Skip to main content

Benchmark Sysbench

These benchmark results show how the supported database engines perform across compute configurations, so you have a starting point when choosing an instance size.

warning

These figures are reference data, not a performance guarantee. Your throughput depends on your workload, schema, indexing, read/write ratio, and storage and network configuration. Test with your own workload before committing to a configuration in production.

What was measured

The benchmark evaluates OLTP read and write performance, shows how throughput scales as CPU and memory increase, and gives comparable numbers across flavors.

Engines covered: PostgreSQL, MySQL, MariaDB, MongoDB, and Redis.

MetricMeaning
Sysbench ReadTotal read queries executed during the test.
Sysbench WriteTotal write queries executed during the test.
QPS (Queries Per Second)Average queries processed per second.
TPS (Transactions Per Second)Average completed transactions per second.

Higher QPS and TPS mean higher throughput under the tested workload.

PostgreSQL

Test environment

ParameterValue
Benchmark toolSysbench (OLTP Read/Write)
Number of tables64
Rows per table1,000,000
Workload typeRead/Write
Thread countConfigured per instance size
PostgreSQL versionPostgreSQL 17

Results

Flavor (vCPU/RAM)ThreadsSysbench ReadSysbench WriteQPSTPS
2C4G642,595,600741,5906,177.66308.88
2C8G642,481,276708,9295,905.53295.27
4C8G643,189,018911,1347,589.71379.48
8C16G644,829,2861,379,73811,496.20574.79
8C32G645,679,8421,622,73213,519.46675.94
16C32G646,448,0361,842,19915,350.46767.49
16C64G646,926,9481,979,03116,489.02824.41

MySQL

Test environment

ParameterValue
Benchmark toolSysbench (OLTP Read/Write)
Number of tables64
Rows per table1,000,000
Workload typeRead/Write
Thread countConfigured per instance size
MySQL versionMySQL 8.0.42

Results

Flavor (vCPU/RAM)ThreadsSysbench ReadSysbench WriteQPSTPS
4C8G166,814,5001,947,00016,224.39811.22
8C16G329,748,1442,785,18423,209.291,160.46
8C32G329,423,8342,692,52422,430.671,121.53
16C32G649,786,2382,796,06823,289.481,164.47

MariaDB

Test environment

ParameterValue
Benchmark toolSysbench (OLTP Read/Write)
Number of tables64
Rows per table1,000,000
Workload typeRead/Write
Thread countConfigured per instance size
MariaDB versionMariaDB 10.6

Results

Flavor (vCPU/RAM)ThreadsSysbench ReadSysbench WriteQPSTPS
4C8G1610,573,5142,111,34125,174.341,258.72
8C16G328,923,2362,094,62821,245.251,062.26
8C32G328,491,1822,086,38820,216.521,010.83
16C32G6410,267,2082,568,03224,444.581,222.23
16C64G6410,789,8842,719,24125,688.301,284.42

MongoDB

Test environment

ParameterValue
Benchmark toolSysbench (OLTP Read/Write)
Number of documents1,000,000
Number of operations1,000,000
Workload typeRead/Write
Thread count (YCSB threads)Configured per instance size
MongoDB versionMongoDB 6.0.6

Results

Flavor (vCPU/RAM)ThreadsSysbench ReadSysbench WriteQPSTPS
2C4G8500,195499,8053,372.363,372.36
2C8G8500,022499,9784,004.934,004.93
4C8G16499,772500,2285,023.815,023.81
8C16G32500,293499,7076,417.546,417.54
8C32G32500,372499,6285,921.645,921.64
16C32G64499,865500,1358,532.798,532.79
16C64G64499,989500,01112,972.0212,972.02

Redis

Test environment

ParameterValue
Benchmark toolSysbench (OLTP Read/Write)
Number of keys1,000,000
Workload typeRead/Write
Redis versionRedis 7.2.1

Results

Flavor (vCPU/RAM)Sysbench ReadSysbench WriteTotal QPSP99 latencyAVG latency
2C4G68,60029,40598,005.2528.933.10
2C8G68,34629,29697,641.6130.853.92
4C8G67,94829,12697,074.2635.336.77
8C16G68,65529,42898,083.0328.033.41
8C32G67,81129,06796,878.2935.845.77
16C32G67,96429,13297,096.0733.544.89
16C64G68,32929,28997,617.7331.744.42

How to read these numbers

Adding CPU and memory generally raises throughput, but each engine scales differently and the gains flatten out at higher configurations depending on the workload and system limits.

Use the tables to narrow your choice to two or three candidate flavors, then validate with your own application. The workload shape matters more than the flavor once you are past the obvious undersizing.

Next steps