** Also affects: linux-raspi (Ubuntu Hirsute)
   Importance: Undecided
       Status: New

-- 
You received this bug notification because you are a member of Kernel
Packages, which is subscribed to linux-raspi in Ubuntu.
https://bugs.launchpad.net/bugs/1932586

Title:
  Processes launched during the NIC load is high may hang up.

Status in linux-raspi package in Ubuntu:
  New
Status in linux-raspi source package in Hirsute:
  New

Bug description:
  1) The release of Ubuntu you are using, via 'lsb_release -rd' or System -> 
About Ubuntu
  ❯ lsb_release -rd
  Description:    Ubuntu 21.04
  Release:        21.04

  2) The version of the package you are using, via 'apt-cache policy pkgname' 
or by checking in Software Center
  ❯ LANG=C apt-cache policy linux-raspi
  linux-raspi:
    Installed: 5.11.0.1009.7
    Candidate: 5.11.0.1009.7
    Version table:
   *** 5.11.0.1009.7 500
          500 http://ports.ubuntu.com/ubuntu-ports hirsute-updates/main arm64 
Packages
          500 http://ports.ubuntu.com/ubuntu-ports hirsute-security/main arm64 
Packages
          100 /var/lib/dpkg/status
       5.11.0.1007.5 500
          500 http://ports.ubuntu.com/ubuntu-ports hirsute/main arm64 Packages

  3) What you expected to happen
  Processes launched during the NIC load is high will exit normally.

  4) What happened instead
  I'm using hirsute on Raspberry Pi 4 model B(4GB RAM).
  Some processes launched during the NIC load is high might not exit.

  What "NIC load is high" means:
  - I have configured crontab to run Ookla's speedtest-cli which generates 
heavy network traffic every 15 minites.
  - During speedtest-cli, Softirq becomes higher.
  - SoC(BCM2711) built-in NIC(driver is bcmgenet)

  What "may not exit" means:
  - Some processes launched during speedtest-cli is running will not exit. It 
remains with consuming CPU 100% and not accept any signals including SIGKILL.
  - Those processes can't be attached by gdb or strace. Trying to do so, gdb 
and strace will freeze.

  I could't terminate the processes in any way. But the system could be
  rebooted by "sudo reboot" command.

  I configured RFS/RPS to distribute Softirq among CPU cores. It was
  quite effective, but did not prevent the problem completely.

To manage notifications about this bug go to:
https://bugs.launchpad.net/ubuntu/+source/linux-raspi/+bug/1932586/+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

Reply via email to