04:26:43 hello 05:20:33 Hi. 05:21:42 blerp 07:28:59 hello there. Sorry skered I guess no. 07:29:29 morning, i got an old 11.3 server up that suddenly shows high load 12+ on an 8core cpu. But I can't see why...process load is minimal, disks are OK, I see no errors whatsoever in dmesg. Any ideas how to investigate this? Im not too used to freebsd. Thanks 07:51:10 systat reports high interrupt load hm 07:58:02 can someone help me interpret this vmstat result? https://pastebin.com/raw/n21DYSAc does it look like ix0 is the cause of this? ix1 has high count too thoguh 08:49:43 dirtwash: do you got two ix(4) interfaces. and you have setup queueing on them? 09:32:48 meena, how do you setup queueing? I have same interfaces as dirtwash but I don't have the same problem (14-CURRENT here) 09:48:32 meka: pf seems to be the only way to add support to it 09:49:05 and so maybe it's just blocklistd's queues? 09:49:29 Wait, I thought you're talking about multiqueue card and activating it's queues 09:49:30 interrupt count is usually a function of the traffic that an interface is receiving, if it's doing high-rate traffic handling it's usually a good idea to switch to polling 09:50:57 huh? how do you do that? 09:51:12 meka: I didn't know that was a thing 09:51:31 * meena doesn't know much about real hardware 09:52:34 meena, I don't know much, either, I just know that enabling ATLQ in the kernel forces all ethernet drivers to switch to single queue, so I thought you know something I don't (which is not hard) 09:54:22 ALTQ/dummynet is about shaping traffic. 09:55:45 10:50 huh? how do you do that? ➡️ ifconfig ix0 polling 09:55:49 For example, if you're doing VoIP + lots of HTTP(S), you want to reserve a (relatively small) amount of bandwidth for the VoIP, because it's very sensitive to latency (and delta latency) - so you configure network queues such that VoIP is highly classified whereas HTTP(S) is classified as bulk traffic. 09:56:04 meena: no, you need device polling enabled in the kernel, otherwise it won't do anything. 09:56:32 oy, why isn't that in GENERIC yet? 09:56:48 Because it's not universally a benefit. 09:57:00 There's no point in using polling if you aren't doing near-linerate routing. 09:57:51 It's ultimately about reducing invulntary context switches at high load. 09:58:00 aye 10:24:31 this continues to be a very strange bug report https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=270528 10:24:33 Title: 270528 – more swap is getting used 10:39:55 good morning 11:31:30 meena: if by strange you mean useless, sure 11:32:58 https://docs.freebsd.org/en/articles/problem-reports/ hasn't been followed, and there's no real evidence of there being a bug 11:32:59 Title: Writing FreeBSD Problem Reports | FreeBSD Documentation Portal 11:47:58 by no evidence of there being a bug, i mean there's no control that it's being compared against 11:52:18 that was my first comment 11:53:10 a crappily written bug report 11:53:19 "some stuff happened" 11:53:41 does at least mention releng/13 11:54:03 i'm not sure what relevance the branch has 11:54:34 besides which, there's no such thing as releng/13 11:54:54 well eliminates 11 12 and 14 at least 11:54:59 not really 11:55:12 there's no control, so you can't eliminate anything 11:55:28 for all we know from the bug report, the user is comparing against linux or windows 12:04:39 the two Operating Systems: https://oxide.computer/ FreeBSD and Ubuntu 12:04:40 Title: Oxide Computer Company 12:05:48 don't oxide target illumos? 12:06:28 🤷🏻‍♀️ 12:06:32 i will say, i do love their rack scale designs that they've been talking about 12:06:50 rectifier in the middle, every machine is powered through direct current bus bars 12:07:33 they borrowed the concept from the hyperscalers, because the hyperscalers don't make their designs available to anyone else 12:07:59 (also it's part of opencompute, so anyone's free to copy the idea as far as i understand it, it's just that nobody has) 12:08:15 "borrowed"? 12:09:12 borrowed cf https://www.opencompute.org/documents/ocphl-r-copyleft-v10 12:10:20 i mean, opencompute probably didn't invent it either, to be honest 12:10:46 the idea of bus bars providing dc power isn't exactly new 12:11:13 but ocp is the first implementation of it i know of on a modern hardware platform 12:15:00 anyway, it's a neat idea in terms of not wasting power, we'll see how the rest of it plays out 12:24:53 debdrup: now you just need to get applications to suck less power… 12:26:12 meena: rctl, see cputime. ;) 12:38:56 * meena needs to try something… 12:39:20 set_loginclass(random()); + rcctl on that… 12:42:19 passing random pointer? 12:45:51 yuripv: a random string, something that doesn't exist in /etc/login.conf 12:49:50 if you pass a non existing class name to limits( 1) it says: (paraphrasing here, cuz I'm away from the computer again) this class doesn't exist, I'll go with default 14:04:31 what's rctl(8)'s underlying syscalls? 