09:21:40 <tsoome> jbk thats yours? #15395 2bba9fd47 Zpool can start allocating from metaslab before TRIMs have completed ?
13:02:00 <jbk> tsoome: yes
13:02:13 <tsoome> nice.
13:05:10 <jbk> it's hopefully not something you'll normally come across
13:05:26 <tsoome> yes, I did read the description:)
13:05:39 <jbk> but still... something that should be fixed
13:05:50 <jbk> it's been reviewed and approved in OpenZFS as well
13:06:00 <jbk> (because they appeared to have the same issue)
13:06:30 <tsoome> yep, thats the line from fbsd commit ;)
13:08:05 <jbk> since you reviewed it, and it's been reviewed by OpenZFS, i'll probably RTI it in the next couple of days unless someone pipes up with an issue in the interim
17:30:40 <jclulow> jbk: Pretty terrifying tbh haha
17:30:53 <jclulow> Not doing anything to improve my general fear of trim
17:40:52 <jbk> i think it should be better with the fix...
17:41:16 <jbk> the implementation actually isn't too complicated... just neglected to consider the behavior on how zfs schedules i/os
17:41:30 <jbk> so writes could skip ahead of the TRIM