All Products
Search

This Product

    ApsaraDB RDS:Performance test on an ApsaraDB RDS instance that runs MySQL 5.6 and uses local disks

    Document Center

    ApsaraDB RDS:Performance test on an ApsaraDB RDS instance that runs MySQL 5.6 and uses local disks

    Last Updated:Nov 18, 2024

    This topic describes the performance test on an ApsaraDB RDS instance that runs MySQL 5.6 and uses a general-purpose instance type and local disks.

    Note

    Test environment

    In the stress testing, sysbench is used to test the performance of five RDS instances that use local disks. The RDS instances use different instance types.

    • Instance types: rds.mysql.s1.small, rds.mysql.s2.large, rds.mysql.m1.medium, rds.mysql.c1.xlarge, and rds.mysql.c2.xlarge

    • Instance family: general-purpose instance family

    • RDS edition: RDS High-availability Edition

    • Storage type: local disk

    Configurations

    The performance is significantly affected by the data volume, stress testing duration, and parameter settings. The following configurations are used for the stress testing:

    • Data volume: The data volume and the number of tables on each RDS instance that you want to test are different. Therefore, the test results for some of the five RDS instances may be similar.

    • Stress testing duration: The stress testing duration is 20 minutes for all RDS instances.

    • Parameter settings:

      • sync_binlog=1 and innodb_flush_log_at_trx_commit=1: ensure that the data submitted each time is completely written to disks.

      • rpl_semi_sync_master_enabled=ON: enables the semi-synchronous mode for an RDS instance to ensure data consistency between the primary and secondary RDS instances.

      • Performance_schema=OFF: automatically enables Performance Schema for an RDS instance that uses an instance type with a memory capacity greater than or equal to 64 GB.

        Note

        These parameter settings are contained in the standard parameter template for ApsaraDB RDS for MySQL. If the standard parameter template is applied to all the RDS instances, data consistency is maximized, and the test environment is more similar to the production environment.

    Test results

    Two types of queries are used to perform stress testing. You can determine the type of stress testing based on your data volume.

    • Stress testing for cache-based queries: This type of stress testing is suitable for scenarios in which a small amount of data is involved. You can store all data in the InnoDB buffer pool for access. For more information about how to change the size of the InnoDB buffer pool, see Change the size of the InnoDB buffer pool for an ApsaraDB RDS for MySQL instance.

    • Stress testing for disk I/O-based queries: This type of stress testing is suitable for scenarios in which a large amount of data is involved. You can store only the most frequently used data in the InnoDB buffer pool for access. During the stress testing, data is read from or written to disks, and the InnoDB buffer pool is updated.

    Type 1: Stress testing for cache-based queries

    image.png

    Instance type

    Data volume in a single table

    Number of tables

    Maximum number of connections

    IOPS

    Number of sysbench threads

    QPS

    TPS

    1 core, 2 GB

    (rds.mysql.s1.small)

    3,000,000

    1

    600

    1,000

    16

    12,761

    638

    2 cores, 4 GB

    (rds.mysql.s2.large)

    3,000,000

    2

    1200

    2,000

    16

    27,521

    1,306

    4 cores, 16 GB

    (rds.mysql.m1.medium)

    6,000,000

    4

    4,000

    7,000

    32

    59,185

    2,959

    8 cores, 32 GB

    (rds.mysql.c1.xlarge)

    6,000,000

    8

    8,000

    12,000

    32

    91,941

    4,597

    16 cores, 64 GB

    (rds.mysql.c2.xlarge)

    6,000,000

    16

    16,000

    14,000

    64

    129,953

    6,498

    Type 2: Stress testing for disk I/O-based queries

    image.png

    Instance type

    Data volume in a single table

    Number of tables

    Maximum number of connections

    IOPS

    Number of sysbench threads

    QPS

    TPS

    1 core, 2 GB

    (rds.mysql.s1.small)

    16,000,000

    1

    600

    1,000

    16

    1,087

    54

    2 cores, 4 GB

    (rds.mysql.s2.large)

    16,000,000

    2

    1,200

    2,000

    16

    2,382

    119

    4 cores, 16 GB

    (rds.mysql.m1.medium)

    32,000,000

    4

    4,000

    7,000

    32

    8,814

    441

    8 cores, 32 GB

    (rds.mysql.c1.xlarge)

    32,000,000

    8

    8,000

    12,000

    32

    15,195

    760

    16 cores, 64 GB

    (rds.mysql.c2.xlarge)

    32,000,000

    16

    16,000

    14,000

    32

    17,764

    888