Re: [Xen-users] Performance of PVM and HVM

[Robin hp <pingh.cd@xxxxxxxxx>]

>Are you sure? setting native parameters can be tricky.

I used a simple method, just keep one 4G RAM in the Computer for the native
test, 
and  I have just one cpu with 4 cores. So, I did this test in the same
conditions.


> I didn't use phy:/ for hvm, but I used file:/ for pvm, and the results
> were
> not different.

>meaning what? you've retested with phy? if not, you should.

I mean that I used file:/ and phy:/ for pvm, not used phy:/ for hvm. 
But I will try that later and post the result.

>dd is almost useless for benchmarking purposes.

>Personally I'd say use real workloads. For example, in the past I was
>choosing the best virtualization platform to run mysql. So I used
>sysbench on vmware, kvm, and xen. The end result was almost the same,
>so I ended up choosing vmware for that project because it was easier
>to maintain.

You are right, I tried to use fio for the r/w testing, but still have no
result.

>It depends.

>64bit pv have some performance penalty for some syscalls which does
>not exist in 32bit pv or hvm (search the list archive for details). In
>some cases this doesn't matter, and other pv-guest benefits more than
>compensate for this penalty.

I heard about this before, and I installed a 32-bit pvm, but nothing was
changed.
Maybe it's because my host was 64-bit system.

>There's an ongoing effort to create hybrid guest to address this
>issue, but it's not ready yet.

>Again, at this point I suggest you:
>- use phy
>- use a benchmark similar to the workload you're going to use

>... and if you have time, try kvm as well :)

I have tested kvm, and the score of unixbenck of kvm was so close to that of
pvm.


-- 





--
View this message in context: 
http://xen.1045712.n5.nabble.com/Performance-of-PVM-and-HVM-tp5711309p5711338.html
Sent from the Xen - User mailing list archive at Nabble.com.

_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxx
http://lists.xen.org/xen-users