Multikernel Linux Tree Released: Runs Multiple Kernels On Bare Metal Without a Hypervisor (itsfoss.com) 37
"Multikernel Technologies has put out mklinux v7.0-mk2, the first public release of the multikernel Linux tree it's been building since last year," reports the blog It's FOSS:
The basic premise of the project is that one physical server can run several independent Linux kernels side by side, each with its own dedicated CPUs and memory. So, the same box could run a database on one kernel and a GPU training job on another without either kernel touching the other's resources... One kernel runs as the host, controlling the machine's CPUs, memory, and PCI devices. When it spins up a new kernel instance, that instance gets its own dedicated slice of hardware and boots straight onto it using Linux's kexec mechanism, running natively rather than under a hypervisor.
The host tracks all of this through device tree overlays under /sys/fs/multikernel/, and it can shift hardware between running instances while everything stays up.
That's a different setup from both VMs and containers. A VM still puts a hypervisor and a host kernel between the app and the hardware. A container skips the hypervisor, but every tenant on the machine shares one kernel... This release only supports x86_64 hardware, though Multikernel Technologies says the architecture-specific code is already modular enough for other ports to follow later.
The article notes they're selling multiple products based on the kernel tree, including one for running AI agents in their own kernel with direct GPU access and one that promises to patch a running kernel without taking the system down.
The host tracks all of this through device tree overlays under /sys/fs/multikernel/, and it can shift hardware between running instances while everything stays up.
That's a different setup from both VMs and containers. A VM still puts a hypervisor and a host kernel between the app and the hardware. A container skips the hypervisor, but every tenant on the machine shares one kernel... This release only supports x86_64 hardware, though Multikernel Technologies says the architecture-specific code is already modular enough for other ports to follow later.
The article notes they're selling multiple products based on the kernel tree, including one for running AI agents in their own kernel with direct GPU access and one that promises to patch a running kernel without taking the system down.
what else can it do? (Score:2)
Can it power off CPUs and other devices allowing for hot-swap? I can imagine the next generation of multi-cpu/conntroller motherboards with power LEDs for each socket.
Re:what else can it do? (Score:5, Interesting)
I believe Linux already supports CPU hot-swap if the hardware supports it. It was needed by IBM so their POWER mainframes could literally do just that.
Unfortunately I don't think there's many x86-based servers that support CPU hot swapping.
Re: (Score:2)
Re:what else can it do? (Score:5, Informative)
Can it power off CPUs and other devices allowing for hot-swap?
Linux introduced CPU Hotplugging in 2.6.16 almost exactly 20 years ago.
Re: (Score:2)
Can you save me the time googling this and point me to a hardware manufacturer who sold systems that supported this?
Re: (Score:1)
Re: (Score:3)
I do recall HP (before the trailing 'e') having some... specifically their top end Itanium systems had hot swap CPU in the hardware. It was developed to compete with the big iron mainframes so that sort of functionality was needed. I remember standing up one of these systems, and because I never actually used that functionality I don't know how it worked or how well it worked but it was definitely a feature I remember the HP touting when we purchased them.
For all its warts, if you ran native code on them th
Re: (Score:2)
Where Itanic sunk is because Intel were heavily pushing the x86 compatibility of the processor
That and the price per op, which was alone enough to make it a flop.
Re: (Score:2)
Mostly big iron like mainframes.
Re: (Score:1)
Re: (Score:2)
Re: (Score:3)
Various SPARC-based Sun Enterprise Server products supported hot-swapping CPUs under Solaris. I think some of the POWER-based IBM System p servers support hot-swapping CPUs under Linux. Maybe some of the Unisys ES7000 support it?
3 separate machines in one box, (Score:2)
Most modern servers have more than one core.
Not that hard to treat each core as a separate machine, all using another core as something like an internal router to access memory, graphic cards, keyboards, etc.
The hardware changes would be minimal. Basically take 4 motherboards, put it one metal box and put most of the real memory, etc. on the 'host' motherboard that allocates between the other 3.
There would be real speed penalties to doing this, but totally possible just using hardware. Duplicating it with
Re: 3 separate machines in one box, (Score:2)
Doing it in software means you can move CPUs from one machine to another based on the time of day. Your CI infrastructure can lose some resources from its UI at night and make another server for nightly builds when most of your users are away, without either having a VM layer in between or needing the builds to happen on a kernel configured with the features needed by the UI.
