K8s 향상된 워크로드 OpenKruise 운영 및 유지 관리 개선

# sidecarset-demo.yaml
apiVersion: apps.kruise.io/v1alpha1
kind: SidecarSet
metadata:
name: scs-demo
spec:
selector:
matchLabels: # 非常重要的属性，会去匹配具有 app=nginx 的 Pod
app: nginx
updateStrategy:
type: RollingUpdate
maxUnavailable: 1
containers:
- name: sidecar1
image: busybox
command: ["sleep", "999d"]
volumeMounts:
- name: log-volume
mountPath: /var/log
volumes: # 该属性会被合并到 pod.spec.volumes 去
- name: log-volume
emptyDir: {}

➜ kubectl get sidecarset
NAME MATCHED UPDATED READY AGE
scs-demo 0 0 0 6s

apiVersion: v1
kind: Pod
metadata:
labels:
app: nginx # 匹配 SidecarSet 里面指定的标签
name: test-pod
spec:
containers:
- name: app
image: nginx:1.7.9

➜ kubectl get pod test-pod
NAME READY STATUSRESTARTS AGE
test-pod 2/2 Running 022s

➜ kubectl get pod test-pod -o yaml
apiVersion: v1
kind: Pod
metadata:
labels:
app: nginx
name: test-pod
namespace: default
spec:
containers:
- command:
- sleep
- 999d
env:
- name: IS_INJECTED
value: "true"
image: busybox
imagePullPolicy: Always
name: sidecar1
resources: {}
volumeMounts:
- mountPath: /var/log
name: log-volume
- image: nginx:1.7.9
imagePullPolicy: IfNotPresent
name: app
# ......
volumes:
- emptyDir: {}
name: log-volume
# ......

➜ kubectl patch sidecarset scs-demo --type='json' -p='[{"op": "replace", "path": "/spec/containers/0/image", "value": "busybox:1.35.0"}]'
sidecarset.apps.kruise.io/scs-demo patched

➜ kubectl get pod test-pod
NAME READY STATUSRESTARTSAGE
test-pod 2/2 Running 1 (67s ago) 28m
➜ kubectl describe pod test-pod
......
Events:
TypeReason AgeFrom Message
---------- ---- ---- -------
# ......
NormalCreated10mkubeletCreated container app
NormalStarted10mkubeletStarted container app
NormalKilling114s kubeletContainer sidecar1 definition changed, will be restarted
NormalPulling84skubeletPulling image "busybox:1.35.0"
NormalCreated77s (x2 over 11m)kubeletCreated container sidecar1
NormalStarted77s (x2 over 11m)kubeletStarted container sidecar1
NormalPulled 77skubeletSuccessfully pulled image "busybox:1.35.0" in 6.901558972s (6.901575894s including waiting)
➜ kubectl get pod test-pod -o yaml |grep busybox
kruise.io/sidecarset-inplace-update-state: '{"scs-demo":{"revision":"f78z4854d9855xd6478fzx9c84645z2548v24z26455db46bdfzw44v49v98f2cw","updateTimestamp":"2023-04-04T08:05:18Z","lastContainerStatuses":{"sidecar1":{"imageID":"docker.io/library/busybox@sha256:b5d6fe0712636ceb7430189de28819e195e8966372edfc2d9409d79402a0dc16"}}}}'
image: busybox:1.35.0
image: docker.io/library/busybox:1.35.0
imageID: docker.io/library/busybox@sha256:223ae047b1065bd069aac01ae3ac8088b3ca4a527827e283b85112f29385fb1b

apiVersion: apps.kruise.io/v1alpha1
kind: SidecarSet
metadata:
name: sidecarset
spec:
selector:
matchLabels:
app: sample
containers:
# 默认的 K8s 容器字段
- name: nginx
image: nginx:alpine
volumeMounts:
- mountPath: /nginx/conf
name: nginxconf
# 扩展的 sidecar 容器字段
podInjectPolicy: BeforeAppContainer
shareVolumePolicy: # 数据卷共享
type: disabled | enabled
transferEnv: # 环境变量共享
- sourceContainerName: main # 会把main容器中的PROXY_IP环境变量注入到当前定义的sidecar容器中
envName: PROXY_IP
volumes:
- Name: nginxconf
hostPath: /data/nginx/conf

