feat: Add ability to select instances by CPU manufacturer (#5769)

aws · Mar 5, 2024 · d3f2536 · d3f2536
1 parent 53dfdea
commit d3f2536
Show file tree

Hide file tree

Showing 15 changed files with 807 additions and 19 deletions.
diff --git a/designs/v1beta1-api.md b/designs/v1beta1-api.md
@@ -344,12 +344,13 @@ status:
 6. `karpenter.k8s.aws/instance-local-nvme`
 7. `karpenter.k8s.aws/instance-size`
 8. `karpenter.k8s.aws/instance-cpu`
-9. `karpenter.k8s.aws/instance-memory`
-10. `karpenter.k8s.aws/instance-network-bandwidth`
-11. `karpenter.k8s.aws/instance-gpu-name`
-12. `karpenter.k8s.aws/instance-gpu-manufacturer`
-13. `karpenter.k8s.aws/instance-gpu-count`
-14. `karpenter.k8s.aws/instance-gpu-memory`
-15. `karpenter.k8s.aws/instance-accelerator-name`
-16. `karpenter.k8s.aws/instance-accelerator-manufacturer`
-17. `karpenter.k8s.aws/instance-accelerator-count`
+9. `karpenter.k8s.aws/instance-cpu-manufacturer`
+10. `karpenter.k8s.aws/instance-memory`
+11. `karpenter.k8s.aws/instance-network-bandwidth`
+12. `karpenter.k8s.aws/instance-gpu-name`
+13. `karpenter.k8s.aws/instance-gpu-manufacturer`
+14. `karpenter.k8s.aws/instance-gpu-count`
+15. `karpenter.k8s.aws/instance-gpu-memory`
+16. `karpenter.k8s.aws/instance-accelerator-name`
+17. `karpenter.k8s.aws/instance-accelerator-manufacturer`
+18. `karpenter.k8s.aws/instance-accelerator-count`
diff --git a/go.mod b/go.mod
@@ -85,7 +85,7 @@ require (
 	github.com/prometheus/statsd_exporter v0.24.0 // indirect
 	github.com/rivo/uniseg v0.4.4 // indirect
 	github.com/robfig/cron/v3 v3.0.1 // indirect
-	github.com/spf13/cobra v1.7.0 // indirect
+	github.com/spf13/cobra v1.8.0 // indirect
 	github.com/spf13/pflag v1.0.5 // indirect
 	go.opencensus.io v0.24.0 // indirect
 	go.uber.org/automaxprocs v1.5.3 // indirect

diff --git a/go.sum b/go.sum
@@ -80,7 +80,7 @@ github.com/chzyer/readline v0.0.0-20180603132655-2972be24d48e/go.mod h1:nSuG5e5P
 github.com/chzyer/test v0.0.0-20180213035817-a1ea475d72b1/go.mod h1:Q3SI9o4m/ZMnBNeIyt5eFwwo7qiLfzFZmjNmxjkiQlU=
 github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw=
 github.com/cncf/udpa/go v0.0.0-20191209042840-269d4d468f6f/go.mod h1:M8M6+tZqaGXZJjfX53e64911xZQV5JYwmTeXPW+k8Sc=
-github.com/cpuguy83/go-md2man/v2 v2.0.2/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
+github.com/cpuguy83/go-md2man/v2 v2.0.3/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
 github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
@@ -335,8 +335,8 @@ github.com/samber/lo v1.39.0/go.mod h1:+m/ZKRl6ClXCE2Lgf3MsQlWfh4bn1bz6CXEOxnEXn
 github.com/sirupsen/logrus v1.2.0/go.mod h1:LxeOpSwHxABJmUn/MG1IvRgCAasNZTLOkJPxbbu5VWo=
 github.com/sirupsen/logrus v1.4.2/go.mod h1:tLMulIdttU9McNUspp0xgXVQah82FyeX6MwdIuYE2rE=
 github.com/sirupsen/logrus v1.6.0/go.mod h1:7uNnSEd1DgxDLC74fIahvMZmmYsHGZGEOFrfsX/uA88=
-github.com/spf13/cobra v1.7.0 h1:hyqWnYt1ZQShIddO5kBpj3vu05/++x6tJ6dg8EC572I=
-github.com/spf13/cobra v1.7.0/go.mod h1:uLxZILRyS/50WlhOIKD7W6V5bgeIt+4sICxh6uRMrb0=
+github.com/spf13/cobra v1.8.0 h1:7aJaZx1B85qltLMc546zn58BxxfZdR/W22ej9CFoEf0=
+github.com/spf13/cobra v1.8.0/go.mod h1:WXLWApfZ71AjXPya3WOlMsY9yMs7YeiHhFVlvLyhcho=
 github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA=
 github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=

