1. 生成测试数据
在TPC-H的官网http://www.tpc.org/tpch/上下载dbgen工具，生成数据http://www.tpc.org/tpch/spec/tpch_2_17_0.zip
[root@ip---- tpch]# wget http://www.tpc.org/tpch/spec/tpch_2_17_0.zip
解压，到dbgen目录下，复制makefile.suite到makefile并作如下修改
[root@ip---- tpch]# yum install unzip
[root@ip---- tpch]# unzip tpch_2_17_0.zip
[root@ip---- tpch]# ls
__MACOSX tpch_2_17_0 tpch_2_17_0.zip
[root@ip---- tpch]# cd tpch_2_17_0
[root@ip---- tpch_2_17_0]# ls
dbgen dev-tools ref_data
[root@ip---- tpch_2_17_0]# cd dbgen/
[root@ip---- dbgen]# ls
BUGS README bcd2.h check_answers dbgen.dsp dss.ddl dsstypes.h permute.c qgen.c reference rnd.h shared.h text.c tpch.sln variants
HISTORY answers bm_utils.c column_split.sh dists.dss dss.h load_stub.c permute.h qgen.vcproj release.h rng64.c speed_seed.c tpcd.h tpch.vcproj varsub.c
PORTING.NOTES bcd2.c build.c config.h driver.c dss.ri makefile.suite print.c queries rnd.c rng64.h tests tpch.dsw update_release.sh
[root@ip---- dbgen]# cp makefile.suite makefile
[root@ip-172-31-10-151 dbgen]# vi makefile
################
## CHANGE NAME OF ANSI COMPILER HERE
################
CC = gcc
# Current values for DATABASE are: INFORMIX, DB2, TDAT (Teradata)
# SQLSERVER, SYBASE, ORACLE, VECTORWISE
# Current values for MACHINE are: ATT, DOS, HP, IBM, ICL, MVS,
# SGI, SUN, U2200, VMS, LINUX, WIN32
# Current values for WORKLOAD are: TPCH
DATABASE= ORACLE
MACHINE = LINUX
WORKLOAD = TPCH
编译代码:
make
编译完成之后会在当前目录下生成dbgen
运行./dbgen -help查看如何使用
jfp4-:/mnt/disk1/tpch_2_17_0/dbgen # ./dbgen -help
TPC-H Population Generator (Version 2.17. build )
Copyright Transaction Processing Performance Council -
USAGE:
dbgen [-{vf}][-T {pcsoPSOL}]
[-s <scale>][-C <procs>][-S <step>]
dbgen [-v] [-O m] [-s <scale>] [-U <updates>] Basic Options
===========================
-C <n> -- separate data set into <n> chunks (requires -S, default: )
-f -- force. Overwrite existing files
-h -- display this message
-q -- enable QUIET mode
-s <n> -- set Scale Factor (SF) to <n> (default: )
-S <n> -- build the <n>th step of the data/update set (used with -C or -U)
-U <n> -- generate <n> update sets
-v -- enable VERBOSE mode Advanced Options
===========================
-b <s> -- load distributions for <s> (default: dists.dss)
-d <n> -- split deletes between <n> files (requires -U)
-i <n> -- split inserts between <n> files (requires -U)
-T c -- generate cutomers ONLY
-T l -- generate nation/region ONLY
-T L -- generate lineitem ONLY
-T n -- generate nation ONLY
-T o -- generate orders/lineitem ONLY
-T O -- generate orders ONLY
-T p -- generate parts/partsupp ONLY
-T P -- generate parts ONLY
-T r -- generate region ONLY
-T s -- generate suppliers ONLY
-T S -- generate partsupp ONLY To generate the SF= (1GB), validation database population, use:
