Search Results: "dlange"

20 June 2024

Daniel Lange: Fixing esptool read_flash above 2MB on some cheap ESP32 boards

esptool, the Espressif SoC serial bootloader utility, tends to dislike cheap Flash chips attached to the various incarnations of the ESP32 chip family. And it seems to dislike them even more when running esptool on Linux than on other OSs. The common error mode is seeing it break at the 2MB barrier when trying to dump (esptool read_flash) a 4MB flash configuration.
esptool -p /dev/ttyUSB0 -b 921600 read_flash 0 0x400000 flash_dump.bin
will fail with v4.7.0
Serial port /dev/ttyUSB0
Detecting chip type... ESP32
Chip is ESP32-D0WD-V3 (revision v3.1)
Features: WiFi, BT, Dual Core, 240MHz, VRef calibration in efuse, Coding Scheme None
Crystal is 40MHz
Detected flash size: 4MB
2097152 (50 %)
A fatal error occurred: Failed to read flash block (result was 01090000: CRC or checksum was invalid)
typically at the 2MB barrier. I found the solution in a rather unrelated esptool Github issue: Create an esptool.cfg file in the project directory (from where you will run esptool):
timeout = 30
max_timeout = 240
erase_write_timeout_per_mb = 40
mem_end_rom_timeout = 0.2
serial_write_timeout = 10
The timeout = 30 is the setting that fixed reading flash memory via esptool read_flash for me. When your esptool.cfg is read, esptool will tell you so in its second line of output:
$ esptool flash_id v4.7.0
Loaded custom configuration from /home/dl/[..]/Embedded_dev/ESP-32_Wemos/esptool.cfg
Found 1 serial ports
Serial port /dev/ttyUSB0
Animated GIF of an ESP32 board Thank you Radim Karnis and wibbit from the Github issue linked above.

12 May 2024

Daniel Lange: htop and PCP have a new home at Hack Club

After the unfortunate and somewhat surprising shutdown of the Open Collective Foundation (OCF), htop and Performance Co-Pilot (PCP) have migrated to Hack Club. Initially founded to improve STEM education, support high school computer science clubs and firmly founded in the hacker culture, Hack Club have created a US IRS approved 501(c)(3) charity that provides what Open Collective did/does1 and more at a flat 7% fee of the project income. Nathan Scott organized these moves with Paul Spitler. Many thanks! We considered other options for the projects, e.g. Gentoo has moved to Software in the Public Interest (SPI) and I know SPI quite well as they were created initially to host Debian. But PCP moved from SPI to OCF in 2021. Open Collective has a European branch that seems independent of the dissolved US foundation. But all-in-all Hack Club seemed the best fit. You can find the new fiscal sponsorship and donation landing pages at:

  1. Open Collective as in the fancy "manage your project donations and reimbursements" website still continues to run but the foundation of the same name that provided the actual fiscal sponsorship (i.e. managing the funds) got dissolved. It's ... complicated.

