Ask Your Question

Revision history [back]

click to hide/show revision 1
initial version

Neutron consuming high CPU

I am running a multinode controller environment in pike. Although there is no load, i see neutron consuming a high cpu, I searched in google but finding nothing, Any ideas on tuning will be much apreciated.

systemd(1)───neutron-server(9212)─┬─neutron-server(13855) ├─neutron-server(13856) ├─neutron-server(13857) ├─neutron-server(13859) ├─neutron-server(13861) ├─neutron-server(13862) ├─neutron-server(13863) ├─neutron-server(13865) ├─neutron-server(13867) ├─neutron-server(13869) ├─neutron-server(13870) ├─neutron-server(13873) ├─neutron-server(13875) ├─neutron-server(13877) ├─neutron-server(13878) ├─neutron-server(13879) ├─neutron-server(13882) ├─neutron-server(13883) ├─neutron-server(13886) ├─neutron-server(13887) ├─neutron-server(13888) ├─neutron-server(13891) ├─neutron-server(13892) ├─neutron-server(13893) ├─neutron-server(13894) ├─neutron-server(13897) └─neutron-server(13898) PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
13894 neutron 20 0 453812 138808 2248 R 89.5 0.1 713:54.25 /usr/bin/python2 /usr/bin/neutron-server --config-file /usr/share/neutron/neutron-dist.conf --config-dir /usr/share/neutron/server --c+

I read reducing report intervel of agents will help, any practical experiences?, please share on what exactly can be tuned without causing problems in future?

Thanks in Advance

Neutron consuming high CPU

I am running a multinode controller environment in pike. Although there is no load, i see neutron consuming a high cpu, I searched in google but finding nothing, Any ideas on tuning will be much apreciated.

pstree of neutron-server :

systemd(1)───neutron-server(9212)─┬─neutron-server(13855) ├─neutron-server(13856) ├─neutron-server(13857) ├─neutron-server(13859) ├─neutron-server(13861) ├─neutron-server(13862) ├─neutron-server(13863) ├─neutron-server(13865) ├─neutron-server(13867) ├─neutron-server(13869) ├─neutron-server(13870) ├─neutron-server(13873) ├─neutron-server(13875) ├─neutron-server(13877) ├─neutron-server(13878) ├─neutron-server(13879) ├─neutron-server(13882) ├─neutron-server(13883) ├─neutron-server(13886) ├─neutron-server(13887) ├─neutron-server(13888) ├─neutron-server(13891) ├─neutron-server(13892) ├─neutron-server(13893) ├─neutron-server(13894) ├─neutron-server(13897) └─neutron-server(13898) └─neutron-server(13898)

Top command output :

PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
13894 neutron 20 0 453812 138808 2248 R 89.5 0.1 713:54.25 /usr/bin/python2 /usr/bin/neutron-server --config-file /usr/share/neutron/neutron-dist.conf --config-dir /usr/share/neutron/server --c+

I read reducing report intervel of agents will help, any practical experiences?, please share on what exactly can be tuned without causing problems in future?

Thanks in Advance

Neutron consuming high CPU

I `I am running a multinode controller environment in pike. Although there is no load, i see neutron consuming a high cpu, I searched in google but finding nothing, Any ideas on tuning will be much apreciated.

pstree of neutron-server :

systemd(1)───neutron-server(9212)─┬─neutron-server(13855) ├─neutron-server(13856) ├─neutron-server(13857) ├─neutron-server(13859) ├─neutron-server(13861) ├─neutron-server(13862) ├─neutron-server(13863) ├─neutron-server(13865) ├─neutron-server(13867) ├─neutron-server(13869) ├─neutron-server(13870) ├─neutron-server(13873) ├─neutron-server(13875) ├─neutron-server(13877) ├─neutron-server(13878) ├─neutron-server(13879) ├─neutron-server(13882) ├─neutron-server(13883) ├─neutron-server(13886) ├─neutron-server(13887) ├─neutron-server(13888) ├─neutron-server(13891) ├─neutron-server(13892) ├─neutron-server(13893) ├─neutron-server(13894) ├─neutron-server(13897) └─neutron-server(13898)

Top command output :

PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
13894 neutron 20 0 453812 138808 2248 R 89.5 0.1 713:54.25 /usr/bin/python2 /usr/bin/neutron-server --config-file /usr/share/neutron/neutron-dist.conf --config-dir /usr/share/neutron/server --c+

I read reducing report intervel of agents will help, any practical experiences?, please share on what exactly can be tuned without causing problems in future?

Thanks in AdvanceAdvance`

Neutron consuming high CPU

`I I am running a multinode controller environment in pike. Although there is no load, i see neutron consuming a high cpu, I searched in google but finding nothing, Any ideas on tuning will be much apreciated.

pstree of neutron-server :

systemd(1)───neutron-server(9212)─┬─neutron-server(13855) ├─neutron-server(13856) ├─neutron-server(13857) ├─neutron-server(13859) ├─neutron-server(13861) ├─neutron-server(13862) ├─neutron-server(13863) ├─neutron-server(13865) ├─neutron-server(13867) ├─neutron-server(13869) ├─neutron-server(13870) ├─neutron-server(13873) ├─neutron-server(13875) ├─neutron-server(13877) ├─neutron-server(13878) ├─neutron-server(13879) ├─neutron-server(13882) ├─neutron-server(13883) ├─neutron-server(13886) ├─neutron-server(13887) ├─neutron-server(13888) ├─neutron-server(13891) ├─neutron-server(13892) ├─neutron-server(13893) ├─neutron-server(13894) ├─neutron-server(13897) └─neutron-server(13898)

Top command output :

PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
13894 neutron 20 0 453812 138808 2248 R 89.5 0.1 713:54.25 /usr/bin/python2 /usr/bin/neutron-server --config-file /usr/share/neutron/neutron-dist.conf --config-dir /usr/share/neutron/server --c+

I read reducing report intervel of agents will help, any practical experiences?, please share on what exactly can be tuned without causing problems in future?

Thanks in Advance`

Neutron consuming high CPU

I am running a multinode 3 node controller environment cluster with haproxy and mysql galera, and two compute nodes in pike. Although there is no load, i see neutron consuming a high cpu, I searched in google but finding nothing, Any ideas on tuning will be much apreciated.

Each controller: CPU(s): 24 On-line CPU(s) list: 0-23 Thread(s) per core: 2 Core(s) per socket: 6 Memory : 94 GB

Compute nodes : CPU(s): 40 On-line CPU(s) list: 0-39 Thread(s) per core: 2 Core(s) per socket: 10 Memory : 250GB

pstree of neutron-server :

systemd(1)───neutron-server(9212)─┬─neutron-server(13855) ├─neutron-server(13856) ├─neutron-server(13857) ├─neutron-server(13859) ├─neutron-server(13861) ├─neutron-server(13862) ├─neutron-server(13863) ├─neutron-server(13865) ├─neutron-server(13867) ├─neutron-server(13869) ├─neutron-server(13870) ├─neutron-server(13873) ├─neutron-server(13875) ├─neutron-server(13877) ├─neutron-server(13878) ├─neutron-server(13879) ├─neutron-server(13882) ├─neutron-server(13883) ├─neutron-server(13886) ├─neutron-server(13887) ├─neutron-server(13888) ├─neutron-server(13891) ├─neutron-server(13892) ├─neutron-server(13893) ├─neutron-server(13894) ├─neutron-server(13897) └─neutron-server(13898)

Top command output :

PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
13894 neutron 20 0 453812 138808 2248 R 89.5 0.1 713:54.25 /usr/bin/python2 /usr/bin/neutron-server --config-file /usr/share/neutron/neutron-dist.conf --config-dir /usr/share/neutron/server --c+

I read reducing report intervel of agents will help, any practical experiences?, please share on what exactly can be tuned without causing problems in future?