[Zesty] TSO doesn't work properly

[Talat Batheesh]

The TSO (TCP segmentation offload), By default it is shown to be ON, but actually aggregation doesn’t happen.
When turning it on again - aggregation is observed.
Same behavior for mlx4_en, mlx5_core, igb.

Steps to repro:
1.
root:~# uname -r
4.10.0-14-generic

2.
root:~# ethtool -i eno2
driver: igb
version: 5.4.0-k
firmware-version: 1.63, 0x800009fa
expansion-rom-version:
bus-info: 0000:06:00.0
supports-statistics: yes
supports-test: yes
supports-eeprom-access: yes
supports-register-dump: yes
supports-priv-flags: no

3.
root:~# ethtool -k eno2 | grep offload
tcp-segmentation-offload: on
udp-fragmentation-offload: off [fixed]
generic-segmentation-offload: on
generic-receive-offload: on
large-receive-offload: off [fixed]
rx-vlan-offload: on
tx-vlan-offload: on
l2-fwd-offload: off [fixed]
hw-tc-offload: off [fixed]

4.
root@:~# ethtool -K eno2 gso off

5.
root@:~# ethtool -k eno2 | grep offload
tcp-segmentation-offload: on
udp-fragmentation-offload: off [fixed]
generic-segmentation-offload: off
generic-receive-offload: on
large-receive-offload: off [fixed]
rx-vlan-offload: on
tx-vlan-offload: on
l2-fwd-offload: off [fixed]
hw-tc-offload: off [fixed]

6.
netperf -H 10.195.43.1 -l 4 -t TCP_STREAM -c -C -- -m 15000
Traffic size less or equal to 1514 is observed, despite the fact TSO is on.

7.
ethtool -K eno2 tso on

8.
netperf -H 10.195.43.1 -l 4 -t TCP_STREAM -c -C -- -m 15000
Traffic size of 64K is observed.

[Brad Figg (brad-figg)]

This bug is missing log files that will aid in diagnosing the problem. From a terminal window please run:

apport-collect 1678585

and then change the status of the bug to 'Confirmed'.

If, due to the nature of the issue you have encountered, you are unable to run this command, please add a comment stating that fact and change the bug status to 'Confirmed'.

This change has been made by an automated script, maintained by the Ubuntu Kernel Team.

[Joseph Salisbury (jsalisbury)]

Would it be possible for you to test the latest upstream kernel? Refer to https://wiki.ubuntu.com/KernelMainlineBuilds . Please test the latest v4.11 kernel[0].

If this bug is fixed in the mainline kernel, please add the following tag 'kernel-fixed-upstream'.

If the mainline kernel does not fix this bug, please add the tag: 'kernel-bug-exists-upstream'.

Once testing of the upstream kernel is complete, please mark this bug as "Confirmed".

Thanks in advance.

[0] http://kernel.ubuntu.com/~kernel-ppa/mainline/v4.11-rc5

[Joseph Salisbury (jsalisbury)]

Also, does this bug go away if you boot with a Yakkety or earlier kernel?

[Talat Batheesh (talat-b87)]

The bug is exist also in kernel that mentioned in commit#2
4.11.0-041100rc5-generic

[Joseph Salisbury (jsalisbury)]

Do you know if this is a regression? If it is, we can bisect down to the commit that introduced the bug.

[Talat Batheesh (talat-b87)]

Unfortunately, No.

[Joseph Salisbury (jsalisbury)]

Can you test the following kernels to see if the bug existed in them:

v3.2: http://kernel.ubuntu.com/~kernel-ppa/mainline/v3.2-precise/
v3.13: http://kernel.ubuntu.com/~kernel-ppa/mainline/v3.13-trusty/

[Talat Batheesh (talat-b87)]

Hi,
This test work properly in the previous releases.

Thanks,
Talat

[Joseph Salisbury (jsalisbury)]

Do you recall in which previous releases? That will help narrow down the kernel version that introduced this. Then we can perform a kernel bisect.

[Talat Batheesh (talat-b87)]

It is working with Ubuntu 16.10 .

[Joseph Salisbury (jsalisbury)]

I'd like to perform a kernel bisect to figure out which commit caused this regression. We need to identify the earliest kernel that did not exhibit the bug and the first kernel that did exhibit the bug.

Can you test the following kernels and post back?

4.8 final: http://kernel.ubuntu.com/~kernel-ppa/mainline/v4.8/
4.9-rc1: http://kernel.ubuntu.com/~kernel-ppa/mainline/v4.9-rc1/
4.9 final: http://kernel.ubuntu.com/~kernel-ppa/mainline/v4.9/
4.10-rc1: http://kernel.ubuntu.com/~kernel-ppa/mainline/v4.10-rc1/
4.10-rc4: http://kernel.ubuntu.com/~kernel-ppa/mainline/v4.10-rc4/

You don't have to test every kernel, just up until the kernel that first has this bug.

Based on your test results, we can figure out which kernel to test next.

Thanks in advance!