Alt account of @Badabinski

Just a sweaty nerd interested in software, home automation, emotional issues, and polite discourse about all of the above.

  • 0 Posts
  • 21 Comments
Joined 5 months ago
cake
Cake day: June 9th, 2024

help-circle







  • Sorry for the off-topic question, but is your username a reference to the Culture books? I think that would have been a great addition to Very Little Gravitas Indeed/Zero Gravitas/Experiencing A Significant Gravitas Shortfall. Like, I can just imagine a book where the Very Little Gravitas Indeed, Zero Gravitas, and A Gravitas Deficiency all happen to be in the same incident group chat and constantly fuck around while the other ships debate and fuss, and then one or all three of them pulls a rabbit out of the hat and fixes the problem while the other Minds aren’t looking.

    God, I miss Iain M. Banks. Also, if your username isn’t a reference then I probably sound like an absolute lunatic.


  • Very true! I was just in a rush and didn’t want to explain who he was.

    For others, Bryan Cantrill (the guy in the video) is an incredibly gifted engineer who worked for Sun Microsystems before they got bought out by Oracle. He was deeply involved in Solaris (Sun’s really cool operating system that included pioneering shit like ZFS), and was then involved with Illumos, which was a fork of Solaris. He worked for a company called Joyent that made a super fucking cool thing called SmartOS, and now he’s the CTO for a company called Oxide Computer.

    This is a hideously bad summary of his accomplishments. People who want to know more should read his Wikipedia article or watch the talk I posted. He’s a great presenter, so his talks are always pretty entertaining.

    EDIT: The shit they’re doing at Oxide is absolutely nuts. They’re making what is effectively a datacenter contained within one 48u rack, and they’re writing all their own firmware and BIOS and shit for it. It’s crazy cool.










  • The other person may have responded with a fair amount of hostility, but they’re absolutely correct. I run Kubernetes clusters hosting millions of containers across hundreds of thousands of VMs at my job, and OOMKills are just a fact of life. Apps will leak memory, and you’re powerless to fix it unless you’re willing to debug the app and fix the leak. It’s better for the container to run out of memory and trigger a cgroup-scoped OOM kill. A system-wide OOM kill will murder the things you love, shit in your hat, and lick your face like David Tennant licked Krysten Ritter.