Argo Rollouts Canary 基础
Argo Rollouts Canary 概述
金丝雀部署是一种部署策略，将一小部分生产流量发布到新版本的应用程序。Argo Rollouts Canary 完整配置
apiVersion: argoproj.io/v1alpha1
kind: Rollout
metadata:
name: example-rollout-canary
spec:
# 运行的Pod实例数量，默认为1.
# Defaults to 1.
replicas: 5
analysis:
# 保留成功的数量
# Defaults to 5.
successfulRunHistoryLimit: 10
# 保留失败的数量
# Stages for unsuccessful: "Error", "Failed", "Inconclusive"
# Defaults to 5.
unsuccessfulRunHistoryLimit: 10
# 筛选Pod对象的标签选择器.
selector:
matchLabels:
app: guestbook
# WorkloadRef holds a references to a workload that provides Pod template
# (e.g. Deployment). If used, then do not use Rollout template property.
workloadRef:
apiVersion: apps/v1
kind: Deployment
name: rollout-ref-deployment
# 指定迁移到 Rollout 后是否缩减工作负载（Deployment）
# "never": Deployment 不会减少
# "onsuccess": 在 Rollout 变得健康后，Deployment会减少
# "progressively": 随着 Rollout 的增加，Deployment 也随之减少
# If the Rollout fails the Deployment will be scaled back up.
scaleDown: never|onsuccess|progressively
# Template describes the pods that will be created. Same as deployment.
# If used, then do not use Rollout workloadRef property.
template:
spec:
containers:
- name: guestbook
image: argoproj/rollouts-demo:blue
# 无容器crash的情况下，新建的Pod被视为可用的最短时长，默认为0，即立即转为Ready
minReadySeconds: 30
# 更新历史中保留的ReplicaSet Revision数量.
# Defaults to 10
revisionHistoryLimit: 3
# 是否置为暂停状态
paused: true
# 更新过程中，更新步骤的最大等待时长，默认为600秒；
# Defaults to 600s
progressDeadlineSeconds: 600
# 未使用analysis或experiment而progressDeadlineSeconds超时的情况下，是否中止更新过程，默认为false；
progressDeadlineAbort: false
# 重启Pod的时刻，其值为UTC时间戳格式；
restartAt: "2020-03-30T21:19:35Z"
# 回滚窗口
rollbackWindow:
revisions: 3
# 更新策略，支持canary和blueGreen两种；
strategy:
canary:
# 由控制器用来匹配到Canary Pods上的Service，trafficRouting依赖于该字段；
canaryService: canary-service
# 由控制器用来匹配到Stable Pods上的Service， trafficRouting依赖于该字段；
stableService: stable-service
# 需要添加到Canary版本的Pod上的元数据，仅存于Canary更新期间，更新完成后即成为Stable；
canaryMetadata:
annotations:
role: canary
labels:
role: canary
# 需要添加到Stable版本的Pod上的元数据；
stableMetadata:
annotations:
role: stable
labels:
role: stable
# 更新期间最多允许处于不可用状态的Pod数量或百分比
maxUnavailable: 1
# maxSurge 定义了 rollout 可以创建的最大副本数，以移动到最后 setWeight 设置的正确比率。maxSurge可以是整数或字符串形式的百分比
maxSurge: "20%"
# 启用了trafficRouting时，缩容前一个ReplicaSet规模的延迟时长，默认为30s；
scaleDownDelaySeconds: 30
# The minimum number of pods that will be requested for each ReplicaSet
# when using traffic routed canary. This is to ensure high availability
# of each ReplicaSet. Defaults to 1. +optional
minPodsPerReplicaSet: 2
# 在旧RS上启动缩容之前，可运行着的旧RS的数量；
scaleDownDelayRevisionLimit: 2
# 在滚动更新期间于后台运行的analysis，可选；
analysis:
templates:
- templateName: success-rate
args:
- name: service-name
value: guestbook-svc.default.svc.cluster.local
# valueFrom.podTemplateHashValue is a convenience to supply the
# rollouts-pod-template-hash value of either the Stable ReplicaSet
# or the Latest ReplicaSet
- name: stable-hash
valueFrom:
podTemplateHashValue: Stable
- name: latest-hash
valueFrom:
