01:41:14 interesting, thanks for the update 18:34:10 With this output from savecore, is there any hope of extracting useful information from the dump? This is a disk subsystem lockup problem, making it catch 22. 18:34:13 https://yagi.h-net.org/copacabana_partialdump.txt 19:52:45 Probably not. :( 19:53:04 #illumos might know tricks I don't, however. 19:53:11 I'll ask there, just in case. 19:53:18 WIth your permission, or you can yourself. 19:53:58 Please feel free 19:54:46 Basically looking for any way to choke up on this blasted occasional lockup problem without just shotgunning parts like the sas/sata backplane, the motherboard, ... 19:55:19 Did you happen to check if there was a panic stack in /var/adm/messages* 19:58:50 Ooh, no, I didn't. There's something there, and I added to the bottom of the above urled page. 20:00:24 er, just remembered to _save_ the file, sorry 20:01:35 2025-03-14T03:32:12.609841+00:00 copacabana genunix: [ID 918906 kern.notice] I/O to pool 'zones' appears to be hung. 20:02:06 Yeah, "something's wrong with..." (and your list of IO path tries). Lemme check #illumos again... 20:02:37 ... yeah only feedback is this: 20:02:39 "16:01 jbk: it'd probably require hacking up savecore (i.e. I don't think there's any flags or mdb magic that can be done)" 20:02:58 Unless you have unix.N and vmcore.N you're out of luck. :( 20:03:05 Yeah, didn't figure, but you folks are pretty sharp, so it was worth asking. 20:03:11 I don't suppose `fmadm faulty` has anything to say? 20:03:27 Yeah, didn't figure, but you folks are pretty sharp, so it was worth asking. 20:03:39 No, nothing useful there. Nothing useful in `ipmitool sel list` 20:15:10 Uggh. 20:15:30 Right? 20:15:39 Thanks for taking the time to look. Much appreciated. 20:19:24 Sorry I couldn't help more.