apiVersion: apps.kruise.io/v1alpha1
kind: SidecarSet
metadata:
name: sidecarset
spec:
# ...
updateStrategy:
type: RollingUpdate
maxUnavailable: 20%
partition: 10
paused: true

apiVersion: apps/v1
kind: Deployment
metadata:
name: nginx
namespace: default
spec:
replicas: 3
revisionHistoryLimit: 3
selector:
matchLabels:
app: nginx
template:
metadata:
labels:
app: nginx
spec:
containers:
- name: ngx
image: nginx:1.7.9
ports:
- containerPort: 80

➜ kubectl get pods -l app=nginx
NAMEREADY STATUSRESTARTS AGE
nginx-6457955f7-7hnjw 2/2 Running 051s
nginx-6457955f7-prkgz 2/2 Running 051s
nginx-6457955f7-tbtxk 2/2 Running 051s
test-pod2/2 Running 04m2s

piVersion: apps.kruise.io/v1alpha1
kind: SidecarSet
metadata:
name: test-sidecarset
spec:
updateStrategy:
type: RollingUpdate
selector:
matchLabels:
canary.release: "true"
containers:
- name: sidecar1
image: busybox:1.35.0
# ......

apiVersion: v1
kind: Pod
metadata:
labels:
app: nginx
canary.release: "true"
name: test-pod
spec:
containers:
- name: app
image: nginx:1.7.9

➜ kubectl describe pod test-pod
Events:
TypeReason AgeFrom Message
---------- ---- ---- -------
NormalKilling7m53skubeletContainer sidecar1 definition changed, will be restarted
NormalCreated7m23s (x2 over 8m17s)kubeletCreated container sidecar1
NormalStarted7m23s (x2 over 8m17s)kubeletStarted container sidecar1
NormalPulling7m23skubeletPulling image "busybox"
NormalPulled 7m23skubeletSuccessfully pulled image "busybox" in 603.928658ms

# hotupgrade-sidecarset.yaml
apiVersion: apps.kruise.io/v1alpha1
kind: SidecarSet
metadata:
name: hotupgrade-sidecarset
spec:
selector:
matchLabels:
app: hotupgrade
containers:
- name: sidecar
image: openkruise/hotupgrade-sample:sidecarv1
imagePullPolicy: Always
lifecycle:
postStart:
exec:
command:
- /bin/sh
- /migrate.sh
upgradeStrategy:
upgradeType: HotUpgrade
hotUpgradeEmptyImage: openkruise/hotupgrade-sample:empty

# hotupgrade-cloneset.yaml
apiVersion: apps.kruise.io/v1alpha1
kind: CloneSet
metadata:
name: busybox
labels:
app: hotupgrade
spec:
replicas: 1
selector:
matchLabels:
app: hotupgrade
template:
metadata:
labels:
app: hotupgrade
spec:
containers:
- name: busybox
image: openkruise/hotupgrade-sample:busybox

