# Coprocessor
__*Coprocessor*__

![left](./student-guide/diagram/Coprocessor01_en_001_2022051.png)

------------------------------------------------------------
So far, our TiKV has solved the problem of data storage, so currently the entire TiDB database can be processed as shown below. TiDB is stateless, and the data is stored in the TiKV layer. When TiDB receives a query request from a client, it gets it from TiKV

Specific data information. There are 2 performance issues with this architecture:

1. TiKV return all the data, and the network is too expensive.

2. TiDB needs to calculate all the data, which consumes a lot of CPU. Relatively, TiKV doesn't have much calculation, and the CPU pressure is very low.