We are simulating infinispan in various situations:
1. client and server nodes running on same host
2. client and server nodes running on different hosts in same location
3. client and server nodes running on different hosts in different locations
here are the results we observed:
1. hotrod timing are far better than memcached timings.
2. hotrod timing are better than memcached timings, even after the fact hotrod timing increased a bit because of i think network transmission and all
BUT, in case:
3. when communication is happening between out internal nyc and hyd host, hotrod timing are way larger then expected and memcached timings can be considered far better than hotRod
We are not able to guess any valid reason for this. Any help will be appreciated.
You can find our findings in the attachment. Each file is list of csv, in the format: number of objects, size of each object, time taken in ms.
File names are in the format: Protocol_Location_Host_ObjectType
Thanks,
Sonal