diff --git a/hack/code/instancetype_testdata_gen/main.go b/hack/code/instancetype_testdata_gen/main.go
@@ -119,6 +119,7 @@ func getInstanceTypeInfo(info *ec2.InstanceTypeInfo) string {
 	fmt.Fprintf(src, "BareMetal: aws.Bool(%t),\n", lo.FromPtr(info.BareMetal))
 	fmt.Fprintf(src, "Hypervisor: aws.String(\"%s\"),\n", lo.FromPtr(info.Hypervisor))
 	fmt.Fprintf(src, "ProcessorInfo: &ec2.ProcessorInfo{\n")
+	fmt.Fprintf(src, "Manufacturer: aws.String(\"%s\"),\n", lo.FromPtr(info.ProcessorInfo.Manufacturer))
 	fmt.Fprintf(src, "SupportedArchitectures: aws.StringSlice([]string{%s}),\n", getStringSliceData(info.ProcessorInfo.SupportedArchitectures))
 	fmt.Fprintf(src, "},\n")
 	fmt.Fprintf(src, "VCpuInfo: &ec2.VCpuInfo{\n")

diff --git a/hack/validation/labels.sh b/hack/validation/labels.sh
@@ -4,4 +4,4 @@
 
 # ## checking for restricted labels while filtering out well known labels
 yq eval '.spec.versions[0].schema.openAPIV3Schema.properties.spec.properties.template.properties.metadata.properties.labels.x-kubernetes-validations += [
-    {"message": "label domain \"karpenter.k8s.aws\" is restricted", "rule": "self.all(x, x in [\"karpenter.k8s.aws/instance-encryption-in-transit-supported\", \"karpenter.k8s.aws/instance-category\", \"karpenter.k8s.aws/instance-hypervisor\", \"karpenter.k8s.aws/instance-family\", \"karpenter.k8s.aws/instance-generation\", \"karpenter.k8s.aws/instance-local-nvme\", \"karpenter.k8s.aws/instance-size\", \"karpenter.k8s.aws/instance-cpu\",\"karpenter.k8s.aws/instance-memory\", \"karpenter.k8s.aws/instance-network-bandwidth\", \"karpenter.k8s.aws/instance-gpu-name\", \"karpenter.k8s.aws/instance-gpu-manufacturer\", \"karpenter.k8s.aws/instance-gpu-count\", \"karpenter.k8s.aws/instance-gpu-memory\", \"karpenter.k8s.aws/instance-accelerator-name\", \"karpenter.k8s.aws/instance-accelerator-manufacturer\", \"karpenter.k8s.aws/instance-accelerator-count\"] || !x.find(\"^([^/]+)\").endsWith(\"karpenter.k8s.aws\"))"}]' -i pkg/apis/crds/karpenter.sh_nodepools.yaml 
+    {"message": "label domain \"karpenter.k8s.aws\" is restricted", "rule": "self.all(x, x in [\"karpenter.k8s.aws/instance-encryption-in-transit-supported\", \"karpenter.k8s.aws/instance-category\", \"karpenter.k8s.aws/instance-hypervisor\", \"karpenter.k8s.aws/instance-family\", \"karpenter.k8s.aws/instance-generation\", \"karpenter.k8s.aws/instance-local-nvme\", \"karpenter.k8s.aws/instance-size\", \"karpenter.k8s.aws/instance-cpu\",\"karpenter.k8s.aws/instance-cpu-manufacturer\",\"karpenter.k8s.aws/instance-memory\", \"karpenter.k8s.aws/instance-network-bandwidth\", \"karpenter.k8s.aws/instance-gpu-name\", \"karpenter.k8s.aws/instance-gpu-manufacturer\", \"karpenter.k8s.aws/instance-gpu-count\", \"karpenter.k8s.aws/instance-gpu-memory\", \"karpenter.k8s.aws/instance-accelerator-name\", \"karpenter.k8s.aws/instance-accelerator-manufacturer\", \"karpenter.k8s.aws/instance-accelerator-count\"] || !x.find(\"^([^/]+)\").endsWith(\"karpenter.k8s.aws\"))"}]' -i pkg/apis/crds/karpenter.sh_nodepools.yaml 
diff --git a/hack/validation/requirements.sh b/hack/validation/requirements.sh
@@ -4,9 +4,9 @@
 
