00:27:19 gnu has --reference=FILE .. maybe it'd be worth using that (for that case) 00:29:48 maybe --reinherit, though that might be worth more thought e.g. should it recurse _up_ then apply encountered inherited ACLs in order (to the target files, not everything inbetween) on the way down 00:30:06 well nto might probably should 00:30:12 (more thought) 01:16:03 I think you'd want to have some way to constrain how far up it looked. 13:16:40 nomad: so after a few too many laaaaate night sessions, the ice driver is (finally) sending and receiving traffic 13:17:25 though a lot of the offloads are still disabled at this point and still missing some other things that need to be implemented) 13:18:59 in particular, the RX checksum bits look to be a bit of a tedious pain (as surprising as that might sound) 13:20:34 though i might import (w/ attribution of course) the rather large static table from the fbsd driver that actually let's you basically lookup when the IP or TCP/UDP checksom has been validated 13:20:45 (building that from hand is the tedious part) 14:24:31 on a somewhat related subject, I was reminded of something I saw from the hyper-v.. I think it's more of a general NDIS thing (though trying to find the actual relevant docs has not proven fruitful, so there's a fair amount of guesswork/assumption) 14:24:44 where they have what they call a 'chimney' 14:25:08 I _think_ the idea is that it allows for selected packets to jump to the front of the line when transmitting 14:27:13 which seems like it might be useful for certain things (imagine getting handed a long chain of packets (mblk_t->b_next) to transmit.. that could tie the TX ring up for a bit and being able to cut in line for things like certain TCP notifications seems like it could maybe be useful? 14:27:57 though I haven't looked to see how often mac sends more than one packet at a time down to the driver 14:29:16 (I'm guessing maybe more likely when the driver applies backpressure and returns mblk_ts in it's mc_tx(9E) function 20:21:13 jbk: I'm trying to work out by what analogy that could be "chimney" and am failig 20:21:20 not that that's not what it means, but I'd love to read the docs 20:21:35 I guess... hotter gasses rise faster? 20:21:43 and handwave handwave 20:41:36 no idea, and since I wasn't able to find good docs, I'm not 100% sure on it 20:41:52 other than it seemed to be a separate 'channel' for sending to the device 20:41:55 I get way too interesetd in how people come up with words 20:42:11 why I thought maybe it was a way to cut in line 20:42:22 at least it seems like something like that could be useful 20:43:08 a multi-flue chimney, perhaps? 20:45:01 a google search for [ndis chimney] turned up: https://learn.microsoft.com/en-us/windows-hardware/drivers/network/full-tcp-offload 20:45:47 ooooh 20:45:48 ok 20:45:50 so not that :) 20:45:56 (err not what I thought) 20:46:02 "This architecture is called a 'chimney offload' architecture because it provides a direct connection, called a 'chimney,' between applications and an offload-capable NIC. The chimney enables the NIC to perform TCP processing for offloaded connections, including maintaining the protocol state. " 20:46:09 so goes from the basement to above the roof 20:46:18 bypassing all the protocol layers on the floors in between 20:46:42 * jbk pictures danmcd doign his best chief inspector deyfuss impression just hearing that description :) 20:50:36 well I guess I should say Herbert Lom's version of it 20:50:48 Complete with eye twitch. 20:50:53 exactly 20:52:02 jbk: do you need testers for ICE or are you not quite there yet? 20:52:22 * nomad has been shopping at RePC, a very dangerous thing indeed. 20:52:31 not quite there yet -- I need to fix some TX bits, at least add some more stats 20:52:51 and probably do a bit more load just to make sure it's not mostly stable 20:52:54 k 20:57:40 the RX problem ended up being silly, but given the size and complexity, probably not too unsurprising given how many interruptions and times i've had to set it aside 20:57:40 though even having copilot analyize the code (_no_ code generation -- just review) couldn't find it either :P 21:01:47 i'm fixing some TX bugs (or trying to today.. i keep getting interrupted by other work things) 21:05:50 ooh nice.. new hard drive arrived... 21:05:50 which means I can use the old one (it's not dead, but has a lot of bad sectors.. more than any reserve) as a guinea pig for doing FW updates :P 23:15:20 can anyone kick redmine?