What is the problem your feature solves, or the need it fulfills?
Although testing cache hit rates using the Zipf distribution yields good results, I propose introducing trace datasets from different production environments to enhance our hit rate testing. From my local testing on some datasets, I've noticed that LRU sometimes performs well, while tinyUFO might not perform as well with smaller cache sizes.
Describe the solution you'd like
Add some real world trace datasets (eg : small csv file).
Parse it use csv crate, do the same thing like the bench_hit_ratio do.
Describe alternatives you've considered
What other solutions, features, or workarounds have you considered that might also solve the issue?
What are the tradeoffs for these alternatives compared to what you're proposing?
What is the problem your feature solves, or the need it fulfills?
Although testing cache hit rates using the Zipf distribution yields good results, I propose introducing trace datasets from different production environments to enhance our hit rate testing. From my local testing on some datasets, I've noticed that LRU sometimes performs well, while tinyUFO might not perform as well with smaller cache sizes.
Describe the solution you'd like
Add some real world trace datasets (eg : small csv file). Parse it use
csv
crate, do the same thing like thebench_hit_ratio
do.Describe alternatives you've considered
What other solutions, features, or workarounds have you considered that might also solve the issue? What are the tradeoffs for these alternatives compared to what you're proposing?
Additional context
https://github.com/twitter/cache-trace http://iotta.snia.org/traces/parallel/27476