Intel® Collaboration Suite for WebRTC
Community support and discussions on the Intel® Collaboration Suite for WebRTC (Intel® CS for WebRTC).
Announcements
Welcome to the Intel Community. If you get an answer you like, please mark it as an Accepted Solution to help others. Thank you!
For the latest information on Intel’s response to the Log4j/Log4Shell vulnerability, please see Intel-SA-00646

Regarding Max Load

Naresh_R_1
New Contributor I
142 Views

Hi Lei,

As i see max load in each worker node as below

#The max CPU/GPU load under which this worker can take new tasks.
max_load = 0.85 #default: 0.85

what are the parameters we have to input in default and what is the max number we can input, also what happens if a worker exceeds the max load

Thanks

Naresh

 

0 Kudos
5 Replies
Naresh_R_1
New Contributor I
142 Views

Hi Team, 

Any help on above mentioned point.

Thanks

Naresh

Lei_Z_Intel1
Employee
142 Views

Default value setting depends on how much load you want the machine to take. If the worker exceeds the max load, then it will not be treated as available worker.

Naresh_R_1
New Contributor I
142 Views

Hi Lei,

 

I have 2 servers in each audio/video agents installed  each with cluster solution and both max load is set to max_load = 0.20 #default: 0.85Now when i am using basic example application only with one single room only 1 server is getting utilised and that too it crossed the max_load. as you told  he worker exceeds the max load, then it will not be treated as available worker.

here then load should go to next available worker right? please explain how this will workl

 

Thanks

Naresh

Li_C_Intel
Employee
142 Views

Hi,

New tasks won't be assigned to a worker, if the cpu exceeds the max load.

While the tasks already run on that unavailable worker won't move to other places.

In your case, if one room is active, then there's only one task for audio and video agent.

Even though the task may cause the load exceeds the threshold, it can't be separated.

Naresh_R_1
New Contributor I
142 Views

Thanks,

is it same with forward room also? if many users login to single room only one worker will get utilised even we have many audio/video_agent workers clustered?

Thanks

Naresh

Reply