Show HN: Smol machines – subsecond coldstart, portable virtual machines (github.com)
191 points by binsquare 6 hours ago
binsquare 6 hours ago
Hello, I'm building a replacement for docker containers with a virtual machine with the ergonomics of containers + subsecond start times.
I worked in AWS previously in the container space + with firecracker. I realized the container is an unnecessary layer that slowed things down + firecracker was a technology designed for AWS org structure + usecase.
So I ended up building a hybrid taking the best of containers with the best of firecracker.
Let me know your thoughts, thanks!
PufPufPuf 4 hours ago
Hey this is super cool. I've been researching tech like this for my AI sandboxing solution, ended up with Lima+Incus: https://github.com/JanPokorny/locki
My problem with microVMs was that they usually won't run docker / kubernetes, I work on apps that consist of whole kubernetes clusters and want the sandbox to contain all that.
Does your solution support running k3s for example?
fqiao 3 hours ago
we will evaluate. I created this issue to track this: https://github.com/smol-machines/smolvm/issues/150
Really appreciate the feedback!
lacoolj 2 hours ago
What percentage of this code was written by LLM/AI?
binsquare 2 hours ago
For myself, I'd estimate ~50%
Not useful for things it hadn't been trained on before. But now I have the core functionality in place - it's been of great help.
RALaBarge an hour ago
Hey mathematician, how much of this formula did you calculate with an abacus instead of a calculator?
anthk 10 minutes ago
topspin 4 hours ago
What is the status of supporting live migration?
That's the one feature of similar systems that always gets left out. I understand why: it's not a priority for "cloud native" workloads. The world, however, has work loads that are not cloud native, because that comes at a high cost, and it always will. So if you'd like a real value-add differentiator for your micro-VM platform (beyond what I believe you already have,) there you go.
Otherwise this looks pretty compelling.
genxy 3 hours ago
It helps if you offer a concrete use case, as in how large the heap is, what kinda of blackout period you can handle, and whether the app can handle all of it's open connections being destroyed, etc. The more an app can handle resetting some of it's own state, the easier LM is going to be to implement. If your workload jives with CRIU https://github.com/checkpoint-restore/criu you could do this already.
By what I assume is your definition, there are plenty of "non cloud native" workloads running on clouds that need live migration. Azure and GCP use LM behind the scenes to give the illusion of long uptime hosts. Guest VMs are moved around for host maintenance.
topspin 3 hours ago
fqiao 3 hours ago
Really appreciate the suggestion! By "live migration", do you mean keeping the existing files and migrate them elsewhere with the vm?
Thanks
topspin 3 hours ago
JuniperMesos an hour ago
What were the biggest challenges in terms of designing the VM to have subsecond start times? And what are the current bottlenecks for deceasing the start time even further?
binsquare an hour ago
No special programming tricks were used.
Linux was built in the 90s. Hardware improved more than a 1000x. Linux virtual machine startup times stayed relatively the same.
Turns out we kept adding junk to the linux kernel + bootup operations.
So all I did was cut and remove unnecessary parts until it still worked.
This ended up also getting boot up times to under 1s. The kernel changes are the 10 commits I made, you can verify here: https://github.com/smol-machines/libkrunfw
There's probably more fat to cut to be honest.
harshdoesdev 6 hours ago
+1. i built something similar called shuru.run because i wanted an easy way to set up microVM sandboxes to run some of my AI apps, and firecracker wasn't available for macOS (and, as you said, it is just too heavy for normal user-level workloads).
sahil-shubham 5 hours ago
Nice work on Shuru — I remember looking at it when I was researching this space. You went with a Rust wrapper on Apple’s Virtualization framework right?
I have been working on something similar but on top of firecracker, called it bhatti (https://github.com/sahil-shubham/bhatti).
I believe anyone with a spare linux box should be able to carve it into isolated programmable machines, without having to worry about provisioning them or their lifecycle.
The documentation’s still early but I have been using it for orchestrating parallel work (with deploy previews), offloading browser automation for my agents etc. An auction bought heztner server is serving me quite well :)
harshdoesdev 4 hours ago
fqiao 5 hours ago
Yes, having a light-weight solution for local devices as well is one primary goal of the design. Another one is to make it easy for hosting, self or managed
thm 5 hours ago
You could add OrbStack to the comp. table
fqiao 5 hours ago
Will do. Thanks for the suggestion!
sdrinf 5 hours ago
hi, great project! Windows support is sorely lacking, though. As someone working a lot with sandboxed LLMs right now, the options-space on windows for sandboxing is _extremely lacking_. Any plans to support it?
fqiao 5 hours ago
Hey, thanks so much! yah we will definitely add windows support later. We are exploring how to get this work with WSL and will release it asap. Stay tuned and thanks!
binsquare 5 hours ago
Yeah, it's in my mind.
WSL2 runs a linux virtual machine. Need to take some time and care to wire that up, but definitely feasible.
gavinray 4 hours ago
The feature that lets you create self-contained binaries seems like a potentially simpler way to package JVM apps than GraalVM Native.