➜ kubectl get sidecarset hotupgrade-sidecarset
NAMEMATCHED UPDATED READY AGE
hotupgrade-sidecarset 1 1 0 58s
➜ kubectl get pods -l app=hotupgrade
NAMEREADY STATUSRESTARTS AGE
busybox-nd5bp 3/3 Running 031s
➜ kubectl describe pod busybox-nd5bp
Name: busybox-nd5bp
Namespace:default
Node: node2/10.206.16.10
# ......
Controlled By:CloneSet/busybox
Containers:
sidecar-1:
Container ID: containerd://511aa4b60d36483177e92805653c1b618495e47d8d5de331008259f78b3be89e
Image:openkruise/hotupgrade-sample:sidecarv1
Image ID: docker.io/openkruise/hotupgrade-sample@sha256:3d677ca19712b67d2c264374736d71089d21e100eff341f6b4bb0f5288ec6f34
Environment:
IS_INJECTED: true
SIDECARSET_VERSION: (v1:metadata.annotations['version.sidecarset.kruise.io/sidecar-1'])
SIDECARSET_VERSION_ALT: (v1:metadata.annotations['versionalt.sidecarset.kruise.io/sidecar-1'])
# ......
sidecar-2:
Container ID: containerd://6b0678695ccb977695248e41108606b409ad0c7e3e4fe1ba9b48e839e3c235ef
Image:openkruise/hotupgrade-sample:empty
Image ID: docker.io/openkruise/hotupgrade-sample@sha256:606be602967c9f91c47e4149af4336c053e26225b717a1b5453ac8fa9a401cc5
Environment:
IS_INJECTED: true
SIDECARSET_VERSION: (v1:metadata.annotations['version.sidecarset.kruise.io/sidecar-2'])
SIDECARSET_VERSION_ALT: (v1:metadata.annotations['versionalt.sidecarset.kruise.io/sidecar-2'])
# ......
busybox:
Container ID: containerd://da7eebb0161bab37f7de75635e68c5284a973a21f6d3f095bb5e8212ac8ce908
Image:openkruise/hotupgrade-sample:busybox
Image ID: docker.io/openkruise/hotupgrade-sample@sha256:08f9ede05850686e1200240e5e376fc76245dd2eb56299060120b8c3dba46dc9
# ......
# ......
Events:
TypeReason Age From Message
---------- -------- -------
NormalScheduled50s default-schedulerSuccessfully assigned default/busybox-nd5bp to node2
NormalPulling49s kubeletPulling image "openkruise/hotupgrade-sample:sidecarv1"
NormalPulled 41s kubeletSuccessfully pulled image "openkruise/hotupgrade-sample:sidecarv1" in 7.929984849s (7.929998445s including waiting)
NormalCreated41s kubeletCreated container sidecar-1
NormalStarted41s kubeletStarted container sidecar-1
NormalPulling36s kubeletPulling image "openkruise/hotupgrade-sample:empty"
NormalPulled 29s kubeletSuccessfully pulled image "openkruise/hotupgrade-sample:empty" in 7.434180553s (7.434189239s including waiting)
NormalCreated29s kubeletCreated container sidecar-2
NormalStarted29s kubeletStarted container sidecar-2
NormalPulling29s kubeletPulling image "openkruise/hotupgrade-sample:busybox"
NormalPulled 22s kubeletSuccessfully pulled image "openkruise/hotupgrade-sample:busybox" in 6.583450981s (6.583456512s including waiting)
NormalCreated22s kubeletCreated container busybox
NormalStarted22s kubeletStarted container busybox
......

➜ kubectl logs -f busybox-nd5bp -c busybox
I0404 09:12:26.513128 1 main.go:39] request sidecar server success, and response(body=This is version(v1) sidecar)
I0404 09:12:26.623496 1 main.go:39] request sidecar server success, and response(body=This is version(v1) sidecar)
I0404 09:12:26.733958 1 main.go:39] request sidecar server success, and response(body=This is version(v1) sidecar)
......

➜ kubectl patch sidecarset hotupgrade-sidecarset --type='json' -p='[{"op": "replace", "path": "/spec/containers/0/image", "value": "openkruise/hotupgrade-sample:sidecarv2"}]'

