06:33:06 kevans: nice. i have pretty minimal jail around 89MB in size with custom SRCCONF and SRC_ENV_CONF. it started and works. the pkgbase variant with FreeBSD-set-jail-minimal maybe little bit smaller but i not completely familiar with pkgbase. 08:30:38 I found something odd.. in FreeBSD, if you're running php_fpm, and you send it a Hangup signal (kill -1 / -HUP), it just kills php_fpm completely. With its debug messages on I see 'Hangup' in the terminal, followed by: /usr/local/etc/rc.d/php_fpm: WARNING: failed to start php_fpm. On Linux, sending signal 1 to the php "master" process just causes it to reload. Anyone know why? It's not a socket or network 08:30:44 issue (tried with both and it does the same thing on both) 08:42:32 damn.. I guess I need to use SIGUSR1 not HUP 08:45:37 pertho: I run php_fpm here and there, but I mostly manage it via the startup scripts. I guess you meant rotating logs with SIGHUP, and so I looked it up in one of my jails, I use SIGUSR1 for that 08:46:19 wow is it me or do passkeys fucking suck? 08:47:48 It's not you. 08:48:03 karolyi: yeah I just changed the newsyslog.conf entry from '1' to '30' (last field) .. which should do the trick 08:48:17 it's been years since I read about php-fpm and signals.. :D 08:48:33 USR2? 08:48:40 USR2 for reload 08:48:45 USR1 for log rotation 08:48:52 USR2 to reload config/children 08:48:52 yea 08:49:05 HUP just kills it dead :D 08:49:25 hooray for consistency! :D 08:49:49 seems a bit unintuitive for a program w/o a controlling terminal. if being run with a controlling terminal HUP killing makes sense, as HUP is the signal sent when the phone line clicks 08:53:18 Heh.. someone on Linux-side wrote a little shell script called /usr/lib/php/php8.x-fpm-reopenlogs .. which looks for the pidfile, and sends kill -USR1 to the number. newsyslog is a lot more capable than logrotate :D 08:53:58 which linux-side? debian? 08:54:09 ubuntu/debian 08:54:36 or, at least, in the Ondřej Surý packages 09:01:07 ah 09:02:26 the php_fpm rc script also has php_fpm_logrotate() so I guess you could just call /usr/local/etc/rc.d/php_fpm logrotate ? 09:14:13 just use SIGUSR1 from newsyslog 09:14:45 also, if you think php_fpm logrotating is a PITA, ask me about rotating uwsgi logs. 09:18:18 hm, now that I mentioned it, I must just make a MR for the project to support it 09:19:56 karolyi: yeah I just used this: /var/log/php-fpm.log root:wheel 644 14 * @T00 GBJC /var/run/php-fpm.pid 30 09:21:28 I should just consolidate into one line and make it /var/log/*php*.log 09:21:42 because I have a php-fpm access log as well 09:27:39 pertho: /home/website-wp/wordpress/log/*.log website-wp:website-wp 644 30 * $D5 JG /var/run/php-fpm.pid SIGUSR1 09:27:47 is what I have. good luck 09:29:19 i wonder if i should do some crimes to php_fpm and uwsgi to obviate the logrotation gluteache 10:25:03 alias add b /buffer 10:27:08 karolyi: thanks! :) 12:36:00 angry_vincent: nice! 15:14:58 if I wanted to clear VERASE2, how would I theoretically go about that 15:16:17 theoretically stty erase2 undef would clear it, disables the erase2 control char entirely by setting it to _POSIX_VDISABLE 18:58:15 hi folks, wondered if somebody can tell me if I have missed a step. I have configured a number of vlan interfaces on parent interface re2. There's no traffic passing into my switch from vlan 160 so to t-shoot I am looking for vlan tagged traffic on the freebsd box with `tcpdump -envi re vlan 160` however nothing is showing up. If I omit the traffic id of 160 I can see all the other vlan traffic belonging to different vlans. 18:58:33 How might I further discover what is going awry? 19:00:01 (typo: `tcpdump -envi re2 vlan 160`) 19:38:37 Been a minute since I did VLANs on FreeBSD. 19:39:38 I seem to remember though, the vlan interface should have its own "NIC" name that you would run tcpdump against. 19:41:05 correct--you end up with ix0.1234 as a vlan interface off of ix0. you can also tcpdump -i ix0 vlan 1234 to see the same traffic as tcpdump -i ix0.1234 19:41:34 skuzzee: pastebin your relavent rc.conf bits as well as the switch port config 20:17:00 I miss all the different things I used to do with FreeBSD when I was at EMC. 20:17:14 All sorts of crazy network appliances. 20:21:06 LACP link-aggregation, VLANs, a "WAN emulator", an in-line sniffer, an ntp server, that could be set to arbitrary times to test how clients would react to it. 22:00:02 Is it wise to use #!/usr/bin/env sh for easy bsd support or should by default I expect bsd developers to change the shebang 22:00:40 hdconfigure_: any reason not to just use #!/bin/sh? 22:01:51 I thought #!/bin/sh does not work on freebsd 22:02:10 works fine, but the key thing to be aware of is that /bin/sh is not bash 22:02:33 so, if your script uses bashisms, you would need #!/usr/bin/env bash 22:02:34 ohhhh that explains why I was confused a few years ago. is freebsd posix compliant? 22:04:43 /bin/sh is indeed POSIX compliant 22:06:13 so my language model is saying to use #!/usr/bin/env -S program --option value 22:06:44 does this seem like the best way if I want the shebang to run any program in "$PATH" with any arguments 22:06:54 if your script needs a POSIX-compliant shell, just use #!/bin/sh. if you use bashisms, use #!/usr/bin/env bash 22:07:19 If all else fails I can use #!/bin/sh and then launch my program from within sh but I want to avoid that redirection and use shebang if possible 22:07:36 my only concern is the portability of this form #!/usr/bin/env -S program --option value 22:08:04 what is program? 22:08:57 any executable that I can launch in sh by typing $/path/to/my/exceutable/executablename.filextension arg1 arg2 argn... 22:10:02 oook, ill leave you to it then 22:10:23 thanks you have helped me alot already. I am gonna move this question to #bash 22:18:31 apparently that form I posted with the -S option is a gnuism 23:33:24 well, freebsds env supports it too, but it isn't in posix, so check if all your target operating systems support it