Probably a lot of other neat usecases for this, too
smolvm pack create --image python:3.12-alpine -o ./python312
./python312 run -- python3 --version
# Python 3.12.x — isolated, no pyenv/venv/conda neededbinsquare 4 hours ago
yeah, it's analogous to Electron.
Electron ships your web app bundled with a browser.
Smol machines ship your software packaged with a linux vm. No need for dependency management or compatibility issues because it is baked in.
I think this is how Codex or Claude Code should be shipped by default, to avoid any isolation issues tbh
fqiao 2 hours ago
yah, i guess everybody share the experience of "i messed up with my dev env" right? We want this "machine" to be shippable, meaning that once it is configured correctly, it can be shared to anyone and use right away.
mrbluecoat 3 hours ago
Can .smolmachine be digitally signed and self authenticate when run? Similar to https://docs.sylabs.io/guides/main/user-guide/signNverify.ht...
chwzr an hour ago
I see the alpine and python:3.12-alpine images in your cli docs. Where does these come from?is it from a docker like registry or are these built in? Can I create my own images? Or this this purely done with the smolfile? Is there a Ubuntu image available?
Looks really nice btw. Hot resize mem/cpu would be nice. This could become a nice tech for a one-backend-per-customer infra orchestrator then.
sureglymop an hour ago
What I really like about containers is quickly being able to spin one up without having to specify resources (e.g. RAM limit). I hope this would let me do that also.
dimitry12 13 minutes ago
https://github.com/earendil-works/gondolin is another project addressing a similar use-case.
simonreiff 2 hours ago
Hey this is pretty neat! I definitely would try using this for benchmarks and other places where I need strong isolation as Docker is just too bloated and slow, but sadly I don't think I can run this natively on my Windows laptop. I hope you extend to WSL! Good luck and congrats on launch.
fqiao 2 hours ago
Hey thanks so much for the feedback. Yah try it and let us know. We have a discord if you want to join, but either github or discord feel free to report any issues you find to us.
Cheers!
cr125rider 6 hours ago
Great job with the comparison table. Immediately I was like “neat sounds like firecracker” then saw your table to see where it was similar and different. Easy!
Nice job! This looks really cool
fqiao 5 hours ago
Thanks so much
akoenig 3 hours ago
smolvm is awesome. The team is highly responsive and very experienced. They clearly know what they’re doing.
I’m currently evaluating smolvm for my project, https://withcave.ai, where I’m using Incus for isolation. The initial integration results look very promising!
indigodaddy an hour ago
This looks super awesome. Very excited for you potentially open sourcing it, as I’d like to customize/extend it a bit for certain use cases. Re: smolvm vs in use, I think even if smolvm works great for it, why not keep incus as an option for people who want to use cave on VMs that don’t have access to /dev/kvm (Eg the user can pick either incus or smolvm for their cave deployment)
fqiao 3 hours ago
Cannot thank you more for this! Lets' work together to see how we can make this easier for cave!
irickt 3 hours ago
Is there a relation to the similarly-purposed and similarly-named https://github.com/CelestoAI/SmolVM
binsquare 2 hours ago
no relation, they build a sandboxing service using firecracker.
I build a virtual machine that is an alternative to firecracker and containers.
timsuchanek 2 hours ago
This is very exciting. It enables a cross platform, language agnostic plugin system, especially for agents, while being safe in a VM.
lambdanodecore 4 hours ago
Basically any open source project nowadays run their software stack in containers often requiring docker compose. Unfortunatley Smol machines do not support Docker inside the microvms and they also do not support nested VMs for things that use Vagrant. I think this is a big drawback.
binsquare 4 hours ago
I can support docker - will ship a compatible kernel with the necessary flags in the next release.
lambdanodecore 4 hours ago
I tried something like this already, also including nested kvm. I think this will increase the boot time quiet a bit.
Also libkrun is not secure by default. From their README.md:
> The libkrun security model is primarily defined by the consideration that both the guest and the VMM pertain to the same security context. For many operations, the VMM acts as a proxy for the guest within the host. Host resources that are accessible to the VMM can potentially be accessed by the guest through it.
> While defining the security implementation of your environment, you should think about the guest and the VMM as a single entity. To prevent the guest from accessing host's resources, you need to use the host's OS security features to run the VMM inside an isolated context. On Linux, the primary mechanism to be used for this purpose is namespaces. Single-user systems may have a more relaxed security policy and just ensure the VMM runs with a particular UID/GID.
> While most virtio devices allow the guest to access resources from the host, two of them require special consideration when used: virtio-fs and virtio-vsock+TSI.
> When exposing a directory in a filesystem from the host to the guest through virtio-fs devices configured with krun_set_root and/or krun_add_virtiofs, libkrun does not provide any protection against the guest attempting to access other directories in the same filesystem, or even other filesystems in the host.
fqiao 2 hours ago
binsquare 2 hours ago
genxy 3 hours ago
So Vagrant is launching the VM locally, is that why it needs nesting?