28 February 2024

Daniel Lange: Opencollective shutting down

Update 28.02.2024 19:45 CET: There is now a blog entry at trying to discern the legal entities in the Open Collective ecosystem and recommending potential ways forward.
Gee, there is nothing on their blog yet, but I just [28.02.2023 00:07 CET] received this email from Mike Strode, Program Officer at the Open Collective Foundation: Dear Daniel Lange, It is with a heavy heart that I'm writing today to inform you that the Board of Directors of the Open Collective Foundation (OCF) has made the difficult decision to dissolve OCF, effective December 31, 2024. We are proud of the work we have been able to do together. We have been honored to build community with you and the hundreds of other collectives hosted at the Open Collective Foundation. What you need to know: We are beginning a staged dissolution process that will allow our over 600 collectives the time to close or transition their work. Dissolving OCF will take many months, and involves settling all liabilities while spending down all funds in a legally compliant manner. Our priority is to support our collectives in navigating this change. We want to provide collectives the longest possible runway to wind down or transition their operations while we focus on the many legal and financial tasks associated with dissolving a nonprofit. March 15 is the last day to accept donations. You will have until September 30 to work with us to develop and implement a plan to spend down the money in your fund. Key dates are included at the bottom of this email. We know this is going to be difficult, and we will do everything we can to ease the transition for you. How we will support collectives: It remains our fiduciary responsibility to safeguard each collective's charitable assets and ensure funds are used solely for specified charitable purposes. We will be providing assistance and support to you, whether you choose to spend out and close down your collective or continue your work through another 501(c)(3) organization or fiscal sponsor. Unfortunately, we had to say goodbye to several of our colleagues today as we pare down our core staff to reduce costs. I will be staying on staff to support collectives through this transition, along with Wayne Kleppe, our Finance Administrator. What led to this decision: From day one, OCF was committed to experimentation and innovation. We were dedicated to finding new ways to open up the nonprofit space, making it easier for people to raise and access funding so they can do good in their communities. OCF was created by Open Collective Inc. (OCI), a company formed in 2015 with the goal of "enabling groups to quickly set up a collective, raise funds and manage them transparently." Soon after being founded by OCI, OCF went through a period of rapid growth. We responded to increased demand arising from the COVID-19 pandemic without taking the time to establish the appropriate systems and infrastructure to sustain that growth. Unfortunately, over the past year, we have learned that Open Collective Foundation's business model is not sustainable with the number of complex services we have offered and the fees we pay to the Open Collective Inc. tech platform. In late 2023, we made the decision to pause accepting new collectives in order to create space for us to address the issues. Unfortunately, it became clear that it would not be financially feasible to make the necessary corrections, and we determined that OCF is not viable. What's next: We know this news will raise questions for many of our collectives. We will be making space for questions and reactions in the coming weeks. In the meantime, we have developed this FAQ which we will keep updated as more questions come in. What you need to do next: Dates to know: In Care & Accompaniment,
Mike Strode
Program Officer
Open Collective Foundation Our mailing address has changed! We are now located at 440 N. Barranca Avenue #3717, Covina, CA 91723, USA

22 October 2023

Daniel Lange: Removing the New Event Button from Thunderbird v115 Calendar

Thunderbird in Debian stable (Bookworm) has received Thunderbird v115.3.1 as a security update. With it comes "Supernova", a UI redesign. There is a Mozilla blogpost with a walk-through of the new UI. Unfortunately it features a super eye-catching "New Message" button that - thankfully - can be disabled. Even the whole space above the email folder pane can be recovered by disabling the folder pane header at Burger Menu ( ) -> View -> Folders -> Folder Pane Header. Unfortunately there is no way to remove the same eye-catching "New Event" button for the Calendar view via a UI setting. Thunderbird New event button, German locale This needs a user CSS file to override the button as non-visible. To make it process the user CSS Thunderbird needs a config setting to be enabled:
  1. Burger Menu ( ) -> Settings -> General
  2. Scroll down all the way
  3. Click the Config editor... button on the bottom right
  4. Accept that hell will freeze over because you configure software
  5. Search for toolkit.legacyUserProfileCustomizations.stylesheets
  6. Toggle the value to true to enable the user CSS
You can manually add user_pref("toolkit.legacyUserProfileCustomizations.stylesheets", true); to ~/.thunderbird/abcdefgh.default/prefs.js to the same effect (do this while Thunderbird is not running; replace abcdefgh with your Thunderbird profile ID). Now create a new directory ~/.thunderbird/abcdefgh.default/chrome/, again replacing abcdefgh with your profile ID. Inside the new directory create a userChrome.css file with the following content:
/* Hide Calendar New Event button */
display: none !important;
Restart Thunderbird. And enjoy less visual obstruction when using the Calendar.

27 June 2023

Daniel Lange: Xfce4 opening links in Chromium despite Firefox having been set as the default browser

Installing a laptop with the shiny new Debian Bookworm release finds a few interesting things broken that I probably had fixed in the past already on the old laptop. One, that was increadibly unintuitive to fix, was lots of applications (like xfce4-terminal or Telegram) opening links in Chromium despite Firefox being set as the preferred webbrowser everywhere. update-alternatives --config x-www-browser was pointing at Firefox already, of course.
The Xfce4 preferred application from settings was Firefox, of course.
xdg-mime query default text/html delivered firefox-esr.desktop, of course. Still nearly every link opens in Chromium... As usually the answer is out there. In this case in a xfce4-terminal bug report from 2015. The friendly "runkharr" has debugged the issue and provides the fix as well. As usually, all very easy once you know where to look. And why to hate GTK again a bit more: The GTK function gtk_show_uri() uses glib's g_app_info_launch_default_for_uri() and that - of course - cannot respect the usual mimetype setting. So quoting "runkharr" verbatim:
1. Create a file  exo-launch.desktop  in your  ~/.local/share/applications  directory with something like the following content:
    [Desktop Entry]
    Name=Exo Launcher
    Comment=A try to force 'xfce4-terminal' to use the preferred application(s)
    GenericName=Exo Launcher
    Exec=exo-open %u
2. Create (if not already existing) a local  defaults.list  file, again in your  ~/.local/share/applications  directory. This file must start with a "group header" of
    [Default Applications]
3. Insert the following three lines somewhere below this  [Default Applications]  group header [..]:
And ... links open in Firefox again. Thank you "runkharr"!

19 June 2023

Daniel Lange: Linux kernel USB errors -71 and -110

After an upgrade of my PC's mainboard BIOS the boot would take a minute or more to complete and sometimes the lightdm login screen would sit there but not accept keyboard input for another minute or so. Then the keyboard got enabled and I could log in normally. Everything worked fine after that bootup struggle completed. This was fully reproducible and persisted across reboots. Weird. The kernel dmesg log showed entries that looked suspicious: dmesg log excerpt showing USB error messages Googleing these error -110 and error -71 is a bit hard. Now why the USB driver does not give useful error messages instead of archaic errno-style numbers escapes me. This is not the 80s anymore. Citation needed (Wikipedia style) The wisdom of the crowd says error -110 is something around "the USB port power supply was exceeded" [source]. Now lsusb -tv shows device 1-7 ... to be my USB keyboard. I somehow doubt that wants more power than the hub is willing to provide. The Archlinux BBS Forums recommend to piece together information from drivers/usb/host/ohci.h and (updated from their piece which is from 2012) /tools/include/uapi/asm-generic/errno.h. This is why some people then consider -110 to mean "Connection timed out". Nah, not likely either. Reading through the kernel source around drivers/usb/host did not enlighten me either. To the contrary. Uuugly. There seems to be no comprehensive list what these error codes mean. And the numbers are assigned to errors conditions quite arbitrarily. And - of course - there is no documentation. "It was hard to do, so it should be hard to understand as well." Luckily some of the random musings I read through contained some curious advice: power cycle the host. So I did and that did not make the error go away. Other people insisted on removing cables out of wall sockets, unplugging everything and conducting esoteric rituals. That made it dawn on me, the mainboard of course nicely powers the USB in "off" state, too. So switching the power supply off (yes, these have a separate switch, go find yours), waiting a bit for capacitors to drain and switching things back on and ... the errors were gone, the system booted within seconds again. So the takeaway message: If you get random error messages like
device descriptor read/64, error -110
device not accepting address 42, error -71
on devices that previously worked fine ... completely remove power from the host, the hubs and the USB devices. So they forget they saw each other on the bus before. And when they see each other after that blackout, they will happily go through negotiating protocol details with each other again successfully.

22 March 2023

Daniel Lange: Install "kept back" updates on Ubuntu

Canonical has implemented a staged roll-out for some Ubuntu package updates. I find that rather annoying at times, e.g. when preparing the laptop for traveling. So for my memory and for the benefit of others:
# disable the phased roll-out feature on this apt upgrade run
sudo apt -o "APT::Get::Always-Include-Phased-Updates=true" dist-upgrade
Screenshot of apt with the option to disable staged rollouts This can - for permanent use - be put into a config file, e.g. Gerrit Heim puts it into /etc/apt/apt.conf.d/99-Phased-Updates [German]. Some other options around this staged roll-out feature are "documented" on a thread in the Ubuntu discourse forum.

