I have read different approaches on how to solve pdes in parallel which are discretized using finite element method. For example:
Non-overlapping domain decomposition approach as mentioned in https://imsc.uni-graz.at/haasegu/Papers/Douglas-Haase-Langer/textbook.pdf at chapter 5.2 . Each process works on each own domain and the solution vector has a consistent storage while right hand sides, residuals and stiffness matrix has an additive storage.
Distribute the mesh into N parts. Each processor has information about it's own sub-domain plus a ghost layer (Global solvers approach).
What are the differences between these two methods, pros and cons? Which parallelization method is used by FEM softwares?