00:23:34 Does FreeBSD have anything similar to Linux's /proc/pressure/memory or MacOS's NOTE_VM_PRESSURE, where a program can be notified when the system/cgroup is low on memory 00:25:20 skyenet: not that I'm aware of 00:32:06 clod: hmm, is there some API that could still give similar information? perhaps via polling 00:44:43 does FreeBSD have any kind of protection that prevents it from showing something as associated with a privatekey in a file? 00:44:58 closest option according to searhes are vm.stats.vm.v_free_count and things like that 00:45:44 skyenet: polling with sysctl 00:46:33 sysctl vm.stats.vm.v_free_count vm.stats.vm.v_free_min vm.stats.vm.v_free_target vm.stats.vm.v_inactive_count 00:49:42 nm, i realize what i did wrong 01:45:20 i am planning to post my issue with my sound card to the FreeBSD forums. what information should i include? 04:29:34 at minimum release number (uname) and your chipset type. also kldstat i'd imagine to show what sound drivers the kernel has loaded 07:32:07 glenny2: putting /var/run/dmesg.boot on https://dmesgd.nycbug.org/dmesgd and linking that would also be a good idea 08:08:12 patch to -wireless 08:39:19 rwp, I have tried ``camcontrol apm da0 -l 254'' -- no effect. 08:42:03 http://okturing.com/src/20591/body 08:42:04 thoughts? 08:43:21 installing arcanist 11:48:59 so I got a null modem adapter and I still cant seem to figure out how to get serial to work 11:49:07 I see the interface server side 11:49:29 client side I have a DB9 M/F NM adapter plugged into a through cable plugged into my laptop usb port 11:49:39 I dont see anything in dmesg 11:49:47 and ls /dev/tty* shows no changes 11:50:13 this is starting to feel helpless 11:56:36 polarian, Have you tried the mailinsg lists, the official issue tracker? 11:57:12 ant-x: this isnt a bug, this is a me issue 11:57:21 and I dont like using mailing lists as I make a fool of myself 11:57:23 lol 11:57:48 What? Did you develop all the hardware and components involved :-? 11:58:00 no 11:58:12 the point is, I cant figure out how to get it working 11:58:15 It may not be a 100% you-issue, then... 11:58:40 Better make fun of yourself and get it working than vice versa, then. 12:04:29 serial port issues are crossed RX-TX lines, 80% of the time 12:11:44 psycorama: elaborate, you want to cross them so that RX is connected to the TX on the other end, and vice versa 12:12:06 do you mean that you have crossed it again so that you have RX crossed to RX? 12:13:22 no matter how much attention i pay for wiring it up. 80% of the time i'll have to cross it again 12:13:50 usually you'll net to connect RX to TX (as both sides are labeled as seeing themself) 12:14:32 It worked fine when I was using usb ttl cables 12:14:43 soldered together RX-TX TX-RX 12:14:55 that worked flawlessly, issue is I cant decrypt a FDE using that 12:16:00 the null-modem adapter, does it expect rs-232 signal levels? 12:17:54 but your real problems seems to be, the adapter not being recognised. 12:20:03 psycorama: JCOM port on motherboard, connected to it is https://www.startech.com/en-us/cables/plate9m16 which shows up within the server dmesg, so success there 12:20:10 then connected to that is a https://www.startech.com/en-us/cables/nm9mf 12:20:28 with a generic through DB9 --> USB cable 12:20:42 I cant for the life of me plug this into any device for serial access 12:20:56 I wonder if I plugged in the adapter the wrong way to the motherboard 12:21:04 there was no marking on the motherboard which is pin 1 12:21:11 so I just yoloed and plugged it in one way 12:21:14 and it showed up 12:21:21 So I assumed it was plugged in correctly 12:21:32 maybe I should flip it around and see? 12:21:42 wait dumb question I should totally do that xD 12:21:44 what can possibly go wrong? :) 12:21:57 I blow the motherboard :p 12:22:07 that might be expensive 12:22:12 but apart from that I honestly dont know what more I could try 12:26:49 the connector plugged into the motherboards JCOM port is totally passiv. so the OS should see the port regardless of anything plugged into it. 12:27:17 psycorama: weirdly enough it doesn't... 12:27:26 ttyu0 didnt exist until I plugged into the JCOM port 12:27:29 or maybe im just blind 12:27:33 but I doubt it 12:27:58 but yeah I assumed it would be passive, its just an adapter 12:27:58 there might be some shenanigans whith a sense pin against the gnd/shield. 