[Hive]Hive调优：让任务并行执行，hive调优

[Hive]Hive调优：让任务并行执行，hive调优

业务背景

extract_trfc_page_kpi的hive sql如下：

set mapred.job.queue.name=pms;
set hive.exec.reducers.max=8;
set mapred.reduce.tasks=8;
set mapred.job.name=extract_trfc_page_kpi;

insert overwrite table pms.extract_trfc_page_kpi partition(ds='$yesterday')
select distinct 
    page_type_id,
    pv,
    uv,
    '$yesterday' update_time 
from
(
    --针对PC、H5
    select 
        page_type_id,
        sum(pv) as pv,
        sum(uv) as uv 
    from dw.rpt_trfc_page_kpi 
    where ds = '$yesterday' and stat_type = 1 
    group by page_type_id 

union all

    --PC搜索页特殊处理
    select 
        5 as page_type_id,
        sum(pv) as pv,
        sum(uv) as uv 
    from dw.rpt_trfc_page_kpi 
    where ds = '$yesterday' and stat_type = 1 and page_type_id in (51, 52)

union all

    --针对APP
    select 
        a.page_type_id,
        sum(pv) as pv,
        sum(uv) as uv 
    from dw.rpt_trfc_page_kpi a 
    left outer join (
        select distinct 
            page_type_id, 
            old_page_type_id 
        from tandem.mobile_backend_page_url_rule 
        where is_delete = 0
    ) b on (a.page_type_id = b.old_page_type_id)
    where a.ds = '$yesterday' and stat_type = 1 
    group by a.page_type_id 
) t;

上面的sql中存在两个union all操作，顺序执行下来的话，需要耗时20分钟。

优化策略

分析以上的sql，其中union all前后的三个查询操作并无直接关联，因此没有必要顺序执行，因此优化的思路是让这三个查询操作并行执行，hive提供了如下参数实现job的并行操作：

// 开启任务并行执行
set hive.exec.parallel=true;
// 同一个sql允许并行任务的最大线程数
set hive.exec.parallel.thread.number=8;

方案一

在执行sql时加上上面的两个hive参数，如：

set mapred.job.queue.name=pms;
set hive.exec.reducers.max=8;
set mapred.reduce.tasks=8;
set hive.exec.parallel=true;
set hive.exec.parallel.thread.number=8;
set mapred.job.name=extract_trfc_page_kpi;

insert overwrite table pms.extract_trfc_page_kpi partition(ds='$yesterday')
select distinct 
    page_type_id,
    pv,
    uv,
    '$yesterday' update_time 
from
(
    --针对PC、H5
    select 
        page_type_id,
        sum(pv) as pv,
        sum(uv) as uv 
    from dw.rpt_trfc_page_kpi 
    where ds = '$yesterday' and stat_type = 1 
    group by page_type_id 

union all

    --PC搜索页特殊处理
    select 
        5 as page_type_id,
        sum(pv) as pv,
        sum(uv) as uv 
    from dw.rpt_trfc_page_kpi 
    where ds = '$yesterday' and stat_type = 1 and page_type_id in (51, 52)

union all

    --针对APP
    select 
        a.page_type_id,
        sum(pv) as pv,
        sum(uv) as uv 
    from dw.rpt_trfc_page_kpi a 
    left