 ## checking for restricted labels while filtering out well known labels
 yq eval '.spec.versions[0].schema.openAPIV3Schema.properties.spec.properties.requirements.items.properties.key.x-kubernetes-validations += [
-    {"message": "label domain \"karpenter.k8s.aws\" is restricted", "rule": "self in [\"karpenter.k8s.aws/instance-encryption-in-transit-supported\", \"karpenter.k8s.aws/instance-category\", \"karpenter.k8s.aws/instance-hypervisor\", \"karpenter.k8s.aws/instance-family\", \"karpenter.k8s.aws/instance-generation\", \"karpenter.k8s.aws/instance-local-nvme\", \"karpenter.k8s.aws/instance-size\", \"karpenter.k8s.aws/instance-cpu\",\"karpenter.k8s.aws/instance-memory\", \"karpenter.k8s.aws/instance-network-bandwidth\", \"karpenter.k8s.aws/instance-gpu-name\", \"karpenter.k8s.aws/instance-gpu-manufacturer\", \"karpenter.k8s.aws/instance-gpu-count\", \"karpenter.k8s.aws/instance-gpu-memory\", \"karpenter.k8s.aws/instance-accelerator-name\", \"karpenter.k8s.aws/instance-accelerator-manufacturer\", \"karpenter.k8s.aws/instance-accelerator-count\"] || !self.find(\"^([^/]+)\").endsWith(\"karpenter.k8s.aws\")"}]' -i pkg/apis/crds/karpenter.sh_nodeclaims.yaml 
+    {"message": "label domain \"karpenter.k8s.aws\" is restricted", "rule": "self in [\"karpenter.k8s.aws/instance-encryption-in-transit-supported\", \"karpenter.k8s.aws/instance-category\", \"karpenter.k8s.aws/instance-hypervisor\", \"karpenter.k8s.aws/instance-family\", \"karpenter.k8s.aws/instance-generation\", \"karpenter.k8s.aws/instance-local-nvme\", \"karpenter.k8s.aws/instance-size\", \"karpenter.k8s.aws/instance-cpu\",\"karpenter.k8s.aws/instance-cpu-manufacturer\",\"karpenter.k8s.aws/instance-memory\", \"karpenter.k8s.aws/instance-network-bandwidth\", \"karpenter.k8s.aws/instance-gpu-name\", \"karpenter.k8s.aws/instance-gpu-manufacturer\", \"karpenter.k8s.aws/instance-gpu-count\", \"karpenter.k8s.aws/instance-gpu-memory\", \"karpenter.k8s.aws/instance-accelerator-name\", \"karpenter.k8s.aws/instance-accelerator-manufacturer\", \"karpenter.k8s.aws/instance-accelerator-count\"] || !self.find(\"^([^/]+)\").endsWith(\"karpenter.k8s.aws\")"}]' -i pkg/apis/crds/karpenter.sh_nodeclaims.yaml 
 # # Adding validation for nodepool
 
