~canonical-kernel/ubuntu/+source/linux-gke/+git/bionic:master-current

Branch merges

Related source package recipes

No recipes using this branch. (?)

Create packaging recipe

Related snap packages

Related charm recipes

f79da6d... by Sultan Alsawaf on 2019-10-02

UBUNTU: Ubuntu-gke-4.15-4.15.0-1046.49

Signed-off-by: Sultan Alsawaf <email address hidden>

8dc9e75... by Sultan Alsawaf on 2019-10-02

UBUNTU: link-to-tracker: update tracking bug

BugLink: https://bugs.launchpad.net/bugs/1846114
Properties: no-test-build
Signed-off-by: Sultan Alsawaf <email address hidden>

44d07f3... by Sultan Alsawaf on 2019-10-02

UBUNTU: Start new release

Ignore: yes
Signed-off-by: Sultan Alsawaf <email address hidden>

ef87d55... by Khaled El Mously on 2019-09-20

UBUNTU: Ubuntu-gke-4.15-4.15.0-1045.48

Signed-off-by: Khalid Elmously <email address hidden>

1776ce9... by Khaled El Mously on 2019-09-20

UBUNTU: link-to-tracker: update tracking bug

BugLink: https://bugs.launchpad.net/bugs/1844382
Properties: no-test-build
Signed-off-by: Khalid Elmously <email address hidden>

ac180c1... by Khaled El Mously on 2019-09-20

UBUNTU: Start new release

Ignore: yes
Signed-off-by: Khalid Elmously <email address hidden>

b38a59c... by Jason Wang on 2019-09-19

virtio_net: ethtool tx napi configuration

BugLink: https://bugs.launchpad.net/bugs/1834681

Implement ethtool .set_coalesce (-C) and .get_coalesce (-c) handlers.
Interrupt moderation is currently not supported, so these accept and
display the default settings of 0 usec and 1 frame.

Toggle tx napi through setting tx-frames. So as to not interfere
with possible future interrupt moderation, value 1 means tx napi while
value 0 means not.

Only allow the switching when device is down for simplicity.

Link: https://patchwork.ozlabs.org/patch/948149/
Suggested-by: Jason Wang <email address hidden>
Signed-off-by: Willem de Bruijn <email address hidden>
Signed-off-by: Jason Wang <email address hidden>
Signed-off-by: David S. Miller <email address hidden>
(cherry picked from commit 0c465be183c7c57a26446df6ea96d8676b865f92)
Signed-off-by: Khalid Elmously <email address hidden>
Acked-by: Kleber Souza <email address hidden>
Acked-by: Sultan Alsawaf <email address hidden>
Signed-off-by: Khalid Elmously <email address hidden>

22e229f... by Willem de Bruijn <email address hidden> on 2019-09-19

virtio_net: enable napi_tx by default

BugLink: https://bugs.launchpad.net/bugs/1834681

NAPI tx mode improves TCP behavior by enabling TCP small queues (TSQ).
TSQ reduces queuing ("bufferbloat") and burstiness.

Previous measurements have shown significant improvement for
TCP_STREAM style workloads. Such as those in commit 86a5df1495cc
("Merge branch 'virtio-net-tx-napi'").

There has been uncertainty about smaller possible regressions in
latency due to increased reliance on tx interrupts.

The above results did not show that, nor did I observe this when
rerunning TCP_RR on Linux 5.1 this week on a pair of guests in the
same rack. This may be subject to other settings, notably interrupt
coalescing.

In the unlikely case of regression, we have landed a credible runtime
solution. Ethtool can configure it with -C tx-frames [0|1] as of
commit 0c465be183c7 ("virtio_net: ethtool tx napi configuration").

NAPI tx mode has been the default in Google Container-Optimized OS
(COS) for over half a year, as of release M70 in October 2018,
without any negative reports.

Link: https://marc.info/?l=linux-netdev&m=149305618416472
Link: https://lwn.net/Articles/507065/
Signed-off-by: Willem de Bruijn <email address hidden>
Acked-by: Michael S. Tsirkin <email address hidden>
Acked-by: Jason Wang <email address hidden>
Signed-off-by: David S. Miller <email address hidden>
(cherry picked from commit 31c03aef9bc22a64a8324d650ca4198819ef3a33 linux-next)
Signed-off-by: Marcelo Henrique Cerri <email address hidden>
Signed-off-by: Khalid Elmously <email address hidden>
Acked-by: Kleber Souza <email address hidden>
Acked-by: Sultan Alsawaf <email address hidden>
Signed-off-by: Khalid Elmously <email address hidden>

17ffa65... by Willem de Bruijn <email address hidden> on 2019-09-19

virtio-net: per-queue RPS config

BugLink: https://bugs.launchpad.net/bugs/1834681

On multiqueue network devices, RPS maps are configured independently
for each receive queue through /sys/class/net/$DEV/queues/rx-*.

On virtio-net currently all packets use the map from rx-0, because the
real rx queue is not known at time of map lookup by get_rps_cpu.

Call skb_record_rx_queue in the driver rx path to make lookup work.

Recording the receive queue has ramifications beyond RPS, such as in
sticky load balancing decisions for sockets (skb_tx_hash) and XPS.

Reported-by: Mark Hlady <email address hidden>
Signed-off-by: Willem de Bruijn <email address hidden>
Acked-by: Jason Wang <email address hidden>
Acked-by: Michael S. Tsirkin <email address hidden>
Signed-off-by: David S. Miller <email address hidden>
(cherry picked from commit 133bbb18ab1a2f5549435c5a3126413344ddbcb8)
Signed-off-by: Marcelo Henrique Cerri <email address hidden>
Signed-off-by: Khalid Elmously <email address hidden>
Acked-by: Kleber Souza <email address hidden>
Acked-by: Sultan Alsawaf <email address hidden>
Signed-off-by: Khalid Elmously <email address hidden>

f2bb8fc... by Caleb Raitto <email address hidden> on 2019-09-19

virtio_net: Stripe queue affinities across cores.

BugLink: https://bugs.launchpad.net/bugs/1834681

Always set the affinity hint, even if #cpu != #vq.

Handle the case where #cpu > #vq (including when #cpu % #vq != 0) and
when #vq > #cpu (including when #vq % #cpu != 0).

Signed-off-by: Caleb Raitto <email address hidden>
Signed-off-by: Willem de Bruijn <email address hidden>
Acked-by: Jon Olson <email address hidden>
Signed-off-by: David S. Miller <email address hidden>
(backported from commit 2ca653d607ce59f2729173a7ea56dbfa6330ec88)
[<email address hidden>: fixed context in the included headers]
Signed-off-by: Marcelo Henrique Cerri <email address hidden>
Signed-off-by: Khalid Elmously <email address hidden>
Acked-by: Kleber Souza <email address hidden>
Acked-by: Sultan Alsawaf <email address hidden>
Signed-off-by: Khalid Elmously <email address hidden>