-
Notifications
You must be signed in to change notification settings - Fork 674
/
common_types.go
235 lines (194 loc) · 9.57 KB
/
common_types.go
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
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
// Copyright 2018 The Kubeflow Authors
//
// 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.
package v1
import (
v1 "k8s.io/api/core/v1"
"k8s.io/apimachinery/pkg/api/resource"
metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
)
const (
// ReplicaIndexLabel represents the label key for the replica-index, e.g. 0, 1, 2.. etc
ReplicaIndexLabel = "training.kubeflow.org/replica-index"
// ReplicaTypeLabel represents the label key for the replica-type, e.g. ps, worker etc.
ReplicaTypeLabel = "training.kubeflow.org/replica-type"
// OperatorNameLabel represents the label key for the operator name, e.g. tf-operator, mpi-operator, etc.
OperatorNameLabel = "training.kubeflow.org/operator-name"
// JobNameLabel represents the label key for the job name, the value is the job name.
JobNameLabel = "training.kubeflow.org/job-name"
// JobRoleLabel represents the label key for the job role, e.g. master.
JobRoleLabel = "training.kubeflow.org/job-role"
)
// JobStatus represents the current observed state of the training Job.
type JobStatus struct {
// Conditions is an array of current observed job conditions.
Conditions []JobCondition `json:"conditions,omitempty"`
// ReplicaStatuses is map of ReplicaType and ReplicaStatus,
// specifies the status of each replica.
ReplicaStatuses map[ReplicaType]*ReplicaStatus `json:"replicaStatuses,omitempty"`
// Represents time when the job was acknowledged by the job controller.
// It is not guaranteed to be set in happens-before order across separate operations.
// It is represented in RFC3339 form and is in UTC.
StartTime *metav1.Time `json:"startTime,omitempty"`
// Represents time when the job was completed. It is not guaranteed to
// be set in happens-before order across separate operations.
// It is represented in RFC3339 form and is in UTC.
CompletionTime *metav1.Time `json:"completionTime,omitempty"`
// Represents last time when the job was reconciled. It is not guaranteed to
// be set in happens-before order across separate operations.
// It is represented in RFC3339 form and is in UTC.
LastReconcileTime *metav1.Time `json:"lastReconcileTime,omitempty"`
}
// ReplicaType represents the type of the replica. Each operator needs to define its
// own set of ReplicaTypes.
type ReplicaType string
// ReplicaStatus represents the current observed state of the replica.
type ReplicaStatus struct {
// The number of actively running pods.
Active int32 `json:"active,omitempty"`
// The number of pods which reached phase Succeeded.
Succeeded int32 `json:"succeeded,omitempty"`
// The number of pods which reached phase Failed.
Failed int32 `json:"failed,omitempty"`
// Deprecated: Use Selector instead
LabelSelector *metav1.LabelSelector `json:"labelSelector,omitempty"`
// A Selector is a label query over a set of resources. The result of matchLabels and
// matchExpressions are ANDed. An empty Selector matches all objects. A null
// Selector matches no objects.
Selector string `json:"selector,omitempty"`
}
// ReplicaSpec is a description of the replica
type ReplicaSpec struct {
// Replicas is the desired number of replicas of the given template.
// If unspecified, defaults to 1.
Replicas *int32 `json:"replicas,omitempty"`
// Template is the object that describes the pod that
// will be created for this replica. RestartPolicy in PodTemplateSpec
// will be overide by RestartPolicy in ReplicaSpec
Template v1.PodTemplateSpec `json:"template,omitempty"`
// Restart policy for all replicas within the job.
// One of Always, OnFailure, Never and ExitCode.
// Default to Never.
RestartPolicy RestartPolicy `json:"restartPolicy,omitempty"`
}
// JobCondition describes the state of the job at a certain point.
type JobCondition struct {
// Type of job condition.
Type JobConditionType `json:"type"`
// Status of the condition, one of True, False, Unknown.
Status v1.ConditionStatus `json:"status"`
// The reason for the condition's last transition.
Reason string `json:"reason,omitempty"`
// A human readable message indicating details about the transition.
Message string `json:"message,omitempty"`
// The last time this condition was updated.
LastUpdateTime metav1.Time `json:"lastUpdateTime,omitempty"`
// Last time the condition transitioned from one status to another.
LastTransitionTime metav1.Time `json:"lastTransitionTime,omitempty"`
}
// JobConditionType defines all kinds of types of JobStatus.
type JobConditionType string
const (
// JobCreated means the job has been accepted by the system,
// but one or more of the pods/services has not been started.
