Latency
Our approach to SQL performance benchmarking is to use sysbench, an industry standard benchmarking tool. We also benchmark Dolt using TPC-C, an industry standard transactional throughput metric.
Performance Roadmap
Dolt is slightly faster than MySQL on the sysbench test suite, approximately 10% faster on writes and 5% slower on reads. The multiple column represents this relationship with regard to a particular benchmark.
Dolt gets about 40% of the transactional throughput on TPC-C than MySQL, 40 transactions per second versus about 100 for MySQL. Most applications are not sensitive to transactional throughput beyond a handful per second.
It's important recognize that these are industry standard tests, and are OLTP-oriented. Performance results may vary but Dolt is generally competitive on latency with MySQL and Postgres.
Benchmark Data
Below are the results of running sysbench MySQL tests against Dolt SQL Server for the most recent release of Dolt in the current default storage format. We will update this with every release. The tests attempt to run as many queries as possible in a fixed 2 minute time window. The Dolt and MySQL columns show the median latency in milliseconds (ms) of each query during that 2 minute time window.
The Dolt version is 1.78.8.
covering_index_scan
1.86
0.55
0.3
groupby_scan
13.7
12.08
0.88
index_join
1.52
1.96
1.29
index_join_scan
1.47
1.34
0.91
index_scan
35.59
22.28
0.63
oltp_point_select
0.2
0.28
1.4
oltp_read_only
3.82
5.28
1.38
select_random_points
0.35
0.58
1.66
select_random_ranges
0.39
0.57
1.46
table_scan
35.59
27.66
0.78
types_table_scan
80.03
65.65
0.82
reads_mean_multiplier
1.05
oltp_delete_insert
8.43
6.55
0.78
oltp_insert
4.18
3.19
0.76
oltp_read_write
9.22
11.65
1.26
oltp_update_index
4.18
3.25
0.78
oltp_update_non_index
4.25
3.19
0.75
oltp_write_only
5.28
6.32
1.2
types_delete_insert
8.58
6.91
0.81
writes_mean_multiplier
0.91
tpcc-scale-factor-1
93.62
36.19
2.59
tpcc_tps_multiplier
2.59
Overall Mean Multiple
1.52
Last updated
Was this helpful?