monitor_ob.yaml 11.7 KB
Newer Older
W
wangzelin.wzl 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92
obInputBasic: &obInputBasic
  plugin: mysqlTableInput
  config:
    timeout: 10s
    pluginConfig:
      maintainCacheThreads: 4
      connection:
        url: ${monagent.ob.monitor.user}:${monagent.ob.monitor.password}@tcp(127.0.0.1:${monagent.ob.sql.port})/oceanbase?interpolateParams=true
        maxIdle: 2
        maxOpen: 32
      defaultConditionValues:
        ob_svr_ip: ${monagent.host.ip}
        ob_svr_port: ${monagent.ob.rpc.port}
        ob_is_rootservice: true
      collectConfig:
        - sql: select /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) */ tenant_name, cache_name, cache_size from __all_virtual_kvcache_info, __all_tenant where __all_tenant.tenant_id = __all_virtual_kvcache_info.tenant_id and svr_ip = ? and svr_port = ?
          params: [ob_svr_ip, ob_svr_port]
          name: ob_cache
          tags:
            tenant_name: tenant_name
            cache_name: cache_name
          metrics:
            size_bytes: cache_size
        - sql: select /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) */ tenant_name, tenant_id, stat_id, value from v$sysstat, __all_tenant where stat_id IN (10000, 10001, 10002, 10003, 10005, 10006, 140002, 140003, 140005, 140006, 60019, 60020, 60024, 80040, 80041, 130000, 130001, 130002, 130004, 20001, 20002, 30000, 30001, 30002, 30005, 30006, 40000, 40001, 40002, 40003, 40004, 40005, 40006, 40007, 40008, 40009, 40010, 40011, 40012, 50000, 50001, 50008, 50009, 60000, 60001, 60002, 60003, 60004, 60005, 60019, 60020, 60021, 60022, 60023, 60024, 80057) and (con_id > 1000 or con_id = 1) and __all_tenant.tenant_id = v$sysstat.con_id and class < 1000
          name: ob_sysstat
          tags:
            tenant_name: tenant_name
            tenant_id: tenant_id
            stat_id: stat_id
          metrics:
            value: value
        - sql: select /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) QUERY_TIMEOUT(100000000) */ tenant_name, 1 as role, case when cnt is null then 0 else cnt end as cnt from (select __all_tenant.tenant_name, t1.cnt from __all_tenant left join (select tenant_id, count(*) as cnt from __all_virtual_partition_info where svr_ip = ? and svr_port = ? group by tenant_id) t1 on __all_tenant.tenant_id = t1.tenant_id) t2
          params: [ob_svr_ip, ob_svr_port]
          name: ob_partition
          tags:
            tenant_name: tenant_name
            role: role
          metrics:
            num: cnt
          enableCache: true
          cacheExpire: 1h
          cacheDataExpire: 2h
        - sql: select /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) */ group_concat(svr_ip SEPARATOR ',') as servers, status, count(1) as cnt from __all_server group by status
          name: ob_server
          tags:
            server_ips: servers
            status: status
          metrics:
            num: cnt
          enableCache: true
          cacheExpire: 60s
          cacheDataExpire: 120s
        - sql: select /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) QUERY_TIMEOUT(100000000)  */ tenant_name, count(*)  as cnt from gv$table group by tenant_id
          name: ob_table
          condition: ob_is_rootservice
          tags:
            tenant_name: tenant_name
          metrics:
            num: cnt
          enableCache: true
          cacheExpire: 1h
          cacheDataExpire: 2h
        - sql: select  /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) */ case when cnt is null then 0 else cnt end as cnt, tenant_name from (select __all_tenant.tenant_name, cnt from __all_tenant left join (select count(*) as cnt, tenant as tenant_name from __all_virtual_processlist where svr_ip = ? and svr_port = ? group by tenant) t1 on __all_tenant.tenant_name = t1.tenant_name) t2
          params: [ob_svr_ip, ob_svr_port]
          name: ob_active_session
          tags:
            tenant_name: tenant_name
          metrics:
            num: cnt
