00:52:09 [illumos-gate] 17101 os-tests: unchecked function return 'fflush' -- Toomas Soome 00:54:25 [illumos-gate] 17102 rootnex: ignoring unreachable code. -- Toomas Soome 10:22:51 [illumos-gate] 17103 testoplock: unchecked function return -- Toomas Soome 16:59:53 Hey) 16:59:55 Does current Mellanox Connect-X driver support RDMA? 17:02:50 AFAIK, none of the mellanox cards support RDMA on illumos 17:17:11 jbk: How do you think, is it hard to add RDAM support ? BTW, what was initial source for the drivers where it was ported? 17:22:40 vetal, it probably depends on the expertise of the person adding it :) doesn't sound that difficult in concept 18:04:00 RDMA is one of those networking features that has to punch through many layers of the stack to get bits from hardware to the application so it ends up likely as a more involved integration than most. 18:06:28 IIRC, the ib support we have is fairly old, but i don't think the rdma bits for it are coupled too tightly, but so it might be able to leverage the existing bits, but not sure how much work might be needed to get all of that up to more recent versions of any of the relevant standards 18:28:10 i'm not sure what source was used for the original drivers (and the person that did the work isn't online) 18:28:23 prior to nvidia buying mellanox, the programming guide was however freely available 18:28:38 so it wouldn't surprise me if that was the basis 18:28:57 I'm not sure how difficult it would be to get an updated one from nvidia 18:29:49 i suspect there's probably some sort of NDA involved, but might be able to just glean the differences by looking at say the freebsd drivers to see what incremental bits were needed to support the newer cards 18:30:48 my recollection on cx-4 -> cx-5 -> cx-6 was that it was mostly additive and there weren't too many radical changes (e.g. maybe a couple of new registers for the newer features/speeds, but most of the base functionality was identical) 18:56:25 There was no 'initial source'. The driver was written as its own thing. 18:57:10 Other things are used as references, but it's not like there's some common code or anything. 19:52:53 i'm assuming a programming guide was the source, but wasn't sure 19:53:32 (source for how it worked) 19:55:06 Yes, I just took vetal's thing to be code source. 19:55:14 And even the public one then was out of date. 19:59:10 I feel like I've missed something 20:01:28 richlowe: mellanox NIC driver stuff 20:08:24 I feel like I'm happy I've missed something 20:20:19 I usually am! 21:21:37 Anyone got cycles to bringup an illumos driver for this? 21:21:39 https://infosec.exchange/@elforesto/113881234510052536 21:22:05 (Bonus points if you can do some HW engineering and create a 4-chip/4-port version of this using a PCIe 4 x4 slot) 21:32:26 I wonder what it is 21:32:45 it seems like nobody new would enter the 10G asic market 21:33:38 Marvel 22:11:43 Yeah, it's actually a much older part that I didn't realize was being refreshed. 22:21:46 I wish these 10GBaseT parts would get older models shrunk/made-cheaper. I'm thinking HDC4 needs 4 10GBaseT ports that do 1/2.5/5/10. Kinda like the Intel X550-series but, well, cheaper. (I see the X722 has disappeared from most folks' radars and modern mobos that go there use X710... curious. :) ) 22:22:14 It's because they dropped it from the PCH. 22:29:01 [illumos-gate] 16906 bhyve should support AMD perf counters -- Patrick Mooney