plain orbit
If you
zpool addone or more vdevs to an existing pool that already has data on it, ZFS isn’t going to redistribute the writes you already made to the older vdevs.For example, let’s say you create a pool with a single 2T vdev, write 1T of data to it, then add another 2T vdev. You’ve got 1T FREE on one vdev and 2T FREE on the other vdev; ZFS will now write two records to the new vdev for every one record it writes to the old one; this means that while your writes will remain imbalanced for the rest of the pool’s life, each vdev will become full at about the same time.
You might ask, why not bias writes to the new vdevs even more heavily, so that they achieve balance before the pool’s full? The answer is consistency. If you distribute two writes to a 2T FREE vdev for every one write to a 1T FREE vdev, you have a consistent write performance profile for the remainder of the life of the pool, rather than a really bad performance profile either now (if you bias all the writes to the vdev with more FREE) or at the end of the pool’s life (if you deliver writes evenly until one vdev is entirely full, then have no choice but to send all writes to the one vdev that still has FREEspace remaining).
https://jrs-s.net/2018/04/11/how-data-gets-imbalanced-on-zfs/
@frosty pond