I have already replied on your StackOverflow thread as follows: Nothing in the gRPC stack seems to cause this limit. What's the average response time on the server side? It looks like you are limited by the ephemeral ports or TCP connection limit and you may want to tweak your kernel as described at here https://www.metabrew.com/article/a-million-user-comet-application-with-mochiweb-part-1 or here https://blog.box.com/ephemeral-port-exhaustion-and-web-services-at-scale
On Thursday, March 4, 2021 at 2:41:47 AM UTC-8 nitish bhardwaj wrote: > Hi, > > I have a simple grpc service that returns "hello" to the client. The > server is running on 80 core machine. I am using *ghz *tool to load test > the service. It's able to serve 40k requests per second but the rest of the > 20k requests are queued and all grpc threads are in waiting state. CPU is > underutilized to 7% and memory is 7-10%. > > More details are mentioned here: > > https://stackoverflow.com/questions/66385871/grpc-server-in-java-to-support-huge-load-of-requests > > What are the required settings to support more load of incoming requests? > > Thanks, > Nitish > -- You received this message because you are subscribed to the Google Groups "grpc.io" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/grpc-io/26d350d0-70cb-4d73-91c6-59ec2ec92937n%40googlegroups.com.
