02:38:27 <jbk> ahh nothing like causing kernel panics on a friday evening :)
06:28:57 <jperkin> sjorge: it looks like we used to (up to 2015Q3) build the version in wip, there's also one in pkgsrc-joyent of unknown state
06:48:49 <jbk> uugh
06:49:36 <jbk> so i'm fairly sure VMware has an extremely unique (*cough*wrong*cough*) interpretation on how various standards deal with deprovisioning space
06:49:42 <jbk> like SCSI
06:49:43 <jbk> NVMe
06:49:45 <jbk> ...
06:50:00 <jbk> which is rather unfortunate
06:51:02 <jbk> i.e. they advertise features that the standards pretty clearly say 'is set, it means XXX works'
06:51:08 <jbk> err if set
06:51:18 <jbk> yet they don't
06:52:12 <jbk> (side note: DO NOT attempt TRIM on a VMware NVMe device, and absolutely do not enable autotrim unless you like panic loops :P)
06:54:11 <jbk> (we probably shouldn't panic if a TRIM command errors out on NVMe, but it shouldn't advertise support if it doesn't)
07:53:36 <tsoome> jbk have you checked if it has been reported to vmware?
10:43:32 <wiedi> for those following along: with "rem_drv + add_drv ahci" I was able to load the driver after booting with disable-ahci=true
10:43:37 <wiedi> dmesg looks like this: https://gist.githubusercontent.com/wiedi/a145e874587b23a0eeb44ca030a6fb15/raw/b6e0f79d13a0ee0544530063e4fe41a47966f5b1/dmesg.txt
10:46:25 <wiedi> https://gist.github.com/wiedi/15b7977627857cc8351438cecbdfe4c1 on the two problematic controllers sd only attached on one of the 4 drives each
18:32:49 <sjorge> jperkin: that lines up with the timeframe from my memory, any chance either the older python or the go-carbon/go-carbonapi could be revived?
20:22:26 <jbk> tsoome_: there's all sorts of things out there about it.. somehow i gather they don't care