Performance regression in libvirt get_available_resource()
Affects | Status | Importance | Assigned to | Milestone | |
---|---|---|---|---|---|
OpenStack Compute (nova) |
Fix Released
|
Undecided
|
Lee Yarwood |
Bug Description
Description
===========
Periodic task update_
instances on local storage:
https:/
Steps to reproduce
==================
1. /etc/nova/
[DEFAULT]
preallocate_
[libvirt]
images_type=raw
2. Launch 100 instances on the host
3. See, that every update_
This performance regression was introduced in this commit:
https:/
and following commit doubles the time:
https:/
Expected result
===============
update_
Actual result
=============
update_
Environment
===========
1. Exact version of OpenStack you are running:
OpenStack Pike
nova 16.1.4, commit b58c7f0
2. Which hypervisor did you use?
Libvirt + KVM/QEMU
2. Which storage type did you use?
local storage, raw
summary: |
- Performance regression in libvirt get_available_resource(nodename) + Performance regression in libvirt get_available_resource() |
Changed in nova: | |
assignee: | Matthew Booth (mbooth-9) → Lee Yarwood (lyarwood) |
Related fix proposed to branch: master /review. openstack. org/589513
Review: https:/