Prometheus监控下的MySQL告警规则

groups:

- name: MySQLStatsAlert

rules:

- alert: MySQL is down

expr: mysql_up == 0

for: 1m

labels:

severity: critical

annotations:

summary: "Instance {{ $labels.instance }} MySQL is down"

description: "MySQL database is down. This requires immediate action!"

- alert: open files is high

expr: mysql_global_status_innodb_num_open_files > (mysql_global_variables_open_files_limit) * 0.75

for: 1m

labels:

severity: warning

annotations:

summary: "Instance {{ $labels.instance }} open files high"

description: "Open files is high. Please consider increasing open_files_limit."

- alert: Read buffer size is bigger than max. allowed packet size

expr: mysql_global_variables_read_buffer_size > mysql_global_variables_slave_max_allowed_packet

for: 1m

labels:

severity: warning

annotations:

summary: "Instance {{ $labels.instance }} Read buffer size is bigger than max. allowed packet size"

description: "Read buffer size (read_buffer_size) is bigger than max. allowed packet size (max_allowed_packet).This can break your replication."

- alert: Thread stack size is too small

expr: mysql_global_variables_thread_stack <196608

for: 1m

labels:

severity: warning

annotations:

summary: "Instance {{ $labels.instance }} Thread stack size is too small"

description: "Thread stack size is too small. This can cause problems when you use Stored Language constructs for example. A typical is 256k for thread_stack_size."

- alert: Used more than 80% of max connections is limited

expr: mysql_global_status_max_used_connections > mysql_global_variables_max_connections * 0.8

for: 1m

labels:

severity: warning

annotations:

summary: "Instance {{ $labels.instance }} Used more than 80% of max connections limited"

description: "Used more than 80% of max connections limited"

- alert: Table open cache too small

expr: mysql_global_status_open_tables >mysql_global_variables_table_open_cache * 99/100

for: 1m

labels:

severity: page

annotations:

summary: "Instance {{ $labels.instance }} Table open cache too small"

description: "Your Table Open Cache is possibly too small (old name Table Cache). If it is much too small this can have significant performance impacts!"

- alert: Thread stack size is possibly too small

expr: mysql_global_variables_thread_stack < 262144

for: 1m

labels:

severity: page

annotations:

summary: "Instance {{ $labels.instance }} Thread stack size is possibly too small"

description: "Thread stack size is possibly too small. This can cause problems when you use Stored Language constructs for example. A typical is 256k for thread_stack_size."

- alert: InnoDB Buffer Pool Instances is too small

expr: mysql_global_variables_innodb_buffer_pool_instances == 1

for: 1m

labels:

severity: page

annotations:

summary: "Instance {{ $labels.instance }} InnoDB Buffer Pool Instances is too small"

description: "If you are using MySQL 5.5 and higher you should use several InnoDB Buffer Pool Instances for performance reasons. Some rules are: InnoDB Buffer Pool Instance should be at least 1 Gbyte in size. InnoDB Buffer Pool Instances you can set equal to the number of cores of your machine."

- alert: Binlog Statement Cache size too small

expr: mysql_global_variables_binlog_stmt_cache_size <1048576 and mysql_global_variables_binlog_stmt_cache_size > 0

for: 1m

labels:

severity: page

annotations:

summary: "Instance {{ $labels.instance }} Binlog Statement Cache size too small"

description: "Binlog Statement Cache size is possibly to small. A value of 1 Mbyte or higher is typically OK."

- alert: IO thread stopped

expr: mysql_slave_status_slave_io_running != 1

for: 1m

labels:

severity: critical

annotations:

summary: "Instance {{ $labels.instance }} IO thread stopped"

description: "IO thread has stopped. This is usually because it cannot connect to the Master any more."

- alert: SQL thread stopped

expr: mysql_slave_status_slave_sql_running == 0

for: 1m

labels:

severity: critical

annotations:

summary: "Instance {{ $labels.instance }} SQL thread stopped"

description: "SQL thread has stopped. This is usually because it cannot apply a SQL statement received from the master."