I have a couple of suggestions:
0. It costs about 29 nanos to grab a timestamp. If you are doing it on
every message sent and received you might end up with your calls to
clock_gettime being your bottleneck
1. Nitsan wakart wrote a nice Java ping benchmark
see
On 2018-04-23 22:33, John Hening wrote:
|
Hello,
1. I have a simple one-threaded tcp server written in Java. I try to
measure its receive-and-process-response latency. More preceisely, the
client sends (by loopback) the 128-bytes message with a timestamp in
the header. The server receives
On Monday, April 23, 2018 at 12:33:17 PM UTC-7, John Hening wrote:
>
> Hello,
>
> 1. I have a simple one-threaded tcp server written in Java. I try to
> measure its receive-and-process-response latency. More preceisely, the
> client sends (by loopback) the 128-bytes message with a timestamp in
Hello,
1. I have a simple one-threaded tcp server written in Java. I try to
measure its receive-and-process-response latency. More preceisely, the
client sends (by loopback) the 128-bytes message with a timestamp in the
header. The server receives a message, reads a content byte by byte and