-
-
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
关于eureka.server.peer-node-read-timeout-ms的查看和调整 #4977
Comments
🤖 您可以通过在Apollo配置管理系统中的'application-custom-defined-discovery.properties'文件中添加此参数来查看和修改'eureka.server.peer-node-read-timeout-ms'参数。 以下是操作步骤: eureka.server.peer-node-read-timeout-ms=您想要设置的值 将'您想要设置的值'替换为您想要为'eureka.server.peer-node-read-timeout-ms'参数设置的值。此值以毫秒为单位,决定了从对等eureka节点读取数据的超时时间。 请注意,更改此文件后,需要重启Apollo服务才能生效。 参考源码: 关于'eureka.server.peer-node-read-timeout-ms'在Apollo配置管理系统中的默认值,我在仓库中没有找到答案,但答案可能在其他地方可用,或者我可能错过了。 另外,根据我在Apollo仓库中找到的类似问题,这个错误通常表示服务器响应慢。如果此错误只偶尔发生,并且元服务器返回正确的数据(/services/config, /services/admin),那么可能不是问题。但是,建议检查服务器状态,如cpu/mem/gc等。还可以检查eureka.service.url配置,可能存在配置错误或机器性能下降。 参考问题:
Sources
This response is meant to be useful and save you time. 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. If you want to continue the conversation, start your reply with @dosu-bot. |
感谢,我是直接下载的github上apollo 2.1编译过程序部署的,我看apollo-adminservice-2.1.0.jar包里的BOOT-INF/classes目录下有个application-custom-defined-discovery.properties文件,可以直接修改这个上传吗? |
不用修改包里的配置文件,直接在部署目录下的 config/application-github.properties 加就可以。 |
@nobodyiam 感谢,目前我的架构是这样的。 数据库容灾: 应用配置: 请问这种架构可以吗?目前就是报eureka.server.peer-node-read-timeout-ms超时的错误,可以通过调整来解决吗? |
eureka.server.peer-node-read-timeout-ms 看配置名称在 config service 的配置文件中修改就可以 |
@nobodyiam 我的admin和config日志都会偶尔有这个报错,我在admin和config的配置文件都增加了eureka.server.peer-node-read-timeout-ms=10000,改成10秒了,在网上查的这个参数默认是200ms,改造后重启,貌似目前没有这个告警了,另外我们机房是专线连接,所以就多中心对等应用多活部署了,这样架构更简单点。 |
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. |
我有两台config在同一个数据中心,另外两台config在另外一个数据中心,4台config组成一个集群,两个数据中心之间可能偶发性的网络延迟有一点大,网络是专线连接的,config偶发性的报错,请问如何查看和修改eureka.server.peer-node-read-timeout-ms参数。
2023-09-21 14:10:14.021 ERROR 14142 --- [TaskBatchingWorker-target_x.x.x.x-13] c.n.e.cluster.ReplicationTaskProcessor : It seems to be a socket read timeout exception, it will retry later. if it continues to happen and some eureka node occupied all the cpu time, you should set property 'eureka.server.peer-node-read-timeout-ms' to a bigger value
The text was updated successfully, but these errors were encountered: