All Products
Search
Document Center

ApsaraDB RDS:Performance parameters

Last Updated:Nov 28, 2023

This topic describes the performance parameters of ApsaraDB RDS.

ApsaraDB RDS for MySQL and ApsaraDB RDS for MariaDB

Note

ApsaraDB RDS for MySQL and ApsaraDB RDS for MariaDB use the same parameters.

Parameter

Description

MySQL_NetworkTraffic

The average volume of inbound traffic to the RDS instance per second and the average volume of outbound traffic from the RDS instance per second. Unit: KB/s.

MySQL_QPSTPS

The average number of SQL statements executed per second and the average number of transactions executed per second.

MySQL_Sessions

The number of active connections and the total number of connections. Unit: counts.

MySQL_InnoDBBufferRatio

The read hit ratio, usage, and dirty ratio of the InnoDB buffer pool. Unit: %.

MySQL_InnoDBDataReadWriten

The average volume of data that InnoDB reads per second and the average volume of data that InnoDB writes per second. Unit: KB.

MySQL_InnoDBLogRequests

The average number of reads from the InnoDB buffer pool per second and the average number of writes to the InnoDB buffer pool per second. Unit: counts/s.

MySQL_InnoDBLogWrites

The average number of log write requests per second, the average number of physical writes to log files per second, and the average number of writes performed by calling the fsync() function to log files per second. Unit: counts/s.

MySQL_TempDiskTableCreates

The number of temporary tables that are automatically created on the hard disk during statement execution. Unit: tables.

MySQL_MyISAMKeyBufferRatio

The average usage, read hit ratio, and write hit ratio of the MyISAM key buffer per second. Unit: %.

MySQL_MyISAMKeyReadWrites

The average number of reads from the buffer pool by MyISAM per second, the average number of writes to the buffer pool by MyISAM per second, the average number of reads from the hard disk by MyISAM per second, and the average number of writes to the hard disk by MyISAM per second. Unit: counts/s.

MySQL_COMDML

The average number of DELETE statements executed per second, the average number of INSERT statements executed per second, the average number of INSERT_SELECT statements executed per second, the average number of REPLACE statements executed per second, the average number of REPLACE_SELECT statements executed per second, the average number of SELECT statements executed per second, and the average number of UPDATE statements executed per second. Unit: counts/s.

MySQL_RowDML

The average number of rows read from InnoDB tables per second, the average number of rows updated in InnoDB tables per second, the average number of rows deleted from InnoDB tables per second, the average number of rows inserted into InnoDB tables per second, and the average number of physical writes to log files per second. Unit: row/s or count/s.

MySQL_MemCpuUsage

The CPU utilization and memory usage of the non-serverless ApsaraDB RDS for MySQL instance within the entire operating system. Unit: %.

MySQL_RCU_MemCpuUsage

The CPU utilization and memory usage of the serverless ApsaraDB RDS for MySQL instance within the entire operating system. Unit: %.

MySQL_IOPS

The input/output operations per second (IOPS) of the RDS instance. Unit: counts/s.

MySQL_DetailedSpaceUsage

The details about the disk usage of the RDS instance. These details include the total amount of disk space occupied by the RDS instance, the amount of disk space occupied by data files, the amount of disk space occupied by log files, the amount of disk space occupied by temporary files, and the amount of disk space occupied by system files. Unit: MB.

slavestat

The latency of data replication to the read-only RDS instance of the RDS instance. Unit: seconds.

MySQL_ThreadStatus

The number of active threads and the number of threads connected. Unit: counts.

MySQL_ReplicationDelay

The latency of data replication to the secondary RDS instance of the RDS instance. Unit: seconds.

MySQL_ReplicationThread

The status of the I/O thread and the status of the SQL thread. The value 1 indicates that the thread is normal, and the value 0 indicates that the thread is lost.

MySQL_ROW_LOCK

The maximum time of a row-level lock that has been waited for in milliseconds, the average time of row-level locks that have been waited for in milliseconds, and the number of times the row-level locks have been waited for.

MySQL_SelectScan

The number of times that full table scans are performed on the RDS instance. Unit: scans.

ApsaraDB RDS for SQL Server

Parameter

Description

SQLServer_Transactions

The average number of transactions per second. Unit: counts/s.

SQLServer_Sessions

The total number of connections. Unit: counts.

SQLServer_BufferHit

The cache hit ratio. Unit: %.

SQLServer_FullScans

The average number of full table scans per second. Unit: counts/s.

SQLServer_SQLCompilations

The number of SQL statement compilations per second. Unit: counts/s.

SQLServer_CheckPoint

The number of checkpoints written to pages per second. Unit: counts/s.

SQLServer_Logins

The number of logons per second. Unit: counts/s.

SQLServer_LockTimeout

The number of lock timeouts per second. Unit: counts/s.

SQLServer_Deadlock

The number of deadlocks per second. Unit: counts/s.

SQLServer_LockWaits

The number of locks that have been waited for per second. Unit: counts/s.

SQLServer_NetworkTraffic

The average volume of inbound traffic to the RDS instance per second and the average volume of outbound traffic from the RDS instance per second. Unit: KB/s.

SQLServer_QPS

The average number of SQL statements executed per second. Unit: counts/s.

SQLServer_InstanceCPUUsage

The CPU utilization of the RDS instance within the operating system. Unit: %.

SQLServer_IOPS

The IOPS of the RDS instance. Unit: counts/s.

SQLServer_DetailedSpaceUsage

The disk usage of the RDS instance. Unit: MB.

ApsaraDB RDS for PostgreSQL

Note

ApsaraDB RDS for PostgreSQL allows you to view more fine-grained enhanced monitoring metrics in the ApsaraDB RDS console. For more information, see View the Enhanced Monitoring metrics. The following table shows the mapping between the values of parameters in the DescribeDBInstancePerformance operation and the enhanced monitoring metrics.

