Skip to content

Commit d20d422

Browse files
authored
clean up autoscaling code for raw deployment (kserve#4349)
Signed-off-by: Dan Sun <dsun20@bloomberg.net>
1 parent 6d69174 commit d20d422

51 files changed

Lines changed: 2043 additions & 1184 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

charts/kserve-crd/templates/serving.kserve.io_inferenceservices.yaml

Lines changed: 45 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1234,6 +1234,9 @@ spec:
12341234
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
12351235
x-kubernetes-int-or-string: true
12361236
type: object
1237+
required:
1238+
- metric
1239+
- target
12371240
type: object
12381241
podmetric:
12391242
properties:
@@ -1278,15 +1281,16 @@ spec:
12781281
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
12791282
x-kubernetes-int-or-string: true
12801283
type: object
1284+
required:
1285+
- metric
1286+
- target
12811287
type: object
12821288
resource:
12831289
properties:
12841290
name:
12851291
enum:
12861292
- cpu
12871293
- memory
1288-
- concurrency
1289-
- rps
12901294
type: string
12911295
target:
12921296
properties:
@@ -1312,13 +1316,18 @@ spec:
13121316
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
13131317
x-kubernetes-int-or-string: true
13141318
type: object
1319+
required:
1320+
- name
1321+
- target
13151322
type: object
13161323
type:
13171324
enum:
13181325
- Resource
13191326
- External
13201327
- PodMetric
13211328
type: string
1329+
required:
1330+
- type
13221331
type: object
13231332
type: array
13241333
type: object
@@ -2895,6 +2904,10 @@ spec:
28952904
- rps
28962905
type: string
28972906
scaleMetricType:
2907+
enum:
2908+
- Utilization
2909+
- Value
2910+
- AverageValue
28982911
type: string
28992912
scaleTarget:
29002913
format: int32
@@ -4357,6 +4370,9 @@ spec:
43574370
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
43584371
x-kubernetes-int-or-string: true
43594372
type: object
4373+
required:
4374+
- metric
4375+
- target
43604376
type: object
43614377
podmetric:
43624378
properties:
@@ -4401,15 +4417,16 @@ spec:
44014417
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
44024418
x-kubernetes-int-or-string: true
44034419
type: object
4420+
required:
4421+
- metric
4422+
- target
44044423
type: object
44054424
resource:
44064425
properties:
44074426
name:
44084427
enum:
44094428
- cpu
44104429
- memory
4411-
- concurrency
4412-
- rps
44134430
type: string
44144431
target:
44154432
properties:
@@ -4435,13 +4452,18 @@ spec:
44354452
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
44364453
x-kubernetes-int-or-string: true
44374454
type: object
4455+
required:
4456+
- name
4457+
- target
44384458
type: object
44394459
type:
44404460
enum:
44414461
- Resource
44424462
- External
44434463
- PodMetric
44444464
type: string
4465+
required:
4466+
- type
44454467
type: object
44464468
type: array
44474469
type: object
@@ -10838,6 +10860,10 @@ spec:
1083810860
- rps
1083910861
type: string
1084010862
scaleMetricType:
10863+
enum:
10864+
- Utilization
10865+
- Value
10866+
- AverageValue
1084110867
type: string
1084210868
scaleTarget:
1084310869
format: int32
@@ -18653,6 +18679,9 @@ spec:
1865318679
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
1865418680
x-kubernetes-int-or-string: true
1865518681
type: object
18682+
required:
18683+
- metric
18684+
- target
1865618685
type: object
1865718686
podmetric:
1865818687
properties:
@@ -18697,15 +18726,16 @@ spec:
1869718726
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
1869818727
x-kubernetes-int-or-string: true
1869918728
type: object
18729+
required:
18730+
- metric
18731+
- target
1870018732
type: object
1870118733
resource:
1870218734
properties:
1870318735
name:
1870418736
enum:
1870518737
- cpu
1870618738
- memory
18707-
- concurrency
18708-
- rps
1870918739
type: string
1871018740
target:
1871118741
properties:
@@ -18731,13 +18761,18 @@ spec:
1873118761
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
1873218762
x-kubernetes-int-or-string: true
1873318763
type: object
18764+
required:
18765+
- name
18766+
- target
1873418767
type: object
1873518768
type:
1873618769
enum:
1873718770
- Resource
1873818771
- External
1873918772
- PodMetric
1874018773
type: string
18774+
required:
18775+
- type
1874118776
type: object
1874218777
type: array
1874318778
type: object
@@ -20314,6 +20349,10 @@ spec:
2031420349
- rps
2031520350
type: string
2031620351
scaleMetricType:
20352+
enum:
20353+
- Utilization
20354+
- Value
20355+
- AverageValue
2031720356
type: string
2031820357
scaleTarget:
2031920358
format: int32

