Most of the time round robin will work well. There are some traffic patterns (few heavy weight requests) or hardware imbalances that don’t do well with round robin.
The way to open source it would be to file a Jira ticket (https://issues.apache.org/jira/browse/TS <https://issues.apache.org/jira/browse/TS>) and then create a pull request on github (https://github.com/apache/trafficserver <https://github.com/apache/trafficserver>). I use ab and depending on the work load http_load (https://github.com/apache/trafficserver/tree/master/tools/http_load <https://github.com/apache/trafficserver/tree/master/tools/http_load>) to do benchmarking. -Bryan > On Aug 11, 2016, at 10:36 PM, Velusamy, Gandhimathi <[email protected]> > wrote: > > Hi, > > I am working for my graduate thesis on load balancer. I am trying to > implement delay based load balancing with Traffic server as a reverse proxy. > I am using balancer.cc and writing my functionality there. I am using a map > to store Sate Machine ids and delays computed between transaction start and > transaction close events. > > But I could not find any difference between round robin method and my delayed > based policy even though my four origin servers are having different CPU and > memory configurations. I am guessing that the computation of comparing > delays by accessing from maps causes more delay. I would like to contribute > my implementation to Traffic server community once I finish my thesis. > > Any pointers on how to proceed or where to look will be appreciated. Also is > there any tool available to load test. Current I used "ab" and "RUBiS" > > Thanks > Gandhimathi > >
