Have you taken a look at the logs across your scheduler / master / agent to see where the latency is introduced? We can then discuss options to reduce the latency.
Ben On Tue, Mar 7, 2017 at 5:03 AM, <[email protected]> wrote: > Hi, > > > > I’m implementing my own framework (scheduler + executor) over mesos. The > framework is oriented for low latency, short running tasks (i.e. task time > is hundreds of ms). > > I wrote a simple scheduler and executor and measured the time of task > submission RTT (round trip) – that is the elapsed time from submitting the > task at scheduler (by accepting and offer) and until the scheduler received > TASK_FINISHED status. > > The task on executor side does nothing but to immediately sending > TASK_FINISHED status. > > > > I see that the RTT is ~50ms which is quite a lot for my scenario, I was > wondering if this is controllable and why does it take so long to receive > status update. > > > > Thanks > > > > *Assaf.* > > ------------------------------ > >
