14:22:50 <andyf> @danmcd - If your memory goes back far enough to OS-5004, I would appreciate your review on illumos 15465 (fenix) which is similar/related.
14:22:51 <fenix> OS-5004: SIOCGLIFADDR doesn't set sin6_scope_id for link-local IPv6 addresses (Resolved)
14:22:51 <fenix> ↳ https://smartos.org/bugview/OS-5004 | https://github.com/joyent/illumos-joyent/commit/a92bddf
14:23:01 <andyf> fenix illumos 15465
14:23:02 <fenix> BUG 15465: SIOCGLIFCONF doesn't set sin6_scope_id for link-local IPv6 addresses (In Progress)
14:23:02 <fenix> ↳ https://www.illumos.org/issues/15465 | https://code.illumos.org/c/illumos-gate/+/2700
14:23:15 <andyf> Well, even if it does not go back that far :)
14:24:11 <andyf> I am suspecting that the test-runner that (I think) MNX provides for libuv acquired a LL IPv6 address since the last libuv release, as the test should have always failed.
15:39:46 <danmcd> WTF didn't I upstream this back then?
15:40:07 <andyf> It was upstreamed, but that was SIOCLIFADDR and this is SIOCLIFCONF
15:40:18 <danmcd> Oh shit.
15:41:19 <danmcd> ahh OS-5004 aka fenix illumos 6680
15:41:22 <fenix> OS-5004: SIOCGLIFADDR doesn't set sin6_scope_id for link-local IPv6 addresses (Resolved)
15:41:22 <fenix> ↳ https://smartos.org/bugview/OS-5004 | https://github.com/joyent/illumos-joyent/commit/a92bddf
15:41:30 <danmcd> fenix illumos 6680
15:41:31 <fenix> BUG 6680: SIOCGLIFADDR doesn't set sin6_scope_id for link-local IPv6 addresses (Closed)
15:41:31 <fenix> ↳ https://www.illumos.org/issues/6680
15:41:36 <danmcd> Okay, gotcha.
15:42:37 <danmcd> RTI it now if you haven't.  I'm sure someone not-me will approve.
15:58:28 <andyf> I'm checking with a few people here first, but will do, thanks!
19:11:34 <danmcd> pmooney: "For AVIC is dark and full of terrors"  
19:11:49 <pmooney> big disappointment, IMO
19:11:58 <pmooney> APICv made a big perf difference on intel
19:12:30 <pmooney> AVIC seemed poised to deliver something similar, including a few facets of it which I thought were an improvement on the INTC design
19:13:21 <pmooney> but between the warning errata, and the fact that the inter-vCPU interrupt tables never seemed to grow support for x2APIC
19:13:26 <pmooney> the value prop definitely fell off some
19:13:36 <pmooney> maybe they'll get their act together
19:15:57 <danmcd> Zen-next (Zen5?  Haven't followed roadmaps much since buying Zen2-powered HDC3 hardware.
19:16:00 <danmcd> )
19:17:27 <rmustacc> This was mostly a problem in Zen 3, IIRC. I believe Zen 4 (Genoa) does have more there, but I'll have to dig a bit. Been a while.
20:13:35 <gitomat> [illumos-gate] 15456 Remove SPARC man pages from section 5 -- Peter Tribble <peter.tribble⊙gc>
20:17:28 <gitomat> [illumos-gate] 15458 Remove SPARC man pages from section 8 -- Peter Tribble <peter.tribble⊙gc>
20:54:36 <alanc> https://illumos.org/opensolaris/bugdb/bug.html#!6425953 was apparantly filed by sommerfeld for the same issue as https://www.illumos.org/issues/15465 nearly 15 years ago
20:54:37 <fenix> → OpenSolaris issue 6425953: SIOCGLIFCONF doesn't fill in sin6_scope_id for link-local addresses (Accepted)
20:55:26 <alanc> sorry, looked at wrong line, make that 17 years ago
21:00:52 <andyf> Crikey, thanks alanc
21:04:24 <andyf> It was also spotted as illumos 15319 (fenix), although that was a lot more recently!
21:04:25 <fenix> BUG 15319: Should getifaddrs() return scope IDs for link local IPv6 addresses? (Duplicate)
21:04:25 <fenix> ↳ https://www.illumos.org/issues/15319
21:48:25 <sommerfeld> alanc: blast from the past!
21:49:21 <sommerfeld> likely filed when I was hip-deep in getting iked to deal with dynamically added addresses or some such.
21:55:18 <danmcd> I can't remember if you were working at all in in.ikev2d before <CENSORED> <CENSORED> us? Or if it was actual in.iked.  (So long ago...)
21:56:00 <sommerfeld> I definitely did a bit of ikev2 implementation work
21:56:21 <sommerfeld> shortly before pulling the ejection lever
21:57:58 <sommerfeld> I haven't looked at the code but I bet https://illumos.org/opensolaris/bugdb/bug.html#!6425939 isn't fixed either.
21:57:59 <fenix> → OpenSolaris issue 6425939: PF_ROUTE doesn't fill in sin6_scope_id in rts_fill_msg_v6 (Accepted)