Parameter

Description

Enhanced monitoring metric

MemoryUsage

The memory usage. Unit: %.

os.mem_usage.total.avg

CpuUsage

The CPU utilization. Unit: %.

os.cpu_usage.total.avg

PgSQL_SpaceUsage

The disk usage of the RDS instance. Unit: bytes.

os.fs_size.wal_dir.avg + os.fs_size.base_dir.avg Unit: MB

PgSQL_IOPS

The IOPS of the RDS instance. Unit: counts/s.

(os.iops.data.avg+os.iops.wal.avg) / os.iops.total.avg * 100

PgSQL_Session

The total number of connections. Unit: counts.

db.connections.total.avg

PolarDBConnections

The following parameters are returned:

  • mean_active_session: the number of active connections.

  • mean_idle_connection: the number of idle connections.

  • mean_total_session: the total number of connections.

  • mean_waiting_connection: the number of connections in the waiting state.

  • db.connections.active.avg

  • db.connections.idle.avg

  • db.connections.total.avg

  • db.connections.waiting.avg

PolarDBRowDML

The following parameters are returned:

  • mean_tup_returned_delta: the number of rows returned per second by full table scans.

  • mean_tup_fetched_delta: the number of tables returned per second by index scans.

  • mean_tup_inserted_delta: the number of rows inserted per second.

  • mean_tup_updated_delta: the number of rows updated per second.

  • mean_tup_deleted_delta: the number of rows deleted per second.

  • db.sql.tup_returned.avg

  • db.sql.tup_fetched.avg

  • db.sql.tup_inserted.avg

  • db.sql.tup_updated.avg

  • db.sql.tup_deleted.avg

PolarDBQPSTPS

The following parameters are returned:

  • mean_commits_delta: the number of transactions committed per second.

  • mean_rollbacks_delta: the number of transactions rolled back per second.

  • mean_deadlocks_delta: the number of deadlocks triggered per second.

  • mean_tps: the number of transactions run per second.

  • db.transactions.xact_commit.avg

  • db.transactions.xact_rollback.avg

  • The enhanced monitoring feature does not collect the number of deadlocks per second.

  • db.transactions.xact_commit.avg+db.transactions.xact_rollback.avg

PolarDBSwellTime

The point in time before which the generated dead tuples can be recycled by the RDS instance. Unit: seconds.

db.swell.swell_time.avg

PolarDBCPU

The CPU utilization.

  • os.cpu_usage.sys.avg

  • os.cpu_usage.user.avg

  • os.cpu_usage.total.avg

PolarDBMemory

The memory usage.

os.mem_usage.total.avg

PolarDBReplication

The following parameters are returned:

  • mean_replay_latency_in_mb: the latency of data replication to the secondary RDS instance of the RDS instance. Unit: bytes.

  • mean_send_latency_in_mb: the latency of data replication from the RDS instance to its secondary RDS instance. Unit: bytes.

  • mean_logical_rep_latency_in_mb: the latency of logical replication. Unit: bytes.

/

PolarDBLongSQL

The following parameters are returned:

  • mean_one_second_executing_sqls: the number of SQL statements that take more than 1 second to execute.

  • mean_three_seconds_executing_sqls: the number of SQL statements that take more than 3 seconds to execute.

  • mean_five_seconds_executing_sqls: the number of SQL statements that take more than 5 seconds to execute.

  • db.slow_sql.one_second.avg

  • db.slow_sql.three_seconds.avg

  • db.slow_sql.five_seconds.avg

PolarDBLongIdleTransaction

The following parameters are returned:

  • mean_one_second_idle_transactions: the number of transactions that sit idle for more than 1 second.

  • mean_three_seconds_idle_transactions: the number of transactions that sit idle for more than 3 seconds.

  • mean_five_seconds_idle_transactions: the number of transactions that sit idle for more than 5 seconds.

  • db.long_transactions.idle_one_second.avg

  • db.long_transactions.idle_three_seconds

  • db.long_transactions.idle_five_seconds.avg

PolarDBLongTransaction

The following parameters are returned:

  • mean_one_second_transactions: the number of transactions that take more than 1 second to run.

  • mean_three_seconds_transactions: the number of transactions that take more than 3 seconds to run.

  • db.long_transactions.active_one_second.avg

  • db.long_transactions.active_three_seconds.avg

PolarDBLongTwoPCTransaction

The following parameters are returned:

  • mean_one_second_two_pc_transactions: the number of transactions that are committed in two phases and take more than 1 second to run.

  • mean_three_seconds_two_pc_transactions: the number of transactions that are committed in two phases and take more than 3 seconds to run.

  • mean_five_seconds_two_pc_transactions: the number of transactions that are committed in two phases and take more than 5 seconds to run.

  • db.long_transactions.two_pc_one_second.avg

  • db.long_transactions.two_pc_three_seconds.avg

  • db.long_transactions.two_pc_five_seconds.avg

PolarDBLocalIOSTAT

The following parameters are returned:

  • mean_local_iops_read: the number of reads from the data disk per second.

  • mean_local_iops_write: the number of writes to the data disk per second.

  • os.iops.read.avg

  • os.iops.write.avg

PolarDBLocalDiskUsage

The following parameters are returned:

  • mean_local_pg_wal_dir_size: the amount of disk space occupied by write-ahead log (WAL) files. Unit: MB.

  • mean_local_pg_log_dir_size: the amount of disk space occupied by log files. Unit: MB.

  • mean_local_base_dir_size: the amount of disk space occupied by data files. Unit: MB.

  • os.fs_size.wal_dir.avg

  • os.fs_size.log_dir.avg

  • os.fs_size.base_dir.avg

What to do next