 # ## checking for restricted labels while filtering out well known labels
 yq eval '.spec.versions[0].schema.openAPIV3Schema.properties.spec.properties.template.properties.spec.properties.requirements.items.properties.key.x-kubernetes-validations  += [
-    {"message": "label domain \"karpenter.k8s.aws\" is restricted", "rule": "self in [\"karpenter.k8s.aws/instance-encryption-in-transit-supported\", \"karpenter.k8s.aws/instance-category\", \"karpenter.k8s.aws/instance-hypervisor\", \"karpenter.k8s.aws/instance-family\", \"karpenter.k8s.aws/instance-generation\", \"karpenter.k8s.aws/instance-local-nvme\", \"karpenter.k8s.aws/instance-size\", \"karpenter.k8s.aws/instance-cpu\",\"karpenter.k8s.aws/instance-memory\", \"karpenter.k8s.aws/instance-network-bandwidth\", \"karpenter.k8s.aws/instance-gpu-name\", \"karpenter.k8s.aws/instance-gpu-manufacturer\", \"karpenter.k8s.aws/instance-gpu-count\", \"karpenter.k8s.aws/instance-gpu-memory\", \"karpenter.k8s.aws/instance-accelerator-name\", \"karpenter.k8s.aws/instance-accelerator-manufacturer\", \"karpenter.k8s.aws/instance-accelerator-count\"] || !self.find(\"^([^/]+)\").endsWith(\"karpenter.k8s.aws\")"}]' -i pkg/apis/crds/karpenter.sh_nodepools.yaml 
+    {"message": "label domain \"karpenter.k8s.aws\" is restricted", "rule": "self in [\"karpenter.k8s.aws/instance-encryption-in-transit-supported\", \"karpenter.k8s.aws/instance-category\", \"karpenter.k8s.aws/instance-hypervisor\", \"karpenter.k8s.aws/instance-family\", \"karpenter.k8s.aws/instance-generation\", \"karpenter.k8s.aws/instance-local-nvme\", \"karpenter.k8s.aws/instance-size\", \"karpenter.k8s.aws/instance-cpu\",\"karpenter.k8s.aws/instance-cpu-manufacturer\",\"karpenter.k8s.aws/instance-memory\", \"karpenter.k8s.aws/instance-network-bandwidth\", \"karpenter.k8s.aws/instance-gpu-name\", \"karpenter.k8s.aws/instance-gpu-manufacturer\", \"karpenter.k8s.aws/instance-gpu-count\", \"karpenter.k8s.aws/instance-gpu-memory\", \"karpenter.k8s.aws/instance-accelerator-name\", \"karpenter.k8s.aws/instance-accelerator-manufacturer\", \"karpenter.k8s.aws/instance-accelerator-count\"] || !self.find(\"^([^/]+)\").endsWith(\"karpenter.k8s.aws\")"}]' -i pkg/apis/crds/karpenter.sh_nodepools.yaml 
diff --git a/pkg/apis/crds/karpenter.sh_nodeclaims.yaml b/pkg/apis/crds/karpenter.sh_nodeclaims.yaml
@@ -226,7 +226,7 @@ spec:
                           - message: label "kubernetes.io/hostname" is restricted
                             rule: self != "kubernetes.io/hostname"
                           - message: label domain "karpenter.k8s.aws" is restricted
-                            rule: self in ["karpenter.k8s.aws/instance-encryption-in-transit-supported", "karpenter.k8s.aws/instance-category", "karpenter.k8s.aws/instance-hypervisor", "karpenter.k8s.aws/instance-family", "karpenter.k8s.aws/instance-generation", "karpenter.k8s.aws/instance-local-nvme", "karpenter.k8s.aws/instance-size", "karpenter.k8s.aws/instance-cpu","karpenter.k8s.aws/instance-memory", "karpenter.k8s.aws/instance-network-bandwidth", "karpenter.k8s.aws/instance-gpu-name", "karpenter.k8s.aws/instance-gpu-manufacturer", "karpenter.k8s.aws/instance-gpu-count", "karpenter.k8s.aws/instance-gpu-memory", "karpenter.k8s.aws/instance-accelerator-name", "karpenter.k8s.aws/instance-accelerator-manufacturer", "karpenter.k8s.aws/instance-accelerator-count"] || !self.find("^([^/]+)").endsWith("karpenter.k8s.aws")
+                            rule: self in ["karpenter.k8s.aws/instance-encryption-in-transit-supported", "karpenter.k8s.aws/instance-category", "karpenter.k8s.aws/instance-hypervisor", "karpenter.k8s.aws/instance-family", "karpenter.k8s.aws/instance-generation", "karpenter.k8s.aws/instance-local-nvme", "karpenter.k8s.aws/instance-size", "karpenter.k8s.aws/instance-cpu","karpenter.k8s.aws/instance-cpu-manufacturer","karpenter.k8s.aws/instance-memory", "karpenter.k8s.aws/instance-network-bandwidth", "karpenter.k8s.aws/instance-gpu-name", "karpenter.k8s.aws/instance-gpu-manufacturer", "karpenter.k8s.aws/instance-gpu-count", "karpenter.k8s.aws/instance-gpu-memory", "karpenter.k8s.aws/instance-accelerator-name", "karpenter.k8s.aws/instance-accelerator-manufacturer", "karpenter.k8s.aws/instance-accelerator-count"] || !self.find("^([^/]+)").endsWith("karpenter.k8s.aws")
                       minValues:
                         description: |-
                           This field is ALPHA and can be dropped or replaced at any time

