10:07:11 <jlevon> anybody interested in picking up https://github.com/hreinecke/sg3_utils/pull/58 ?
14:54:53 <jbk> jlevon: it looks like (from a quick glance) that the 'upstream' (I guess, i never quite understood the relationship between the two sg3 utils repos on GH) has that fix
14:55:03 <jbk> https://github.com/doug-gilbert/sg3_utils/commit/b07ad28107659f532c54659f5ecd12eaf086ea0b
14:59:19 <jbk> (is it a fork? is one 'abandoned', etc)
15:12:16 <jlevon> I think at the time, that didn't exist. thanks
15:34:52 <jbk> yeah, i have no idea what the relationship is there other than the one he references seems to have the change..
15:35:03 <jbk> i've been able to build them and use them w/o any problem
15:35:22 <jbk> it's been helpful for all of my SATL changes (I still have a few more I need to get up for review)
15:36:16 <jbk> also helpful when trying to figure out how broken VMware's scsi emulation is
15:36:39 <jbk> (sadly their NVMe emulation isn't any better)
15:42:53 <jbk> I do also have a change I could upstream (at least I don't think i've upstreamed it yet) where drives that don't advertise support for UNMAP, but do advertise some other bits, it will issue WRITE SAME (with zeros) CDBs for DKIOCFREE ioctls instead of issuing UNMAP CDBs
15:43:19 <jbk> which on VMware at least, will shrink thin-provisioned vmdks
19:36:57 <gitomat> [illumos-gate] 5915 msgpullup(9f) behaves as if len is always -1 -- Kyle Simpson <kyle⊙oc>
22:14:58 <sommerfeld> pardon my off-topic rant: I hate AFCI circuit breakers.   (the circuit my illumos dev machine is plugged into was taken down by a false arc fault trip when a vacuum cleaner stopped).
22:21:27 <tsoome> :(
22:21:53 <tsoome> hopefully nothing lost...
22:24:42 <vetal> jclulow: About c39t5000CCA04D1A6BA9d0 = it is another system with another case with changing c39->c38
22:25:22 <jclulow> vetal: Right, I think we want to get all of the details that we can about that system so that we can figure out what's going on
22:25:25 <vetal> jclulow: However both path with c38 and c39 still exist. I think you are right and it is multipathing cases
22:25:57 <vetal> jclulow: https://gist.github.com/gusev-vitaliy/7c29ae481964e20dc933d7d4f45888cb
22:27:17 <vetal> jclulow: However I am confused why diskinfo reports only one path.
22:27:37 <jclulow> diskinfo does some deduplication based on media identity
22:27:59 <jclulow> It gets a bit confused if two disks are apparently identical, I think
22:28:47 <jclulow> vetal: Can you grab all the other commands I listed on that system as wel l
22:30:45 <sommerfeld> tsoome: just my time..  
22:31:37 <gitomat> [illumos-gate] 16854 CPUID_PASS_IDENT is sufficient for cpuid_getsig -- Luqman Aden <luqman⊙oc>
22:32:35 <vetal> jclulow: fmtopo-Vp.txt   https://file.io/Ita7LGuClvkh
22:36:40 <jclulow> vetal: It says it's been deleted
22:46:16 <vetal> jclulow: Interesting. Sorry for that. https://file.io/jWwj65leCTV3
22:46:50 <vetal> jclulow: "File will be deleted after download". It seems it is only for one download.
22:48:54 <jclulow> vetal: I've created a bug now: https://www.illumos.org/issues/16937
22:48:55 <fenix> → BUG 16937: multipathing not engaging on SAS JBOD? (New)
22:49:05 <jclulow> It includes a list of things we should gather as part of investigating
22:49:10 <jclulow> if you can whack the files in there that should be easier hopefully
22:50:01 <vetal> jclulow: Will provide required files tomorrow. 
22:50:05 <jclulow> Ok, thanks!
22:50:17 <vetal> jclulow: Thank you too!
22:50:36 <jclulow> You're welcome! Hopefully something will jump out in the data and it's an easy fix