The architecture of Huawei's 18K high-end storage

The contents of the white paper are as follows:

The OceanStor high-end storage system has two types of clusters: "control" and "business":

"Control cluster" elects a management server among all controllers

This is easier to understand.

The "service cluster" is mainly carried out in one engine (two controllers). When a single controller fails, the other controller can take over all the services of the controller, thereby ensuring the least impact on the host IO.

This is also easier to understand.

The question is: what is the relationship between engines?

These engines should be an aggregation of computing resources, so what is the working mode of this "aggregation"?

1. Can all engines access the same LUN in the way of alua?

2. Can all engines use slua to access the same lun?

Also about raid2.0 under 18K

Is it possible to realize the disk domain of raid2.0 across engines?

Thanks