On Sun, 19 Jan 2020 23:45:46 -0800
Michael Hinton <[email protected]> wrote:

> Hello,
> 
> I have found that running code in an inmate is a lot slower than
> running that same code in the root cell on my x86 machine. I am not
> sure why.

Can you elaborate on "code" and "a lot"? Maybe roughly tell us what
your testcase does and how severe your slowdown is. Synthetic
microbenchmark to measure context switching ?

As Ralf already said, anything causing "exits" can be subject to
slowdown. But that should be roughly the same for the root cell or any
non-root cell, is it truly the "same" code?

And of cause anything accessing shared resources can be slowed down by
the sharing. Caches/buses ... but i would not expect "a lot".

regards,
Henning

> Am I correct in assuming that when `jailhouse enable <root_cell>` is 
> called, everything that runs after that in the Linux root cell is
> running under the hypervisor, even when the inmate hasn’t started
> yet? Both the inmate and the Linux root cell should both be equally
> subjected to the same hypervisor performance penalty, right?
> 
> Are there any high-level differences between the root and the inmate
> that could account for this large discrepancy? I know that Turbo
> Boost is likely not happening in my inmate while it is happening in
> the root cell, but I don’t believe that can account for the huge gap
> in execution duration that I see.
> 
> 
> I'm not expecting anyone to debug this in depth for me, but I would 
> appreciate any ideas I could look into.
> 
> Thanks,
> 
> Michael
> 

-- 
You received this message because you are subscribed to the Google Groups 
"Jailhouse" 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/jailhouse-dev/20200120144629.201f3081%40md1za8fc.ad001.siemens.net.

Reply via email to