02:17:06 <jclulow> jbk: I only use SNMP for things without a functional alternative haha
02:17:22 <jclulow> i.e., in the current lab, it's just the APC PDUs and the Cisco switches
02:18:38 <jclulow> I feel like the prometheus metrics format is looking to achieve a new SNMP status at this point haha
02:18:59 <jclulow> viz., not especially good, but well-defined and widely used
02:35:10 <jbk> yeah, i think it made more sense at the time (2007/2008 i think) why i was surprised about the desire for it now since it seems like everyone uses some other format
06:26:46 <gitomat> [illumos-gate] 16339 sockfs: variable may be used uninitialized -- Toomas Soome <tsoome⊙mc>
11:29:16 <vetal> Hye, I see very slow perfromance for ramdisk (ramdisk -a test 2g) -> read 422 MB/s.
11:29:56 <vetal> Is it buggy or It could be improved somehow by tuning something ?
11:30:22 <vetal> command: dd if=/dev/ramdisk/test of=/dev/null bs=1M
13:34:40 <tsoome_> vetal how much throughput do you get reading from cached file? 
13:39:19 <vetal> tsoome_: "dd if=/dev/zvol/rdsk/rpool/swap bs=1M count=2048 of=/dev/null" gets 655 MB/s
13:39:43 <vetal> tsoome_: But it is ZFS with its locks, etc.
13:40:07 <vetal> tsoome_: ramdisk should be fast like in Linux 5-10 GB/s
13:41:04 <vetal> tsoome_: even on non-debug kernel (OI hipster) it produces reading from ramdisk (874 MiB/sec)
13:43:41 <tsoome_> I meant something simple like reading iso or usb image few times to see the memory throughput:  dd if=OpenIndiana_Text_X86.usb of=/dev/null bs=1M
13:43:47 <tsoome_> 886046720 bytes (845 MiB) transferred in 0,161758 secs (5,1 GiB/sec)
13:45:00 <tsoome_> regarding to ramdisk, I have no comments about its implementation, probably worth grabbing flamegraph or like and see what is going on.
13:45:39 <tsoome_> we do not use ramdisk too much (I think oxide is probably using it;)
13:46:20 <tsoome_> tmpfs (used by /tmp, /var/run and such, is not ramdisk)
13:49:10 <tsoome_> hm, it may be the installer (in some distribution) may use ramdisk with miniroot from install media... 
13:50:28 <gitomat> [illumos-gate] 16340 sockfs: label defined but not used -- Toomas Soome <tsoome⊙mc>
14:27:25 <vetal> tsoome_: Good, Thanks, I will look into it and will try to improve.
15:38:41 <gitomat> [illumos-gate] 16192 Retire libc's thr_debug.h in favor of <sys/debug.h> -- Bill Sommerfeld <sommerfeld⊙ho>
18:30:56 <gitomat> [illumos-gate] 16480 krtld doesn't properly handle tail called sdt probes on x86 -- Luqman Aden <luqman⊙oc>
18:53:50 <richlowe> tsoome_: unless you're going to get 16498 really soon, I probably can.
18:54:18 <richlowe> but I have literal bytes/second of bandwidth, so it's... exciting to use ssh over a vpn right now :)
18:55:14 <richlowe> alanc's not theh only one typing blind and hoping the right window is underneath it once the characters catch up :)
19:34:55 <Agnar> good evening, does anyone here has a recommendation for a S3 bucket server on illumos? MinIO doesn't build because of some file method abstractions missing, garage fails because one dependency complains it has no idea what "illumos" is...
19:45:28 <gitomat> [illumos-gate] 16446 dtrace consumers should not be isaexec'd -- Richard Lowe <richlowe⊙rn>
19:55:02 <tsoome_> richlowe :) I still have small queue of my active bits (and long queue of inactive ones:D)
20:40:14 <CrazyBread> Hello (echo)
21:14:21 <gitomat> [illumos-gate] 16455 want TCP_MD5SIG socket option -- Andy Fiddaman <illumos⊙fn>
22:02:16 <jbk> https://github.com/illumos/illumos-gate/blob/master/usr/src/uts/common/sys/sata/impl/sata.h#L63-L66 whoops :)
22:25:52 <rzezeski> jbk: ha, I wonder how hard it is to train smatch to catch that
22:27:59 <sommerfeld> someone wanted to typedef the struct definition, saw that it was done differently, but didn't completely convert it...
22:28:42 <sommerfeld> rzezeski: you need something like lint's global crosschecks to notice that nobody references it as a global..
22:28:52 <tsoome_> ouch...
22:29:56 <jbk> they did typedef it, just with more vowels :)
22:30:33 <sommerfeld> unless you wanted to add some sort of "identifiers must be unique even if vowels are missing" rule.
22:30:55 <sommerfeld> which will really mess up everyone's favorite for loop variable.
22:31:37 <sommerfeld> or maybe an opinionated "things ending in _t must be types" rule.
22:32:49 <sommerfeld> vowel-insensitive names, one step beyond case-insensitive names.
22:43:24 <rzezeski> sommerfeld: I don't know exactly how smatch works, but I thought it had some notion of the AST. So I was thinking more along the lines of "we never define a struct with a declarator". But probably not worth the effort given how unlikely this is to happen.
22:53:57 <tsoome_> its always about cost versus profit:) but then again, it can also be interesting challenge:)
23:08:52 <richlowe> rzezeski: I've tried a few times to add things to smatch, and not been happy.
23:09:25 <richlowe> if one of you do figure out how to, I'd love a check that getopt's return is not a character, and rmustacc would like a check that id_t is not printed with a literal %d or %ld
23:09:42 <richlowe> 'cos they're non-portable but impossible to teach gcc about
23:47:07 <rzezeski> I did contribute to smatch to fix a bug (that helps with perf), but I didn't really look at how you write rules for it.
23:47:48 <rzezeski> but if I ever do look, I'll keep those in mind
23:58:21 <richlowe> if this is _after_ perf fixes, I'd hate to see before
23:58:28 <richlowe> have you ever watched it think over nvme.c?
23:59:44 <richlowe> I thought I'd broke something and went running to rm :)
23:59:45 <rzezeski> haha, pretty sure we haven't updated to the version that includes my fix, it was pretty recent
23:59:46 <rzezeski> https://github.com/error27/smatch/pull/8