-
-
Notifications
You must be signed in to change notification settings - Fork 10.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
portal和adminservice通信导致HA问题 #4948
Comments
排查apollo代码发现portal调用adminservice非get请求没有重试,如果eureka通知不及时,k8s环境下客户端请求失效服务端,易引发客户端超时 |
Answer generated by a 🤖 Answer为了改善Apollo配置管理系统中portal和adminservice之间的通信并防止高负载期间的超时错误,您可以考虑以下方法:
eureka:
client:
registryFetchIntervalSeconds: 60
eureka:
client:
fetchRegistry: true
cacheRefreshExecutorExpiryInSeconds: 300
cacheRefreshExecutorIntervalInSeconds: 30
server:
tomcat:
connectionTimeout: 20000
eureka:
client:
eurekaServiceUrlPollIntervalSeconds: 30 请注意,这些都是一般性建议,实际值可能需要根据您的特定用例和环境进行调整。 来源:
Sources
This response is meant to be useful, save you time, and share context. It is not meant to be a precise solution, but rather a starting point for your own research. Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant. |
This issue has been automatically marked as stale because it has not had activity in the last 30 days. It will be closed in 7 days unless it is tagged "help wanted" or other activity occurs. Thank you for your contributions. |
This issue has been automatically closed because it has not had activity in the last 7 days. If this issue is still valid, please ping a maintainer and ask them to label it as "help wanted". Thank you for your contributions. |
portal与adminservice间的服务注册发现基于eureka,
如果adminservice部分节点重启,由于eureka是ap架构,导致portal获取adminservice列表通知不及时,通过压测portal写接口发现存在超时错误,如何改善?
The text was updated successfully, but these errors were encountered: