-
Notifications
You must be signed in to change notification settings - Fork 147
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.
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
add gke hyperdisk support #3210
Open
chengcongdu
wants to merge
2
commits into
GoogleCloudPlatform:develop
Choose a base branch
from
chengcongdu:storage
base: develop
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from all commits
Commits
Show all changes
2 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
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 +1,218 @@ | ||
| # Copyright 2024 Google LLC | ||
| # | ||
| # Licensed under the Apache License, Version 2.0 (the "License"); | ||
| # you may not use this file except in compliance with the License. | ||
| # You may obtain a copy of the License at | ||
| # | ||
| # http://www.apache.org/licenses/LICENSE-2.0 | ||
| # | ||
| # Unless required by applicable law or agreed to in writing, software | ||
| # distributed under the License is distributed on an "AS IS" BASIS, | ||
| # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| # See the License for the specific language governing permissions and | ||
| # limitations under the License. | ||
| --- | ||
| blueprint_name: gke-storage-hyperdisk | ||
| vars: | ||
| project_id: ## Set GCP Project ID Here ## | ||
| deployment_name: gke-storage-hyperdisk | ||
| region: us-central1 | ||
| zone: us-central1-c | ||
|
|
||
| # Cidr block containing the IP of the machine calling terraform. | ||
| # The following line must be updated for this example to work. | ||
| authorized_cidr: <your-ip-address>/32 | ||
|
|
||
| deployment_groups: | ||
| - group: primary | ||
| modules: | ||
| - id: network | ||
| source: modules/network/vpc | ||
| settings: | ||
| subnetwork_name: gke-subnet-hyperdisk | ||
| secondary_ranges: | ||
| gke-subnet-hyperdisk: | ||
| - range_name: pods | ||
| ip_cidr_range: 10.4.0.0/14 | ||
| - range_name: services | ||
| ip_cidr_range: 10.0.32.0/20 | ||
|
|
||
| - id: gke_cluster | ||
| source: modules/scheduler/gke-cluster | ||
| use: [network] | ||
| settings: | ||
| enable_persistent_disk_csi: true # enable Hyperdisk for the cluster | ||
| configure_workload_identity_sa: true | ||
| enable_private_endpoint: false # Allows for access from authorized public IPs | ||
| master_authorized_networks: | ||
| - display_name: deployment-machine | ||
| cidr_block: $(vars.authorized_cidr) | ||
| outputs: [instructions] | ||
|
|
||
| ### Set up storage class and persistent volume claim for Hyperdisk ### | ||
| - id: hyperdisk-balanced-setup | ||
| source: modules/file-system/gke-storage | ||
| use: [gke_cluster] | ||
| settings: | ||
| storage_type: Hyperdisk-balanced | ||
| access_mode: ReadWriteOnce | ||
| sc_volume_binding_mode: Immediate | ||
| sc_reclaim_policy: Delete | ||
| sc_topology_zones: [$(vars.zone)] | ||
| pvc_count: 1 | ||
| capacity_gb: 100 | ||
|
|
||
| - id: hyperdisk-throughput-setup | ||
| source: modules/file-system/gke-storage | ||
| use: [gke_cluster] | ||
| settings: | ||
| storage_type: Hyperdisk-throughput | ||
| access_mode: ReadWriteOnce | ||
| sc_volume_binding_mode: Immediate | ||
| sc_reclaim_policy: Delete | ||
| sc_topology_zones: [$(vars.zone)] | ||
| pvc_count: 1 | ||
| capacity_gb: 5000 | ||
|
|
||
| - id: hyperdisk-extreme-setup | ||
| source: modules/file-system/gke-storage | ||
| use: [gke_cluster] | ||
