It depends on many factors. You should check what's the bottleneck first.
I'd start with a single core and later with 2 cores and grow it exponentially.
It either may be the IO overhead (most chances the network
virtualization) or the
cpu overhead with regard to locking. OSv has a different filesystem too.
Let's see what you have to share first.

On Mon, Feb 24, 2020 at 6:32 PM <[email protected]> wrote:
>
> Running some benchmarks on OSv. Getting some results opposite to what I was 
> expecting based off what I have learned of unikernels. When running my 
> benchmark on the host with 32 cores, it runs in about 2s. However, when 
> running the OSv build inside on KVM (run.py), I pass in 32 cores and it takes 
> 9s to complete. My assumption was it would be the same speed, possibly 
> faster. Any ideas as to why the decrease?
>
> --
> You received this message because you are subscribed to the Google Groups 
> "OSv Development" group.
> To unsubscribe from this group and stop receiving emails from it, send an 
> email to [email protected].
> To view this discussion on the web visit 
> https://groups.google.com/d/msgid/osv-dev/cac7dca2-eaa3-4c66-a8b7-705182e67942%40googlegroups.com.

-- 
You received this message because you are subscribed to the Google Groups "OSv 
Development" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
To view this discussion on the web visit 
https://groups.google.com/d/msgid/osv-dev/CAKUaUn7NHQ1mFLQwANH6%2BF1NXx%2ByOzRQ8eYjN_GD3qTF9o2adQ%40mail.gmail.com.

Reply via email to