03:45:55 53008 bytes seems like an odd buffer size for the network stack to use.. 03:46:18 https://pastebin.com/MzENswHy 06:02:47 is it 52K - sizeof(some headers)? 11:55:48 What does the definition NO_UNLOAD_STUB(procfs, oprgetstatus,nomod_zero) in modstub.S do? 12:02:32 I guess a static function is not necessary to list there? 12:35:25 richlowe: no idea, but the fact it happened twice seems to suggest it wasn't just random 12:35:36 (even ignoring the 0 byte usage on one) 14:12:37 NO_UNLOAD means once you hit the symbol and the module loads, said module will not unload afterwards. 14:30:48 is there a way to add a dataset to a zone online, the same way the zone does it on booting? If I mount the dataset into the zone with mount(8), the mountpoint must be legacy of course, that way I cannot restart the zone without loosing the mount. 14:35:38 Could you not update the zone properties (zonecfg) in parallel with the explicit mount such that next reboot it'd just work? 14:45:57 danmcd: I can do that, I just wanted to get a whole dataset delegates to the zone without having to restart the (central database) zone 14:46:31 I did a bad design choice when configuring the zone. 14:47:19 and I must work somehow, I just wonder if we have a userland option for it. if not, that would be a good RFE 15:03:16 um, I think S11.4 got live zonecfg updates at some point in time. 15:04:49 yes, they have a zonecfg -r for running config 15:05:17 I wondered if there is just some mount flag or low level tool around ;) 15:51:41 uugh 15:51:55 does dhcpagent try to explicit start the routing/route service? 15:52:19 i have 3 interfaces on the same subnet all w/ dhcp 15:52:49 and every so often ipadm marks them disabled which ends up being some unfixable state aside from rebooting 15:53:02 ipadm enable-addr doesn't work on it 15:54:14 which seems like a bug, but also not something I can really dig into right now unfortunately 15:55:55 (granted, we should probably move dlmgtd and ipmgmtd to store their stuff in smf instead of their own bespoke code which is buggy) 16:27:06 the -t handling in particular 16:51:09 jbk: the temp flag? I have not had issues with that and I use it almost everyday. Are there any existing issues written for this? 17:03:03 I only had issues when nwam was running, but those are nwam bugs 17:03:50 i thought i filed one 17:04:05 but like using that to reconfigure an aggr is _horribly_ broken 17:08:36 oh, ok - that might be. I rarely use aggregates 17:12:31 ahh there was just an internal ticket... but I can file an illumos.org one 17:12:54 I remember looking at trying to solve it correctly, and IIRC it was a mess because of all of the bespoke db management code 17:15:29 https://www.illumos.org/issues/18366 17:15:30 → BUG 18366: Mixing temporary and persistent dladm aggr commands can create Schrödinger's aggr (New) 17:29:17 the scenario was 'i want to remove this link from the aggr, but not persist across reboot... ok now I want to add it back to the aggr (and have it persist)' 19:11:04 rmustacc: https://github.com/illumos/illumos-gate/blob/master/usr/src/uts/common/io/i40e/i40e_intr.c#L472-L473 -- shouldn't that be `>=` ? (I'm like 98% sure yes, but then I'm trying to understand why if true, why it's not caused problems to date) 19:13:39 (I'm happy to file a bug and fix it -- we have a customer where all 4 ports on one i40e card seem to have stopped generating interrupts as best as I can tell, which led me down this route) 19:14:35 just.. we have a fair amount of customers using them as well as it seems at least somewhat popular in the illumos communtiy w/o similar reports, which makes me wonder if i'm just missing something obvious 19:15:06 (looking at the full queues, 1500MTUs, no LSO, data is copied, so the 8 descriptor limit is not a factor) 20:58:54 jbk: It'll be a bit before I can look. Just it's been a long time since I've beeni n this code. 21:03:04 ok