特别是当节点加入网络之前服务已经启动时，除了控制报文大小的变化以外，不会造成额外的控制开销。
Especially no additional cost exists if services have started before the network topology is formed, except the size of control packets grows.
比较案例3和6可发现，取决于报文的大小，相同的设置可能导致从1.8到7GB的不同吞吐量。
Comparing cases 3 and 6 shows that identical setups might result in throughputs from 1.8 to 7 GB, depending on the message size.
由于每个事务都有一个基本的开销，如果报文的平均大小较小(例如10KB)，那么事务持续时间不会显著减少。
As there is a base overhead per transaction, a smaller average message (10 KB, for instance) will not reduce the transaction duration significantly.
使用这种方法，您至少可以了解(或者猜测)在不对ip层进行分片的情况下可能通过的tcp报文段的大小。
Using this method, you can at least know (or guess, rather) what TCP segment sizes are likely to be passed through without getting fragmented at the IP level.
提出了从抽样后的报文中估计一定时间刻度原始流量的大小、估计原始报文长度与协议分布的方法。
It offers the way of estimating the primitive traffic at some time and the length of primitive message aod the way of protocol distribution from the message sampled.
提出了从抽样后的报文中估计一定时间刻度原始流量的大小、估计原始报文长度与协议分布的方法。
It offers the way of estimating the primitive traffic at some time and the length of primitive message aod the way of protocol distribution from the message sampled.
应用推荐