Hi kata-folks One of the topics in today's agent was QEMU 4 and the work that we are doing to support it in Kata Containers. I ran the boot time and memory footprint metrics in my workstation to compare QEMU 4 vs QEMU-lite (2.11). Here the results. Feel free to comment and raise your concerns about QEMU 4. [cid:0167e7dca7f28c0cac1fcbc4b25a97cfeec1de1a.camel@intel.com] [cid:78029be0c3d799ae75a605b679187f4b84a38ae2.camel@intel.com]
* Montes, Julio (julio.montes@intel.com) wrote:
Hi kata-folks
One of the topics in today's agent was QEMU 4 and the work that we are doing to support it in Kata Containers. I ran the boot time and memory footprint metrics in my workstation to compare QEMU 4 vs QEMU-lite (2.11). Here the results.
Feel free to comment and raise your concerns about QEMU 4.
So that looks pretty nice for QEMU 4; at least as fast and in the noise on the memory usage? Do you have any notes on how you configured and built the qemu 4 ? Dave
[cid:0167e7dca7f28c0cac1fcbc4b25a97cfeec1de1a.camel@intel.com]
[cid:78029be0c3d799ae75a605b679187f4b84a38ae2.camel@intel.com]
_______________________________________________ kata-dev mailing list kata-dev@lists.katacontainers.io http://lists.katacontainers.io/cgi-bin/mailman/listinfo/kata-dev
-- Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
On Tue, 2019-05-28 at 18:19 +0100, Dr. David Alan Gilbert wrote:
* Montes, Julio (julio.montes@intel.com) wrote:
Hi kata-folks
One of the topics in today's agent was QEMU 4 and the work that we are doing to support it in Kata Containers. I ran the boot time and memory footprint metrics in my workstation to compare QEMU 4 vs QEMU-lite (2.11). Here the results.
Feel free to comment and raise your concerns about QEMU 4.
So that looks pretty nice for QEMU 4; at least as fast and in the noise on the memory usage?
yeah - IMO QEMU 4 has a good performance and new features, it's a good hypervisor for Kata Containers.
Do you have any notes on how you configured and built the qemu 4 ?
Yes, we use this script [1] to build all QEMUs [1] - https://github.com/kata-containers/packaging/blob/master/scripts/configure-h...
Dave
[cid:0167e7dca7f28c0cac1fcbc4b25a97cfeec1de1a.camel@intel.com]
[cid:78029be0c3d799ae75a605b679187f4b84a38ae2.camel@intel.com]
_______________________________________________ kata-dev mailing list kata-dev@lists.katacontainers.io http://lists.katacontainers.io/cgi-bin/mailman/listinfo/kata-dev
-- Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
* Montes, Julio (julio.montes@intel.com) wrote:
On Tue, 2019-05-28 at 18:19 +0100, Dr. David Alan Gilbert wrote:
* Montes, Julio (julio.montes@intel.com) wrote:
Hi kata-folks
One of the topics in today's agent was QEMU 4 and the work that we are doing to support it in Kata Containers. I ran the boot time and memory footprint metrics in my workstation to compare QEMU 4 vs QEMU-lite (2.11). Here the results.
Feel free to comment and raise your concerns about QEMU 4.
So that looks pretty nice for QEMU 4; at least as fast and in the noise on the memory usage?
yeah - IMO QEMU 4 has a good performance and new features, it's a good hypervisor for Kata Containers.
Great! Please keep running these tests to make sure we don't regress in future versions (especially on our soft-freezes etc so we can spot them before the next release.
Do you have any notes on how you configured and built the qemu 4 ?
Yes, we use this script [1] to build all QEMUs
[1] - https://github.com/kata-containers/packaging/blob/master/scripts/configure-h...