14:05:16 truss it! :D 14:05:43 apropos -s2 rctl 14:06:17 src/sys/kern/kern_racct.c is probably a good place to start 14:10:03 yuripv: i've read https://github.com/freebsd/freebsd-src/blob/main/usr.bin/rctl/rctl.c and it's just rctl_add_rule(2) but according to the docs it only adds the rule to the database… 14:10:04 Title: freebsd-src/rctl.c at main · freebsd/freebsd-src · GitHub 14:10:56 * debdrup remembers when rctl used to be called hierarchical resource limits 14:11:20 probably good that it got renamed, because that's a handful to type and remember 14:11:54 meena: https://wiki.freebsd.org/Hierarchical_Resource_Limits#Implementation_details 14:11:55 Title: Hierarchical_Resource_Limits - FreeBSD Wiki 14:12:23 hrl sounds more fun to say than rctl tho 14:12:41 yes, yes it is 14:15:00 * meena 's first language has a bunch of words with "r" as the emphasized letter: krv, vrt, 14:15:43 meena: https://pastebin.com/XtQcV2r4 14:15:44 Title: $ grep -oE 'rctl_[a-z_]+' usr.bin/rctl/rctl.c | sort -urctl_add_rulerctl_get - Pastebin.com 14:16:38 so i'm not sure what you meant previously; also see the apropos command above :) 14:17:27 i wonder why that manual page doesn't have an alias for rctl(2) which is .Xr'd in rctl(4) and rctl(8).. 14:19:01 i don't see it: https://man.freebsd.org/cgi/man.cgi?query=rctl&apropos=0&sektion=4&manpath=FreeBSD+14.0-CURRENT&arch=default&format=html 14:19:02 Title: rctl(4) 14:22:38 anybody care to help setting up the steam client? it reports 'authorization required but no authorization protocol specified' and also 'cannot open display:' i've follow the instruction and am running `steam' after the `steam-install' command on the `steam' dedicated account. I've setup a password for it, is that why it wont work? 14:24:09 meena: right, that's what I was saying; https://cgit.freebsd.org/src/tree/lib/libc/sys/Makefile.inc#n455 needs a link to rctl.2 14:24:11 Title: Makefile.inc « sys « libc « lib - src - FreeBSD source tree 14:24:35 and then rctl(4) and rctl(8) needs to have cross-references to it with .Xr rctl 2 14:24:42 ah 14:25:07 I misread you: i thought you meant: rctl(4) and rctl(8) reference rctl(2), but there's no such alias 14:25:18 fair 14:25:23 no harm no foul 14:26:26 gzar: do you allow this user to open windows in your session? e.g. https://unix.stackexchange.com/questions/613458/how-to-enable-xhost-access-from-second-user-when-display0-is-on-first-user ? 14:26:27 Title: x11 - How to enable xhost access from second user when display:0 is on first user? - Unix & Linux Stack Exchange 14:26:45 where is the rctl database? 14:26:52 very likely not, thanks, will check this out 14:28:24 meena: it's an in-memory thing that gets read from rctl.conf(5), iirc 14:28:53 not an on-disk thing like what's found in /var/db/ 14:30:43 if the word dataset didn't have connotations from zfs, that might be a better word for it 14:30:51 it's not a database in the relational sense, more in the array sense 14:31:28 database as in organized collection of structured data, i guess is the way to say it properly? 14:32:13 i'm not saying racct/rctl uses arrays, obviously, since i haven't looked at it in probably a decade? 14:37:15 thanks ridcully_ , that did the trick 15:56:28 ridcully_: read your answer and started scrolling after someone with steam issues =D 16:07:43 debdrup: I want thinking /var/db, but more like /etc/pwd.db and their like 16:11:58 oh well, it seems like steam wont start either way 16:12:17 seems to be stuck in some 'assertion failure' loop or something 16:18:50 gzar: what's dtruss say? 16:20:06 i dont have dtruss 16:23:48 gzar: then install dtrace-toolkit 16:25:44 https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=270546 this seems… dubious. 16:25:46 Title: 270546 – nullfs prevents zfs from freeing space 16:42:46 <_xor> Aside from putting it inside of a jail, are there other options to limit a process to a specific network interface? (assume the process doesn't support configuration for that) 16:43:23 <_xor> I was looking at the rctl man page, but didn't see a resource listed for netif. 16:45:25 <_xor> In my case, the issue is that I use an app that utilizes UDP broadcast. My machine has a primary interface (re0) and a bridge0 interface (for jails, etc). Problem is that the app is is broadcasting on all interfaces, which is causing it to screw up due to duplicate broadcasts (one going out on re0, and another going out on bridge0). 16:46:41 <_xor> I could use pf to block it, but I don't want to restrict the ability of bridged jails to be able to broadcast if necessary. Ideally it would be done via some host mechanism so that said process only sees re0, while everything else by default can see bridge0. 16:47:27 <_xor> Oh, just hit me, can devfs.rules + devd accomplish this? 17:09:24 _xor: maybe you could use vlans to get seperate layer 2 multicast? Or maybe there some equivalent to virtual ethernet in freebsd that you could bind the process to? not very good with networking just thought id put out some thoughts 17:10:41 ohh udp multicast so not layer 2 multicast then sorry 19:55:14 hope do you set something at 19:55:23 as RT https://lists.freebsd.org/archives/freebsd-hackers/2023-March/002060.html ? 19:55:25 Title: Re: Periodic rant about SCHED_ULE 19:58:35 how… 19:59:20 let's try this again: how do you set a process / process group (service) to be RT? 20:15:35 real time priority? 20:16:05 man 1 rtprio 20:16:21 i.have been waiting years for this question 20:17:37 rtprio waited for yeara to become useful 20:25:17 <_xor> lol 20:44:59 _xor: you're also waiting for your turn, isn't it? 20:50:32 rtprio: thanks! 20:53:31 rtprio: I'm surprised it's in section 1 20:53:42 it's/you're 21:37:40 i installed fbsd but there is no boot loader 21:50:20 linsux: FreeBSD has a thing called loader(8) and it generally has a menu, unless the timeout is set to 0 21:50:27 does it boot?