Flink问题解决及性能调优-【Flink根据不同场景状态后端使用调优】

Flink 实时groupby聚合场景操作时，由于使用的是rocksdb状态后端，发现CPU的高负载卡在rocksdb的读写上，导致上游算子背压特别大。通过调优使用hashmap状态后端代替rocksdb状态后端，使吞吐量有了质的飞跃（20倍的性能提升），并分析整理。

实例代码

--SET table.exec.state.ttl=86400s; --24 hour,默认: 0 ms
SET table.exec.state.ttl=2592000s; --30 days,默认: 0 ms

CREATE TABLE kafka_table (
     mid bigint,
     db string,
     sch string,
     tab string,
     opt string,
     ts bigint,
     ddl string,
     err string,
     src map<string,string>,
     cur map<string,string>,
     cus map<string,string>,
     account_id AS IF(cur['account_id'] IS NOT NULL , cur['account_id'], src ['account_id']),
     publish_time AS IF(cur['publish_time'] IS NOT NULL , cur['publish_time'], src ['publish_time']),
     msg_status AS IF(cur['msg_status'] IS NOT NULL , cur['msg_status'], src ['msg_status']),
     send_type AS IF(cur['send_type'] IS NOT NULL , cur['send_type'], src ['send_type'])
     --event_time as cast(IF(cur['update_time'] IS NOT NULL , cur['update_time'], src ['update_time']) AS TIMESTAMP(3)), -- TIMESTAMP(3)/TIMESTAMP_LTZ(3)
     --WATERMARK FOR event_time AS event_time - INTERVAL '1' MINUTE     --SECOND
) WITH (
  'connector' = 'kafka',
  'topic' = 't1',
  'properties.bootstrap.servers' = 'xx.xx.xx.xx:9092',
  'properties.group.id' = 'g1',
  'scan.startup.mode' = 'earliest-offset',  --group-offsets/earliest-offset/latest-offset
   --  'properties.enable.auto.commit',= 'true' -- default:false, 如果为false，则在发生checkpoint时触发offset提交
  'format' = 'json'
);



CREATE TABLE es_sink