Test bench scheduler controller

[tao-stones]

Problem

To observe different Schedulers performance, scheduling behavior, and how low-prio non-contend tx being scheduled.

Summary of Changes

• add bench setup

Fixes #

[tao-stones]

• with 16 unique receiving accounts, non-contend took almost 5X longer, fully-contend change slightly
• greedy isn't much better than prio-graph in these two extreme scenario
• Tracer placement in fully-contend scenarios are not fully expected.

bench_prio_graph_non_contend_transactions/sdk_transaction_type
                        time:   [303.21 ms 308.86 ms 315.09 ms]
                        change: [-1.9760% +0.5269% +3.1610%] (p = 0.71 > 0.05)
                        No change in performance detected.

== Averaged per bench stats to empty Container ==
            number of scheduling: 100
            number of Works: 1600
            number of transactions scheduled: 100000
            number of transactions per work: 62
            Tracer placement: 100000
Benchmarking bench_prio_graph_fully_contend_transactions/sdk_transaction_type: Warming up for 3.0000 s
Warning: Unable to complete 10 samples in 5.0s. You may wish to increase target time to 35.1s.
bench_prio_graph_fully_contend_transactions/sdk_transaction_type
                        time:   [556.00 ms 570.06 ms 589.64 ms]
                        change: [-6.7949% -2.2685% +2.7725%] (p = 0.39 > 0.05)
                        No change in performance detected.
Found 1 outliers among 10 measurements (10.00%)
  1 (10.00%) high severe

== Averaged per bench stats to empty Container ==
            number of scheduling: 100
            number of Works: 100000
            number of transactions scheduled: 100000
            number of transactions per work: 1
            Tracer placement: 99746
Benchmarking bench_greedy_non_contend_transactions/sdk_transaction_type: Warming up for 3.0000 s
Warning: Unable to complete 10 samples in 5.0s. You may wish to increase target time to 32.0s.
bench_greedy_non_contend_transactions/sdk_transaction_type
                        time:   [299.99 ms 310.50 ms 323.11 ms]
                        change: [-2.9341% +1.3619% +5.8495%] (p = 0.58 > 0.05)
                        No change in performance detected.
Found 3 outliers among 10 measurements (30.00%)
  1 (10.00%) low mild
  2 (20.00%) high severe

== Averaged per bench stats to empty Container ==
            number of scheduling: 1
            number of Works: 1584
            number of transactions scheduled: 100000
            number of transactions per work: 63
            Tracer placement: 100000
Benchmarking bench_greedy_fully_contend_transactions/sdk_transaction_type: Warming up for 3.0000 s
Warning: Unable to complete 10 samples in 5.0s. You may wish to increase target time to 34.0s.
bench_greedy_fully_contend_transactions/sdk_transaction_type
                        time:   [502.38 ms 517.80 ms 534.91 ms]
                        change: [-8.7162% -3.0078% +2.8615%] (p = 0.36 > 0.05)
                        No change in performance detected.

== Averaged per bench stats to empty Container ==
            number of scheduling: 1
            number of Works: 100000
            number of transactions scheduled: 100000
            number of transactions per work: 1
            Tracer placement: 100000