aws-samples / aws-samples/trading-latency-benchmark
Standardise latency response times, trim raw data and accept custom percentiles for summarisation
- Dominant language
- C
- Stars
- 95
- Forks
- 26
- PR merge metrics
- No merged PRs in 30d
Description
### Describe the feature
a) Allow conversion of all latency response times to microseconds or milliseconds
b) Allow trimming of total set of data points for a test run by accepting lower and upper percentiles before/after which to trim the data. Upper is more important than lower
c) Allow configurable percentile reporting by taking any range of percentiles as input for report generation and bucket by these in the summary report
### Use Case
Prevents having to manipulate the raw data to standardise latency times, trim outliers or generate custom percentile buckets for reporting.
### Proposed Solution
_No response_
### Other Information
_No response_
### Acknowledgements
- [ ] I may be able to implement this feature request
- [ ] This feature might incur a breaking change
### Language
Java
Contributor guide
Research direction
Start by reviewing the existing latency measurement, test-run data handling, and summary report generation flow. Determine where response-time units, percentile trimming, and percentile buckets are currently defined, then verify that configurable units, bounds, and reporting ranges are reflected in generated summaries.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- c, java
- Domain
- analytics, performance
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100