| settings: | ||
| storage_type: Hyperdisk-extreme | ||
| access_mode: ReadWriteOnce | ||
| sc_volume_binding_mode: Immediate | ||
| sc_reclaim_policy: Delete | ||
| sc_topology_zones: [$(vars.zone)] | ||
| pvc_count: 1 | ||
| capacity_gb: 100 | ||
|
|
||
| - id: sample-pool | ||
| source: modules/compute/gke-node-pool | ||
| use: [gke_cluster] | ||
| settings: | ||
| name: sample-pool | ||
| zones: [$(vars.zone)] | ||
| machine_type: c3-standard-88 # Hyperdisk-extreme required C3 machine with 88 or more vCPUs | ||
|
|
||
| # Train a TensorFlow model with Keras and Hyperdisk Balanced on GKE | ||
| # Tutorial: https://cloud.google.com/parallelstore/docs/tensorflow-sample | ||
| - id: hyperdisk-balanced-job | ||
| source: modules/compute/gke-job-template | ||
| use: | ||
| - gke_cluster | ||
| - hyperdisk-balanced-setup | ||
| settings: | ||
| name: tensorflow | ||
| image: jupyter/tensorflow-notebook@sha256:173f124f638efe870bb2b535e01a76a80a95217e66ed00751058c51c09d6d85d | ||
| security_context: # to make sure the job have enough access to execute the jobs and r/w from hyperdisk | ||
| - key: runAsUser | ||
| value: 1000 | ||
| - key: runAsGroup | ||
| value: 100 | ||
| - key: fsGroup | ||
| value: 100 | ||
| command: | ||
| - bash | ||
| - -c | ||
| - | | ||
| pip install transformers datasets | ||
| python - <<EOF | ||
| from datasets import load_dataset | ||
| dataset = load_dataset("glue", "cola", cache_dir='/data/hyperdisk-balanced-pvc-0') | ||
| dataset = dataset["train"] | ||
| from transformers import AutoTokenizer | ||
| import numpy as np | ||
| tokenizer = AutoTokenizer.from_pretrained("bert-base-cased") | ||
| tokenized_data = tokenizer(dataset["sentence"], return_tensors="np", padding=True) | ||
| tokenized_data = dict(tokenized_data) | ||
| labels = np.array(dataset["label"]) | ||
| from transformers import TFAutoModelForSequenceClassification | ||
| from tensorflow.keras.optimizers import Adam | ||
| model = TFAutoModelForSequenceClassification.from_pretrained("bert-base-cased") | ||
| model.compile(optimizer=Adam(3e-5)) | ||
| model.fit(tokenized_data, labels) | ||
| EOF | ||
| node_count: 1 | ||
| outputs: [instructions] | ||
|
|
||
| # Train a TensorFlow model with Keras and Hyperdisk Extreme on GKE | ||
| # Tutorial: https://cloud.google.com/parallelstore/docs/tensorflow-sample | ||
| - id: hyperdisk-extreme-job | ||
| source: modules/compute/gke-job-template | ||
| use: | ||
| - gke_cluster | ||
| - hyperdisk-extreme-setup | ||
| settings: | ||
| name: tensorflow | ||
| image: jupyter/tensorflow-notebook@sha256:173f124f638efe870bb2b535e01a76a80a95217e66ed00751058c51c09d6d85d | ||
| security_context: # to make sure the job have enough access to execute the jobs and r/w from hyperdisk | ||
| - key: runAsUser | ||
| value: 1000 | ||
| - key: runAsGroup | ||
| value: 100 | ||
| - key: fsGroup | ||
| value: 100 | ||
| command: | ||
| - bash | ||
| - -c | ||
| - | | ||
| pip install transformers datasets | ||
| python - <<EOF | ||
| from datasets import load_dataset | ||
| dataset = load_dataset("glue", "cola", cache_dir='/data/hyperdisk-extreme-pvc-0') | ||
| dataset = dataset["train"] | ||
| from transformers import AutoTokenizer | ||
| import numpy as np | ||
| tokenizer = AutoTokenizer.from_pretrained("bert-base-cased") | ||
| tokenized_data = tokenizer(dataset["sentence"], return_tensors="np", padding=True) | ||