dbgen -vf -s To generate updates for a SF= (1GB), use:
dbgen -v -U -s
运行./dbgen -s 1024生成1TB数据
jfp4-:/mnt/disk1/tpch_2_17_0/dbgen # ll *.tbl
-rw-r--r-- root root Jul : customer.tbl
-rw-r--r-- root root Jul : lineitem.tbl
-rw-r--r-- root root Jul : nation.tbl
-rw-r--r-- root root Jul : orders.tbl
-rw-r--r-- root root Jul : part.tbl
-rw-r--r-- root root Jul : partsupp.tbl
-rw-r--r-- root root Jul : region.tbl
-rw-r--r-- root root Jul : supplier.tbl
将数据移动到一个单独的目录
mkdir ../data1024g
mv *.tbl ../data1024g
2.下载impala版本的TPCH-H脚本
建立原始表linetext，为text文件:大小776GB
jfp4-:/mnt/disk1/tpch_2_17_0/dbgen # hdfs dfs -du /shaochen/tpch
/shaochen/tpch/customer
/shaochen/tpch/lineitem
/shaochen/tpch/nation
/shaochen/tpch/orders
/shaochen/tpch/part
/shaochen/tpch/partsupp
/shaochen/tpch/region
/shaochen/tpch/supplier
Create external table lineitem (L_ORDERKEY INT, L_PARTKEY INT, L_SUPPKEY INT, L_LINENUMBER INT, L_QUANTITY DOUBLE, L_EXTENDEDPRICE DOUBLE, L_DISCOUNT DOUBLE, L_TAX DOUBLE, L_RETURNFLAG STRING, L_LINESTATUS STRING, L_SHIPDATE STRING, L_COMMITDATE STRING, L_RECEIPTDATE STRING, L_SHIPINSTRUCT STRING, L_SHIPMODE STRING, L_COMMENT STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' LOCATION '/shaochen/tpch/lineitem';
从原始text表中统计记录条数:
[jfp4-:] > select count(*) from lineitem;
Query: select count(*) from lineitem
+------------+
| count(*) |
+------------+
| |
+------------+
Returned row(s) in .47s
在脚本运行过程中，观察到Cluster Disk IO速度平均接近1GB，原始数据为776GB，由于是IO密集型操作，估算应该在776GB/1GB/s=800s完成。符合预期
将lineitem表保存为parquet格式：
[jfp4-:] > insert overwrite lineitem_parquet select * from lineitem;
Query: insert overwrite lineitem_parquet select * from lineitem
Inserted rows in .52s
在脚本运行过程中，该SQL为由于涉及到parquet文件的转换和Snappy压缩，属于混合型（IO密集+CPU密集），观察到Cluster Disk IO中读速率均值约为210M，估算在776/0.2=3800秒左右完成。符合预期。
根据写速率为140兆，parquet文件大小约为3800*0.14=532GB,再除以复制因子3，为180GB。
jfp4-:/mnt/disk1/tpch_2_17_0/dbgen # hdfs dfs -du -h /user/hive/warehouse/tpch.db
200.9 G /user/hive/warehouse/tpch.db/lineitem_parquet
/user/hive/warehouse/tpch.db/q1_pricing_summary_report
真实的parquet文件大小为200G,符合预期。
再次统计记录条数：
[jfp4-:] > select count(*) from lineitem_parquet;
Query: select count(*) from lineitem_parquet
+------------+
| count(*) |
+------------+
| |
+------------+
Returned row(s) in .04s
在text文件格式上运行Q1：
[jfp4-:] > -- the query
> INSERT OVERWRITE TABLE q1_pricing_summary_report
> SELECT
> L_RETURNFLAG, L_LINESTATUS, SUM(L_QUANTITY), SUM(L_EXTENDEDPRICE), SUM(L_EXTENDEDPRICE*(-L_DISCOUNT)), SUM(L_EXTENDEDPRICE*(-L_DISCOUNT)*(+L_TAX)), AVG(L_QUANTITY), AVG(L_EXTENDEDPRICE), AVG(L_DISCOUNT), cast(COUNT() as int)
> FROM
> lineitem
> WHERE
> L_SHIPDATE<='1998-09-02'
