We present new results on the Relaxed Dimensional Factorization (RDF) preconditioner for solving saddle point problems from incompressible flow simulations, first introduced in Benzi et al. (2011). This method contains a parameter α>0α>0, to be chosen by the user. Previous works provided an estimate of αα in the 2D case using Local Fourier Analysis. A novel algebraic estimation technique for finding a suitable value of the RDF parameter in both the 2D and the 3D case with arbitrary geometries is proposed. This technique is tested on a variety of discrete saddle point problems arising from the approximation of the Navier–Stokes equations using a Marker-and-Cell scheme and a finite element one. We also show results for a large-scale problem relevant for hemodynamics simulation that we solve in parallel using up to 8196 cores.