The "junk" areas of repetitive DNA were actually identified as cauldrons of evolution in the early days of research, so we have known since the beginning that the junk was actually crucial.
Barbara McClintock's Nobel for this was awarded way back in 1983
By far most junk DNA really is junk. We know this because we know its nonfunctional origin (transposons, pseudogenes and similar), because we can do studies of conservation between species, and because there is a huge range of junk DNA content in otherwise similar species.
The misconception come from media bias: You'll never hear a story about "junk DNA really is junk, researchers find"
"While some TEs confer benefits on their hosts, most are regarded as selfish DNA parasites" (https://en.wikipedia.org/wiki/Transposable_element#Evolution)
"Pseudogene sequences may be transcribed into RNA at low levels, due to promoter elements inherited from the ancestral gene or arising by new mutations. Although most of these transcripts will have no more functional significance than chance transcripts from other parts of the genome, some have given rise to beneficial regulatory RNAs and new proteins." (https://en.wikipedia.org/wiki/Pseudogene)
I would define truly junk DNA as any DNA that if removed would be beneficial or not harmful to the majority of organisms in a species, and be beneficial or not harmful to the ability of a species to adapt and evolve its genome.
Ok, but by that definition, nothing is really junk: Even our own junkyards are still home to all sorts of animals and microorganisms which feed on the junk.
Not even starting with the recycling/upcycling movement.
Doesn't change the fact that it's junk in the sense of its original purpose and immediate utility to us.
In the same way, if junk DNA really has no effect on the body it's currently part of (like freed but uncleared memory in RAM), then I think the name is appropriate.
What I'm really missing in popular reporting about genetics though is more focus on the "regulatory elements". The understanding of DNA as given by pop-science articles is mostly that DNA is either instructions for building proteins or "junk", nothing else. This completely leaves out the question how the cell decides when/if a particular protein should be built - which is of course integral for understanding how a number of protein building instructions can result in a complex organism.
It's like describing a programming language as consisting only of instructions and comments but completely leaving out branches and loops.
(even though gene regulation does not happen through branches and loops)
One of the worst names I've come across for a concept