> GROUP BY L_RETURNFLAG, L_LINESTATUS
> ORDER BY L_RETURNFLAG, L_LINESTATUS
> LIMIT ;
Query: INSERT OVERWRITE TABLE q1_pricing_summary_report SELECT L_RETURNFLAG, L_LINESTATUS, SUM(L_QUANTITY), SUM(L_EXTENDEDPRICE), SUM(L_EXTENDEDPRICE*(-L_DISCOUNT)), SUM(L_EXTENDEDPRICE*(-L_DISCOUNT)*(+L_TAX)), AVG(L_QUANTITY), AVG(L_EXTENDEDPRICE), AVG(L_DISCOUNT), cast(COUNT() as int) FROM lineitem WHERE L_SHIPDATE<='1998-09-02' GROUP BY L_RETURNFLAG, L_LINESTATUS ORDER BY L_RETURNFLAG, L_LINESTATUS LIMIT
^C[jfp4-:] > INSERT OVERWRITE TABLE q1_pricing_summary_report
> SELECT
> L_RETURNFLAG, L_LINESTATUS, SUM(L_QUANTITY), SUM(L_EXTENDEDPRICE), SUM(L_EXTENDEDPRICE*(-L_DISCOUNT)), SUM(L_EXTENDEDPRICE*(-L_DISCOUNT)*(+L_TAX)), AVG(L_QUANTITY), AVG(L_EXTENDEDPRICE), AVG(L_DISCOUNT), cast(COUNT() as int)
> FROM
> lineitem
> WHERE
> L_SHIPDATE<='1998-09-02'
> GROUP BY L_RETURNFLAG, L_LINESTATUS
> ORDER BY L_RETURNFLAG, L_LINESTATUS
> LIMIT ;
Query: insert OVERWRITE TABLE q1_pricing_summary_report SELECT L_RETURNFLAG, L_LINESTATUS, SUM(L_QUANTITY), SUM(L_EXTENDEDPRICE), SUM(L_EXTENDEDPRICE*(-L_DISCOUNT)), SUM(L_EXTENDEDPRICE*(-L_DISCOUNT)*(+L_TAX)), AVG(L_QUANTITY), AVG(L_EXTENDEDPRICE), AVG(L_DISCOUNT), cast(COUNT() as int) FROM lineitem WHERE L_SHIPDATE<='1998-09-02' GROUP BY L_RETURNFLAG, L_LINESTATUS ORDER BY L_RETURNFLAG, L_LINESTATUS LIMIT
Inserted rows in .57s
查询查询计划:
[jfp4-:] > explain INSERT OVERWRITE TABLE q1_pricing_summary_report
> SELECT
> L_RETURNFLAG, L_LINESTATUS, SUM(L_QUANTITY), SUM(L_EXTENDEDPRICE), SUM(L_EXTENDEDPRICE*(-L_DISCOUNT)), SUM(L_EXTENDEDPRICE*(-L_DISCOUNT)*(+L_TAX)), AVG(L_QUANTITY), AVG(L_EXTENDEDPRICE), AVG(L_DISCOUNT), cast(COUNT() as int)
> FROM
> lineitem
> WHERE
> L_SHIPDATE<='1998-09-02'
> GROUP BY L_RETURNFLAG, L_LINESTATUS
> ORDER BY L_RETURNFLAG, L_LINESTATUS
> LIMIT ;
Query: explain INSERT OVERWRITE TABLE q1_pricing_summary_report SELECT L_RETURNFLAG, L_LINESTATUS, SUM(L_QUANTITY), SUM(L_EXTENDEDPRICE), SUM(L_EXTENDEDPRICE*(-L_DISCOUNT)), SUM(L_EXTENDEDPRICE*(-L_DISCOUNT)*(+L_TAX)), AVG(L_QUANTITY), AVG(L_EXTENDEDPRICE), AVG(L_DISCOUNT), cast(COUNT() as int) FROM lineitem WHERE L_SHIPDATE<='1998-09-02' GROUP BY L_RETURNFLAG, L_LINESTATUS ORDER BY L_RETURNFLAG, L_LINESTATUS LIMIT
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Explain String |
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Estimated Per-Host Requirements: Memory=.13GB VCores= |
| WARNING: The following tables are missing relevant table and/or column statistics. |
| tpch.lineitem |
| |
| WRITE TO HDFS [tpch.q1_pricing_summary_report, OVERWRITE=true] |
| | partitions= |
| | |
| :TOP-N [LIMIT=] |
| | order by: L_RETURNFLAG ASC, L_LINESTATUS ASC |
