This topic describes the performance test results of a general-purpose ApsaraDB for RDS instance that runs MySQL 5.6.

Scenario 1: All the data that you query is hit in the cache.

Set the table_size parameter to 25000 and the tables parameter to 250 in SysBench.

Scenario 1 based on ApsaraDB RDS for MySQL 5.6
CPU

(Number of cores)

Memory

(GB)

Maximum number of connections IOPS Number of SysBench threads SysBench QPS SysBench TPS
1 1 300 600 8 638.25 31.91
1 2 600 1,000 8 1774.43 88.72
2 4 1,200 2,000 8 18561.51 928.08
2 8 2,000 4,000 8 18672.65 933.63
4 8 2,000 5,000 16 47272.72 2363.64
4 16 4,000 7,000 16 48104.96 2405.25
8 16 4,000 8,000 32 71899.12 3594.96
8 32 8,000 12,000 32 73847.17 3692.36
16 64 16,000 14,000 64 107670.53 5383.53
16 96 24,000 16,000 64 108473.73 5423.69

Scenario 2: Only some data that you query is hit in the cache, and the RDS instance needs to read and write data to disks and update the cache to complete queries.

Set the table_size parameter to 800000 and the tables parameter to 150 in SysBench.

Scenario 2 based on ApsaraDB RDS for MySQL 5.6
CPU

(Number of cores)

Memory

(GB)

Maximum number of connections IOPS Number of SysBench threads SysBench QPS SysBench TPS
1 1 300 600 64 395.41 19.77
1 2 600 1,000 64 682.55 34.13
2 4 1,200 2,000 64 1477.06 73.85
2 8 2,000 4,000 64 3395.79 169.79
4 8 2,000 5,000 64 4245.29 212.26
4 16 4,000 7,000 64 7759.08 387.95
8 16 4,000 8,000 64 8865.62 443.28
8 32 8,000 12,000 64 28084.63 1404.23
16 64 16,000 14,000 64 97350.85 4867.54
16 96 24,000 16,000 64 98914.56 4945.73