Re: (Score:2)
"Doing it in software means you can move CPUs from one machine to another based on the time of day."
Which you could do with a single OS much more effectively.
"Your CI infrastructure can lose some resources from its UI at night and make another server for nightly builds when most of your users are away, without either having a VM layer in between or needing the builds to happen on a kernel configured with the features needed by the UI."
But not without restarting and with the limitation that different "system
Sounds like an LPAR but for a PC (Score:5, Interesting)
IBM mainframes have LPARS - logical partitions - to divide up the hardware. This sounds like almost the same thing, but for PCs.
https://www.ibm.com/docs/en/zos-basic-skills?topic=design-mainframe-hardware-logical-partitions-lpars
Re: Sounds like an LPAR but for a PC (Score:3)
mklinux: name already taken (Score:5, Informative)
As someone who worked a bit on mklinux (after Apple abandoned it), I wonder if they googled before choosing a name. The mklinux.org website is actually still up, amazingly.
Re:mklinux: name already taken (Score:5, Interesting)
As someone who worked a bit on mklinux (after Apple abandoned it), I wonder if they googled before choosing a name. The mklinux.org website is actually still up, amazingly.
Yes, it's being served by a Mac Mini in my TV room closet. :-D
Long time, no see.
Re:mklinux: name already taken (Score:5, Informative)
Ha! I thought you were making a joke, but - it appears you are being completely serious [mklinux.org].
Re:mklinux: name already taken (Score:4, Interesting)
Yup. I don't think I ever met him in person (not positive about that, given that this was roughly 25 to 35 years ago), but as soon as I saw the name, I immediately recognized it both from MkLinux and from NetBSD-mac68k before that. Good times.
For context, I think the last thing I did for MkLinux was hack up the timezone files for the DST changes in 2007.
Pretty sure if anybody tried to actually run it now, it would be a security nightmare. But on the flip side, nobody would still remember how to compile code for it, so maybe not. :-D
Either way, it was cool seeing a familiar name again after so many years.
Re: (Score:2)
> But on the flip side, nobody would still remember how to compile code for it, so maybe not
Oh, I think I might remember or could figure it out rather quickly. I remember developing for KDE on a Performa 6100(?) back in the day and the compile of the entire KDE suite taking 3 days or so. I still have the machine with an out of spec 72MB of RAM sitting in my attic. I haven't touched it in 2 decades, so it's probably dead or needs batteries at least. mkLinux is still on the hard drive since I never wiped
Re: mklinux: name already taken (Score:2)
Yup, name taken find a new name!
Pretty sure I could remember how to build/deploy it for my 6100 if I really tried, but it has been about 20 years since I last built it.
Re: (Score:3)
The next most rational alternative, MuKLinux, could be problematic for Greek reasons as well. :-D (mu = micro)
[*waves at another old friend*]
Re: (Score:2)
Wow, it has been over 20 years! Darn, now I feel really old. Saw the post and said "Wait, mklinux? that doesn't mean multikernel linux, it means microkernel linux. All part of the environment that gave birth to Mac OSX sitting on the mach kernel.
I guess it is a sign of my age that I find it amazing that someone working on kernel stuff would be too young to know about another kernel project, especially one that doesn't feel that long ago to me.
Have people forgotten the microkernel vs. monolithic kernel
Re: mklinux: name already taken (Score:3)
Re: (Score:3)
A 100% original original OG! That's awesome!!
Re: (Score:2)
My guess is they knew of the name's history. There's a case to be made that it's an homage, but IMHO a stronger case to be made that the confusion outweighs any merits of this name. "Multikernel Linux" would've been better.
Re: (Score:2)
I agree that the name is not worth the confusion.
My first thought on seeing the name was, "Someone is still working on mkLinux?" I think it would be possible to run multiple kernels on the Mach microkernel, but kernel development was never my thing.
Re: (Score:3)
Why yes, I am rather old. Why do you ask?
Reminds me of the old Sun Fire & E10k systems (Score:2)
Without the 300 baud jtag interface.
Interesting, but... (Score:2)
This is interesting, but I'm trying to figure out what the real-world applications of this might be. What the purpose or point of this?
As a sysadmin... (Score:2)
...and a former Mainframe op, this means very little to me unless / until it has a decent TUI and/or GUI interface to report on, configure, and manage things.
Give me an ISO to boot and an interface as described above, and I'll dedicate some time to testing it.
How is it different? (Score:2)