During my setup of benchmarking I run a quick test-sysbench script to ensure my configuration is right before running an hour+ duration test.
When pointing to a Readyset cache where I have cached the 5 queries used in the sysbench test, but I have not run any execution of the SQL, throughput went up 10x in 5 seconds.
$ sysbench --config-file=readyset.cnf --report-interval=1 --histogram=1 --threads=4 core.lua --type=title run
[ 1s ] thds: 4 tps: 896.02 qps: 4495.06 (r/w/o: 4495.06/0.00/0.00) lat (ms,95%): 11.65 err/s: 0.00 reconn/s: 0.00
[ 2s ] thds: 4 tps: 4545.69 qps: 22719.47 (r/w/o: 22719.47/0.00/0.00) lat (ms,95%): 3.30 err/s: 0.00 reconn/s: 0.00
[ 3s ] thds: 4 tps: 8816.92 qps: 44082.59 (r/w/o: 44082.59/0.00/0.00) lat (ms,95%): 0.52 err/s: 0.00 reconn/s: 0.00
[ 4s ] thds: 4 tps: 8933.11 qps: 44672.57 (r/w/o: 44672.57/0.00/0.00) lat (ms,95%): 0.51 err/s: 0.00 reconn/s: 0.00
[ 5s ] thds: 4 tps: 8883.88 qps: 44415.38 (r/w/o: 44415.38/0.00/0.00) lat (ms,95%): 0.51 err/s: 0.00 reconn/s: 0.00
Answer: < 5 seconds.
