number_of_netty_threads: Number frontend netty thread. This specifies the numer of threads in the child EventLoopGroup of the frontend netty server. This group provides EventLoops for processing Netty Channel events (namely inference and management requests) from accepted connections. Default: ~number of logical processors available to the JVM~.
~Default is 0~.
I want to make a pull request for this, but I am not able to push to pytorch/serve
📚 Documentation
In configuration.md
number_of_netty_threads
: Number frontend netty thread. This specifies the numer of threads in the child EventLoopGroup of the frontend netty server. This group provides EventLoops for processing Netty Channel events (namely inference and management requests) from accepted connections. Default: ~number of logical processors available to the JVM~. ~Default is 0~.I want to make a pull request for this, but I am not able to push to
pytorch/serve
Update
The default number of netty threads is twice the number of available number processors to JVM Ref: https://github.com/pytorch/serve/pull/873#issuecomment-745011364
Trace proves 2 * num_processors used when 0 is supplied as default netty thread count