Shutian
Shutian
感谢对Trace的关注。生产集群是会出现微服务自调用的情况。具体原因很复杂，例如，微服务对上游的调用先汇聚到一个接口，进行条件语句判断后，再调用到自身的其他接口上，这样会形成自调用。
Thanks for your interest! The timestamp only reflects the time of a given day. We only release 12-hour traces, so the timestamp ranges from 0 to 43200000 (twelve hours: 12...
Yes, you are right about the MS_CallGraph_Table.
Thanks for your interest and question. You are right about the MQ. We mark the rpctype as "userDefined" if developers adopt their preferred middleware rather than the typical middleware in...
Thanks for your interest! rcpID records a call between a pair of UM and DM instead of one UM or DM. Therefore, there is no UM rpcID and DM rpcID...
谢谢对traces的关注。是的。我们是对call graphs进行采样，被采样到的call graph的调用链路是完整的。
Thanks for the questions and your interest! One node has multiple containers. One node has multiple containers. CPU utilization in the node and MS_Metrics quantify the CPU usage in nodes...
It is a good question. As Fig. 4 in the paper (SoCC’21) shows the distribution of the in-degree and out-degree of microservices, 90% of microservices have an in-degree of one...
Thanks for your interest. In the paper, when analyzing call dependencies and topology of the call graph, we do not consider the instanceid and use the merged-together graphs as you...
Thanks for your question. The call recorded twice is via remote invocation between two stateless microservices instead of mc between a stateless microservice and a stateful microservice. In the case...