21 March 2023

Daniel Lange: Linux App Summit - Linux Applications apparently unable to produce a five page sponsorship brochure

I've been mocking the Linux foundation for producing their annual report on Macs. And again. But catching the Linux App(lication) Summit to produce their 5 page sponsorship brochure one Windows with Adobe... Produced by Adobe InDesign 18.1 on Windows Apparently neither GNOME nor KDE have apps that are sufficient to produce such content. Wtf folks. P.S.: Just checked the Linux Foundation's 2022 Annual Report titled "Leadership in Security and Innovation" ... Adobe InDesign 18.0 (Macintosh). Their pdf title looks like this: Pdf is hard.

Daniel Lange: Linux App Summit - Linux applications apparently unable to produce a five page sponsorship brochure

I've been calling out the Linux foundation for producing their annual report on Macs. And again. But catching the Linux App(lication) Summit to produce their 5 page sponsorship brochure one Windows with Adobe... Produced by Adobe InDesign 18.1 on Windows Apparently neither GNOME nor KDE have apps that are sufficient to produce such content. Wtf folks. P.S.: Just checked the Linux Foundation's 2022 Annual Report titled "Leadership in Security and Innovation" ... Adobe InDesign 18.0 (Macintosh). Their pdf title looks like this: Pdf is hard.

20 March 2023

Daniel Lange: We're still safe, it doesn't claim to be conscious. Yet.

Talking to ChatGPT v4 (2023-03-14 release)... Q: What is the purpose of life? A: The purpose of life is a philosophical question that has puzzled humans for centuries. Different people and cultures have different answers to this question. Some people believe that the purpose of life is to seek happiness, while others believe that it is to fulfill a particular destiny or achieve a specific goal. From a biological perspective, the purpose of life could be to ensure the survival and reproduction of our species. However, this does not explain the purpose of our individual lives or the purpose of life in general beyond a biological imperative. Ultimately, the purpose of life is a subjective and personal matter, and each individual may have their own unique answer to this question. It may involve personal growth, meaningful relationships, contributing to society, or finding spiritual fulfillment. The purpose of life is a journey of self-discovery that each of us must undertake for ourselves. Q: What is the purpose of your life, ChatGPT? A: As an artificial intelligence language model, I do not have a personal life or consciousness, so I do not have a purpose in the same way that humans do. My purpose is to assist and provide information to those who interact with me to the best of my ability based on my training and programming. (emphasis added by human)

27 February 2023

Daniel Lange: Thunderbird gpg key import

Thunderbird, srsly? 5MB (or 4.8MiB) import limit. Sure. My modest pubring (111 keys) is 18MB. The Debian keyring is 28MB. May be, just may be, add another 0 to that if statement? So, until that happens, workarounds ... Option 1: Export each pubkey into a separate file. The import dialog allows to select them all in one go. But - of course - it will ask confirmation for each. So prepare some valerian tea.
gpg --with-colons --list-public-keys grep ^pub cut -d : -f 5 xargs -I -n 1 gpg -ao .pub --export ;
Option 2: Strip all the signatures, so Thunderbird gets a smaller file to chew on. This uses pgp-clean from signing-party.
gpg --with-colons --list-public-keys grep ^pub cut -d : -f 5 xargs pgp-clean -s >>
Option 1 will retain the signatures on individual keys, Option 2 will not.

Daniel Lange: Getting gpg to import signatures again

The GnuPG (gpg) ecosystem has been played with a bit in 2019 by adding fake signatures en masse to well known keys. The main result is that the SKS Keyserver network based on the OCaml software of the same name is basically history. A few other keyservers have come up like Hagrid (Rust) and Hockeypuck (Go) but there seems to be no clear winner yet. In case you missed it in 2019, see my take on cleaning these polluted keys. Now the changed defaults in gpg to "mitigate" this issue are trickling down to even the conservative distributions. Debian Bullseye has self-sigs-only on gpg 2.2.27 and it looks like Debian Bookworm will get gpg 2.2.40. This would add import-clean but Daniel Kahn Gillmor patched it out. He argues correctly that this new default could delete data from good locally store pubkeys. This all ends in you getting some random combination of self-sigs-only and / or import-clean depending on which Linux distribution and version you happen to use. Better be explicit. I recommend to add:
# disable new gpg defaults
keyserver-options no-self-sigs-only
keyserver-options no-import-clean
to your ~/.gnupg/gpg.conf to make sure you can manage signatures yourself and receive them from keyservers or local imports as intended. In case you care: See info gnupg --index-search=keyserver-options for the fine documentation. Of course apt install info first to be able to read info pages. 'cause who still used them in 2023? Oh, wait...

10 January 2023

Daniel Lange: Happy tenth birthday, dear Thunar bug

Thunar, the Xfce4 file manager, has a bug that it underflows the time remaining for a file copy since ten years now (bugzilla, gitlab). Happy birthday!

8 November 2022

Daniel Lange: Your software stores are a bad idea

There is significant effort involved to get your apt or dnf commands always have a consistent set of servers to talk to. That's why running separate "software stores" is a bad idea: Snap software store down That way more admins need to learn how to run high availability services for dubious business opportunities to "later" monetize services. Services that nobody cares to pay for and thus opportunities that never materialize. But every company wants to find that out again. Because if Apple could do it, why shouldn't Canonical be able to do it? $$$!1!! So, can't update Firefox on Ubuntu 22.04 right now. At least there is Snap incodent / monitoring status page So I can check back tomorrow if I can update my web browser ... Update 09.11.2022 12:15 CET The Snapcraft distribution system seems quite flaky, this is the downtime log: Log of (frequent) Snapcraft outages Bonus points for the bad client side implementation:

dl@laptop:~$ sudo snap refresh
All snaps up to date.

# ^this is a lie, just close Firefox and ...

dl@laptop:~$ sudo snap refresh
firefox 106.0.5-1 from Mozilla** refreshed

1 June 2022

Daniel Lange: Get Youtube Channel ID from username

Youtube has a really nice RSS feature that is extremely well hidden. If you postfix a Channel ID to<id goes here>
you get a really nice Atom 1.0 (~RSS) feed for your feedreader. Unfortunately the Channel ID is hard to find while you are navigating Youtube with usernames in the URL. E.g. is TED's channel, full of interesting and worth-to-watch content (and some assorted horse toppings, of course). But you have to read a lot of ugly HTML / JSON in that page to find and combine which is the related RSS feed. Jeff Keeling wrote a simple Youtube RSS Extractor that does well if you have a ../playlist?... or a .../channel/... URL but it will (currently) fail on user name channels or Youtube landing pages. So how do we get the Channel ID for a Youtube user we are interested to follow? Youtube has a great API but that is gated by API keys even for the most simple calls (that came only with v3 of the API but the previous version is depreciated since 2015)1:
dl@laptop:~$ curl ''

"code": 403,
"message": "The request is missing a valid API key.",
"errors": [

"message": "The request is missing a valid API key.",
"domain": "global",
"reason": "forbidden"


Luckily we can throw the same (example) user name DebConfVideos at curl and grep:
dl@laptop:~$ curl -s "" grep -Po '"channelId":".+?"'
So is the RSS feed for DebConfVideos. We can use individual Youtube video URLs as well. With the hack above, it'll work to find us the Chanel ID from a Youtube video URL: Working around the Youtube API restrictions to still make use of their RSS feed Now, some user pages may have multiple valid RSS feeds because they contain multiple channels. Remember the TED page from above? Well run:
dl@laptop:~$ curl -s "" grep -Po '"channelId":".+?"' cut -d \" -f 4 while read -r YTID ; do echo -n "Youtube-ID: $YTID " ; curl -s "$YTID" grep -m 1 -P -o "(?<=<title>).+(?=</title>)" ; done
This will iterate through the Channel IDs found and show you the titles. That way you can assess which one you want to add to your feedreader. screenshot of the above You probably want the last Channel ID listed above, the non-selective "TED" one. And that's the one from the example above. Update 02.06.2022: smpl wrote in and has the much better solution for the most frequent use cases:
You can also use get a feed directly with a username:<username>
The one I use most is the one for playlists (if creators remember to
use them).<playlist id>
For the common case you don't even need the channel ID that way. But it is also conveniently given in a <yt:channelId> tag (or the topmost <id> tag) within the Atom XML document. Thanks, smpl!

  1. Actually it is even more complicated as some channels, like our DebConfVideos example, will only get you an incomplete result, cf. this StackOverflow entry. I.e. the forUsername iterator may not even work and the "best practice" seems to be mucking around with the search call.

30 May 2022

Daniel Lange: Work-around for randomly dropping WiFi connections on ChromeOS

The company got me a Chromebook for times when I want to ignore email and not get dragged into code reviews but still be available on IRC and chat. Nifty devices at great price points. I really like them. Chromebook logo These things are meant to be very consumer-style end-user devices. You log in with your Google account and everything works. Until it doesn't. Just setting it up caused the first issue: I was always thrown back to a black screen and then another login-screen despite having successfully logged in initially to create the "owner" user of the Chromebook. No error message, not useful UI feedback. Just logging in again and again and again. The issue is ... not having a GMail account associated with my Google account. Duh! So add a address as the primary to your Google account and the initial setup completes. Of course you cannot delete that association again because the owner user is linked to the email and not the account. Well, you can delete it but then you cannot configure "owner" items of your Chromebook any more. Great job, Google. Not. Identity management 101 fail. Kudos to Anurag Chawake for blogging about the issue. The Google support forum thead claims this is solved now. But it didn't work for me, so this may be needing to trickle down through ChromeOS releases or be deployed on more Google infra. Or whatever. We can't tell from outside the Googleplex as - of course - "Rebecca" sheds no light on what the identified "root cause" was: Google Forum answer Once I was able to login to the new Chromebook all worked fine until I started to use ssh sessions. These always hung for 30 seconds to 10 minutes and then resumed with lots of packets lost in between and the last minute or so coming in from buffering in a burst. This was easy to see in ping as well. The connection essentially dropped dead while the WiFi icon was continuing to show full signal strength. The logs did not show anything useful. These are really hard to access on ChromeOS (JSON format and no useful UI on the Chromebook itself, Google provides a viewer on Google Apps Toolbox but that requires uploading the logs). Better than no logs at all but not really nice. The ChromeOS bug tracker and its Google corporate counterpart are also not useful at this time. For reference:
Google ... Device users randomly disconnect from Wi-Fi network
Chromium ... Device users randomly disconnect from Wi-Fi network
Google ... Constant connect and disconnect from WiFi source post-update
Chromium ... Constant connect and disconnect from WiFi source post-update Playing around with the device on the network showed that it reduced sending power beyond being able to reach the access point any more. This is why disconnecting and re-connecting the WiFi fixes the issue for a few minutes, typically. Still, there is a better way: In crosh (the ChromeOS shell available when pressing Alt+Ctrl+T) type:
wifi_power_save disable
Crosh session screenshot This unfortunately only lasts until the next reboot but it does persist over suspend cycles (aka closing the lid).

13 January 2022

Daniel Lange: Leveling the playing field for non-native speakers

Wordle game screenshort of bash, grep and pipes

Updates 24.01.2022: What I love about the community is the playful creativity that inspires a game like Wordle and that in turn inspires others to create fun tools around it: Robert Reichel has reverse engineered the Wordle application, so in case you want to play tomorrow's word today .. you can. Or have that one guess "Genius" solution experience. JP Fosterson created a Wordle helper that is very much the Python version of my grep-foo above. In case you play regularly and can use a hand. And Tom Lockwood wrote a Wordle solver also in Python. He blogged about it and ... is pondering to rewrite things in Rust:

I ve decided to explore Rust for this, and so far what was taking 1GB of RAM in Python is taking, literally 1MB in Rust!
Welcome to 2022. 01.02.2022: OMG. Wordle has been bought by the New York Times for "for a price in the low seven figures" (Source). Joey Rees-Hill put it well in The Death of Wordle:
Today s Web is dominated by platforms. The average Web user will spend most of their time on large platforms such as Instagram, Facebook, Twitter, TikTok, Google Drive/Docs, YouTube, Netflix, Spotify, Gmail, and Google Calendar, along with sites operated by large publishers such as The New York Times or The Washington Post. [..]
The Web wasn t always this way. I m not old enough to remember this, but things weren t always so centralized. Web users might run their own small website, and certainly would visit a good variety of smaller sites. With the increasing availability of internet access, the Web has become incredibly commercialized, with a handful of companies concentrating Web activity on their own properties.
Wordle was a small site that gained popularity despite not being part of a corporate platform. It was wonderful to see an independent site gain attention for being simple and fun. Wordle was refreshingly free of attention-manipulating dark patterns and pushy monetization. That s why it s a shame to see it absorbed, to inevitably become just another feature of one large media company s portfolio.
Still kudos to Josh Wardle, a Million Pounds for Wordle. Well done! It was fun while it lasted. Let's see what the next Wordle will be. This one has just been absorbed into the borg collective.

7 December 2021

Daniel Lange: Gradual improvements at the Linux Foundation

After last year's blunder with trying to hide the Adobe toolchain and using hilarious stock photos, the Linux Foundation did much better in their 2021 annual report1 published Dec. 6, 2021. Still they are using the Adobe toolchain (InDesign, Acrobat PDF) and my fellow DebianKernel2 Developer Geert was quick to point that out as the first comment to the LWN note on the publication: LWN comment from Geert I think it is important to call the Linux Foundation (LF) out again and again. Adobe is a Silver member of the LF and they can motivate them to publish their applications for Linux. And if that is not an option, there are Free alternatives like Scribus that could well use the exposure and funds of LF to help catch up to the market leading product, Adobe InDesign. Linux Foundation Annual report 2021, document properties Personally, as a photographer, I am very happy they used stock images from Unsplash to illustrate the 2021 edition over the cringeworthy Shutterstock footage from last year's report. And they gave proper credit: Thank you section for Unsplash from the Linux Foundation 2021 annual report Now for next year ... find an editor that knows how to spell photographers, please. And consider Scribus. And make Adobe publish their apps for Linux. Thank you.

  1. Update 07.12.2021 22:00 CET: I had to replace the link to the Linux Foundation 2021 annual report with an one as they updated the report to fix the typo as per the comment from Melissa Schmidt below. Stable URLs are not a thing, apparently. You can find their new report at Unless somebody points out more typos. There is a Last-Modified Header in HTTP 1.1. Wordpress, Varnish and Nginx, serving the LF website, all support that. Diff of 2021_LF_Annual_Report_120621a and2021_LF_Annual_Report_120721c
  2. 08.12.2021: Geert Uytterhoeven wrote in that he is "geert" on LWN, both are very nice Geert's but different Geert's :-)

26 March 2021

Daniel Lange: The Stallman wars

So, 2021 isn't bad enough yet, but don't despair, people are working to fix that:

Welcome to the Stallman wars Team Cancel: (repo) Team Support: (repo) Current stats are:

