Sync with upstream v1.20.3 (#130)

* Fix cluster-autoscaler clusterapi sample manifest

This commit fixes sample manifest of cluster-autoscaler clusterapi
provider.

(cherry picked from commit a5fee21)

* Adding functionality to cordon the node before destroying it. This helps load balancer to remove the node from healthy hosts (ALB does have this support).
This won't fix the issue of 502 completely as there is some time node has to live even after cordoning as to serve In-Flight request but load balancer can be configured to remove Cordon nodes from healthy host list.
This feature is enabled by cordon-node-before-terminating flag with default value as false to retain existing behavior.

* Set maxAsgNamesPerDescribe to the new maximum value

While this was previously effectively limited to 50, `DescribeAutoScalingGroups` now supports
fetching 100 ASG per calls on all regions, matching what's documented:
https://docs.aws.amazon.com/autoscaling/ec2/APIReference/API_DescribeAutoScalingGroups.html
```
     AutoScalingGroupNames.member.N
       The names of the Auto Scaling groups.
       By default, you can only specify up to 50 names.
       You can optionally increase this limit using the MaxRecords parameter.
     MaxRecords
       The maximum number of items to return with this call.
       The default value is 50 and the maximum value is 100.
```

Doubling this halves API calls on large clusters, which should help to prevent throttling.

* Break out unmarshal from GenerateEC2InstanceTypes

Refactor to allow for optimisation

* Optimise GenerateEC2InstanceTypes unmarshal memory usage

The pricing json for us-east-1 is currently 129MB. Currently fetching
this into memory and parsing results in a large memory footprint on
startup, and can lead to the autoscaler being OOMKilled.

Change the ReadAll/Unmarshal logic to a stream decoder to significantly
reduce the memory use.

* use aws sdk to find region

* update readme

* Update cluster-autoscaler/cloudprovider/aws/README.md

Co-authored-by: Guy Templeton <[email protected]>

* Merge pull request kubernetes#4274 from kinvolk/imran/cloud-provider-packet-fix

Cloud provider[Packet] fixes

* Fix bug where a node that becomes ready after 2 mins can be treated as unready. Deprecated LongNotStarted

 In cases where node n1 would:
 1) Be created at t=0min
 2) Ready condition is true at t=2.5min
 3) Not ready taint is removed at t=3min
 the ready node is counted as unready

 Tested cases after fix:
 1) Case described above
 2) Nodes not starting even after 15mins still
 treated as unready
 3) Nodes created long ago that suddenly become unready are
 counted as unready.

* Improve misleading log

Signed-off-by: Sylvain Rabot <[email protected]>

* dont proactively decrement azure cache for unregistered nodes

* Cluster Autoscaler: fix unit tests after kubernetes#3924 was backported to 1.20 in kubernetes#4319

The backport included unit tests using a function that changed signature
after 1.20. This was not detected before merging because CI is not
running correctly on 1.20.

* Cluster Autoscaler: backport Github Actions CI to 1.20 (kubernetes#4366)

* annotate fakeNodes so that cloudprovider implementations can identify them if needed

* move annotations to cloudprovider package

* fix 1.19 test

* remove flaky test that's removed in master

* Cluster Autoscaler 1.20.1

* Make arch-specific releases use separate images instead of tags on the same image

This seems to be the current convention in k8s.

* Cluster Autoscaler: add arch-specific build targets to .gitignore

* CA - AWS - Instance List Update 03-10-21 - 1.20 release branch

* CA - AWS - Instance List Update 29-10-21 - 1.20 release branch

* Cluster-Autoscaler update AWS EC2 instance types with g5, m6 and r6

* CA - AWS Instance List Update - 13/12/21 - 1.20

* Merge pull request kubernetes#4497 from marwanad/add-more-azure-instance-types

add more azure instance types

* Cluster Autoscaler 1.20.2

* Add `--feature-gates` flag to support scale up on volume limits (CSI migration enabled)