| tokenized_data = dict(tokenized_data) | ||
| labels = np.array(dataset["label"]) | ||
| from transformers import TFAutoModelForSequenceClassification | ||
| from tensorflow.keras.optimizers import Adam | ||
| model = TFAutoModelForSequenceClassification.from_pretrained("bert-base-cased") | ||
| model.compile(optimizer=Adam(3e-5)) | ||
| model.fit(tokenized_data, labels) | ||
| EOF | ||
| node_count: 1 | ||
| outputs: [instructions] | ||
|
|
||
| # Train a TensorFlow model with Keras and Hyperdisk Throughput on GKE | ||
| # Tutorial: https://cloud.google.com/parallelstore/docs/tensorflow-sample | ||
| - id: hyperdisk-throughput-job | ||
| source: modules/compute/gke-job-template | ||
| use: | ||
| - gke_cluster | ||
| - hyperdisk-throughput-setup | ||
| settings: | ||
| name: tensorflow | ||
| image: jupyter/tensorflow-notebook@sha256:173f124f638efe870bb2b535e01a76a80a95217e66ed00751058c51c09d6d85d | ||
| security_context: # to make sure the job have enough access to execute the jobs and r/w from hyperdisk | ||
| - key: runAsUser | ||
| value: 1000 | ||
| - key: runAsGroup | ||
| value: 100 | ||
| - key: fsGroup | ||
| value: 100 | ||
| command: | ||
| - bash | ||
| - -c | ||
| - | | ||
| pip install transformers datasets | ||
| python - <<EOF | ||
| from datasets import load_dataset | ||
| dataset = load_dataset("glue", "cola", cache_dir='/data/hyperdisk-throughput-pvc-0') | ||
| dataset = dataset["train"] | ||
| from transformers import AutoTokenizer | ||
| import numpy as np | ||
| tokenizer = AutoTokenizer.from_pretrained("bert-base-cased") | ||
| tokenized_data = tokenizer(dataset["sentence"], return_tensors="np", padding=True) | ||
| tokenized_data = dict(tokenized_data) | ||
| labels = np.array(dataset["label"]) | ||
| from transformers import TFAutoModelForSequenceClassification | ||
| from tensorflow.keras.optimizers import Adam | ||
| model = TFAutoModelForSequenceClassification.from_pretrained("bert-base-cased") | ||
| model.compile(optimizer=Adam(3e-5)) | ||
| model.fit(tokenized_data, labels) | ||
| EOF | ||
| node_count: 1 | ||
| outputs: [instructions] | ||
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
15 changes: 15 additions & 0 deletions
15
modules/file-system/gke-storage/persistent-volume-claim/hyperdisk-balanced-pvc.yaml.tftpl
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 +1,15 @@ | ||
| apiVersion: v1 | ||
| kind: PersistentVolumeClaim | ||
| metadata: | ||
| name: ${pvc_name} | ||
| labels: | ||
| %{~ for key, val in labels ~} | ||
| ${key}: ${val} | ||
| %{~ endfor ~} | ||
| spec: | ||
| accessModes: | ||
| - ${access_mode} | ||
| resources: | ||
| requests: | ||
| storage: ${capacity} | ||
| storageClassName: ${storage_class_name} |
15 changes: 15 additions & 0 deletions
15
modules/file-system/gke-storage/persistent-volume-claim/hyperdisk-extreme-pvc.yaml.tftpl
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 +1,15 @@ | ||
| apiVersion: v1 | ||
| kind: PersistentVolumeClaim | ||
| metadata: | ||
| name: ${pvc_name} | ||
| labels: | ||
| %{~ for key, val in labels ~} | ||
| ${key}: ${val} | ||
| %{~ endfor ~} | ||
| spec: | ||
| accessModes: | ||
| - ${access_mode} | ||
| resources: | ||
| requests: | ||
| storage: ${capacity} | ||
| storageClassName: ${storage_class_name} |
15 changes: 15 additions & 0 deletions
15
modules/file-system/gke-storage/persistent-volume-claim/hyperdisk-throughput-pvc.yaml.tftpl
