performance improvement + reduce number of worker threads

[jknack]

wrk -t4 -c128 -d30s http://localhost:8080 -s pipeline.lua --latency -- / 16

On a simple hello world undertow application using cores * 8 worker threads

Give us:

Running 30s test @ http://localhost:8080
  4 threads and 128 connections
  Thread Stats   Avg      Stdev     Max   +/- Stdev
    Latency     5.65ms    9.56ms 212.87ms   72.74%
    Req/Sec    58.26k     9.39k   71.60k    88.80%
  Latency Distribution
     50%    6.93ms
     75%   58.64ms
     90%    0.00us
     99%    0.00us
  6936432 requests in 30.01s, 740.89MB read
  Socket errors: connect 0, read 1, write 0, timeout 0
Requests/sec: 231100.65
Transfer/sec:     24.68MB