07:59:52 <tsoome> sigh... https://src.illumos.org/source/xref/illumos-gate/usr/src/lib/libgss/gssd_pname_to_uid.c?r=b9175c69#288 
08:08:28 <LXGHTNXNG> what's up?
12:44:01 <sjorge> should nfs and smb performance be more or less equal when sharing the same dataset?
12:44:33 <sjorge> i'm getting like max 35MB/s over SMB but hitting like 400MB/s over NFS
12:44:42 <sjorge> client is a bhyve vm
12:44:51 <sjorge> i would expect it to be closer?
12:59:34 <sensille> smb does some internal windowing, depending on the client
13:00:08 <sensille> shouldn't matter much when the latency is very low
13:01:23 <sensille> dumb clients do 16k ping pong
13:44:34 <short-bike> I'm running Hipster as a VM guest and trying to find documentation on how to adjust the display resolution above the 1280x720 maximum right now. Any pointers would be helpful. Thank you. 
13:54:05 <sjorge> I fiddled a bit on the client side with the options but can't get it faster at all -_- guess I'll need to mess around with nfs4_acls to get the permisisons on NFS OK :(
16:30:38 <KungFuJesus> tsoome: so if namebuf.value == NULL, s becomes an uninitialized pointer?
16:30:49 <tsoome> yes
16:31:16 <tsoome> well, it is uninitialized before we set it:)
16:32:14 <KungFuJesus> hmm, is that case possible?  I mean it should be initialized regardless, I'm just wondering if that's a possible corner case being hit
16:33:03 <KungFuJesus> I mean I guess it is if it's checked and conditionally assigned, hah
16:36:10 <KungFuJesus> I'd hope this is userspace code at least?
16:56:42 <tsoome> yes it is
19:15:14 <copec> How far back does this go? https://illumos.org/man/8/ksslcfg I'm messing around with nginx kTLS ssl_sendfile()
19:32:53 <jclulow> copec: I think we retired that actually?  https://www.illumos.org/issues/14767
19:32:54 <fenix> → BUG 14767: retire kssl (Closed) | https://code.illumos.org/c/illumos-gate/+/2207
19:34:05 <copec> Yeah, it was looking old. Is implementing ssl_sendfile() on anyone's list?
19:34:25 <jclulow> Not that I know of
19:38:03 <copec> If I had a business riding on it, I would do it / pay to have it done. No complaints here. I've just been slowly watching the kTLS stuff matriculate into mainstream and was curious.
19:38:54 <jclulow> A business riding on TLS throughput specifically?
19:51:29 <copec> Sure, at first I saw stuff from Netflix about their cache boxes, but now I see stuff from all sorts
19:53:00 <copec> You have NVMe drives and want to saturate your network connections, that copy from kernel to userspace and back can make or break doing that
20:00:28 <copec> https://youtu.be/36qZYL5RlgY?t=425 Is recent
20:04:18 <copec> Of course Netflix is probably the most extreme case, but since everything is TLS based these days, kTLS becoming a standard thing to do is inevitable 
21:49:04 <tsoome> this is something funny: https://src.illumos.org/source/xref/illumos-gate/usr/src/lib/auditd_plugins/remote/audit_remote.c?r=bbf21555&mo=5209&fi=203#236
22:08:13 <richlowe> good grief
22:08:23 <richlowe> tsoome: I'm glad your on a system-wide source trawl and get to see the horrors, too
22:08:27 <richlowe> it feels like I have company
22:09:04 <tsoome> :D
22:11:34 <jclulow> copec: I think that assumes, still, bulk TLS transfer of data that requires no transformation; i.e., static file service
22:11:49 <richlowe> that is an awful lot of stuff
22:11:49 <rzezeski> tsoome: ouch
22:13:40 <jclulow> I also don't really understand how it interacts with, say, wanting to reuse a single connection for many things like you do with some of the more advanced HTTP stuff
22:13:53 <richlowe> that I don't know
22:14:36 <jclulow> I get that it helps Netflix, but they also control both the server and the client, and have a pretty specific need
22:14:49 <richlowe> but I think we have a long history of ignoring stuff like this because it's not some magically general solution 
22:14:55 <richlowe> and probably shouldn't just go "eh" off the bat
22:15:05 <jclulow> To be clear I'm super inf
22:15:15 <jclulow> in favour of someone to whom it is relevant, working on it
22:15:30 <jclulow> I just believe understand why nobody is
22:15:48 <jclulow> (at least visibly) doing so
22:40:18 <LXGHTNXNG> e
23:45:07 <richlowe> andyf: did we ever convince your relative(?) to make interrupting wsdiff work properly?
23:45:46 <LXGHTNXNG> there are whole families working on this?
23:48:13 <jlevon> lol
23:55:31 <andyf> tsoome - that's horrific
23:55:46 <andyf> richlowe - I know that an attempt was made, but I don't think it was successful