        - sql: select /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) */ zone, name, value, time_to_usec(now()) as current from __all_zone
          name: ob_zone
          tags:
            zone: zone
            name: name
          metrics:
            stat: value
            current_timestamp: current
        - sql: select /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) */ tenant_name, mem_used, access_count, hit_count from v$plan_cache_stat join __all_tenant on v$plan_cache_stat.tenant_id = __all_tenant.tenant_id
          name: ob_plan_cache
          tags:
            tenant_name: tenant_name
          metrics:
            memory_bytes: mem_used
            access_total: access_count
            hit_total: hit_count
        - sql: select /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) */ tenant_name, sum(total_waits) as total_waits, sum(time_waited_micro) / 1000000 as time_waited from v$system_event join __all_tenant on v$system_event.con_id = __all_tenant.tenant_id where v$system_event.wait_class <> 'IDLE' group by tenant_name
          name: ob_waitevent
          tags:
            tenant_name: tenant_name
          metrics:
            wait_total: total_waits
            wait_seconds_total: time_waited
W
wangzelin.wzl 已提交
93 94 95 96 97 98 99 100
        - sql: select /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) */ tenant_name, response_time / 1000000 as response_time, count, total from __all_virtual_query_response_time join __all_tenant on __all_virtual_query_response_time.tenant_id = __all_tenant.tenant_id
          name: ob_query_response_time
          tags:
            tenant_name: tenant_name
            le: response_time
          metrics:
            count: count
            total: total
W
wangzelin.wzl 已提交
101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253

obInputExtra: &obInputExtra
  plugin: mysqlTableInput
  config:
    timeout: 10s
    pluginConfig:
      maintainCacheThreads: 4
      connection:
        url: ${monagent.ob.monitor.user}:${monagent.ob.monitor.password}@tcp(127.0.0.1:${monagent.ob.sql.port})/oceanbase?interpolateParams=true
        maxIdle: 2
        maxOpen: 32
      defaultConditionValues:
        ob_svr_ip: ${monagent.host.ip}
        ob_svr_port: ${monagent.ob.rpc.port}
        ob_is_rootservice: true
      collectConfig:
        - sql: select /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) */ count(*) as cnt from v$unit
          name: ob_unit
          metrics:
            num: cnt
        - sql: select /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) */ total_size, free_size from __all_virtual_disk_stat where svr_ip = ? and svr_port = ?
          params: [ob_svr_ip, ob_svr_port]
          name: ob_disk
          metrics:
            total_bytes: total_size
            free_bytes: free_size
          enableCache: true
          cacheExpire: 1h
          cacheDataExpire: 2h
        - sql: select /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) */ cpu_total,cpu_assigned,mem_total,mem_assigned,disk_total,disk_assigned,unit_num,migrating_unit_num,cpu_assigned_percent, mem_assigned_percent, disk_assigned_percent from __all_virtual_server_stat where svr_ip = ? and svr_port = ?
          params: [ob_svr_ip, ob_svr_port]
          name: ob_server_resource
          metrics:
            cpu: cpu_total
            cpu_assigned: cpu_assigned
            memory_bytes: mem_total
            memory_assigned_bytes: mem_assigned
            disk_bytes: disk_total
            disk_assigned_bytes: disk_assigned
            unit_num: unit_num
            migrating_unit_num: migrating_unit_num
            cpu_assigned_percent: cpu_assigned_percent
            memory_assigned_percent: mem_assigned_percent
            disk_assigned_percent: disk_assigned_percent
          enableCache: true
          cacheExpire: 60s
          cacheDataExpire: 120s
        - sql: select /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) */ count(1) as cnt from __all_virtual_trans_stat where part_trans_action > 2 and ctx_create_time < date_sub(now(), interval 600 second) and svr_ip = ? and svr_port = ?
