Repository metrics
- Stars
- (24,849 stars)
- PR merge metrics
- (Avg merge 1d 1h) (4 merged PRs in 30d)
Description
1、服务端版本：3.2.3.0 3台48C126G物理机器的集群
2、创库语句
CREATE DATABASE taos_iot BUFFER 256 CACHESIZE 512 CACHEMODEL 'both' COMP 2 DURATION 14400m WAL_FSYNC_PERIOD 3000 MAXROWS 4096 MINROWS 100 STT_TRIGGER 1 KEEP 5256000m,5256000m,5256000m PAGES 256 PAGESIZE 4 PRECISION 'ms' REPLICA 3 WAL_LEVEL 1 VGROUPS 80 SINGLE_STABLE 0 TABLE_PREFIX 0 TABLE_SUFFIX 0 TSDB_PAGESIZE 4 WAL_RETENTION_PERIOD 3600 WAL_RETENTION_SIZE 0 KEEP_TIME_OFFSET 0
3、超级表
CREATE STABLE td_iot_data (report_time TIMESTAMP, dval DOUBLE, sval VARCHAR(1024)) TAGS (device_id BIGINT, identifier NCHAR(100), product_id BIGINT, belong_id BIGINT, belong_type TINYINT, region_id BIGINT)
当前数据量：24951662
4、vgroups情况
5、查询语句： select device_id,identifier,report_time,dval,sval from td_iot_data where device_id = '1772468719746809936' and belong_id = '1772092418104045612' and report_time >= '2024-04-24 22:30:00.000' and report_time <= '2024-04-25 00:00:00.999' partition by tbname order by report_time desc limit 0,10;
问题： 查询响应时间波动情况如下，在高并发压测下去执行响应时间更长，导致并发性能较低以及在高并发下查询响应变得更长导致响应超时