07:27:10 [illumos-gate] 15583 Panic due to assertion failure when dumping userland process core -- Andy Fiddaman 07:32:48 My brain skipped the 'process core' bit and I was like well dumping the entire userland will surely cause panics :D 07:34:52 Heh. This is an unlikely edge case, and a non-default configuration, but a core dumping userland process is not supposed to take the kernel with it. 11:17:28 [illumos-gate] 15507 smbd logging every 5 sec. after join failure -- Gordon Ross 11:31:40 [illumos-gate] 15579 smbsrv: smb_server_listener() error messages need review -- Toomas Soome 11:35:23 [illumos-gate] 15602 loader: gzipfs should follow NFSREAD_MAX_SIZE -- Toomas Soome 15:55:29 rmustacc: can you think of any reason _not_ to add ufm support to sd.c? I know some of the other properties have the FW info, but it'd be nice to have (as much as possible) a way to get the info with the same API 15:55:49 (I suppose a reason other than not wanting to touch a 30,000 line .c file :P) 15:56:54 There's no particular reason, but it depends mostly on where you want to perform processing and it's pretty easy for topo to create it itself. 15:57:14 Also, given there are already fwflash plugins, perhaps slightly more limited value since we don't have a write path through the ufm subsystem yet. 15:58:02 But off hand, probably worth exploring a bit. 17:09:39 I'm not sure we actually have a full set of fwflash bits for a lot of stuff 17:18:38 We don't. 17:33:29 ptribble: FYI: https://github.com/libffi/libffi/issues/778 17:34:14 (upgrading libffi broke GNOME 41 on SPARC for us, we've had to make it build with the old version for now) 17:43:24 Thanks! Oh joy, another incompatibility. 18:19:41 Has anyone seen this at boot time? I think it's new with some PCIe changes: 18:19:47 WARNING: pci_lcap_locate: unexpected pci header type:40 18:20:54 That byte changes on me from machine to machine, but remains unchanged across reboots. 18:21:12 I haven't, but I think it's from 14195 (fenix?) 18:21:26 fenix illumos#14195 18:21:27 BUG 14195: pci_cap_locate and pci_xcap_locate need additional bounds (Closed) 18:21:27 ↳ https://www.illumos.org/issues/14195 | https://code.illumos.org/c/illumos-gate/+/2190 18:21:49 And to be fair, it only manifests on the three identical pieces of SuperMicro HW that are 1U Haswell-E servers. 18:22:06 The Haswell client (Xeon-E3 to be pedantic) does NOT issue this error. 18:22:33 So my money is on HW flake, but if it piques the interest of anyone who knows PCIe, I figured sharing was better than not. 18:22:35 to be clear, I don't think robert introduced it. I just can't think of other ways it could be new 18:22:56 I don't think he introduce it either. I think the flaky-HW's flakiness is just More Visible now. 18:23:19 I'm hoping for, "Oh cool, we detected X now where we didn't used to!" 18:23:22 If we can do a pcieadm save-cfgspace and indicate which devices, I can invesetigate it. 18:23:32 Easy peasy... 18:23:41 I'm not sure which device it's referring to. 18:25:35 MD5 == 54078b32e0bff698fe907bcbdd9f5b3f 18:25:40 https://kebe.com/~danmcd/webrevs/larry.tgz 18:26:04 Don't break your back over it. I'm honestly thinking this is one of those things where new improvements in SW find old crud in HW. 18:42:13 [illumos-gate] 15584 misc. components use headers from the build machine -- Richard Lowe 18:42:25 every second of gitomat latency makes me slightly more scared 18:49:59 lol sorry 20:04:47 clearly we need to start routing gitomat messages over uucp via kremvax so rich knows to expect long delays 20:21:01 haha 20:39:45 github!att!ftmeade!bletchley!kremvax!ccpvax!libera 20:44:02 @uucp.Berkeley.EDU 20:44:33 That was a blast, or should I say bang, from the past. 20:56:23 One of my ancient .signatures had an estimate bang-path to reach me, but even in the late-80s RFC 822 was working well enough I never used UUCP save for USENET and rn(1) and NNTP hid that well enough. 21:02:14 I don't think I ever had a bang path in my .signature, but I did have a bitnet address listed for a while 21:04:31 by the late 80's the USENET core mostly wasn't using UUCP any more. Bang-paths were still used with NNTP to trace the path of a message as it was flooded through the network. 21:09:18 My mid-80s .sign had hp-pcd!orstcs!nomad - I don't think there was anything in front of hp-pcd but that was long, long ago. 21:11:31 I somewhere have some ancient mailing lists archives -- including a young sommerfeld if I remember -- where mail systems were still trying to interoperate and chewing up eachother's addresses 21:11:35 email: it used to be even worse 21:14:39 Not worse, just differently sucky. (I think I was too young for UUNET and BITNET to be part of my daily driving.) 21:15:01 Tell someone from 1989 about HTML email and top-posting culture, e.g. 21:15:08 I remember running pathalias and being absolutely amazed it worked. 21:16:02 When I first joined the Interneted world I was in the CS department. We were part of CSnet Phonenet. They would call us a few times a day to deliver our @addressed email. 21:16:53 In order to get email from the computing center (which was on bitnet) to the CS department, a distance of several hundred feet, it had to go from Oregon to New York, through a bitnet|internet gateway, to CSnet, then eventually was delivered to us. 21:17:12 Time critical email was not a thing.