| | |
| :EXCHANGE [PARTITION=UNPARTITIONED] |
| | |
| :TOP-N [LIMIT=] |
| | order by: L_RETURNFLAG ASC, L_LINESTATUS ASC |
| | |
| :AGGREGATE [MERGE FINALIZE] |
| | output: sum(sum(L_QUANTITY)), sum(sum(L_EXTENDEDPRICE)), sum(sum(L_EXTENDEDPRICE * (1.0 - L_DISCOUNT))), sum(sum(L_EXTENDEDPRICE * (1.0 - L_DISCOUNT) * (1.0 + L_TAX))), sum(count(L_QUANTITY)), sum(count(L_EXTENDEDPRICE)), sum(sum(L_DISCOUNT)), sum(count(L_DISCOUNT)), sum(count()) |
| | group by: L_RETURNFLAG, L_LINESTATUS |
| | |
| :EXCHANGE [PARTITION=HASH(L_RETURNFLAG,L_LINESTATUS)] |
| | |
| :AGGREGATE |
| | output: sum(L_QUANTITY), sum(L_EXTENDEDPRICE), sum(L_EXTENDEDPRICE * (1.0 - L_DISCOUNT)), sum(L_EXTENDEDPRICE * (1.0 - L_DISCOUNT) * (1.0 + L_TAX)), count(L_QUANTITY), count(L_EXTENDEDPRICE), sum(L_DISCOUNT), count(L_DISCOUNT), count() |
| | group by: L_RETURNFLAG, L_LINESTATUS |
| | |
| :SCAN HDFS [tpch.lineitem] |
| partitions=/ size=.30GB |
| predicates: L_SHIPDATE <= '1998-09-02' |
+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
Returned row(s) in .15s
计算一下表的统计信息：
[jfp4-:] > compute stats lineitem;
Query: compute stats lineitem
+------------------------------------------+
| summary |
+------------------------------------------+
| Updated partition(s) and column(s). |
+------------------------------------------+
Returned row(s) in .34s
根据执行结果，发现compute stats 原来是如此花费时间！观察执行过程中，前15分钟的DISK IO是非常高，达到900M/s左右，基本上是集群中所有的磁盘都在满负荷的读文件的。之后的IO也保持在130M/s左右。看来compute status是一个昂贵的操作
在parquet表上统计一下：
[jfp4-1:21000] > compute stats lineitem_parquet;
Query: compute stats lineitem_parquet
Query aborted.
[jfp4-1:21000] > SET
> NUM_SCANNER_THREADS=2
> ;
NUM_SCANNER_THREADS set to 2
[jfp4-1:21000] > compute stats lineitem_parquet;
Query: compute stats lineitem_parquet
+------------------------------------------+
| summary |
+------------------------------------------+
| Updated 1 partition(s) and 16 column(s). |
+------------------------------------------+
Returned 1 row(s) in 5176.29s
[jfp4-1:21000] >
注意需要设置NUM_SCANNER_THREAD,才能成功
查看snappy压缩对parquet表的压缩和查询效率的影响：
[jfp4-:] > set PARQUET_COMPRESSION_CODEC=snappy;
PARQUET_COMPRESSION_CODEC set to snappy
[jfp4-:] > create table lineitem_parquet_snappy (L_ORDERKEY INT, L_PARTKEY INT, L_SUPPKEY INT, L_LINENUMBER INT, L_QUANTITY DOUBLE, L_EXT DOUBLE, L_TAX DOUBLE, L_RETURNFLAG STRING, L_LINESTATUS STRING, L_SHIPDATE STRING, L_COMMITDATE STRING, L_RECEIPTDATE STRING, L_SHIPINSTRUCT SOMMENT STRING) STORED AS PARQUET;
Query: create table lineitem_parquet_snappy (L_ORDERKEY INT, L_PARTKEY INT, L_SUPPKEY INT, L_LINENUMBER INT, L_QUANTITY DOUBLE, L_EXTENDEDPRICE_TAX DOUBLE, L_RETURNFLAG STRING, L_LINESTATUS STRING, L_SHIPDATE STRING, L_COMMITDATE STRING, L_RECEIPTDATE STRING, L_SHIPINSTRUCT STRING, L_SING) STORED AS PARQUET Returned row(s) in .30s
