Severe performance regression in Infiniband or IPoIB

[Timothy Pearson]

When upgrading to the latest 4.4 test kernel from mainline development, all IPoIB links showed a severe performance regression as compared with kernel 4.2. The bandwidth of each link dropped from around 3Gbps to around 3Mbps (3 orders of magnitude worse!); reverting to the 4.2 kernel immediately fixed this problem.

The 4.3 kernel from Debian does not appear to suffer from this regression. The regression shows up on both IB ports of the Mellanox MT25208 controller. Other hardware has not been tested.

[Ubuntu Foundations Team Bug Bot (crichton)]

Thank you for taking the time to report this bug and helping to make Ubuntu better. It seems that your bug report is not filed about a specific source package though, rather it is just filed against Ubuntu in general. It is important that bug reports be filed about source packages so that people interested in the package can find the bugs about it. You can find some hints about determining what package your bug might be about at https://wiki.ubuntu.com/Bugs/FindRightPackage. You might also ask for help in the #ubuntu-bugs irc channel on Freenode.

To change the source package that this bug is filed about visit https://bugs.launchpad.net/ubuntu/+bug/1536837/+editstatus and add the package name in the text box next to the word Package.

[This is an automated message. I apologize if it reached you inappropriately; please just reply to this message indicating so.]

[Timothy Pearson (kb9vqf)]

I tried to assign the source package but received the same error as when I filed this bug:
"There is no package named 'linux-image-4.4.0-0-generic' published in Ubuntu."

[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 1536837

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.

[Timothy Pearson (kb9vqf)]

The machine I originally tested the 4.4 kernel on is not available right now; I will retry as time permits. Would the dmesg output from the failed boot help or are you looking for something else in the apport output?

[John-Michael (thesaxophonist)]

This appears to be an upstream kernel bug, and not limited to just Ubuntu/Debian. I'm currently running Arch Linux and this regression showed up in the 4.4 kernel. The last known good kernel version was 4.3.3. Kernel versions that have the issue include 4.4.1 and 4.5rc1.

[John-Michael (thesaxophonist)]

https://bugzilla.kernel.org/show_bug.cgi?id=111921 may be of interest.