yahoo-eng-team team mailing list archive

[OpenStack Infra <1501358@xxxxxxxxxxxxxxxxxx>]

*** This bug is a duplicate of bug 1467927 ***
    https://bugs.launchpad.net/bugs/1467927

Reviewed:  https://review.openstack.org/229575
Committed: https://git.openstack.org/cgit/openstack/nova/commit/?id=d5bed8fad9d51dd0d4ba9cf452c6f5c8c543b264
Submitter: Jenkins
Branch:    master

commit d5bed8fad9d51dd0d4ba9cf452c6f5c8c543b264
Author: Nikola Dipanov <ndipanov@xxxxxxxxxx>
Date:   Wed Sep 30 19:30:59 2015 +0100

    Fix CPU pinning for odd number of CPUs w hyperthreading
    
    Previous logic was not handling the cases when the instance cell has an
    odd number of vcpus that is larger than any sibling set on the host. The
    logic would (accidentally) either reject to pin such an instance even
    though there is ample free cores, or would (in case there were enough
    free sibling sets on the host) spread the instance instead of pack it
    onto siblings as the default policy suggests.
    
    This patch fixes some incorrect assumptions in the code, while also
    simplifying it. As an added bonus - we still attempt to expose
    (via the Topology, and this time correctly) the largest possible number
    of threads that we can expose to the instance.
    
    Finally - we add some more comments to clear up the intent behind the
    current packing logic with pointers how it could be tweaked to achieve
    different results in the future.
    
    Change-Id: I2c0b3b250ffb1a7483299df13b317cdb24f8141d
    Co-Authored-By: Stephen Finucane <stephen.finucane@xxxxxxxxx>
    Closes-bug: 1501358
    Closes-bug: 1467927


** Changed in: nova
       Status: In Progress => Fix Released

-- 
You received this bug notification because you are a member of Yahoo!
Engineering Team, which is subscribed to OpenStack Compute (nova).
https://bugs.launchpad.net/bugs/1501358

Title:
  cpu pinning on the host that has siblings does not work properly in
  some cases (instance with odd CPUs)

Status in OpenStack Compute (nova):
  Fix Released

Bug description:
  Calculating CPU pinning for an instance for the host with
  hyperthreading fails in certain cases. Most notably when the instance
  has an odd number of CPUs, due to a bug in the logic we might either
  fail to pin entirely or end up avoiding siblings by accident, although
  the default policy should be to prefer them (which is what happens
  when we have an even number of CPUs).

  Consider a host with CPUs [(0, 3), (1, 4), (2, 5)]  (brackets denote
  thread siblings). Instance with 5 CPUs would fail to get fitted onto
  this host even though it's clear that it's absolutely possible to fit
  that instance on there.

  Another unexpected result happens when we have a host [[0, 8], [1, 9],
  [2, 10], [3, 11], [4, 12], [5, 13], [6, 14], [7, 15]] and a 5 CPU
  instance. In this case an instance with 5 CPUs would get pinned as
  follows (instance cpu -> host cpu): [(0 -> 0), (1 -> 1), (2 -> 2), (3
  -> 3), (4 -> 4)] which is wrong since the default for instances with
  an even number of CPUs would be to prefer sibling CPUs.

  After inspecting the fitting logic code:

  https://github.com/openstack/nova/blob/b0013d93ffeaed53bc28d9558def26bdb7041ed7/nova/virt/hardware.py#L653

  I also noticed that we would consult the existing topology of the
  instance NUMA cell when deciding on the proper way to fit instance
  CPUs onto host. This is actually wrong after
  https://review.openstack.org/#/c/198312/. We don't need to consider
  the requested topology in the CPU fitting any more as the code that
  decides on the final CPU topology takes all of this into account.

To manage notifications about this bug go to:
https://bugs.launchpad.net/nova/+bug/1501358/+subscriptions