12:28:17 lemme flip it around and see what happens 12:28:19 is there documentation for the board? 12:28:27 nothing about the JCOM port funny enough 12:28:32 and honestly I forgot which board it is 12:28:47 and im not stripping the server to find out 12:28:57 if I dont need to ofc 12:29:04 yeah, understandable 12:31:58 polarian: whats the serial problem? 12:32:23 f451: well the problem is nothing shows up on the client side 12:32:44 is the client side freebsd? 12:32:49 yes 12:32:52 and the server side is freebsd 12:33:10 whats the cable? null modem or ttl <> usb 12:33:17 listed above 12:33:28 i cant see it as i had to reboot 12:33:40 https://www.startech.com/en-us/cables/plate9m16 --> https://www.startech.com/en-us/cables/nm9mf --> some generic through DB9 --> USB cable 12:33:58 ok lemme look 12:34:56 dumb q but is the port turned on in the bios? 12:36:21 f451: I dont see anything about it in the bios lol 12:36:48 however: https://bpa.st/UHPA 12:37:24 and theres a /dev/ttyu0 12:37:28 server side 12:38:47 does connecting RX-TX on server (and client) give you echo on the consoles? 12:39:05 ok - that https://bpa.st/UHPA thats server? 12:39:32 and it's /dev/ttyu0 not /dev/ttyU0 12:39:38 ? 12:39:39 f451: yes 12:39:45 U0 would be usb based 12:39:47 afaik 12:40:11 ls -lah /dev/cua* ? 12:40:56 no - U) the caps means carrier is high 12:41:01 https://bpa.st/ZGJQ 12:41:21 U in caps in that context means the carrier is high 12:41:35 ah 12:41:48 makes sense 12:42:52 i have 2x serial ports connected /dev/cuaU0 /dev/cuaU1 both with init and lock 12:43:03 wait did you want this on the server or clie nt 12:43:07 this is still server side jsyn 12:43:42 I said to psy that I would flip around the connector on the mobo 12:43:45 see if it helps 12:43:51 yes those things i posted were from the client part 12:43:54 there is no pin on the board 12:44:11 f451: well the server has cua and tty 12:44:19 let me check my server side 12:44:43 im currently mid make installworld, in 1 min I will pull the server apart and flip the connector on the mobo 12:44:45 see if that does anything 12:45:03 theres no pin markings so I just plugged it in one way and hoped it would work 12:45:11 and then forgot about it while waiting for the nullmodem adapter 12:45:17 hehee 12:45:46 if that makes no difference then im clueless 12:45:58 I dont see much more what I can try, server side looks fine 12:46:07 what i was going to suggest was if, on booting you saw, once removed, still, the 16550A uart 12:46:15 that card thing 12:46:29 its an adapter 12:46:34 so it might still show up 12:46:38 if you pulled that do you still see 16550A when the server boots in dmesg 12:46:44 but I dont remember seeing a ttyu* without having the header in use 12:46:54 so maybe theres a pin there to detect if a adapter is connected? 12:47:00 I dont know how JCOM works so yeah 12:47:14 f451: will pull it boot it and then I will flip it around then 12:47:24 id like to make sure its the card being detected which is why im saying pull it 12:47:29 yeah 12:48:34 btw on a rpi1b 'server' - the ttl end of the serial is plugged into rpi4 gpio pins to get console, the other end into a usb port on the rpi1 12:48:53 has /dev/cuaU0 12:49:32 same with /dev/ttyU0 12:49:56 i guess the rpi1 is also a 'client' thinking about it 12:51:03 brb 12:57:02 f451: I cant even decrypt my server at this point as all the keyboards are defective lol 13:00:49 congrats 13:02:02 https://bpa.st/7E3Q 13:02:06 still there with flipping the connector to the mobo 13:02:18 theres also uart: ns8250: UART FCR is broken (0x1) 13:02:21 but this afaik means nothing 13:02:27 I read in some bug that this wont cause any issues 13:03:41 nope still nothing 13:08:27 lemme dmidecode the mobo and see if I can find anything in the docs but im clueless on what to do 13:09:37 dmesg: https://bpa.st/AIIQ 13:09:42 interfaces 13:10:13 https://bpa.st/KHHA 13:10:20 this is with NOTHING plugged into the jcom port 13:10:41 there is a keyboard ethernet and power, nothing else plugged into the mobo 13:10:58 lemme dmidecode and see if I can find the mobo 13:18:03 anyone is using Anubis ? I've added -difficulty 4 to the rc.conf but I'm still getting 2 ... any idea? 13:19:00 I've set anubis_args="-difficulty 4 -target "http://0.0.0.0" -bind "192.168.0.50:8923" -hs512-secret xxx -cookie-dynamic-domain" 13:19:13 (there is an HAProxy in front) 13:32:49 f451: omfg, maybe both cables are nullmodems, but wait no that means one would counteract the other 