On Wed, Jun 1, 2011 at 2:30 AM, Anthony Liguori <anthony@xxxxxxxxxxxxx> wrote: > On 05/31/2011 02:24 PM, Vivek Goyal wrote: >> >> On Tue, May 31, 2011 at 01:39:47PM -0500, Anthony Liguori wrote: >>> >>> On 05/31/2011 12:59 PM, Vivek Goyal wrote: >> >> Ok, so we seem to be talking of two requirements. >> >> - A consistent experience to guest >> - Isolation between VMs. >> >> If this qcow2 mapping/metada overhead is not significant, then we >> don't have to worry about IOPs perceived by guest. It will be more or less >> same. If it is significant then we provide more consistent experience to >> guest but then weaken the isolation between guest and might overload the >> backend storage and in turn might not get the expected IOPS for the >> guest anyway. > > That's quite a bit of hand waving considering your following argument is > that you can't be precise enough at the QEMU level. > >> So I think these two things are not independent. >> >> I agree though that advantage of qemu is that everything is a file >> and handling all the complex configuraitons becomes very easy. >> >> Having said that, to provide a consistent experience to guest, you >> also need to know where IO from guest is going and whether underlying >> storage system can support that kind of IO or not. >> >> IO limits are of not much use if if these are put in isolation without >> knowing where IO is going and how many VMs are doing IO to it. Otherwise >> there are no gurantees/estimates on minimum bandwidth for guests hence >> there is no consistent experience. > > Consistent and maximum are two very different things. > > QEMU can, very effectively, enforce a maximum I/O rate. ÂThis can then be > used to provide mostly consistent performance across different generations > of hardware, to implement service levels in a tiered offering, etc. What is the point of view, guest or host? It is not possible to enforce any rates which would make sense to guests without taking into account guest clock and execution speed. If instead you mean host rate (which would not be in sync with I/O rates seen by guest), then I'd suppose metadata accesses would also matter and then the host facilities should produce same results. On a positive side, they may only exist on newer Linux and not on other OS so introducing them to QEMU would not be so bad idea. > The level of consistency will then depend on whether you overcommit your > hardware and how you have it configured. > > Consistency is very hard because at the end of the day, you still have > shared resources. ÂEven with blkio, I presume one guest can still impact > another guest by forcing the disk to do excessive seeking or something of > that nature. > > So absolutely consistency can't be the requirement for the use-case. The > use-cases we are interested really are more about providing caps than > anything else. > > Regards, > > Anthony Liguori > >> >> Thanks >> Vivek >> > > > -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
