The flip side of this tends to be that if 1,000 lines of code need to happen, filling the review queue up with 10x PRs each of 100 lines isn't exactly great either. The author spends a bunch of extra effort producing a raft of atomic PRs, and the reviewers get to context-switch a whole bunch (and may not end up with a clear picture of the feature end-to-end).

I think the ultimate answer to this is a stacked PR workflow (which we had at Meta), where I can cheaply maintain/review a 1,000 line PR as a stack of 10 incremental PRs. But unfortunately GitHub et al are still not quite there on this one.