Yesterday I wrote in passing that it would probably be very hard to persuade us to go for a single vendor solution for our fileserver needs instead of one built on open standards with replaceable components. Today I feel like justifying that casual aside, even though some people will consider it obvious.

The simple version is that a (single) vendor solution requires more trust. Everything is in the hands of the vendor, it is generally very hard to inspect and verify the solution from the outside, and you are completely at the mercy of the vendor's quality of implementation. With a system built on open standards with multiple sources of the components you only have to trust that the standards themselves are decent (which to some extent can actually be tested and verified) and that some collection of people will support the standards with decent implementations. If an individual component supplier is not good enough you can swap them out without destroying the entire plan.

Both parts of this are important. Genuinely open standards give you (and other people) some chance of evaluating whether the standard is actually fit for the purpose, can perform decently on stuff you can afford, and so on. They can also create more implementations that people are willing to talk about so you can find that yes, people have gotten them to work and work well. Replaceable components mean both that you have options if one part isn't up to what you want and that the people involved are hopefully being pushed by competition to improve things.

This shouldn't be a dogmatic approach, and indeed our current system only partially follows it. ZFS is not an 'open standard' and at the time we adopted it there was effectively only one vendor. On the other hand it was replaceable from a larger scale view and replacing it with something else wouldn't have required us to throw out any other parts of the overall system.

(That you don't need to throw out much or anything else if you have to replace one bit is of course a good sign of a modular system design.)