The idea would be to use LVM to get writeback caching on the block-device level, then use those cached LVM devices as backing devices for a ZFS pool.
I've tested this on a small scale prototype level (one HDD and one NVME SSD) and there it worked quite well. But like I said it feels a bit fragile, lots of moving parts.
I've tested this on a small scale prototype level (one HDD and one NVME SSD) and there it worked quite well. But like I said it feels a bit fragile, lots of moving parts.