Improve simple map benchmark

[puzpuzpuz]

• Replaces existing SimpleMapBenchmark.js benchmark with two simple parallel ops benchmark.
• Generic benchmark logic was moved into a common module.
• The common benchmark module runs multiple operations in parallel. Thus it loads the client and the server more effectively.
• A couple of runner scripts were introduced.
• MapRandomOpRunner runner is using the original random operation generator.
• MapPutRunner runner removes randomness factor and dependency on server-side from the benchmark: all operations now are map.put('foo', 'bar').
• Also includes a readme to simplify running benchmarks.
• Tested on node 4 & 10.

Old benchmark showed about 16-17K ops/sec on my laptop, while the new one (namely MapPutRunner) shows about 50-60K ops/sec.

[mustafaiman]

I liked the new benchmark using the client to its fullest performance. Thanks for noticing the old benchmark was self throttling.

About this new one, is it possible to re-introduce the parameterized put-get-remove options? We can set PUT_PERCENTAGE to 100 to consistently test put throughput. Also, I think having a key space and some randomness makes more sense because we would like to test it against a cluster of multiple instances. Having a single key makes the client use only a single instance. Even with a single instance scenario, we are limiting hazelcast member to utilize only a single partition. Therefore, we remove parallelization from member by using a single key.

Also, I would like to have benchmark code compatible with node.js 4 as long as we support it.

[puzpuzpuz]

@mustafaiman
I could extract generic benchmark logic into a common module and introduce a couple of runner scripts. The first one would be using the original random operation generator, while the second one would be doing map.put('foo', 'bar').
WDYT?

As for the node 4, I'll downgrade syntax to support it.

[mustafaiman]

@puzpuzpuz sounds awesome

[puzpuzpuz]

@mustafaiman
I've updated the code according to our discussions. Could review it once again?