// This includes time before pods being scheduled and launched.
JobCreated JobConditionType = "Created"
// JobRunning means all sub-resources (e.g. services/pods) of this job
// have been successfully scheduled and launched.
// The training is running without error.
JobRunning JobConditionType = "Running"
// JobRestarting means one or more sub-resources (e.g. services/pods) of this job
// reached phase failed but maybe restarted according to it's restart policy
// which specified by user in v1.PodTemplateSpec.
// The training is freezing/pending.
JobRestarting JobConditionType = "Restarting"
// JobSucceeded means all sub-resources (e.g. services/pods) of this job
// reached phase have terminated in success.
// The training is complete without error.
JobSucceeded JobConditionType = "Succeeded"
// JobSuspended means the job has been suspended.
JobSuspended JobConditionType = "Suspended"
// JobFailed means one or more sub-resources (e.g. services/pods) of this job
// reached phase failed with no restarting.
// The training has failed its execution.
JobFailed JobConditionType = "Failed"
)
// CleanPodPolicy describes how to deal with pods when the job is finished.
type CleanPodPolicy string
const (
CleanPodPolicyUndefined CleanPodPolicy = ""
CleanPodPolicyAll CleanPodPolicy = "All"
CleanPodPolicyRunning CleanPodPolicy = "Running"
CleanPodPolicyNone CleanPodPolicy = "None"
)
// RestartPolicy describes how the replicas should be restarted.
// Only one of the following restart policies may be specified.
// If none of the following policies is specified, the default one
// is RestartPolicyAlways.
type RestartPolicy string
const (
RestartPolicyAlways RestartPolicy = "Always"
RestartPolicyOnFailure RestartPolicy = "OnFailure"
RestartPolicyNever RestartPolicy = "Never"
// RestartPolicyExitCode policy means that user should add exit code by themselves,
// The job operator will check these exit codes to
// determine the behavior when an error occurs:
// - 1-127: permanent error, do not restart.
// - 128-255: retryable error, will restart the pod.
RestartPolicyExitCode RestartPolicy = "ExitCode"
)
// RunPolicy encapsulates various runtime policies of the distributed training
// job, for example how to clean up resources and how long the job can stay
// active.
type RunPolicy struct {
// CleanPodPolicy defines the policy to kill pods after the job completes.
// Default to None.
CleanPodPolicy *CleanPodPolicy `json:"cleanPodPolicy,omitempty"`
// TTLSecondsAfterFinished is the TTL to clean up jobs.
// It may take extra ReconcilePeriod seconds for the cleanup, since
// reconcile gets called periodically.
// Default to infinite.
TTLSecondsAfterFinished *int32 `json:"ttlSecondsAfterFinished,omitempty"`
// Specifies the duration in seconds relative to the startTime that the job may be active
// before the system tries to terminate it; value must be positive integer.
// +optional
ActiveDeadlineSeconds *int64 `json:"activeDeadlineSeconds,omitempty"`
// Optional number of retries before marking this job failed.
// +optional
BackoffLimit *int32 `json:"backoffLimit,omitempty"`
// SchedulingPolicy defines the policy related to scheduling, e.g. gang-scheduling
// +optional
SchedulingPolicy *SchedulingPolicy `json:"schedulingPolicy,omitempty"`
// suspend specifies whether the Job controller should create Pods or not.
// If a Job is created with suspend set to true, no Pods are created by
// the Job controller. If a Job is suspended after creation (i.e. the
// flag goes from false to true), the Job controller will delete all
// active Pods and PodGroups associated with this Job.
// Users must design their workload to gracefully handle this.
// Suspending a Job will reset the StartTime field of the Job.
//
// Defaults to false.
// +kubebuilder:default:=false
// +optional
Suspend *bool `json:"suspend,omitempty"`
}
// SchedulingPolicy encapsulates various scheduling policies of the distributed training
// job, for example `minAvailable` for gang-scheduling.
type SchedulingPolicy struct {
MinAvailable *int32 `json:"minAvailable,omitempty"`
// +kubebuilder:validation:XValidation:rule="self == oldSelf", message="spec.runPolicy.schedulingPolicy.queue is immutable"
Queue string `json:"queue,omitempty"`
MinResources *map[v1.ResourceName]resource.Quantity `json:"minResources,omitempty"`
PriorityClass string `json:"priorityClass,omitempty"`
ScheduleTimeoutSeconds *int32 `json:"scheduleTimeoutSeconds,omitempty"`
}