The throughput probing implementation currently reports the following metrics:

• timesIncreased
• totalAmountIncreased
• timesDecreased
• totalAmountDecreased
• resizeDurationMicros

Adding a few more metrics would help us better diagnose the behavior of throughput probing in tickets like HELP-69090:

• timesProbedStable: the cumulative number of times the algorithm performed a stable probe
• timesProbedUp: the cumulative number of times the algorithm probed up
• timesProbedDown: the cumulative number of times the algorithm probed down

Note that these metrics are different from timesIncreased and timesDecreased. The existing metrics measure how many times a probe up/down resulted in accepting the new concurrency.