13:33:18 https://http.icebound.dev/httpfileupload/kQwj1F-qoDNyW1CBdI4bZ-vEgGQ/7d12a4f0-1a38-4046-8fb4-2d1d3e3bba5a.png 13:33:24 so I dmidecoded and found the mobo, and found this 13:33:27 the pinout for it 13:33:46 https://sgcdn.startech.com/005329/media/sets/PLATE9M16_Manual/PLATE9Mxxx.pdf 13:33:51 the pinout for the plate adapter is a through adapter, cool 13:34:02 https://techschematic.com/db9-connector-pin-diagram 13:34:05 thats the rs232 pinout 13:34:26 2 is receieved and 3 is transmit 13:34:31 so a nullmodem will cross 2 and 3 over 13:36:02 and the pinout from the mobo shows pin 2 is rx and pin 3 is tx 13:36:09 so with through, you would have rx-rx tx-tx 13:36:28 https://media.startech.com/cms/pdfs/nm9mf_datasheet.pdf 13:37:47 no pinout but if startech is to be trusted, the rx/tx pins are flipped 13:38:19 wait I wonder if it matters what way around the M/F is 13:38:27 because its plugged in F/M 13:41:40 maybe this is going to need some electronics testing 13:41:55 using a multimeter and some paperclips 14:39:02 back 14:40:50 polarian: in an x2 box theres a standard serial port, it's that old 14:41:00 i use this: 14:41:12 https://www.amazon.co.uk/dp/B00VBODA0G 15:28:09 Hi,I don't suppose anyone could tell me how to list the open files/locks an nfs client has on a freebsd based nfs server? 15:29:57 We've a freebsd nfs server and a load of linux clients. The server shows nfsd at 5580% cpu, 10-15k of open files and a few hundred locks for most of the clients according to nfsdumpstate. The linux nfs clients don't seem to think they have any open files/locks. 15:36:20 hi rp, id be interested in that too 15:37:41 I'm open to any pointers on how to debug something like this... 15:44:45 Honestly I would probably start by rebooting the nfsd server so that it would start from a known good state. nfsdumpstate immediately after boot. Then watch to see if there is some resource leak happening. 15:45:38 The server does this every Friday, we reboot the clients every Monday. I suspect it builds to the point it breaks 15:45:55 so yes, I can reboot it but that isn't really going to help me 15:52:32 Hmm... Well... I have no more ideas. Good hunting! 15:54:29 thanks! :) 15:55:07 Reboot more often? :-) 15:59:08 I thought bsd was better than that! (he says laughing) :) 15:59:45 It should be, but sadly the lack of resources sometimes shows 16:00:34 I know the feeling. FWIW I'm from the Yocto Project and the server in question sits in the middle of our CI which is currently dead in the water due to this :/ 16:14:24 RP: Which NFS protocol are you using? That might matter for this. 16:14:46 Ooh... And you're not running straight FreeBSD on your NFS server. 16:15:15 (At least, that's what I'm gathering from "freebsd based".) 16:15:24 mason: nfs 4.2 16:16:52 There are a couple knobs noted here, at least one lock-related: https://man.freebsd.org/cgi/man.cgi?query=nfsv4(4) 16:16:56 mason: it should be a standard freebsd install of 14.4 16:19:40 mason: I hadn't spotted that page, I'll have a better read. I think we just use file locking, not byte range locking though 16:22:26 I'd be curious what locks are being held. Might be possible to explore with DDB. https://docs.freebsd.org/en/books/developers-handbook/kerneldebug/#kerneldebug-online-ddb 16:25:22 Unfortunately this system is doing other things I really don't want to interrupt so that kind of debugging may not be a good idea. Is there any other way to find out the locks being held? 16:28:14 RP: There's lockstat, but you'll want to set that up in advance. 16:28:53 RP: Hm, I've never used this, but I just noticed /usr/sbin/clear_locks 16:30:07 lockstat might not be useful - wrong locks :P 16:32:50 so many different kinds of locking... 16:33:21 RP: Might be worth sending an email here to get some targeted advice: https://lists.freebsd.org/subscription/freebsd-fs 16:34:51 RP: Also looks like you can run rpc.lockd with debugging turned on. 16:35:21 thanks, I'll send something and ask 16:46:46 should "mount_udf" be able to mount a win 10 install dvd/iso? 20:40:27 I'd welcome critiques here. I'm very, very new to pkgbase: https://wiki.freebsd.org/MasonLoringBliss/PkgBaseChroot 21:17:58 everyone is new to pkgbase. 21:34:51 pkg-version doesn't work with pkgbase? 23:12:18 jbo: pkg search confirms that there is FreeBSD-set-base-jail-15.1 and some related jail packages and I bet I should be using those instead. Will test them this weekend.