Update the limitation of multiple servers binding to the same http/gr…

…p… (triton-inference-server#4991) * Update the limitation of multiple server binding to the same http/grpc port * Address comment * Address comment
Spartee · Oct 18, 2022 · dfa101c · dfa101c
1 parent 0301b7a
commit dfa101c
Showing 1 changed file with 6 additions and 2 deletions.
diff --git a/src/main.cc b/src/main.cc
@@ -401,7 +401,9 @@ std::vector<Option> options_
        "The port for the server to listen on for HTTP requests."},
       {OPTION_REUSE_HTTP_PORT, "reuse-http-port", Option::ArgBool,
        "Allow multiple servers to listen on the same HTTP port when every "
-       "server has this option set."},
+       "server has this option set. If you plan to use this option as a way to "
+       "load balance between different Triton servers, the same model "
+       "repository or set of models must be used for every server."},
       {OPTION_HTTP_ADDRESS, "http-address", Option::ArgStr,
        "The address for the http server to binds to."},
       {OPTION_HTTP_THREAD_COUNT, "http-thread-count", Option::ArgInt,
@@ -414,7 +416,9 @@ std::vector<Option> options_
        "The port for the server to listen on for GRPC requests."},
       {OPTION_REUSE_GRPC_PORT, "reuse-grpc-port", Option::ArgBool,
        "Allow multiple servers to listen on the same GRPC port when every "
-       "server has this option set."},
+       "server has this option set. If you plan to use this option as a way to "
+       "load balance between different Triton servers, the same model "
+       "repository or set of models must be used for every server."},
       {OPTION_GRPC_ADDRESS, "grpc-address", Option::ArgStr,
        "The address for the grpc server to binds to."},
       {OPTION_GRPC_INFER_ALLOCATION_POOL_SIZE,