➜ kubectl get pods -l app=hotupgrade
NAMEREADY STATUSRESTARTSAGE
busybox-nd5bp 3/3 Running 2 (45s ago) 23m
➜ kubectl describe pods busybox-nd5bp
......
Events:
......
NormalPulling33skubeletPulling image "openkruise/hotupgrade-sample:sidecarv2"
NormalKilling33skubeletContainer sidecar-2 definition changed, will be restarted
NormalStarted25s (x2 over 22m)kubeletStarted container sidecar-2
NormalCreated25s (x2 over 22m)kubeletCreated container sidecar-2
NormalPulled 25skubeletSuccessfully pulled image "openkruise/hotupgrade-sample:sidecarv2" in 8.169453753s (8.16946743s including waiting)
NormalKilling14skubeletContainer sidecar-1 definition changed, will be restarted
NormalResetContainerSucceed14ssidecarset-controllerreset sidecar container image empty successfully
NormalPulling14skubeletPulling image "openkruise/hotupgrade-sample:empty"
NormalCreated12s (x2 over 22m)kubeletCreated container sidecar-1
NormalStarted12s (x2 over 22m)kubeletStarted container sidecar-1
NormalPulled 12skubeletSuccessfully pulled image "openkruise/hotupgrade-sample:empty" in 1.766097364s (1.766109087s including waiting)

➜ kubectl logs -f busybox-nd5bp -c busybox
I0306 11:08:47.587727 1 main.go:39] request sidecar server success, and response(body=This is version(v1) sidecar)
I0404 09:14:28.588973 1 main.go:39] request sidecar server success, and response(body=This is version(v2) sidecar)
# ......

# crr-demo.yaml
apiVersion: apps.kruise.io/v1alpha1
kind: ContainerRecreateRequest
metadata:
name: crr-dmo
spec:
podName: pod-name
containers: # 要重建的容器名字列表，至少要有 1 个
- name: app
- name: sidecar
strategy:
failurePolicy: Fail # 'Fail' 或 'Ignore'，表示一旦有某个容器停止或重建失败， CRR 立即结束
orderedRecreate: false # 'true' 表示要等前一个容器重建完成了，再开始重建下一个
terminationGracePeriodSeconds: 30 # 等待容器优雅退出的时间，不填默认用 Pod 中定义的
unreadyGracePeriodSeconds: 3 # 在重建之前先把 Pod 设为 not ready，并等待这段时间后再开始执行重建
minStartedSeconds: 10 # 重建后新容器至少保持运行这段时间，才认为该容器重建成功
activeDeadlineSeconds: 300 # 如果 CRR 执行超过这个时间，则直接标记为结束（未结束的容器标记为失败）
ttlSecondsAfterFinished: 1800 # CRR 结束后，过了这段时间自动被删除掉

➜ kubectl get nodeimage
NAMEDESIRED PULLING SUCCEED FAILED AGE
master1 0 0 0 05d
node1 0 0 0 05d
node2 0 0 0 05d

➜ kubectl get nodeimage node1 -o yaml
apiVersion: apps.kruise.io/v1alpha1
kind: NodeImage
metadata:
name: node1
# ......
spec: {}
status:
desired: 0
failed: 0
pulling: 0
succeeded: 0

......
spec:
images:
ubuntu:# 镜像 name
tags:
- tag: latest# 镜像 tag
pullPolicy:
ttlSecondsAfterFinished: 300# [required] 拉取完成（成功或失败）超过 300s 后，将这个任务从 NodeImage 中清除
timeoutSeconds: 600 # [optional] 每一次拉取的超时时间, 默认为 600
backoffLimit: 3 # [optional] 拉取的重试次数，默认为 3
activeDeadlineSeconds: 1200 # [optional] 整个任务的超时时间，无默认值

➜ kubectl describe nodeimage node1
Name: node1
Namespace:
# ......
Spec:
Images:
Ubuntu:
Tags:
Created At:2023-04-04T09:29:18Z
Pull Policy:
Active Deadline Seconds: 1200
Backoff Limit: 3
Timeout Seconds: 600
Ttl Seconds After Finished:300
Tag: latest
Status:
Desired:1
Failed: 0
Image Statuses:
Ubuntu:
Tags:
Completion Time:2023-04-04T09:29:28Z
Phase:Succeeded
Progress: 100
Start Time: 2023-04-04T09:29:18Z
Tag:latest
Pulling:0
Succeeded:1
Events:
TypeReasonAge From Message
------------------ -------
NormalPullImageSucceed11s kruise-daemon-imagepullerImage ubuntu:latest, ecalpsedTime 10.066193581s

