Add Benchmark concepts of service time and latency

[Naarcha-AWS]

Checklist

• By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license and subject to the Developers Certificate of Origin.
  For more information on following Developer Certificate of Origin and signing off your commits, please check here.

[IanHoang]

left some comments

[Naarcha-AWS]

@IanHoang: This is ready for your review again.

[hdhalter]

Looks good, just a few suggestions.

[saimedhi]

Hello @Naarcha-AWS, I believe the service time measured in OSB is just the time taken from "request reached server" to "response provided by server". Please correct me if I am wrong. Thanks :)

[Naarcha-AWS]

@IanHoang: What do you think? I can adjust the wording if needed.

[natebower]

@Naarcha-AWS Please see my comments and changes and let me know if you have any questions. Thanks!

[natebower]

Should "time" be "times"?

[saimedhi]

Correct me if I am wrong @dblock, @IanHoang.

In OpenSearch benchmarks, Service Time is calculated in osbenchmark/client.py using the following trace configuration:

trace_config = aiohttp.TraceConfig()
trace_config.on_request_start.append(on_request_start)
trace_config.on_request_end.append(on_request_end)

I believe the first definition (common definition) in the above documentation code aligns more accurately with our interpretation of Service Time.

Service Time: Represents the interval from the server receiving the request to the server sending the response.

Additional Information:
I attempted to calculate the times by implementing a function perform_request within the AIOHttpConnection in osbenchmark/async_connection.py. The times obtained indicate that the calculated service time doesn't include client processing time.

async def perform_request(self, method, url, params=None, body=None, timeout=None, ignore=(), headers=None):
    print("AIOHttpConnection perform_request start time", time.perf_counter())
    status, headers, raw_data = await super().perform_request(method=method, url=url, params=params, body=body, timeout=timeout, ignore=ignore, headers=self.headers)
    print("AIOHttpConnection perform_request end time", time.perf_counter())
    return status, headers, raw_data

Sample output:

AIOHttpConnection perform_request start time 19.0016295
AIOHttpConnection perform_request end time 19.007145792
service time start 19.001905542
service time end 19.007082167
service time 0.005176625000000712
AIOHttpConnection perform_request start time 19.008452584
AIOHttpConnection perform_request end time 19.012769334
service time start 19.008625875
service time end 19.012713375
service time 0.004087500000000688