00:12:26 <sommerfeld> rmustacc: zfs doesn't have lfs's "segment cleaner" which would empty out a metaslab for fresh sequential writing.
00:15:50 <sommerfeld> alanc: reads mainly like "whoever ported zfs to linux didn't understand linux's user namespaces"
00:22:13 <sommerfeld> jbk: I think you have the metaslab spacemap thing (which indeed uses less space to keep track of free/allocated when the slab is nearly full) confused with intent logs (which use blocks that aren't marked allocated in the spacemaps..)
00:23:24 <jbk> yeah it could be the spacemaps i'm think of... it's been a _long_ time since I've had to look that deeply :)
00:24:09 <jbk> intent logs seem like they'd work well since you're really just appending
00:24:27 <sommerfeld> in other news I gave Hans's NVME host memory buffer patch (https://code.illumos.org/c/illumos-gate/+/4929) a spin on a test machine where it would used and .. I guess it works?  nothing blew up, things seem to be performant.
00:24:28 <fenix> → CODE REVIEW 4929: 18307 nvme: want support for Host Memory Buffer feature (NEW) | https://www.illumos.org/issues/18307
00:26:13 <sommerfeld> I don't know nvme-level things well enough to seriously review it.