diff --git a/pkg/apis/crds/karpenter.sh_nodepools.yaml b/pkg/apis/crds/karpenter.sh_nodepools.yaml
@@ -190,7 +190,7 @@ spec:
                             - message: label "kubernetes.io/hostname" is restricted
                               rule: self.all(x, x != "kubernetes.io/hostname")
                             - message: label domain "karpenter.k8s.aws" is restricted
-                              rule: self.all(x, x in ["karpenter.k8s.aws/instance-encryption-in-transit-supported", "karpenter.k8s.aws/instance-category", "karpenter.k8s.aws/instance-hypervisor", "karpenter.k8s.aws/instance-family", "karpenter.k8s.aws/instance-generation", "karpenter.k8s.aws/instance-local-nvme", "karpenter.k8s.aws/instance-size", "karpenter.k8s.aws/instance-cpu","karpenter.k8s.aws/instance-memory", "karpenter.k8s.aws/instance-network-bandwidth", "karpenter.k8s.aws/instance-gpu-name", "karpenter.k8s.aws/instance-gpu-manufacturer", "karpenter.k8s.aws/instance-gpu-count", "karpenter.k8s.aws/instance-gpu-memory", "karpenter.k8s.aws/instance-accelerator-name", "karpenter.k8s.aws/instance-accelerator-manufacturer", "karpenter.k8s.aws/instance-accelerator-count"] || !x.find("^([^/]+)").endsWith("karpenter.k8s.aws"))
+                              rule: self.all(x, x in ["karpenter.k8s.aws/instance-encryption-in-transit-supported", "karpenter.k8s.aws/instance-category", "karpenter.k8s.aws/instance-hypervisor", "karpenter.k8s.aws/instance-family", "karpenter.k8s.aws/instance-generation", "karpenter.k8s.aws/instance-local-nvme", "karpenter.k8s.aws/instance-size", "karpenter.k8s.aws/instance-cpu","karpenter.k8s.aws/instance-cpu-manufacturer","karpenter.k8s.aws/instance-memory", "karpenter.k8s.aws/instance-network-bandwidth", "karpenter.k8s.aws/instance-gpu-name", "karpenter.k8s.aws/instance-gpu-manufacturer", "karpenter.k8s.aws/instance-gpu-count", "karpenter.k8s.aws/instance-gpu-memory", "karpenter.k8s.aws/instance-accelerator-name", "karpenter.k8s.aws/instance-accelerator-manufacturer", "karpenter.k8s.aws/instance-accelerator-count"] || !x.find("^([^/]+)").endsWith("karpenter.k8s.aws"))
                       type: object
                     spec:
                       description: NodeClaimSpec describes the desired state of the NodeClaim
@@ -354,7 +354,7 @@ spec:
                                   - message: label "kubernetes.io/hostname" is restricted
                                     rule: self != "kubernetes.io/hostname"
                                   - message: label domain "karpenter.k8s.aws" is restricted
