sync guest calls made async on host - SQLite performance

Hi,

I would like to call attention to the SQLite performance under KVM in the current Ubuntu Alpha.

http://www.phoronix.com/scan.php?page=article&item=linux_2631_kvm&num=3

SQLite's benchmark as part of the Phoronix Test Suite is typically IO limited and is affected by both disk and filesystem performance.

When comparing SQLite under the host against the guest OS, there is an order of magnitude _IMPROVEMENT_ in the measured performance of the guest.

I am expecting that the host is doing synchronous IO operations but somewhere in the stack the calls are ultimately being made asynchronous or at the very least batched for writing.

On the surface, this represents a data integrity issue and I am interested in the KVM communities thoughts on this behaviour. Is it expected? Is it acceptable? Is it safe?

Quoted 14 lines · Matthew Tippett

Hi,

I would like to call attention to the SQLite performance under KVM in the current Ubuntu Alpha.

http://www.phoronix.com/scan.php?page=article&item=linux_2631_kvm&num=3

SQLite's benchmark as part of the Phoronix Test Suite is typically IO limited and is affected by both disk and filesystem performance.

When comparing SQLite under the host against the guest OS, there is an order of magnitude _IMPROVEMENT_ in the measured performance of the guest.

Quoted 7 lines

I am expecting that the host is doing synchronous IO operations but somewhere in the stack the calls are ultimately being made asynchronous or at the very least batched for writing.

On the surface, this represents a data integrity issue and I am interested in the KVM communities thoughts on this behaviour. Is it expected? Is it acceptable? Is it safe?

qemu defaults to write-through caching, so there is no data integrity concern.

--
Do not meddle in the internals of kernels, for they are subtle and quick to panic.

Thanks Avi,

I am still trying to reconcile the your statement with the potential data risks and the numbers observed.

My read of your response is that the guest sees a consistent view - the data is commited to the virtual disk device. Does a synchronous write within the guest trigger a synchronous write of the virtual device within the host?

I don't think offering SQLite users a 10 fold increase in performance with no data integrity risks just by using KVM is a sane proposition.

Quoted 10 lines · Matthew Tippett

Thanks Avi,

I am still trying to reconcile the your statement with the potential data risks and the numbers observed.

My read of your response is that the guest sees a consistent view - the data is commited to the virtual disk device. Does a synchronous write within the guest trigger a synchronous write of the virtual device within the host?

Yes.

Quoted 3 lines

I don't think offering SQLite users a 10 fold increase in performance with no data integrity risks just by using KVM is a sane proposition.

It isn't, my guess is that the test setup is broken somehow.

--
Do not meddle in the internals of kernels, for they are subtle and quick to panic.

The test itself is a simple usage of SQLite. It is stock KVM as available in 2.6.31 on Ubuntu Karmic. So it would be the environment, not the test.

So assuming that KVM upstream works as expected that would leave either 2.6.31 having an issue, or Ubuntu having an issue.

Care to make an assertion on the KVM in 2.6.31? Leaving only Ubuntu's installation.

Can some KVM developers attempt to confirm that a 'correctly' configured KVM will not demonstrate this behaviour?
http://www.phoronix-test-suite.com/ (or is already available in newer distributions of Fedora, openSUSE and Ubuntu.

Quoted 10 lines · Matthew Tippett

The test itself is a simple usage of SQLite. It is stock KVM as available in 2.6.31 on Ubuntu Karmic. So it would be the environment, not the test.

So assuming that KVM upstream works as expected that would leave either 2.6.31 having an issue, or Ubuntu having an issue.

Care to make an assertion on the KVM in 2.6.31? Leaving only Ubuntu's installation.

kvm has nothing to do with it, it's purely qemu. For a long time qemu has defaulted to write-through cacheing. This can be overridden and maybe that's what Ubuntu or Phoronix do.

Quoted 5 lines

Can some KVM developers attempt to confirm that a 'correctly' configured KVM will not demonstrate this behaviour?
http://www.phoronix-test-suite.com/ (or is already available in newer distributions of Fedora, openSUSE and Ubuntu.

A correctly configured kvm will not demonstrate this behaviour.

--
Do not meddle in the internals of kernels, for they are subtle and quick to panic.

First up, Phoronix hasn't tuned. It's observing the delivered state by an OS vendor. I started with what I believe to be the starting point - KVM.

So the position of the KVM now is that it is either QEMU's configuration or Ubuntu's configuration. No further guidance or suggestions? Note that the prevailing response here does not see the 10 fold sqlite performance with guest vs host as a problem.

I'll move this discussion to qemu then, is there any kvm developers who are willing to maintain this position in a discussion with QEMU?

Hi,

I would like to call attention to the SQLite performance under KVM in the current Ubuntu Alpha.

http://www.phoronix.com/scan.php?page=article&item=linux_2631_kvm&num=3

SQLite's benchmark as part of the Phoronix Test Suite is typically IO limited and is affected by both disk and filesystem performance.

Quoted 10 lines · Matthew Tippett

The test itself is a simple usage of SQLite. It is stock KVM as available in 2.6.31 on Ubuntu Karmic. So it would be the environment, not the test.

So assuming that KVM upstream works as expected that would leave either 2.6.31 having an issue, or Ubuntu having an issue.

Care to make an assertion on the KVM in 2.6.31? Leaving only Ubuntu's installation.

kvm has nothing to do with it, it's purely qemu. For a long time qemu has defaulted to write-through cacheing. This can be overridden and maybe that's what Ubuntu or Phoronix do.

Quoted 5 lines

Can some KVM developers attempt to confirm that a 'correctly' configured KVM will not demonstrate this behaviour?
http://www.phoronix-test-suite.com/ (or is already available in newer distributions of Fedora, openSUSE and Ubuntu.

A correctly configured kvm will not demonstrate this behaviour.

First up, Phoronix hasn't tuned. It's observing the delivered state by an OS vendor. I started with what I believe to be the starting point - KVM.

So the position of the KVM now is that it is either QEMU's configuration or Ubuntu's configuration. No further guidance or suggestions? Note that the prevailing response here does not see the 10 fold sqlite performance with guest vs host as a problem.