Thanks for your feedback and tests Murilo*2 (There seems to be a team of Murilo's on this :-) - thanks for your efforts and fast responses bringing this case forward.)
With the main changes requested I really think we need the patch in #8 to avoid issues on other HW setups that due to the new code will end up having non-aligned sections in vfio_memory-Listener. We need #8 clearly more for the avoidance of the false-positive fatal error than the log. And we then need #9 to avoid this log from flooding and instead being a tracepoint. I have respun the build in the PPA [1] which now is at 2.11+dfsg- 1ubuntu7.20~ppa2 including these patches. It would be great if you could give these another try - not that we might have introduced changes breaking to your case by that. [1]: https://launchpad.net/~paelzer/+archive/ubuntu/bug-1847948-nvmeperf-1842774 -z15name-bionic/ -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1847948 Title: Improve NVMe guest performance on Bionic QEMU Status in The Ubuntu-power-systems project: Triaged Status in linux package in Ubuntu: Fix Released Status in qemu package in Ubuntu: Fix Released Status in linux source package in Bionic: New Status in qemu source package in Bionic: Triaged Bug description: [Impact] * In the past qemu has generally not allowd MSI-X BAR mapping on VFIO. But there can be platforms (like ppc64 spapr) that can and want to do exactly that. * Backport two patches from upstream (in since qemu 2.12 / Disco). * Due to that there is a tremendous speedup, especially useful with page size bigger than 4k. This avoids that being split into chunks and makes direct MMIO access possible for the guest. [Test Case] * On ppc64 pass through an NVME device to the guest and run I/O benchmarks, see below for Details how to set that up. Note this needs the HWE kernel or another kernel fixup for [1]. [Regression Potential] * Changes: a) if the host driver allows mapping of MSI-X data the entire BAR is mapped. This is only done if the kernel reports that capability [1]. This ensures that only on kernels able to do so qemu does expose the new behavior (safe against regression in that regard) b) on ppc64 MSI-X emulation is disabled for VFIO devices this is local to just this HW and will not affect other HW. Generally the regressions that come to mind are slight changes in behavior (real HW vs the former emulation) that on some weird/old guests could cause trouble. But then it is limited to only PPC where only a small set of certified HW is really allowed. The mapping that might be added even on other platforms should not consume too much extra memory as long as it isn't used. Further since it depends on the kernel capability it isn't randomly issues on kernels where we expect it to fail. So while it is quite a change, it seems safe to me. [Other Info] * I know, one could as well call that a "feature", but it really is a performance bug fix more than anything else. Also the SRU policy allows exploitation/toleration of new HW especially for LTS releases. Therefore I think this is fine as SRU. [1]: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=a32295c612c57990d17fb0f41e7134394b2f35f6 == Comment: #0 - Murilo Opsfelder Araujo - 2019-10-11 14:16:14 == ---Problem Description--- Back-port the following patches to Bionic QEMU to improve NVMe guest performance by more than 200%: ?vfio-pci: Allow mmap of MSIX BAR? https://git.qemu.org/?p=qemu.git;a=commit;h=ae0215b2bb56a9d5321a185dde133bfdd306a4c0 ?ppc/spapr, vfio: Turn off MSIX emulation for VFIO devices? https://git.qemu.org/?p=qemu.git;a=commit;h=fcad0d2121976df4b422b4007a5eb7fcaac01134 ---uname output--- na ---Additional Hardware Info--- 0030:01:00.0 Non-Volatile memory controller: Samsung Electronics Co Ltd NVMe SSD Controller 172Xa/172Xb (rev 01) Machine Type = AC922 ---Debugger--- A debugger is not configured ---Steps to Reproduce--- Install or setup a guest image and boot it. Once guest is running, passthrough the NVMe disk to the guest using the XML: host$ cat nvme-disk.xml <hostdev mode='subsystem' type='pci' managed='no'> <driver name='vfio'/> <source> <address domain='0x0030' bus='0x01' slot='0x00' function='0x0'/> </source> </hostdev> host$ virsh attach-device <domain> nvme-disk.xml --live On the guest, run fio benchmarks: guest$ fio --direct=1 --rw=randrw --refill_buffers --norandommap --randrepeat=0 --ioengine=libaio --bs=4k --rwmixread=100 --iodepth=16 --runtime=60 --name=job1 --filename=/dev/nvme0n1 --numjobs=4 Results are similar with numjobs=4 and numjobs=64, respectively: READ: bw=385MiB/s (404MB/s), 78.0MiB/s-115MiB/s (81.8MB/s-120MB/s), io=11.3GiB (12.1GB), run=30001-30001msec READ: bw=382MiB/s (400MB/s), 2684KiB/s-12.6MiB/s (2749kB/s-13.2MB/s), io=11.2GiB (12.0GB), run=30001-30009msec With the two patches applied, performance improved significantly for numjobs=4 and numjobs=64 cases, respectively: READ: bw=1191MiB/s (1249MB/s), 285MiB/s-309MiB/s (299MB/s-324MB/s), io=34.9GiB (37.5GB), run=30001-30001msec READ: bw=4273MiB/s (4481MB/s), 49.7MiB/s-113MiB/s (52.1MB/s-119MB/s), io=125GiB (134GB), run=30001-30005msec Userspace tool common name: qemu Userspace rpm: qemu The userspace tool has the following bit modes: 64-bit Userspace tool obtained from project website: na To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu-power-systems/+bug/1847948/+subscriptions -- Mailing list: https://launchpad.net/~kernel-packages Post to : kernel-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~kernel-packages More help : https://help.launchpad.net/ListHelp