Thanks! Dave
Dave
[cid:0167e7dca7f28c0cac1fcbc4b25a97cfeec1de1a.camel@intel.com]
[cid:78029be0c3d799ae75a605b679187f4b84a38ae2.camel@intel.com]
_______________________________________________ kata-dev mailing list kata-dev@lists.katacontainers.io http://lists.katacontainers.io/cgi-bin/mailman/listinfo/kata-dev
-- Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK -- Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
-----Original Message----- From: Dr. David Alan Gilbert [mailto:dgilbert@redhat.com] Sent: Tuesday, May 28, 2019 7:40 PM To: Montes, Julio <julio.montes@intel.com>; pbonzini@redhat.com Cc: kata-dev@lists.katacontainers.io Subject: Re: [kata-dev] QEMU 4 and QEMU-lite
* Montes, Julio (julio.montes@intel.com) wrote:
On Tue, 2019-05-28 at 18:19 +0100, Dr. David Alan Gilbert wrote:
* Montes, Julio (julio.montes@intel.com) wrote:
Hi kata-folks
One of the topics in today's agent was QEMU 4 and the work that we are doing to support it in Kata Containers. I ran the boot time and memory footprint metrics in my workstation to compare QEMU 4 vs QEMU-lite (2.11). Here the results.
Feel free to comment and raise your concerns about QEMU 4.
So that looks pretty nice for QEMU 4; at least as fast and in the noise on the memory usage?
yeah - IMO QEMU 4 has a good performance and new features, it's a good hypervisor for Kata Containers.
Great! Please keep running these tests to make sure we don't regress in future versions (especially on our soft-freezes etc so we can spot them before the next release.
We do have a 'metrics CI' running on Kata, that in theory would detect any major (roughly +/- 5%) shifts - but, that would only happen when Kata updates the version of Qemu it is tracking... And, yes, we will almost definitely have to tweak that CI to account for the new numbers when we land The qemu4 PR ... Graham --------------------------------------------------------------------- Intel Corporation (UK) Limited Registered No. 1134945 (England) Registered Office: Pipers Way, Swindon SN3 1RJ VAT No: 860 2173 47 This e-mail and any attachments may contain confidential material for the sole use of the intended recipient(s). Any review or distribution by others is strictly prohibited. If you are not the intended recipient, please contact the sender and delete all copies.
On 5/28/2019 11:54 AM, Whaley, Graham wrote:
-----Original Message----- From: Dr. David Alan Gilbert [mailto:dgilbert@redhat.com] Sent: Tuesday, May 28, 2019 7:40 PM To: Montes, Julio <julio.montes@intel.com>; pbonzini@redhat.com Cc: kata-dev@lists.katacontainers.io Subject: Re: [kata-dev] QEMU 4 and QEMU-lite
On Tue, 2019-05-28 at 18:19 +0100, Dr. David Alan Gilbert wrote:
Hi kata-folks
One of the topics in today's agent was QEMU 4 and the work that we are doing to support it in Kata Containers. I ran the boot time and memory footprint metrics in my workstation to compare QEMU 4 vs QEMU-lite (2.11). Here the results.
Feel free to comment and raise your concerns about QEMU 4. So that looks pretty nice for QEMU 4; at least as fast and in
* Montes, Julio (julio.montes@intel.com) wrote: the noise on the memory usage? yeah - IMO QEMU 4 has a good performance and new features, it's a good hypervisor for Kata Containers. Great! Please keep running these tests to make sure we don't regress in future versions (especially on our soft-freezes etc so we can spot
* Montes, Julio (julio.montes@intel.com) wrote: them before the next release. We do have a 'metrics CI' running on Kata, that in theory would detect any major (roughly +/- 5%) shifts - but, that would only happen when Kata updates the version of Qemu it is tracking... And, yes, we will almost definitely have to tweak that CI to account for the new numbers when we land The qemu4 PR ...
Just curious about whether you are providing the uncompressed kernel image in these Qemu 4 tests or not. Qemu 4.0 supports booting the uncompressed kernel binary in order to reduce boot time (if the kernel is version 4.21 or higher with CONFIG_PVH). Thanks, -Maran
Graham --------------------------------------------------------------------- Intel Corporation (UK) Limited Registered No. 1134945 (England) Registered Office: Pipers Way, Swindon SN3 1RJ VAT No: 860 2173 47
This e-mail and any attachments may contain confidential material for the sole use of the intended recipient(s). Any review or distribution by others is strictly prohibited. If you are not the intended recipient, please contact the sender and delete all copies. _______________________________________________ kata-dev mailing list kata-dev@lists.katacontainers.io http://lists.katacontainers.io/cgi-bin/mailman/listinfo/kata-dev
On Tue, 2019-05-28 at 12:10 -0700, Maran Wilson wrote:
On 5/28/2019 11:54 AM, Whaley, Graham wrote:
-----Original Message----- From: Dr. David Alan Gilbert [mailto:dgilbert@redhat.com] Sent: Tuesday, May 28, 2019 7:40 PM To: Montes, Julio <julio.montes@intel.com>; pbonzini@redhat.com Cc: kata-dev@lists.katacontainers.io Subject: Re: [kata-dev] QEMU 4 and QEMU-lite
* Montes, Julio (julio.montes@intel.com) wrote:
On Tue, 2019-05-28 at 18:19 +0100, Dr. David Alan Gilbert wrote:
* Montes, Julio (julio.montes@intel.com) wrote:
Hi kata-folks
One of the topics in today's agent was QEMU 4 and the work that we are doing to support it in Kata Containers. I ran the boot time and memory footprint metrics in my workstation to compare QEMU 4 vs QEMU-lite (2.11). Here the results.
