Radu Iliescu
Radu Iliescu
You definitely need to flush metrics, or at least one metric in a signal handler. Is important to not lose critical events as seccomp failures. But one can have multiple...
@kzys is this still of interest for go-sdk?
Hi @srobertjames , >>>Is this doable now? If so, how (I wasn't able to figure it out). If not, it would be a great feature. This is not possible just...
Such a script would need to be tailored per use case, and we would let the community develop it as 3rd party tools. For example if your untrusted-linux-executable is just...
I am renaming this item and I'm adding it on the Firecracker roadmap as a research item.
Hi @luben , Beside memory hotplug, which is not implemented in Firecracker, an alternative for your use case might be memory ballooning. Please take a look here - https://github.com/firecracker-microvm/firecracker/blob/main/docs/ballooning.md Thanks!
Hi @jeromegn! You might also want to look at cpu online/offline kernel feature - https://www.kernel.org/doc/Documentation/ABI/testing/sysfs-devices-system-cpu. On the downside you will always need to start the microVM with the max number...
I think we may need to write our own tool here. Is pretty simple just have an echo server and a client that computes the roundtrip time.
Not sure if that is correct, since on a test like this you may apply statistical processing and run it for a longer time. Still reusing that code is a...
Why not use 1588/PTP? It will give much better syncronization