Would you be ok with a trampoline that launched the VM as a sibling to the Vagrant VM?
ukuina 4 hours ago
Doesn't Docker's sbx do this?
binsquare 4 hours ago
sandboxing is one of the features of virtual machines.
I'm building a different virtual machine.
isterin 4 hours ago
We’re using smolmachines to create environments for our agents to execute code. It’s been great so far and the team is super responsive. The dev ergonomics are also great.
fqiao 3 hours ago
Really appreciate it! Would love to work together to make this easier to use.
0cf8612b2e1e 5 hours ago
This looks very cool. Does the VM machinery still work if I run it in a bubblewrap? Can it talk to a GPU?
Can you pipe into one? It would be cute if I could wget in machine 1 and send that result to offline machine 2 for processing.
binsquare 5 hours ago
Haven't tried with bubblewrap - but it should.
Yes! GPU passthrough is being actively worked on and will land in next major release: https://github.com/smol-machines/smolvm/pull/96
Yea just tried piping, it works:
``` smolvm machine exec --name m1 -- wget -qO- https://example.com/data.csv \ | smolvm machine exec --name m2 -i -- python3 process.py ```
bch 5 hours ago
see too[0][1] for projects of a similar* vein, incl historical account.
*yes, FreeBSD is specifically developed against Firecracker which is specifically avoided w "Smol machines", but interesting nonetheless
[0] https://github.com/NetBSDfr/smolBSD
[1] https://www.usenix.org/publications/loginonline/freebsd-fire...
binsquare 4 hours ago
that was one of my inspirations but I don't think they went far enough in innovation.
microvm space is still underserved.
bch 4 hours ago
> that was one of my inspirations
Colins FreeBSD work or Emiles NetBSD work?
binsquare an hour ago
rkagerer 2 hours ago
I see you support Linux and MacOS hosts. Any Windows support planned?
parasitid 3 hours ago
hi! congrats for your work that's really nice.
question: why do you report that qemu is 15s<x<30s? for instance with katacontainers, you can run fast microvms, and even faster with unikernels. what was your setup?
thanks a lot
nonameiguess 4 hours ago
What are you actually doing on top of libkrun? Providing really small machine images that boot quickly? If I run the smolvm run --image alpine example, what is "alpine?" Where is that image coming from? Does this have some built-in default registry of machine images it pulls from? Does it need an Internet connection that allows outbound access to wherever this registry runs? Is it one of a default set of pre-built images that comes with the software itself and is stored on my own filesystem? Where are the builds for these images? Where do these machine images end up? ~/.local/share/smolvm/?
binsquare 2 hours ago
i run a custom fork of libkrun, libkrunfw (linux kernel), etc etc: https://github.com/orgs/smol-machines/repositories
Got a lot of questions on how I spin up linux VM's so quickly
Explanation is pretty straight forward.
Linux was built in the 90s. Hardware improved more than a 1000x. Linux virtual machine startup times stayed relatively the same.
Turns out we kept adding junk to the linux kernel + bootup operations.
So all I did was cut and remove unnecessary parts until it still worked. This ended up also getting boot up times to under 1s.
Big part of it was systemd btw.
binsquare 2 hours ago
those images are pulling from the public docker registry.
fqiao 6 hours ago
Give it a try folks. Would really love to hear all the feedbacks!
Cheers!
leetrout 5 hours ago
why did you seemingly create two HN accounts?
Edit: I see this appears to be a contributor to the project as well. It was not obvious to me.
fqiao 5 hours ago
this is me: https://github.com/phooq
@binsquare is this one: https://github.com/BinSquare
fqiao 2 hours ago
No worry at all! Thanks!
chrisweekly 3 hours ago
This looks awesome. Thanks for sharing!
fqiao 2 hours ago
Thanks so much! Feel free to try it out if you have a chance, and let's us know your thoughts. Thanks!
messh 4 hours ago
https://shellbox.dev is a hosted version of something very similar
tomComb an hour ago
This sounds great, except for one thing: you can scale your compute (CPU & RAM) as needed but your storage appears to scale with it.
So, if I use a "16 vCPUs, 32GB RAM, 400GB SSD" machine for a period of intense compute, and then want to scale that down to "2 vCPUs, 4GB RAM", most of my storage disappears?
That rather ruins the potential of the advertised scalability.
harshdoesdev 6 hours ago
its a really innovative idea! very interested in the subsecond coldstart claim, how does it achieve that?
fqiao 6 hours ago
@binsquare basically brute-force trimmed down unnecessary linux kernel modules, tried to get the vm started with just bare minimum. There are more rooms for improvement for sure. We will keep trying!
deivid 5 hours ago
With this approach I managed to get to sub-10ms start (to pid1), if you can accept a few constraints there's plenty of room!
Though my version was only tested on Linux hosts
binsquare 4 hours ago
harshdoesdev 5 hours ago
nice! for most local workloads, it is actually sufficient. so, do you ship a complete disk snapshot of the machines?
fqiao 5 hours ago
cperciva 4 hours ago
See also SmolBSD -- similar idea, similar name, using NetBSD.
fqiao 3 hours ago
I came across SmolBSD before too. Cool project!