Alexander Motin

> Once https://cgit.freebsd.org/src/commit/?id=8aad1e6148d3389df100bb0391e2d3a909f26ecf lands we can go ahead and merge this. @behlendorf It is in FreeBSD main already, and I'll merge it into stable branches tomorrow. Hope I'll be allowed...

@behlendorf Unless anybody knows any specific issues, with us already branched 2.4 and FreeBSD branched stable/15, I'd say it is as good time to merge this as we ever get.

@jumbi77 It seems https://github.com/openzfs/zfs/pull/11277 fixed specifically the case of removed top-level vdev. It should not affect this case of mirror element.

While I understand your motivation, it still looks weird to me report time in two properties. Sure it may work as the change notification, but for any other use it...

> since the Unix epoch can be reconstructed It can't, if a new snapshot is created between reading two properties. > Having said that, I'd be fine with changing snapshots_changed_nsecs...

> How about CPU load, especially when running on a NVMe pool? Thanks. I don't think it matters, unless you mean CPU load from metaslab loads/unloads. Which loads/unloads I think...

Addition of the new algorithm is a routine, but selection of one is not so much. I remember we selected new fragmentation metrics, and there was some logic, based on...

@Adi-Goll I haven't looked into that test much, but what I see there is zero writes with compression enabled. With compression enabled you can write zeroes till the heat death...

Is there anything common between those two systems/pools? I suppose they are not clones of each-other?

I wonder what error is returned there by `ddt_object_remove()`. Wish instead of `VERIFY(... == 0)` there was `VERIFY0(...)`, so that it would report. If it is some `EIO`, then it...