...
BGP receive and send can be split in into sub-tasks by specific parameters, for example, it is possible to run input per each peer or group all peer inputs and run them in the main process. This split by sub-tasks is controlled with input.affinity
and output.affinity
parameter configuration in /routing/bgp/template
.It is possible to boost performance by playing with affinity values on devices with less fewer cores , since sharing data between tasks is a bit slower than process processing the same data within one task. For example, on single-core or two-core devices running input and output in the main or instance process will boost performance.
Note |
---|
BGP can have up to 100 unique processes. |
All currently used tasks and their allocated private/shared memory can be monitored using the command:
Code Block | ||
---|---|---|
| ||
/routing/stats/process/print |
...