Signed-off-by: ialidzhikov <[email protected]>

* CA - AWS Cloud Provider - 1.20 Static Instance List Update 02-06-2022

* Cluster Autoscaler - 1.20.3 release

* sync_file updates & other changes

* Updating vendor against [email protected]:kubernetes/kubernetes.git:e3de62298a730415c5d2ab72607ef6adadd6304d (e3de622)

* fixed some declaration errors

Co-authored-by: Kubernetes Prow Robot <[email protected]>
Co-authored-by: Hidekazu Nakamura <[email protected]>
Co-authored-by: atul <[email protected]>
Co-authored-by: Benjamin Pineau <[email protected]>
Co-authored-by: Adrian Lai <[email protected]>
Co-authored-by: darkpssngr <[email protected]>
Co-authored-by: Guy Templeton <[email protected]>
Co-authored-by: Vivek Bagade <[email protected]>
Co-authored-by: Sylvain Rabot <[email protected]>
Co-authored-by: Marwan Ahmed <[email protected]>
Co-authored-by: Jakub Tużnik <[email protected]>
Co-authored-by: GuyTempleton <[email protected]>
Co-authored-by: sturman <[email protected]>
Co-authored-by: Maciek Pytel <[email protected]>
Co-authored-by: ialidzhikov <[email protected]>

.github/workflows/ci.yaml

@@ -0,0 +1,36 @@
+name: Tests
+
+on:
+  - push
+  - pull_request
+
+env:
+  GOPATH: ${{ github.workspace }}/go
+
+jobs:
+  test-and-verify:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Set up Go
+        uses: actions/setup-go@v2
+        with:
+          go-version: 1.15
+
+      - uses: actions/checkout@v2
+        with:
+          path: ${{ env.GOPATH }}/src/k8s.io/autoscaler
+
+      - name: Apt-get
+        run: sudo apt-get install libseccomp-dev -qq
+
+      - name: Prepare
+        working-directory: ${{ env.GOPATH }}/src/k8s.io/autoscaler
+        run: hack/install-verify-tools.sh
+
+      - name: Verify
+        working-directory: ${{ env.GOPATH }}/src/k8s.io/autoscaler
+        run: hack/verify-all.sh -v
+
+      - name: Test
+        working-directory: ${{ env.GOPATH }}/src/k8s.io/autoscaler
+        run: hack/for-go-proj.sh test

cluster-autoscaler/.gitignore

@@ -1,4 +1,6 @@
 cluster-autoscaler
+cluster-autoscaler-amd64
+cluster-autoscaler-arm64
 cluster_autoscaler
 main
 .cover

cluster-autoscaler/Makefile

@@ -28,6 +28,9 @@ ifdef DOCKER_RM
 else
   RM_FLAG=
 endif
+IMAGE=$(REGISTRY)/cluster-autoscaler$(PROVIDER)
+
+export DOCKER_CLI_EXPERIMENTAL := enabled
 
 build: build-arch-$(GOARCH)
 
@@ -53,24 +56,24 @@ make-image: make-image-arch-$(GOARCH)
 make-image-arch-%:
 ifdef BASEIMAGE
 	docker build --pull --build-arg BASEIMAGE=${BASEIMAGE} \
-		-t ${REGISTRY}/cluster-autoscaler${PROVIDER}:${TAG}-$* \
+		-t ${IMAGE}-$*:${TAG} \
 		-f Dockerfile.$* .
 else
 	docker build --pull \
-		-t ${REGISTRY}/cluster-autoscaler${PROVIDER}:${TAG}-$* \
+		-t ${IMAGE}-$*:${TAG} \
 		-f Dockerfile.$* .
 endif
 	@echo "Image ${TAG}${FOR_PROVIDER}-$* completed"
 
 push-image: push-image-arch-$(GOARCH)
 
