forked from GoogleCloudPlatform/python-docs-samples
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathcreate_with_persistent_disk.py
More file actions
132 lines (109 loc) · 4.68 KB
/
create_with_persistent_disk.py
File metadata and controls
132 lines (109 loc) · 4.68 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
# 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.
# [START batch_create_persistent_disk_job]
from google.cloud import batch_v1
def create_with_pd_job(
project_id: str,
region: str,
job_name: str,
disk_name: str,
zone: str,
existing_disk_name=None,
) -> batch_v1.Job:
"""
This method shows how to create a sample Batch Job that will run
a simple command on Cloud Compute instances with mounted persistent disk.
Args:
project_id: project ID or project number of the Cloud project you want to use.
region: name of the region you want to use to run the job. Regions that are
available for Batch are listed on: https://cloud.google.com/batch/docs/get-started#locations
job_name: the name of the job that will be created.
It needs to be unique for each project and region pair.
disk_name: name of the disk to be mounted for your Job.
existing_disk_name(optional): existing disk name, which you want to attach to a job
Returns:
A job object representing the job created.
"""
client = batch_v1.BatchServiceClient()
# Define what will be done as part of the job.
task = batch_v1.TaskSpec()
runnable = batch_v1.Runnable()
runnable.script = batch_v1.Runnable.Script()
runnable.script.text = (
"echo Hello world from task ${BATCH_TASK_INDEX}. >> /mnt/disks/"
+ disk_name
+ "/output_task_${BATCH_TASK_INDEX}.txt"
)
task.runnables = [runnable]
task.max_retry_count = 2
task.max_run_duration = "3600s"
volume = batch_v1.Volume()
volume.device_name = disk_name
volume.mount_path = f"/mnt/disks/{disk_name}"
task.volumes = [volume]
if existing_disk_name:
volume2 = batch_v1.Volume()
volume2.device_name = existing_disk_name
volume2.mount_path = f"/mnt/disks/{existing_disk_name}"
task.volumes.append(volume2)
# Tasks are grouped inside a job using TaskGroups.
# Currently, it's possible to have only one task group.
group = batch_v1.TaskGroup()
group.task_count = 4
group.task_spec = task
disk = batch_v1.AllocationPolicy.Disk()
# The disk type of the new persistent disk, either pd-standard,
# pd-balanced, pd-ssd, or pd-extreme. For Batch jobs, the default is pd-balanced
disk.type_ = "pd-balanced"
disk.size_gb = 10
# Policies are used to define on what kind of virtual machines the tasks will run on.
# Read more about local disks here: https://cloud.google.com/compute/docs/disks/persistent-disks
policy = batch_v1.AllocationPolicy.InstancePolicy()
policy.machine_type = "n1-standard-1"
attached_disk = batch_v1.AllocationPolicy.AttachedDisk()
attached_disk.new_disk = disk
attached_disk.device_name = disk_name
policy.disks = [attached_disk]
if existing_disk_name:
attached_disk2 = batch_v1.AllocationPolicy.AttachedDisk()
attached_disk2.existing_disk = (
f"projects/{project_id}/zones/{zone}/disks/{existing_disk_name}"
)
attached_disk2.device_name = existing_disk_name
policy.disks.append(attached_disk2)
instances = batch_v1.AllocationPolicy.InstancePolicyOrTemplate()
instances.policy = policy
allocation_policy = batch_v1.AllocationPolicy()
allocation_policy.instances = [instances]
location = batch_v1.AllocationPolicy.LocationPolicy()
location.allowed_locations = [f"zones/{zone}"]
allocation_policy.location = location
job = batch_v1.Job()
job.task_groups = [group]
job.allocation_policy = allocation_policy
job.labels = {"env": "testing", "type": "script"}
create_request = batch_v1.CreateJobRequest()
create_request.job = job
create_request.job_id = job_name
# The job's parent is the region in which the job will run
create_request.parent = f"projects/{project_id}/locations/{region}"
return client.create_job(create_request)
# [END batch_create_persistent_disk_job]
if __name__ == "__main__":
import google.auth
PROJECT = google.auth.default()[1]
REGION = "europe-west4"
ZONE = "europe-west4-c"
job = create_with_pd_job(PROJECT, REGION, "pd-job-batch", "pd-1", ZONE)
print(job)