Edit Question - KnowledgeHub

Title Body

I am performing repeated send/recv calls on TCP sockets in Ruby, and have found significant speed differences between two socket uses---simply put, reusing a socket is proving slower than continually closing and re-opening one. The server is thus: s = TCPServer.new( 4545 ) while( c = s.accept ) while( m = c.gets ) c.puts( m.chomp ) end end s.close It simply echoes the request back to the client. Client 1 reconnects each time: t1 = Time.now 1000.times{ s = TCPSocket.new( '127.0.0.1', 4545 ) s.puts( 'test' ) s.gets s.close } puts "Reconnecting: #{Time.now - t1}s" Client 2 holds its socket open: t1 = Time.now s = TCPSocket.new( '127.0.0.1', 4545 ) s.setsockopt(Socket::IPPROTO_TCP, Socket::TCP_NODELAY, 1) #Nagle 1000.times{ s.puts( 'test' ) s.gets } s.close puts "Persistent: #{Time.now - t1}s" The result of running this code is as below: % ruby test_client.rb Reconnecting: 0.233751849s Persistent (w/Nagle): 79.925120196s Persistent (NODELAY): 39.958955967s It is my understanding that reusing a socket should save me time (not take 347 times longer!). I've tried calling IO#flush after writing to sockets, but this makes no difference. Disabling Nagle's algorithm helps to some extent but nowhere near enough. What would cause the code above (running on Linux 3.8.5 and ruby 2.0.0) to execute with such a great discrepancy in speed, and how can I rectify this?

Tags (comma-separated) Cancel