-                                    rule: self in ["karpenter.k8s.aws/instance-encryption-in-transit-supported", "karpenter.k8s.aws/instance-category", "karpenter.k8s.aws/instance-hypervisor", "karpenter.k8s.aws/instance-family", "karpenter.k8s.aws/instance-generation", "karpenter.k8s.aws/instance-local-nvme", "karpenter.k8s.aws/instance-size", "karpenter.k8s.aws/instance-cpu","karpenter.k8s.aws/instance-memory", "karpenter.k8s.aws/instance-network-bandwidth", "karpenter.k8s.aws/instance-gpu-name", "karpenter.k8s.aws/instance-gpu-manufacturer", "karpenter.k8s.aws/instance-gpu-count", "karpenter.k8s.aws/instance-gpu-memory", "karpenter.k8s.aws/instance-accelerator-name", "karpenter.k8s.aws/instance-accelerator-manufacturer", "karpenter.k8s.aws/instance-accelerator-count"] || !self.find("^([^/]+)").endsWith("karpenter.k8s.aws")
+                                    rule: self in ["karpenter.k8s.aws/instance-encryption-in-transit-supported", "karpenter.k8s.aws/instance-category", "karpenter.k8s.aws/instance-hypervisor", "karpenter.k8s.aws/instance-family", "karpenter.k8s.aws/instance-generation", "karpenter.k8s.aws/instance-local-nvme", "karpenter.k8s.aws/instance-size", "karpenter.k8s.aws/instance-cpu","karpenter.k8s.aws/instance-cpu-manufacturer","karpenter.k8s.aws/instance-memory", "karpenter.k8s.aws/instance-network-bandwidth", "karpenter.k8s.aws/instance-gpu-name", "karpenter.k8s.aws/instance-gpu-manufacturer", "karpenter.k8s.aws/instance-gpu-count", "karpenter.k8s.aws/instance-gpu-memory", "karpenter.k8s.aws/instance-accelerator-name", "karpenter.k8s.aws/instance-accelerator-manufacturer", "karpenter.k8s.aws/instance-accelerator-count"] || !self.find("^([^/]+)").endsWith("karpenter.k8s.aws")
                               minValues:
                                 description: |-
                                   This field is ALPHA and can be dropped or replaced at any time

diff --git a/pkg/apis/v1beta1/labels.go b/pkg/apis/v1beta1/labels.go
@@ -35,6 +35,7 @@ func init() {
 		LabelInstanceSize,
 		LabelInstanceLocalNVME,
 		LabelInstanceCPU,
+		LabelInstanceCPUManufacturer,
 		LabelInstanceMemory,
 		LabelInstanceNetworkBandwidth,
 		LabelInstanceGPUName,
@@ -103,6 +104,7 @@ var (
 	LabelInstanceLocalNVME                    = Group + "/instance-local-nvme"
 	LabelInstanceSize                         = Group + "/instance-size"
 	LabelInstanceCPU                          = Group + "/instance-cpu"
+	LabelInstanceCPUManufacturer              = Group + "/instance-cpu-manufacturer"
 	LabelInstanceMemory                       = Group + "/instance-memory"
 	LabelInstanceNetworkBandwidth             = Group + "/instance-network-bandwidth"
 	LabelInstanceGPUName                      = Group + "/instance-gpu-name"