20:09:15 <Molnija> what's illumos' relationship with XTI/TLI?
20:11:50 <richlowe> are you meaning is it still present and supported? (yes), or do we like it? (not really)
20:12:01 <richlowe> danmcd is probably the one for actual details
20:12:10 <danmcd> Oh...
20:12:23 <danmcd> Yeah... XTI/TLI still exist.
20:13:57 <danmcd> Biggest mission-critical user is NFS & friends AFAICT.  TCP/IP itself is direct-sockets these days, unless you have REALLY OLD CODE that either uses TLI/XTI or worse, does socket() followed by an I_POP of "sockmod" which means you were optimizing for pre-Solaris-2.6.
20:14:12 <danmcd> We highly recommend you NOT use XTI/TLI.
20:14:20 <danmcd> @Molnija that answer your question?
20:14:51 <Molnija> very thoroughly, thanks.
20:15:30 <Molnija> So, except for a toy, don't write new code that uses that interface?
20:15:41 <danmcd> YW.  And yes, your last sentence is correct.
20:16:12 <Molnija> Understood, understood.
20:18:48 <Molnija> So were XTI and TLI kinda like a collective delusion or something? That's the energy I get from reading about it.
20:20:42 <Molnija> damn, my music player skips a lot. I should get a pair of SSDs, or a rank of SAS rotaries
20:22:03 <danmcd> Molnija... I wasn't involved in Solaris or SysV when that decision was made.  The idea was AT&T's SysV folks REALLY LIKED STREAMS (when you were shouting STREAMS), and thought it would take over the world.
20:22:15 <Molnija> hehe
20:22:29 <danmcd> They included "sockmod" and "libsocket" for compatiblity with BSD sockets apps.
20:22:43 <danmcd> Now in a world with not many connections and data dominance, it wasn't HORRIBLE.
20:23:06 <Molnija> ... and popping sockmod was a way of stripping the BSD compatibility after you'd used it?
20:23:42 <danmcd> Popping sockmod was done after acceptance/connection because read/write didn't need any of its functionality.
20:24:08 <Molnija> ah
20:24:10 <danmcd> Early web deployments shined a light on how horrible it was.  Apps were used to the sockets API, and a TCP accept() employed 6 (yes six) syscalls under sockmod/libsocket.
20:24:26 <Molnija> woof!
20:24:53 <Molnija> Sounds like something I should be glad for the death of
20:25:00 <danmcd> In Solaris 2.6 sockfs was developed, and while it kept the STREAMS TCP/IP kernel code, it obviated libsocket and sockmod.
20:25:32 <danmcd> (For historical purposes... SysV dropped in the late 80s, Solaris 2.0/SunOS 5.0 was 1991, and Solaris 2.6 was 1997.)
20:26:49 <danmcd> After sockfs bought us some time, the FireEngine project, while not perfect, was a good de-streams-ing of the TCP/IP stack.  The Nemo (GLDv3) project finished the device-driver side of the job. And the Volo (direct-sockets) project finished the API/sockfs side of the job.
20:27:02 <Molnija> aha
20:28:02 <danmcd> And finally, the IP datapath refactoring (concurrent with, but required for Volo) cleaned up TCP/IP's paths even more.
20:28:39 <danmcd> IP datapath and Volo were the last Big things to come out of Sun before Oracle closed things.  Nemo, BTW, introduced vnics as well.
20:30:53 <Molnija> right on
20:34:35 <Molnija> Thanks for the talk. I think I understand the situation a little better. Sorry for wasting your time on this. >.<
21:24:52 <danmcd> You did not waste my time (esp. two days before the US Thanksgiving holiday), I hope I didn't waste yours (and I REALLY hope I didn't get any details wrong).
21:25:01 <danmcd> (And pardon the latency Molnija...)
21:26:35 <Molnija> you have not wasted my time at all
21:29:08 <nbjoerg> it was interesting to read
21:30:06 <richlowe> maybe one day alanc &co will write us an official history
21:30:32 <Molnija> a
21:30:41 <alanc> dan was much closer to all that than I was
21:30:59 <alanc> I just have the benefit of still having SCCS history to look at
21:31:00 <richlowe> Yes, I meant of everything.
21:31:03 <richlowe> he was part of the &co
21:31:36 <alanc> "In the beginning there was BSD, and wnj said it was good..."
21:38:21 * alanc goes back to writing his second EOF ARC case of the week
21:38:57 <richlowe> exciting?
21:39:27 <Molnija> wnj?
21:39:35 <Molnija> Bill Joy?
21:39:41 <alanc> yes
21:39:45 <Molnija> ah
21:40:19 <alanc> richlowe: not really, just time to remove libXevie and libXxf86misc since X.Org abandoned them several years back
21:50:45 * danmcd is feeling old
21:51:01 <danmcd> (My "30 years in this business" anniversary is 14mos away.)  Gotta run, errand.
22:01:40 <Molnija> you've been ITB longer than I've been alive
22:02:48 <tsoome> I guess iI can not say "in this business" as I did start working in university:D
22:02:49 <yuripv> now danmcd feels really old :D
22:03:52 <Molnija> I'm just a smol dragon
22:03:54 <tsoome> back then, we got 2x sun3 workstations.
22:05:46 <tsoome> but my first unix account was created in SCO unix... 
22:06:06 <tsoome> fun time it was.
22:09:31 <Molnija> wew.
22:30:43 <alanc> my first account was on DEC Ultrix, my first root was on Apollo Domain/OS
22:31:17 <alanc> my first OS-level source commit was (big surprise) Solaris
23:04:07 <sjorge> does our nfs server support proto=rdma?
23:21:06 <sjorge> looks like we dont