| 2018-09-04 15:43:16 |
Tee Ngo |
bug |
|
|
added bug |
| 2018-09-04 15:43:58 |
Dariush Eslimi |
starlingx: assignee |
|
Tee Ngo (teewrs) |
|
| 2018-09-04 15:44:20 |
Tee Ngo |
description |
Description
-----------
The current setting of notification workers can result in an excessive number in system ]
that has controller(s) with high number of cores. This should be limited to 10 max to
avoid unnecessary system resources consumption and to improve vcpu scaling responsiveness.
The degraded scaling performance due to excessive number of workers is caused
by time taken to rebuild the transformer caches in all workers following a swact/service
restart as well as the increased cpu sample age in these caches.
The setting should be revised and further reduced once ceilometer transformers have all been
deprecated and transformation functionality moved to ceilometer backend.
Severity
--------
Major
Steps to reproduce
------------------
In a system with high-core (30+) controllers, execute vcpu scaling test case either
repeatedly (e.g. 25 times) or right after a controller swact.
Expected behavior
-----------------
TC executed successfully
Actual behavior
---------------
Occasional timeout
Reproducibility
---------------
Infrequent
System configuration
--------------------
Multi-node with high core controllers
Timestamp/Logs
--------------
N/A |
Description
-----------
The current setting of notification workers can result in an excessive number in system that has controller(s) with high number of cores. This should be limited to 10 max to avoid unnecessary system resources consumption and to improve vcpu scaling responsiveness. The degraded scaling performance due to excessive number of workers is caused by time taken to rebuild the transformer caches in all workers following a swact/service restart as well as the increased cpu sample age in these caches.
The setting should be revised and further reduced once ceilometer transformers have all been deprecated and transformation functionality moved to ceilometer backend.
Severity
--------
Major
Steps to reproduce
------------------
In a system with high-core (30+) controllers, execute vcpu scaling test case either
repeatedly (e.g. 25 times) or right after a controller swact.
Expected behavior
-----------------
TC executed successfully
Actual behavior
---------------
Occasional timeout
Reproducibility
---------------
Infrequent
System configuration
--------------------
Multi-node with high core controllers
Timestamp/Logs
--------------
N/A |
|
| 2018-09-04 15:44:50 |
Tee Ngo |
description |
Description
-----------
The current setting of notification workers can result in an excessive number in system that has controller(s) with high number of cores. This should be limited to 10 max to avoid unnecessary system resources consumption and to improve vcpu scaling responsiveness. The degraded scaling performance due to excessive number of workers is caused by time taken to rebuild the transformer caches in all workers following a swact/service restart as well as the increased cpu sample age in these caches.
The setting should be revised and further reduced once ceilometer transformers have all been deprecated and transformation functionality moved to ceilometer backend.
Severity
--------
Major
Steps to reproduce
------------------
In a system with high-core (30+) controllers, execute vcpu scaling test case either
repeatedly (e.g. 25 times) or right after a controller swact.
Expected behavior
-----------------
TC executed successfully
Actual behavior
---------------
Occasional timeout
Reproducibility
---------------
Infrequent
System configuration
--------------------
Multi-node with high core controllers
Timestamp/Logs
--------------
N/A |
Description
-----------
The current setting of notification workers can result in an excessive number in system that has controller(s) with high number of cores. This should be limited to 10 max to avoid unnecessary system resources consumption and to improve vcpu scaling responsiveness. The degraded scaling performance due to excessive number of workers is caused by time taken to rebuild the transformer caches in all workers following a swact/service restart as well as the increased cpu sample age in these caches.
The setting should be revised and further reduced once ceilometer transformers have all been deprecated and transformation functionality moved to ceilometer backend.
Severity
--------
Major
Steps to reproduce
------------------
In a system with high-core (30+) controllers, execute vcpu scaling test case either repeatedly (e.g. 25 times) or right after a controller swact.
Expected behavior
-----------------
TC executed successfully
Actual behavior
---------------
Occasional timeout
Reproducibility
---------------
Infrequent
System configuration
--------------------
Multi-node with high core controllers
Timestamp/Logs
--------------
N/A |
|
| 2018-09-04 18:29:18 |
OpenStack Infra |
starlingx: status |
New |
In Progress |
|
| 2018-09-04 19:53:32 |
Ghada Khalil |
tags |
|
stx.2018.10 stx.config stx.distro.openstack |
|
| 2018-09-04 19:54:00 |
Ghada Khalil |
starlingx: importance |
Undecided |
High |
|
| 2018-09-04 20:52:33 |
OpenStack Infra |
starlingx: status |
In Progress |
Fix Released |
|
| 2019-04-06 16:12:52 |
Ken Young |
tags |
stx.2018.10 stx.config stx.distro.openstack |
stx.1.0 stx.config stx.distro.openstack |
|