ubuntu@node1:~$ sudo ctr -n k8s.io i ls|grep ubuntu
docker.io/library/ubuntu:latestapplication/vnd.oci.image.index.v1+json sha256:67211c14fa74f070d27cc59d69a7fa9aeff8e28ea118ef3babc295a0428a6d21 28.2 MiBlinux/amd64,linux/arm/v7,linux/arm64/v8,linux/ppc64le,linux/s390xio.cri-containerd.image=managed
docker.io/library/ubuntu@sha256:67211c14fa74f070d27cc59d69a7fa9aeff8e28ea118ef3babc295a0428a6d21 application/vnd.oci.image.index.v1+json sha256:67211c14fa74f070d27cc59d69a7fa9aeff8e28ea118ef3babc295a0428a6d21 28.2 MiBlinux/amd64,linux/arm/v7,linux/arm64/v8,linux/ppc64le,linux/s390xio.cri-containerd.image=managed
ubuntu@node1:~$

apiVersion: apps.kruise.io/v1alpha1
kind: ImagePullJob
metadata:
name: job-with-always
spec:
image: nginx:1.9.1 # [required] 完整的镜像名 name:tag
parallelism: 10 # [optional] 最大并发拉取的节点梳理, 默认为 1
selector: # [optional] 指定节点的 名字列表 或 标签选择器 (只能设置其中一种)
names:
- node1
- node2
matchLabels:
node-type: xxx
# podSelector: # [optional] pod label 选择器来在这些 pod 所在节点上拉取镜像, 与 selector 不能同时设置.
#pod-label: xxx
completionPolicy:
type: Always # [optional] 默认为 Always
activeDeadlineSeconds: 1200 # [optional] 无默认值, 只对 Alway 类型生效
ttlSecondsAfterFinished: 300 # [optional] 无默认值, 只对 Alway 类型生效
pullPolicy: # [optional] 默认 backoffLimit=3, timeoutSecnotallow=600
backoffLimit: 3
timeoutSeconds: 300
pullSecrets:
- secret-name1
- secret-name2

# ...
spec:
pullSecrets:
- secret-name1
- secret-name2

apiVersion: v1
kind: Pod
annotations:
apps.kruise.io/container-launch-priority: Ordered
spec:
containers:
- name: sidecar
# ...
- name: main
# ...

apiVersion: v1
kind: Pod
spec:
containers:
- name: main
# ...
- name: sidecar
env:
- name: KRUISE_CONTAINER_PRIORITY
value: "1"
# ...

apiVersion: apps.kruise.io/v1alpha1
kind: ResourceDistribution
metadata:
name: sample
spec:
resource: ... ...
targets: ... ...

apiVersion: apps.kruise.io/v1alpha1
kind: ResourceDistribution
metadata:
name: sample
spec:
resource:
apiVersion: v1
kind: ConfigMap
metadata:
name: game-demo
data:
game.properties: |
enemy.types=aliens,monsters
player.maximum-lives=5
player_initial_lives: "3"
ui_properties_file_name: user-interface.properties
user-interface.properties: |
color.good=purple
color.bad=yellow
allow.textmode=true
targets: ... ...

apiVersion: apps.kruise.io/v1alpha1
kind: ResourceDistribution
metadata:
name: sample
spec:
resource: ... ...
targets:
includedNamespaces:
list:
- name: ns-1
- name: ns-4
namespaceLabelSelector:
matchLabels:
group: test
excludedNamespaces:
list:
- name: ns-3

apiVersion: v1
kind: ConfigMap
metadata:
name: demo
annotations:
kruise.io/resourcedistribution.resource.from: sample
kruise.io/resourcedistribution.resource.distributed.timestamp: 2021-09-06 08:44:52.7861421 +0000 UTC m=+12896.810364601
kruise.io/resourcedistribution.resource.hashcode: 0821a13321b2c76b5bd63341a0d97fb46bfdbb2f914e2ad6b613d10632fa4b63
... ...