00:00:05 I guess one question is what the memory map looks like on each node and how you "name" the chunks of memory across the set of cooperating processors. 00:00:23 So, first I don't think CPUs can reach remote memory. 00:01:23 Certainly, the other stuff suggests that a single system is the coherency domain and that the local CPU can cache the local GPU's memory coherently, but I don't see anything beyond that. 00:01:58 It's also not clear to me that the remote GPU stuff is coherent per se, so I think if you were looking for a place to research, I'd go to how does this work with CUDA across multiple GPUs connected via NVLink today. 00:02:28 đź‘Ť 00:06:34 I've seen some indications that perfect coherency was surprisingly unimportant for ML training job communications(!) 00:07:57 Coherency is expensive. 15:05:09 [illumos-gate] 15496 dr: array subscript 3 is above array bounds -- Toomas Soome 15:38:34 when upgrading, how does smf determine if it should (re)import a manifest? I thought I found the bits that do that a while ago, but can't find it now, and I can't recall if it's just looking at a timestamp or doing a checksum of some sort on the manifest itself... 16:09:29 jbk: I also vaguely recall finding that recently and don't remember the answer.. 16:12:04 comments in /usr/src/cmd/svc/manifest-import strongly imply a hash 16:15:43 yeah, i encountered it somewhere in the past, but can't remember where now, or find it again :) 16:16:57 svccfg -s smf/manifest listprop dumps all the hashes. there's a pair of framework properties for each imported manifest with the pathname and a hash value 16:21:19 usr/src/cmd/svc/common/manifest_hash.c 16:21:23 using (alas) MD5 16:22:59 not because it's a vulnerability, but because it creates the possibility that you might need to prove to people that it's not a vulnerability in this application... 16:25:04 block comments around mhash_test_file() explain what it's looking for... 16:27:03 two hashes - one of file metadata, one of file contents. 17:11:01 @sommerfeld MD5 as CRC or as something actually secure? 18:10:48 I think the hash is used for rename detection or something? but it's been ages 18:11:05 and liane only explained the rename stuff to be very briefly, and in terms centered on it being a shame 18:12:07 but I thought it was in the same tub of magic as the `cmd/svc/shell/mfsthistory` file 18:12:12 but I could be 100% wrong 18:15:22 danmcd: used as change detection. 18:15:57 like I said, "use of MD5 creates creates the possibility that you might need to prove to people that it's not a vulnerability in this application.." 18:24:48 used only on files contained in directory hierarchies that ought to be writable only to system administrators. 19:58:09 sommerfeld: agreed 20:39:25 given an fd that's an open device node (i.e. S_ISCHR(mode) != 0), what would be the easiest way to determine the name of the driver for that (userland)? 20:50:11 get major number of st_rdev, convert to decimal, grep in /etc/name_to_major ? 20:52:13 (spot checking this appears to produce sane results) 21:00:30 (if you need to do this a lot, build an index, but you said "easy"..) 21:08:23 I had thought there was something in libdevinfo, but I'm not finding it 21:08:37 (probably to go from a major to a node to a name, but...) 21:25:09 jbk: https://github.com/illumos/illumos-gate/blob/master/usr/src/lib/libdevinfo/devfsinfo.c#L1502 21:25:40 (modctl is private, but that is the meat you would grind your interface from) 22:09:33 It's been long enough where I don't remember --> How do you determine which versions of `gmp`, `mpc`, and `mpfr` to use with a given version of gcc? Asking for a gcc14-curious friend. :) 22:10:03 [illumos-gate] 16867 gcc 14 needs to use -gstrict-dwarf afterall -- Toomas Soome 22:10:11 I just use the latest, I don't remember having to use specific versions 22:11:02 Gotcha. Latest it is. 22:29:54 is it possible to pass a virtual serial port using passthrough to bhyve ?, but what happens when that virtual serial port disappears?