#
…

2021-02-17

00:00BaughnLogBot has joined #asahi
00:01BaughnLogBot has quit [Client Quit]
00:02BaughnLogBot has joined #asahi
00:11BaughnLogBot has quit [Quit: ZNC 1.6.2+deb1 - http://znc.in]
00:11BaughnLogBot has joined #asahi
00:12BaughnLogBot has quit [Client Quit]
00:13rwhitbymarcan: https://twitter.com/rwhitby/status/1361829828786229248 - this glasgow board under development might be useful as input to your serial cable work today
00:34vafanlignarderwhitby: nice work
00:35rwhitbyThanks. It's not been to manufacture yet. I have a breadboard implementation I'm testing.
00:59ky0ko has joined #asahi
02:02qyousef has quit [Ping timeout: 256 seconds]
02:03riker77_ has joined #asahi
02:04qyousef has joined #asahi
02:04riker77 has quit [Ping timeout: 264 seconds]
02:04riker77_ is now known as riker77
03:12phiologe has quit [Ping timeout: 260 seconds]
03:12phiologe has joined #asahi
03:22TheJollyRoger has quit [Ping timeout: 268 seconds]
03:30TheJollyRoger has joined #asahi
04:44gabiruh has quit [Quit: ZNC 1.7.5 - https://znc.in]
04:45gabiruh has joined #asahi
04:52marvin24 has quit [Ping timeout: 240 seconds]
04:53marvin24 has joined #asahi
05:08Bublik has quit [Ping timeout: 240 seconds]
05:10Bublik has joined #asahi
05:19GlanzmannWhen I close the lid on my macbook air, I assume macos destages the RAM to the NVMe in order to save battery on memory consumption, is that true? I assume that is the reason it can stay like forever on 'standby' without drawing battery?
05:20Bublik has quit [Ping timeout: 256 seconds]
05:22Bublik has joined #asahi
05:35mjg59Glanzmann: Memory in self refresh takes very little power
06:10VinDuv has joined #asahi
06:47Glanzmannmjg59: I didn't know. I see.
06:48mjg59Glanzmann: If you only get something like ~3GB/sec, it'd take ~5 seconds to restore RAM from NVMe
06:49mjg59(Actually more than that, because if you've powered down RAM you're going to need to go through firmware and start a bootloader that's able to start restoring that image and there's probably going to be some relocation involved as well)
06:51mjg59Pushing RAM out to non-volatile storage is great if you're expecting to be asleep for an extended period of time, but in general this is implemented by suspending to RAM (and keeping the RAM in self refresh) and then setting a wakeup timer for some point in the future, and if that goes off then suspending to storage instead
07:01mndza has joined #asahi
07:24macc24 has quit [Quit: ZNC 1.7.5 - https://znc.in]
07:33VinDuv has quit [Quit: Leaving.]
07:48bkeroIt's also great if you need a lot of RAM. What's the price of 1TB DRAM versus 1TB NVMe or whatever Intel's thing is called again
07:48bkeroOptane Persistent Memory
07:52bkero...that's probably not very relevant to these machine sthough
08:00maor26 has joined #asahi
08:06amw has joined #asahi
08:07matsdidnt intel kill that product line recently?
08:08matsah just the consumer lines
08:32M0_osx[m] is now known as osxre
08:33osxre is now known as M0_osx[m]
08:39ephe_meral has joined #asahi
08:57amw has quit [Ping timeout: 246 seconds]
08:59bisko has quit [Ping timeout: 240 seconds]
09:00redbluescreen[m] has quit [Quit: Idle for 30+ days]
09:00rockinrobstar[m] has quit [Quit: Idle for 30+ days]
09:00crafteck[m] has quit [Quit: Idle for 30+ days]
09:19ifthenelse has joined #asahi
09:26Lumi[m] has quit [Quit: issued !quit command]
09:29TheJollyRoger has quit [Remote host closed the connection]
09:29TheJollyRoger has joined #asahi
09:46bisko has joined #asahi
09:51Glanzmannmjg59: Yes, makes sense. I also benchmarked the nvme speed on macbook and it seems to be like 3 gb/s for linear read with large block/page size.
09:51GlanzmannAnd the macbook is always instead on, at least it feels that way.
09:52GlanzmannAbout marcan serial cable, is there a part list yet that I can order in order to assemble one?
09:52GlanzmannI think there was alread one in the wiki, wasn't it?
09:56Glanzmannunignore 1
10:38amw has joined #asahi
10:39marcanGlanzmann: not yet, not for the new one
10:40marcanfor the old one, you can cobble it together from a FUSB302, an arduino, some kind of 1.2V serial interface, and a USB-C breakout board
10:40j`eymarcan: is the diagram you posted enough to start on schematics? or is there more design left
10:40marcanmostly just narrowing down specific parts, but I can start on part of the schematics already
10:41marcanthe big parts to choose are STM32, muxes (and exact layout, could be one or two chained), and USB hub
10:42amw has quit [Ping timeout: 256 seconds]
10:42j`eymarcan: what is the hub for?
10:43j`ey(I havent watched the stream (yet))
10:43marcanso upstream can talk to both the mac target, and the stm32
10:43marcanpotentially up to two ports on the mac target
10:43marcanand a fourth, different port if you use it as a chromebook suzy cable
10:43marcan(which, since 4-port hubs are standard, makes sense to do)
11:01ephe_meral has quit [Ping timeout: 246 seconds]
11:10ephe_meral has joined #asahi
11:25bisko_ has joined #asahi
11:26bisko has quit [Read error: Connection reset by peer]
11:26xarkes has quit [Ping timeout: 240 seconds]
11:36xarkes has joined #asahi
11:36Glanzmannmarcan: I see.
12:06JTL has quit [Ping timeout: 246 seconds]
12:14JTL has joined #asahi
12:22ephe_meral has quit [Ping timeout: 246 seconds]
12:31bisko_ has quit [Quit: My MacBook has gone to sleep. ZZZzzz…]
12:56xarkes has quit [Ping timeout: 264 seconds]
13:09xarkes has joined #asahi
13:30nebh^ has quit []
13:37never_releasedData Units Written: 35,121,211 [17.9 TB]
13:37never_releasedmacOS continuing to be macOS
13:42davidrysk[m]never_released: is it primarily kernel_task that's doing it?
13:42marcandavidrysk[m]: btw, did you see that tweet I RTed?
13:42davidrysk[m]I'm at 461.80GB of kernel_task writing in 20h29m of uptime
13:42marcanof the guy with the same volume as you, but a 256GB SSD
13:43davidrysk[m]wonder what typical uptimes are
13:43davidrysk[m]never_released: do you avoid rebooting?
13:46arndI wonder if you can move the swap file to an external ssd to see if the remaining I/O within the expected range
13:47arndI tried to see what it's actually doing, but I don't seem to have permissions to run iosnoop
13:48delrothI wonder how much of the "kernel_task is writing a lot of data" is swapping vs. bad accounting :)
13:49delrothe.g. syncs being accounted to kernel_task for some reason
13:52luca020400does mac os x has something zram like?
13:55luca020400and it concurrently does swap to disk?
13:55marcanI'm not entirely sure what the logic is
13:57luca020400interesting, I've never had a setup with both
14:02xarkes has quit [Ping timeout: 260 seconds]
14:07never_releaseddavidrysk[m]: yeah I don't reboot all the time
14:08never_releasedjust on OS updates mostly
14:08davidrysk[m]my hypothesis is that there's something leak-like that causes the problem to happen after 24-48h of uptime
14:08never_releasedluca020400: WKdm
14:08davidrysk[m]at 517.16GB written now
14:08never_releasedaka page-level compression
14:08never_releasedit's done through a CPU extension
14:09never_releasedbut XNU has an implementation using regular assembly
14:09davidrysk[m]55.36GB in 26 minutes
14:09davidrysk[m]is 100GBW per hour excessive?
14:09never_releaseddavidrysk[m]: kernel_task is at 4.05TB here
14:09never_releasedvery excessive
14:09davidrysk[m]I thought so :)
14:10never_releasedinb4 iOS has this bug too
14:10davidrysk[m]I thought iOS doesn't swap
14:10davidrysk[m]but freezes processes instead
14:11never_releasedno swap doesn't mean that file-backed mappings can't cause issues like this one
14:11davidrysk[m]no backing store so there's no paging
14:12davidrysk[m]never_released: can you try `sudo zprint`?
14:12davidrysk[m]I can't get it to work (but I do have security on)
14:12never_releaseddavidrysk[m]: SIP on here
14:12never_releasedzprint only works with SIP off
14:12davidrysk[m]it's SIP that blocks it? okay
14:12davidrysk[m]guess I'll have to turn SIP off
14:13davidrysk[m]I was going to make a script that captures zprint output every minute or so
14:13davidrysk[m]and then look for a leak
14:13never_releasednot a good idea generally
14:13davidrysk[m]oh I know the downsides of turning off SIP
14:13never_releasedyou have vm_stat, davidrysk[m]
14:13davidrysk[m]not too worried about that... what I'm not doing is amfi_get_out_of_my_way=1 because that breaks a lot of things
14:13davidrysk[m]vm_stat doesn't give enough detail
14:14davidrysk[m]though zprint might not either
14:14never_releasedamfi_get_out_of_my_way is a bad idea in general
14:14xarkes has joined #asahi
14:16macc24 has joined #asahi
14:16davidrysk[m]already at 536.05GB
14:16davidrysk[m]so yeah, 100GBW per hour
14:17davidrysk[m]and I'm only looking at kernel_task's writes
14:18davidrysk[m]how dangerous is it to turn off swap with bootargs?
