Pod traffic not taking advantage of interfaces with multiple tx queues

[Tim Gardner]

SRU Justification

[Impact]

https://patchwork.kernel.org/project/netdevbpf/patch<email address hidden>/

Performance is impacted when multiple TX queues are enabled.

[Fix]
commit 710ad98c363a66a0cd8526465426c5c5f8377ee0 ("veth: Do not record rx queue hint in veth_xmit")

This patch is already scheduled for release in these stable kernel versions:

linux-5.10.y.txt:5f76445a31b79be85b337cce5f35affb77cc18fc veth: Do not record rx queue hint in veth_xmit
linux-5.15.y.txt:78a19e506bdcd1bfff73523ec99190794e0af39c veth: Do not record rx queue hint in veth_xmit
linux-5.16.y.txt:bf8963ea39ecfd1bddc657a81f1d657b43c950e8 veth: Do not record rx queue hint in veth_xmit
linux-5.4.y.txt:d08a0a88db88462bdf1b2df33ded23269b832afc veth: Do not record rx queue hint in veth_xmit

[Test Plan]

Upstream tested

[Where things could go wrong]

Transmit performance could be impacted in other ways.

[Other Info]

SF: #00326544

[Ubuntu Kernel Bot (ubuntu-kernel-bot)]

This bug is awaiting verification that the linux/5.13.0-29.32 kernel in -proposed solves the problem. Please test the kernel and update this bug with the results. If the problem is solved, change the tag 'verification-needed-impish' to 'verification-done-impish'. If the problem still exists, change the tag 'verification-needed-impish' to 'verification-failed-impish'.

If verification is not done by 5 working days from today, this fix will be dropped from the source code, and this bug will be closed.

See https://wiki.ubuntu.com/Testing/EnableProposed for documentation how to enable and use -proposed. Thank you!

[Ubuntu Kernel Bot (ubuntu-kernel-bot)]

This bug is awaiting verification that the linux-hwe-5.11/5.11.0-60.60 kernel in -proposed solves the problem. Please test the kernel and update this bug with the results. If the problem is solved, change the tag 'verification-needed-focal' to 'verification-done-focal'. If the problem still exists, change the tag 'verification-needed-focal' to 'verification-failed-focal'.

If verification is not done by 5 working days from today, this fix will be dropped from the source code, and this bug will be closed.

See https://wiki.ubuntu.com/Testing/EnableProposed for documentation how to enable and use -proposed. Thank you!

[Łukasz Zemczak (sil2100)]

The verification of the Stable Release Update for linux-hwe-5.13 has completed successfully and the package is now being released to -updates. Subsequently, the Ubuntu Stable Release Updates Team is being unsubscribed and will not receive messages about this bug report. In the event that you encounter a regression using the package from -updates please report a new bug using ubuntu-bug and tag the bug report regression-update so we can easily find any regressions.

[Launchpad Janitor (janitor)]

This bug was fixed in the package linux - 5.13.0-30.33

---------------
linux (5.13.0-30.33) impish; urgency=medium

  * impish/linux: 5.13.0-30.33 -proposed tracker (LP: #1960055)

  * systemd/248.3-1ubuntu8.2 ADT test failure with linux/5.13.0-29.32
    (LP: #1960034)
    - Revert "block: avoid to quiesce queue in elevator_init_mq"
    - Revert "blk-mq: cancel blk-mq dispatch work in both blk_cleanup_queue and
      disk_release()"

linux (5.13.0-29.32) impish; urgency=medium

  * impish/linux: 5.13.0-29.32 -proposed tracker (LP: #1959238)

  * Packaging resync (LP: #1786013)
    - debian/dkms-versions -- update from kernel-versions (main/2022.01.31)

  * CVE-2022-22942
    - SAUCE: drm/vmwgfx: Fix stale file descriptors on failed usercopy

  * CVE-2022-0330
    - drm/i915: Flush TLBs before releasing backing store

  * Impish update: upstream stable patchset 2022-01-05 (LP: #1956508)
    - ACPI: Get acpi_device's parent from the parent field
    - USB: serial: option: add Telit LE910S1 0x9200 composition
    - USB: serial: option: add Fibocom FM101-GL variants
    - usb: dwc2: gadget: Fix ISOC flow for elapsed frames
    - usb: dwc2: hcd_queue: Fix use of floating point literal
    - usb: dwc3: gadget: Ignore NoStream after End Transfer
    - usb: dwc3: gadget: Check for L1/L2/U3 for Start Transfer
    - usb: dwc3: gadget: Fix null pointer exception
    - net: nexthop: fix null pointer dereference when IPv6 is not enabled
    - usb: chipidea: ci_hdrc_imx: fix potential error pointer dereference in probe
    - usb: typec: fusb302: Fix masking of comparator and bc_lvl interrupts
    - usb: hub: Fix usb enumeration issue due to address0 race
    - usb: hub: Fix locking issues with address0_mutex
    - binder: fix test regression due to sender_euid change
    - ALSA: ctxfi: Fix out-of-range access
    - ALSA: hda/realtek: Add quirk for ASRock NUC Box 1100
    - ALSA: hda/realtek: Fix LED on HP ProBook 435 G7
    - media: cec: copy sequence field for the reply
    - Revert "parisc: Fix backtrace to always include init funtion names"
    - HID: wacom: Use "Confidence" flag to prevent reporting invalid contacts
    - staging/fbtft: Fix backlight
    - staging: greybus: Add missing rwsem around snd_ctl_remove() calls
    - staging: rtl8192e: Fix use after free in _rtl92e_pci_disconnect()
    - fuse: release pipe buf after last use
    - xen: don't continue xenstore initialization in case of errors
    - xen: detect uninitialized xenbus in xenbus_init
    - KVM: PPC: Book3S HV: Prevent POWER7/8 TLB flush flushing SLB
    - tracing/uprobe: Fix uprobe_perf_open probes iteration
    - tracing: Fix pid filtering when triggers are attached
    - mmc: sdhci-esdhc-imx: disable CMDQ support
    - mmc: sdhci: Fix ADMA for PAGE_SIZE >= 64KiB
    - mdio: aspeed: Fix "Link is Down" issue
    - powerpc/32: Fix hardlockup on vmap stack overflow
    - PCI: aardvark: Deduplicate code in advk_pcie_rd_conf()
    - PCI: aardvark: Implement re-issuing config requests on CRS response
    - PCI: aardvark: Simplify initialization of rootcap on virtual bridge
    - PCI: aardvark: Fix link training
    - proc/vmcore: fix clearing user buffer by properly using clear_user()
...