 push-image-arch-%:
-	./push_image.sh ${REGISTRY}/cluster-autoscaler${PROVIDER}:${TAG}-$*
+	./push_image.sh ${IMAGE}-$*:${TAG}
 
 push-manifest:
-	DOCKER_CLI_EXPERIMENTAL=enabled docker manifest create ${REGISTRY}/cluster-autoscaler${PROVIDER}:${TAG} \
-		$(addprefix $(REGISTRY)/cluster-autoscaler$(PROVIDER):$(TAG)-, $(ALL_ARCH))
-	DOCKER_CLI_EXPERIMENTAL=enabled docker manifest push --purge ${REGISTRY}/cluster-autoscaler${PROVIDER}:${TAG}
+	docker manifest create ${IMAGE}:${TAG} \
+	    $(addprefix $(REGISTRY)/cluster-autoscaler$(PROVIDER)-, $(addsuffix :$(TAG), $(ALL_ARCH)))
+	docker manifest push --purge ${IMAGE}:${TAG}
 
 execute-release: $(addprefix make-image-arch-,$(ALL_ARCH)) $(addprefix push-image-arch-,$(ALL_ARCH)) push-manifest
 	@echo "Release ${TAG}${FOR_PROVIDER} completed"

cluster-autoscaler/SYNC-CHANGES/SYNC-CHANGES-1.20.md

@@ -7,7 +7,13 @@
         - [During merging](#during-merging)
         - [During vendoring k8s](#during-vendoring-k8s)
         - [Others](#others)
-
+- [v1.20.1](#v1201)
+    - [Synced with which upstream CA](#synced-with-which-upstream-ca-1)
+    - [Changes made](#changes-made-1)
+        - [To FAQ](#to-faq-1)
+        - [During merging](#during-merging-1)
+        - [During vendoring k8s](#during-vendoring-k8s-1)
+        - [Others](#others-1)
 
 
 # v1.20.0
@@ -34,3 +40,21 @@ _None_
 ### Others
 - Updated README.md for cluster-autoscaler repo to contain new [release matrix](../README.md#releases-gardenerautoscaler) of Gardener Autoscaler
 
+# v1.20.1
+
+
+## Synced with which upstream CA
+
+[v1.20.3](https://github.com/kubernetes/autoscaler/tree/cluster-autoscaler-1.20.3/cluster-autoscaler)
+
+## Changes made
+
+### To FAQ
+_None_
+### During merging
+- didn't update `cluster-autoscaler/cloudprovider/aws/ec2_instance_types.go` as its not used anymore by mcm, the one used
+now (in worst case) is `cluster-autoscaler/cloudprovider/mcm/ec2_instance_types.go`
+### During vendoring k8s
+_None_
+### Others
+_None_

cluster-autoscaler/cloudprovider/aws/README.md

@@ -354,3 +354,6 @@ To refresh static list, please run `go run ec2_instance_types/gen.go` under
   `aws:///us-east-1a/i-01234abcdef`.
 * If you want to use regional STS endpoints (e.g. when using VPC endpoint for
   STS) the env `AWS_STS_REGIONAL_ENDPOINTS=regional` should be set.
+* If you want to run it on instances with IMDSv1 disabled make sure your
+  EC2 launch configuration has the setting `Metadata response hop limit` set to `2`.
+  Otherwise, the `/latest/api/token` call will timeout and result in an error. See [AWS docs here](https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/configuring-instance-metadata-service.html#configuring-instance-metadata-options) for further information. 

cluster-autoscaler/cloudprovider/aws/auto_scaling_test.go

@@ -27,22 +27,22 @@ import (
 	"github.com/stretchr/testify/require"
 )
 
-func TestMoreThen50Groups(t *testing.T) {
+func TestMoreThen100Groups(t *testing.T) {
 	service := &AutoScalingMock{}
 	autoScalingWrapper := &autoScalingWrapper{
 		autoScaling: service,
 	}
 
-	// Generate 51 ASG names
-	names := make([]string, 51)
+	// Generate 101 ASG names
+	names := make([]string, 101)
 	for i := 0; i < len(names); i++ {
 		names[i] = fmt.Sprintf("asg-%d", i)
 	}
 
-	// First batch, first 50 elements
+	// First batch, first 100 elements
 	service.On("DescribeAutoScalingGroupsPages",
 		&autoscaling.DescribeAutoScalingGroupsInput{
-			AutoScalingGroupNames: aws.StringSlice(names[:50]),
+			AutoScalingGroupNames: aws.StringSlice(names[:100]),
 			MaxRecords:            aws.Int64(maxRecordsReturnedByAPI),
 		},
 		mock.AnythingOfType("func(*autoscaling.DescribeAutoScalingGroupsOutput, bool) bool"),
@@ -51,10 +51,10 @@ func TestMoreThen50Groups(t *testing.T) {
 		fn(testNamedDescribeAutoScalingGroupsOutput("asg-1", 1, "test-instance-id"), false)
 	}).Return(nil)
 
-	// Second batch, element 51
+	// Second batch, element 101
 	service.On("DescribeAutoScalingGroupsPages",
 		&autoscaling.DescribeAutoScalingGroupsInput{
-			AutoScalingGroupNames: aws.StringSlice([]string{"asg-50"}),
+			AutoScalingGroupNames: aws.StringSlice([]string{"asg-100"}),
 			MaxRecords:            aws.Int64(maxRecordsReturnedByAPI),
 		},
 		mock.AnythingOfType("func(*autoscaling.DescribeAutoScalingGroupsOutput, bool) bool"),

cluster-autoscaler/cloudprovider/aws/aws_manager.go

@@ -49,7 +49,7 @@ const (
 	operationWaitTimeout    = 5 * time.Second
 	operationPollInterval   = 100 * time.Millisecond
 	maxRecordsReturnedByAPI = 100
-	maxAsgNamesPerDescribe  = 50
+	maxAsgNamesPerDescribe  = 100
 	refreshInterval         = 1 * time.Minute
 	autoDiscovererTypeASG   = "asg"
 	asgAutoDiscovererKeyTag = "tag"
@@ -312,7 +312,7 @@ func (m *AwsManager) getAsgTemplate(asg *asg) (*asgTemplate, error) {
 	region := az[0 : len(az)-1]
 
 	if len(asg.AvailabilityZones) > 1 {
-		klog.Warningf("Found multiple availability zones for ASG %q; using %s\n", asg.Name, az)
+		klog.V(4).Infof("Found multiple availability zones for ASG %q; using %s for %s label\n", asg.Name, az, apiv1.LabelFailureDomainBetaZone)
 	}
 
 	instanceTypeName, err := m.buildInstanceType(asg)

cluster-autoscaler/cloudprovider/aws/aws_util.go

@@ -20,21 +20,26 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"github.com/aws/aws-sdk-go/aws/endpoints"
-	"io/ioutil"
-	klog "k8s.io/klog/v2"
+	"io"
 	"net/http"
 	"os"
 	"regexp"
 	"strconv"
 	"strings"
+
+	"github.com/aws/aws-sdk-go/aws"
+	"github.com/aws/aws-sdk-go/aws/ec2metadata"
+	"github.com/aws/aws-sdk-go/aws/endpoints"
+	"github.com/aws/aws-sdk-go/aws/session"
+
+	klog "k8s.io/klog/v2"
 )
 
 var (
-	ec2MetaDataServiceUrl          = "http://169.254.169.254/latest/dynamic/instance-identity/document"
+	ec2MetaDataServiceUrl          = "http://169.254.169.254"
 	ec2PricingServiceUrlTemplate   = "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonEC2/current/%s/index.json"
 	ec2PricingServiceUrlTemplateCN = "https://pricing.cn-north-1.amazonaws.com.cn/offers/v1.0/cn/AmazonEC2/current/%s/index.json"
-	staticListLastUpdateTime       = "2019-10-14"
+	staticListLastUpdateTime       = "2022-06-02"
 )
 
 type response struct {
@@ -82,16 +87,9 @@ func GenerateEC2InstanceTypes(region string) (map[string]*InstanceType, error) {
 
 			defer res.Body.Close()
 
-			body, err := ioutil.ReadAll(res.Body)
+			unmarshalled, err := unmarshalProductsResponse(res.Body)
 			if err != nil {
-				klog.Warningf("Error parsing %s skipping...\n", url)
-				continue
-			}
-
-			var unmarshalled = response{}
-			err = json.Unmarshal(body, &unmarshalled)
-			if err != nil {
-				klog.Warningf("Error unmarshalling %s, skip...\n", url)
+				klog.Warningf("Error parsing %s skipping...\n%s\n", url, err)
 				continue
 			}
 
@@ -127,6 +125,58 @@ func GetStaticEC2InstanceTypes() (map[string]*InstanceType, string) {
 	return InstanceTypes, staticListLastUpdateTime
 }
 
+func unmarshalProductsResponse(r io.Reader) (*response, error) {
+	dec := json.NewDecoder(r)
+	t, err := dec.Token()
+	if err != nil {
+		return nil, err
+	}
+	if delim, ok := t.(json.Delim); !ok || delim.String() != "{" {
+		return nil, errors.New("Invalid products json")
+	}
+
+	unmarshalled := response{map[string]product{}}
+
+	for dec.More() {
+		t, err = dec.Token()
+		if err != nil {
+			return nil, err
+		}
+
+		if t == "products" {
+			tt, err := dec.Token()
+			if err != nil {
+				return nil, err
+			}
+			if delim, ok := tt.(json.Delim); !ok || delim.String() != "{" {
+				return nil, errors.New("Invalid products json")
+			}
+			for dec.More() {
+				productCode, err := dec.Token()
+				if err != nil {
+					return nil, err
+				}
+
+				prod := product{}
+				if err = dec.Decode(&prod); err != nil {
+					return nil, err
+				}
+				unmarshalled.Products[productCode.(string)] = prod
+			}
+		}
+	}
+
+	t, err = dec.Token()
+	if err != nil {
+		return nil, err
+	}
+	if delim, ok := t.(json.Delim); !ok || delim.String() != "}" {
+		return nil, errors.New("Invalid products json")
+	}
+
+	return &unmarshalled, nil
+}
+
 func parseMemory(memory string) int64 {
 	reg, err := regexp.Compile("[^0-9\\.]+")
 	if err != nil {
@@ -155,26 +205,13 @@ func GetCurrentAwsRegion() (string, error) {
 	region, present := os.LookupEnv("AWS_REGION")
 
 	if !present {
-		klog.V(1).Infof("fetching %s\n", ec2MetaDataServiceUrl)
-		res, err := http.Get(ec2MetaDataServiceUrl)
-		if err != nil {
-			return "", fmt.Errorf("Error fetching %s", ec2MetaDataServiceUrl)
-		}
-
-		defer res.Body.Close()
-
-		body, err := ioutil.ReadAll(res.Body)
+		c := aws.NewConfig().
+			WithEndpoint(ec2MetaDataServiceUrl)
+		sess, err := session.NewSession()
 		if err != nil {
-			return "", fmt.Errorf("Error parsing %s", ec2MetaDataServiceUrl)
+			return "", fmt.Errorf("failed to create session")
 		}
-
-		var unmarshalled = map[string]string{}
-		err = json.Unmarshal(body, &unmarshalled)
-		if err != nil {
-			klog.Warningf("Error unmarshalling %s, skip...\n", ec2MetaDataServiceUrl)
-		}
-
-		region = unmarshalled["region"]
+		return ec2metadata.New(sess, c).Region()
 	}
 
 	return region, nil