Add juicefsruntime dataload function #1539
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,4 @@ | ||
| ### 0.1.0 | ||
|
|
||
| - Support parallel prefetch job | ||
| - Support configurations by setting values |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,23 @@ | ||
| apiVersion: v2 | ||
| name: fluid-dataloader | ||
| description: A Helm chart for Fluid to prefetch data | ||
|
|
||
| # A chart can be either an 'application' or a 'library' chart. | ||
| # | ||
| # Application charts are a collection of templates that can be packaged into versioned archives | ||
| # to be deployed. | ||
| # | ||
| # Library charts provide useful utilities or functions for the chart developer. They're included as | ||
| # a dependency of application charts to inject those utilities and functions into the rendering | ||
| # pipeline. Library charts do not define any templates and therefore cannot be deployed. | ||
| type: application | ||
|
|
||
| # This is the chart version. This version number should be incremented each time you make changes | ||
| # to the chart and its templates, including the app version. | ||
| # Versions are expected to follow Semantic Versioning (https://semver.org/) | ||
| version: 0.1.0 | ||
|
|
||
| # This is the version number of the application being deployed. This version number should be | ||
| # incremented each time you make changes to the application. Versions are not expected to | ||
| # follow Semantic Versioning. They should reflect the version the application is using. | ||
| appVersion: 0.1.0 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,33 @@ | ||
| apiVersion: v1 | ||
| kind: ConfigMap | ||
| metadata: | ||
| name: {{ printf "%s-data-load-script" .Release.Name }} | ||
| labels: | ||
| release: {{ .Release.Name }} | ||
| role: dataload-job | ||
| data: | ||
| dataloader.distributedLoad: | | ||
| #!/usr/bin/env bash | ||
| set -xe | ||
|
|
||
| function main() { | ||
| paths="$DATA_PATH" | ||
| paths=(${paths//:/ }) | ||
|
|
||
| podNames="$POD_NAMES" | ||
| podNames=(${podNames//:/ }) | ||
|
|
||
| ns="$POD_NAMESPACE" | ||
| for((i=0;i<${#podNames[@]};i++)) do | ||
| local pod="${podNames[i]}" | ||
|
|
||
| for((j=0;j<${#paths[@]};j++)) do | ||
| echo -e "juicefs warmup on $pod ${paths[j]} starts" | ||
| /usr/local/bin/kubectl -n $ns exec -it $pod -- $COMMAND | ||
| /usr/local/bin/kubectl -n $ns exec -it $pod -- juicefs warmup $MOUNTPATH${paths[j]} | ||
| /usr/local/bin/kubectl -n $ns exec -it $pod -- umount $MOUNTPATH | ||
| echo -e "juicefs warmup on $pod ${paths[j]} ends" | ||
| done | ||
| done | ||
| } | ||
| main "$@" | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,146 @@ | ||
| # .Release.Name will be used to decide which dataset will be preload | ||
| # .Release.Name should be like `<pvc-name>-load`(e.g. hbase-load for a PersistentVolumeClaim named `hbase`) | ||
| # TODO: the length of .Release.Name won't exceed 53(limited by Helm), which means length of `<pvc-name>` can't exceed 48. This might be a problem. | ||
| {{/* {{ $datasetName := "" -}}*/}} | ||
| {{/* {{- $randomSuffix := "" -}}*/}} | ||
| {{/* {{- if regexMatch "^[A-Za-z0-9._-]+-load-[A-Za-z0-9]{5}$" .Release.Name -}}*/}} | ||
| {{/* {{- $arr := regexSplit "-load-" .Release.Name -1 -}}*/}} | ||
| {{/* {{- $datasetName = first $arr -}}*/}} | ||
| {{/* {{- $randomSuffix = last $arr -}}*/}} | ||
| {{/* {{- else -}}*/}} | ||