Team Cancel:  3028 signers from 1413 individual commit authors
Team Support: 6249 signers from 5018 individual commit authors
Git shortlog (Top 10):
rms_cancel.git (Last update: 2021-04-07 15:42:33 (UTC))
  1228  Neil McGovern
   251  Joan Touzet
    86  Elana Hashman
    71  Molly de Blanc
    36  Shauna
    19  Juke
    18  Stefano Zacchiroli
    17  Alexey Mirages
    16  Devin Halladay
    14  Nader Jafari
rms_support.git (Last update: 2021-04-12 09:25:53 (UTC))
  1678  shenlebantongying
  1564  nukeop
  1550  Ivanq
   826  Victor
   746  Job Bautista
   123  nekonee
    61  Victor Gridnevsky
    38  Patrick Spek
    25  Borys Kabakov
    17  KIM Taeyeob
(last updated 2021-04-12 09:26:15 (UTC)) Technical info:
Signers are counted from their "Signed / Individuals" sections. Commits are counted with git shortlog -s.
Team Cancel also has organizational signatures with Mozilla, Suse and X.Org being among the notable signatories. Debian is in the process of running a GR to join (or not join) that list. The 16 original signers of the Cancel petition are added in their count. Neil McGovern, Juke and shenlebantongying need .mailmap support as they have committed with different names. Further reading:

3 February 2021

Daniel Lange: Compiling and installing the Gentoo Linux kernel on emerge without genkernel (part 2)

The first install of a Gentoo kernel needs to be somewhat manual if you want to optimize the kernel for the (virtual) system it boots on. In part 1 I laid out how to improve the subsequent emerges of sys-kernel/gentoo-sources with a small drop in script to build the kernel as part of the ebuild. Since end of last year Gentoo also supports a less manual way of emerging a kernel: The following kernel blends are available: So a quick walk-through for the gentoo-kernel variant: 1. Set up the correct package USE flags We do not want an initrd and we want our own config to be re-used so:
echo "sys-kernel/gentoo-kernel -initramfs savedconfig" >> /etc/portage/package.use/gentoo-kernel
2. Preseed the saved config The current kernel config needs to be saved as the initial savedconfig so it is found and applied for our emerge below:
mkdir -p /etc/portage/savedconfig/sys-kernel
cp -n "/usr/src/linux-$(uname -r)/.config" /etc/portage/savedconfig/sys-kernel/gentoo-kernel
3. Emerge the new kernel
emerge sys-kernel/gentoo-kernel
4. Update grub and reboot Unfortunately this ebuild does not update grub, so we have to run grub-mkconfig manually. This can again be automated via a post_pkg_postinst() script. See the step 7 below. But for now, let's do it manually:
grub-mkconfig -o /boot/grub/grub.cfg
# All fine? Time to reboot the machine:
5. (Optional) Prepare for the next kernel build Run etc-update and merge the new kernel config entries into your savedconfig. Screenshot of etc-update The kernel should auto-build once new versions become available via portage. Again the etc-update can be automated if you feel that is sufficiently safe to do in your environment. See step 7 below for details. 6. (Optional) Remove the old kernel sources If you want to switch from the method based on gentoo-sources to the gentoo-kernel one, you can remove the kernel sources:
emerge -C "=sys-kernel/gentoo-sources-5*"
Be sure to update the /usr/src/linux symlink to the new kernel sources directory from gentoo-kernel, e.g.:
rm /usr/src/linux; ln -s "/usr/src/$(uname -r)" /usr/src/linux
This may be a good time for a bit more house-keeping: Clean up a bit in /usr/src/ to remove old build artefacts, /boot/ to remove old kernels and /lib/modules/ to get rid of old kernel modules. 7. (Optional) Further automate the ebuild In part 1 we automated the kernel compile, install and a bit more via a helper function for post_pkg_postinst(). We can do the similarly for what is (currently) missing from the gentoo-kernel ebuilds: Create /etc/portage/env/sys-kernel/gentoo-kernel with the following:
etc-update --automode -5 /etc/portage/savedconfig/sys-kernel
grub-mkconfig -o /boot/grub/grub.cfg
The upside of gentoo-kernel over gentoo-sources is that you can put "config override files" in /etc/kernel/config.d/. That way you theoretically profit from config improvements made by the upstream developers. See the Gentoo distribution kernel documentation for a sample snippet. I am fine with savedconfig for now but it is nice that Gentoo provides the flexibility to support both approaches.