          params: [ob_svr_ip, ob_svr_port]
          name: ob_trans
          condition: ob_is_rootservice
          metrics:
            expire_num: cnt
        - sql: select /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) QUERY_TIMEOUT(100000000)  */ count(*) as cnt from gv$table where table_type in (5) and index_status in (5, 6)
          name: ob_index
          condition: ob_is_rootservice
          metrics:
            error_num: cnt
        - sql: select /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) */ __all_tenant.tenant_name,  active, total, freeze_trigger, freeze_cnt from gv$memstore, __all_tenant  where gv$memstore.tenant_id = __all_tenant.tenant_id and ip = ? and port = ?
          params: [ob_svr_ip, ob_svr_port]
          name: ob_memstore
          tags:
            tenant_name: tenant_name
          metrics:
            active_bytes: active
            total_bytes: total
            freeze_trigger_bytes: freeze_trigger
            freeze_times: freeze_cnt
        - sql: select /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) */ sum(hold) as hold, sum(used) as used from __all_virtual_memory_info where tenant_id = 500 and svr_ip = ? and svr_port = ?
          params: [ob_svr_ip, ob_svr_port]
          name: ob_tenant500_memory
          metrics:
            hold_bytes: hold
            used_bytes: used
        - sql: select /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) */ tenant_name, __all_unit_config.name, max_cpu, min_cpu, max_memory, min_memory, max_iops, min_iops, max_disk_size, max_session_num from __all_tenant, __all_resource_pool, __all_unit_config, __all_unit  where __all_tenant.tenant_id = __all_resource_pool.tenant_id and __all_resource_pool.unit_config_id = __all_unit_config.unit_config_id and __all_unit.resource_pool_id = __all_resource_pool.resource_pool_id and __all_unit.svr_ip = ? and __all_unit.svr_port = ?
          params: [ob_svr_ip, ob_svr_port]
          name: ob_unit_config
          tags:
            tenant_name: tenant_name
            unit_config_name: name
          metrics:
            max_cpu: max_cpu
            min_cpu: min_cpu
            max_memory_bytes: max_memory
            min_memory_bytes: min_memory
            max_iops: max_iops
            min_iops: min_iops
            max_disk_size_bytes: max_disk_size
            max_session_num: max_session_num
        - sql: select /*+ MONITOR_AGENT READ_CONSISTENCY(WEAK) */ tenant_name, tenant_id, name, gets, misses, sleeps, immediate_gets, immediate_misses, spin_gets, wait_time / 1000000 as wait_time from v$latch, __all_tenant where __all_tenant.tenant_id = v$latch.con_id
          name: ob_latch
          tags:
            tenant_name: tenant_name
            tenant_id: tenant_id
            name: name
          metrics:
            get_total: gets
            miss_total: misses
            sleep_total: sleeps
            immediate_get_total: immediate_gets
            immediate_miss_total: immediate_misses
            spin_get_total: spin_gets
            wait_seconds_total: wait_time

retagProcessor: &retagProcessor
  plugin: retagProcessor
  config:
    timout: 10s
    pluginConfig:
      newTags:
        app: OB
        obzone: ${monagent.ob.zone.name}
        svr_ip: ${monagent.host.ip}
        ob_cluster_id: ${monagent.ob.cluster.id}
        ob_cluster_name: ${monagent.ob.cluster.name}

prometheusExporter: &prometheusExporter
  plugin: prometheusExporter
  config:
    timout: 10s
    pluginConfig:
      formatType: fmtText

modules:
  - module: monitor.ob
    moduleType: monagent.pipeline
    process: monagent
    config:
      name: monitor.ob
      status: ${monagent.pipeline.ob.status}
      pipelines:
        - name: ob_basic
          config:
            scheduleStrategy: trigger
            exposeUrl: /metrics/ob/basic
          structure:
            inputs:
              - <<: *obInputBasic
            processors:
              - <<: *retagProcessor
            exporter:
              <<: *prometheusExporter
        - name: ob_extra
          config:
            scheduleStrategy: trigger
            exposeUrl: /metrics/ob/extra
          structure:
            inputs:
              - <<: *obInputExtra
            processors:
              - <<: *retagProcessor
            exporter:
              <<: *prometheusExporter