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 +1,15 @@ | ||
| apiVersion: v1 | ||
| kind: PersistentVolumeClaim | ||
| metadata: | ||
| name: ${pvc_name} | ||
| labels: | ||
| %{~ for key, val in labels ~} | ||
| ${key}: ${val} | ||
| %{~ endfor ~} | ||
| spec: | ||
| accessModes: | ||
| - ${access_mode} | ||
| resources: | ||
| requests: | ||
| storage: ${capacity} | ||
| storageClassName: ${storage_class_name} |
25 changes: 25 additions & 0 deletions
25
modules/file-system/gke-storage/storage-class/hyperdisk-balanced-sc.yaml.tftpl
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 +1,25 @@ | ||
| apiVersion: storage.k8s.io/v1 | ||
| kind: StorageClass | ||
| metadata: | ||
| name: ${name} | ||
| labels: | ||
| %{~ for key, val in labels ~} | ||
| ${key}: ${val} | ||
| %{~ endfor ~} | ||
| provisioner: pd.csi.storage.gke.io | ||
| allowVolumeExpansion: true | ||
| parameters: | ||
| type: hyperdisk-balanced | ||
| provisioned-throughput-on-create: "250Mi" | ||
| provisioned-iops-on-create: "7000" | ||
| volumeBindingMode: ${volume_binding_mode} | ||
| reclaimPolicy: ${reclaim_policy} | ||
| %{~ if topology_zones != null ~} | ||
| allowedTopologies: | ||
| - matchLabelExpressions: | ||
| - key: topology.gke.io/zone | ||
| values: | ||
| %{~ for z in topology_zones ~} | ||
| - ${z} | ||
| %{~ endfor ~} | ||
| %{~ endif ~} |
24 changes: 24 additions & 0 deletions
24
modules/file-system/gke-storage/storage-class/hyperdisk-extreme-sc.yaml.tftpl
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 +1,24 @@ | ||
| apiVersion: storage.k8s.io/v1 | ||
| kind: StorageClass | ||
| metadata: | ||
| name: ${name} | ||
| labels: | ||
| %{~ for key, val in labels ~} | ||
| ${key}: ${val} | ||
| provisioner: pd.csi.storage.gke.io | ||
| allowVolumeExpansion: true | ||
| parameters: | ||
| %{~ endfor ~} | ||
| type: hyperdisk-extreme | ||
| provisioned-iops-on-create: "50000" | ||
| volumeBindingMode: ${volume_binding_mode} | ||
| reclaimPolicy: ${reclaim_policy} | ||
| %{~ if topology_zones != null ~} | ||
| allowedTopologies: | ||
| - matchLabelExpressions: | ||
| - key: topology.gke.io/zone | ||
| values: | ||
| %{~ for z in topology_zones ~} | ||
| - ${z} | ||
| %{~ endfor ~} | ||
| %{~ endif ~} |
24 changes: 24 additions & 0 deletions
24
modules/file-system/gke-storage/storage-class/hyperdisk-throughput-sc.yaml.tftpl
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 +1,24 @@ | ||
| apiVersion: storage.k8s.io/v1 | ||
| kind: StorageClass | ||
| metadata: | ||
| name: ${name} | ||
| labels: | ||
| %{~ for key, val in labels ~} | ||
| ${key}: ${val} | ||
| %{~ endfor ~} | ||
| provisioner: pd.csi.storage.gke.io | ||
| allowVolumeExpansion: true | ||
| parameters: | ||
| type: hyperdisk-throughput | ||
| provisioned-throughput-on-create: "250Mi" | ||
| volumeBindingMode: ${volume_binding_mode} | ||
| reclaimPolicy: ${reclaim_policy} | ||
| %{~ if topology_zones != null ~} | ||
| allowedTopologies: | ||
| - matchLabelExpressions: | ||
| - key: topology.gke.io/zone | ||
| values: | ||
| %{~ for z in topology_zones ~} | ||
| - ${z} | ||
| %{~ endfor ~} | ||
| %{~ endif ~} |
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.
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.
Is this be default mode?
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.
If yes perhaps we can remove this line