charts/kserve-resources/templates/configmap.yaml

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -445,13 +445,13 @@ data:
445445
# Example
446446
service: |-
447447
{
448-
"serviceClusterIPNone": "false"
448+
"serviceClusterIPNone": false
449449
}
450450
service: |-
451451
{
452452
# ServiceClusterIPNone is a flag to indicate if the service should have a clusterIP set to None.
453453
# If the DeploymentMode is Raw, the default value for ServiceClusterIPNone if not set is false
454-
# "serviceClusterIPNone": "false"
454+
# "serviceClusterIPNone": false
455455
}
456456
457457
# ====================================== METRICS CONFIGURATION ======================================
@@ -548,7 +548,7 @@ data:
548548
}
549549
service: |-
550550
{
551-
"serviceClusterIPNone": "{{ .Values.kserve.service.serviceClusterIPNone }}"
551+
"serviceClusterIPNone": {{ .Values.kserve.service.serviceClusterIPNone }}
552552
}
553553
explainers: |-
554554
{

config/crd/full/serving.kserve.io_inferenceservices.yaml

Lines changed: 45 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1234,6 +1234,9 @@ spec:
12341234
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
12351235
x-kubernetes-int-or-string: true
12361236
type: object
1237+
required:
1238+
- metric
1239+
- target
12371240
type: object
12381241
podmetric:
12391242
properties:
@@ -1278,15 +1281,16 @@ spec:
12781281
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
12791282
x-kubernetes-int-or-string: true
12801283
type: object
1284+
required:
1285+
- metric
1286+
- target
12811287
type: object
12821288
resource:
12831289
properties:
12841290
name:
12851291
enum:
12861292
- cpu
12871293
- memory
1288-
- concurrency
1289-
- rps
12901294
type: string
12911295
target:
12921296
properties:
@@ -1312,13 +1316,18 @@ spec:
13121316
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
13131317
x-kubernetes-int-or-string: true
13141318
type: object
1319+
required:
1320+
- name
1321+
- target
13151322
type: object
13161323
type:
13171324
enum:
13181325
- Resource
13191326
- External
13201327
- PodMetric
13211328
type: string
1329+
required:
1330+
- type
13221331
type: object
13231332
type: array
13241333
type: object
@@ -2895,6 +2904,10 @@ spec:
28952904
- rps
28962905
type: string
28972906
scaleMetricType:
2907+
enum:
2908+
- Utilization
2909+
- Value
2910+
- AverageValue
28982911
type: string
28992912
scaleTarget:
29002913
format: int32
@@ -4357,6 +4370,9 @@ spec:
43574370
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
43584371
x-kubernetes-int-or-string: true
43594372
type: object
4373+
required:
4374+
- metric
4375+
- target
43604376
type: object
43614377
podmetric:
43624378
properties:
@@ -4401,15 +4417,16 @@ spec:
44014417
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
44024418
x-kubernetes-int-or-string: true
44034419
type: object
4420+
required:
4421+
- metric
4422+
- target
44044423
type: object
44054424
resource:
44064425
properties:
44074426
name:
44084427
enum:
44094428
- cpu
44104429
- memory
4411-
- concurrency
4412-
- rps
44134430
type: string
44144431
target:
44154432
properties:
@@ -4435,13 +4452,18 @@ spec:
44354452
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
44364453
x-kubernetes-int-or-string: true
44374454
type: object
4455+
required:
4456+
- name
4457+
- target
44384458
type: object
44394459
type:
44404460
enum:
44414461
- Resource
44424462
- External
44434463
- PodMetric
44444464
type: string
4465+
required:
4466+
- type
44454467
type: object
44464468
type: array
44474469
type: object
@@ -10838,6 +10860,10 @@ spec:
1083810860
- rps
1083910861
type: string
1084010862
scaleMetricType:
10863+
enum:
10864+
- Utilization
10865+
- Value
10866+
- AverageValue
1084110867
type: string
1084210868
scaleTarget:
1084310869
format: int32
@@ -18653,6 +18679,9 @@ spec:
1865318679
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
1865418680
x-kubernetes-int-or-string: true
1865518681
type: object
18682+
required:
18683+
- metric
18684+
- target
1865618685
type: object
1865718686
podmetric:
1865818687
properties:
@@ -18697,15 +18726,16 @@ spec:
1869718726
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
1869818727
x-kubernetes-int-or-string: true
1869918728
type: object
18729+
required:
18730+
- metric
18731+
- target
1870018732
type: object
1870118733
resource:
1870218734
properties:
1870318735
name:
1870418736
enum:
1870518737
- cpu
1870618738
- memory
18707-
- concurrency
18708-
- rps
1870918739
type: string
1871018740
target:
1871118741
properties:
@@ -18731,13 +18761,18 @@ spec:
1873118761
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
1873218762
x-kubernetes-int-or-string: true
1873318763
type: object
18764+
required:
18765+
- name
18766+
- target
1873418767
type: object
1873518768
type:
1873618769
enum:
1873718770
- Resource
1873818771
- External
1873918772
- PodMetric
1874018773
type: string
18774+
required:
18775+
- type
1874118776
type: object
1874218777
type: array
1874318778
type: object
@@ -20314,6 +20349,10 @@ spec:
2031420349
- rps
2031520350
type: string
2031620351
scaleMetricType:
20352+
enum:
20353+
- Utilization
20354+
- Value
20355+
- AverageValue
2031720356
type: string
2031820357
scaleTarget:
2031920358
format: int32