podTemplateHashValue: Latest
# valueFrom.fieldRef allows metadata about the rollout to be
# supplied as arguments to analysis.
- name: region
valueFrom:
fieldRef:
fieldPath: metadata.labels['region']
# Canary更新期间要执行的步骤，可选；
steps:
# 设定Canary版本ReplicSet激活的Pod比例，以及调度至Canary版本的流量比例；
- setWeight: 20
# 暂停step. Supported units: s, m, h
- pause:
duration: 1h
# Pauses indefinitely until manually resumed
- pause: {}
# 设定Canary扩容期间Pod扩增与流量扩增的对应关系
# (supported only with trafficRouting)
- setCanaryScale:
replicas: 3 # 明确设定Canary RS的规模为该处指定的Pod数量，但不改变先前设定的流量比例；
# 设定Canary扩容期间Pod扩增与流量扩增的对应关系
# (supported only with trafficRouting)
- setCanaryScale:
weight: 25 # 明确设定Canary RS的规模为该处指定的比例，但不改变先前设定的流量比例；
# 设定Canary扩容期间Pod扩增与流量扩增的对应关系
- setCanaryScale:
matchTrafficWeight: true # 设定Canary的Pod规模与调度至这些Pod的流量同比例滚动；
# Sets header based route with specified header values
# Setting header based route will send all traffic to the canary for the requests
# with a specified header, in this case request header "version":"2"
# (supported only with trafficRouting, for Istio only at the moment)
- setHeaderRoute:
# Name of the route that will be created by argo rollouts this must also be configured
# in spec.strategy.canary.trafficRouting.managedRoutes
name: "header-route-1"
# The matching rules for the header route, if this is missing it acts as a removal of the route.
match:
# headerName The name of the header to apply the match rules to.
- headerName: "version"
# headerValue must contain exactly one field of exact, regex, or prefix. Not all traffic routers support
# all types
headerValue:
# Exact will only match if the header value is exactly the same
exact: "2"
# Will match the rule if the regular expression matches
regex: "2.0.(.*)"
# prefix will be a prefix match of the header value
prefix: "2.0"
# Sets up a mirror/shadow based route with the specified match rules
# The traffic will be mirrored at the configured percentage to the canary service
# during the rollout
# (supported only with trafficRouting, for Istio only at the moment)
- setMirrorRoute:
# Name of the route that will be created by argo rollouts this must also be configured
# in spec.strategy.canary.trafficRouting.managedRoutes
name: "header-route-1"
# The percentage of the matched traffic to mirror to the canary
percentage: 100
# The matching rules for the header route, if this is missing it acts as a removal of the route.
# All conditions inside a single match block have AND semantics, while the list of match blocks have OR semantics.
# Each type within a match (method, path, headers) must have one and only one match type (exact, regex, prefix)
# Not all match types (exact, regex, prefix) will be supported by all traffic routers.
match:
- method: # What HTTP method to match
exact: "GET"
regex: "P.*"
prefix: "POST"
path: # What HTTP url paths to match.
exact: "/test"
regex: "/test/.*"
prefix: "/"
headers:
agent-1b: # What HTTP header name to use in the match.
exact: "firefox"
regex: "firefox2(.*)"
prefix: "firefox"
# 内联定义或调用的analysis step
- analysis:
templates:
- templateName: success-rate
# 内联定义或调用的experiment step；
- experiment:
duration: 1h
templates:
- name: baseline
specRef: stable
# optional, creates a service for the experiment if set
service:
# optional, service: {} is also acceptable if name is not included
name: test-service
- name: canary
specRef: canary
# optional, set the weight of traffic routed to this version
weight: 10
analyses:
- name : mann-whitney
templateName: mann-whitney
# Metadata which will be attached to the AnalysisRun.
analysisRunMetadata:
labels:
app.service.io/analysisType: smoke-test
annotations:
link.argocd.argoproj.io/external-link: http://my-loggin-platform.com/pre-generated-link
# 定义Canary Pod与旧ReplicaSet Pod之间的反亲和关系；
antiAffinity:
requiredDuringSchedulingIgnoredDuringExecution: {}
preferredDuringSchedulingIgnoredDuringExecution:
weight: 1 # Between 1 - 100
# 设定Ingress Controller或ServiceMesh如何动态调整配置以完成精细化地流量分割和流量迁移；
trafficRouting:
# This is a list of routes that Argo Rollouts has the rights to manage it is currently only required for
# setMirrorRoute and setHeaderRoute. The order of managedRoutes array also sets the precedence of the route
# in the traffic router. Argo Rollouts will place these routes in the order specified above any routes already
# defined in the used traffic router if something exists. The names here must match the names from the
# setHeaderRoute and setMirrorRoute steps.
managedRoutes:
- name: set-header
- name: mirror-route
# 与Istio协同完成流量迁移
istio:
# Canary期间要自动动态调整其配置以完成流量迁移的的VirtualService资源
virtualService:
name: rollout-vsvc # VirtualService资源的名称
routes: # 指定的VirtualService资源上要动态调整的路由条目的名称列表，仅有一个路由时可省略该字段
- primary # optional if there is a single route in VirtualService, required otherwise
virtualServices: # Canary期间要自动动态调整其配置以完成流量迁移的的VirtualService资源列表
# One or more virtualServices can be configured
- name: rollouts-vsvc1 # required
routes:
- primary # optional if there is a single route in VirtualService, required otherwise
- name: rollouts-vsvc2 # required
routes:
- secondary # optional if there is a single route in VirtualService, required otherwise
- name: rollout-vsvc # required
tcpRoutes: # TCP 流量分割
# Below fields are optional but if defined, they should match exactly with at least one of the TCP route match rules in your VirtualService
- port: 3000 # Only required if you want to match any rule in your VirtualService which contains this port
# Canary期间要自动动态调整其配置以完成流量迁移的DestinationRule资源
destinationRule:
name: rollout-destrule # required，DestinationRule资源的名称
canarySubsetName: canary # required，DestinationRule中临时使用的Canary子集的名称
stableSubsetName: stable # required，DestinationRule中临时使用的Stable子集的名称
# 与Ingress Nginx协同完成流量迁移
nginx:
# 要调整的Stable Ingress资源的名称
stableIngress: primary-ingress
stableIngresses:
- primary-ingress
- secondary-ingress
- tertiary-ingress
annotationPrefix: customingress.nginx.ingress.kubernetes.io # optional
additionalIngressAnnotations: # optional
canary-by-header: X-Canary
canary-by-header-value: iwantsit
# ALB Ingress Controller routing configuration
alb:
ingress: ingress # required
servicePort: 443 # required
annotationPrefix: custom.alb.ingress.kubernetes.io # optional
# Service Mesh Interface routing configuration
smi:
rootService: root-svc # optional
trafficSplitName: rollout-example-traffic-split # optional
# 启用了trafficRouting时，因更新中止 而收缩Canary版本Pod数量之前的延迟时长，默认为30s；
abortScaleDownDelaySeconds: 30Argo Rollouts Canary 示例
apiVersion: argoproj.io/v1alpha1
kind: Rollout
metadata:
name: rollouts-nginx-with-analysis
namespace: argo-demo
spec:
replicas: 10
strategy:
canary:
trafficRouting:
istio:
virtualService:
name: nginx-rollout-vsvc
routes:
- primary
destinationRule:
name: nginx-rollout-destrule
canarySubsetName: canary
stableSubsetName: stable
analysis:
templates:
- templateName: success-rate
args:
- name: service-name
# change this value to your service name
value: nginx.argo-demo.svc.wgs.local
startingStep: 2
steps:
- setWeight: 5
- pause: {duration: 1m}
- setWeight: 10
- pause: {duration: 1m}
- setWeight: 30
- pause: {duration: 1m}
- setWeight: 60
- pause: {duration: 1m}
revisionHistoryLimit: 5
selector:
matchLabels:
app: nginx
template:
metadata:
labels:
app: nginx
spec:
containers:
- name: nginx
image: nginx:1.24-alpine
ports:
- name: http
containerPort: 80
protocol: TCP
resources:
requests:
memory: 32Mi
cpu: 50m
livenessProbe:
httpGet:
path: '/'
port: 80
scheme: HTTP
readinessProbe:
httpGet:
path: '/'
port: 80
scheme: HTTP
initialDelaySeconds: 5参考文档
https://argoproj.github.io/argo-rollouts/features/canary/
