first of all, I intend to learn in depth about distributed related content, including spark,Hadoop cloud computing, as well as load balancing and service-oriented, to conduct in-depth and systematic learning. Of course, some aspects are familiar with and understand it, and some aspects are in-depth learning, but the whole thing requires multiple systems. Want to simulate a whole set of hardware environment, but do not want to install a virtual machine, on the one hand, there are too many environments in the computer, on the other hand, it is afraid that the virtual machine will interfere with each other, such as performance testing can not be accurate.

so now I want to buy a series of hardware, but if I buy hardware, it will be a lot of money.

considering the above opportunities, can anyone give me a more practical suggestion or plan?