[jfp4-1:21000] > insert overwrite lineitem_parquet_snappy select * from lineitem;
Query: insert overwrite lineitem_parquet_snappy select * from lineitem
Inserted 6144008876 rows in 3836.99s
查看snappy表的大小:
jfp4-:~ # hdfs dfs -du -h /user/hive/warehouse/tpch.db
200.9 G /user/hive/warehouse/tpch.db/lineitem_parquet
200.9 G /user/hive/warehouse/tpch.db/lineitem_parquet_snappy
/user/hive/warehouse/tpch.db/q1_pricing_summary_report
发现lineitem_parquet_snappy和lineitem_parquet大小是一样的，可见默认情况下，impala的parquet表默认是用snappy压缩的
[jfp4-:] > insert overwrite lineitem_parquet_raw select * from lineitem;
Query: insert overwrite lineitem_parquet_raw select * from lineitem
Inserted rows in .22s
snappy + parquet在写数据上比不压缩的parquet还是要节省了一些时间的！
看看raw parquet的大小:
jfp4-:~ # hdfs dfs -du -h /user/hive/warehouse/tpch.db
200.9 G /user/hive/warehouse/tpch.db/lineitem_parquet
319.2 G /user/hive/warehouse/tpch.db/lineitem_parquet_raw
200.9 G /user/hive/warehouse/tpch.db/lineitem_parquet_snappy
/user/hive/warehouse/tpch.db/q1_pricing_summary_report
看看gzip+snappy的效果：
[jfp4-:] > set PARQUET_COMPRESSION_CODEC=gzip;
PARQUET_COMPRESSION_CODEC set to gzip
[jfp4-:] > create table lineitem_parquet_gzip (L_ORDERKEY INT, L_PARTKEY INT, L_SUPPKEY INT, L_LINENUMBER INT, L_QUANTITY DOUBLE, L_EXTENDEDPRICE DOUBLE, L_DISCOUNT DOUBLE, L_TAX DOUBLE, L_RETURNFLAG STRING, L_LINESTATUS STRING, L_SHIPDATE STRING, L_COMMITDATE STRING, L_RECEIPTDATE STRING, L_SHIPINSTRUCT STRING, L_SHIPMODE STRING, L_COMMENT STRING) STORED AS PARQUET;
Query: create table lineitem_parquet_gzip (L_ORDERKEY INT, L_PARTKEY INT, L_SUPPKEY INT, L_LINENUMBER INT, L_QUANTITY DOUBLE, L_EXTENDEDPRICE DOUBLE, L_DISCOUNT DOUBLE, L_TAX DOUBLE, L_RETURNFLAG STRING, L_LINESTATUS STRING, L_SHIPDATE STRING, L_COMMITDATE STRING, L_RECEIPTDATE STRING, L_SHIPINSTRUCT STRING, L_SHIPMODE STRING, L_COMMENT STRING) STORED AS PARQUET Returned row(s) in .26s
[jfp4-:] > insert overwrite lineitem_parquet_gzip select * from lineitem;
Query: insert overwrite lineitem_parquet_gzip select * from lineitem
Inserted rows in .71s
jfp4-:~ # hdfs dfs -du -h /user/hive/warehouse/tpch.db
200.9 G /user/hive/warehouse/tpch.db/lineitem_parquet
155.1 G /user/hive/warehouse/tpch.db/lineitem_parquet_gzip
319.2 G /user/hive/warehouse/tpch.db/lineitem_parquet_raw
200.9 G /user/hive/warehouse/tpch.db/lineitem_parquet_snappy
/user/hive/warehouse/tpch.db/q1_pricing_summary_report
[jfp4-:] > select count(*) from lineitem_parquet_gzip;
Query: select count(*) from lineitem_parquet_gzip
+------------+
| count(*) |
+------------+
| |
+------------+
Returned row(s) in .54s