dubbo 2.7.8版本使用kryo序列化比默认的hessian2性能更差

[axin3892]

Pre-check

• I am sure that all the content I provide is in English.

Apache Dubbo Component

Java SDK (apache/dubbo)

Details

按照这个文档https://cn.dubbo.apache.org/zh-cn/docsv2.7/user/serialization/ 来使用kryo序列化，结果发现比默认的序列化性能更差，具体表现为接口耗时增加了15ms左右，cpu使用率也高于默认序列化
cpu使用率分别为8%和11%左右


请问这是为什么，kryo默认配置理论应该也比hessian好一点才对吧，为啥反而是更差，而且差的还挺明显

Code of Conduct

• I agree to follow this project's Code of Conduct

[AlbumenJ]

Please re-submit the discussion in English. GitHub Discussion is only for English.