| {{/* {{- printf "Illegal release name. Should be like <dataset-name>-load-<suffix-length-5>. Current name: %s" .Release.Name | fail -}}*/}} | ||
| {{/* {{- end }}*/}} | ||
| apiVersion: batch/v1 | ||
| kind: Job | ||
| metadata: | ||
| name: {{ printf "%s-job" .Release.Name }} | ||
| labels: | ||
| release: {{ .Release.Name }} | ||
| role: dataload-job | ||
| app: juicefs | ||
| targetDataset: {{ required "targetDataset should be set" .Values.dataloader.targetDataset }} | ||
| spec: | ||
| backoffLimit: {{ .Values.dataloader.backoffLimit | default "3" }} | ||
| completions: 1 | ||
| parallelism: 1 | ||
| template: | ||
| metadata: | ||
| name: {{ printf "%s-loader" .Release.Name }} | ||
| labels: | ||
| release: {{ .Release.Name }} | ||
| role: dataload-pod | ||
| app: juicefs | ||
| targetDataset: {{ required "targetDataset should be set" .Values.dataloader.targetDataset }} | ||
| spec: | ||
| restartPolicy: OnFailure | ||
| {{- range $key, $val := .Values.dataloader.options }} | ||
| {{- if eq $key "runtimeName" }} | ||
| serviceAccountName: {{ printf "%s-loader" $val | quote }} | ||
| {{- end }} | ||
| {{- end }} | ||
| containers: | ||
| - name: dataloader | ||
| image: {{ required "Dataloader image should be set" .Values.dataloader.image }} | ||
| imagePullPolicy: IfNotPresent | ||
| command: ["/bin/sh", "-c"] | ||
| args: ["/scripts/juicefs_dataload.sh"] | ||
| {{- $targetPaths := "" }} | ||
| {{- range .Values.dataloader.targetPaths }} | ||
| {{- $targetPaths = cat $targetPaths (required "Path must be set" .path) ":" }} | ||
| {{- end }} | ||
| {{- $targetPaths = $targetPaths | nospace | trimSuffix ":" }} | ||
|
|
||
| {{- $pathReplicas := ""}} | ||
| {{- range .Values.dataloader.targetPaths }} | ||
| {{- $pathReplicas = cat $pathReplicas ( default 1 .replicas ) ":"}} | ||
| {{- end }} | ||
| {{- $pathReplicas = $pathReplicas | nospace | trimSuffix ":"}} | ||
|
|
||
| env: | ||
| - name: STORAGE_ADDRESS | ||
| valueFrom: | ||
| fieldRef: | ||
| fieldPath: status.podIP | ||
| - name: CACHEDIR2 | ||
| value: /test | ||
| {{- range $key, $val := .Values.dataloader.options }} | ||
| {{- if eq $key "cachedir" }} | ||
| - name: CACHEDIR | ||
| value: {{ $val | quote }} | ||
| {{- end }} | ||
| {{- if eq $key "mountpath" }} | ||
| - name: MOUNTPATH | ||
| value: {{ $val | quote }} | ||
| {{- end }} | ||
| {{- if eq $key "command" }} | ||
| - name: COMMAND | ||
| value: {{ $val | quote }} | ||
| {{- end }} | ||
| {{- end }} | ||
| - name: DATA_PATH | ||
| value: {{ $targetPaths | quote }} | ||
| - name: PATH_REPLICAS | ||
| value: {{ $pathReplicas | quote }} | ||
| {{- range $key, $val := .Values.dataloader.options }} | ||
| {{- if eq $key "podNames" }} | ||
| - name: POD_NAMES | ||
| value: {{ $val | quote }} | ||
| {{- end }} | ||
| {{- end }} | ||
| - name: POD_NAMESPACE | ||
| value: {{ .Release.Namespace | quote }} | ||
| envFrom: | ||
| - configMapRef: | ||
| name: {{ required "targetDataset should be set" .Values.dataloader.targetDataset }}-juicefs-values | ||
| securityContext: | ||
| privileged: true | ||
| volumeMounts: | ||
| - mountPath: /scripts | ||
| name: data-load-script | ||
| {{- range .Values.dataloader.targetPaths }} | ||
| {{- if .fluidNative }} | ||
| - mountPath: {{ .path | trimAll "/" | replace "/" "-" | printf "/data/%s"}} | ||
| name: {{ .path | trimAll "/" | replace "/" "-" | printf "native-%s"}} | ||
| {{- end }} | ||
| {{- end }} | ||
| {{- range $key, $val := .Values.dataloader.options }} | ||