14:19luca020400never_released: thanks, headers explains enough to understand what it does
14:27never_releasedhas funny things
14:29luca020400oh, so these funny registers where from this feature lol
14:29luca020400I saw the define before
14:33davidrysk[m]Still getting this deadlock on shutdown…
14:40never_releaseddavidrysk[m]: I am getting that deadlock on shutdown too.
14:40never_releasedyou aren't the only one
15:02davidrysk[m]never_released: disabled sip, still can't zprint -t
15:03davidrysk[m]zprint: mach_memory_info: (os/kern) invalid host (try running as root)
15:21mndza has quit [Read error: Connection reset by peer]
15:22mndza has joined #asahi
15:24Helikoptere has joined #asahi
15:40davidrysk[m]never_released: do you use little snitch or blockblock?
15:47GlanzmannDoes someone know if macos runs in parallels or the macos hypervisor on m1?
15:51davidrysk[m]Glanzmann: it doesn't
16:00odmir has quit [Remote host closed the connection]
16:00bisko has joined #asahi
16:01odmir has joined #asahi
16:17davidrysk[m]parallels or the hypervisor would have to support the peripherals needed for it (or well, enough of them)
16:26odmir has quit []
16:27jato_ is now known as jato
16:42ephe_meral has joined #asahi
16:59odmir has joined #asahi
17:04ephe_meral has quit [Ping timeout: 272 seconds]
17:07ephe_meral has joined #asahi
17:16Mrmaxmeier has quit [Remote host closed the connection]
17:19mndza has quit [Ping timeout: 260 seconds]
17:30vimal has joined #asahi
17:38VinDuv has joined #asahi
17:41Glanzmanndavidrysk[m]: Of course, writing device simulators without documentation is almost the same problem we have. :-)
17:49vimal has quit [Remote host closed the connection]
17:54raster has joined #asahi
18:03davidrysk[m]I have parallels running a Windows 10 VM with 4GB of allocated RAM and the kernel_task memory usage is rapidly increasing
18:05arekm has quit [Ping timeout: 264 seconds]
18:07arekm has joined #asahi
18:08mndza has joined #asahi
18:10GlanzmannAny idea what this paging is about?
18:11GlanzmannLast time I heard about a unix paging without memory pressure, is when there wasn't MMU and process was paged to the disk on cotext switch. :-)
18:17bisko has quit [Quit: My MacBook has gone to sleep. ZZZzzz…]
18:52modwizcodeIt's interesting that apple has (in addition to their generic Hypervisor acceleration extension framework) a second API just for easily bootstrapping Linux VMs, but it's specific to Linux VMs.
18:52Namidairo has quit [Read error: Connection reset by peer]
18:54Namidairo has joined #asahi
19:02never_releasedmodwizcode: in past versions, had some entry points for macOS ones
19:02never_releasedbut seems to be gone for now
19:03mndza has quit [Ping timeout: 240 seconds]
19:20vimal has joined #asahi
19:22modwizcodeinteresting
19:26ephe_meral has quit [Ping timeout: 272 seconds]
19:26vimal has quit [Ping timeout: 272 seconds]
19:45vimal has joined #asahi
20:03ephe_meral has joined #asahi
20:19odmir has quit []
20:20brandas[m] has joined #asahi
20:24davidrysk[m]modwizcode: are you talking about Virtualization.framework?
20:32brandas[m] has left #asahi ["User left"]
20:36brandas[m]1 has joined #asahi
20:45ephe_meral has quit [Ping timeout: 265 seconds]
20:47rockinrobstar[m] has joined #asahi
20:48davidrysk[m]modwizcode: cool :)
20:51odmir has joined #asahi
20:53brandas[m]1 has left #asahi ["User left"]
21:13raster has quit [Ping timeout: 265 seconds]
21:38ky0ko has quit [Quit: http://quassel-irc.org - Chat comfortably. Anywhere.]
21:42VinDuv has quit [Quit: Leaving.]
22:12raster has joined #asahi
22:12kubes has quit [Quit: Leaving]
22:31raster has quit [Ping timeout: 264 seconds]
22:32raster has joined #asahi
23:21inglor_ has joined #asahi
23:22inglor has quit [Ping timeout: 264 seconds]
23:28maor26 has quit [Ping timeout: 256 seconds]
23:53zopieux has quit [Ping timeout: 272 seconds]
23:54zopieux has joined #asahi
23:59ky0ko has joined #asahi
…