Some L3 RPCs are time-consuming especially get_routers
Affects | Status | Importance | Assigned to | Milestone | |
---|---|---|---|---|---|
neutron |
Confirmed
|
Medium
|
Unassigned |
Bug Description
Examples:
http://
http://
http://
http://
Some possible reasons:
1. neutron server is busy while it can not process this RPC
2. DB slow query
3. L3 agent thread (context) switching
Maybe a bug to bring to the performance meeting? logs.openstack. org/11/ 669111/ 4/check/ neutron- rally-task/ e48e2e7/ results/ report. html.gz
http://
If some of these calls are large offenders time-wise, we could check the osprofiler results like http:// logs.openstack. org/11/ 669111/ 4/check/ neutron- rally-task/ e48e2e7/ results/ report. html.gz# /NeutronNetwork s.create_ and_list_ routers