SEDA model: using the SEDA model in our IoTDB

[liukun4515]

Is your feature request related to a problem? Please describe.

The concurrency model in our IoTDB is thread-base, each client thread corresponds to a server thread.

disadvantage:

1. The context switch is overload.
2. We can't control the resource of the thread.

Proposal:

Using the SEDA model in our IoTDB.

Possible impaction:

1. the latency of each operation will increase
2. the throughput of writing operation will decrease

Advantage:

1. We can control the resource of the thread
2. We can trace different request in different stage

Describe the solution you'd like A clear and concise description of what you want to happen.

Describe alternatives you've considered A clear and concise description of any alternative solutions or features you've considered.

Additional context Add any other context or screenshots about the feature request here.

[liukun4515]

@jixuan1989 @MyXOF @qiaojialin @Beyyes

[jixuan1989]

I like SEDA. Maybe the latency of each operation will increase, but the throughput will increase if we can assign the resources fine-grained.