显示基于Web的监控项目的实时数据和历史数据。有近16个采样频率为50Hz的传感器。传感器的所有原始数据都必须存储在数据库中,每秒钟可达到近900个数据。数据必须保存至少三年。数据库是oracle 11g。实时数据表到历史数据表的数据丢失
我的工作是为传感器硬件公司的工程师设计数据库结构,他将编写数据采集程序并将数据存储到数据库中。
设计了实时数据表和历史数据表。从实时数据表中读取实时数据,并从历史数据表中读取历史数据。
实数据表如下,仅存储一分钟数据。
Create Table real_data(
record_time timestamp(3),
ac_1 Float,
ac_2 Float,
ac_3 Float,
ac_4 Float,
ac_5 Float,
ac_6 Float,
ac_7 Float,
ac_8 Float,
ac_9 Float,
ac_10 Float,
ac_11 Float,
ac_12 Float,
ac_13 Float,
ac_14 Float,
ac_15 Float,
ac_16 Float
)
Tablespace data_test;
历史数据表的结构是与真实数据,它由主键和分区
Create Table history_data(
record_time timestamp(3),
ac_1 Float,
ac_2 Float,
ac_3 Float,
ac_4 Float,
ac_5 Float,
ac_6 Float,
ac_7 Float,
ac_8 Float,
ac_9 Float,
ac_10 Float,
ac_11 Float,
ac_12 Float,
ac_13 Float,
ac_14 Float,
ac_15 Float,
ac_16 Float
)
Tablespace data_test
PARTITION BY RANGE(record_time)
INTERVAL(numtodsinterval(1,'day'))
(
PARTITION P1 VALUES LESS THAN (TO_DATE('2016-08-01', 'YYYY-MM-DD'))
);
alter table history_data add constraint RECORD_DATE primary key (RECORD_TIME);
间隔分区被选择用于两个原因相同:
sql查询是基于web客户端的时间记录,如
select ac_1来自ac_test where record_time> = to_timestamp('2016-08-01 00:00:00','yyyy-mm-dd hh24:mi:ss') and record_time < = to_timestamp('2016-08-01 00 :30:00','yyyy-mm-dd hh24:mi:ss');
间隔分区的范围是天。在一天数据测试期间,每天近430万数据的成本为近40秒。
执行作业以每一分钟将实际数据传送到历史数据表。传输过程由oracle过程完成,传输时间由另一个表记录:real_data_top_backup_date。
create or replace procedure copy_to_history_test is
d_top_backup_date timestamp(3);
begin
select top_backup_date into d_top_backup_date from real_data_top_backup_date;
Insert Into history_data Select * From real_data where record_time <d_top_backup_date;
delete from real_data where record_time <d_top_backup_date;
Update real_data_top_backup_date Set top_backup_date=(d_top_backup_date+1/24/60);
commit;
end copy_to_history_test;
并编写仿真程序来模拟传感器数据采集和插入。
Declare
time_index Number;
start_time Timestamp(3);
tmp_time Timestamp(3);
tmp_value1 Float;
tmp_value2 Float;
tmp_value3 Float;
tmp_value4 Float;
tmp_value5 Float;
tmp_value6 Float;
tmp_value7 Float;
tmp_value8 Float;
tmp_value9 Float;
tmp_value10 Float;
tmp_value11 Float;
tmp_value12 Float;
tmp_value13 Float;
tmp_value14 Float;
tmp_value15 Float;
tmp_value16 Float;
Begin
--initiaze the variable
time_index:=0;
SELECT to_timestamp('2016-08-01 00:00:00:000', 'yyyy-mm-dd h24:mi:ss:ff') Into start_time FROM DUAL;
While time_index<(50*60*60*24*7)
Loop
-- add 20 millionseconds
SELECT start_time+numtodsinterval((0.02*time_index),'SECOND') Into tmp_time FROM DUAL;
-- dbms_output.put_line(tmp_time);
-- create random number
select dbms_random.value Into tmp_value1 from dual ;
select dbms_random.value Into tmp_value2 from dual ;
select dbms_random.value Into tmp_value3 from dual ;
select dbms_random.value Into tmp_value4 from dual ;
select dbms_random.value Into tmp_value5 from dual ;
select dbms_random.value Into tmp_value6 from dual ;
select dbms_random.value Into tmp_value7 from dual ;
select dbms_random.value Into tmp_value8 from dual ;
select dbms_random.value Into tmp_value9 from dual ;
select dbms_random.value Into tmp_value10 from dual ;
select dbms_random.value Into tmp_value11 from dual ;
select dbms_random.value Into tmp_value12 from dual ;
select dbms_random.value Into tmp_value13 from dual ;
select dbms_random.value Into tmp_value14 from dual ;
select dbms_random.value Into tmp_value15 from dual ;
select dbms_random.value Into tmp_value16 from dual ;
--dbms_output.put_line(tmp_value);
-- Insert Into ac_data (sensor_id,data,record_time) Values(sensor_index,tmp_value,tmp_time);
Insert Into real_data Values(tmp_time,tmp_value1,tmp_value2,tmp_value3,tmp_value4,tmp_value5,tmp_value6,tmp_value7,tmp_value8,tmp_value9,tmp_value10,tmp_value11,tmp_value12,tmp_value13,tmp_value14,tmp_value15,tmp_value16);
if mod(time_index,50)=0 then
commit;
dbms_lock.sleep(1);
End If;
time_index:=time_index+1;
End Loop;
-- dbms_output.put_line(c);
Exception
WHEN OTHERS THEN
log_write('insert data failure!');
End;
问题是,在传输数据过程中,接近0.1%的传感器数据量将会丢失。我认为传输数据(插入数据和删除数据)的并行操作会导致数据丢失。如何处理这个问题?
在这种情况下,数据库结构是否可行?数据库有更好的设计吗?
你怎么知道数据已经丢失? –
@EvgeniyK。我发现有一天有4316850个传感器数据,它应该由432000个数据组成。 – skyspeed