| {{- if eq $key "cachedir" }} | ||
| - mountPath: {{ $val | quote }} | ||
| {{- end }} | ||
| {{- end }} | ||
| name: cachedir | ||
| {{- range $key, $val := .Values.dataloader.options }} | ||
| {{- if eq $key "mountpath" }} | ||
| - mountPath: {{ $val | quote }} | ||
| {{- end }} | ||
| {{- end }} | ||
| name: mountpath1 | ||
| volumes: | ||
| - name: data-load-script | ||
| configMap: | ||
| name: {{ printf "%s-data-load-script" .Release.Name }} | ||
| items: | ||
| - key: dataloader.distributedLoad | ||
| path: juicefs_dataload.sh | ||
| mode: 365 | ||
| {{- range .Values.dataloader.targetPaths }} | ||
| {{- if .fluidNative }} | ||
| - name: {{ .path | trimAll "/" | replace "/" "-" | printf "native-%s"}} | ||
| hostPath: | ||
| path: {{ .path }} | ||
| {{- end }} | ||
| {{- end }} | ||
| - name: cachedir | ||
| {{- range $key, $val := .Values.dataloader.options }} | ||
| {{- if eq $key "cachedir" }} | ||
| hostPath: | ||
| path: {{ $val | quote }} | ||
| {{- end }} | ||
| {{- end }} | ||
| - name: mountpath1 | ||
| {{- range $key, $val := .Values.dataloader.options }} | ||
| {{- if eq $key "mountpath" }} | ||
| hostPath: | ||
| path: {{ $val | quote }} | ||
| {{- end }} | ||
| {{- end }} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,34 @@ | ||
| # Default values for fluid-dataloader. | ||
| # This is a YAML-formatted file. | ||
| # Declare variables to be passed into your templates. | ||
|
|
||
| dataloader: | ||
| # Optional | ||
| # Default: 3 | ||
| # Description: how many times the prefetch job can fail, i.e. `Job.spec.backoffLimit` | ||
| backoffLimit: 3 | ||
|
|
||
| # Required | ||
| # Description: the dataset that this DataLoad targets | ||
| targetDataset: #imagenet | ||
|
|
||
| # Optional | ||
| # Default: false | ||
| # Description: should load metadata from UFS when doing data load | ||
| loadMetadata: false | ||
|
|
||
| # Optional | ||
| # Default: (path: "/", replicas: 1, fluidNative: false) | ||
| # Description: which paths should the DataLoad load | ||
| targetPaths: | ||
| - path: "/" | ||
| replicas: 1 | ||
| fluidNative: false | ||
|
|
||
| # Required | ||
| # Description: the image that the DataLoad job uses | ||
| image: #<juicefs-image> | ||
|
|
||
| # Optional | ||
| # Description: optional parameter DataLoad job uses | ||
| options: |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,34 @@ | ||
| --- | ||
| apiVersion: rbac.authorization.k8s.io/v1 | ||
| kind: ClusterRole | ||
| metadata: | ||
| name: {{ printf "%s-loader" .Release.Name }} | ||
| rules: | ||
| - apiGroups: | ||
| - "" | ||
| resources: | ||
| - pods | ||
| - pods/exec | ||
| verbs: | ||
| - get | ||
| - create | ||
| - list | ||
| --- | ||
| apiVersion: rbac.authorization.k8s.io/v1 | ||
| kind: ClusterRoleBinding | ||
| metadata: | ||
| name: {{ printf "%s-loader" .Release.Name }} | ||
| roleRef: | ||
| apiGroup: rbac.authorization.k8s.io | ||
| kind: ClusterRole | ||
| name: {{ printf "%s-loader" .Release.Name }} | ||
| subjects: | ||
| - kind: ServiceAccount | ||
| name: {{ printf "%s-loader" .Release.Name }} | ||
| namespace: {{ .Release.Namespace | quote }} | ||
| --- | ||
| apiVersion: v1 | ||
| kind: ServiceAccount | ||
| metadata: | ||
| name: {{ printf "%s-loader" .Release.Name }} | ||
| namespace: {{ .Release.Namespace | quote }} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Will you add
timeoutto avoid the job hang?There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
done