Feel free to comment and raise your concerns about QEMU 4.
So that looks pretty nice for QEMU 4; at least as fast and in the noise on the memory usage?
yeah - IMO QEMU 4 has a good performance and new features, it's a good hypervisor for Kata Containers.
Great! Please keep running these tests to make sure we don't regress in future versions (especially on our soft-freezes etc so we can spot them before the next release.
We do have a 'metrics CI' running on Kata, that in theory would detect any major (roughly +/- 5%) shifts - but, that would only happen when Kata updates the version of Qemu it is tracking... And, yes, we will almost definitely have to tweak that CI to account for the new numbers when we land The qemu4 PR ...
Just curious about whether you are providing the uncompressed kernel image in these Qemu 4 tests or not. Qemu 4.0 supports booting the uncompressed kernel binary in order to reduce boot time (if the kernel
\o/ interesting I will try, thanks.
is version 4.21 or higher with CONFIG_PVH).
nop, I ran those test with 4.19.x
Thanks, -Maran
Graham ----------------------------------------------------------------- ---- Intel Corporation (UK) Limited Registered No. 1134945 (England) Registered Office: Pipers Way, Swindon SN3 1RJ VAT No: 860 2173 47
This e-mail and any attachments may contain confidential material for the sole use of the intended recipient(s). Any review or distribution by others is strictly prohibited. If you are not the intended recipient, please contact the sender and delete all copies. _______________________________________________ kata-dev mailing list kata-dev@lists.katacontainers.io http://lists.katacontainers.io/cgi-bin/mailman/listinfo/kata-dev
_______________________________________________ kata-dev mailing list kata-dev@lists.katacontainers.io http://lists.katacontainers.io/cgi-bin/mailman/listinfo/kata-dev
On Tue, May 28, 2019 at 07:21:38PM +0000, Montes, Julio wrote:
On Tue, 2019-05-28 at 12:10 -0700, Maran Wilson wrote:
On 5/28/2019 11:54 AM, Whaley, Graham wrote:
-----Original Message----- From: Dr. David Alan Gilbert [mailto:dgilbert@redhat.com] Sent: Tuesday, May 28, 2019 7:40 PM To: Montes, Julio <julio.montes@intel.com>; pbonzini@redhat.com Cc: kata-dev@lists.katacontainers.io Subject: Re: [kata-dev] QEMU 4 and QEMU-lite
* Montes, Julio (julio.montes@intel.com) wrote:
On Tue, 2019-05-28 at 18:19 +0100, Dr. David Alan Gilbert wrote:
* Montes, Julio (julio.montes@intel.com) wrote: > Hi kata-folks > > One of the topics in today's agent was QEMU 4 and the work > that we > are doing to support it in Kata Containers. > I ran the boot time and memory footprint metrics in my > workstation > to compare QEMU 4 vs QEMU-lite (2.11). > Here the results. > > Feel free to comment and raise your concerns about QEMU 4.
So that looks pretty nice for QEMU 4; at least as fast and in the noise on the memory usage?
yeah - IMO QEMU 4 has a good performance and new features, it's a good hypervisor for Kata Containers.
Great! Please keep running these tests to make sure we don't regress in future versions (especially on our soft-freezes etc so we can spot them before the next release.
We do have a 'metrics CI' running on Kata, that in theory would detect any major (roughly +/- 5%) shifts - but, that would only happen when Kata updates the version of Qemu it is tracking... And, yes, we will almost definitely have to tweak that CI to account for the new numbers when we land The qemu4 PR ...
