#
✕ nick:Glanzmann
#asahi · 2021-12-09 20:55
Glanzmannzimsneexh: Start from scratch, what you get is probably not what you want.
#asahi · 2021-12-09 20:53
GlanzmannAlso on the olddefconfig, otherwise the config is screwed.
#asahi · 2021-12-09 20:53
Glanzmannzimsneexh: When you're crosscompiling, you need to specify the arch. See here: https://ab34.de/u/asahi.txt
#asahi · 2021-12-09 20:04
Glanzmanndmesg: https://pbot.rmdir.de/x6EXyRd9zAcCK7GWK-YdKw
#asahi · 2021-12-09 20:04
Glanzmannjannau: Firefox does not start with your kernel / config. However with alyssas config it worked. However the framebuffer seems to be much faster than the dcp.
#asahi · 2021-12-09 20:04
Glanzmannj`ey: At least for me the following works: USB-A Keyboard and Mouse. USB-C Hub with Tesira Forte Echo Cancler and Network Card.
#asahi · 2021-11-21 08:01
GlanzmannDoes someone have a tree that works ond a macbook air including keyboard, wifi and framebuffer x?
#asahi · 2021-11-21 05:15
GlanzmannOf course you could also boot via iscsi or nvme-over-tcp.
#asahi · 2021-11-21 05:15
GlanzmannThat is on the mini. I than installed xorg, firefox, fvwm2, you name it and was able to work from it for a week.
#asahi · 2021-11-21 05:14
GlanzmannRealityVoid: I used the following procedure to install Debian based on what allyssa did. https://ab34.de/u/asahi.txt
#asahi · 2021-11-18 09:50
Glanzmannmarcan: I had the very same problem. I did only saw the notice for step2.sh after it rebooted, because the boot picker covered it up and rebooted afterwards.
#asahi · 2021-10-21 19:44
Glanzmannmini: Did you tune the fan curves for the nuc? I didn't and it is noisy as hell.
#asahi · 2021-10-21 19:40
Glanzmannmini: I have the very same model (NUC8i5BEH): [ 0.000000] DMI: Intel(R) Client Systems NUC8i5INH/NUC8i5INB, BIOS INWHL357.0043.2021.0817.1957 08/17/2021
#asahi · 2021-10-21 19:35
Glanzmannmini: I normally use an intel nuc as workstation which is really noisy. If the nuc is off, I don't hear anything. For me the mini appears to be silent.
#asahi · 2021-10-21 19:29
GlanzmannBut if you watch a 4k video on cpu or run qemu it will.
#asahi · 2021-10-21 19:29
GlanzmannFor me it never turned on so far.
#asahi · 2021-10-21 19:28
Glanzmanntertu: Nope, they have a fan but it rarely engages.
#asahi · 2021-10-21 19:27
Glanzmannkettenis: My models (macbook air and mini) have 500 GB NVMe.
#asahi · 2021-10-21 19:26
Glanzmannj_ey: Corrected.
#asahi · 2021-10-21 19:26
Glanzmannyes.
#asahi · 2021-10-21 19:24
Glanzmannkettenis: OpenBSD beats Macos in SSD 4k random write performance. Question: What size is your NVMe? I updated https://ab34.de/u/m1-nvme-performance-linux-vs-macos-2021-10-18.txt
#asahi · 2021-10-18 21:35
GlanzmannAnyway, I'll hit bed now, if I should do any more tests, let me know.
#asahi · 2021-10-18 21:33
GlanzmannI did the test on the usb stick: 250 IOPS vs (50 on the nvme): https://pbot.rmdir.de/u/-eBt-nonVsZadqu1OheYLA
#asahi · 2021-10-18 21:32
GlanzmannDid I just quit irc, strange.
#asahi · 2021-10-18 21:30
GlanzmannI thought we don't have thunderbolt yet? But I have no thudnerbold drive, but I have a usb stick. Lets try that.
#asahi · 2021-10-18 21:26
GlanzmannBut if you want I can kick out the cpufreq driver and run the cpufreq experiment in m1n1, as I used to and reproduce the issue.
#asahi · 2021-10-18 21:26
Glanzmannsven: Probably it is best if you do the benchmarks yourself, than you trust them. :-)
#asahi · 2021-10-18 21:22
Glanzmannj_ey: Let me check.
#asahi · 2021-10-18 21:22
GlanzmannThis is how it looks with one thread. https://ab34.de/u/screenshot-nuc-2021-10-18-23_22_16.png
#asahi · 2021-10-18 21:21
Glanzmannsven: You saw my screenshot. This is 80 threads, I ran on of them.
#asahi · 2021-10-18 21:21
GlanzmannBut, if you want I can also run the m1n1 cpufreq experiment.
#asahi · 2021-10-18 21:20
Glanzmannsven: Even if it didn't its way to bad.
#asahi · 2021-10-18 21:20
GlanzmannYes, the driver is in.
#asahi · 2021-10-18 21:19
GlanzmannLet me check.
#asahi · 2021-10-18 21:19
Glanzmannsven: No, I did not. I ran alyssas tree.
#asahi · 2021-10-18 21:18
Glanzmannsven: I ran it multiple times. I notices the bad performance immediatly after I was installing my first debian package using apt. I ran 80 threads in parallel. I get 1000 IOPS. Look at the CPU: https://ab34.de/u/screenshot-nuc-2021-10-18-23_16_33.png
#asahi · 2021-10-18 20:58
Glanzmannsven / jey: I did not pin the core, but the point is the random write 4k are really bad.
#asahi · 2021-10-18 20:01
Glanzmannjmr2: Thank you.
#asahi · 2021-10-18 20:00
Glanzmannkettenis: Yes, but you can also paste the whole output.
#asahi · 2021-10-18 19:53
GlanzmannI added a TLDR: https://ab34.de/u/m1-nvme-performance-linux-vs-macos-2021-10-18.txt
#asahi · 2021-10-18 19:52
Glanzmannkettenis: For Linux we get only 50 iops, no idea why.
#asahi · 2021-10-18 19:51
GlanzmannThanks.
#asahi · 2021-10-18 19:51
GlanzmannYou can also compile it from source it is straightforward. just git clone and make.
#asahi · 2021-10-18 19:51
Glanzmannhttps://github.com/axboe/fio
#asahi · 2021-10-18 19:49
Glanzmannkettenis: Could you try this command and let me know how many iops do you get? fio --ioengine=sync --direct=0 --fsync_on_close=1 --randrepeat=0 --nrfiles=1 --name=randwrite --rw=randwrite --bs=4K --size=1G --end_fsync=1 --fallocate=none --overwrite=0 --numjobs=1 --sync=1 --directory=/mnt
#asahi · 2021-10-18 19:46
GlanzmannUnder OpenBSD?
#asahi · 2021-10-18 19:46
Glanzmannkettenis: Did you do performance benchmarks on the nvme?
#asahi · 2021-10-18 19:46
Glanzmannkettenis: I see. I used the mini on Linux for a few days, works good so far. Did not had any issues beside the dcp, but once the display is up it is stable.
#asahi · 2021-10-18 19:44
Glanzmannkettenis: What is the status of OpenBSD on m1?
#asahi · 2021-10-18 18:49
Glanzmannnobodynada: The good usb cable you only need to use a second m1 as a uart replacement. vuart works with a normal cable.

plus ›