hack/violation_exceptions.list

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -19,6 +19,7 @@ API rule violation: list_type_missing,github.com/kserve/kserve/pkg/apis/serving/
1919
API rule violation: list_type_missing,github.com/kserve/kserve/pkg/apis/serving/v1beta1,InferenceServicesConfig,ServiceLabelDisallowedList
2020
API rule violation: list_type_missing,github.com/kserve/kserve/pkg/apis/serving/v1beta1,LoggerSpec,MetadataHeaders
2121
API rule violation: list_type_missing,github.com/kserve/kserve/pkg/apis/serving/v1beta1,MultiNodeConfig,CustomGPUResourceTypeList
22+
API rule violation: list_type_missing,github.com/kserve/kserve/pkg/apis/serving/v1beta1,PodMetrics,MetricNames
2223
API rule violation: list_type_missing,github.com/kserve/kserve/pkg/apis/serving/v1beta1,PodSpec,Containers
2324
API rule violation: list_type_missing,github.com/kserve/kserve/pkg/apis/serving/v1beta1,PodSpec,EphemeralContainers
2425
API rule violation: list_type_missing,github.com/kserve/kserve/pkg/apis/serving/v1beta1,PodSpec,HostAliases
@@ -27,7 +28,6 @@ API rule violation: list_type_missing,github.com/kserve/kserve/pkg/apis/serving/
2728
API rule violation: list_type_missing,github.com/kserve/kserve/pkg/apis/serving/v1beta1,PodSpec,ReadinessGates
2829
API rule violation: list_type_missing,github.com/kserve/kserve/pkg/apis/serving/v1beta1,PodSpec,Tolerations
2930
API rule violation: list_type_missing,github.com/kserve/kserve/pkg/apis/serving/v1beta1,PodSpec,Volumes
30-
API rule violation: list_type_missing,github.com/kserve/kserve/pkg/apis/serving/v1beta1,PodsMetricSource,MetricNames
3131
API rule violation: names_match,github.com/kserve/kserve/pkg/apis/serving/v1alpha1,InferenceGraphSpec,TimeoutSeconds
3232
API rule violation: names_match,github.com/kserve/kserve/pkg/apis/serving/v1alpha1,InferenceStep,StepName
3333
API rule violation: names_match,github.com/kserve/kserve/pkg/apis/serving/v1alpha1,InferenceTarget,ServiceURL

0 commit comments

Comments
 (0)