tencent cloud

Feedback

Test Results

Last updated: 2024-08-09 15:24:42
    This document will verify the performance data of TencentDB for PostgreSQL in write-only, read-only and read-write scenarios of Sysbench.

    Scenario 1: Full Cache

    In the full cache scenario, all data can be stored in the cache, so there is no need to read or write the disk to update the cache during the query process.

    Write-only

    Instance specifications
    Concurrency
    Single-table data size (table_size)
    Total number of tables (tables)
    QPS
    TPS
    1-core 2 GB memory
    32
    25000
    64
    21308.50
    3551.41
    4-core 16 GB memory
    32
    25000
    64
    139100.86
    23183.37
    8-core 32 GB memory
    64
    25000
    64
    219394.80
    36565.50
    48-core 480 GB memory
    512
    25000
    256
    357198.25
    59531.89

    Read-only

    Instance specifications
    Concurrency
    Single-table data size (table_size)
    Total number of tables (tables)
    QPS
    TPS
    1-core 2 GB memory
    32
    25000
    64
    26327.01
    1645.44
    4-core 16 GB memory
    32
    25000
    64
    111475.78
    6967.24
    8-core 32 GB memory
    64
    25000
    64
    179257.13
    11203.57
    48-core 480 GB memory
    512
    25000
    256
    346572.52
    21660.78

    Read-write

    Instance specifications
    Concurrency
    Single-table data size (table_size)
    Total number of tables (tables)
    QPS
    TPS
    1-core 2 GB memory
    32
    25000
    64
    17282.27
    864.11
    4-core 16 GB memory
    32
    25000
    64
    80646.27
    4032.31
    8-core 32 GB memory
    64
    25000
    64
    115549.05
    5777.44
    48-core 480 GB memory
    256
    25000
    256
    173502.17
    8675.04

    Scenario 2: Big Dataset

    In the big dataset scenario, all data cannot be stored in the cache (the data size is more than twice the memory size), so the disk needs to be read and written to update the cache during the query process.

    Write-only

    Instance specifications
    Concurrency
    Single-table data size (table_size)
    Total number of tables (tables)
    QPS
    TPS
    1-core 2 GB memory
    32
    10000000
    64
    16973.36
    2828.89
    4-core 16 GB memory
    32
    10000000
    64
    64245.25
    10707.54
    8-core 32 GB memory
    64
    10000000
    64
    100686.77
    16781.13
    48-core 480 GB memory
    256
    10000000
    640
    125237.97
    20873.00

    Read-only

    Instance specifications
    Concurrency
    Single-table data size (table_size)
    Total number of tables (tables)
    QPS
    TPS
    1-core 2 GB memory
    32
    10000000
    64
    14407.49
    900.47
    4-core 16 GB memory
    32
    10000000
    64
    58952.38
    3684.52
    8-core 32 GB memory
    64
    10000000
    64
    87727.56
    5482.97
    48-core 480 GB memory
    512
    10000000
    640
    137603.21
    8600.20

    Read-write

    Instance specifications
    Concurrency
    Single-table data size (table_size)
    Total number of tables (tables)
    QPS
    TPS
    1-core 2 GB memory
    32
    10000000
    64
    13655.23
    682.76
    4-core 16 GB memory
    32
    10000000
    64
    58426.87
    2921.34
    8-core 32 GB memory
    64
    10000000
    64
    80741.40
    4037.07
    48-core 480 GB memory
    256
    10000000
    640
    114922.98
    5746.15
    Contact Us

    Contact our sales team or business advisors to help your business.

    Technical Support

    Open a ticket if you're looking for further assistance. Our Ticket is 7x24 avaliable.

    7x24 Phone Support