我们在kubernetes集群（GKE）内进行通信时出现了非常奇怪的行为，并具有无法接受的大延迟。 对于具有Memorystore获取/存储操作和CloudSQL查询的端点，延迟在600ms和1s之间跳跃。在开发环境中本地运行的相同设置（尽管没有k8s）没有显示这种延迟。
关于我们的架构： 我们正在GKE上运行k8s集群，使用terraform和服务/部署（yaml）文件进行创建（我在下面添加了这些文件）。 我们正在运行两个节点API（koa.js 2.5）。一个API向公众公开，并通过节点端口连接到API容器。
另一个API窗格是私有的，可以通过Google的内部负载均衡器访问。该API已连接到我们需要的所有资源（CloudSQL，Cloud Storage）。
两个API也都连接到Memorystore（Redis）。
这些Pod之间的通信通过自签名的服务器/客户端证书进行保护（这不是问题，我们已经将其暂时删除以进行测试）。
我们检查了日志，发现从公共API到私有API的请求仅花费大约200毫秒即可到达。 私有API对公共API的响应也花费了大约600毫秒（从私有API的整个业务逻辑抛出直到我们从pubilc API收到响应的那一刻就确定了这一点）
我们真的没有办法尝试...我们已经将所有Google Cloud资源连接到我们的本地环境，而这并没有显示出这种不良延迟。
在完整的本地设置中，延迟仅是我们在云设置中看到的延迟的1/5到1/10。 我们还尝试从0.100ms范围内的公共POD ping私人POD。
您有什么想法可以进一步调查吗？ 这是有关我们的Google Cloud设置的Terraform脚本
// Configure the Google Cloud provider
provider "google" {
project = "${var.project}"
region = "${var.region}"
}
data "google_compute_zones" "available" {}
# Ensuring relevant service APIs are enabled in your project. Alternatively visit and enable the needed services
resource "google_project_service" "serviceapi" {
service = "serviceusage.googleapis.com"
disable_on_destroy = false
}
resource "google_project_service" "sqlapi" {
service = "sqladmin.googleapis.com"
disable_on_destroy = false
depends_on = ["google_project_service.serviceapi"]
}
resource "google_project_service" "redisapi" {
service = "redis.googleapis.com"
disable_on_destroy = false
depends_on = ["google_project_service.serviceapi"]
}
# Create a VPC and a subnetwork in our region
resource "google_compute_network" "appnetwork" {
name = "${var.environment}-vpn"
auto_create_subnetworks = "false"
}
resource "google_compute_subnetwork" "network-with-private-secondary-ip-ranges" {
name = "${var.environment}-vpn-subnet"
ip_cidr_range = "10.2.0.0/16"
region = "europe-west1"
network = "${google_compute_network.appnetwork.self_link}"
secondary_ip_range {
range_name = "kubernetes-secondary-range-pods"
ip_cidr_range = "10.60.0.0/16"
}
secondary_ip_range {
range_name = "kubernetes-secondary-range-services"
ip_cidr_range = "10.70.0.0/16"
}
}
# GKE cluster setup
resource "google_container_cluster" "primary" {
name = "${var.environment}-cluster"
zone = "${data.google_compute_zones.available.names[1]}"
initial_node_count = 1
description = "Kubernetes Cluster"
network = "${google_compute_network.appnetwork.self_link}"
subnetwork = "${google_compute_subnetwork.network-with-private-secondary-ip-ranges.self_link}"
depends_on = ["google_project_service.serviceapi"]
additional_zones = [
"${data.google_compute_zones.available.names[0]}",
"${data.google_compute_zones.available.names[2]}",
]
master_auth {
username = "xxxxxxx"
password = "xxxxxxx"
}
ip_allocation_policy {
cluster_secondary_range_name = "kubernetes-secondary-range-pods"
services_secondary_range_name = "kubernetes-secondary-range-services"
}
node_config {
oauth_scopes = [
"https://www.googleapis.com/auth/compute",
"https://www.googleapis.com/auth/devstorage.read_only",
"https://www.googleapis.com/auth/logging.write",
"https://www.googleapis.com/auth/monitoring",
"https://www.googleapis.com/auth/trace.append"
]
tags = ["kubernetes", "${var.environment}"]
}
}
##################
# MySQL DATABASES
##################
resource "google_sql_database_instance" "core" {
name = "${var.environment}-sql-core"
database_version = "MYSQL_5_7"
region = "${var.region}"
depends_on = ["google_project_service.sqlapi"]
settings {
# Second-generation instance tiers are based on the machine
# type. See argument reference below.
tier = "db-n1-standard-1"
}
}
resource "google_sql_database_instance" "tenant1" {
name = "${var.environment}-sql-tenant1"
database_version = "MYSQL_5_7"
region = "${var.region}"
depends_on = ["google_project_service.sqlapi"]
settings {
# Second-generation instance tiers are based on the machine
# type. See argument reference below.
tier = "db-n1-standard-1"
}
}
resource "google_sql_database_instance" "tenant2" {
name = "${var.environment}-sql-tenant2"
database_version = "MYSQL_5_7"
region = "${var.region}"
depends_on = ["google_project_service.sqlapi"]
