On Fri, Jul 29, 2016 at 10:58 AM, Wind Yu <[email protected]> wrote:
> Hi everyone, > I want to compare the network performance of OSV and Linux. I really want > to know how to do the performance test. I don't know if I get the meaning. > What do you mean "the meaning"? I assume that to compare the performance of OSv and Linux, you'd need to do exactly that... I.e., picks a workload (an application already ported to OSv or your own application), run it on both an OSv guest and Linux guest (make sure you run these guests with exactly the same hypervisor parameters, number of virtual CPUs, and so on), load both workloads with an identical load, and compare the performance (transactions per second, time to finish, or whatever is relevant in your benchmark). > Test 1: To run an osv which acts as a server, and run a Linux or osv which > acts as a client. Test 2: Using the qemu/kvm to run a Linux which acts as a > server,and run a Linux or osv which acts as a client. Then ,just compare > the result of Test1 and Test2. Am I right? > Sounds like you're right, but I'm not sure I understand the details of exactly what you did. > If I were right, the result is really amazing, the result of test 1 is 10 > times than that of test2. > Yes, 10-fold speed improvement is too good to be true - we've never seen anything even close to that from just switching to OSv alone. Although I'd be happy to be pleasantly surprised :-) Nadav. -- 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]. For more options, visit https://groups.google.com/d/optout.
