By "a three node couchdb cluster" do you mean BigCouch? If not, then you have three independent couchdb servers, so your findings aren’t that surprising.
B. On 9 Apr 2014, at 17:36, Alexander Shorin <[email protected]> wrote: > On Wed, Apr 9, 2014 at 7:11 PM, Arnaud Schoonjans > <[email protected]> wrote: >> The purpose of the firewall rule in the middle of the benchmark is to >> simulate network-failure. The benchmark test examines how the couchdb >> database reacts to a network partition by looking at the latency of the >> different operations in time. > > Side note: if you really want to test behavior on unstable networks, use netem > http://www.linuxfoundation.org/collaborate/workgroups/networking/netem > Since destination down is quite trivial case and you only can test > there timeouts and request repeating. Packets loss, corruption and > duplication, rate limiting and delays are the real behavior of the > real unstable networks, especially like wifi and 3g. > > About the subj: what have you used for balancing? Are you sure that > this phenomena isn't balancer issue which tries to reach "failed" node > before try the next one - that could cause the latency. > > As usual for any benchmarks, it would be good to see numbers and > how-to guide to reproduce test bench and results locally. > > Thanks. > > -- > ,,,^..^,,,
