00:56:53 i can't find it, but I seem to recall there was an issue with the ena driver that some specific thing could cause a panic, but I can't find the bug to know if it was fixed 00:56:57 anyone recall that offhand? 01:28:45 jbk: I don't believe it was fixed. I'm looking for the bug. 01:29:31 jbk: https://www.illumos.org/issues/14267 and https://www.illumos.org/issues/14845 01:29:32 → BUG 14267: ena panic triggered by static networking (New) 01:30:53 [illumos-gate] 16170 Flesh out AMD Zen4 microarchitecture (core) revisions. -- Luqman Aden 01:52:57 yeah, sucks it's not fixed :( maybe I can dig into that 01:53:14 IIRC, didn't rpz port it from fbsd? 06:17:57 jbk: rpz certainly used the FBSD stuff for inspiration. 16:23:37 sommerfeld: regarding that snapshot destruction - checked and in fact yes, dedup is there (between GZ rootfs and local zone roots trees - one of those having been the "problematic" dataset) 16:28:42 would not be surprised if illumos zfs is missing a dedup fix from openzfs, but zfs dedup has long had a reputation as a cursed feature (with unusual performance impacts). I've been avoiding it. 18:31:54 well, it seems useful and just moderately impactful for WORM datasets like the global and local zone roots, which share a lot of similarities and do not suffer write overheads other than when updating the OS or creating the zones. Data and var live elsewhere. 18:33:05 on that particular system there's just a couple of zones; still dedup claims 1.35 savings... (got another 3.52 from compression) 19:37:47 [illumos-gate] 16143 git-pbchk should handle Change-Id in multi-commit workspaces -- Bill Sommerfeld 21:08:48 [illumos-gate] 16133 lex: exit() does not return -- Toomas Soome 21:43:53 [illumos-gate] 16154 OpenZFS ZTS: pool_checkpoint improvements -- Brian Behlendorf 21:45:41 [illumos-gate] 16159 Update prototypes to 2024 -- Robert Mustacchi