Just curious about whether you are providing the uncompressed kernel image in these Qemu 4 tests or not. Qemu 4.0 supports booting the uncompressed kernel binary in order to reduce boot time (if the kernel
\o/ interesting I will try, thanks.
As Maran, I'm also curious about a comparison with the new QEMU 4.0 feature to boot uncompressed kernel binary. Here you can find some useful information (I hope :)): https://gist.github.com/stefano-garzarella/7b7e17e75add20abd1c42fb496cc6504 Thanks, Stefano
Hi In order to reduce the noise, I re-ran the tests in a new no-GUI system. In the case of QEMU4+PVH the boot time is a little bit better but the memory footprint is bigger than qemu4 and qemu-lite. Here the results [cid:a6bdb98d6536701ca8d4b30ea31d0507cf6e95f3.camel@intel.com] [cid:84d6f227a6d69b926015c0b9d916c3d5f4ddd746.camel@intel.com] On Wed, 2019-05-29 at 11:07 +0200, Stefano Garzarella wrote: On Tue, May 28, 2019 at 07:21:38PM +0000, Montes, Julio wrote: On Tue, 2019-05-28 at 12:10 -0700, Maran Wilson wrote: On 5/28/2019 11:54 AM, Whaley, Graham wrote: -----Original Message----- From: Dr. David Alan Gilbert [mailto:dgilbert@redhat.com<mailto:dgilbert@redhat.com>] Sent: Tuesday, May 28, 2019 7:40 PM To: Montes, Julio <julio.montes@intel.com<mailto:julio.montes@intel.com>>; pbonzini@redhat.com<mailto:pbonzini@redhat.com> Cc: kata-dev@lists.katacontainers.io<mailto:kata-dev@lists.katacontainers.io> Subject: Re: [kata-dev] QEMU 4 and QEMU-lite * Montes, Julio (julio.montes@intel.com<mailto:julio.montes@intel.com>) wrote: On Tue, 2019-05-28 at 18:19 +0100, Dr. David Alan Gilbert wrote: * Montes, Julio (julio.montes@intel.com<mailto:julio.montes@intel.com>) wrote: Hi kata-folks One of the topics in today's agent was QEMU 4 and the work that we are doing to support it in Kata Containers. I ran the boot time and memory footprint metrics in my workstation to compare QEMU 4 vs QEMU-lite (2.11). Here the results. Feel free to comment and raise your concerns about QEMU 4. So that looks pretty nice for QEMU 4; at least as fast and in the noise on the memory usage? yeah - IMO QEMU 4 has a good performance and new features, it's a good hypervisor for Kata Containers. Great! Please keep running these tests to make sure we don't regress in future versions (especially on our soft-freezes etc so we can spot them before the next release. We do have a 'metrics CI' running on Kata, that in theory would detect any major (roughly +/- 5%) shifts - but, that would only happen when Kata updates the version of Qemu it is tracking... And, yes, we will almost definitely have to tweak that CI to account for the new numbers when we land The qemu4 PR ... Just curious about whether you are providing the uncompressed kernel image in these Qemu 4 tests or not. Qemu 4.0 supports booting the uncompressed kernel binary in order to reduce boot time (if the kernel \o/ interesting I will try, thanks. As Maran, I'm also curious about a comparison with the new QEMU 4.0 feature to boot uncompressed kernel binary. Here you can find some useful information (I hope :)): https://gist.github.com/stefano-garzarella/7b7e17e75add20abd1c42fb496cc6504 Thanks, Stefano
Thanks for sharing Julio. It seems like overall the numbers look better with QEMU 4. On Wed, May 29, 2019 at 8:36 AM Montes, Julio <julio.montes@intel.com> wrote:
Hi
In order to reduce the noise, I re-ran the tests in a new no-GUI system. In the case of QEMU4+PVH the boot time is a little bit better but the memory footprint is bigger than qemu4 and qemu-lite. Here the results
On Wed, 2019-05-29 at 11:07 +0200, Stefano Garzarella wrote:
On Tue, May 28, 2019 at 07:21:38PM +0000, Montes, Julio wrote:
On Tue, 2019-05-28 at 12:10 -0700, Maran Wilson wrote:
On 5/28/2019 11:54 AM, Whaley, Graham wrote:
-----Original Message----- From: Dr. David Alan Gilbert [mailto:dgilbert@redhat.com] Sent: Tuesday, May 28, 2019 7:40 PM To: Montes, Julio <julio.montes@intel.com>; pbonzini@redhat.com Cc: kata-dev@lists.katacontainers.io Subject: Re: [kata-dev] QEMU 4 and QEMU-lite
* Montes, Julio (julio.montes@intel.com) wrote:
On Tue, 2019-05-28 at 18:19 +0100, Dr. David Alan Gilbert wrote:
* Montes, Julio (julio.montes@intel.com) wrote:
Hi kata-folks
One of the topics in today's agent was QEMU 4 and the work that we are doing to support it in Kata Containers. I ran the boot time and memory footprint metrics in my workstation to compare QEMU 4 vs QEMU-lite (2.11). Here the results.
