Libtraceevent 1.7.2 is released with minor updates.

https://git.kernel.org/pub/scm/libs/libtrace/libtraceevent.git/tag/?h=libtraceevent-1.7.2

Send an email to press@twitter.com and you’ll get a nice autoreply 💩

Random first trial post: today, March 14th, is the 29th anniversary of the Linux 1.0 announcement.

Of course, there are other arguably more important dates in Linux history, but this is one of them.

There’s no hell like trying to make a project build with autoconf - automake written in 2009 work with today’s autoconf - automake.

Today is the anniversary of the public announcement of streamline_config.pl. What eventually became “make localmodconfig” https://lore.kernel.org/lkml/Pine.LNX.4.58.0503110338230.19798@localhost.localdomain/

And today’s hack is: https://lore.kernel.org/all/20230306122529.44e8d566@gandalf.local.home/

PowerTop has had a copy of libtraceevent for over 10 years, with the assumption it would use the external library when ready. That library has been ready for a few years now, but I finally got around to porting PowerTop to it. https://github.com/fenrus75/powertop/pull/122

Running my tests costs me a bit in my electricity bill!

Anyone else hate upgrades that mess with your fonts?? For some reason, every so often, after an upgrade. My default fonts are all messed up. WTF!

Now I know why they say there's a "FOSDEM Flu" 🤧 At least I didn't get the "FOSDEM Covid"!

I'm excited about my first time at FOSDEM. Unfortunately, all the talks I'm interested in are on Sunday. At least that means I can use tomorrow to figure out my way around the conference.

Copied my ktest.pl config from my server (58 cores / 256G of RAM) to my laptop. I guess running make -j120 isn’t good for the poor thing 😢

Today marks the day I officially converted my internal C and bin directories over to git from subversion. I have a set of personal tools I use (or just to test how things work) that I’ve kept in subversion.

Why?

Because the central repository was perfect for it. I did not care about distributed environment. I would always commit back to the central authority.

Why did I change?

Well, I do modify the code from different machines here and there, and I finally hit a merge conflict that is pretty much impossible to solve with subversion. Which caused me a couple of hours to get it back to a working state as subversion makes it very difficult to resolve nasty conflicts.

Thank God for git svn as I needed to maintain the history as well.

Oh well, Goodbye subversion. It was fun while it lasted.

For my day off, I decided to implement passing a stack trace from start event to end event (to show the backtrace of the longest blocked areas).

I usually add this to my .bashrc file to all my work machines.

alias reboot='echo "Wrong window idiot!"'
alias halt='echo "Wrong window idiot!"'
alias shutdown='echo "Wrong window idiot!"'

But I just learned, that I never added it to my Google workstation 😛

The blog on the responses from the Linux Plumbers survey is now published. https://lpc.events/blog/2022/index.php/2023/01/06/lpc-2022-attendee-survey-summary/

Happy New Year to the new force of social media!

Continuing my Rust Rants :-)

It’s unfortunate that move is a keyword. As I write my little programs, I found that that’s a common function name I use. Now I need to come up with something else. adjust ?

There’s gotta be a better way…

use std::env;
use std::path::Path;

fn usage(arg: &String) {
    let path = Path::new(arg);

    println!("usage: {} a b", path.file_name().unwrap().to_str().unwrap());
}

fn main() {
    let args = env::args();

    if args.len() < 3 {
        usage(&args.collect::<Vec<String>>()[0]);
    }
}

Using the holiday break to learn Rust, I'm getting frustrated with Cargo. I mean, with C, I have a bunch of small programs that I use. But it seems that with Rust, to do the same, I have to make each one into a separate project, which I find overkill. Is there a easy way to make 100 little programs without making a 100 little projects???