.1")
|
||||
queues: "default" # multiple queues can be specified separated by a space (e.g. "important_jobs default")
|
||||
@@ -215,6 +219,7 @@ agentGroups:
|
||||
agent-group-gpu:
|
||||
name: agent-group-gpu
|
||||
replicaCount: 0
|
||||
updateStrategy: Recreate
|
||||
nvidiaGpusPerAgent: 1
|
||||
agentVersion: "" # if set, it *MUST* include comparison operator (e.g. ">=0.16.1")
|
||||
queues: "default" # multiple queues can be specified separated by a space (e.g. "important_jobs default")
|
||||
|
||||
Reference in New Issue
Block a user