canonical-ubuntu-qa team mailing list archive

[Jürg Häfliger <1951289@xxxxxxxxxxxxxxxxxx>]

** Tags added: kernel-daily-bug

-- 
You received this bug notification because you are a member of Canonical
Platform QA Team, which is subscribed to ubuntu-kernel-tests.
https://bugs.launchpad.net/bugs/1951289

Title:
  ubuntu_ltp_controllers:cpuset_sched_domains: tests 3,9,11,17,19,25
  report incorrect sched domain for cpu#32

Status in kunpeng920:
  Fix Released
Status in kunpeng920 ubuntu-18.04 series:
  Fix Released
Status in kunpeng920 ubuntu-18.04-hwe series:
  Fix Released
Status in kunpeng920 ubuntu-20.04 series:
  Fix Released
Status in kunpeng920 upstream-kernel series:
  Fix Released
Status in ubuntu-kernel-tests:
  Invalid
Status in linux package in Ubuntu:
  Fix Released
Status in linux source package in Bionic:
  Fix Released
Status in linux source package in Focal:
  Fix Released
Status in linux source package in Hirsute:
  Won't Fix

Bug description:
  [Impact]
  The LTP cpuset_sched_domains test, authored by Miao Xie, fails on a Kunpeng920
  server that has 4 NUMA nodes:
    https://launchpad.net/bugs/1951289

  This does appear to be a real bug. /proc/schedstat displays 4 domain levels for
  CPUs on 2 of the nodes, but only 3 levels for the others 2 (see below).
  I assume this means the scheduler is making suboptimal decisions about
  where to place/move processes.

  [Test Case]
  On a 128 core Kunpeng 920 system, observe that half the CPUs are missing a 3rd level scheduling domain:

  ubuntu@d06-4:~$ grep domain2 /proc/schedstat  | wc -l
  128
  ubuntu@d06-4:~$ grep domain3 /proc/schedstat  | wc -l
  64
  ubuntu@d06-4:~$

  [What Could Go Wrong]
  This changes the code used for populating sched domains, so it could potentially break on other systems, leading to poor scheduling characteristics (higher latencies, lower overall throughput etc).

To manage notifications about this bug go to:
https://bugs.launchpad.net/kunpeng920/+bug/1951289/+subscriptions