settings {
# Second-generation instance tiers are based on the machine
# type. See argument reference below.
tier = "db-n1-standard-1"
}
}
resource "google_sql_database" "core" {
name = "project_core"
instance = "${google_sql_database_instance.core.name}"
}
resource "google_sql_database" "tenant1" {
name = "project_tenant_1"
instance = "${google_sql_database_instance.tenant1.name}"
}
resource "google_sql_database" "tenant2" {
name = "project_tenant_2"
instance = "${google_sql_database_instance.tenant2.name}"
}
##################
# MySQL USERS
##################
resource "google_sql_user" "core-user" {
name = "${var.sqluser}"
instance = "${google_sql_database_instance.core.name}"
host = "cloudsqlproxy~%"
password = "${var.sqlpassword}"
}
resource "google_sql_user" "tenant1-user" {
name = "${var.sqluser}"
instance = "${google_sql_database_instance.tenant1.name}"
host = "cloudsqlproxy~%"
password = "${var.sqlpassword}"
}
resource "google_sql_user" "tenant2-user" {
name = "${var.sqluser}"
instance = "${google_sql_database_instance.tenant2.name}"
host = "cloudsqlproxy~%"
password = "${var.sqlpassword}"
}
##################
# REDIS
##################
resource "google_redis_instance" "redis" {
name = "${var.environment}-redis"
tier = "BASIC"
memory_size_gb = 1
depends_on = ["google_project_service.redisapi"]
authorized_network = "${google_compute_network.appnetwork.self_link}"
region = "${var.region}"
location_id = "${data.google_compute_zones.available.names[0]}"
redis_version = "REDIS_3_2"
display_name = "Redis Instance"
}
# The following outputs allow authentication and connectivity to the GKE Cluster.
output "client_certificate" {
value = "${google_container_cluster.primary.master_auth.0.client_certificate}"
}
output "client_key" {
value = "${google_container_cluster.primary.master_auth.0.client_key}"
}
output "cluster_ca_certificate" {
value = "${google_container_cluster.primary.master_auth.0.cluster_ca_certificate}"
}
私有API的服务和部署
# START CRUD POD
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
name: crud-pod
labels:
app: crud
spec:
template:
metadata:
labels:
app: crud
spec:
containers:
- name: crud
image: eu.gcr.io/dev-xxxxx/crud:latest-unstable
ports:
- containerPort: 3333
env:
- name: NODE_ENV
value: develop
volumeMounts:
- [..MountedConfigFiles..]
# [START proxy_container]
- name: cloudsql-proxy
image: gcr.io/cloudsql-docker/gce-proxy:1.11
command: ["/cloud_sql_proxy",
"-instances=dev-xxxx:europe-west1:dev-sql-core=tcp:3306,dev-xxxx:europe-west1:dev-sql-tenant1=tcp:3307,dev-xxxx:europe-west1:dev-sql-tenant2=tcp:3308",
"-credential_file=xxxx"]
volumeMounts:
- name: cloudsql-instance-credentials
mountPath: /secrets/cloudsql
readOnly: true
# [END proxy_container]
# [START volumes]
volumes:
- name: cloudsql-instance-credentials
secret:
secretName: cloudsql-instance-credentials
- [..ConfigFilesVolumes..]
# [END volumes]
# END CRUD POD
-------
# START CRUD SERVICE
apiVersion: v1
kind: Service
metadata:
name: crud
annotations:
cloud.google.com/load-balancer-type: "Internal"
spec:
type: LoadBalancer
loadBalancerSourceRanges:
- 10.60.0.0/16
ports:
- name: crud-port
port: 3333
protocol: TCP # default; can also specify UDP
selector:
app: crud # label selector for Pods to target
# END CRUD SERVICE
与公众（包括入口）
# START SAPI POD
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
name: sapi-pod
labels:
app: sapi
spec:
template:
metadata:
labels:
app: sapi
spec:
containers:
- name: sapi
image: eu.gcr.io/dev-xxx/sapi:latest-unstable
ports:
- containerPort: 8080
env:
- name: NODE_ENV
value: develop
volumeMounts:
- [..MountedConfigFiles..]
volumes:
- [..ConfigFilesVolumes..]
# END SAPI POD
-------------
# START SAPI SERVICE
kind: Service
apiVersion: v1
metadata:
name: sapi # Service name
spec:
selector:
app: sapi
ports:
- port: 8080
targetPort: 8080
type: NodePort
# END SAPI SERVICE
--------------
apiVersion: extensions/v1beta1
kind: Ingress
metadata:
name: dev-ingress
annotations:
kubernetes.io/ingress.global-static-ip-name: api-dev-static-ip
labels:
app: sapi-ingress
spec:
backend:
serviceName: sapi
servicePort: 8080
tls:
- hosts:
- xxxxx
secretName: xxxxx
答案 0 :(得分：0)
我们通过从logTransport中删除@ google-cloud / logging-winston来解决此问题。 由于某种原因，它阻止了我们的流量，因此我们的延迟很长。