From: Alex Mastro <amastro@fb.com>
To: David Matlack <dmatlack@google.com>
Cc: Alex Williamson <alex.williamson@redhat.com>,
Alex Williamson <alex@shazbot.org>,
Jason Gunthorpe <jgg@nvidia.com>, Josh Hilke <jrhilke@google.com>,
<kvm@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
<linux-kselftest@vger.kernel.org>,
Raghavendra Rao Ananta <rananta@google.com>,
Vipin Sharma <vipinsh@google.com>
Subject: Re: [PATCH v2 00/18] vfio: selftests: Support for multi-device tests
Date: Wed, 12 Nov 2025 14:07:20 -0800 [thread overview]
Message-ID: <aRUFGHPe+EXao10B@devgpu015.cco6.facebook.com> (raw)
In-Reply-To: <20251112192232.442761-1-dmatlack@google.com>
On Wed, Nov 12, 2025 at 07:22:14PM +0000, David Matlack wrote:
> This series adds support for tests that use multiple devices, and adds
> one new test, vfio_pci_device_init_perf_test, which measures parallel
> device initialization time to demonstrate the improvement from commit
> e908f58b6beb ("vfio/pci: Separate SR-IOV VF dev_set").
The new test runs and passes for me.
Tested-by: Alex Mastro <amastro@fb.com>
$ vfio_pci_device_init_perf_test $(readlink -f /sys/class/vfio-dev/*/../.. | xargs -n1 basename)
Testing parallel initialization of 24 devices:
0000:05:00.0
0000:06:00.0
0000:27:00.0
0000:28:00.0
0000:e5:00.0
0000:e6:00.0
0000:e7:00.0
0000:e8:00.0
0000:e9:00.0
0000:ea:00.0
0000:c5:00.0
0000:c6:00.0
0000:07:00.0
0000:c7:00.0
0000:c8:00.0
0000:c9:00.0
0000:ca:00.0
0000:08:00.0
0000:09:00.0
0000:0a:00.0
0000:23:00.0
0000:24:00.0
0000:25:00.0
0000:26:00.0
TAP version 13
1..5
# Starting 5 tests from 5 test cases.
# RUN vfio_pci_device_init_perf_test.vfio_type1_iommu.init ...
Wall time: 1.440004083s
Min init time (per device): 1.236283226s
Max init time (per device): 1.440002010s
Avg init time (per device): 1.258762246s
# OK vfio_pci_device_init_perf_test.vfio_type1_iommu.init
ok 1 vfio_pci_device_init_perf_test.vfio_type1_iommu.init
# RUN vfio_pci_device_init_perf_test.vfio_type1v2_iommu.init ...
Wall time: 1.448952696s
Min init time (per device): 1.242623358s
Max init time (per device): 1.448951915s
Avg init time (per device): 1.264836317s
# OK vfio_pci_device_init_perf_test.vfio_type1v2_iommu.init
ok 2 vfio_pci_device_init_perf_test.vfio_type1v2_iommu.init
# RUN vfio_pci_device_init_perf_test.iommufd_compat_type1.init ...
Wall time: 1.446931666s
Min init time (per device): 1.242316634s
Max init time (per device): 1.446927360s
Avg init time (per device): 1.264904097s
# OK vfio_pci_device_init_perf_test.iommufd_compat_type1.init
ok 3 vfio_pci_device_init_perf_test.iommufd_compat_type1.init
# RUN vfio_pci_device_init_perf_test.iommufd_compat_type1v2.init ...
Wall time: 1.449211729s
Min init time (per device): 1.243377853s
Max init time (per device): 1.449211729s
Avg init time (per device): 1.264266785s
# OK vfio_pci_device_init_perf_test.iommufd_compat_type1v2.init
ok 4 vfio_pci_device_init_perf_test.iommufd_compat_type1v2.init
# RUN vfio_pci_device_init_perf_test.iommufd.init ...
Wall time: 1.447583702s
Min init time (per device): 1.241216318s
Max init time (per device): 1.447582350s
Avg init time (per device): 1.264159293s
# OK vfio_pci_device_init_perf_test.iommufd.init
ok 5 vfio_pci_device_init_perf_test.iommufd.init
# PASSED: 5 / 5 tests passed.
# Totals: pass:5 fail:0 xfail:0 xpass:0 skip:0 error:0
next prev parent reply other threads:[~2025-11-12 22:07 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-11-12 19:22 [PATCH v2 00/18] vfio: selftests: Support for multi-device tests David Matlack
2025-11-12 19:22 ` [PATCH v2 01/18] vfio: selftests: Move run.sh into scripts directory David Matlack
2025-11-12 19:22 ` [PATCH v2 02/18] vfio: selftests: Split run.sh into separate scripts David Matlack
2025-11-17 19:58 ` Alex Mastro
2025-11-17 21:08 ` David Matlack
2025-11-12 19:22 ` [PATCH v2 03/18] vfio: selftests: Allow passing multiple BDFs on the command line David Matlack
2025-11-12 19:22 ` [PATCH v2 04/18] vfio: selftests: Rename struct vfio_iommu_mode to iommu_mode David Matlack
2025-11-12 19:22 ` [PATCH v2 05/18] vfio: selftests: Introduce struct iommu David Matlack
2025-11-12 19:22 ` [PATCH v2 06/18] vfio: selftests: Support multiple devices in the same container/iommufd David Matlack
2025-11-12 19:22 ` [PATCH v2 07/18] vfio: selftests: Eliminate overly chatty logging David Matlack
2025-11-12 19:22 ` [PATCH v2 08/18] vfio: selftests: Prefix logs with device BDF where relevant David Matlack
2025-11-12 19:22 ` [PATCH v2 09/18] vfio: selftests: Upgrade driver logging to dev_err() David Matlack
2025-11-12 19:22 ` [PATCH v2 10/18] vfio: selftests: Rename struct vfio_dma_region to dma_region David Matlack
2025-11-12 19:22 ` [PATCH v2 11/18] vfio: selftests: Move IOMMU library code into iommu.c David Matlack
2025-11-12 19:22 ` [PATCH v2 12/18] vfio: selftests: Move IOVA allocator into iova_allocator.c David Matlack
2025-11-12 19:22 ` [PATCH v2 13/18] vfio: selftests: Stop passing device for IOMMU operations David Matlack
2025-11-12 19:22 ` [PATCH v2 14/18] vfio: selftests: Rename vfio_util.h to libvfio.h David Matlack
2025-11-12 19:22 ` [PATCH v2 15/18] vfio: selftests: Move vfio_selftests_*() helpers into libvfio.c David Matlack
2025-11-12 19:22 ` [PATCH v2 16/18] vfio: selftests: Split libvfio.h into separate header files David Matlack
2025-11-12 19:22 ` [PATCH v2 17/18] vfio: selftests: Eliminate INVALID_IOVA David Matlack
2025-11-12 19:22 ` [PATCH v2 18/18] vfio: selftests: Add vfio_pci_device_init_perf_test David Matlack
2025-11-12 22:53 ` Alex Mastro
2025-11-13 0:34 ` David Matlack
2025-11-12 22:07 ` Alex Mastro [this message]
2025-11-13 0:36 ` [PATCH v2 00/18] vfio: selftests: Support for multi-device tests David Matlack
2025-11-17 20:13 ` Alex Mastro
2025-11-19 17:03 ` David Matlack
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=aRUFGHPe+EXao10B@devgpu015.cco6.facebook.com \
--to=amastro@fb.com \
--cc=alex.williamson@redhat.com \
--cc=alex@shazbot.org \
--cc=dmatlack@google.com \
--cc=jgg@nvidia.com \
--cc=jrhilke@google.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=rananta@google.com \
--cc=vipinsh@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox