Fibre Cache HIT benchmarks
every operation reads a resident key
Throughput in Mops/s: Operations completed per second across all workers over a 10 s run at capacity 10000. Measured on MacBook M4 Pro (14 cores).
The best result in each row is highlighted, leaving out quick_cache, which is a yardstick and is not ranked. Italics mean quick_cache is above the best ranked engine. A dash means the engine has no API for that mode.
sync
| Workers | fibre_cache.s3fifo | fibre_cache.tinylfu | moka | quick_cache | stretto |
|---|---|---|---|---|---|
| 1 | 44.40 | 23.64 | 12.39 | 166.44 | 23.77 |
| 8 | 108.22 | 37.55 | 6.42 | 94.76 | 4.27 |
async
| Workers | fibre_cache.s3fifo | fibre_cache.tinylfu | moka | quick_cache | stretto |
|---|---|---|---|---|---|
| 64 | 224.77 | 47.58 | 28.12 | 104.90 | 4.76 |
Hit ratio and peak entries
| Mode | Workers | fibre_cache.s3fifo | fibre_cache.tinylfu | moka | quick_cache | stretto |
|---|---|---|---|---|---|---|
| sync | 1 | 0.953 / 9531 | 0.955 / 9549 | 1.000 / 10000 | 0.963 / 9635 | 1.000 / 10000 |
| sync | 8 | 0.956 / 9565 | 0.956 / 9559 | 1.000 / 10000 | 0.963 / 9631 | 1.000 / 10000 |
| async | 64 | 0.954 / 9539 | 0.949 / 9494 | 1.000 / 10000 | 0.975 / 9748 | 1.000 / 10000 |
Hit ratio over the run, then the highest entry count the sampler saw against the capacity.