Feel free to comment and raise your concerns about QEMU 4.
So that looks pretty nice for QEMU 4; at least as fast and in the noise on the memory usage?
yeah - IMO QEMU 4 has a good performance and new features, it's a good hypervisor for Kata Containers.
Great! Please keep running these tests to make sure we don't regress in future versions (especially on our soft-freezes etc so we can spot them before the next release.
We do have a 'metrics CI' running on Kata, that in theory would detect any major (roughly +/- 5%) shifts - but, that would only happen when Kata updates the version of Qemu it is tracking... And, yes, we will almost definitely have to tweak that CI to account for the new numbers when we land The qemu4 PR ...
Just curious about whether you are providing the uncompressed kernel image in these Qemu 4 tests or not. Qemu 4.0 supports booting the uncompressed kernel binary in order to reduce boot time (if the kernel
\o/ interesting I will try, thanks.
As Maran, I'm also curious about a comparison with the new QEMU 4.0 feature to boot uncompressed kernel binary.
Here you can find some useful information (I hope :)): https://gist.github.com/stefano-garzarella/7b7e17e75add20abd1c42fb496cc6504
Thanks, Stefano
_______________________________________________ kata-dev mailing list kata-dev@lists.katacontainers.io http://lists.katacontainers.io/cgi-bin/mailman/listinfo/kata-dev
On Wed, May 29, 2019 at 03:12:50PM +0000, Montes, Julio wrote:
Hi
In order to reduce the noise, I re-ran the tests in a new no-GUI system. In the case of QEMU4+PVH the boot time is a little bit better but the memory footprint is bigger than qemu4 and qemu-lite. Here the results
Thanks Julio! I'll investigate if we can reduce the footprint when we load the uncompressed kernel, but I think we allocate a piece of ROM where the kernel is stored, so when it is uncompressed, the memory used is bigger. Just a question, are you using the bzImage with qemu-lite? Thanks, Stefano
On Thu, 2019-05-30 at 11:29 +0200, Stefano Garzarella wrote:
On Wed, May 29, 2019 at 03:12:50PM +0000, Montes, Julio wrote:
Hi
In order to reduce the noise, I re-ran the tests in a new no-GUI system. In the case of QEMU4+PVH the boot time is a little bit better but the memory footprint is bigger than qemu4 and qemu-lite. Here the results
Thanks Julio!
I'll investigate if we can reduce the footprint when we load the uncompressed kernel, but I think we allocate a piece of ROM where the kernel is stored, so when it is uncompressed, the memory used is bigger.
Thanks Stefano! :)
Just a question, are you using the bzImage with qemu-lite?
Yes
Thanks, Stefano
On Wed, May 29, 2019 at 12:57 AM Montes, Julio <julio.montes@intel.com> wrote:
Hi kata-folks
One of the topics in today's agent was QEMU 4 and the work that we are doing to support it in Kata Containers. I ran the boot time and memory footprint metrics in my workstation to compare QEMU 4 vs QEMU-lite (2.11). Here the results.
Feel free to comment and raise your concerns about QEMU 4.
That's pretty good results and a good evidence for kata to move ahead to qemu 4 by default. Thanks Julio! Cheers, Tao -- Into something rich and strange.
participants (7)
-
Dr. David Alan Gilbert
-
Maran Wilson
-
Montes, Julio
-
Ricardo Aravena
-
Stefano Garzarella
-
Tao Peng
-
Whaley, Graham